release 2016.02.13

This reverts commit 3d98f97c64.

AUTHORS

@@ -144,3 +144,16 @@ Lee Jenkins
 Anssi Hannula
 Lukáš Lalinský
 Qijiang Fan
+Rémy Léone
+Marco Ferragina
+reiv
+Muratcan Simsek
+Evan Lu
+flatgreen
+Brian Foley
+Vignesh Venkat
+Tom Gijselinck
+Founder Fang
+Andrew Alexeyew
+Saso Bezlaj
+Erwin de Haan

CONTRIBUTING.md

@@ -1,6 +1,20 @@
-**Please include the full output of youtube-dl when run with `-v`**.
+**Please include the full output of youtube-dl when run with `-v`**, i.e. add `-v` flag to your command line, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this:
+```
+$ youtube-dl -v http://www.youtube.com/watch?v=BaW_jenozKcj
+[debug] System config: []
+[debug] User config: []
+[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
+[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
+[debug] youtube-dl version 2015.12.06
+[debug] Git HEAD: 135392e
+[debug] Python version 2.6.6 - Windows-2003Server-5.2.3790-SP2
+[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
+[debug] Proxy map: {}
+...
+```
+**Do not post screenshots of verbose log only plain text is acceptable.**
 
-The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
+The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
 
 Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
 
@@ -14,13 +28,13 @@ So please elaborate on what feature you are requesting, or what bug you want to
 - How it could be fixed
 - How your proposed solution would look like
 
-If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
+If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a committer myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
 
 For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the `-v` flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
 
 If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
 
-**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
+**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `http://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `http://www.youtube.com/`) is *not* an example URL.
 
 ###  Are you using the latest version?
 
@@ -28,7 +42,7 @@ Before reporting any issue, type `youtube-dl -U`. This should report that you're
 
 ###  Is the issue already documented?
 
-Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
+Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/rg3/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
 
 ###  Why are existing options not enough?
 
@@ -114,17 +128,18 @@ If you want to add support for a new site, you can follow this quick list (assum
             webpage = self._download_webpage(url, video_id)
 
             # TODO more code goes here, for example ...
-            title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
+            title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
 
             return {
                 'id': video_id,
                 'title': title,
                 'description': self._og_search_description(webpage),
+                'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
                 # TODO more properties (see youtube_dl/extractor/common.py)
             }
     ```
 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
-6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
+6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
 8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
 9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:

Makefile

@@ -61,34 +61,34 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
 	chmod a+x youtube-dl
 
 README.md: youtube_dl/*.py youtube_dl/*/*.py
-	COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py
+	COLUMNS=80 $(PYTHON) youtube_dl/__main__.py --help | $(PYTHON) devscripts/make_readme.py
 
 CONTRIBUTING.md: README.md
-	python devscripts/make_contributing.py README.md CONTRIBUTING.md
+	$(PYTHON) devscripts/make_contributing.py README.md CONTRIBUTING.md
 
 supportedsites:
-	python devscripts/make_supportedsites.py docs/supportedsites.md
+	$(PYTHON) devscripts/make_supportedsites.py docs/supportedsites.md
 
 README.txt: README.md
 	pandoc -f markdown -t plain README.md -o README.txt
 
 youtube-dl.1: README.md
-	python devscripts/prepare_manpage.py >youtube-dl.1.temp.md
+	$(PYTHON) devscripts/prepare_manpage.py >youtube-dl.1.temp.md
 	pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1
 	rm -f youtube-dl.1.temp.md
 
 youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-completion.in
-	python devscripts/bash-completion.py
+	$(PYTHON) devscripts/bash-completion.py
 
 bash-completion: youtube-dl.bash-completion
 
 youtube-dl.zsh: youtube_dl/*.py youtube_dl/*/*.py devscripts/zsh-completion.in
-	python devscripts/zsh-completion.py
+	$(PYTHON) devscripts/zsh-completion.py
 
 zsh-completion: youtube-dl.zsh
 
 youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in
-	python devscripts/fish-completion.py
+	$(PYTHON) devscripts/fish-completion.py
 
 fish-completion: youtube-dl.fish
 

README.md

@@ -35,7 +35,7 @@ You can also use pip:
 
     sudo pip install youtube-dl
 
-Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html .
+Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html).
 
 # DESCRIPTION
 **youtube-dl** is a small command-line program to download videos from
@@ -173,6 +173,10 @@ which means you can modify it, redistribute it or use it however you like.
                                      expected filesize (experimental)
     --hls-prefer-native              Use the native HLS downloader instead of
                                      ffmpeg (experimental)
+    --hls-use-mpegts                 Use the mpegts container for HLS videos,
+                                     allowing to play the video while
+                                     downloading (some players may not be able
+                                     to play it)
     --external-downloader COMMAND    Use the specified external downloader.
                                      Currently supports
                                      aria2c,axel,curl,httpie,wget
@@ -319,7 +323,8 @@ which means you can modify it, redistribute it or use it however you like.
     --all-formats                    Download all available video formats
     --prefer-free-formats            Prefer free video formats unless a specific
                                      one is requested
-    -F, --list-formats               List all available formats
+    -F, --list-formats               List all available formats of requested
+                                     videos
     --youtube-skip-dash-manifest     Do not download the DASH manifests and
                                      related data on YouTube videos
     --merge-output-format FORMAT     If a merge is required (e.g.
@@ -329,8 +334,8 @@ which means you can modify it, redistribute it or use it however you like.
 
 ## Subtitle Options:
     --write-sub                      Write subtitle file
-    --write-auto-sub                 Write automatic subtitle file (YouTube
-                                     only)
+    --write-auto-sub                 Write automatically generated subtitle file
+                                     (YouTube only)
     --all-subs                       Download all the available subtitles of the
                                      video
     --list-subs                      List all available subtitles for the video
@@ -338,8 +343,8 @@ which means you can modify it, redistribute it or use it however you like.
                                      preference, for example: "srt" or
                                      "ass/srt/best"
     --sub-lang LANGS                 Languages of the subtitles to download
-                                     (optional) separated by commas, use IETF
-                                     language tags like 'en,pt'
+                                     (optional) separated by commas, use --list-
+                                     subs for available language tags
 
 ## Authentication Options:
     -u, --username USERNAME          Login with this account ID
@@ -399,23 +404,23 @@ which means you can modify it, redistribute it or use it however you like.
                                      downloading, similar to find's -exec
                                      syntax. Example: --exec 'adb push {}
                                      /sdcard/Music/ && rm {}'
-    --convert-subtitles FORMAT       Convert the subtitles to other format
+    --convert-subs FORMAT            Convert the subtitles to other format
                                      (currently supported: srt|ass|vtt)
 
 # CONFIGURATION
 
-You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux, system wide configuration file is located at `/etc/youtube-dl.conf` and user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. For example, with the following configration file youtube-dl will always extract the audio, not copy the mtime and use proxy:
+You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime and use a proxy:
 ```
 --extract-audio
 --no-mtime
 --proxy 127.0.0.1:3128
 ```
 
-You can use `--ignore-config` if you want to disable configuration file for a particular youtube-dl run.
+You can use `--ignore-config` if you want to disable the configuration file for a particular youtube-dl run.
 
-### Authentication with `.netrc` file ###
+### Authentication with `.netrc` file
 
-You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in shell command history. You can achieve this using [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create `.netrc` file in your `$HOME` and restrict permissions to read/write by you only:
+You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create a`.netrc` file in your `$HOME` and restrict permissions to read/write by you only:
 ```
 touch $HOME/.netrc
 chmod a-rwx,u+rw $HOME/.netrc
@@ -429,52 +434,183 @@ For example:
 machine youtube login myaccount@gmail.com password my_youtube_password
 machine twitch login my_twitch_account_name password my_twitch_password
 ```
-To activate authentication with `.netrc` file you should pass `--netrc` to youtube-dl or place it in [configuration file](#configuration).
+To activate authentication with the `.netrc` file you should pass `--netrc` to youtube-dl or place it in the [configuration file](#configuration).
 
-On Windows you may also need to setup `%HOME%` environment variable manually.
+On Windows you may also need to setup the `%HOME%` environment variable manually.
 
 # OUTPUT TEMPLATE
 
-The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parenthesis, followed by a lowercase S. Allowed names are:
+The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a lowercase S. Allowed names are:
 
- - `id`: The sequence will be replaced by the video identifier.
- - `url`: The sequence will be replaced by the video URL.
- - `uploader`: The sequence will be replaced by the nickname of the person who uploaded the video.
- - `upload_date`: The sequence will be replaced by the upload date in YYYYMMDD format.
- - `title`: The sequence will be replaced by the video title.
- - `ext`: The sequence will be replaced by the appropriate extension (like flv or mp4).
- - `epoch`: The sequence will be replaced by the Unix epoch when creating the file.
- - `autonumber`: The sequence will be replaced by a five-digit number that will be increased with each download, starting at zero.
- - `playlist`: The sequence will be replaced by the name or the id of the playlist that contains the video.
- - `playlist_index`: The sequence will be replaced by the index of the video in the playlist padded with leading zeros according to the total length of the playlist.
- - `format_id`: The sequence will be replaced by the format code specified by `--format`.
- - `duration`: The sequence will be replaced by the length of the video in seconds.
+ - `id`: Video identifier
+ - `title`: Video title
+ - `url`: Video URL
+ - `ext`: Video filename extension
+ - `alt_title`: A secondary title of the video
+ - `display_id`: An alternative identifier for the video
+ - `uploader`: Full name of the video uploader
+ - `creator`: The main artist who created the video
+ - `release_date`: The date (YYYYMMDD) when the video was released
+ - `timestamp`: UNIX timestamp of the moment the video became available
+ - `upload_date`: Video upload date (YYYYMMDD)
+ - `uploader_id`: Nickname or id of the video uploader
+ - `location`: Physical location where the video was filmed
+ - `duration`: Length of the video in seconds
+ - `view_count`: How many users have watched the video on the platform
+ - `like_count`: Number of positive ratings of the video
+ - `dislike_count`: Number of negative ratings of the video
+ - `repost_count`: Number of reposts of the video
+ - `average_rating`: Average rating give by users, the scale used depends on the webpage
+ - `comment_count`: Number of comments on the video
+ - `age_limit`: Age restriction for the video (years)
+ - `format`: A human-readable description of the format 
+ - `format_id`: Format code specified by `--format`
+ - `format_note`: Additional info about the format
+ - `width`: Width of the video
+ - `height`: Height of the video
+ - `resolution`: Textual description of width and height
+ - `tbr`: Average bitrate of audio and video in KBit/s
+ - `abr`: Average audio bitrate in KBit/s
+ - `acodec`: Name of the audio codec in use
+ - `asr`: Audio sampling rate in Hertz
+ - `vbr`: Average video bitrate in KBit/s
+ - `fps`: Frame rate
+ - `vcodec`: Name of the video codec in use
+ - `container`: Name of the container format
+ - `filesize`: The number of bytes, if known in advance
+ - `filesize_approx`: An estimate for the number of bytes
+ - `protocol`: The protocol that will be used for the actual download
+ - `extractor`: Name of the extractor
+ - `extractor_key`: Key name of the extractor
+ - `epoch`: Unix epoch when creating the file
+ - `autonumber`: Five-digit number that will be increased with each download, starting at zero
+ - `playlist`: Name or id of the playlist that contains the video
+ - `playlist_index`: Index of the video in the playlist padded with leading zeros according to the total length of the playlist
+
+Available for the video that belongs to some logical chapter or section:
+ - `chapter`: Name or title of the chapter the video belongs to
+ - `chapter_number`: Number of the chapter the video belongs to
+ - `chapter_id`: Id of the chapter the video belongs to
+
+Available for the video that is an episode of some series or programme:
+ - `series`: Title of the series or programme the video episode belongs to
+ - `season`: Title of the season the video episode belongs to
+ - `season_number`: Number of the season the video episode belongs to
+ - `season_id`: Id of the season the video episode belongs to
+ - `episode`: Title of the video episode
+ - `episode_number`: Number of the video episode within a season
+ - `episode_id`: Id of the video episode
+
+Each aforementioned sequence when referenced in output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by particular extractor, such sequences will be replaced with `NA`.
+
+For example for `-o %(title)s-%(id)s.%(ext)s` and mp4 video with title `youtube-dl test video` and id `BaW_jenozKcj` this will result in a `youtube-dl test video-BaW_jenozKcj.mp4` file created in the current directory.
+
+Output template can also contain arbitrary hierarchical path, e.g. `-o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s'` that will result in downloading each video in a directory corresponding to this path template. Any missing directory will be automatically created for you.
+
+To specify percent literal in output template use `%%`. To output to stdout use `-o -`.
 
 The current default template is `%(title)s-%(id)s.%(ext)s`.
 
 In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title:
 
+Examples (note on Windows you may need to use double quotes instead of single):
+
 ```bash
-$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc
+$ youtube-dl --get-filename -o '%(title)s.%(ext)s' BaW_jenozKc
 youtube-dl test video ''_ä↭𝕐.mp4    # All kinds of weird characters
-$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames
+
+$ youtube-dl --get-filename -o '%(title)s.%(ext)s' BaW_jenozKc --restrict-filenames
 youtube-dl_test_video_.mp4          # A simple file name
+
+# Download YouTube playlist videos in separate directory indexed by video order in a playlist
+$ youtube-dl -o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
+
+# Download Udemy course keeping each chapter in separate directory under MyVideos directory in your home
+$ youtube-dl -u user -p password -o '~/MyVideos/%(playlist)s/%(chapter_number)s - %(chapter)s/%(title)s.%(ext)s' https://www.udemy.com/java-tutorial/
+
+# Download entire series season keeping each series and each season in separate directory under C:/MyVideos
+$ youtube-dl -o "C:/MyVideos/%(series)s/%(season_number)s - %(season)s/%(episode_number)s - %(episode)s.%(ext)s" http://videomore.ru/kino_v_detalayah/5_sezon/367617
+
+# Stream the video being downloaded to stdout
+$ youtube-dl -o - BaW_jenozKc
 ```
 
 # FORMAT SELECTION
 
-By default youtube-dl tries to download the best quality, but sometimes you may want to download other format.
-The simplest case is requesting a specific format, for example `-f 22`. You can get the list of available formats using `--list-formats`, you can also use a file extension (currently it supports aac, m4a, mp3, mp4, ogg, wav, webm) or the special names `best`, `bestvideo`, `bestaudio` and `worst`.
+By default youtube-dl tries to download the best available quality, i.e. if you want the best quality you **don't need** to pass any special options, youtube-dl will guess it for you by **default**.
 
-If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes, as in `-f 22/17/18`. You can also filter the video results by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`).  This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so  `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. Use commas to download multiple formats, such as `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. You can merge the video and audio of two formats into a single file using `-f <video-format>+<audio-format>` (requires ffmpeg or avconv), for example `-f bestvideo+bestaudio`. Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`.
+But sometimes you may want to download in a different format, for example when you are on a slow or intermittent connection. The key mechanism for achieving this is so called *format selection* based on which you can explicitly specify desired format, select formats based on some criterion or criteria, setup precedence and much more.
 
-Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
+The general syntax for format selection is `--format FORMAT` or shorter `-f FORMAT` where `FORMAT` is a *selector expression*, i.e. an expression that describes format or formats you would like to download.
+
+The simplest case is requesting a specific format, for example with `-f 22` you can download the format with format code equal to 22. You can get the list of available format codes for particular video using `--list-formats` or `-F`. Note that these format codes are extractor specific. 
+
+You can also use a file extension (currently `3gp`, `aac`, `flv`, `m4a`, `mp3`, `mp4`, `ogg`, `wav`, `webm` are supported) to download best quality format of particular file extension served as a single file, e.g. `-f webm` will download best quality format with `webm` extension served as a single file.
+
+You can also use special names to select particular edge case format:
+ - `best`: Select best quality format represented by single file with video and audio
+ - `worst`: Select worst quality format represented by single file with video and audio
+ - `bestvideo`: Select best quality video only format (e.g. DASH video), may not be available
+ - `worstvideo`: Select worst quality video only format, may not be available
+ - `bestaudio`: Select best quality audio only format, may not be available
+ - `worstaudio`: Select worst quality audio only format, may not be available
+
+For example, to download worst quality video only format you can use `-f worstvideo`.
+
+If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes. Note that slash is left-associative, i.e. formats on the left hand side are preferred, for example `-f 22/17/18` will download format 22 if it's available, otherwise it will download format 17 if it's available, otherwise it will download format 18 if it's available, otherwise it will complain that no suitable formats are available for download.
+
+If you want to download several formats of the same video use comma as a separator, e.g. `-f 22,17,18` will download all these three formats, of course if they are available. Or more sophisticated example combined with precedence feature `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`.
+
+You can also filter the video formats by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`).
+
+The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `>=`, `=` (equals), `!=` (not equals):
+ - `filesize`: The number of bytes, if known in advance
+ - `width`: Width of the video, if known
+ - `height`: Height of the video, if known
+ - `tbr`: Average bitrate of audio and video in KBit/s
+ - `abr`: Average audio bitrate in KBit/s
+ - `vbr`: Average video bitrate in KBit/s
+ - `asr`: Audio sampling rate in Hertz
+ - `fps`: Frame rate
+
+Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begins with), `$=` (ends with), `*=` (contains) and following string meta fields:
+ - `ext`: File extension
+ - `acodec`: Name of the audio codec in use
+ - `vcodec`: Name of the video codec in use
+ - `container`: Name of the container format
+ - `protocol`: The protocol that will be used for the actual download, lower-case. `http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `m3u8`, or `m3u8_native`
+
+Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by video hoster.
+
+Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s.
+
+You can merge the video and audio of two formats into a single file using `-f <video-format>+<audio-format>` (requires ffmpeg or avconv installed), for example `-f bestvideo+bestaudio` will download best video only format, best audio only format and mux them together with ffmpeg/avconv.
+
+Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`.
+
+Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some DASH formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
+
+If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download the best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl.
+
+Examples (note on Windows you may need to use double quotes instead of single):
+```bash
+# Download best mp4 format available or any other best if no mp4 available
+$ youtube-dl -f 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best'
+
+# Download best format available but not better that 480p
+$ youtube-dl -f 'bestvideo[height<=480]+bestaudio/best[height<=480]'
+
+# Download best video only format but no bigger that 50 MB
+$ youtube-dl -f 'best[filesize<50M]'
+
+# Download best format available via direct link over HTTP/HTTPS protocol
+$ youtube-dl -f '(bestvideo+bestaudio/best)[protocol^=http]'
+```
 
-If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl.
 
 # VIDEO SELECTION
 
-Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`, they accept dates in two formats:
+Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`. They accept dates in two formats:
 
  - Absolute dates: Dates in the format `YYYYMMDD`.
  - Relative dates: Dates in the format `(now|today)[+-][0-9](day|week|month|year)(s)?`
@@ -488,7 +624,7 @@ $ youtube-dl --dateafter now-6months
 # Download only the videos uploaded on January 1, 1970
 $ youtube-dl --date 19700101
 
-$ # will only download the videos uploaded in the 200x decade
+$ # Download only the videos uploaded in the 200x decade
 $ youtube-dl --dateafter 20000101 --datebefore 20091231
 ```
 
@@ -500,7 +636,7 @@ If you've followed [our manual installation instructions](http://rg3.github.io/y
 
 If you have used pip, a simple `sudo pip install -U youtube-dl` is sufficient to update.
 
-If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to http://yt-dl.org/ to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distributions serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum.
+If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to http://yt-dl.org/ to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distribution serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum.
 
 As a last resort, you can also uninstall the version installed by your package manager and follow our manual installation instructions. For that, remove the distribution's package, with a line like
 
@@ -534,6 +670,12 @@ Most people asking this question are not aware that youtube-dl now defaults to d
 
 Apparently YouTube requires you to pass a CAPTCHA test if you download too much. We're [considering to provide a way to let you solve the CAPTCHA](https://github.com/rg3/youtube-dl/issues/154), but at the moment, your best course of action is pointing a webbrowser to the youtube URL, solving the CAPTCHA, and restart youtube-dl.
 
+### Do I need any other programs?
+
+youtube-dl works fine on its own on most sites. However, if you want to convert video/audio, you'll need [avconv](https://libav.org/) or [ffmpeg](https://www.ffmpeg.org/). On some sites - most notably YouTube - videos can be retrieved in a higher quality format without sound. youtube-dl will detect whether avconv/ffmpeg is present and automatically pick the best option.
+
+Videos or video formats streamed via RTMP protocol can only be downloaded when [rtmpdump](https://rtmpdump.mplayerhq.hu/) is installed. Downloading MMS and RTSP videos requires either [mplayer](http://mplayerhq.hu/) or [mpv](https://mpv.io/) to be installed.
+
 ### I have downloaded a video but how can I play it?
 
 Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
@@ -552,13 +694,13 @@ If you want to play the video on a machine that is not running youtube-dl, you c
 
 YouTube has switched to a new video info format in July 2011 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
 
-### ERROR: unable to download video ###
+### ERROR: unable to download video
 
 YouTube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
 
-### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command` ###
+### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command`
 
-That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell).
+That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by the shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell).
 
 For example if your URL is https://www.youtube.com/watch?t=4&v=BaW_jenozKc you should end up with following command:
 
@@ -580,7 +722,7 @@ In February 2015, the new YouTube player contained a character sequence in a str
 
 These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address.
 
-### SyntaxError: Non-ASCII character ###
+### SyntaxError: Non-ASCII character
 
 The error
 
@@ -609,7 +751,7 @@ From then on, after restarting your shell, you will be able to access both youtu
 
 Use the `-o` to specify an [output template](#output-template), for example `-o "/home/user/videos/%(title)s-%(id)s.%(ext)s"`. If you want this for all of your downloads, put the option into your [configuration file](#configuration).
 
-### How do I download a video starting with a `-` ?
+### How do I download a video starting with a `-`?
 
 Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the options with `--`:
 
@@ -618,9 +760,9 @@ Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the opt
 
 ### How do I pass cookies to youtube-dl?
 
-Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. Note that cookies file must be in Mozilla/Netscape format and the first line of cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in cookies file and convert newlines if necessary to correspond your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
+Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
 
-Passing cookies to youtube-dl is a good way to workaround login when particular extractor does not implement it explicitly.
+Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. Another use case is working around [CAPTCHA](https://en.wikipedia.org/wiki/CAPTCHA) some websites require you to solve in particular cases in order to get access (e.g. YouTube, CloudFlare).
 
 ### Can you add support for this anime video site, or site which shows current movies for free?
 
@@ -710,17 +852,18 @@ If you want to add support for a new site, you can follow this quick list (assum
             webpage = self._download_webpage(url, video_id)
 
             # TODO more code goes here, for example ...
-            title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
+            title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
 
             return {
                 'id': video_id,
                 'title': title,
                 'description': self._og_search_description(webpage),
+                'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
                 # TODO more properties (see youtube_dl/extractor/common.py)
             }
     ```
 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
-6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
+6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
 8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
 9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
@@ -749,7 +892,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
     ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
 ```
 
-Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L117-L265). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
+Most likely, you'll want to use various options. For a list of what can be done, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L121-L269). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
 
 Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
 
@@ -790,11 +933,25 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
 
 # BUGS
 
-Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the irc channel #youtube-dl on freenode.
+Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>. Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](http://webchat.freenode.net/?randomnick=1&channels=youtube-dl)).
 
-**Please include the full output of youtube-dl when run with `-v`**.
+**Please include the full output of youtube-dl when run with `-v`**, i.e. add `-v` flag to your command line, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this:
+```
+$ youtube-dl -v http://www.youtube.com/watch?v=BaW_jenozKcj
+[debug] System config: []
+[debug] User config: []
+[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
+[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
+[debug] youtube-dl version 2015.12.06
+[debug] Git HEAD: 135392e
+[debug] Python version 2.6.6 - Windows-2003Server-5.2.3790-SP2
+[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
+[debug] Proxy map: {}
+...
+```
+**Do not post screenshots of verbose log only plain text is acceptable.**
 
-The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
+The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
 
 Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
 
@@ -808,13 +965,13 @@ So please elaborate on what feature you are requesting, or what bug you want to
 - How it could be fixed
 - How your proposed solution would look like
 
-If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
+If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a committer myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
 
 For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the `-v` flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
 
 If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
 
-**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
+**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `http://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `http://www.youtube.com/`) is *not* an example URL.
 
 ###  Are you using the latest version?
 
@@ -822,7 +979,7 @@ Before reporting any issue, type `youtube-dl -U`. This should report that you're
 
 ###  Is the issue already documented?
 
-Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
+Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/rg3/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
 
 ###  Why are existing options not enough?
 
@@ -852,4 +1009,4 @@ It may sound strange, but some bug reports we receive are completely unrelated t
 
 youtube-dl is released into the public domain by the copyright holders.
 
-This README file was originally written by Daniel Bolton (<https://github.com/dbbolton>) and is likewise released into the public domain.
+This README file was originally written by [Daniel Bolton](https://github.com/dbbolton) and is likewise released into the public domain.

devscripts/gh-pages/update-copyright.py

@@ -5,7 +5,7 @@ from __future__ import with_statement, unicode_literals
 
 import datetime
 import glob
-import io  # For Python 2 compatibilty
+import io  # For Python 2 compatibility
 import os
 import re
 

docs/supportedsites.md

@@ -1,6 +1,7 @@
 # Supported sites
  - **1tv**: Первый канал
  - **1up.com**
+ - **20min**
  - **220.ro**
  - **22tracks:genre**
  - **22tracks:track**
@@ -15,11 +16,15 @@
  - **abc.net.au**
  - **Abc7News**
  - **AcademicEarth:Course**
+ - **acast**
+ - **acast:channel**
  - **AddAnime**
  - **AdobeTV**
+ - **AdobeTVChannel**
+ - **AdobeTVShow**
  - **AdobeTVVideo**
  - **AdultSwim**
- - **Aftenposten**
+ - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network
  - **Aftonbladet**
  - **AirMozilla**
  - **AlJazeera**
@@ -30,12 +35,15 @@
  - **Aparat**
  - **AppleConnect**
  - **AppleDaily**: 臺灣蘋果日報
- - **AppleTrailers**
+ - **appletrailers**
+ - **appletrailers:section**
  - **archive.org**: archive.org videos
  - **ARD**
+ - **ARD:mediathek**: Saarländischer Rundfunk
  - **ARD:mediathek**
  - **arte.tv**
  - **arte.tv:+7**
+ - **arte.tv:cinema**
  - **arte.tv:concert**
  - **arte.tv:creative**
  - **arte.tv:ddc**
@@ -43,9 +51,11 @@
  - **arte.tv:future**
  - **AtresPlayer**
  - **ATTTechChannel**
+ - **AudiMedia**
  - **audiomack**
  - **audiomack:album**
  - **Azubu**
+ - **AzubuLive**
  - **BaiduVideo**: 百度视频
  - **bambuser**
  - **bambuser:channel**
@@ -53,34 +63,41 @@
  - **Bandcamp:album**
  - **bbc**: BBC
  - **bbc.co.uk**: BBC iPlayer
+ - **bbc.co.uk:article**: BBC articles
  - **BeatportPro**
  - **Beeg**
  - **BehindKink**
  - **Bet**
+ - **Bigflix**
  - **Bild**: Bild.de
  - **BiliBili**
+ - **BleacherReport**
+ - **BleacherReportCMS**
  - **blinkx**
- - **blip.tv:user**
- - **BlipTV**
  - **Bloomberg**
  - **Bpb**: Bundeszentrale für politische Bildung
  - **BR**: Bayerischer Rundfunk Mediathek
  - **Break**
- - **Brightcove**
+ - **brightcove:legacy**
+ - **brightcove:new**
  - **bt:article**: Bergens Tidende Articles
  - **bt:vestlendingen**: Bergens Tidende - Vestlendingen
  - **BuzzFeed**
  - **BYUtv**
  - **Camdemy**
  - **CamdemyFolder**
- - **Canal13cl**
  - **canalc2.tv**
  - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
+ - **Canvas**
+ - **CBC**
+ - **CBCPlayer**
  - **CBS**
  - **CBSNews**: CBS News
+ - **CBSNewsLiveVideo**: CBS News Live Videos
  - **CBSSports**
  - **CeskaTelevize**
  - **channel9**: Channel 9
+ - **Chaturbate**
  - **Chilloutzone**
  - **chirbit**
  - **chirbit:profile**
@@ -89,8 +106,10 @@
  - **Clipfish**
  - **cliphunter**
  - **Clipsyndicate**
+ - **cloudtime**: CloudTime
  - **Cloudy**
  - **Clubic**
+ - **Clyp**
  - **cmt.com**
  - **CNET**
  - **CNN**
@@ -103,6 +122,7 @@
  - **ComedyCentralShows**: The Daily Show / The Colbert Report
  - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
  - **Cracked**
+ - **Crackle**
  - **Criterion**
  - **CrooksAndLiars**
  - **Crunchyroll**
@@ -110,20 +130,31 @@
  - **CSpan**: C-SPAN
  - **CtsNews**: 華視新聞
  - **culturebox.francetvinfo.fr**
+ - **CultureUnplugged**
+ - **CWTV**
  - **dailymotion**
  - **dailymotion:playlist**
  - **dailymotion:user**
  - **DailymotionCloud**
  - **daum.net**
+ - **daum.net:clip**
+ - **daum.net:playlist**
+ - **daum.net:user**
  - **DBTV**
  - **DCN**
+ - **dcn:live**
+ - **dcn:season**
+ - **dcn:video**
  - **DctpTv**
  - **DeezerPlaylist**
  - **defense.gouv.fr**
+ - **democracynow**
  - **DHM**: Filmarchiv - Deutsches Historisches Museum
+ - **Digiteka**
  - **Discovery**
  - **Dotsub**
  - **DouyuTV**: 斗鱼
+ - **DPlay**
  - **dramafever**
  - **dramafever:series**
  - **DRBonanza**
@@ -148,7 +179,7 @@
  - **Eporner**
  - **EroProfile**
  - **Escapist**
- - **ESPN** (Currently broken)
+ - **ESPN**
  - **EsriVideo**
  - **Europa**
  - **EveryonesMixtape**
@@ -156,26 +187,32 @@
  - **ExpoTV**
  - **ExtremeTube**
  - **facebook**
+ - **facebook:post**
  - **faz.net**
  - **fc2**
+ - **Fczenit**
  - **fernsehkritik.tv**
  - **Firstpost**
  - **FiveTV**
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
  - **FootyRoom**
+ - **FOX**
  - **Foxgay**
  - **FoxNews**: Fox News and Fox Business Video
  - **FoxSports**
  - **france2.fr:generation-quoi**
  - **FranceCulture**
+ - **FranceCultureEmission**
  - **FranceInter**
  - **francetv**: France 2, 3, 4, 5 and Ô
  - **francetvinfo.fr**
  - **Freesound**
  - **freespeech.org**
  - **FreeVideo**
+ - **Funimation**
  - **FunnyOrDie**
+ - **GameInformer**
  - **Gamekings**
  - **GameOne**
  - **gameone:playlist**
@@ -191,11 +228,13 @@
  - **Giga**
  - **Glide**: Glide mobile video messages (glide.me)
  - **Globo**
+ - **GloboArticle**
  - **GodTube**
  - **GoldenMoustache**
  - **Golem**
- - **GorillaVid**: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net and filehoot.com
+ - **GoogleDrive**
  - **Goshgay**
+ - **GPUTechConf**
  - **Groupon**
  - **Hark**
  - **HearThisAt**
@@ -204,11 +243,11 @@
  - **Helsinki**: helsinki.fi
  - **HentaiStigma**
  - **HistoricFilms**
- - **History**
  - **hitbox**
  - **hitbox:live**
  - **HornBunny**
  - **HotNewHipHop**
+ - **HotStar**
  - **Howcast**
  - **HowStuffWorks**
  - **HuffPost**: Huffington Post
@@ -231,12 +270,13 @@
  - **Ir90Tv**
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
+ - **ivideon**: Ivideon TV
  - **Izlesene**
  - **JadoreCettePub**
  - **JeuxVideo**
  - **Jove**
  - **jpopsuki.tv**
- - **Jukebox**
+ - **JWPlatform**
  - **Kaltura**
  - **KanalPlay**: Kanal 5/9/11 Play
  - **Kankan**
@@ -246,6 +286,7 @@
  - **KeezMovies**
  - **KhanAcademy**
  - **KickStarter**
+ - **KonserthusetPlay**
  - **kontrtube**: KontrTube.ru - Труба зовёт
  - **KrasView**: Красвью
  - **Ku6**
@@ -258,7 +299,9 @@
  - **la7.tv**
  - **Laola1Tv**
  - **Lecture2Go**
+ - **Lemonde**
  - **Letv**: 乐视网
+ - **LetvCloud**: 乐视云
  - **LetvPlaylist**
  - **LetvTv**
  - **Libsyn**
@@ -271,16 +314,18 @@
  - **livestream**
  - **livestream:original**
  - **LnkGo**
+ - **LoveHomePorn**
  - **lrt.lt**
  - **lynda**: lynda.com videos
  - **lynda:course**: lynda.com online courses
  - **m6**
  - **macgamestore**: MacGameStore trailers
  - **mailru**: Видео@Mail.Ru
+ - **MakerTV**
  - **Malemotion**
- - **MDR**
+ - **MatchTV**
+ - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
- - **MegaVideoz**
  - **metacafe**
  - **Metacritic**
  - **Mgoon**
@@ -301,7 +346,6 @@
  - **MovieClips**
  - **MovieFap**
  - **Moviezine**
- - **movshare**: MovShare
  - **MPORA**
  - **MSNBC**
  - **MTV**
@@ -344,11 +388,13 @@
  - **Newstube**
  - **NextMedia**: 蘋果日報
  - **NextMediaActionNews**: 蘋果日報 - 動新聞
+ - **nextmovie.com**
  - **nfb**: National Film Board of Canada
  - **nfl.com**
  - **nhl.com**
  - **nhl.com:news**: NHL news
  - **nhl.com:videocenter**: NHL videocenter category
+ - **nick.com**
  - **niconico**: ニコニコ動画
  - **NiconicoPlaylist**
  - **njoy**: N-JOY
@@ -361,12 +407,14 @@
  - **nowness**
  - **nowness:playlist**
  - **nowness:series**
- - **NowTV**
+ - **NowTV** (Currently broken)
+ - **NowTVList**
  - **nowvideo**: NowVideo
  - **npo**: npo.nl and ntr.nl
  - **npo.nl:live**
  - **npo.nl:radio**
  - **npo.nl:radio:fragment**
+ - **Npr**
  - **NRK**
  - **NRKPlaylist**
  - **NRKTV**: NRK TV and NRK Radio
@@ -381,22 +429,26 @@
  - **OnionStudios**
  - **Ooyala**
  - **OoyalaExternal**
+ - **OraTV**
  - **orf:fm4**: radio FM4
  - **orf:iptv**: iptv.ORF.at
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
+ - **pandora.tv**: 판도라TV
  - **parliamentlive.tv**: UK parliament videos
  - **Patreon**
- - **PBS**
+ - **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET  (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC)
+ - **pcmag**
  - **Periscope**: Periscope
  - **PhilharmonieDeParis**: Philharmonie de Paris
- - **Phoenix**
+ - **phoenix.de**
  - **Photobucket**
  - **Pinkbike**
  - **Pladform**
  - **PlanetaPlay**
  - **play.fm**
  - **played.to**
+ - **PlaysTV**
  - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
  - **Playvid**
  - **Playwire**
@@ -421,7 +473,6 @@
  - **qqmusic:playlist**: QQ音乐 - 歌单
  - **qqmusic:singer**: QQ音乐 - 歌手
  - **qqmusic:toplist**: QQ音乐 - 排行榜
- - **Quickscope**: Quick Scope
  - **QuickVid**
  - **R7**
  - **radio.de**
@@ -429,16 +480,20 @@
  - **radiofrance**
  - **RadioJavan**
  - **Rai**
+ - **RaiTV**
  - **RBMARadio**
  - **RDS**: RDS.ca
  - **RedTube**
+ - **RegioTV**
  - **Restudy**
  - **ReverbNation**
+ - **Revision3**
  - **RingTV**
  - **RottenTomatoes**
  - **Roxwel**
  - **RTBF**
- - **Rte**
+ - **rte**: Raidió Teilifís Éireann TV
+ - **rte:radio**: Raidió Teilifís Éireann radio
  - **rtl.nl**: rtl.nl and rtlxl.nl
  - **RTL2**
  - **RTP**
@@ -448,6 +503,7 @@
  - **rtve.es:live**: RTVE.es live streams
  - **RTVNH**
  - **RUHD**
+ - **RulePorn**
  - **rutube**: Rutube videos
  - **rutube:channel**: Rutube channels
  - **rutube:embed**: Rutube embedded videos
@@ -461,6 +517,7 @@
  - **Sapo**: SAPO Vídeos
  - **savefrom.net**
  - **SBS**: sbs.com.au
+ - **schooltv**
  - **SciVee**
  - **screen.yahoo:search**: Yahoo screen search
  - **Screencast**
@@ -474,6 +531,8 @@
  - **Shared**: shared.sx and vivo.sx
  - **ShareSix**
  - **Sina**
+ - **skynewsarabia:video**
+ - **skynewsarabia:video**
  - **Slideshare**
  - **Slutload**
  - **smotri**: Smotri.com
@@ -484,10 +543,9 @@
  - **SnagFilmsEmbed**
  - **Snotr**
  - **Sohu**
- - **soompi**
- - **soompi:show**
  - **soundcloud**
  - **soundcloud:playlist**
+ - **soundcloud:search**: Soundcloud search
  - **soundcloud:set**
  - **soundcloud:user**
  - **soundgasm**
@@ -509,11 +567,12 @@
  - **SportBoxEmbed**
  - **SportDeutschland**
  - **Sportschau**
- - **Srf**
- - **SRMediathek**: Saarländischer Rundfunk
+ - **SRGSSR**
+ - **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
  - **SSA**
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
+ - **Stitcher**
  - **streamcloud.eu**
  - **StreamCZ**
  - **StreetVoice**
@@ -534,14 +593,15 @@
  - **TechTalks**
  - **techtv.mit.edu**
  - **ted**
+ - **Tele13**
  - **TeleBruxelles**
  - **Telecinco**: telecinco.es, cuatro.com and mediaset.es
  - **Telegraaf**
  - **TeleMB**
  - **TeleTask**
  - **TenPlay**
- - **TestTube**
  - **TF1**
+ - **TheIntercept**
  - **TheOnion**
  - **ThePlatform**
  - **ThePlatformFeed**
@@ -551,22 +611,28 @@
  - **THVideo**
  - **THVideoPlaylist**
  - **tinypic**: tinypic.com videos
- - **tlc.com**
  - **tlc.de**
  - **TMZ**
  - **TMZArticle**
  - **TNAFlix**
+ - **toggle**
  - **tou.tv**
  - **Toypics**: Toypics user profile
  - **ToypicsUser**: Toypics user profile
  - **TrailerAddict** (Currently broken)
  - **Trilulilu**
+ - **trollvids**
  - **TruTube**
  - **Tube8**
  - **TubiTv**
- - **Tudou**
+ - **tudou**
+ - **tudou:album**
+ - **tudou:playlist**
  - **Tumblr**
- - **TuneIn**
+ - **tunein:clip**
+ - **tunein:program**
+ - **tunein:station**
+ - **tunein:topic**
  - **Turbo**
  - **Tutv**
  - **tv.dfb.de**
@@ -576,6 +642,7 @@
  - **TVC**
  - **TVCArticle**
  - **tvigle**: Интернет-телевидение Tvigle.ru
+ - **tvland.com**
  - **tvp.pl**
  - **tvp.pl:Series**
  - **TVPlay**: TV3Play and related services
@@ -587,12 +654,12 @@
  - **twitch:stream**
  - **twitch:video**
  - **twitch:vod**
- - **TwitterCard**
+ - **twitter**
+ - **twitter:card**
  - **Ubu**
  - **udemy**
  - **udemy:course**
  - **UDNEmbed**: 聯合影音
- - **Ultimedia**
  - **Unistra**
  - **Urort**: NRK P3 Urørt
  - **ustream**
@@ -604,7 +671,7 @@
  - **Vessel**
  - **Vesti**: Вести.Ru
  - **Vevo**
- - **VGTV**: VGTV and BTTV
+ - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
  - **vh1.com**
  - **Vice**
  - **Viddler**
@@ -612,16 +679,21 @@
  - **video.mit.edu**
  - **VideoDetective**
  - **videofy.me**
- - **videolectures.net**
- - **VideoMega**
+ - **VideoMega** (Currently broken)
+ - **videomore**
+ - **videomore:season**
+ - **videomore:video**
  - **VideoPremium**
- - **VideoTt**: video.tt - Your True Tube
+ - **VideoTt**: video.tt - Your True Tube (Currently broken)
  - **videoweed**: VideoWeed
- - **Vidme**
+ - **vidme**
+ - **vidme:user**
+ - **vidme:user:likes**
  - **Vidzi**
  - **vier**
  - **vier:videos**
  - **Viewster**
+ - **Viidea**
  - **viki**
  - **viki:channel**
  - **vimeo**
@@ -656,6 +728,8 @@
  - **WebOfStories**
  - **WebOfStoriesPlaylist**
  - **Weibo**
+ - **WeiqiTV**: WQTV
+ - **wholecloud**: WholeCloud
  - **Wimp**
  - **Wistia**
  - **WNL**
@@ -664,6 +738,7 @@
  - **WSJ**: Wall Street Journal
  - **XBef**
  - **XboxClips**
+ - **XFileShare**: XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me
  - **XHamster**
  - **XHamsterEmbed**
  - **XMinus**
@@ -691,6 +766,7 @@
  - **youtube:favorites**: YouTube.com favourite videos, ":ytfav" for short (requires authentication)
  - **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication)
  - **youtube:playlist**: YouTube.com playlists
+ - **youtube:playlists**: YouTube.com user/channel playlists
  - **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication)
  - **youtube:search**: YouTube.com searches
  - **youtube:search:date**: YouTube.com searches, newest videos first
@@ -704,3 +780,4 @@
  - **ZDFChannel**
  - **zingmp3:album**: mp3.zing.vn albums
  - **zingmp3:song**: mp3.zing.vn songs
+ - **ZippCast**

setup.py

@@ -28,7 +28,7 @@ py2exe_options = {
     "compressed": 1,
     "optimize": 2,
     "dist_dir": '.',
-    "dll_excludes": ['w9xpopen.exe'],
+    "dll_excludes": ['w9xpopen.exe', 'crypt32.dll'],
 }
 
 py2exe_console = [{

test/test_InfoExtractor.py

@@ -35,10 +35,18 @@ class TestInfoExtractor(unittest.TestCase):
             <meta name="og:title" content='Foo'/>
             <meta content="Some video's description " name="og:description"/>
             <meta property='og:image' content='http://domain.com/pic.jpg?key1=val1&amp;key2=val2'/>
+            <meta content='application/x-shockwave-flash' property='og:video:type'>
+            <meta content='Foo' property=og:foobar>
+            <meta name="og:test1" content='foo > < bar'/>
+            <meta name="og:test2" content="foo >//< bar"/>
             '''
         self.assertEqual(ie._og_search_title(html), 'Foo')
         self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
         self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
+        self.assertEqual(ie._og_search_video_url(html, default=None), None)
+        self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
+        self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar')
+        self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar')
 
     def test_html_search_meta(self):
         ie = self.ie

test/test_YoutubeDL.py

@@ -12,8 +12,9 @@ import copy
 
 from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
-from youtube_dl.compat import compat_str
+from youtube_dl.compat import compat_str, compat_urllib_error
 from youtube_dl.extractor import YoutubeIE
+from youtube_dl.extractor.common import InfoExtractor
 from youtube_dl.postprocessor.common import PostProcessor
 from youtube_dl.utils import ExtractorError, match_filter_func
 
@@ -221,6 +222,16 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'dash-video-low')
 
+        formats = [
+            {'format_id': 'vid-vcodec-dot', 'ext': 'mp4', 'preference': 1, 'vcodec': 'avc1.123456', 'acodec': 'none', 'url': TEST_URL},
+        ]
+        info_dict = _make_result(formats)
+
+        ydl = YDL({'format': 'bestvideo[vcodec=avc1.123456]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot')
+
     def test_youtube_format_selection(self):
         order = [
             '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '36', '17', '13',
@@ -237,6 +248,17 @@ class TestFormatSelection(unittest.TestCase):
 
         def format_info(f_id):
             info = YoutubeIE._formats[f_id].copy()
+
+            # XXX: In real cases InfoExtractor._parse_mpd_formats() fills up 'acodec'
+            # and 'vcodec', while in tests such information is incomplete since
+            # commit a6c2c24479e5f4827ceb06f64d855329c0a6f593
+            # test_YoutubeDL.test_youtube_format_selection is broken without
+            # this fix
+            if 'acodec' in info and 'vcodec' not in info:
+                info['vcodec'] = 'none'
+            elif 'vcodec' in info and 'acodec' not in info:
+                info['acodec'] = 'none'
+
             info['format_id'] = f_id
             info['url'] = 'url:' + f_id
             return info
@@ -631,6 +653,47 @@ class TestYoutubeDL(unittest.TestCase):
         result = get_ids({'playlist_items': '10'})
         self.assertEqual(result, [])
 
+    def test_urlopen_no_file_protocol(self):
+        # see https://github.com/rg3/youtube-dl/issues/8227
+        ydl = YDL()
+        self.assertRaises(compat_urllib_error.URLError, ydl.urlopen, 'file:///etc/passwd')
+
+    def test_do_not_override_ie_key_in_url_transparent(self):
+        ydl = YDL()
+
+        class Foo1IE(InfoExtractor):
+            _VALID_URL = r'foo1:'
+
+            def _real_extract(self, url):
+                return {
+                    '_type': 'url_transparent',
+                    'url': 'foo2:',
+                    'ie_key': 'Foo2',
+                }
+
+        class Foo2IE(InfoExtractor):
+            _VALID_URL = r'foo2:'
+
+            def _real_extract(self, url):
+                return {
+                    '_type': 'url',
+                    'url': 'foo3:',
+                    'ie_key': 'Foo3',
+                }
+
+        class Foo3IE(InfoExtractor):
+            _VALID_URL = r'foo3:'
+
+            def _real_extract(self, url):
+                return _make_result([{'url': TEST_URL}])
+
+        ydl.add_info_extractor(Foo1IE(ydl))
+        ydl.add_info_extractor(Foo2IE(ydl))
+        ydl.add_info_extractor(Foo3IE(ydl))
+        ydl.extract_info('foo1:')
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['url'], TEST_URL)
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_all_urls.py

@@ -56,7 +56,7 @@ class TestAllURLsMatching(unittest.TestCase):
         assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
 
     def test_youtube_user_matching(self):
-        self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
+        self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
 
     def test_youtube_feeds(self):
         self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater'])
@@ -121,8 +121,8 @@ class TestAllURLsMatching(unittest.TestCase):
 
     def test_pbs(self):
         # https://github.com/rg3/youtube-dl/issues/2350
-        self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
-        self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])
+        self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs'])
+        self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs'])
 
     def test_yahoo_https(self):
         # https://github.com/rg3/youtube-dl/issues/2701

test/test_compat.py

@@ -13,8 +13,10 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 from youtube_dl.utils import get_filesystem_encoding
 from youtube_dl.compat import (
     compat_getenv,
+    compat_etree_fromstring,
     compat_expanduser,
     compat_shlex_split,
+    compat_str,
     compat_urllib_parse_unquote,
     compat_urllib_parse_unquote_plus,
 )
@@ -71,5 +73,20 @@ class TestCompat(unittest.TestCase):
     def test_compat_shlex_split(self):
         self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two'])
 
+    def test_compat_etree_fromstring(self):
+        xml = '''
+            <root foo="bar" spam="中文">
+                <normal>foo</normal>
+                <chinese>中文</chinese>
+                <foo><bar>spam</bar></foo>
+            </root>
+        '''
+        doc = compat_etree_fromstring(xml.encode('utf-8'))
+        self.assertTrue(isinstance(doc.attrib['foo'], compat_str))
+        self.assertTrue(isinstance(doc.attrib['spam'], compat_str))
+        self.assertTrue(isinstance(doc.find('normal').text, compat_str))
+        self.assertTrue(isinstance(doc.find('chinese').text, compat_str))
+        self.assertTrue(isinstance(doc.find('foo/bar').text, compat_str))
+
 if __name__ == '__main__':
     unittest.main()

test/test_download.py

@@ -102,7 +102,7 @@ def generator(test_case):
 
         params = get_params(test_case.get('params', {}))
         if is_playlist and 'playlist' not in test_case:
-            params.setdefault('extract_flat', True)
+            params.setdefault('extract_flat', 'in_playlist')
             params.setdefault('skip_download', True)
 
         ydl = YoutubeDL(params, auto_init=False)

test/test_jsinterp.py

@@ -19,6 +19,9 @@ class TestJSInterpreter(unittest.TestCase):
         jsi = JSInterpreter('function x3(){return 42;}')
         self.assertEqual(jsi.call_function('x3'), 42)
 
+        jsi = JSInterpreter('var x5 = function(){return 42;}')
+        self.assertEqual(jsi.call_function('x5'), 42)
+
     def test_calc(self):
         jsi = JSInterpreter('function x4(a){return 2*a+1;}')
         self.assertEqual(jsi.call_function('x4', 3), 7)

test/test_subtitles.py

@@ -11,7 +11,6 @@ from test.helper import FakeYDL, md5
 
 
 from youtube_dl.extractor import (
-    BlipTVIE,
     YoutubeIE,
     DailymotionIE,
     TEDIE,
@@ -22,12 +21,13 @@ from youtube_dl.extractor import (
     NPOIE,
     ComedyCentralIE,
     NRKTVIE,
-    RaiIE,
+    RaiTVIE,
     VikiIE,
     ThePlatformIE,
     ThePlatformFeedIE,
     RTVEALaCartaIE,
     FunnyOrDieIE,
+    DemocracynowIE,
 )
 
 
@@ -65,16 +65,16 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
         self.assertEqual(len(subtitles.keys()), 13)
-        self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260')
-        self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d')
-        for lang in ['it', 'fr', 'de']:
+        self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
+        self.assertEqual(md5(subtitles['it']), '6d752b98c31f1cf8d597050c7a2cb4b5')
+        for lang in ['fr', 'de']:
             self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
 
-    def test_youtube_subtitles_sbv_format(self):
+    def test_youtube_subtitles_ttml_format(self):
         self.DL.params['writesubtitles'] = True
-        self.DL.params['subtitlesformat'] = 'sbv'
+        self.DL.params['subtitlesformat'] = 'ttml'
         subtitles = self.getSubtitles()
-        self.assertEqual(md5(subtitles['en']), '13aeaa0c245a8bed9a451cb643e3ad8b')
+        self.assertEqual(md5(subtitles['en']), 'e306f8c42842f723447d9f63ad65df54')
 
     def test_youtube_subtitles_vtt_format(self):
         self.DL.params['writesubtitles'] = True
@@ -144,18 +144,6 @@ class TestTedSubtitles(BaseTestSubtitles):
             self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
 
 
-class TestBlipTVSubtitles(BaseTestSubtitles):
-    url = 'http://blip.tv/a/a-6603250'
-    IE = BlipTVIE
-
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['en']))
-        self.assertEqual(md5(subtitles['en']), '5b75c300af65fe4476dff79478bb93e4')
-
-
 class TestVimeoSubtitles(BaseTestSubtitles):
     url = 'http://vimeo.com/76979871'
     IE = VimeoIE
@@ -272,7 +260,7 @@ class TestNRKSubtitles(BaseTestSubtitles):
 
 class TestRaiSubtitles(BaseTestSubtitles):
     url = 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
-    IE = RaiIE
+    IE = RaiTVIE
 
     def test_allsubtitles(self):
         self.DL.params['writesubtitles'] = True
@@ -346,5 +334,25 @@ class TestFunnyOrDieSubtitles(BaseTestSubtitles):
         self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4')
 
 
+class TestDemocracynowSubtitles(BaseTestSubtitles):
+    url = 'http://www.democracynow.org/shows/2015/7/3'
+    IE = DemocracynowIE
+
+    def test_allsubtitles(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['en']))
+        self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
+
+    def test_subtitles_in_page(self):
+        self.url = 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree'
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['en']))
+        self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_update.py

@@ -0,0 +1,30 @@
+#!/usr/bin/env python
+
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+import json
+from youtube_dl.update import rsa_verify
+
+
+class TestUpdate(unittest.TestCase):
+    def test_rsa_verify(self):
+        UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
+        with open(os.path.join(os.path.dirname(os.path.abspath(__file__)), 'versions.json'), 'rb') as f:
+            versions_info = f.read().decode()
+        versions_info = json.loads(versions_info)
+        signature = versions_info['signature']
+        del versions_info['signature']
+        self.assertTrue(rsa_verify(
+            json.dumps(versions_info, sort_keys=True).encode('utf-8'),
+            signature, UPDATES_RSA_KEY))
+
+
+if __name__ == '__main__':
+    unittest.main()

test/test_utils.py

@@ -21,6 +21,9 @@ from youtube_dl.utils import (
     clean_html,
     DateRange,
     detect_exe_version,
+    determine_ext,
+    dict_get,
+    encode_compat_str,
     encodeFilename,
     escape_rfc3986,
     escape_url,
@@ -42,6 +45,7 @@ from youtube_dl.utils import (
     sanitize_path,
     prepend_extension,
     replace_extension,
+    remove_quotes,
     shell_quote,
     smuggle_url,
     str_to_int,
@@ -68,6 +72,9 @@ from youtube_dl.utils import (
     cli_valueless_option,
     cli_bool_option,
 )
+from youtube_dl.compat import (
+    compat_etree_fromstring,
+)
 
 
 class TestUtil(unittest.TestCase):
@@ -196,6 +203,15 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
         self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
 
+    def test_remove_quotes(self):
+        self.assertEqual(remove_quotes(None), None)
+        self.assertEqual(remove_quotes('"'), '"')
+        self.assertEqual(remove_quotes("'"), "'")
+        self.assertEqual(remove_quotes(';'), ';')
+        self.assertEqual(remove_quotes('";'), '";')
+        self.assertEqual(remove_quotes('""'), '')
+        self.assertEqual(remove_quotes('";"'), ';')
+
     def test_ordered_set(self):
         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
         self.assertEqual(orderedSet([]), [])
@@ -207,8 +223,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unescapeHTML('%20;'), '%20;')
         self.assertEqual(unescapeHTML('/'), '/')
         self.assertEqual(unescapeHTML('/'), '/')
-        self.assertEqual(
-            unescapeHTML('é'), 'é')
+        self.assertEqual(unescapeHTML('é'), 'é')
+        self.assertEqual(unescapeHTML('�'), '�')
 
     def test_daterange(self):
         _20century = DateRange("19000101", "20000101")
@@ -233,6 +249,14 @@ class TestUtil(unittest.TestCase):
             unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
             '20150202')
         self.assertEqual(unified_strdate('25-09-2014'), '20140925')
+        self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
+
+    def test_determine_ext(self):
+        self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
+        self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
+        self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
+        self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
+        self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
 
     def test_find_xpath_attr(self):
         testxml = '''<root>
@@ -242,7 +266,7 @@ class TestUtil(unittest.TestCase):
             <node x="b" y="d" />
             <node x="" />
         </root>'''
-        doc = xml.etree.ElementTree.fromstring(testxml)
+        doc = compat_etree_fromstring(testxml)
 
         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
@@ -263,7 +287,7 @@ class TestUtil(unittest.TestCase):
                 <url>http://server.com/download.mp3</url>
             </media:song>
         </root>'''
-        doc = xml.etree.ElementTree.fromstring(testxml)
+        doc = compat_etree_fromstring(testxml)
         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
         self.assertTrue(find('media:song') is not None)
         self.assertEqual(find('media:song/media:author').text, 'The Author')
@@ -275,9 +299,16 @@ class TestUtil(unittest.TestCase):
         p = xml.etree.ElementTree.SubElement(div, 'p')
         p.text = 'Foo'
         self.assertEqual(xpath_element(doc, 'div/p'), p)
+        self.assertEqual(xpath_element(doc, ['div/p']), p)
+        self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
         self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
+        self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
         self.assertTrue(xpath_element(doc, 'div/bar') is None)
+        self.assertTrue(xpath_element(doc, ['div/bar']) is None)
+        self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
         self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
+        self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
+        self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
 
     def test_xpath_text(self):
         testxml = '''<root>
@@ -285,7 +316,7 @@ class TestUtil(unittest.TestCase):
                 <p>Foo</p>
             </div>
         </root>'''
-        doc = xml.etree.ElementTree.fromstring(testxml)
+        doc = compat_etree_fromstring(testxml)
         self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
         self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
         self.assertTrue(xpath_text(doc, 'div/bar') is None)
@@ -297,7 +328,7 @@ class TestUtil(unittest.TestCase):
                 <p x="a">Foo</p>
             </div>
         </root>'''
-        doc = xml.etree.ElementTree.fromstring(testxml)
+        doc = compat_etree_fromstring(testxml)
         self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
         self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
         self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
@@ -420,11 +451,39 @@ class TestUtil(unittest.TestCase):
         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
         self.assertTrue(isinstance(data, bytes))
 
+    def test_dict_get(self):
+        FALSE_VALUES = {
+            'none': None,
+            'false': False,
+            'zero': 0,
+            'empty_string': '',
+            'empty_list': [],
+        }
+        d = FALSE_VALUES.copy()
+        d['a'] = 42
+        self.assertEqual(dict_get(d, 'a'), 42)
+        self.assertEqual(dict_get(d, 'b'), None)
+        self.assertEqual(dict_get(d, 'b', 42), 42)
+        self.assertEqual(dict_get(d, ('a', )), 42)
+        self.assertEqual(dict_get(d, ('b', 'a', )), 42)
+        self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42)
+        self.assertEqual(dict_get(d, ('b', 'c', )), None)
+        self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42)
+        for key, false_value in FALSE_VALUES.items():
+            self.assertEqual(dict_get(d, ('b', 'c', key, )), None)
+            self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value)
+
+    def test_encode_compat_str(self):
+        self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
+        self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
+
     def test_parse_iso8601(self):
         self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
         self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
         self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
         self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
+        self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
+        self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
 
     def test_strip_jsonp(self):
         stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
@@ -435,6 +494,10 @@ class TestUtil(unittest.TestCase):
         d = json.loads(stripped)
         self.assertEqual(d, {'STATUS': 'OK'})
 
+        stripped = strip_jsonp('ps.embedHandler({"status": "success"});')
+        d = json.loads(stripped)
+        self.assertEqual(d, {'status': 'success'})
+
     def test_uppercase_escape(self):
         self.assertEqual(uppercase_escape('aä'), 'aä')
         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
@@ -495,6 +558,9 @@ class TestUtil(unittest.TestCase):
             "playlist":[{"controls":{"all":null}}]
         }''')
 
+        inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
+        self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
+
         inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
         json_code = js_to_json(inp)
         self.assertEqual(json.loads(json_code), json.loads(inp))
@@ -627,12 +693,13 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
             {'like_count': 190, 'dislike_count': 10}))
 
     def test_parse_dfxp_time_expr(self):
-        self.assertEqual(parse_dfxp_time_expr(None), 0.0)
-        self.assertEqual(parse_dfxp_time_expr(''), 0.0)
+        self.assertEqual(parse_dfxp_time_expr(None), None)
+        self.assertEqual(parse_dfxp_time_expr(''), None)
         self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
         self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
         self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
         self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
+        self.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
 
     def test_dfxp2srt(self):
         dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
@@ -642,6 +709,9 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
                     <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
                     <p begin="1" end="2">第二行<br/>♪♪</p>
                     <p begin="2" dur="1"><span>Third<br/>Line</span></p>
+                    <p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
+                    <p begin="-1" end="-1">Ignore, two</p>
+                    <p begin="3" dur="-1">Ignored, three</p>
                 </div>
             </body>
             </tt>'''

test/test_write_annotations.py

@@ -66,7 +66,7 @@ class TestAnnotations(unittest.TestCase):
                 textTag = a.find('TEXT')
                 text = textTag.text
                 self.assertTrue(text in expected)  # assertIn only added in python 2.7
-                # remove the first occurance, there could be more than one annotation with the same text
+                # remove the first occurrence, there could be more than one annotation with the same text
                 expected.remove(text)
         # We should have seen (and removed) all the expected annotation texts.
         self.assertEqual(len(expected), 0, 'Not all expected annotations were found.')

test/test_youtube_lists.py

@@ -34,7 +34,7 @@ class TestYoutubeLists(unittest.TestCase):
         ie = YoutubePlaylistIE(dl)
         # TODO find a > 100 (paginating?) videos course
         result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
-        entries = result['entries']
+        entries = list(result['entries'])
         self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs')
         self.assertEqual(len(entries), 25)
         self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
@@ -57,5 +57,14 @@ class TestYoutubeLists(unittest.TestCase):
         entries = result['entries']
         self.assertEqual(len(entries), 100)
 
+    def test_youtube_flat_playlist_titles(self):
+        dl = FakeYDL()
+        dl.params['extract_flat'] = True
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
+        self.assertIsPlaylist(result)
+        for entry in result['entries']:
+            self.assertTrue(entry.get('title'))
+
 if __name__ == '__main__':
     unittest.main()

test/versions.json

@@ -0,0 +1,34 @@
+{
+    "latest": "2013.01.06", 
+    "signature": "72158cdba391628569ffdbea259afbcf279bbe3d8aeb7492690735dc1cfa6afa754f55c61196f3871d429599ab22f2667f1fec98865527b32632e7f4b3675a7ef0f0fbe084d359256ae4bba68f0d33854e531a70754712f244be71d4b92e664302aa99653ee4df19800d955b6c4149cd2b3f24288d6e4b40b16126e01f4c8ce6", 
+    "versions": {
+        "2013.01.02": {
+            "bin": [
+                "http://youtube-dl.org/downloads/2013.01.02/youtube-dl", 
+                "f5b502f8aaa77675c4884938b1e4871ebca2611813a0c0e74f60c0fbd6dcca6b"
+            ], 
+            "exe": [
+                "http://youtube-dl.org/downloads/2013.01.02/youtube-dl.exe", 
+                "75fa89d2ce297d102ff27675aa9d92545bbc91013f52ec52868c069f4f9f0422"
+            ], 
+            "tar": [
+                "http://youtube-dl.org/downloads/2013.01.02/youtube-dl-2013.01.02.tar.gz", 
+                "6a66d022ac8e1c13da284036288a133ec8dba003b7bd3a5179d0c0daca8c8196"
+            ]
+        }, 
+        "2013.01.06": {
+            "bin": [
+                "http://youtube-dl.org/downloads/2013.01.06/youtube-dl", 
+                "64b6ed8865735c6302e836d4d832577321b4519aa02640dc508580c1ee824049"
+            ], 
+            "exe": [
+                "http://youtube-dl.org/downloads/2013.01.06/youtube-dl.exe", 
+                "58609baf91e4389d36e3ba586e21dab882daaaee537e4448b1265392ae86ff84"
+            ], 
+            "tar": [
+                "http://youtube-dl.org/downloads/2013.01.06/youtube-dl-2013.01.06.tar.gz", 
+                "fe77ab20a95d980ed17a659aa67e371fdd4d656d19c4c7950e7b720b0c2f1a86"
+            ]
+        }
+    }
+}

youtube_dl/YoutubeDL.py

@@ -28,6 +28,7 @@ if os.name == 'nt':
     import ctypes
 
 from .compat import (
+    compat_basestring,
     compat_cookiejar,
     compat_expanduser,
     compat_get_terminal_size,
@@ -37,6 +38,7 @@ from .compat import (
     compat_tokenize_tokenize,
     compat_urllib_error,
     compat_urllib_request,
+    compat_urllib_request_DataHandler,
 )
 from .utils import (
     ContentTooShortError,
@@ -44,8 +46,11 @@ from .utils import (
     DateRange,
     DEFAULT_OUTTMPL,
     determine_ext,
+    determine_protocol,
     DownloadError,
+    encode_compat_str,
     encodeFilename,
+    error_to_compat_str,
     ExtractorError,
     format_bytes,
     formatSeconds,
@@ -62,6 +67,7 @@ from .utils import (
     SameFileError,
     sanitize_filename,
     sanitize_path,
+    sanitized_Request,
     std_headers,
     subtitles_filename,
     UnavailableVideoError,
@@ -155,7 +161,7 @@ class YoutubeDL(object):
     writethumbnail:    Write the thumbnail image to a file
     write_all_thumbnails:  Write all thumbnail formats to files
     writesubtitles:    Write the video subtitles to a file
-    writeautomaticsub: Write the automatic subtitles to a file
+    writeautomaticsub: Write the automatically generated subtitles to a file
     allsubtitles:      Downloads all the subtitles of the video
                        (requires writesubtitles or writeautomaticsub)
     listsubtitles:     Lists all available subtitles for the video
@@ -257,7 +263,7 @@ class YoutubeDL(object):
     the downloader (see youtube_dl/downloader/common.py):
     nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test,
     noresizebuffer, retries, continuedl, noprogress, consoletitle,
-    xattr_set_filesize, external_downloader_args.
+    xattr_set_filesize, external_downloader_args, hls_use_mpegts.
 
     The following options are used by the post processors:
     prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
@@ -492,7 +498,7 @@ class YoutubeDL(object):
                     tb = ''
                     if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
                         tb += ''.join(traceback.format_exception(*sys.exc_info()[1].exc_info))
-                    tb += compat_str(traceback.format_exc())
+                    tb += encode_compat_str(traceback.format_exc())
                 else:
                     tb_data = traceback.format_list(traceback.extract_stack())
                     tb = ''.join(tb_data)
@@ -571,7 +577,7 @@ class YoutubeDL(object):
                                  if v is not None)
             template_dict = collections.defaultdict(lambda: 'NA', template_dict)
 
-            outtmpl = sanitize_path(self.params.get('outtmpl', DEFAULT_OUTTMPL))
+            outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
             tmpl = compat_expanduser(outtmpl)
             filename = tmpl % template_dict
             # Temporary fix for #4787
@@ -579,7 +585,7 @@ class YoutubeDL(object):
             # to workaround encoding issues with subprocess on python2 @ Windows
             if sys.version_info < (3, 0) and sys.platform == 'win32':
                 filename = encodeFilename(filename, True).decode(preferredencoding())
-            return filename
+            return sanitize_path(filename)
         except ValueError as err:
             self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
             return None
@@ -671,14 +677,14 @@ class YoutubeDL(object):
                     return self.process_ie_result(ie_result, download, extra_info)
                 else:
                     return ie_result
-            except ExtractorError as de:  # An error we somewhat expected
-                self.report_error(compat_str(de), de.format_traceback())
+            except ExtractorError as e:  # An error we somewhat expected
+                self.report_error(compat_str(e), e.format_traceback())
                 break
             except MaxDownloadsReached:
                 raise
             except Exception as e:
                 if self.params.get('ignoreerrors', False):
-                    self.report_error(compat_str(e), tb=compat_str(traceback.format_exc()))
+                    self.report_error(error_to_compat_str(e), tb=encode_compat_str(traceback.format_exc()))
                     break
                 else:
                     raise
@@ -701,7 +707,6 @@ class YoutubeDL(object):
         It will also download the videos if 'download'.
         Returns the resolved ie_result.
         """
-
         result_type = ie_result.get('_type', 'video')
 
         if result_type in ('url', 'url_transparent'):
@@ -730,7 +735,7 @@ class YoutubeDL(object):
 
             force_properties = dict(
                 (k, v) for k, v in ie_result.items() if v is not None)
-            for f in ('_type', 'url'):
+            for f in ('_type', 'url', 'ie_key'):
                 if f in force_properties:
                     del force_properties[f]
             new_result = info.copy()
@@ -832,6 +837,7 @@ class YoutubeDL(object):
                                                       extra_info=extra)
                 playlist_results.append(entry_result)
             ie_result['entries'] = playlist_results
+            self.to_screen('[download] Finished downloading playlist: %s' % playlist)
             return ie_result
         elif result_type == 'compat_list':
             self.report_warning(
@@ -892,11 +898,14 @@ class YoutubeDL(object):
             STR_OPERATORS = {
                 '=': operator.eq,
                 '!=': operator.ne,
+                '^=': lambda attr, value: attr.startswith(value),
+                '$=': lambda attr, value: attr.endswith(value),
+                '*=': lambda attr, value: value in attr,
             }
             str_operator_rex = re.compile(r'''(?x)
                 \s*(?P<key>ext|acodec|vcodec|container|protocol)
                 \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
-                \s*(?P<value>[a-zA-Z0-9_-]+)
+                \s*(?P<value>[a-zA-Z0-9._-]+)
                 \s*$
                 ''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
             m = str_operator_rex.search(filter_spec)
@@ -936,7 +945,7 @@ class YoutubeDL(object):
                     filter_parts.append(string)
 
         def _remove_unused_ops(tokens):
-            # Remove operators that we don't use and join them with the sourrounding strings
+            # Remove operators that we don't use and join them with the surrounding strings
             # for example: 'mp4' '-' 'baseline' '-' '16x9' is converted to 'mp4-baseline-16x9'
             ALLOWED_OPS = ('/', '+', ',', '(', ')')
             last_string, last_start, last_end, last_line = None, None, None, None
@@ -1106,6 +1115,12 @@ class YoutubeDL(object):
                                           'contain the video, try using '
                                           '"-f %s+%s"' % (format_2, format_1))
                         return
+                    # Formats must be opposite (video+audio)
+                    if formats_info[0].get('acodec') == 'none' and formats_info[1].get('acodec') == 'none':
+                        self.report_error(
+                            'Both formats %s and %s are video-only, you must specify "-f video+audio"'
+                            % (format_1, format_2))
+                        return
                     output_ext = (
                         formats_info[0]['ext']
                         if self.params.get('merge_output_format') is None
@@ -1185,7 +1200,7 @@ class YoutubeDL(object):
         return res
 
     def _calc_cookies(self, info_dict):
-        pr = compat_urllib_request.Request(info_dict['url'])
+        pr = sanitized_Request(info_dict['url'])
         self.cookiejar.add_cookie_header(pr)
         return pr.get_header('Cookie')
 
@@ -1232,6 +1247,12 @@ class YoutubeDL(object):
             except (ValueError, OverflowError, OSError):
                 pass
 
+        # Auto generate title fields corresponding to the *_number fields when missing
+        # in order to always have clean titles. This is very common for TV series.
+        for field in ('chapter', 'season', 'episode'):
+            if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
+                info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
+
         subtitles = info_dict.get('subtitles')
         if subtitles:
             for _, subtitle in subtitles.items():
@@ -1267,6 +1288,9 @@ class YoutubeDL(object):
 
             if format.get('format_id') is None:
                 format['format_id'] = compat_str(i)
+            else:
+                # Sanitize format_id from characters used in format selector expression
+                format['format_id'] = re.sub('[\s,/+\[\]()]', '_', format['format_id'])
             format_id = format['format_id']
             if format_id not in formats_dict:
                 formats_dict[format_id] = []
@@ -1288,6 +1312,10 @@ class YoutubeDL(object):
             # Automatically determine file extension if missing
             if 'ext' not in format:
                 format['ext'] = determine_ext(format['url']).lower()
+            # Automatically determine protocol if missing (useful for format
+            # selection purposes)
+            if 'protocol' not in format:
+                format['protocol'] = determine_protocol(format)
             # Add HTTP headers, so that external programs can use them from the
             # json output
             full_format_info = info_dict.copy()
@@ -1300,7 +1328,7 @@ class YoutubeDL(object):
             # only set the 'formats' fields if the original info_dict list them
             # otherwise we end up with a circular reference, the first (and unique)
             # element in the 'formats' field in info_dict is info_dict itself,
-            # wich can't be exported to json
+            # which can't be exported to json
             info_dict['formats'] = formats
         if self.params.get('listformats'):
             self.list_formats(info_dict)
@@ -1313,7 +1341,6 @@ class YoutubeDL(object):
         if req_format is None:
             req_format_list = []
             if (self.params.get('outtmpl', DEFAULT_OUTTMPL) != '-' and
-                    info_dict['extractor'] in ['youtube', 'ted'] and
                     not info_dict.get('is_live')):
                 merger = FFmpegMergerPP(self)
                 if merger.available and merger.can_merge():
@@ -1449,7 +1476,7 @@ class YoutubeDL(object):
             if dn and not os.path.exists(dn):
                 os.makedirs(dn)
         except (OSError, IOError) as err:
-            self.report_error('unable to create directory ' + compat_str(err))
+            self.report_error('unable to create directory ' + error_to_compat_str(err))
             return
 
         if self.params.get('writedescription', False):
@@ -1500,7 +1527,7 @@ class YoutubeDL(object):
                             sub_info['url'], info_dict['id'], note=False)
                     except ExtractorError as err:
                         self.report_warning('Unable to download subtitle for "%s": %s' %
-                                            (sub_lang, compat_str(err.cause)))
+                                            (sub_lang, error_to_compat_str(err.cause)))
                         continue
                 try:
                     sub_filename = subtitles_filename(filename, sub_lang, sub_format)
@@ -1770,7 +1797,7 @@ class YoutubeDL(object):
             else:
                 res = '%sp' % format['height']
         elif format.get('width') is not None:
-            res = '?x%d' % format['width']
+            res = '%dx?' % format['width']
         else:
             res = default
         return res
@@ -1779,6 +1806,10 @@ class YoutubeDL(object):
         res = ''
         if fdict.get('ext') in ['f4f', 'f4m']:
             res += '(unsupported) '
+        if fdict.get('language'):
+            if res:
+                res += ' '
+            res += '[%s]' % fdict['language']
         if fdict.get('format_note') is not None:
             res += fdict['format_note'] + ' '
         if fdict.get('tbr') is not None:
@@ -1869,6 +1900,8 @@ class YoutubeDL(object):
 
     def urlopen(self, req):
         """ Start an HTTP download """
+        if isinstance(req, compat_basestring):
+            req = sanitized_Request(req)
         return self._opener.open(req, timeout=self._socket_timeout)
 
     def print_debug_header(self):
@@ -1967,8 +2000,20 @@ class YoutubeDL(object):
         debuglevel = 1 if self.params.get('debug_printtraffic') else 0
         https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
         ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
+        data_handler = compat_urllib_request_DataHandler()
+
+        # When passing our own FileHandler instance, build_opener won't add the
+        # default FileHandler and allows us to disable the file protocol, which
+        # can be used for malicious purposes (see
+        # https://github.com/rg3/youtube-dl/issues/8227)
+        file_handler = compat_urllib_request.FileHandler()
+
+        def file_open(*args, **kwargs):
+            raise compat_urllib_error.URLError('file:// scheme is explicitly disabled in youtube-dl for security reasons')
+        file_handler.file_open = file_open
+
         opener = compat_urllib_request.build_opener(
-            proxy_handler, https_handler, cookie_processor, ydlh)
+            proxy_handler, https_handler, cookie_processor, ydlh, data_handler, file_handler)
 
         # Delete the default user-agent header, which would otherwise apply in
         # cases where our custom HTTP handler doesn't come into play
@@ -2026,4 +2071,4 @@ class YoutubeDL(object):
                                    (info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename))
                 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
                     self.report_warning('Unable to download thumbnail "%s": %s' %
-                                        (t['url'], compat_str(err)))
+                                        (t['url'], error_to_compat_str(err)))

youtube_dl/__init__.py

@@ -369,6 +369,7 @@ def _real_main(argv=None):
         'no_color': opts.no_color,
         'ffmpeg_location': opts.ffmpeg_location,
         'hls_prefer_native': opts.hls_prefer_native,
+        'hls_use_mpegts': opts.hls_use_mpegts,
         'external_downloader_args': external_downloader_args,
         'postprocessor_args': postprocessor_args,
         'cn_verification_proxy': opts.cn_verification_proxy,
@@ -377,7 +378,7 @@ def _real_main(argv=None):
     with YoutubeDL(ydl_opts) as ydl:
         # Update version
         if opts.update_self:
-            update_self(ydl.to_screen, opts.verbose)
+            update_self(ydl.to_screen, opts.verbose, ydl._opener)
 
         # Remove cache dir
         if opts.rm_cachedir:

youtube_dl/compat.py

@@ -1,7 +1,10 @@
 from __future__ import unicode_literals
 
+import binascii
 import collections
+import email
 import getpass
+import io
 import optparse
 import os
 import re
@@ -11,6 +14,7 @@ import socket
 import subprocess
 import sys
 import itertools
+import xml.etree.ElementTree
 
 
 try:
@@ -38,6 +42,11 @@ try:
 except ImportError:  # Python 2
     import urlparse as compat_urlparse
 
+try:
+    import urllib.response as compat_urllib_response
+except ImportError:  # Python 2
+    import urllib as compat_urllib_response
+
 try:
     import http.cookiejar as compat_cookiejar
 except ImportError:  # Python 2
@@ -155,6 +164,40 @@ except ImportError:  # Python 2
         string = string.replace('+', ' ')
         return compat_urllib_parse_unquote(string, encoding, errors)
 
+try:
+    from urllib.request import DataHandler as compat_urllib_request_DataHandler
+except ImportError:  # Python < 3.4
+    # Ported from CPython 98774:1733b3bd46db, Lib/urllib/request.py
+    class compat_urllib_request_DataHandler(compat_urllib_request.BaseHandler):
+        def data_open(self, req):
+            # data URLs as specified in RFC 2397.
+            #
+            # ignores POSTed data
+            #
+            # syntax:
+            # dataurl   := "data:" [ mediatype ] [ ";base64" ] "," data
+            # mediatype := [ type "/" subtype ] *( ";" parameter )
+            # data      := *urlchar
+            # parameter := attribute "=" value
+            url = req.get_full_url()
+
+            scheme, data = url.split(":", 1)
+            mediatype, data = data.split(",", 1)
+
+            # even base64 encoded data URLs might be quoted so unquote in any case:
+            data = compat_urllib_parse_unquote_to_bytes(data)
+            if mediatype.endswith(";base64"):
+                data = binascii.a2b_base64(data)
+                mediatype = mediatype[:-7]
+
+            if not mediatype:
+                mediatype = "text/plain;charset=US-ASCII"
+
+            headers = email.message_from_string(
+                "Content-type: %s\nContent-length: %d\n" % (mediatype, len(data)))
+
+            return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
+
 try:
     compat_basestring = basestring  # Python 2
 except NameError:
@@ -170,6 +213,43 @@ try:
 except ImportError:  # Python 2.6
     from xml.parsers.expat import ExpatError as compat_xml_parse_error
 
+if sys.version_info[0] >= 3:
+    compat_etree_fromstring = xml.etree.ElementTree.fromstring
+else:
+    # python 2.x tries to encode unicode strings with ascii (see the
+    # XMLParser._fixtext method)
+    etree = xml.etree.ElementTree
+
+    try:
+        _etree_iter = etree.Element.iter
+    except AttributeError:  # Python <=2.6
+        def _etree_iter(root):
+            for el in root.findall('*'):
+                yield el
+                for sub in _etree_iter(el):
+                    yield sub
+
+    # on 2.6 XML doesn't have a parser argument, function copied from CPython
+    # 2.7 source
+    def _XML(text, parser=None):
+        if not parser:
+            parser = etree.XMLParser(target=etree.TreeBuilder())
+        parser.feed(text)
+        return parser.close()
+
+    def _element_factory(*args, **kwargs):
+        el = etree.Element(*args, **kwargs)
+        for k, v in el.items():
+            if isinstance(v, bytes):
+                el.set(k, v.decode('utf-8'))
+        return el
+
+    def compat_etree_fromstring(text):
+        doc = _XML(text, parser=etree.XMLParser(target=etree.TreeBuilder(element_factory=_element_factory)))
+        for el in _etree_iter(doc):
+            if el.text is not None and isinstance(el.text, bytes):
+                el.text = el.text.decode('utf-8')
+        return doc
 
 try:
     from urllib.parse import parse_qs as compat_parse_qs
@@ -353,7 +433,7 @@ if sys.version_info < (3, 0) and sys.platform == 'win32':
 else:
     compat_getpass = getpass.getpass
 
-# Old 2.6 and 2.7 releases require kwargs to be bytes
+# Python < 2.6.5 require kwargs to be bytes
 try:
     def _testfunc(x):
         pass
@@ -434,7 +514,7 @@ else:
                     ['stty', 'size'],
                     stdout=subprocess.PIPE, stderr=subprocess.PIPE)
                 out, err = sp.communicate()
-                _columns, _lines = map(int, out.split())
+                _lines, _columns = map(int, out.split())
             except Exception:
                 _columns, _lines = _terminal_size(*fallback)
 
@@ -465,6 +545,7 @@ __all__ = [
     'compat_chr',
     'compat_cookiejar',
     'compat_cookies',
+    'compat_etree_fromstring',
     'compat_expanduser',
     'compat_get_terminal_size',
     'compat_getenv',
@@ -489,6 +570,8 @@ __all__ = [
     'compat_urllib_parse_unquote_to_bytes',
     'compat_urllib_parse_urlparse',
     'compat_urllib_request',
+    'compat_urllib_request_DataHandler',
+    'compat_urllib_response',
     'compat_urlparse',
     'compat_urlretrieve',
     'compat_xml_parse_error',

youtube_dl/downloader/common.py

@@ -5,9 +5,9 @@ import re
 import sys
 import time
 
-from ..compat import compat_str
 from ..utils import (
     encodeFilename,
+    error_to_compat_str,
     decodeArgument,
     format_bytes,
     timeconvert,
@@ -42,9 +42,10 @@ class FileDownloader(object):
     min_filesize:       Skip files smaller than this size
     max_filesize:       Skip files larger than this size
     xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
-                        (experimenatal)
+                        (experimental)
     external_downloader_args:  A list of additional command-line arguments for the
                         external downloader.
+    hls_use_mpegts:     Use the mpegts container for HLS videos.
 
     Subclasses of this one must re-define the real_download method.
     """
@@ -186,7 +187,7 @@ class FileDownloader(object):
                 return
             os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
         except (IOError, OSError) as err:
-            self.report_error('unable to rename file: %s' % compat_str(err))
+            self.report_error('unable to rename file: %s' % error_to_compat_str(err))
 
     def try_utime(self, filename, last_modified_hdr):
         """Try to set the last-modified time of the given file."""
@@ -295,7 +296,7 @@ class FileDownloader(object):
 
     def report_retry(self, count, retries):
         """Report retry in case of HTTP error 5xx"""
-        self.to_screen('[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
+        self.to_screen('[download] Got server HTTP error. Retrying (attempt %d of %.0f)...' % (count, retries))
 
     def report_file_already_downloaded(self, file_name):
         """Report file has already been fully downloaded."""
@@ -325,7 +326,7 @@ class FileDownloader(object):
         )
 
         # Check file already present
-        if filename != '-' and nooverwrites_and_exists or continuedl_and_exists:
+        if filename != '-' and (nooverwrites_and_exists or continuedl_and_exists):
             self.report_file_already_downloaded(filename)
             self._hook_progress({
                 'filename': filename,

youtube_dl/downloader/dash.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import FileDownloader
-from ..compat import compat_urllib_request
+from ..utils import sanitized_Request
 
 
 class DashSegmentsFD(FileDownloader):
@@ -22,7 +22,7 @@ class DashSegmentsFD(FileDownloader):
 
         def append_url_to_file(outf, target_url, target_name, remaining_bytes=None):
             self.to_screen('[DashSegments] %s: Downloading %s' % (info_dict['id'], target_name))
-            req = compat_urllib_request.Request(target_url)
+            req = sanitized_Request(target_url)
             if remaining_bytes is not None:
                 req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
 
@@ -40,9 +40,10 @@ class DashSegmentsFD(FileDownloader):
             return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', target_url)
 
         with open(tmpfilename, 'wb') as outf:
-            append_url_to_file(
-                outf, combine_url(base_url, info_dict['initialization_url']),
-                'initialization segment')
+            if info_dict.get('initialization_url'):
+                append_url_to_file(
+                    outf, combine_url(base_url, info_dict['initialization_url']),
+                    'initialization segment')
             for i, segment_url in enumerate(segment_urls):
                 segment_len = append_url_to_file(
                     outf, combine_url(base_url, segment_url),

youtube_dl/downloader/f4m.py

@@ -5,15 +5,17 @@ import io
 import itertools
 import os
 import time
-import xml.etree.ElementTree as etree
 
 from .fragment import FragmentFD
 from ..compat import (
+    compat_etree_fromstring,
     compat_urlparse,
     compat_urllib_error,
+    compat_urllib_parse_urlparse,
 )
 from ..utils import (
     encodeFilename,
+    fix_xml_ampersands,
     sanitize_open,
     struct_pack,
     struct_unpack,
@@ -271,23 +273,34 @@ class F4mFD(FragmentFD):
         return fragments_list
 
     def _parse_bootstrap_node(self, node, base_url):
-        if node.text is None:
+        # Sometimes non empty inline bootstrap info can be specified along
+        # with bootstrap url attribute (e.g. dummy inline bootstrap info
+        # contains whitespace characters in [1]). We will prefer bootstrap
+        # url over inline bootstrap info when present.
+        # 1. http://live-1-1.rutube.ru/stream/1024/HDS/SD/C2NKsS85HQNckgn5HdEmOQ/1454167650/S-s604419906/move/four/dirs/upper/1024-576p.f4m
+        bootstrap_url = node.get('url')
+        if bootstrap_url:
             bootstrap_url = compat_urlparse.urljoin(
-                base_url, node.attrib['url'])
+                base_url, bootstrap_url)
             boot_info = self._get_bootstrap_from_url(bootstrap_url)
         else:
             bootstrap_url = None
             bootstrap = base64.b64decode(node.text.encode('ascii'))
             boot_info = read_bootstrap_info(bootstrap)
-        return (boot_info, bootstrap_url)
+        return boot_info, bootstrap_url
 
     def real_download(self, filename, info_dict):
         man_url = info_dict['url']
         requested_bitrate = info_dict.get('tbr')
         self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
-        manifest = self.ydl.urlopen(man_url).read()
+        urlh = self.ydl.urlopen(man_url)
+        man_url = urlh.geturl()
+        # Some manifests may be malformed, e.g. prosiebensat1 generated manifests
+        # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244
+        # and https://github.com/rg3/youtube-dl/issues/7823)
+        manifest = fix_xml_ampersands(urlh.read().decode('utf-8', 'ignore')).strip()
 
-        doc = etree.fromstring(manifest)
+        doc = compat_etree_fromstring(manifest)
         formats = [(int(f.attrib.get('bitrate', -1)), f)
                    for f in self._get_unencrypted_media(doc)]
         if requested_bitrate is None:
@@ -309,7 +322,8 @@ class F4mFD(FragmentFD):
             metadata = None
 
         fragments_list = build_fragments_list(boot_info)
-        if self.params.get('test', False):
+        test = self.params.get('test', False)
+        if test:
             # We only download the first fragment
             fragments_list = fragments_list[:1]
         total_frags = len(fragments_list)
@@ -319,6 +333,7 @@ class F4mFD(FragmentFD):
         ctx = {
             'filename': filename,
             'total_frags': total_frags,
+            'live': live,
         }
 
         self._prepare_frag_download(ctx)
@@ -329,20 +344,25 @@ class F4mFD(FragmentFD):
         if not live:
             write_metadata_tag(dest_stream, metadata)
 
+        base_url_parsed = compat_urllib_parse_urlparse(base_url)
+
         self._start_frag_download(ctx)
 
         frags_filenames = []
         while fragments_list:
             seg_i, frag_i = fragments_list.pop(0)
             name = 'Seg%d-Frag%d' % (seg_i, frag_i)
-            url = base_url + name
+            query = []
+            if base_url_parsed.query:
+                query.append(base_url_parsed.query)
             if akamai_pv:
-                url += '?' + akamai_pv.strip(';')
+                query.append(akamai_pv.strip(';'))
             if info_dict.get('extra_param_to_segment_url'):
-                url += info_dict.get('extra_param_to_segment_url')
+                query.append(info_dict['extra_param_to_segment_url'])
+            url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query))
             frag_filename = '%s-%s' % (ctx['tmpfilename'], name)
             try:
-                success = ctx['dl'].download(frag_filename, {'url': url})
+                success = ctx['dl'].download(frag_filename, {'url': url_parsed.geturl()})
                 if not success:
                     return False
                 (down, frag_sanitized) = sanitize_open(frag_filename, 'rb')
@@ -368,7 +388,7 @@ class F4mFD(FragmentFD):
                 else:
                     raise
 
-            if not fragments_list and live and bootstrap_url:
+            if not fragments_list and not test and live and bootstrap_url:
                 fragments_list = self._update_live_fragments(bootstrap_url, frag_i)
                 total_frags += len(fragments_list)
                 if fragments_list and (fragments_list[0][1] > frag_i + 1):

youtube_dl/downloader/fragment.py

@@ -26,7 +26,11 @@ class FragmentFD(FileDownloader):
         self._start_frag_download(ctx)
 
     def _prepare_frag_download(self, ctx):
-        self.to_screen('[%s] Total fragments: %d' % (self.FD_NAME, ctx['total_frags']))
+        if 'live' not in ctx:
+            ctx['live'] = False
+        self.to_screen(
+            '[%s] Total fragments: %s'
+            % (self.FD_NAME, ctx['total_frags'] if not ctx['live'] else 'unknown (live)'))
         self.report_destination(ctx['filename'])
         dl = HttpQuietDownloader(
             self.ydl,
@@ -59,37 +63,44 @@ class FragmentFD(FileDownloader):
             'filename': ctx['filename'],
             'tmpfilename': ctx['tmpfilename'],
         }
+
         start = time.time()
-        ctx['started'] = start
+        ctx.update({
+            'started': start,
+            # Total complete fragments downloaded so far in bytes
+            'complete_frags_downloaded_bytes': 0,
+            # Amount of fragment's bytes downloaded by the time of the previous
+            # frag progress hook invocation
+            'prev_frag_downloaded_bytes': 0,
+        })
 
         def frag_progress_hook(s):
             if s['status'] not in ('downloading', 'finished'):
                 return
 
-            frag_total_bytes = s.get('total_bytes', 0)
-            if s['status'] == 'finished':
-                state['downloaded_bytes'] += frag_total_bytes
-                state['frag_index'] += 1
-
-            estimated_size = (
-                (state['downloaded_bytes'] + frag_total_bytes) /
-                (state['frag_index'] + 1) * total_frags)
             time_now = time.time()
-            state['total_bytes_estimate'] = estimated_size
             state['elapsed'] = time_now - start
+            frag_total_bytes = s.get('total_bytes') or 0
+            if not ctx['live']:
+                estimated_size = (
+                    (ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) /
+                    (state['frag_index'] + 1) * total_frags)
+                state['total_bytes_estimate'] = estimated_size
 
             if s['status'] == 'finished':
-                progress = self.calc_percent(state['frag_index'], total_frags)
+                state['frag_index'] += 1
+                state['downloaded_bytes'] += frag_total_bytes - ctx['prev_frag_downloaded_bytes']
+                ctx['complete_frags_downloaded_bytes'] = state['downloaded_bytes']
+                ctx['prev_frag_downloaded_bytes'] = 0
             else:
                 frag_downloaded_bytes = s['downloaded_bytes']
-                frag_progress = self.calc_percent(frag_downloaded_bytes,
-                                                  frag_total_bytes)
-                progress = self.calc_percent(state['frag_index'], total_frags)
-                progress += frag_progress / float(total_frags)
-
-                state['eta'] = self.calc_eta(
-                    start, time_now, estimated_size, state['downloaded_bytes'] + frag_downloaded_bytes)
+                state['downloaded_bytes'] += frag_downloaded_bytes - ctx['prev_frag_downloaded_bytes']
+                if not ctx['live']:
+                    state['eta'] = self.calc_eta(
+                        start, time_now, estimated_size,
+                        state['downloaded_bytes'])
                 state['speed'] = s.get('speed')
+                ctx['prev_frag_downloaded_bytes'] = frag_downloaded_bytes
             self._hook_progress(state)
 
         ctx['dl'].add_progress_hook(frag_progress_hook)

youtube_dl/downloader/hls.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 import os
 import re
 import subprocess
+import sys
 
 from .common import FileDownloader
 from .fragment import FragmentFD
@@ -13,6 +14,7 @@ from ..utils import (
     encodeArgument,
     encodeFilename,
     sanitize_open,
+    handle_youtubedl_headers,
 )
 
 
@@ -30,21 +32,37 @@ class HlsFD(FileDownloader):
 
         args = [ffpp.executable, '-y']
 
-        if info_dict['http_headers']:
+        if info_dict['http_headers'] and re.match(r'^https?://', url):
             # Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
             # [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
+            headers = handle_youtubedl_headers(info_dict['http_headers'])
             args += [
                 '-headers',
-                ''.join('%s: %s\r\n' % (key, val) for key, val in info_dict['http_headers'].items())]
+                ''.join('%s: %s\r\n' % (key, val) for key, val in headers.items())]
 
-        args += ['-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc']
+        args += ['-i', url, '-c', 'copy']
+        if self.params.get('hls_use_mpegts', False):
+            args += ['-f', 'mpegts']
+        else:
+            args += ['-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
 
         args = [encodeArgument(opt) for opt in args]
         args.append(encodeFilename(ffpp._ffmpeg_filename_argument(tmpfilename), True))
 
         self._debug_cmd(args)
 
-        retval = subprocess.call(args)
+        proc = subprocess.Popen(args, stdin=subprocess.PIPE)
+        try:
+            retval = proc.wait()
+        except KeyboardInterrupt:
+            # subprocces.run would send the SIGKILL signal to ffmpeg and the
+            # mp4 file couldn't be played, but if we ask ffmpeg to quit it
+            # produces a file that is playable (this is mostly useful for live
+            # streams). Note that Windows is not affected and produces playable
+            # files (see https://github.com/rg3/youtube-dl/issues/8300).
+            if sys.platform != 'win32':
+                proc.communicate(b'q')
+            raise
         if retval == 0:
             fsize = os.path.getsize(encodeFilename(tmpfilename))
             self.to_screen('\r[%s] %s bytes' % (args[0], fsize))

youtube_dl/downloader/http.py

@@ -7,14 +7,12 @@ import time
 import re
 
 from .common import FileDownloader
-from ..compat import (
-    compat_urllib_request,
-    compat_urllib_error,
-)
+from ..compat import compat_urllib_error
 from ..utils import (
     ContentTooShortError,
     encodeFilename,
     sanitize_open,
+    sanitized_Request,
 )
 
 
@@ -29,8 +27,8 @@ class HttpFD(FileDownloader):
         add_headers = info_dict.get('http_headers')
         if add_headers:
             headers.update(add_headers)
-        basic_request = compat_urllib_request.Request(url, None, headers)
-        request = compat_urllib_request.Request(url, None, headers)
+        basic_request = sanitized_Request(url, None, headers)
+        request = sanitized_Request(url, None, headers)
 
         is_test = self.params.get('test', False)
 

youtube_dl/downloader/rtmp.py

@@ -105,7 +105,7 @@ class RtmpFD(FileDownloader):
         protocol = info_dict.get('rtmp_protocol', None)
         real_time = info_dict.get('rtmp_real_time', False)
         no_resume = info_dict.get('no_resume', False)
-        continue_dl = info_dict.get('continuedl', True)
+        continue_dl = self.params.get('continuedl', True)
 
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
@@ -117,7 +117,7 @@ class RtmpFD(FileDownloader):
             return False
 
         # Download using rtmpdump. rtmpdump returns exit code 2 when
-        # the connection was interrumpted and resuming appears to be
+        # the connection was interrupted and resuming appears to be
         # possible. This is part of rtmpdump's normal usage, AFAIK.
         basic_args = [
             'rtmpdump', '--verbose', '-r', url,

youtube_dl/extractor/__init__.py

@@ -3,13 +3,19 @@ from __future__ import unicode_literals
 from .abc import ABCIE
 from .abc7news import Abc7NewsIE
 from .academicearth import AcademicEarthCourseIE
+from .acast import (
+    ACastIE,
+    ACastChannelIE,
+)
 from .addanime import AddAnimeIE
 from .adobetv import (
     AdobeTVIE,
+    AdobeTVShowIE,
+    AdobeTVChannelIE,
     AdobeTVVideoIE,
 )
 from .adultswim import AdultSwimIE
-from .aftenposten import AftenpostenIE
+from .aenetworks import AENetworksIE
 from .aftonbladet import AftonbladetIE
 from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
@@ -20,7 +26,10 @@ from .aol import AolIE
 from .allocine import AllocineIE
 from .aparat import AparatIE
 from .appleconnect import AppleConnectIE
-from .appletrailers import AppleTrailersIE
+from .appletrailers import (
+    AppleTrailersIE,
+    AppleTrailersSectionIE,
+)
 from .archiveorg import ArchiveOrgIE
 from .ard import (
     ARDIE,
@@ -33,33 +42,43 @@ from .arte import (
     ArteTVCreativeIE,
     ArteTVConcertIE,
     ArteTVFutureIE,
+    ArteTVCinemaIE,
     ArteTVDDCIE,
     ArteTVEmbedIE,
 )
 from .atresplayer import AtresPlayerIE
 from .atttechchannel import ATTTechChannelIE
+from .audimedia import AudiMediaIE
 from .audiomack import AudiomackIE, AudiomackAlbumIE
-from .azubu import AzubuIE
+from .azubu import AzubuIE, AzubuLiveIE
 from .baidu import BaiduVideoIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbc import (
     BBCCoUkIE,
+    BBCCoUkArticleIE,
     BBCIE,
 )
 from .beeg import BeegIE
 from .behindkink import BehindKinkIE
 from .beatportpro import BeatportProIE
 from .bet import BetIE
+from .bigflix import BigflixIE
 from .bild import BildIE
 from .bilibili import BiliBiliIE
+from .bleacherreport import (
+    BleacherReportIE,
+    BleacherReportCMSIE,
+)
 from .blinkx import BlinkxIE
-from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
 from .bpb import BpbIE
 from .br import BRIE
 from .breakcom import BreakIE
-from .brightcove import BrightcoveIE
+from .brightcove import (
+    BrightcoveLegacyIE,
+    BrightcoveNewIE,
+)
 from .buzzfeed import BuzzFeedIE
 from .byutv import BYUtvIE
 from .c56 import C56IE
@@ -67,15 +86,23 @@ from .camdemy import (
     CamdemyIE,
     CamdemyFolderIE
 )
-from .canal13cl import Canal13clIE
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
+from .canvas import CanvasIE
+from .cbc import (
+    CBCIE,
+    CBCPlayerIE,
+)
 from .cbs import CBSIE
-from .cbsnews import CBSNewsIE
+from .cbsnews import (
+    CBSNewsIE,
+    CBSNewsLiveVideoIE,
+)
 from .cbssports import CBSSportsIE
 from .ccc import CCCIE
 from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
+from .chaturbate import ChaturbateIE
 from .chilloutzone import ChilloutzoneIE
 from .chirbit import (
     ChirbitIE,
@@ -88,6 +115,7 @@ from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
 from .cloudy import CloudyIE
 from .clubic import ClubicIE
+from .clyp import ClypIE
 from .cmt import CMTIE
 from .cnet import CNETIE
 from .cnn import (
@@ -102,6 +130,7 @@ from .comcarcoff import ComCarCoffIE
 from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
 from .condenast import CondeNastIE
 from .cracked import CrackedIE
+from .crackle import CrackleIE
 from .criterion import CriterionIE
 from .crooksandliars import CrooksAndLiarsIE
 from .crunchyroll import (
@@ -110,21 +139,35 @@ from .crunchyroll import (
 )
 from .cspan import CSpanIE
 from .ctsnews import CtsNewsIE
+from .cultureunplugged import CultureUnpluggedIE
+from .cwtv import CWTVIE
 from .dailymotion import (
     DailymotionIE,
     DailymotionPlaylistIE,
     DailymotionUserIE,
     DailymotionCloudIE,
 )
-from .daum import DaumIE
+from .daum import (
+    DaumIE,
+    DaumClipIE,
+    DaumPlaylistIE,
+    DaumUserIE,
+)
 from .dbtv import DBTVIE
-from .dcn import DCNIE
+from .dcn import (
+    DCNIE,
+    DCNVideoIE,
+    DCNLiveIE,
+    DCNSeasonIE,
+)
 from .dctp import DctpTvIE
 from .deezer import DeezerPlaylistIE
+from .democracynow import DemocracynowIE
 from .dfb import DFBIE
 from .dhm import DHMIE
 from .dotsub import DotsubIE
 from .douyutv import DouyuTVIE
+from .dplay import DPlayIE
 from .dramafever import (
     DramaFeverIE,
     DramaFeverSeriesIE,
@@ -163,9 +206,13 @@ from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
 from .expotv import ExpoTVIE
 from .extremetube import ExtremeTubeIE
-from .facebook import FacebookIE
+from .facebook import (
+    FacebookIE,
+    FacebookPostIE,
+)
 from .faz import FazIE
 from .fc2 import FC2IE
+from .fczenit import FczenitIE
 from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
@@ -175,10 +222,14 @@ from .flickr import FlickrIE
 from .folketinget import FolketingetIE
 from .footyroom import FootyRoomIE
 from .fourtube import FourTubeIE
+from .fox import FOXIE
 from .foxgay import FoxgayIE
 from .foxnews import FoxNewsIE
 from .foxsports import FoxSportsIE
-from .franceculture import FranceCultureIE
+from .franceculture import (
+    FranceCultureIE,
+    FranceCultureEmissionIE,
+)
 from .franceinter import FranceInterIE
 from .francetv import (
     PluzzIE,
@@ -190,7 +241,9 @@ from .francetv import (
 from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
 from .freevideo import FreeVideoIE
+from .funimation import FunimationIE
 from .funnyordie import FunnyOrDieIE
+from .gameinformer import GameInformerIE
 from .gamekings import GamekingsIE
 from .gameone import (
     GameOneIE,
@@ -207,14 +260,18 @@ from .gfycat import GfycatIE
 from .giantbomb import GiantBombIE
 from .giga import GigaIE
 from .glide import GlideIE
-from .globo import GloboIE
+from .globo import (
+    GloboIE,
+    GloboArticleIE,
+)
 from .godtube import GodTubeIE
 from .goldenmoustache import GoldenMoustacheIE
 from .golem import GolemIE
+from .googledrive import GoogleDriveIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
-from .gorillavid import GorillaVidIE
 from .goshgay import GoshgayIE
+from .gputechconf import GPUTechConfIE
 from .groupon import GrouponIE
 from .hark import HarkIE
 from .hearthisat import HearThisAtIE
@@ -223,16 +280,20 @@ from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
 from .historicfilms import HistoricFilmsIE
-from .history import HistoryIE
 from .hitbox import HitboxIE, HitboxLiveIE
 from .hornbunny import HornBunnyIE
 from .hotnewhiphop import HotNewHipHopIE
+from .hotstar import HotStarIE
 from .howcast import HowcastIE
 from .howstuffworks import HowStuffWorksIE
 from .huffpost import HuffPostIE
 from .hypem import HypemIE
 from .iconosquare import IconosquareIE
-from .ign import IGNIE, OneUPIE
+from .ign import (
+    IGNIE,
+    OneUPIE,
+    PCMagIE,
+)
 from .imdb import (
     ImdbIE,
     ImdbListIE
@@ -256,11 +317,12 @@ from .ivi import (
     IviIE,
     IviCompilationIE
 )
+from .ivideon import IvideonIE
 from .izlesene import IzleseneIE
 from .jadorecettepub import JadoreCettePubIE
 from .jeuxvideo import JeuxVideoIE
 from .jove import JoveIE
-from .jukebox import JukeboxIE
+from .jwplatform import JWPlatformIE
 from .jpopsukitv import JpopsukiIE
 from .kaltura import KalturaIE
 from .kanalplay import KanalPlayIE
@@ -271,6 +333,7 @@ from .keezmovies import KeezMoviesIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
+from .konserthusetplay import KonserthusetPlayIE
 from .kontrtube import KontrTubeIE
 from .krasview import KrasViewIE
 from .ku6 import Ku6IE
@@ -285,10 +348,12 @@ from .kuwo import (
 from .la7 import LA7IE
 from .laola1tv import Laola1TvIE
 from .lecture2go import Lecture2GoIE
+from .lemonde import LemondeIE
 from .letv import (
     LetvIE,
     LetvTvIE,
-    LetvPlaylistIE
+    LetvPlaylistIE,
+    LetvCloudIE,
 )
 from .libsyn import LibsynIE
 from .lifenews import (
@@ -307,6 +372,7 @@ from .livestream import (
     LivestreamShortenerIE,
 )
 from .lnkgo import LnkGoIE
+from .lovehomeporn import LoveHomePornIE
 from .lrt import LRTIE
 from .lynda import (
     LyndaIE,
@@ -315,9 +381,10 @@ from .lynda import (
 from .m6 import M6IE
 from .macgamestore import MacGameStoreIE
 from .mailru import MailRuIE
+from .makertv import MakerTVIE
 from .malemotion import MalemotionIE
+from .matchtv import MatchTVIE
 from .mdr import MDRIE
-from .megavideoz import MegaVideozIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
@@ -339,7 +406,6 @@ from .motherless import MotherlessIE
 from .motorsport import MotorsportIE
 from .movieclips import MovieClipsIE
 from .moviezine import MoviezineIE
-from .movshare import MovShareIE
 from .mtv import (
     MTVIE,
     MTVServicesEmbeddedIE,
@@ -392,6 +458,7 @@ from .nextmedia import (
     NextMediaActionNewsIE,
     AppleDailyIE,
 )
+from .nextmovie import NextMovieIE
 from .nfb import NFBIE
 from .nfl import NFLIE
 from .nhl import (
@@ -399,28 +466,39 @@ from .nhl import (
     NHLNewsIE,
     NHLVideocenterIE,
 )
+from .nick import NickIE
 from .niconico import NiconicoIE, NiconicoPlaylistIE
 from .ninegag import NineGagIE
 from .noco import NocoIE
 from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE
 from .nova import NovaIE
-from .novamov import NovaMovIE
+from .novamov import (
+    NovaMovIE,
+    WholeCloudIE,
+    NowVideoIE,
+    VideoWeedIE,
+    CloudTimeIE,
+)
 from .nowness import (
     NownessIE,
     NownessPlaylistIE,
     NownessSeriesIE,
 )
-from .nowtv import NowTVIE
-from .nowvideo import NowVideoIE
+from .nowtv import (
+    NowTVIE,
+    NowTVListIE,
+)
 from .npo import (
     NPOIE,
     NPOLiveIE,
     NPORadioIE,
     NPORadioFragmentIE,
+    SchoolTVIE,
     VPROIE,
     WNLIE
 )
+from .npr import NprIE
 from .nrk import (
     NRKIE,
     NRKPlaylistIE,
@@ -440,19 +518,18 @@ from .ooyala import (
     OoyalaIE,
     OoyalaExternalIE,
 )
+from .ora import OraTVIE
 from .orf import (
     ORFTVthekIE,
     ORFOE1IE,
     ORFFM4IE,
     ORFIPTVIE,
 )
+from .pandoratv import PandoraTVIE
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
-from .periscope import (
-    PeriscopeIE,
-    QuickscopeIE,
-)
+from .periscope import PeriscopeIE
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
@@ -461,6 +538,7 @@ from .planetaplay import PlanetaPlayIE
 from .pladform import PladformIE
 from .played import PlayedIE
 from .playfm import PlayFMIE
+from .plays import PlaysTVIE
 from .playtvak import PlaytvakIE
 from .playvid import PlayvidIE
 from .playwire import PlaywireIE
@@ -496,18 +574,23 @@ from .radiode import RadioDeIE
 from .radiojavan import RadioJavanIE
 from .radiobremen import RadioBremenIE
 from .radiofrance import RadioFranceIE
-from .rai import RaiIE
+from .rai import (
+    RaiTVIE,
+    RaiIE,
+)
 from .rbmaradio import RBMARadioIE
 from .rds import RDSIE
 from .redtube import RedTubeIE
+from .regiotv import RegioTVIE
 from .restudy import RestudyIE
 from .reverbnation import ReverbNationIE
+from .revision3 import Revision3IE
 from .ringtv import RingTVIE
 from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtbf import RTBFIE
-from .rte import RteIE
+from .rte import RteIE, RteRadioIE
 from .rtlnl import RtlNlIE
 from .rtl2 import RTL2IE
 from .rtp import RTPIE
@@ -515,6 +598,7 @@ from .rts import RTSIE
 from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
 from .rtvnh import RTVNHIE
 from .ruhd import RUHDIE
+from .ruleporn import RulePornIE
 from .rutube import (
     RutubeIE,
     RutubeChannelIE,
@@ -544,6 +628,10 @@ from .shahid import ShahidIE
 from .shared import SharedIE
 from .sharesix import ShareSixIE
 from .sina import SinaIE
+from .skynewsarabia import (
+    SkyNewsArabiaIE,
+    SkyNewsArabiaArticleIE,
+)
 from .slideshare import SlideshareIE
 from .slutload import SlutloadIE
 from .smotri import (
@@ -558,15 +646,12 @@ from .snagfilms import (
 )
 from .snotr import SnotrIE
 from .sohu import SohuIE
-from .soompi import (
-    SoompiIE,
-    SoompiShowIE,
-)
 from .soundcloud import (
     SoundcloudIE,
     SoundcloudSetIE,
     SoundcloudUserIE,
-    SoundcloudPlaylistIE
+    SoundcloudPlaylistIE,
+    SoundcloudSearchIE
 )
 from .soundgasm import (
     SoundgasmIE,
@@ -585,13 +670,17 @@ from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
+from .stitcher import StitcherIE
 from .sport5 import Sport5IE
 from .sportbox import (
     SportBoxIE,
     SportBoxEmbedIE,
 )
 from .sportdeutschland import SportDeutschlandIE
-from .srf import SrfIE
+from .srgssr import (
+    SRGSSRIE,
+    SRGSSRPlayIE,
+)
 from .srmediathek import SRMediathekIE
 from .ssa import SSAIE
 from .stanfordoc import StanfordOpenClassroomIE
@@ -618,6 +707,7 @@ from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
+from .tele13 import Tele13IE
 from .telebruxelles import TeleBruxellesIE
 from .telecinco import TelecincoIE
 from .telegraaf import TelegraafIE
@@ -625,8 +715,8 @@ from .telemb import TeleMBIE
 from .teletask import TeleTaskIE
 from .tenplay import TenPlayIE
 from .testurl import TestURLIE
-from .testtube import TestTubeIE
 from .tf1 import TF1IE
+from .theintercept import TheInterceptIE
 from .theonion import TheOnionIE
 from .theplatform import (
     ThePlatformIE,
@@ -636,7 +726,7 @@ from .thesixtyone import TheSixtyOneIE
 from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
-from .tlc import TlcIE, TlcDeIE
+from .tlc import TlcDeIE
 from .tmz import (
     TMZIE,
     TMZArticleIE,
@@ -646,6 +736,7 @@ from .tnaflix import (
     EMPFlixIE,
     MovieFapIE,
 )
+from .toggle import ToggleIE
 from .thvideo import (
     THVideoIE,
     THVideoPlaylistIE
@@ -654,12 +745,23 @@ from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
+from .trollvids import TrollvidsIE
 from .trutube import TruTubeIE
 from .tube8 import Tube8IE
 from .tubitv import TubiTvIE
-from .tudou import TudouIE
+from .tudou import (
+    TudouIE,
+    TudouPlaylistIE,
+    TudouAlbumIE,
+)
 from .tumblr import TumblrIE
-from .tunein import TuneInIE
+from .tunein import (
+    TuneInClipIE,
+    TuneInStationIE,
+    TuneInProgramIE,
+    TuneInTopicIE,
+    TuneInShortenerIE,
+)
 from .turbo import TurboIE
 from .tutv import TutvIE
 from .tv2 import (
@@ -672,10 +774,12 @@ from .tvc import (
     TVCArticleIE,
 )
 from .tvigle import TvigleIE
+from .tvland import TVLandIE
 from .tvp import TvpIE, TvpSeriesIE
 from .tvplay import TVPlayIE
 from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
+from .twentymin import TwentyMinutenIE
 from .twentytwotracks import (
     TwentyTwoTracksIE,
     TwentyTwoTracksGenreIE
@@ -689,14 +793,14 @@ from .twitch import (
     TwitchBookmarksIE,
     TwitchStreamIE,
 )
-from .twitter import TwitterCardIE
+from .twitter import TwitterCardIE, TwitterIE
 from .ubu import UbuIE
 from .udemy import (
     UdemyIE,
     UdemyCourseIE
 )
 from .udn import UDNEmbedIE
-from .ultimedia import UltimediaIE
+from .digiteka import DigitekaIE
 from .unistra import UnistraIE
 from .urort import UrortIE
 from .ustream import UstreamIE, UstreamChannelIE
@@ -716,16 +820,24 @@ from .vh1 import VH1IE
 from .vice import ViceIE
 from .viddler import ViddlerIE
 from .videodetective import VideoDetectiveIE
-from .videolecturesnet import VideoLecturesNetIE
 from .videofyme import VideofyMeIE
 from .videomega import VideoMegaIE
+from .videomore import (
+    VideomoreIE,
+    VideomoreVideoIE,
+    VideomoreSeasonIE,
+)
 from .videopremium import VideoPremiumIE
 from .videott import VideoTtIE
-from .videoweed import VideoWeedIE
-from .vidme import VidmeIE
+from .vidme import (
+    VidmeIE,
+    VidmeUserIE,
+    VidmeUserLikesIE,
+)
 from .vidzi import VidziIE
 from .vier import VierIE, VierVideosIE
 from .viewster import ViewsterIE
+from .viidea import ViideaIE
 from .vimeo import (
     VimeoIE,
     VimeoAlbumIE,
@@ -771,6 +883,7 @@ from .webofstories import (
     WebOfStoriesPlaylistIE,
 )
 from .weibo import WeiboIE
+from .weiqitv import WeiqiTVIE
 from .wimp import WimpIE
 from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
@@ -778,6 +891,7 @@ from .wrzuta import WrzutaIE
 from .wsj import WSJIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
+from .xfileshare import XFileShareIE
 from .xhamster import (
     XHamsterIE,
     XHamsterEmbedIE,
@@ -821,6 +935,7 @@ from .youtube import (
     YoutubeTruncatedIDIE,
     YoutubeTruncatedURLIE,
     YoutubeUserIE,
+    YoutubePlaylistsIE,
     YoutubeWatchLaterIE,
 )
 from .zapiks import ZapiksIE
@@ -829,6 +944,7 @@ from .zingmp3 import (
     ZingMp3SongIE,
     ZingMp3AlbumIE,
 )
+from .zippcast import ZippCastIE
 
 _ALL_CLASSES = [
     klass

youtube_dl/extractor/abc.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class ABCIE(InfoExtractor):
     IE_NAME = 'abc.net.au'
-    _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'http://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
@@ -23,6 +23,7 @@ class ABCIE(InfoExtractor):
             'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
             'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
         },
+        'skip': 'this video has expired',
     }, {
         'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
         'md5': 'db2a5369238b51f9811ad815b69dc086',
@@ -36,6 +37,19 @@ class ABCIE(InfoExtractor):
             'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
         },
         'add_ie': ['Youtube'],
+        'skip': 'Not accessible from Travis CI server',
+    }, {
+        'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
+        'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
+        'info_dict': {
+            'id': '6880080',
+            'ext': 'mp3',
+            'title': 'NAB lifts interest rates, following Westpac and CBA',
+            'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
+        },
+    }, {
+        'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -43,9 +57,12 @@ class ABCIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         mobj = re.search(
-            r'inline(?P<type>Video|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
+            r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
             webpage)
         if mobj is None:
+            expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>', webpage, 'expired', None)
+            if expired:
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True)
             raise ExtractorError('Unable to extract video urls')
 
         urls_info = self._parse_json(
@@ -60,11 +77,13 @@ class ABCIE(InfoExtractor):
 
         formats = [{
             'url': url_info['url'],
+            'vcodec': url_info.get('codec') if mobj.group('type') == 'Video' else 'none',
             'width': int_or_none(url_info.get('width')),
             'height': int_or_none(url_info.get('height')),
             'tbr': int_or_none(url_info.get('bitrate')),
             'filesize': int_or_none(url_info.get('filesize')),
         } for url_info in urls_info]
+
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/abc7news.py

@@ -44,7 +44,6 @@ class Abc7NewsIE(InfoExtractor):
             'contentURL', webpage, 'm3u8 url', fatal=True)
 
         formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
-        self._sort_formats(formats)
 
         title = self._og_search_title(webpage).strip()
         description = self._og_search_description(webpage).strip()

youtube_dl/extractor/acast.py

@@ -0,0 +1,72 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import int_or_none
+
+
+class ACastIE(InfoExtractor):
+    IE_NAME = 'acast'
+    _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
+    _TEST = {
+        'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
+        'md5': 'ada3de5a1e3a2a381327d749854788bb',
+        'info_dict': {
+            'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
+            'ext': 'mp3',
+            'title': '"Where Are You?": Taipei 101, Taiwan',
+            'timestamp': 1196172000000,
+            'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
+            'duration': 211,
+        }
+    }
+
+    def _real_extract(self, url):
+        channel, display_id = re.match(self._VALID_URL, url).groups()
+
+        embed_page = self._download_webpage(
+            re.sub('(?:www\.)?acast\.com', 'embedcdn.acast.com', url), display_id)
+        cast_data = self._parse_json(self._search_regex(
+            r'window\[\'acast/queries\'\]\s*=\s*([^;]+);', embed_page, 'acast data'),
+            display_id)['GetAcast/%s/%s' % (channel, display_id)]
+
+        return {
+            'id': compat_str(cast_data['id']),
+            'display_id': display_id,
+            'url': cast_data['blings'][0]['audio'],
+            'title': cast_data['name'],
+            'description': cast_data.get('description'),
+            'thumbnail': cast_data.get('image'),
+            'timestamp': int_or_none(cast_data.get('publishingDate')),
+            'duration': int_or_none(cast_data.get('duration')),
+        }
+
+
+class ACastChannelIE(InfoExtractor):
+    IE_NAME = 'acast:channel'
+    _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
+    _TEST = {
+        'url': 'https://www.acast.com/condenasttraveler',
+        'info_dict': {
+            'id': '50544219-29bb-499e-a083-6087f4cb7797',
+            'title': 'Condé Nast Traveler Podcast',
+            'description': 'md5:98646dee22a5b386626ae31866638fbd',
+        },
+        'playlist_mincount': 20,
+    }
+    _API_BASE_URL = 'https://www.acast.com/api/'
+
+    @classmethod
+    def suitable(cls, url):
+        return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id)
+        casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id)
+        entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts]
+
+        return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description'))

youtube_dl/extractor/adobetv.py

@@ -1,23 +1,32 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     parse_duration,
     unified_strdate,
     str_to_int,
+    int_or_none,
     float_or_none,
     ISO639Utils,
+    determine_ext,
 )
 
 
-class AdobeTVIE(InfoExtractor):
-    _VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)'
+class AdobeTVBaseIE(InfoExtractor):
+    _API_BASE_URL = 'http://tv.adobe.com/api/v4/'
+
+
+class AdobeTVIE(AdobeTVBaseIE):
+    _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
 
     _TEST = {
         'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
         'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
         'info_dict': {
-            'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop',
+            'id': '10981',
             'ext': 'mp4',
             'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
             'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
@@ -29,50 +38,106 @@ class AdobeTVIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        language, show_urlname, urlname = re.match(self._VALID_URL, url).groups()
+        if not language:
+            language = 'en'
 
-        player = self._parse_json(
-            self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'),
-            video_id)
-
-        title = player.get('title') or self._search_regex(
-            r'data-title="([^"]+)"', webpage, 'title')
-        description = self._og_search_description(webpage)
-        thumbnail = self._og_search_thumbnail(webpage)
-
-        upload_date = unified_strdate(
-            self._html_search_meta('datepublished', webpage, 'upload date'))
-
-        duration = parse_duration(
-            self._html_search_meta('duration', webpage, 'duration') or
-            self._search_regex(
-                r'Runtime:\s*(\d{2}:\d{2}:\d{2})',
-                webpage, 'duration', fatal=False))
-
-        view_count = str_to_int(self._search_regex(
-            r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>',
-            webpage, 'view count'))
+        video_data = self._download_json(
+            self._API_BASE_URL + 'episode/get/?language=%s&show_urlname=%s&urlname=%s&disclosure=standard' % (language, show_urlname, urlname),
+            urlname)['data'][0]
 
         formats = [{
-            'url': source['src'],
-            'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None,
-            'tbr': source.get('bitrate'),
-        } for source in player['sources']]
+            'url': source['url'],
+            'format_id': source.get('quality_level') or source['url'].split('-')[-1].split('.')[0] or None,
+            'width': int_or_none(source.get('width')),
+            'height': int_or_none(source.get('height')),
+            'tbr': int_or_none(source.get('video_data_rate')),
+        } for source in video_data['videos']]
         self._sort_formats(formats)
 
         return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'upload_date': upload_date,
-            'duration': duration,
-            'view_count': view_count,
+            'id': compat_str(video_data['id']),
+            'title': video_data['title'],
+            'description': video_data.get('description'),
+            'thumbnail': video_data.get('thumbnail'),
+            'upload_date': unified_strdate(video_data.get('start_date')),
+            'duration': parse_duration(video_data.get('duration')),
+            'view_count': str_to_int(video_data.get('playcount')),
             'formats': formats,
         }
 
 
+class AdobeTVPlaylistBaseIE(AdobeTVBaseIE):
+    def _parse_page_data(self, page_data):
+        return [self.url_result(self._get_element_url(element_data)) for element_data in page_data]
+
+    def _extract_playlist_entries(self, url, display_id):
+        page = self._download_json(url, display_id)
+        entries = self._parse_page_data(page['data'])
+        for page_num in range(2, page['paging']['pages'] + 1):
+            entries.extend(self._parse_page_data(
+                self._download_json(url + '&page=%d' % page_num, display_id)['data']))
+        return entries
+
+
+class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
+    _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
+
+    _TEST = {
+        'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost',
+        'info_dict': {
+            'id': '36',
+            'title': 'The Complete Picture with Julieanne Kost',
+            'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27',
+        },
+        'playlist_mincount': 136,
+    }
+
+    def _get_element_url(self, element_data):
+        return element_data['urls'][0]
+
+    def _real_extract(self, url):
+        language, show_urlname = re.match(self._VALID_URL, url).groups()
+        if not language:
+            language = 'en'
+        query = 'language=%s&show_urlname=%s' % (language, show_urlname)
+
+        show_data = self._download_json(self._API_BASE_URL + 'show/get/?%s' % query, show_urlname)['data'][0]
+
+        return self.playlist_result(
+            self._extract_playlist_entries(self._API_BASE_URL + 'episode/?%s' % query, show_urlname),
+            compat_str(show_data['id']),
+            show_data['show_name'],
+            show_data['show_description'])
+
+
+class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
+    _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
+
+    _TEST = {
+        'url': 'http://tv.adobe.com/channel/development',
+        'info_dict': {
+            'id': 'development',
+        },
+        'playlist_mincount': 96,
+    }
+
+    def _get_element_url(self, element_data):
+        return element_data['url']
+
+    def _real_extract(self, url):
+        language, channel_urlname, category_urlname = re.match(self._VALID_URL, url).groups()
+        if not language:
+            language = 'en'
+        query = 'language=%s&channel_urlname=%s' % (language, channel_urlname)
+        if category_urlname:
+            query += '&category_urlname=%s' % category_urlname
+
+        return self.playlist_result(
+            self._extract_playlist_entries(self._API_BASE_URL + 'show/?%s' % query, channel_urlname),
+            channel_urlname)
+
+
 class AdobeTVVideoIE(InfoExtractor):
     _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
 
@@ -91,28 +156,25 @@ class AdobeTVVideoIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        player_params = self._parse_json(self._search_regex(
-            r'var\s+bridge\s*=\s*([^;]+);', webpage, 'player parameters'),
-            video_id)
+        video_data = self._download_json(url + '?format=json', video_id)
 
         formats = [{
+            'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')),
             'url': source['src'],
-            'width': source.get('width'),
-            'height': source.get('height'),
-            'tbr': source.get('bitrate'),
-        } for source in player_params['sources']]
+            'width': int_or_none(source.get('width')),
+            'height': int_or_none(source.get('height')),
+            'tbr': int_or_none(source.get('bitrate')),
+        } for source in video_data['sources']]
+        self._sort_formats(formats)
 
         # For both metadata and downloaded files the duration varies among
         # formats. I just pick the max one
         duration = max(filter(None, [
             float_or_none(source.get('duration'), scale=1000)
-            for source in player_params['sources']]))
+            for source in video_data['sources']]))
 
         subtitles = {}
-        for translation in player_params.get('translations', []):
+        for translation in video_data.get('translations', []):
             lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
             if lang_id not in subtitles:
                 subtitles[lang_id] = []
@@ -124,8 +186,9 @@ class AdobeTVVideoIE(InfoExtractor):
         return {
             'id': video_id,
             'formats': formats,
-            'title': player_params['title'],
-            'description': self._og_search_description(webpage),
+            'title': video_data['title'],
+            'description': video_data.get('description'),
+            'thumbnail': video_data['video'].get('poster'),
             'duration': duration,
             'subtitles': subtitles,
         }

youtube_dl/extractor/adultswim.py

@@ -41,7 +41,8 @@ class AdultSwimIE(InfoExtractor):
             'id': 'rQxZvXQ4ROaSOqq-or2Mow',
             'title': 'Rick and Morty - Pilot',
             'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
-        }
+        },
+        'skip': 'This video is only available for registered users',
     }, {
         'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
         'playlist': [
@@ -67,7 +68,7 @@ class AdultSwimIE(InfoExtractor):
                 'md5': '3e346a2ab0087d687a05e1e7f3b3e529',
                 'info_dict': {
                     'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0',
-                    'ext': 'flv',
+                    'ext': 'mp4',
                     'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
                     'description': 'Dr. Brule reports live from Wine Country with a special report on wines.  \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
                 },
@@ -78,6 +79,10 @@ class AdultSwimIE(InfoExtractor):
             'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
             'description': 'Dr. Brule reports live from Wine Country with a special report on wines.  \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
         },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
     }]
 
     @staticmethod
@@ -134,7 +139,13 @@ class AdultSwimIE(InfoExtractor):
             show = bootstrapped_data['show']
             show_title = show['title']
             stream = video_info.get('stream')
-            clips = [stream] if stream else video_info['clips']
+            clips = [stream] if stream else video_info.get('clips')
+            if not clips:
+                raise ExtractorError(
+                    'This video is only available via cable service provider subscription that'
+                    ' is not currently supported. You may want to use --cookies.'
+                    if video_info.get('auth') is True else 'Unable to find stream or clips',
+                    expected=True)
             segment_ids = [clip['videoPlaybackID'] for clip in clips]
 
         episode_id = video_info['id']
@@ -176,7 +187,8 @@ class AdultSwimIE(InfoExtractor):
                 media_url = file_el.text
                 if determine_ext(media_url) == 'm3u8':
                     formats.extend(self._extract_m3u8_formats(
-                        media_url, segment_title, 'mp4', 'm3u8_native', preference=0, m3u8_id='hls'))
+                        media_url, segment_title, 'mp4', preference=0,
+                        m3u8_id='hls', fatal=False))
                 else:
                     formats.append({
                         'format_id': '%s_%s' % (bitrate, ftype),

youtube_dl/extractor/aenetworks.py

@@ -0,0 +1,66 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import smuggle_url
+
+
+class AENetworksIE(InfoExtractor):
+    IE_NAME = 'aenetworks'
+    IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
+    _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])'
+
+    _TESTS = [{
+        'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
+        'info_dict': {
+            'id': 'g12m5Gyt3fdR',
+            'ext': 'mp4',
+            'title': "Bet You Didn't Know: Valentine's Day",
+            'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'add_ie': ['ThePlatform'],
+        'expected_warnings': ['JSON-LD'],
+    }, {
+        'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
+        'info_dict': {
+            'id': 'eg47EERs_JsZ',
+            'ext': 'mp4',
+            'title': "Winter Is Coming",
+            'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'add_ie': ['ThePlatform'],
+    }, {
+        'url': 'http://www.aetv.com/shows/duck-dynasty/video/inlawful-entry',
+        'only_matching': True
+    }, {
+        'url': 'http://www.fyi.tv/shows/tiny-house-nation/videos/207-sq-ft-minnesota-prairie-cottage',
+        'only_matching': True
+    }, {
+        'url': 'http://www.mylifetime.com/shows/project-runway-junior/video/season-1/episode-6/superstar-clients',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url_re = [
+            r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id,
+            r"media_url\s*=\s*'([^']+)'"
+        ]
+        video_url = self._search_regex(video_url_re, webpage, 'video url')
+
+        info = self._search_json_ld(webpage, video_id, fatal=False)
+        info.update({
+            '_type': 'url_transparent',
+            'url': smuggle_url(video_url, {'sig': {'key': 'crazyjava', 'secret': 's3cr3t'}}),
+        })
+        return info

youtube_dl/extractor/aftenposten.py

@@ -1,23 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-
-
-class AftenpostenIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/(?:#!/)?video/(?P<id>\d+)'
-    _TEST = {
-        'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
-        'md5': 'fd828cd29774a729bf4d4425fe192972',
-        'info_dict': {
-            'id': '21039',
-            'ext': 'mov',
-            'title': 'TRAILER: "Sweatshop" - I can´t take any more',
-            'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238',
-            'timestamp': 1416927969,
-            'upload_date': '20141125',
-        }
-    }
-
-    def _real_extract(self, url):
-        return self.url_result('xstream:ap:%s' % self._match_id(url), 'Xstream')

youtube_dl/extractor/aljazeera.py

@@ -15,7 +15,7 @@ class AlJazeeraIE(InfoExtractor):
             'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.',
             'uploader': 'Al Jazeera English',
         },
-        'add_ie': ['Brightcove'],
+        'add_ie': ['BrightcoveLegacy'],
         'skip': 'Not accessible from Travis CI server',
     }
 
@@ -32,5 +32,5 @@ class AlJazeeraIE(InfoExtractor):
                 'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc'
                 '&%40videoPlayer={0}'.format(brightcove_id)
             ),
-            'ie_key': 'Brightcove',
+            'ie_key': 'BrightcoveLegacy',
         }

youtube_dl/extractor/allocine.py

@@ -8,6 +8,8 @@ from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
     qualities,
+    unescapeHTML,
+    xpath_element,
 )
 
 
@@ -31,7 +33,7 @@ class AllocineIE(InfoExtractor):
             'id': '19540403',
             'ext': 'mp4',
             'title': 'Planes 2 Bande-annonce VF',
-            'description': 'md5:eeaffe7c2d634525e21159b93acf3b1e',
+            'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {
@@ -41,7 +43,7 @@ class AllocineIE(InfoExtractor):
             'id': '19544709',
             'ext': 'mp4',
             'title': 'Dragons 2 - Bande annonce finale VF',
-            'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac',
+            'description': 'md5:601d15393ac40f249648ef000720e7e3',
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {
@@ -59,14 +61,18 @@ class AllocineIE(InfoExtractor):
         if typ == 'film':
             video_id = self._search_regex(r'href="/video/player_gen_cmedia=([0-9]+).+"', webpage, 'video id')
         else:
-            player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player')
-
-            player_data = json.loads(player)
-            video_id = compat_str(player_data['refMedia'])
+            player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player', default=None)
+            if player:
+                player_data = json.loads(player)
+                video_id = compat_str(player_data['refMedia'])
+            else:
+                model = self._search_regex(r'data-model="([^"]+)">', webpage, 'data model')
+                model_data = self._parse_json(unescapeHTML(model), display_id)
+                video_id = compat_str(model_data['id'])
 
         xml = self._download_xml('http://www.allocine.fr/ws/AcVisiondataV4.ashx?media=%s' % video_id, display_id)
 
-        video = xml.find('.//AcVisionVideo').attrib
+        video = xpath_element(xml, './/AcVisionVideo').attrib
         quality = qualities(['ld', 'md', 'hd'])
 
         formats = []

youtube_dl/extractor/amp.py

@@ -0,0 +1,81 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class AMPIE(InfoExtractor):
+    # parse Akamai Adaptive Media Player feed
+    def _extract_feed_info(self, url):
+        item = self._download_json(
+            url, None, 'Downloading Akamai AMP feed',
+            'Unable to download Akamai AMP feed')['channel']['item']
+
+        video_id = item['guid']
+
+        def get_media_node(name, default=None):
+            media_name = 'media-%s' % name
+            media_group = item.get('media-group') or item
+            return media_group.get(media_name) or item.get(media_name) or item.get(name, default)
+
+        thumbnails = []
+        media_thumbnail = get_media_node('thumbnail')
+        if media_thumbnail:
+            if isinstance(media_thumbnail, dict):
+                media_thumbnail = [media_thumbnail]
+            for thumbnail_data in media_thumbnail:
+                thumbnail = thumbnail_data['@attributes']
+                thumbnails.append({
+                    'url': self._proto_relative_url(thumbnail['url'], 'http:'),
+                    'width': int_or_none(thumbnail.get('width')),
+                    'height': int_or_none(thumbnail.get('height')),
+                })
+
+        subtitles = {}
+        media_subtitle = get_media_node('subTitle')
+        if media_subtitle:
+            if isinstance(media_subtitle, dict):
+                media_subtitle = [media_subtitle]
+            for subtitle_data in media_subtitle:
+                subtitle = subtitle_data['@attributes']
+                lang = subtitle.get('lang') or 'en'
+                subtitles[lang] = [{'url': subtitle['href']}]
+
+        formats = []
+        media_content = get_media_node('content')
+        if isinstance(media_content, dict):
+            media_content = [media_content]
+        for media_data in media_content:
+            media = media_data['@attributes']
+            media_type = media['type']
+            if media_type == 'video/f4m':
+                formats.extend(self._extract_f4m_formats(
+                    media['url'] + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124',
+                    video_id, f4m_id='hds', fatal=False))
+            elif media_type == 'application/x-mpegURL':
+                formats.extend(self._extract_m3u8_formats(
+                    media['url'], video_id, 'mp4', m3u8_id='hls', fatal=False))
+            else:
+                formats.append({
+                    'format_id': media_data['media-category']['@attributes']['label'],
+                    'url': media['url'],
+                    'tbr': int_or_none(media.get('bitrate')),
+                    'filesize': int_or_none(media.get('fileSize')),
+                })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': get_media_node('title'),
+            'description': get_media_node('description'),
+            'thumbnails': thumbnails,
+            'timestamp': parse_iso8601(item.get('pubDate'), ' '),
+            'duration': int_or_none(media_content[0].get('@attributes', {}).get('duration')),
+            'subtitles': subtitles,
+            'formats': formats,
+        }

youtube_dl/extractor/anitube.py

@@ -1,11 +1,9 @@
 from __future__ import unicode_literals
 
-import re
-
-from .common import InfoExtractor
+from .nuevo import NuevoBaseIE
 
 
-class AnitubeIE(InfoExtractor):
+class AnitubeIE(NuevoBaseIE):
     IE_NAME = 'anitube.se'
     _VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
 
@@ -22,38 +20,11 @@ class AnitubeIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        key = self._html_search_regex(
-            r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)', webpage, 'key')
+        key = self._search_regex(
+            r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key')
 
-        config_xml = self._download_xml(
-            'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key)
-
-        video_title = config_xml.find('title').text
-        thumbnail = config_xml.find('image').text
-        duration = float(config_xml.find('duration').text)
-
-        formats = []
-        video_url = config_xml.find('file')
-        if video_url is not None:
-            formats.append({
-                'format_id': 'sd',
-                'url': video_url.text,
-            })
-        video_url = config_xml.find('filehd')
-        if video_url is not None:
-            formats.append({
-                'format_id': 'hd',
-                'url': video_url.text,
-            })
-
-        return {
-            'id': video_id,
-            'title': video_title,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'formats': formats
-        }
+        return self._extract_nuevo(
+            'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, video_id)

youtube_dl/extractor/appletrailers.py

@@ -11,6 +11,7 @@ from ..utils import (
 
 
 class AppleTrailersIE(InfoExtractor):
+    IE_NAME = 'appletrailers'
     _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)'
     _TESTS = [{
         'url': 'http://trailers.apple.com/trailers/wb/manofsteel/',
@@ -63,6 +64,12 @@ class AppleTrailersIE(InfoExtractor):
                 },
             },
         ]
+    }, {
+        'url': 'http://trailers.apple.com/trailers/magnolia/blackthorn/',
+        'info_dict': {
+            'id': 'blackthorn',
+        },
+        'playlist_mincount': 2,
     }, {
         'url': 'http://trailers.apple.com/ca/metropole/autrui/',
         'only_matching': True,
@@ -79,7 +86,7 @@ class AppleTrailersIE(InfoExtractor):
 
         def fix_html(s):
             s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
-            s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
+            s = re.sub(r'<img ([^<]*?)/?>', r'<img \1/>', s)
             # The ' in the onClick attributes are not escaped, it couldn't be parsed
             # like: http://trailers.apple.com/trailers/wb/gravity/
 
@@ -96,6 +103,9 @@ class AppleTrailersIE(InfoExtractor):
             trailer_info_json = self._search_regex(self._JSON_RE,
                                                    on_click, 'trailer info')
             trailer_info = json.loads(trailer_info_json)
+            first_url = trailer_info.get('url')
+            if not first_url:
+                continue
             title = trailer_info['title']
             video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
             thumbnail = li.find('.//img').attrib['src']
@@ -107,7 +117,6 @@ class AppleTrailersIE(InfoExtractor):
             if m:
                 duration = 60 * int(m.group('minutes')) + int(m.group('seconds'))
 
-            first_url = trailer_info['url']
             trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower()
             settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id)
             settings = self._download_json(settings_json_url, trailer_id, 'Downloading settings json')
@@ -144,3 +153,76 @@ class AppleTrailersIE(InfoExtractor):
             'id': movie,
             'entries': playlist,
         }
+
+
+class AppleTrailersSectionIE(InfoExtractor):
+    IE_NAME = 'appletrailers:section'
+    _SECTIONS = {
+        'justadded': {
+            'feed_path': 'just_added',
+            'title': 'Just Added',
+        },
+        'exclusive': {
+            'feed_path': 'exclusive',
+            'title': 'Exclusive',
+        },
+        'justhd': {
+            'feed_path': 'just_hd',
+            'title': 'Just HD',
+        },
+        'mostpopular': {
+            'feed_path': 'most_pop',
+            'title': 'Most Popular',
+        },
+        'moviestudios': {
+            'feed_path': 'studios',
+            'title': 'Movie Studios',
+        },
+    }
+    _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/#section=(?P<id>%s)' % '|'.join(_SECTIONS)
+    _TESTS = [{
+        'url': 'http://trailers.apple.com/#section=justadded',
+        'info_dict': {
+            'title': 'Just Added',
+            'id': 'justadded',
+        },
+        'playlist_mincount': 80,
+    }, {
+        'url': 'http://trailers.apple.com/#section=exclusive',
+        'info_dict': {
+            'title': 'Exclusive',
+            'id': 'exclusive',
+        },
+        'playlist_mincount': 80,
+    }, {
+        'url': 'http://trailers.apple.com/#section=justhd',
+        'info_dict': {
+            'title': 'Just HD',
+            'id': 'justhd',
+        },
+        'playlist_mincount': 80,
+    }, {
+        'url': 'http://trailers.apple.com/#section=mostpopular',
+        'info_dict': {
+            'title': 'Most Popular',
+            'id': 'mostpopular',
+        },
+        'playlist_mincount': 80,
+    }, {
+        'url': 'http://trailers.apple.com/#section=moviestudios',
+        'info_dict': {
+            'title': 'Movie Studios',
+            'id': 'moviestudios',
+        },
+        'playlist_mincount': 80,
+    }]
+
+    def _real_extract(self, url):
+        section = self._match_id(url)
+        section_data = self._download_json(
+            'http://trailers.apple.com/trailers/home/feeds/%s.json' % self._SECTIONS[section]['feed_path'],
+            section)
+        entries = [
+            self.url_result('http://trailers.apple.com' + e['location'])
+            for e in section_data]
+        return self.playlist_result(entries, section, self._SECTIONS[section]['title'])

youtube_dl/extractor/ard.py

@@ -14,8 +14,8 @@ from ..utils import (
     parse_duration,
     unified_strdate,
     xpath_text,
-    parse_xml,
 )
+from ..compat import compat_etree_fromstring
 
 
 class ARDMediathekIE(InfoExtractor):
@@ -110,13 +110,15 @@ class ARDMediathekIE(InfoExtractor):
                 server = stream.get('_server')
                 for stream_url in stream_urls:
                     ext = determine_ext(stream_url)
+                    if quality != 'auto' and ext in ('f4m', 'm3u8'):
+                        continue
                     if ext == 'f4m':
                         formats.extend(self._extract_f4m_formats(
                             stream_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
-                            video_id, preference=-1, f4m_id='hds'))
+                            video_id, preference=-1, f4m_id='hds', fatal=False))
                     elif ext == 'm3u8':
                         formats.extend(self._extract_m3u8_formats(
-                            stream_url, video_id, 'mp4', preference=1, m3u8_id='hls'))
+                            stream_url, video_id, 'mp4', preference=1, m3u8_id='hls', fatal=False))
                     else:
                         if server and server.startswith('rtmp'):
                             f = {
@@ -161,7 +163,7 @@ class ARDMediathekIE(InfoExtractor):
             raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
 
         if re.search(r'[\?&]rss($|[=&])', url):
-            doc = parse_xml(webpage)
+            doc = compat_etree_fromstring(webpage.encode('utf-8'))
             if doc.tag == 'rss':
                 return GenericIE()._extract_rss(url, video_id, doc)
 

youtube_dl/extractor/arte.py

@@ -13,6 +13,7 @@ from ..utils import (
     unified_strdate,
     get_element_by_attribute,
     int_or_none,
+    NO_DEFAULT,
     qualities,
 )
 
@@ -68,9 +69,13 @@ class ArteTVPlus7IE(InfoExtractor):
     def _extract_url_info(cls, url):
         mobj = re.match(cls._VALID_URL, url)
         lang = mobj.group('lang')
-        # This is not a real id, it can be for example AJT for the news
-        # http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
-        video_id = mobj.group('id')
+        query = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        if 'vid' in query:
+            video_id = query['vid'][0]
+        else:
+            # This is not a real id, it can be for example AJT for the news
+            # http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
+            video_id = mobj.group('id')
         return video_id, lang
 
     def _real_extract(self, url):
@@ -79,13 +84,28 @@ class ArteTVPlus7IE(InfoExtractor):
         return self._extract_from_webpage(webpage, video_id, lang)
 
     def _extract_from_webpage(self, webpage, video_id, lang):
+        patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']')
+        ids = (video_id, '')
+        # some pages contain multiple videos (like
+        # http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D),
+        # so we first try to look for json URLs that contain the video id from
+        # the 'vid' parameter.
+        patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates]
         json_url = self._html_search_regex(
-            [r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'],
-            webpage, 'json vp url', default=None)
+            patterns, webpage, 'json vp url', default=None)
         if not json_url:
-            iframe_url = self._html_search_regex(
-                r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
-                webpage, 'iframe url', group='url')
+            def find_iframe_url(webpage, default=NO_DEFAULT):
+                return self._html_search_regex(
+                    r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
+                    webpage, 'iframe url', group='url', default=default)
+
+            iframe_url = find_iframe_url(webpage, None)
+            if not iframe_url:
+                embed_url = self._html_search_regex(
+                    r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url')
+                player = self._download_json(
+                    embed_url, video_id, 'Downloading player page')
+                iframe_url = find_iframe_url(player['html'])
             json_url = compat_parse_qs(
                 compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
         return self._extract_from_json_url(json_url, video_id, lang)
@@ -189,25 +209,19 @@ class ArteTVCreativeIE(ArteTVPlus7IE):
 
 class ArteTVFutureIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:future'
-    _VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de)/(thema|sujet)/.*?#article-anchor-(?P<id>\d+)'
+    _VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de)/(?P<id>.+)'
 
-    _TEST = {
-        'url': 'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081',
+    _TESTS = [{
+        'url': 'http://future.arte.tv/fr/info-sciences/les-ecrevisses-aussi-sont-anxieuses',
         'info_dict': {
-            'id': '5201',
+            'id': '050940-028-A',
             'ext': 'mp4',
-            'title': 'Les champignons au secours de la planète',
-            'upload_date': '20131101',
+            'title': 'Les écrevisses aussi peuvent être anxieuses',
         },
-    }
-
-    def _real_extract(self, url):
-        anchor_id, lang = self._extract_url_info(url)
-        webpage = self._download_webpage(url, anchor_id)
-        row = self._search_regex(
-            r'(?s)id="%s"[^>]*>.+?(<div[^>]*arte_vp_url[^>]*>)' % anchor_id,
-            webpage, 'row')
-        return self._extract_from_webpage(row, anchor_id, lang)
+    }, {
+        'url': 'http://future.arte.tv/fr/la-science-est-elle-responsable',
+        'only_matching': True,
+    }]
 
 
 class ArteTVDDCIE(ArteTVPlus7IE):
@@ -245,6 +259,23 @@ class ArteTVConcertIE(ArteTVPlus7IE):
     }
 
 
+class ArteTVCinemaIE(ArteTVPlus7IE):
+    IE_NAME = 'arte.tv:cinema'
+    _VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>de|fr)/(?P<id>.+)'
+
+    _TEST = {
+        'url': 'http://cinema.arte.tv/de/node/38291',
+        'md5': '6b275511a5107c60bacbeeda368c3aa1',
+        'info_dict': {
+            'id': '055876-000_PWA12025-D',
+            'ext': 'mp4',
+            'title': 'Tod auf dem Nil',
+            'upload_date': '20160122',
+            'description': 'md5:7f749bbb77d800ef2be11d54529b96bc',
+        },
+    }
+
+
 class ArteTVEmbedIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:embed'
     _VALID_URL = r'''(?x)

youtube_dl/extractor/atresplayer.py

@@ -2,16 +2,18 @@ from __future__ import unicode_literals
 
 import time
 import hmac
+import hashlib
+import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
     compat_urllib_parse,
-    compat_urllib_request,
 )
 from ..utils import (
     int_or_none,
     float_or_none,
+    sanitized_Request,
     xpath_text,
     ExtractorError,
 )
@@ -32,6 +34,19 @@ class AtresPlayerIE(InfoExtractor):
                 'duration': 5527.6,
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
+            'skip': 'This video is only available for registered users'
+        },
+        {
+            'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html',
+            'md5': '0d0e918533bbd4b263f2de4d197d4aac',
+            'info_dict': {
+                'id': 'capitulo-112-david-bustamante',
+                'ext': 'flv',
+                'title': 'David Bustamante',
+                'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6',
+                'duration': 1439.0,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
         },
         {
             'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html',
@@ -50,6 +65,13 @@ class AtresPlayerIE(InfoExtractor):
 
     _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
 
+    _ERRORS = {
+        'UNPUBLISHED': 'We\'re sorry, but this video is not yet available.',
+        'DELETED': 'This video has expired and is no longer available for online streaming.',
+        'GEOUNPUBLISHED': 'We\'re sorry, but this video is not available in your region due to right restrictions.',
+        # 'PREMIUM': 'PREMIUM',
+    }
+
     def _real_initialize(self):
         self._login()
 
@@ -63,7 +85,7 @@ class AtresPlayerIE(InfoExtractor):
             'j_password': password,
         }
 
-        request = compat_urllib_request.Request(
+        request = sanitized_Request(
             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         response = self._download_webpage(
@@ -83,58 +105,72 @@ class AtresPlayerIE(InfoExtractor):
         episode_id = self._search_regex(
             r'episode="([^"]+)"', webpage, 'episode id')
 
+        request = sanitized_Request(
+            self._PLAYER_URL_TEMPLATE % episode_id,
+            headers={'User-Agent': self._USER_AGENT})
+        player = self._download_json(request, episode_id, 'Downloading player JSON')
+
+        episode_type = player.get('typeOfEpisode')
+        error_message = self._ERRORS.get(episode_type)
+        if error_message:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
+
+        formats = []
+        video_url = player.get('urlVideo')
+        if video_url:
+            format_info = {
+                'url': video_url,
+                'format_id': 'http',
+            }
+            mobj = re.search(r'(?P<bitrate>\d+)K_(?P<width>\d+)x(?P<height>\d+)', video_url)
+            if mobj:
+                format_info.update({
+                    'width': int_or_none(mobj.group('width')),
+                    'height': int_or_none(mobj.group('height')),
+                    'tbr': int_or_none(mobj.group('bitrate')),
+                })
+            formats.append(format_info)
+
         timestamp = int_or_none(self._download_webpage(
             self._TIME_API_URL,
             video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
         timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
         token = hmac.new(
             self._MAGIC.encode('ascii'),
-            (episode_id + timestamp_shifted).encode('utf-8')
+            (episode_id + timestamp_shifted).encode('utf-8'), hashlib.md5
         ).hexdigest()
 
-        formats = []
-        for fmt in ['windows', 'android_tablet']:
-            request = compat_urllib_request.Request(
-                self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
-            request.add_header('User-Agent', self._USER_AGENT)
+        request = sanitized_Request(
+            self._URL_VIDEO_TEMPLATE.format('windows', episode_id, timestamp_shifted, token),
+            headers={'User-Agent': self._USER_AGENT})
 
-            fmt_json = self._download_json(
-                request, video_id, 'Downloading %s video JSON' % fmt)
+        fmt_json = self._download_json(
+            request, video_id, 'Downloading windows video JSON')
 
-            result = fmt_json.get('resultDes')
-            if result.lower() != 'ok':
-                raise ExtractorError(
-                    '%s returned error: %s' % (self.IE_NAME, result), expected=True)
+        result = fmt_json.get('resultDes')
+        if result.lower() != 'ok':
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, result), expected=True)
 
-            for format_id, video_url in fmt_json['resultObject'].items():
-                if format_id == 'token' or not video_url.startswith('http'):
-                    continue
-                if video_url.endswith('/Manifest'):
-                    if 'geodeswowsmpra3player' in video_url:
-                        f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
-                        f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
-                        # this videos are protected by DRM, the f4m downloader doesn't support them
-                        continue
-                    else:
-                        f4m_url = video_url[:-9] + '/manifest.f4m'
-                    formats.extend(self._extract_f4m_formats(f4m_url, video_id))
-                else:
-                    formats.append({
-                        'url': video_url,
-                        'format_id': 'android-%s' % format_id,
-                        'preference': 1,
-                    })
+        for format_id, video_url in fmt_json['resultObject'].items():
+            if format_id == 'token' or not video_url.startswith('http'):
+                continue
+            if 'geodeswowsmpra3player' in video_url:
+                f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
+                f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
+                # this videos are protected by DRM, the f4m downloader doesn't support them
+                continue
+            else:
+                f4m_url = video_url[:-9] + '/manifest.f4m'
+            formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False))
         self._sort_formats(formats)
 
-        player = self._download_json(
-            self._PLAYER_URL_TEMPLATE % episode_id,
-            episode_id)
-
         path_data = player.get('pathData')
 
         episode = self._download_xml(
-            self._EPISODE_URL_TEMPLATE % path_data,
-            video_id, 'Downloading episode XML')
+            self._EPISODE_URL_TEMPLATE % path_data, video_id,
+            'Downloading episode XML')
 
         duration = float_or_none(xpath_text(
             episode, './media/asset/info/technical/contentDuration', 'duration'))

youtube_dl/extractor/audimedia.py

@@ -0,0 +1,80 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+    sanitized_Request,
+)
+
+
+class AudiMediaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?audimedia\.tv/(?:en|de)/vid/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'https://audimedia.tv/en/vid/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test',
+        'md5': '79a8b71c46d49042609795ab59779b66',
+        'info_dict': {
+            'id': '1565',
+            'ext': 'mp4',
+            'title': '60 Seconds of Audi Sport 104/2015 - WEC Bahrain, Rookie Test',
+            'description': 'md5:60e5d30a78ced725f7b8d34370762941',
+            'upload_date': '20151124',
+            'timestamp': 1448354940,
+            'duration': 74022,
+            'view_count': int,
+        }
+    }
+    # extracted from https://audimedia.tv/assets/embed/embedded-player.js (dataSourceAuthToken)
+    _AUTH_TOKEN = 'e25b42847dba18c6c8816d5d8ce94c326e06823ebf0859ed164b3ba169be97f2'
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        raw_payload = self._search_regex(r'<script[^>]+class="amtv-embed"[^>]+id="([^"]+)"', webpage, 'raw payload')
+        _, stage_mode, video_id, lang = raw_payload.split('-')
+
+        # TODO: handle s and e stage_mode (live streams and ended live streams)
+        if stage_mode not in ('s', 'e'):
+            request = sanitized_Request(
+                'https://audimedia.tv/api/video/v1/videos/%s?embed[]=video_versions&embed[]=thumbnail_image&where[content_language_iso]=%s' % (video_id, lang),
+                headers={'X-Auth-Token': self._AUTH_TOKEN})
+            json_data = self._download_json(request, video_id)['results']
+            formats = []
+
+            stream_url_hls = json_data.get('stream_url_hls')
+            if stream_url_hls:
+                formats.extend(self._extract_m3u8_formats(
+                    stream_url_hls, video_id, 'mp4',
+                    entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
+
+            stream_url_hds = json_data.get('stream_url_hds')
+            if stream_url_hds:
+                formats.extend(self._extract_f4m_formats(
+                    stream_url_hds + '?hdcore=3.4.0',
+                    video_id, f4m_id='hds', fatal=False))
+
+            for video_version in json_data.get('video_versions'):
+                video_version_url = video_version.get('download_url') or video_version.get('stream_url')
+                if not video_version_url:
+                    continue
+                formats.append({
+                    'url': video_version_url,
+                    'width': int_or_none(video_version.get('width')),
+                    'height': int_or_none(video_version.get('height')),
+                    'abr': int_or_none(video_version.get('audio_bitrate')),
+                    'vbr': int_or_none(video_version.get('video_bitrate')),
+                })
+            self._sort_formats(formats)
+
+            return {
+                'id': video_id,
+                'title': json_data['title'],
+                'description': json_data.get('subtitle'),
+                'thumbnail': json_data.get('thumbnail_image', {}).get('file'),
+                'timestamp': parse_iso8601(json_data.get('publication_date')),
+                'duration': int_or_none(json_data.get('duration')),
+                'view_count': int_or_none(json_data.get('view_count')),
+                'formats': formats,
+            }

youtube_dl/extractor/audiomack.py

@@ -56,7 +56,7 @@ class AudiomackIE(InfoExtractor):
 
         # API is inconsistent with errors
         if 'url' not in api_response or not api_response['url'] or 'error' in api_response:
-            raise ExtractorError('Invalid url %s', url)
+            raise ExtractorError('Invalid url %s' % url)
 
         # Audiomack wraps a lot of soundcloud tracks in their branded wrapper
         # if so, pass the work off to the soundcloud extractor

youtube_dl/extractor/azubu.py

@@ -3,7 +3,11 @@ from __future__ import unicode_literals
 import json
 
 from .common import InfoExtractor
-from ..utils import float_or_none
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    sanitized_Request,
+)
 
 
 class AzubuIE(InfoExtractor):
@@ -91,3 +95,37 @@ class AzubuIE(InfoExtractor):
             'view_count': view_count,
             'formats': formats,
         }
+
+
+class AzubuLiveIE(InfoExtractor):
+    _VALID_URL = r'http://www.azubu.tv/(?P<id>[^/]+)$'
+
+    _TEST = {
+        'url': 'http://www.azubu.tv/MarsTVMDLen',
+        'only_matching': True,
+    }
+
+    def _real_extract(self, url):
+        user = self._match_id(url)
+
+        info = self._download_json(
+            'http://api.azubu.tv/public/modules/last-video/{0}/info'.format(user),
+            user)['data']
+        if info['type'] != 'STREAM':
+            raise ExtractorError('{0} is not streaming live'.format(user), expected=True)
+
+        req = sanitized_Request(
+            'https://edge-elb.api.brightcove.com/playback/v1/accounts/3361910549001/videos/ref:' + info['reference_id'])
+        req.add_header('Accept', 'application/json;pk=BCpkADawqM1gvI0oGWg8dxQHlgT8HkdE2LnAlWAZkOlznO39bSZX726u4JqnDsK3MDXcO01JxXK2tZtJbgQChxgaFzEVdHRjaDoxaOu8hHOO8NYhwdxw9BzvgkvLUlpbDNUuDoc4E4wxDToV')
+        bc_info = self._download_json(req, user)
+        m3u8_url = next(source['src'] for source in bc_info['sources'] if source['container'] == 'M2TS')
+        formats = self._extract_m3u8_formats(m3u8_url, user, ext='mp4')
+
+        return {
+            'id': info['id'],
+            'title': self._live_title(info['title']),
+            'uploader_id': user,
+            'formats': formats,
+            'is_live': True,
+            'thumbnail': bc_info['poster'],
+        }

youtube_dl/extractor/baidu.py

@@ -4,7 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..utils import unescapeHTML
 
 
 class BaiduVideoIE(InfoExtractor):
@@ -14,8 +14,8 @@ class BaiduVideoIE(InfoExtractor):
         'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
         'info_dict': {
             'id': '1069',
-            'title': '中华小当家 TV版 (全52集)',
-            'description': 'md5:395a419e41215e531c857bb037bbaf80',
+            'title': '中华小当家 TV版国语',
+            'description': 'md5:51be07afe461cf99fa61231421b5397c',
         },
         'playlist_count': 52,
     }, {
@@ -25,45 +25,32 @@ class BaiduVideoIE(InfoExtractor):
             'title': 're:^奔跑吧兄弟',
             'description': 'md5:1bf88bad6d850930f542d51547c089b8',
         },
-        'playlist_mincount': 3,
+        'playlist_mincount': 12,
     }]
 
+    def _call_api(self, path, category, playlist_id, note):
+        return self._download_json('http://app.video.baidu.com/%s/?worktype=adnative%s&id=%s' % (
+            path, category, playlist_id), playlist_id, note)
+
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        playlist_id = mobj.group('id')
-        category = category2 = mobj.group('type')
+        category, playlist_id = re.match(self._VALID_URL, url).groups()
         if category == 'show':
-            category2 = 'tvshow'
+            category = 'tvshow'
+        if category == 'tv':
+            category = 'tvplay'
 
-        webpage = self._download_webpage(url, playlist_id)
+        playlist_detail = self._call_api(
+            'xqinfo', category, playlist_id, 'Download playlist JSON metadata')
 
-        playlist_title = self._html_search_regex(
-            r'title\s*:\s*(["\'])(?P<title>[^\']+)\1', webpage,
-            'playlist title', group='title')
-        playlist_description = self._html_search_regex(
-            r'<input[^>]+class="j-data-intro"[^>]+value="([^"]+)"/>', webpage,
-            playlist_id, 'playlist description')
+        playlist_title = playlist_detail['title']
+        playlist_description = unescapeHTML(playlist_detail.get('intro'))
 
-        site = self._html_search_regex(
-            r'filterSite\s*:\s*["\']([^"]*)["\']', webpage,
-            'primary provider site')
-        api_result = self._download_json(
-            'http://v.baidu.com/%s_intro/?dtype=%sPlayUrl&id=%s&site=%s' % (
-                category, category2, playlist_id, site),
-            playlist_id, 'Get playlist links')
+        episodes_detail = self._call_api(
+            'xqsingle', category, playlist_id, 'Download episodes JSON metadata')
 
-        entries = []
-        for episode in api_result[0]['episodes']:
-            episode_id = '%s_%s' % (playlist_id, episode['episode'])
-
-            redirect_page = self._download_webpage(
-                compat_urlparse.urljoin(url, episode['url']), episode_id,
-                note='Download Baidu redirect page')
-            real_url = self._html_search_regex(
-                r'location\.replace\("([^"]+)"\)', redirect_page, 'real URL')
-
-            entries.append(self.url_result(
-                real_url, video_title=episode['single_title']))
+        entries = [self.url_result(
+            episode['url'], video_title=episode['title']
+        ) for episode in episodes_detail['videos']]
 
         return self.playlist_result(
             entries, playlist_id, playlist_title, playlist_description)

youtube_dl/extractor/bambuser.py

@@ -6,13 +6,13 @@ import itertools
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
-    compat_urllib_request,
     compat_str,
 )
 from ..utils import (
     ExtractorError,
     int_or_none,
     float_or_none,
+    sanitized_Request,
 )
 
 
@@ -57,7 +57,7 @@ class BambuserIE(InfoExtractor):
             'pass': password,
         }
 
-        request = compat_urllib_request.Request(
+        request = sanitized_Request(
             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
         request.add_header('Referer', self._LOGIN_URL)
         response = self._download_webpage(
@@ -126,7 +126,7 @@ class BambuserChannelIE(InfoExtractor):
                 '&sort=created&access_mode=0%2C1%2C2&limit={count}'
                 '&method=broadcast&format=json&vid_older_than={last}'
             ).format(user=user, count=self._STEP, last=last_id)
-            req = compat_urllib_request.Request(req_url)
+            req = sanitized_Request(req_url)
             # Without setting this header, we wouldn't get any result
             req.add_header('Referer', 'http://bambuser.com/channel/%s' % user)
             data = self._download_json(

youtube_dl/extractor/bandcamp.py

@@ -10,6 +10,8 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    float_or_none,
+    int_or_none,
 )
 
 
@@ -52,11 +54,11 @@ class BandcampIE(InfoExtractor):
                     ext, abr_str = format_id.split('-', 1)
                     formats.append({
                         'format_id': format_id,
-                        'url': format_url,
+                        'url': self._proto_relative_url(format_url, 'http:'),
                         'ext': ext,
                         'vcodec': 'none',
                         'acodec': ext,
-                        'abr': int(abr_str),
+                        'abr': int_or_none(abr_str),
                     })
 
                 self._sort_formats(formats)
@@ -65,7 +67,7 @@ class BandcampIE(InfoExtractor):
                     'id': compat_str(data['id']),
                     'title': data['title'],
                     'formats': formats,
-                    'duration': float(data['duration']),
+                    'duration': float_or_none(data.get('duration')),
                 }
             else:
                 raise ExtractorError('No free songs found')
@@ -93,8 +95,8 @@ class BandcampIE(InfoExtractor):
         final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
         # If we could correctly generate the .rand field the url would be
         # in the "download_url" key
-        final_url = self._search_regex(
-            r'"retry_url":"(.*?)"', final_url_webpage, 'final video URL')
+        final_url = self._proto_relative_url(self._search_regex(
+            r'"retry_url":"(.+?)"', final_url_webpage, 'final video URL'), 'http:')
 
         return {
             'id': video_id,

youtube_dl/extractor/bbc.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -11,32 +10,55 @@ from ..utils import (
     int_or_none,
     parse_duration,
     parse_iso8601,
+    remove_end,
+    unescapeHTML,
+)
+from ..compat import (
+    compat_etree_fromstring,
+    compat_HTTPError,
 )
-from ..compat import compat_HTTPError
 
 
 class BBCCoUkIE(InfoExtractor):
     IE_NAME = 'bbc.co.uk'
     IE_DESC = 'BBC iPlayer'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
+    _ID_REGEX = r'[pb][\da-z]{7}'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?bbc\.co\.uk/
+                        (?:
+                            programmes/(?!articles/)|
+                            iplayer(?:/[^/]+)?/(?:episode/|playlist/)|
+                            music/clips[/#]|
+                            radio/player/
+                        )
+                        (?P<id>%s)
+                    ''' % _ID_REGEX
 
     _MEDIASELECTOR_URLS = [
         # Provides HQ HLS streams with even better quality that pc mediaset but fails
         # with geolocation in some cases when it's even not geo restricted at all (e.g.
-        # http://www.bbc.co.uk/programmes/b06bp7lf)
+        # http://www.bbc.co.uk/programmes/b06bp7lf). Also may fail with selectionunavailable.
         'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
         'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s',
     ]
 
+    _MEDIASELECTION_NS = 'http://bbc.co.uk/2008/mp/mediaselection'
+    _EMP_PLAYLIST_NS = 'http://bbc.co.uk/2008/emp/playlist'
+
+    _NAMESPACES = (
+        _MEDIASELECTION_NS,
+        _EMP_PLAYLIST_NS,
+    )
+
     _TESTS = [
         {
             'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
             'info_dict': {
                 'id': 'b039d07m',
                 'ext': 'flv',
-                'title': 'Kaleidoscope, Leonard Cohen',
+                'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4',
                 'description': 'The Canadian poet and songwriter reflects on his musical career.',
-                'duration': 1740,
             },
             'params': {
                 # rtmp download
@@ -99,16 +121,17 @@ class BBCCoUkIE(InfoExtractor):
             'params': {
                 # rtmp download
                 'skip_download': True,
-            }
+            },
+            'skip': 'Episode is no longer available on BBC iPlayer Radio',
         }, {
-            'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
+            'url': 'http://www.bbc.co.uk/music/clips/p022h44b',
             'note': 'Audio',
             'info_dict': {
-                'id': 'p02frcch',
+                'id': 'p022h44j',
                 'ext': 'flv',
-                'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix',
-                'description': 'French house superstar Madeon takes us out of the club and onto the after party.',
-                'duration': 3507,
+                'title': 'BBC Proms Music Guides, Rachmaninov: Symphonic Dances',
+                'description': "In this Proms Music Guide, Andrew McGregor looks at Rachmaninov's Symphonic Dances.",
+                'duration': 227,
             },
             'params': {
                 # rtmp download
@@ -159,13 +182,25 @@ class BBCCoUkIE(InfoExtractor):
         }, {
             # iptv-all mediaset fails with geolocation however there is no geo restriction
             # for this programme at all
-            'url': 'http://www.bbc.co.uk/programmes/b06bp7lf',
+            'url': 'http://www.bbc.co.uk/programmes/b06rkn85',
             'info_dict': {
-                'id': 'b06bp7kf',
+                'id': 'b06rkms3',
                 'ext': 'flv',
-                'title': "Annie Mac's Friday Night, B.Traits sits in for Annie",
-                'description': 'B.Traits sits in for Annie Mac with a Mini-Mix from Disclosure.',
-                'duration': 10800,
+                'title': "Best of the Mini-Mixes 2015: Part 3, Annie Mac's Friday Night - BBC Radio 1",
+                'description': "Annie has part three in the Best of the Mini-Mixes 2015, plus the year's Most Played!",
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        }, {
+            # compact player (https://github.com/rg3/youtube-dl/issues/8147)
+            'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
+            'info_dict': {
+                'id': 'p028bfkj',
+                'ext': 'flv',
+                'title': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
+                'description': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
             },
             'params': {
                 # rtmp download
@@ -180,6 +215,9 @@ class BBCCoUkIE(InfoExtractor):
         }, {
             'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
             'only_matching': True,
+        }, {
+            'url': 'http://www.bbc.co.uk/radio/player/p03cchwf',
+            'only_matching': True,
         }
     ]
 
@@ -193,6 +231,7 @@ class BBCCoUkIE(InfoExtractor):
 
     def _extract_connection(self, connection, programme_id):
         formats = []
+        kind = connection.get('kind')
         protocol = connection.get('protocol')
         supplier = connection.get('supplier')
         if protocol == 'http':
@@ -209,16 +248,14 @@ class BBCCoUkIE(InfoExtractor):
             elif transfer_format == 'dash':
                 pass
             elif transfer_format == 'hls':
-                m3u8_formats = self._extract_m3u8_formats(
+                formats.extend(self._extract_m3u8_formats(
                     href, programme_id, ext='mp4', entry_protocol='m3u8_native',
-                    m3u8_id=supplier, fatal=False)
-                if m3u8_formats:
-                    formats.extend(m3u8_formats)
+                    m3u8_id=supplier, fatal=False))
             # Direct link
             else:
                 formats.append({
                     'url': href,
-                    'format_id': supplier,
+                    'format_id': supplier or kind or protocol,
                 })
         elif protocol == 'rtmp':
             application = connection.get('application', 'ondemand')
@@ -238,16 +275,24 @@ class BBCCoUkIE(InfoExtractor):
         return formats
 
     def _extract_items(self, playlist):
-        return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item')
+        return playlist.findall('./{%s}item' % self._EMP_PLAYLIST_NS)
+
+    def _findall_ns(self, element, xpath):
+        elements = []
+        for ns in self._NAMESPACES:
+            elements.extend(element.findall(xpath % ns))
+        return elements
 
     def _extract_medias(self, media_selection):
-        error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error')
+        error = media_selection.find('./{%s}error' % self._MEDIASELECTION_NS)
+        if error is None:
+            media_selection.find('./{%s}error' % self._EMP_PLAYLIST_NS)
         if error is not None:
             raise BBCCoUkIE.MediaSelectionError(error.get('id'))
-        return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
+        return self._findall_ns(media_selection, './{%s}media')
 
     def _extract_connections(self, media):
-        return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection')
+        return self._findall_ns(media, './{%s}connection')
 
     def _extract_video(self, media, programme_id):
         formats = []
@@ -261,13 +306,14 @@ class BBCCoUkIE(InfoExtractor):
             conn_formats = self._extract_connection(connection, programme_id)
             for format in conn_formats:
                 format.update({
-                    'format_id': '%s_%s' % (service, format['format_id']),
                     'width': width,
                     'height': height,
                     'vbr': vbr,
                     'vcodec': vcodec,
                     'filesize': file_size,
                 })
+                if service:
+                    format['format_id'] = '%s_%s' % (service, format['format_id'])
             formats.extend(conn_formats)
         return formats
 
@@ -312,7 +358,7 @@ class BBCCoUkIE(InfoExtractor):
                 return self._download_media_selector_url(
                     mediaselector_url % programme_id, programme_id)
             except BBCCoUkIE.MediaSelectionError as e:
-                if e.id in ('notukerror', 'geolocation'):
+                if e.id in ('notukerror', 'geolocation', 'selectionunavailable'):
                     last_exception = e
                     continue
                 self._raise_extractor_error(e)
@@ -323,8 +369,8 @@ class BBCCoUkIE(InfoExtractor):
             media_selection = self._download_xml(
                 url, programme_id, 'Downloading media selection XML')
         except ExtractorError as ee:
-            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
-                media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8'))
+            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code in (403, 404):
+                media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8'))
             else:
                 raise
         return self._process_media_selector(media_selection, programme_id)
@@ -382,7 +428,7 @@ class BBCCoUkIE(InfoExtractor):
             url, playlist_id, 'Downloading legacy playlist XML')
 
     def _extract_from_legacy_playlist(self, playlist, playlist_id):
-        no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
+        no_items = playlist.find('./{%s}noItems' % self._EMP_PLAYLIST_NS)
         if no_items is not None:
             reason = no_items.get('reason')
             if reason == 'preAvailability':
@@ -399,8 +445,9 @@ class BBCCoUkIE(InfoExtractor):
             kind = item.get('kind')
             if kind != 'programme' and kind != 'radioProgramme':
                 continue
-            title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
-            description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
+            title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
+            description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)
+            description = description_el.text if description_el is not None else None
 
             def get_programme_id(item):
                 def get_from_attributes(item):
@@ -409,16 +456,18 @@ class BBCCoUkIE(InfoExtractor):
                         if value and re.match(r'^[pb][\da-z]{7}$', value):
                             return value
                 get_from_attributes(item)
-                mediator = item.find('./{http://bbc.co.uk/2008/emp/playlist}mediator')
+                mediator = item.find('./{%s}mediator' % self._EMP_PLAYLIST_NS)
                 if mediator is not None:
                     return get_from_attributes(mediator)
 
             programme_id = get_programme_id(item)
             duration = int_or_none(item.get('duration'))
-            # TODO: programme_id can be None and media items can be incorporated right inside
-            # playlist's item (e.g. http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
-            # as f4m and m3u8
-            formats, subtitles = self._download_media_selector(programme_id)
+
+            if programme_id:
+                formats, subtitles = self._download_media_selector(programme_id)
+            else:
+                formats, subtitles = self._process_media_selector(item, playlist_id)
+                programme_id = playlist_id
 
         return programme_id, title, description, duration, formats, subtitles
 
@@ -428,6 +477,7 @@ class BBCCoUkIE(InfoExtractor):
         webpage = self._download_webpage(url, group_id, 'Downloading video page')
 
         programme_id = None
+        duration = None
 
         tviplayer = self._search_regex(
             r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
@@ -440,14 +490,19 @@ class BBCCoUkIE(InfoExtractor):
 
         if not programme_id:
             programme_id = self._search_regex(
-                r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
+                r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None)
 
         if programme_id:
             formats, subtitles = self._download_media_selector(programme_id)
-            title = self._og_search_title(webpage)
+            title = self._og_search_title(webpage, default=None) or self._html_search_regex(
+                (r'<h2[^>]+id="parent-title"[^>]*>(.+?)</h2>',
+                 r'<div[^>]+class="info"[^>]*>\s*<h1>(.+?)</h1>'), webpage, 'title')
             description = self._search_regex(
-                r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
-                webpage, 'description', fatal=False)
+                (r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
+                 r'<div[^>]+class="info_+synopsis"[^>]*>([^<]+)</div>'),
+                webpage, 'description', default=None)
+            if not description:
+                description = self._html_search_meta('description', webpage)
         else:
             programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
 
@@ -470,6 +525,9 @@ class BBCIE(BBCCoUkIE):
     _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)'
 
     _MEDIASELECTOR_URLS = [
+        # Provides HQ HLS streams but fails with geolocation in some cases when it's
+        # even not geo restricted at all
+        'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
         # Provides more formats, namely direct mp4 links, but fails on some videos with
         # notukerror for non UK (?) users (e.g.
         # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
@@ -479,8 +537,7 @@ class BBCIE(BBCCoUkIE):
     ]
 
     _TESTS = [{
-        # article with multiple videos embedded with data-media-meta containing
-        # playlist.sxml, externalId and no direct video links
+        # article with multiple videos embedded with data-playable containing vpids
         'url': 'http://www.bbc.com/news/world-europe-32668511',
         'info_dict': {
             'id': 'world-europe-32668511',
@@ -489,7 +546,7 @@ class BBCIE(BBCCoUkIE):
         },
         'playlist_count': 2,
     }, {
-        # article with multiple videos embedded with data-media-meta (more videos)
+        # article with multiple videos embedded with data-playable (more videos)
         'url': 'http://www.bbc.com/news/business-28299555',
         'info_dict': {
             'id': 'business-28299555',
@@ -500,6 +557,7 @@ class BBCIE(BBCCoUkIE):
         'skip': 'Save time',
     }, {
         # article with multiple videos embedded with `new SMP()`
+        # broken
         'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
         'info_dict': {
             'id': '3662a707-0af9-3149-963f-47bea720b460',
@@ -507,12 +565,13 @@ class BBCIE(BBCCoUkIE):
         },
         'playlist_count': 18,
     }, {
-        # single video embedded with mediaAssetPage.init()
+        # single video embedded with data-playable containing vpid
         'url': 'http://www.bbc.com/news/world-europe-32041533',
         'info_dict': {
             'id': 'p02mprgb',
             'ext': 'mp4',
             'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
+            'description': 'md5:2868290467291b37feda7863f7a83f54',
             'duration': 47,
             'timestamp': 1427219242,
             'upload_date': '20150324',
@@ -522,15 +581,14 @@ class BBCIE(BBCCoUkIE):
             'skip_download': True,
         }
     }, {
-        # article with single video embedded with data-media-meta containing
-        # direct video links (for now these are extracted) and playlist.xml (with
-        # media items as f4m and m3u8 - currently unsupported)
+        # article with single video embedded with data-playable containing XML playlist
+        # with direct video links as progressiveDownloadUrl (for now these are extracted)
+        # and playlist with f4m and m3u8 as streamingUrl
         'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
         'info_dict': {
             'id': '150615_telabyad_kentin_cogu',
             'ext': 'mp4',
             'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde",
-            'duration': 47,
             'timestamp': 1434397334,
             'upload_date': '20150615',
         },
@@ -538,13 +596,12 @@ class BBCIE(BBCCoUkIE):
             'skip_download': True,
         }
     }, {
-        # single video embedded with mediaAssetPage.init() (regional section)
+        # single video embedded with data-playable containing XML playlists (regional section)
         'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
         'info_dict': {
             'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
             'ext': 'mp4',
             'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
-            'duration': 87,
             'timestamp': 1434713142,
             'upload_date': '20150619',
         },
@@ -559,6 +616,7 @@ class BBCIE(BBCCoUkIE):
             'ext': 'mp4',
             'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
             'duration': 56,
+            'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
         },
         'params': {
             'skip_download': True,
@@ -586,27 +644,35 @@ class BBCIE(BBCCoUkIE):
             'ext': 'mp4',
             'title': 'Hyundai Santa Fe Sport: Rock star',
             'description': 'md5:b042a26142c4154a6e472933cf20793d',
-            'timestamp': 1368473503,
-            'upload_date': '20130513',
+            'timestamp': 1415867444,
+            'upload_date': '20141113',
         },
         'params': {
             # rtmp download
             'skip_download': True,
         }
     }, {
-        # single video with playlist.sxml URL
+        # single video with playlist.sxml URL in playlist param
         'url': 'http://www.bbc.com/sport/0/football/33653409',
         'info_dict': {
             'id': 'p02xycnp',
             'ext': 'mp4',
             'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
-            'description': 'md5:398fca0e2e701c609d726e034fa1fc89',
+            'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
             'duration': 140,
         },
         'params': {
             # rtmp download
             'skip_download': True,
         }
+    }, {
+        # article with multiple videos embedded with playlist.sxml in playlist param
+        'url': 'http://www.bbc.com/sport/0/football/34475836',
+        'info_dict': {
+            'id': '34475836',
+            'title': 'What Liverpool can expect from Klopp',
+        },
+        'playlist_count': 3,
     }, {
         # single video with playlist URL from weather section
         'url': 'http://www.bbc.com/weather/features/33601775',
@@ -619,7 +685,7 @@ class BBCIE(BBCCoUkIE):
 
     @classmethod
     def suitable(cls, url):
-        return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url)
+        return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) else super(BBCIE, cls).suitable(url)
 
     def _extract_from_media_meta(self, media_meta, video_id):
         # Direct links to media in media metadata (e.g.
@@ -648,40 +714,100 @@ class BBCIE(BBCCoUkIE):
 
         return [], []
 
+    def _extract_from_playlist_sxml(self, url, playlist_id, timestamp):
+        programme_id, title, description, duration, formats, subtitles = \
+            self._process_legacy_playlist_url(url, playlist_id)
+        self._sort_formats(formats)
+        return {
+            'id': programme_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
 
         webpage = self._download_webpage(url, playlist_id)
 
-        timestamp = parse_iso8601(self._search_regex(
-            [r'"datePublished":\s*"([^"]+)',
-             r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"',
-             r'itemprop="datePublished"[^>]+datetime="([^"]+)"'],
-            webpage, 'date', default=None))
+        json_ld_info = self._search_json_ld(webpage, playlist_id, default=None)
+        timestamp = json_ld_info.get('timestamp')
+        playlist_title = json_ld_info.get('title')
+        playlist_description = json_ld_info.get('description')
 
-        # single video with playlist.sxml URL (e.g. http://www.bbc.com/sport/0/football/3365340ng)
-        playlist = self._search_regex(
-            r'<param[^>]+name="playlist"[^>]+value="([^"]+)"',
-            webpage, 'playlist', default=None)
-        if playlist:
-            programme_id, title, description, duration, formats, subtitles = \
-                self._process_legacy_playlist_url(playlist, playlist_id)
-            self._sort_formats(formats)
-            return {
-                'id': programme_id,
-                'title': title,
-                'description': description,
-                'duration': duration,
-                'timestamp': timestamp,
-                'formats': formats,
-                'subtitles': subtitles,
-            }
+        if not timestamp:
+            timestamp = parse_iso8601(self._search_regex(
+                [r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"',
+                 r'itemprop="datePublished"[^>]+datetime="([^"]+)"',
+                 r'"datePublished":\s*"([^"]+)'],
+                webpage, 'date', default=None))
+
+        entries = []
+
+        # article with multiple videos embedded with playlist.sxml (e.g.
+        # http://www.bbc.com/sport/0/football/34475836)
+        playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage)
+        playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage))
+        if playlists:
+            entries = [
+                self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp)
+                for playlist_url in playlists]
+
+        # news article with multiple videos embedded with data-playable
+        data_playables = re.findall(r'data-playable=(["\'])({.+?})\1', webpage)
+        if data_playables:
+            for _, data_playable_json in data_playables:
+                data_playable = self._parse_json(
+                    unescapeHTML(data_playable_json), playlist_id, fatal=False)
+                if not data_playable:
+                    continue
+                settings = data_playable.get('settings', {})
+                if settings:
+                    # data-playable with video vpid in settings.playlistObject.items (e.g.
+                    # http://www.bbc.com/news/world-us-canada-34473351)
+                    playlist_object = settings.get('playlistObject', {})
+                    if playlist_object:
+                        items = playlist_object.get('items')
+                        if items and isinstance(items, list):
+                            title = playlist_object['title']
+                            description = playlist_object.get('summary')
+                            duration = int_or_none(items[0].get('duration'))
+                            programme_id = items[0].get('vpid')
+                            formats, subtitles = self._download_media_selector(programme_id)
+                            self._sort_formats(formats)
+                            entries.append({
+                                'id': programme_id,
+                                'title': title,
+                                'description': description,
+                                'timestamp': timestamp,
+                                'duration': duration,
+                                'formats': formats,
+                                'subtitles': subtitles,
+                            })
+                    else:
+                        # data-playable without vpid but with a playlist.sxml URLs
+                        # in otherSettings.playlist (e.g.
+                        # http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani)
+                        playlist = data_playable.get('otherSettings', {}).get('playlist', {})
+                        if playlist:
+                            entries.append(self._extract_from_playlist_sxml(
+                                playlist.get('progressiveDownloadUrl'), playlist_id, timestamp))
+
+        if entries:
+            playlist_title = playlist_title or remove_end(self._og_search_title(webpage), ' - BBC News')
+            playlist_description = playlist_description or self._og_search_description(webpage, default=None)
+            return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
 
         # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
         programme_id = self._search_regex(
-            [r'data-video-player-vpid="([\da-z]{8})"',
-             r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'],
+            [r'data-video-player-vpid="(%s)"' % self._ID_REGEX,
+             r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
+             r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
             webpage, 'vpid', default=None)
+
         if programme_id:
             formats, subtitles = self._download_media_selector(programme_id)
             self._sort_formats(formats)
@@ -714,7 +840,7 @@ class BBCIE(BBCCoUkIE):
 
         # Multiple video article (e.g.
         # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
-        EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?'
+        EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX
         entries = []
         for match in extract_all(r'new\s+SMP\(({.+?})\)'):
             embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
@@ -803,3 +929,33 @@ class BBCIE(BBCCoUkIE):
             })
 
         return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
+
+
+class BBCCoUkArticleIE(InfoExtractor):
+    _VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
+    IE_NAME = 'bbc.co.uk:article'
+    IE_DESC = 'BBC articles'
+
+    _TEST = {
+        'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer',
+        'info_dict': {
+            'id': '3jNQLTMrPlYGTBn0WV6M2MS',
+            'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four',
+            'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.',
+        },
+        'playlist_count': 4,
+        'add_ie': ['BBCCoUk'],
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage).strip()
+
+        entries = [self.url_result(programme_url) for programme_url in re.findall(
+            r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)]
+
+        return self.playlist_result(entries, playlist_id, title, description)

youtube_dl/extractor/beeg.py

@@ -1,65 +1,105 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..compat import (
+    compat_chr,
+    compat_ord,
+    compat_urllib_parse_unquote,
+)
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
 
 
 class BeegIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
     _TEST = {
         'url': 'http://beeg.com/5416503',
-        'md5': '1bff67111adb785c51d1b42959ec10e5',
+        'md5': '46c384def73b33dbc581262e5ee67cef',
         'info_dict': {
             'id': '5416503',
             'ext': 'mp4',
             'title': 'Sultry Striptease',
-            'description': 'md5:6db3c6177972822aaba18652ff59c773',
-            'categories': list,  # NSFW
-            'thumbnail': 're:https?://.*\.jpg$',
+            'description': 'md5:d22219c09da287c14bed3d6c37ce4bc2',
+            'timestamp': 1391813355,
+            'upload_date': '20140207',
+            'duration': 383,
+            'tags': list,
             'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        video = self._download_json(
+            'https://api.beeg.com/api/v5/video/%s' % video_id, video_id)
 
-        quality_arr = self._search_regex(
-            r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats')
+        def split(o, e):
+            def cut(s, x):
+                n.append(s[:x])
+                return s[x:]
+            n = []
+            r = len(o) % e
+            if r > 0:
+                o = cut(o, r)
+            while len(o) > e:
+                o = cut(o, e)
+            n.append(o)
+            return n
 
-        formats = [{
-            'url': fmt[1],
-            'format_id': fmt[0],
-            'height': int(fmt[0][:-1]),
-        } for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)]
+        def decrypt_key(key):
+            # Reverse engineered from http://static.beeg.com/cpl/1105.js
+            a = '5ShMcIQlssOd7zChAIOlmeTZDaUxULbJRnywYaiB'
+            e = compat_urllib_parse_unquote(key)
+            o = ''.join([
+                compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21)
+                for n in range(len(e))])
+            return ''.join(split(o, 3)[::-1])
 
+        def decrypt_url(encrypted_url):
+            encrypted_url = self._proto_relative_url(
+                encrypted_url.replace('{DATA_MARKERS}', ''), 'https:')
+            key = self._search_regex(
+                r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None)
+            if not key:
+                return encrypted_url
+            return encrypted_url.replace(key, decrypt_key(key))
+
+        formats = []
+        for format_id, video_url in video.items():
+            if not video_url:
+                continue
+            height = self._search_regex(
+                r'^(\d+)[pP]$', format_id, 'height', default=None)
+            if not height:
+                continue
+            formats.append({
+                'url': decrypt_url(video_url),
+                'format_id': format_id,
+                'height': int(height),
+            })
         self._sort_formats(formats)
 
-        title = self._html_search_regex(
-            r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title')
+        title = video['title']
+        video_id = video.get('id') or video_id
+        display_id = video.get('code')
+        description = video.get('desc')
 
-        description = self._html_search_regex(
-            r'<meta name="description" content="([^"]*)"',
-            webpage, 'description', fatal=False)
-        thumbnail = self._html_search_regex(
-            r'\'previewer.url\'\s*:\s*"([^"]*)"',
-            webpage, 'thumbnail', fatal=False)
+        timestamp = parse_iso8601(video.get('date'), ' ')
+        duration = int_or_none(video.get('duration'))
 
-        categories_str = self._html_search_regex(
-            r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
-        categories = (
-            None if categories_str is None
-            else categories_str.split(','))
+        tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': title,
             'description': description,
-            'thumbnail': thumbnail,
-            'categories': categories,
+            'timestamp': timestamp,
+            'duration': duration,
+            'tags': tags,
             'formats': formats,
             'age_limit': 18,
         }

youtube_dl/extractor/bigflix.py

@@ -0,0 +1,85 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import base64
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
+
+
+class BigflixIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.bigflix.com/Hindi-movies/Action-movies/Singham-Returns/16537',
+        'md5': 'ec76aa9b1129e2e5b301a474e54fab74',
+        'info_dict': {
+            'id': '16537',
+            'ext': 'mp4',
+            'title': 'Singham Returns',
+            'description': 'md5:3d2ba5815f14911d5cc6a501ae0cf65d',
+        }
+    }, {
+        # 2 formats
+        'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
+        'info_dict': {
+            'id': '16070',
+            'ext': 'mp4',
+            'title': 'Madarasapatinam',
+            'description': 'md5:63b9b8ed79189c6f0418c26d9a3452ca',
+            'formats': 'mincount:2',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        # multiple formats
+        'url': 'http://www.bigflix.com/Malayalam-movies/Drama-movies/Indian-Rupee/15967',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+            r'<div[^>]+class=["\']pagetitle["\'][^>]*>(.+?)</div>',
+            webpage, 'title')
+
+        def decode_url(quoted_b64_url):
+            return base64.b64decode(compat_urllib_parse_unquote(
+                quoted_b64_url).encode('ascii')).decode('utf-8')
+
+        formats = []
+        for height, encoded_url in re.findall(
+                r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage):
+            video_url = decode_url(encoded_url)
+            f = {
+                'url': video_url,
+                'format_id': '%sp' % height,
+                'height': int(height),
+            }
+            if video_url.startswith('rtmp'):
+                f['ext'] = 'flv'
+            formats.append(f)
+
+        file_url = self._search_regex(
+            r'file=([^&]+)', webpage, 'video url', default=None)
+        if file_url:
+            video_url = decode_url(file_url)
+            if all(f['url'] != video_url for f in formats):
+                formats.append({
+                    'url': decode_url(file_url),
+                })
+
+        self._sort_formats(formats)
+
+        description = self._html_search_meta('description', webpage)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'formats': formats
+        }

youtube_dl/extractor/bild.py

@@ -4,7 +4,7 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
-    fix_xml_ampersands,
+    unescapeHTML,
 )
 
 
@@ -17,26 +17,24 @@ class BildIE(InfoExtractor):
         'info_dict': {
             'id': '38184146',
             'ext': 'mp4',
-            'title': 'BILD hat sie getestet',
+            'title': 'Das können die  neuen iPads',
+            'description': 'md5:a4058c4fa2a804ab59c00d7244bbf62f',
             'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 196,
-            'description': 'Mit dem iPad Air 2 und dem iPad Mini 3 hat Apple zwei neue Tablet-Modelle präsentiert. BILD-Reporter Sven Stein durfte die Geräte bereits testen. ',
         }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        xml_url = url.split(".bild.html")[0] + ",view=xml.bild.xml"
-        doc = self._download_xml(xml_url, video_id, transform_source=fix_xml_ampersands)
-
-        duration = int_or_none(doc.attrib.get('duration'), scale=1000)
+        video_data = self._download_json(
+            url.split('.bild.html')[0] + ',view=json.bild.html', video_id)
 
         return {
             'id': video_id,
-            'title': doc.attrib['ueberschrift'],
-            'description': doc.attrib.get('text'),
-            'url': doc.attrib['src'],
-            'thumbnail': doc.attrib.get('img'),
-            'duration': duration,
+            'title': unescapeHTML(video_data['title']).strip(),
+            'description': unescapeHTML(video_data.get('description')),
+            'url': video_data['clipList'][0]['srces'][0]['src'],
+            'thumbnail': video_data.get('poster'),
+            'duration': int_or_none(video_data.get('durationSec')),
         }

youtube_dl/extractor/bilibili.py

@@ -2,141 +2,109 @@
 from __future__ import unicode_literals
 
 import re
-import itertools
-import json
-import xml.etree.ElementTree as ET
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
-    unified_strdate,
+    unescapeHTML,
     ExtractorError,
+    xpath_text,
 )
 
 
 class BiliBiliIE(InfoExtractor):
-    _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'
+    _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?'
 
     _TESTS = [{
         'url': 'http://www.bilibili.tv/video/av1074402/',
         'md5': '2c301e4dab317596e837c3e7633e7d86',
         'info_dict': {
-            'id': '1074402_part1',
+            'id': '1554319',
             'ext': 'flv',
             'title': '【金坷垃】金泡沫',
-            'duration': 308,
+            'duration': 308313,
             'upload_date': '20140420',
             'thumbnail': 're:^https?://.+\.jpg',
+            'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
+            'timestamp': 1397983878,
+            'uploader': '菊子桑',
         },
     }, {
         'url': 'http://www.bilibili.com/video/av1041170/',
         'info_dict': {
             'id': '1041170',
             'title': '【BD1080P】刀语【诸神&异域】',
+            'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
+            'uploader': '枫叶逝去',
+            'timestamp': 1396501299,
         },
         'playlist_count': 9,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        page_num = mobj.group('page_num') or '1'
 
-        if '(此视频不存在或被删除)' in webpage:
-            raise ExtractorError(
-                'The video does not exist or was deleted', expected=True)
+        view_data = self._download_json(
+            'http://api.bilibili.com/view?type=json&appkey=8e9fc618fbd41e28&id=%s&page=%s' % (video_id, page_num),
+            video_id)
+        if 'error' in view_data:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, view_data['error']), expected=True)
 
-        if '>你没有权限浏览！ 由于版权相关问题 我们不对您所在的地区提供服务<' in webpage:
-            raise ExtractorError(
-                'The video is not available in your region due to copyright reasons',
-                expected=True)
+        cid = view_data['cid']
+        title = unescapeHTML(view_data['title'])
 
-        video_code = self._search_regex(
-            r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
+        doc = self._download_xml(
+            'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid,
+            cid,
+            'Downloading page %s/%s' % (page_num, view_data['pages'])
+        )
 
-        title = self._html_search_meta(
-            'media:title', video_code, 'title', fatal=True)
-        duration_str = self._html_search_meta(
-            'duration', video_code, 'duration')
-        if duration_str is None:
-            duration = None
-        else:
-            duration_mobj = re.match(
-                r'^T(?:(?P<hours>[0-9]+)H)?(?P<minutes>[0-9]+)M(?P<seconds>[0-9]+)S$',
-                duration_str)
-            duration = (
-                int_or_none(duration_mobj.group('hours'), default=0) * 3600 +
-                int(duration_mobj.group('minutes')) * 60 +
-                int(duration_mobj.group('seconds')))
-        upload_date = unified_strdate(self._html_search_meta(
-            'uploadDate', video_code, fatal=False))
-        thumbnail = self._html_search_meta(
-            'thumbnailUrl', video_code, 'thumbnail', fatal=False)
-
-        cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
+        if xpath_text(doc, './result') == 'error':
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, xpath_text(doc, './message')), expected=True)
 
         entries = []
 
-        lq_page = self._download_webpage(
-            'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
-            video_id,
-            note='Downloading LQ video info'
-        )
-        try:
-            err_info = json.loads(lq_page)
-            raise ExtractorError(
-                'BiliBili said: ' + err_info['error_text'], expected=True)
-        except ValueError:
-            pass
-
-        lq_doc = ET.fromstring(lq_page)
-        lq_durls = lq_doc.findall('./durl')
-
-        hq_doc = self._download_xml(
-            'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
-            video_id,
-            note='Downloading HQ video info',
-            fatal=False,
-        )
-        if hq_doc is not False:
-            hq_durls = hq_doc.findall('./durl')
-            assert len(lq_durls) == len(hq_durls)
-        else:
-            hq_durls = itertools.repeat(None)
-
-        i = 1
-        for lq_durl, hq_durl in zip(lq_durls, hq_durls):
+        for durl in doc.findall('./durl'):
+            size = xpath_text(durl, ['./filesize', './size'])
             formats = [{
-                'format_id': 'lq',
-                'quality': 1,
-                'url': lq_durl.find('./url').text,
-                'filesize': int_or_none(
-                    lq_durl.find('./size'), get_attr='text'),
+                'url': durl.find('./url').text,
+                'filesize': int_or_none(size),
+                'ext': 'flv',
             }]
-            if hq_durl is not None:
-                formats.append({
-                    'format_id': 'hq',
-                    'quality': 2,
-                    'ext': 'flv',
-                    'url': hq_durl.find('./url').text,
-                    'filesize': int_or_none(
-                        hq_durl.find('./size'), get_attr='text'),
-                })
-            self._sort_formats(formats)
+            backup_urls = durl.find('./backup_url')
+            if backup_urls is not None:
+                for backup_url in backup_urls.findall('./url'):
+                    formats.append({'url': backup_url.text})
+            formats.reverse()
 
             entries.append({
-                'id': '%s_part%d' % (video_id, i),
+                'id': '%s_part%s' % (cid, xpath_text(durl, './order')),
                 'title': title,
+                'duration': int_or_none(xpath_text(durl, './length'), 1000),
                 'formats': formats,
-                'duration': duration,
-                'upload_date': upload_date,
-                'thumbnail': thumbnail,
             })
 
-            i += 1
-
-        return {
-            '_type': 'multi_video',
-            'entries': entries,
-            'id': video_id,
-            'title': title
+        info = {
+            'id': compat_str(cid),
+            'title': title,
+            'description': view_data.get('description'),
+            'thumbnail': view_data.get('pic'),
+            'uploader': view_data.get('author'),
+            'timestamp': int_or_none(view_data.get('created')),
+            'view_count': int_or_none(view_data.get('play')),
+            'duration': int_or_none(xpath_text(doc, './timelength')),
         }
+
+        if len(entries) == 1:
+            entries[0].update(info)
+            return entries[0]
+        else:
+            info.update({
+                '_type': 'multi_video',
+                'id': video_id,
+                'entries': entries,
+            })
+            return info

youtube_dl/extractor/bleacherreport.py

@@ -0,0 +1,106 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .amp import AMPIE
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class BleacherReportIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/articles/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://bleacherreport.com/articles/2496438-fsu-stat-projections-is-jalen-ramsey-best-defensive-player-in-college-football',
+        'md5': 'a3ffc3dc73afdbc2010f02d98f990f20',
+        'info_dict': {
+            'id': '2496438',
+            'ext': 'mp4',
+            'title': 'FSU Stat Projections: Is Jalen Ramsey Best Defensive Player in College Football?',
+            'uploader_id': 3992341,
+            'description': 'CFB, ACC, Florida State',
+            'timestamp': 1434380212,
+            'upload_date': '20150615',
+            'uploader': 'Team Stream Now ',
+        },
+        'add_ie': ['Ooyala'],
+    }, {
+        'url': 'http://bleacherreport.com/articles/2586817-aussie-golfers-get-fright-of-their-lives-after-being-chased-by-angry-kangaroo',
+        'md5': 'af5f90dc9c7ba1c19d0a3eac806bbf50',
+        'info_dict': {
+            'id': '2586817',
+            'ext': 'mp4',
+            'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo',
+            'timestamp': 1446839961,
+            'uploader': 'Sean Fay',
+            'description': 'md5:825e94e0f3521df52fa83b2ed198fa20',
+            'uploader_id': 6466954,
+            'upload_date': '20151011',
+        },
+        'add_ie': ['Youtube'],
+    }]
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+
+        article_data = self._download_json('http://api.bleacherreport.com/api/v1/articles/%s' % article_id, article_id)['article']
+
+        thumbnails = []
+        primary_photo = article_data.get('primaryPhoto')
+        if primary_photo:
+            thumbnails = [{
+                'url': primary_photo['url'],
+                'width': primary_photo.get('width'),
+                'height': primary_photo.get('height'),
+            }]
+
+        info = {
+            '_type': 'url_transparent',
+            'id': article_id,
+            'title': article_data['title'],
+            'uploader': article_data.get('author', {}).get('name'),
+            'uploader_id': article_data.get('authorId'),
+            'timestamp': parse_iso8601(article_data.get('createdAt')),
+            'thumbnails': thumbnails,
+            'comment_count': int_or_none(article_data.get('commentsCount')),
+            'view_count': int_or_none(article_data.get('hitCount')),
+        }
+
+        video = article_data.get('video')
+        if video:
+            video_type = video['type']
+            if video_type == 'cms.bleacherreport.com':
+                info['url'] = 'http://bleacherreport.com/video_embed?id=%s' % video['id']
+            elif video_type == 'ooyala.com':
+                info['url'] = 'ooyala:%s' % video['id']
+            elif video_type == 'youtube.com':
+                info['url'] = video['id']
+            elif video_type == 'vine.co':
+                info['url'] = 'https://vine.co/v/%s' % video['id']
+            else:
+                info['url'] = video_type + video['id']
+            return info
+        else:
+            raise ExtractorError('no video in the article', expected=True)
+
+
+class BleacherReportCMSIE(AMPIE):
+    _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36})'
+    _TESTS = [{
+        'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
+        'md5': '8c2c12e3af7805152675446c905d159b',
+        'info_dict': {
+            'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
+            'ext': 'flv',
+            'title': 'Cena vs. Rollins Would Expose the Heavyweight Division',
+            'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        info = self._extract_feed_info('http://cms.bleacherreport.com/media/items/%s/akamai.json' % video_id)
+        info['id'] = video_id
+        return info

youtube_dl/extractor/bliptv.py

@@ -1,292 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-
-from ..compat import (
-    compat_urllib_request,
-    compat_urlparse,
-)
-from ..utils import (
-    clean_html,
-    int_or_none,
-    parse_iso8601,
-    unescapeHTML,
-    xpath_text,
-    xpath_with_ns,
-)
-
-
-class BlipTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+_]+)))'
-
-    _TESTS = [
-        {
-            'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
-            'md5': '80baf1ec5c3d2019037c1c707d676b9f',
-            'info_dict': {
-                'id': '5779306',
-                'ext': 'm4v',
-                'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
-                'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
-                'timestamp': 1323138843,
-                'upload_date': '20111206',
-                'uploader': 'cbr',
-                'uploader_id': '679425',
-                'duration': 81,
-            }
-        },
-        {
-            # https://github.com/rg3/youtube-dl/pull/2274
-            'note': 'Video with subtitles',
-            'url': 'http://blip.tv/play/h6Uag5OEVgI.html',
-            'md5': '309f9d25b820b086ca163ffac8031806',
-            'info_dict': {
-                'id': '6586561',
-                'ext': 'mp4',
-                'title': 'Red vs. Blue Season 11 Episode 1',
-                'description': 'One-Zero-One',
-                'timestamp': 1371261608,
-                'upload_date': '20130615',
-                'uploader': 'redvsblue',
-                'uploader_id': '792887',
-                'duration': 279,
-            }
-        },
-        {
-            # https://bugzilla.redhat.com/show_bug.cgi?id=967465
-            'url': 'http://a.blip.tv/api.swf#h6Uag5KbVwI',
-            'md5': '314e87b1ebe7a48fcbfdd51b791ce5a6',
-            'info_dict': {
-                'id': '6573122',
-                'ext': 'mov',
-                'upload_date': '20130520',
-                'description': 'Two hapless space marines argue over what to do when they realize they have an astronomically huge problem on their hands.',
-                'title': 'Red vs. Blue Season 11 Trailer',
-                'timestamp': 1369029609,
-                'uploader': 'redvsblue',
-                'uploader_id': '792887',
-            }
-        },
-        {
-            'url': 'http://blip.tv/play/gbk766dkj4Yn',
-            'md5': 'fe0a33f022d49399a241e84a8ea8b8e3',
-            'info_dict': {
-                'id': '1749452',
-                'ext': 'mp4',
-                'upload_date': '20090208',
-                'description': 'Witness the first appearance of the Nostalgia Critic character, as Doug reviews the movie Transformers.',
-                'title': 'Nostalgia Critic: Transformers',
-                'timestamp': 1234068723,
-                'uploader': 'NostalgiaCritic',
-                'uploader_id': '246467',
-            }
-        },
-        {
-            # https://github.com/rg3/youtube-dl/pull/4404
-            'note': 'Audio only',
-            'url': 'http://blip.tv/hilarios-productions/weekly-manga-recap-kingdom-7119982',
-            'md5': '76c0a56f24e769ceaab21fbb6416a351',
-            'info_dict': {
-                'id': '7103299',
-                'ext': 'flv',
-                'title': 'Weekly Manga Recap: Kingdom',
-                'description': 'And then Shin breaks the enemy line, and he&apos;s all like HWAH! And then he slices a guy and it&apos;s all like FWASHING! And... it&apos;s really hard to describe the best parts of this series without breaking down into sound effects, okay?',
-                'timestamp': 1417660321,
-                'upload_date': '20141204',
-                'uploader': 'The Rollo T',
-                'uploader_id': '407429',
-                'duration': 7251,
-                'vcodec': 'none',
-            }
-        },
-        {
-            # missing duration
-            'url': 'http://blip.tv/rss/flash/6700880',
-            'info_dict': {
-                'id': '6684191',
-                'ext': 'm4v',
-                'title': 'Cowboy Bebop: Gateway Shuffle Review',
-                'description': 'md5:3acc480c0f9ae157f5fe88547ecaf3f8',
-                'timestamp': 1386639757,
-                'upload_date': '20131210',
-                'uploader': 'sfdebris',
-                'uploader_id': '706520',
-            }
-        }
-    ]
-
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
-        if mobj:
-            return 'http://blip.tv/a/a-' + mobj.group(1)
-        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
-        if mobj:
-            return mobj.group(1)
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        lookup_id = mobj.group('lookup_id')
-
-        # See https://github.com/rg3/youtube-dl/issues/857 and
-        # https://github.com/rg3/youtube-dl/issues/4197
-        if lookup_id:
-            urlh = self._request_webpage(
-                'http://blip.tv/play/%s' % lookup_id, lookup_id, 'Resolving lookup id')
-            url = compat_urlparse.urlparse(urlh.geturl())
-            qs = compat_urlparse.parse_qs(url.query)
-            mobj = re.match(self._VALID_URL, qs['file'][0])
-
-        video_id = mobj.group('id')
-
-        rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS')
-
-        def _x(p):
-            return xpath_with_ns(p, {
-                'blip': 'http://blip.tv/dtd/blip/1.0',
-                'media': 'http://search.yahoo.com/mrss/',
-                'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
-            })
-
-        item = rss.find('channel/item')
-
-        video_id = xpath_text(item, _x('blip:item_id'), 'video id') or lookup_id
-        title = xpath_text(item, 'title', 'title', fatal=True)
-        description = clean_html(xpath_text(item, _x('blip:puredescription'), 'description'))
-        timestamp = parse_iso8601(xpath_text(item, _x('blip:datestamp'), 'timestamp'))
-        uploader = xpath_text(item, _x('blip:user'), 'uploader')
-        uploader_id = xpath_text(item, _x('blip:userid'), 'uploader id')
-        duration = int_or_none(xpath_text(item, _x('blip:runtime'), 'duration'))
-        media_thumbnail = item.find(_x('media:thumbnail'))
-        thumbnail = (media_thumbnail.get('url') if media_thumbnail is not None
-                     else xpath_text(item, 'image', 'thumbnail'))
-        categories = [category.text for category in item.findall('category') if category is not None]
-
-        formats = []
-        subtitles_urls = {}
-
-        media_group = item.find(_x('media:group'))
-        for media_content in media_group.findall(_x('media:content')):
-            url = media_content.get('url')
-            role = media_content.get(_x('blip:role'))
-            msg = self._download_webpage(
-                url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url',
-                video_id, 'Resolving URL for %s' % role)
-            real_url = compat_urlparse.parse_qs(msg.strip())['message'][0]
-
-            media_type = media_content.get('type')
-            if media_type == 'text/srt' or url.endswith('.srt'):
-                LANGS = {
-                    'english': 'en',
-                }
-                lang = role.rpartition('-')[-1].strip().lower()
-                langcode = LANGS.get(lang, lang)
-                subtitles_urls[langcode] = url
-            elif media_type.startswith('video/'):
-                formats.append({
-                    'url': real_url,
-                    'format_id': role,
-                    'format_note': media_type,
-                    'vcodec': media_content.get(_x('blip:vcodec')) or 'none',
-                    'acodec': media_content.get(_x('blip:acodec')),
-                    'filesize': media_content.get('filesize'),
-                    'width': int_or_none(media_content.get('width')),
-                    'height': int_or_none(media_content.get('height')),
-                })
-        self._check_formats(formats, video_id)
-        self._sort_formats(formats)
-
-        subtitles = self.extract_subtitles(video_id, subtitles_urls)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'timestamp': timestamp,
-            'uploader': uploader,
-            'uploader_id': uploader_id,
-            'duration': duration,
-            'thumbnail': thumbnail,
-            'categories': categories,
-            'formats': formats,
-            'subtitles': subtitles,
-        }
-
-    def _get_subtitles(self, video_id, subtitles_urls):
-        subtitles = {}
-        for lang, url in subtitles_urls.items():
-            # For some weird reason, blip.tv serves a video instead of subtitles
-            # when we request with a common UA
-            req = compat_urllib_request.Request(url)
-            req.add_header('User-Agent', 'youtube-dl')
-            subtitles[lang] = [{
-                # The extension is 'srt' but it's actually an 'ass' file
-                'ext': 'ass',
-                'data': self._download_webpage(req, None, note=False),
-            }]
-        return subtitles
-
-
-class BlipTVUserIE(InfoExtractor):
-    _VALID_URL = r'(?:(?:https?://(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$'
-    _PAGE_SIZE = 12
-    IE_NAME = 'blip.tv:user'
-    _TEST = {
-        'url': 'http://blip.tv/actone',
-        'info_dict': {
-            'id': 'actone',
-            'title': 'Act One: The Series',
-        },
-        'playlist_count': 5,
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        username = mobj.group(1)
-
-        page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
-
-        page = self._download_webpage(url, username, 'Downloading user page')
-        mobj = re.search(r'data-users-id="([^"]+)"', page)
-        page_base = page_base % mobj.group(1)
-        title = self._og_search_title(page)
-
-        # Download video ids using BlipTV Ajax calls. Result size per
-        # query is limited (currently to 12 videos) so we need to query
-        # page by page until there are no video ids - it means we got
-        # all of them.
-
-        video_ids = []
-        pagenum = 1
-
-        while True:
-            url = page_base + "&page=" + str(pagenum)
-            page = self._download_webpage(
-                url, username, 'Downloading video ids from page %d' % pagenum)
-
-            # Extract video identifiers
-            ids_in_page = []
-
-            for mobj in re.finditer(r'href="/([^"]+)"', page):
-                if mobj.group(1) not in ids_in_page:
-                    ids_in_page.append(unescapeHTML(mobj.group(1)))
-
-            video_ids.extend(ids_in_page)
-
-            # A little optimization - if current page is not
-            # "full", ie. does not contain PAGE_SIZE video ids then
-            # we can assume that this page is the last one - there
-            # are no more ids on further pages - no need to query
-            # again.
-
-            if len(ids_in_page) < self._PAGE_SIZE:
-                break
-
-            pagenum += 1
-
-        urls = ['http://blip.tv/%s' % video_id for video_id in video_ids]
-        url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls]
-        return self.playlist_result(
-            url_entries, playlist_title=title, playlist_id=username)

youtube_dl/extractor/bloomberg.py

@@ -6,9 +6,9 @@ from .common import InfoExtractor
 
 
 class BloombergIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.bloomberg\.com/news/videos/[^/]+/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?bloomberg\.com/(?:[^/]+/)*(?P<id>[^/?#]+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2',
         # The md5 checksum changes
         'info_dict': {
@@ -17,22 +17,35 @@ class BloombergIE(InfoExtractor):
             'title': 'Shah\'s Presentation on Foreign-Exchange Strategies',
             'description': 'md5:a8ba0302912d03d246979735c17d2761',
         },
-    }
+    }, {
+        'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.bloomberg.com/politics/videos/2015-11-25/karl-rove-on-jeb-bush-s-struggles-stopping-trump',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         name = self._match_id(url)
         webpage = self._download_webpage(url, name)
-        video_id = self._search_regex(r'"bmmrId":"(.+?)"', webpage, 'id')
+        video_id = self._search_regex(
+            r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>.+?)\1',
+            webpage, 'id', group='url')
         title = re.sub(': Video$', '', self._og_search_title(webpage))
 
         embed_info = self._download_json(
             'http://www.bloomberg.com/api/embed?id=%s' % video_id, video_id)
         formats = []
         for stream in embed_info['streams']:
-            if stream["muxing_format"] == "TS":
-                formats.extend(self._extract_m3u8_formats(stream['url'], video_id))
+            stream_url = stream.get('url')
+            if not stream_url:
+                continue
+            if stream['muxing_format'] == 'TS':
+                formats.extend(self._extract_m3u8_formats(
+                    stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
             else:
-                formats.extend(self._extract_f4m_formats(stream['url'], video_id))
+                formats.extend(self._extract_f4m_formats(
+                    stream_url, video_id, f4m_id='hds', fatal=False))
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/bpb.py

@@ -1,7 +1,13 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    determine_ext,
+)
 
 
 class BpbIE(InfoExtractor):
@@ -10,7 +16,8 @@ class BpbIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',
-        'md5': '0792086e8e2bfbac9cdf27835d5f2093',
+        # md5 fails in Python 2.6 due to buggy server response and wrong handling of urllib2
+        'md5': 'c4f84c8a8044ca9ff68bb8441d300b3f',
         'info_dict': {
             'id': '297',
             'ext': 'mp4',
@@ -25,13 +32,26 @@ class BpbIE(InfoExtractor):
 
         title = self._html_search_regex(
             r'<h2 class="white">(.*?)</h2>', webpage, 'title')
-        video_url = self._html_search_regex(
-            r'(http://film\.bpb\.de/player/dokument_[0-9]+\.mp4)',
-            webpage, 'video URL')
+        video_info_dicts = re.findall(
+            r"({\s*src:\s*'http://film\.bpb\.de/[^}]+})", webpage)
+
+        formats = []
+        for video_info in video_info_dicts:
+            video_info = self._parse_json(video_info, video_id, transform_source=js_to_json)
+            quality = video_info['quality']
+            video_url = video_info['src']
+            formats.append({
+                'url': video_url,
+                'preference': 10 if quality == 'high' else 0,
+                'format_note': quality,
+                'format_id': '%s-%s' % (quality, determine_ext(video_url)),
+            })
+
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'url': video_url,
+            'formats': formats,
             'title': title,
             'description': self._og_search_description(webpage),
         }

youtube_dl/extractor/br.py

@@ -1,18 +1,21 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
     parse_duration,
+    xpath_element,
+    xpath_text,
 )
 
 
 class BRIE(InfoExtractor):
     IE_DESC = 'Bayerischer Rundfunk Mediathek'
-    _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html'
-    _BASE_URL = 'http://www.br.de'
+    _VALID_URL = r'(?P<base_url>https?://(?:www\.)?br(?:-klassik)?\.de)/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html'
 
     _TESTS = [
         {
@@ -22,7 +25,7 @@ class BRIE(InfoExtractor):
                 'id': '48f656ef-287e-486f-be86-459122db22cc',
                 'ext': 'mp4',
                 'title': 'Die böse Überraschung',
-                'description': 'Betriebliche Altersvorsorge: Die böse Überraschung',
+                'description': 'md5:ce9ac81b466ce775b8018f6801b48ac9',
                 'duration': 180,
                 'uploader': 'Reinhard Weber',
                 'upload_date': '20150422',
@@ -30,23 +33,23 @@ class BRIE(InfoExtractor):
         },
         {
             'url': 'http://www.br.de/nachrichten/oberbayern/inhalt/muenchner-polizeipraesident-schreiber-gestorben-100.html',
-            'md5': 'a44396d73ab6a68a69a568fae10705bb',
+            'md5': 'af3a3a4aa43ff0ce6a89504c67f427ef',
             'info_dict': {
                 'id': 'a4b83e34-123d-4b81-9f4e-c0d3121a4e05',
-                'ext': 'mp4',
+                'ext': 'flv',
                 'title': 'Manfred Schreiber ist tot',
-                'description': 'Abendschau kompakt: Manfred Schreiber ist tot',
+                'description': 'md5:b454d867f2a9fc524ebe88c3f5092d97',
                 'duration': 26,
             }
         },
         {
-            'url': 'http://www.br.de/radio/br-klassik/sendungen/allegro/premiere-urauffuehrung-the-land-2015-dance-festival-muenchen-100.html',
+            'url': 'https://www.br-klassik.de/audio/peeping-tom-premierenkritik-dance-festival-muenchen-100.html',
             'md5': '8b5b27c0b090f3b35eac4ab3f7a73d3d',
             'info_dict': {
                 'id': '74c603c9-26d3-48bb-b85b-079aeed66e0b',
                 'ext': 'aac',
                 'title': 'Kurzweilig und sehr bewegend',
-                'description': '"The Land" von Peeping Tom: Kurzweilig und sehr bewegend',
+                'description': 'md5:0351996e3283d64adeb38ede91fac54e',
                 'duration': 296,
             }
         },
@@ -57,7 +60,7 @@ class BRIE(InfoExtractor):
                 'id': '6ba73750-d405-45d3-861d-1ce8c524e059',
                 'ext': 'mp4',
                 'title': 'Umweltbewusster Häuslebauer',
-                'description': 'Uwe Erdelt: Umweltbewusster Häuslebauer',
+                'description': 'md5:d52dae9792d00226348c1dbb13c9bae2',
                 'duration': 116,
             }
         },
@@ -68,7 +71,7 @@ class BRIE(InfoExtractor):
                 'id': 'd982c9ce-8648-4753-b358-98abb8aec43d',
                 'ext': 'mp4',
                 'title': 'Folge 1 - Metaphysik',
-                'description': 'Kant für Anfänger: Folge 1 - Metaphysik',
+                'description': 'md5:bb659990e9e59905c3d41e369db1fbe3',
                 'duration': 893,
                 'uploader': 'Eva Maria Steimle',
                 'upload_date': '20140117',
@@ -77,28 +80,31 @@ class BRIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        base_url, display_id = re.search(self._VALID_URL, url).groups()
         page = self._download_webpage(url, display_id)
         xml_url = self._search_regex(
             r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/(?:[a-z0-9\-]+/)+[a-z0-9/~_.-]+)'}\)\);", page, 'XMLURL')
-        xml = self._download_xml(self._BASE_URL + xml_url, None)
+        xml = self._download_xml(base_url + xml_url, display_id)
 
         medias = []
 
         for xml_media in xml.findall('video') + xml.findall('audio'):
+            media_id = xml_media.get('externalId')
             media = {
-                'id': xml_media.get('externalId'),
-                'title': xml_media.find('title').text,
-                'duration': parse_duration(xml_media.find('duration').text),
-                'formats': self._extract_formats(xml_media.find('assets')),
-                'thumbnails': self._extract_thumbnails(xml_media.find('teaserImage/variants')),
-                'description': ' '.join(xml_media.find('shareTitle').text.splitlines()),
-                'webpage_url': xml_media.find('permalink').text
+                'id': media_id,
+                'title': xpath_text(xml_media, 'title', 'title', True),
+                'duration': parse_duration(xpath_text(xml_media, 'duration')),
+                'formats': self._extract_formats(xpath_element(
+                    xml_media, 'assets'), media_id),
+                'thumbnails': self._extract_thumbnails(xpath_element(
+                    xml_media, 'teaserImage/variants'), base_url),
+                'description': xpath_text(xml_media, 'desc'),
+                'webpage_url': xpath_text(xml_media, 'permalink'),
+                'uploader': xpath_text(xml_media, 'author'),
             }
-            if xml_media.find('author').text:
-                media['uploader'] = xml_media.find('author').text
-            if xml_media.find('broadcastDate').text:
-                media['upload_date'] = ''.join(reversed(xml_media.find('broadcastDate').text.split('.')))
+            broadcast_date = xpath_text(xml_media, 'broadcastDate')
+            if broadcast_date:
+                media['upload_date'] = ''.join(reversed(broadcast_date.split('.')))
             medias.append(media)
 
         if len(medias) > 1:
@@ -109,35 +115,54 @@ class BRIE(InfoExtractor):
             raise ExtractorError('No media entries found')
         return medias[0]
 
-    def _extract_formats(self, assets):
-
-        def text_or_none(asset, tag):
-            elem = asset.find(tag)
-            return None if elem is None else elem.text
-
-        formats = [{
-            'url': text_or_none(asset, 'downloadUrl'),
-            'ext': text_or_none(asset, 'mediaType'),
-            'format_id': asset.get('type'),
-            'width': int_or_none(text_or_none(asset, 'frameWidth')),
-            'height': int_or_none(text_or_none(asset, 'frameHeight')),
-            'tbr': int_or_none(text_or_none(asset, 'bitrateVideo')),
-            'abr': int_or_none(text_or_none(asset, 'bitrateAudio')),
-            'vcodec': text_or_none(asset, 'codecVideo'),
-            'acodec': text_or_none(asset, 'codecAudio'),
-            'container': text_or_none(asset, 'mediaType'),
-            'filesize': int_or_none(text_or_none(asset, 'size')),
-        } for asset in assets.findall('asset')
-            if asset.find('downloadUrl') is not None]
-
+    def _extract_formats(self, assets, media_id):
+        formats = []
+        for asset in assets.findall('asset'):
+            format_url = xpath_text(asset, ['downloadUrl', 'url'])
+            asset_type = asset.get('type')
+            if asset_type == 'HDS':
+                formats.extend(self._extract_f4m_formats(
+                    format_url + '?hdcore=3.2.0', media_id, f4m_id='hds', fatal=False))
+            elif asset_type == 'HLS':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, media_id, 'mp4', 'm3u8_native', m3u8_id='hds', fatal=False))
+            else:
+                format_info = {
+                    'ext': xpath_text(asset, 'mediaType'),
+                    'width': int_or_none(xpath_text(asset, 'frameWidth')),
+                    'height': int_or_none(xpath_text(asset, 'frameHeight')),
+                    'tbr': int_or_none(xpath_text(asset, 'bitrateVideo')),
+                    'abr': int_or_none(xpath_text(asset, 'bitrateAudio')),
+                    'vcodec': xpath_text(asset, 'codecVideo'),
+                    'acodec': xpath_text(asset, 'codecAudio'),
+                    'container': xpath_text(asset, 'mediaType'),
+                    'filesize': int_or_none(xpath_text(asset, 'size')),
+                }
+                format_url = self._proto_relative_url(format_url)
+                if format_url:
+                    http_format_info = format_info.copy()
+                    http_format_info.update({
+                        'url': format_url,
+                        'format_id': 'http-%s' % asset_type,
+                    })
+                    formats.append(http_format_info)
+                server_prefix = xpath_text(asset, 'serverPrefix')
+                if server_prefix:
+                    rtmp_format_info = format_info.copy()
+                    rtmp_format_info.update({
+                        'url': server_prefix,
+                        'play_path': xpath_text(asset, 'fileName'),
+                        'format_id': 'rtmp-%s' % asset_type,
+                    })
+                    formats.append(rtmp_format_info)
         self._sort_formats(formats)
         return formats
 
-    def _extract_thumbnails(self, variants):
+    def _extract_thumbnails(self, variants, base_url):
         thumbnails = [{
-            'url': self._BASE_URL + variant.find('url').text,
-            'width': int_or_none(variant.find('width').text),
-            'height': int_or_none(variant.find('height').text),
-        } for variant in variants.findall('variant')]
+            'url': base_url + xpath_text(variant, 'url'),
+            'width': int_or_none(xpath_text(variant, 'width')),
+            'height': int_or_none(xpath_text(variant, 'height')),
+        } for variant in variants.findall('variant') if xpath_text(variant, 'url')]
         thumbnails.sort(key=lambda x: x['width'] * x['height'], reverse=True)
         return thumbnails

youtube_dl/extractor/brightcove.py

@@ -3,15 +3,14 @@ from __future__ import unicode_literals
 
 import re
 import json
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_etree_fromstring,
     compat_parse_qs,
     compat_str,
     compat_urllib_parse,
     compat_urllib_parse_urlparse,
-    compat_urllib_request,
     compat_urlparse,
     compat_xml_parse_error,
 )
@@ -20,12 +19,18 @@ from ..utils import (
     ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
+    float_or_none,
+    js_to_json,
+    int_or_none,
+    parse_iso8601,
+    sanitized_Request,
     unescapeHTML,
     unsmuggle_url,
 )
 
 
-class BrightcoveIE(InfoExtractor):
+class BrightcoveLegacyIE(InfoExtractor):
+    IE_NAME = 'brightcove:legacy'
     _VALID_URL = r'(?:https?://.*brightcove\.com/(services|viewer).*?\?|brightcove:)(?P<query>.*)'
     _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
 
@@ -119,7 +124,7 @@ class BrightcoveIE(InfoExtractor):
         object_str = fix_xml_ampersands(object_str)
 
         try:
-            object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
+            object_doc = compat_etree_fromstring(object_str.encode('utf-8'))
         except compat_xml_parse_error:
             return
 
@@ -245,7 +250,7 @@ class BrightcoveIE(InfoExtractor):
 
     def _get_video_info(self, video_id, query_str, query, referer=None):
         request_url = self._FEDERATED_URL_TEMPLATE % query_str
-        req = compat_urllib_request.Request(request_url)
+        req = sanitized_Request(request_url)
         linkBase = query.get('linkBaseURL')
         if linkBase is not None:
             referer = linkBase[0]
@@ -346,3 +351,181 @@ class BrightcoveIE(InfoExtractor):
         if 'url' not in info and not info.get('formats'):
             raise ExtractorError('Unable to extract video url for %s' % info['id'])
         return info
+
+
+class BrightcoveNewIE(InfoExtractor):
+    IE_NAME = 'brightcove:new'
+    _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>(?:ref:)?\d+)'
+    _TESTS = [{
+        'url': 'http://players.brightcove.net/929656772001/e41d32dc-ec74-459e-a845-6c69f7b724ea_default/index.html?videoId=4463358922001',
+        'md5': 'c8100925723840d4b0d243f7025703be',
+        'info_dict': {
+            'id': '4463358922001',
+            'ext': 'mp4',
+            'title': 'Meet the man behind Popcorn Time',
+            'description': 'md5:eac376a4fe366edc70279bfb681aea16',
+            'duration': 165.768,
+            'timestamp': 1441391203,
+            'upload_date': '20150904',
+            'uploader_id': '929656772001',
+            'formats': 'mincount:22',
+        },
+    }, {
+        # with rtmp streams
+        'url': 'http://players.brightcove.net/4036320279001/5d112ed9-283f-485f-a7f9-33f42e8bc042_default/index.html?videoId=4279049078001',
+        'info_dict': {
+            'id': '4279049078001',
+            'ext': 'mp4',
+            'title': 'Titansgrave: Chapter 0',
+            'description': 'Titansgrave: Chapter 0',
+            'duration': 1242.058,
+            'timestamp': 1433556729,
+            'upload_date': '20150606',
+            'uploader_id': '4036320279001',
+            'formats': 'mincount:41',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        # ref: prefixed video id
+        'url': 'http://players.brightcove.net/3910869709001/21519b5c-4b3b-4363-accb-bdc8f358f823_default/index.html?videoId=ref:7069442',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_url(webpage):
+        urls = BrightcoveNewIE._extract_urls(webpage)
+        return urls[0] if urls else None
+
+    @staticmethod
+    def _extract_urls(webpage):
+        # Reference:
+        # 1. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideoiniframe
+        # 2. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideousingjavascript
+        # 3. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/embed-in-page.html
+        # 4. https://support.brightcove.com/en/video-cloud/docs/dynamically-assigning-videos-player
+
+        entries = []
+
+        # Look for iframe embeds [1]
+        for _, url in re.findall(
+                r'<iframe[^>]+src=(["\'])((?:https?:)//players\.brightcove\.net/\d+/[^/]+/index\.html.+?)\1', webpage):
+            entries.append(url)
+
+        # Look for embed_in_page embeds [2]
+        for video_id, account_id, player_id, embed in re.findall(
+                # According to examples from [3] it's unclear whether video id
+                # may be optional and what to do when it is
+                # According to [4] data-video-id may be prefixed with ref:
+                r'''(?sx)
+                    <video[^>]+
+                        data-video-id=["\']((?:ref:)?\d+)["\'][^>]*>.*?
+                    </video>.*?
+                    <script[^>]+
+                        src=["\'](?:https?:)?//players\.brightcove\.net/
+                        (\d+)/([\da-f-]+)_([^/]+)/index\.min\.js
+                ''', webpage):
+            entries.append(
+                'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
+                % (account_id, player_id, embed, video_id))
+
+        return entries
+
+    def _real_extract(self, url):
+        account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups()
+
+        webpage = self._download_webpage(
+            'http://players.brightcove.net/%s/%s_%s/index.min.js'
+            % (account_id, player_id, embed), video_id)
+
+        policy_key = None
+
+        catalog = self._search_regex(
+            r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
+        if catalog:
+            catalog = self._parse_json(
+                js_to_json(catalog), video_id, fatal=False)
+            if catalog:
+                policy_key = catalog.get('policyKey')
+
+        if not policy_key:
+            policy_key = self._search_regex(
+                r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
+                webpage, 'policy key', group='pk')
+
+        req = sanitized_Request(
+            'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s'
+            % (account_id, video_id),
+            headers={'Accept': 'application/json;pk=%s' % policy_key})
+        json_data = self._download_json(req, video_id)
+
+        title = json_data['name']
+
+        formats = []
+        for source in json_data.get('sources', []):
+            source_type = source.get('type')
+            src = source.get('src')
+            if source_type == 'application/x-mpegURL':
+                if not src:
+                    continue
+                formats.extend(self._extract_m3u8_formats(
+                    src, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            else:
+                streaming_src = source.get('streaming_src')
+                stream_name, app_name = source.get('stream_name'), source.get('app_name')
+                if not src and not streaming_src and (not stream_name or not app_name):
+                    continue
+                tbr = float_or_none(source.get('avg_bitrate'), 1000)
+                height = int_or_none(source.get('height'))
+                f = {
+                    'tbr': tbr,
+                    'width': int_or_none(source.get('width')),
+                    'height': height,
+                    'filesize': int_or_none(source.get('size')),
+                    'container': source.get('container'),
+                    'vcodec': source.get('codec'),
+                    'ext': source.get('container').lower(),
+                }
+
+                def build_format_id(kind):
+                    format_id = kind
+                    if tbr:
+                        format_id += '-%dk' % int(tbr)
+                    if height:
+                        format_id += '-%dp' % height
+                    return format_id
+
+                if src or streaming_src:
+                    f.update({
+                        'url': src or streaming_src,
+                        'format_id': build_format_id('http' if src else 'http-streaming'),
+                        'preference': 2 if src else 1,
+                    })
+                else:
+                    f.update({
+                        'url': app_name,
+                        'play_path': stream_name,
+                        'format_id': build_format_id('rtmp'),
+                    })
+                formats.append(f)
+        self._sort_formats(formats)
+
+        description = json_data.get('description')
+        thumbnail = json_data.get('thumbnail')
+        timestamp = parse_iso8601(json_data.get('published_at'))
+        duration = float_or_none(json_data.get('duration'), 1000)
+        tags = json_data.get('tags', [])
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'uploader_id': account_id,
+            'formats': formats,
+            'tags': tags,
+        }

youtube_dl/extractor/byutv.py

@@ -14,9 +14,10 @@ class BYUtvIE(InfoExtractor):
         'info_dict': {
             'id': 'studio-c-season-5-episode-5',
             'ext': 'mp4',
-            'description': 'md5:5438d33774b6bdc662f9485a340401cc',
+            'description': 'md5:e07269172baff037f8e8bf9956bc9747',
             'title': 'Season 5 Episode 5',
-            'thumbnail': 're:^https?://.*\.jpg$'
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 1486.486,
         },
         'params': {
             'skip_download': True,

youtube_dl/extractor/canal13cl.py

@@ -1,48 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-
-
-class Canal13clIE(InfoExtractor):
-    _VALID_URL = r'^http://(?:www\.)?13\.cl/(?:[^/?#]+/)*(?P<id>[^/?#]+)'
-    _TEST = {
-        'url': 'http://www.13.cl/t13/nacional/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
-        'md5': '4cb1fa38adcad8fea88487a078831755',
-        'info_dict': {
-            'id': '1403022125',
-            'display_id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
-            'ext': 'mp4',
-            'title': 'El "círculo de hierro" de Michelle Bachelet en su regreso a La Moneda',
-            'description': '(Foto: Agencia Uno) En nueve días más, Michelle Bachelet va a asumir por segunda vez como presidenta de la República. Entre aquellos que la acompañarán hay caras que se repiten y otras que se consolidan en su entorno de colaboradores más cercanos.',
-        }
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('id')
-
-        webpage = self._download_webpage(url, display_id)
-
-        title = self._html_search_meta(
-            'twitter:title', webpage, 'title', fatal=True)
-        description = self._html_search_meta(
-            'twitter:description', webpage, 'description')
-        url = self._html_search_regex(
-            r'articuloVideo = \"(.*?)\"', webpage, 'url')
-        real_id = self._search_regex(
-            r'[^0-9]([0-9]{7,})[^0-9]', url, 'id', default=display_id)
-        thumbnail = self._html_search_regex(
-            r'articuloImagen = \"(.*?)\"', webpage, 'thumbnail')
-
-        return {
-            'id': real_id,
-            'display_id': display_id,
-            'url': url,
-            'title': title,
-            'description': description,
-            'ext': 'mp4',
-            'thumbnail': thumbnail,
-        }

youtube_dl/extractor/canalc2.py

@@ -4,38 +4,65 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import parse_duration
 
 
 class Canalc2IE(InfoExtractor):
     IE_NAME = 'canalc2.tv'
-    _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:(?:www\.)?canalc2\.tv/video/|archives-canalc2\.u-strasbg\.fr/video\.asp\?.*\bidVideo=)(?P<id>\d+)'
 
-    _TEST = {
-        'url': 'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
+    _TESTS = [{
+        'url': 'http://www.canalc2.tv/video/12163',
         'md5': '060158428b650f896c542dfbb3d6487f',
         'info_dict': {
             'id': '12163',
-            'ext': 'mp4',
-            'title': 'Terrasses du Numérique'
+            'ext': 'flv',
+            'title': 'Terrasses du Numérique',
+            'duration': 122,
+        },
+        'params': {
+            'skip_download': True,  # Requires rtmpdump
         }
-    }
+    }, {
+        'url': 'http://archives-canalc2.u-strasbg.fr/video.asp?idVideo=11427&voir=oui',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        video_id = re.match(self._VALID_URL, url).group('id')
-        # We need to set the voir field for getting the file name
-        url = 'http://www.canalc2.tv/video.asp?idVideo=%s&voir=oui' % video_id
-        webpage = self._download_webpage(url, video_id)
-        file_name = self._search_regex(
-            r"so\.addVariable\('file','(.*?)'\);",
-            webpage, 'file name')
-        video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://www.canalc2.tv/video/%s' % video_id, video_id)
+
+        formats = []
+        for _, video_url in re.findall(r'file\s*=\s*(["\'])(.+?)\1', webpage):
+            if video_url.startswith('rtmp://'):
+                rtmp = re.search(
+                    r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
+                formats.append({
+                    'url': rtmp.group('url'),
+                    'format_id': 'rtmp',
+                    'ext': 'flv',
+                    'app': rtmp.group('app'),
+                    'play_path': rtmp.group('play_path'),
+                    'page_url': url,
+                })
+            else:
+                formats.append({
+                    'url': video_url,
+                    'format_id': 'http',
+                })
+        self._sort_formats(formats)
 
         title = self._html_search_regex(
-            r'class="evenement8">(.*?)</a>', webpage, 'title')
+            r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')
+        duration = parse_duration(self._search_regex(
+            r'id=["\']video_duree["\'][^>]*>([^<]+)',
+            webpage, 'duration', fatal=False))
 
         return {
             'id': video_id,
-            'ext': 'mp4',
-            'url': video_url,
             'title': title,
+            'duration': duration,
+            'formats': formats,
         }

youtube_dl/extractor/canalplus.py

@@ -10,13 +10,14 @@ from ..utils import (
     unified_strdate,
     url_basename,
     qualities,
+    int_or_none,
 )
 
 
 class CanalplusIE(InfoExtractor):
     IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
     _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
-    _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s'
+    _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
     _SITE_ID_MAP = {
         'canalplus.fr': 'cplus',
         'piwiplus.fr': 'teletoon',
@@ -26,10 +27,10 @@ class CanalplusIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092',
-        'md5': 'b3481d7ca972f61e37420798d0a9d934',
+        'md5': '12164a6f14ff6df8bd628e8ba9b10b78',
         'info_dict': {
             'id': '1263092',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Le Zapping - 13/05/15',
             'description': 'md5:09738c0d06be4b5d06a0940edb0da73f',
             'upload_date': '20150513',
@@ -56,10 +57,10 @@ class CanalplusIE(InfoExtractor):
         'skip': 'videos get deleted after a while',
     }, {
         'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
-        'md5': 'f3a46edcdf28006598ffaf5b30e6a2d4',
+        'md5': '38b8f7934def74f0d6f3ba6c036a5f82',
         'info_dict': {
             'id': '1213714',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45',
             'description': 'md5:8216206ec53426ea6321321f3b3c16db',
             'upload_date': '20150211',
@@ -78,18 +79,20 @@ class CanalplusIE(InfoExtractor):
         if video_id is None:
             webpage = self._download_webpage(url, display_id)
             video_id = self._search_regex(
-                r'<canal:player[^>]+?videoId="(\d+)"', webpage, 'video id')
+                [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)', r'id=["\']canal_video_player(?P<id>\d+)'],
+                webpage, 'video id', group='id')
 
         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
-        doc = self._download_xml(info_url, video_id, 'Downloading video XML')
+        video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
 
-        video_info = [video for video in doc if video.find('ID').text == video_id][0]
-        media = video_info.find('MEDIA')
-        infos = video_info.find('INFOS')
+        if isinstance(video_data, list):
+            video_data = [video for video in video_data if video.get('ID') == video_id][0]
+        media = video_data['MEDIA']
+        infos = video_data['INFOS']
 
-        preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
+        preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
 
-        fmt_url = next(iter(media.find('VIDEOS'))).text
+        fmt_url = next(iter(media.get('VIDEOS')))
         if '/geo' in fmt_url.lower():
             response = self._request_webpage(
                 HEADRequest(fmt_url), video_id,
@@ -100,35 +103,42 @@ class CanalplusIE(InfoExtractor):
                     expected=True)
 
         formats = []
-        for fmt in media.find('VIDEOS'):
-            format_url = fmt.text
+        for format_id, format_url in media['VIDEOS'].items():
             if not format_url:
                 continue
-            format_id = fmt.tag
             if format_id == 'HLS':
                 formats.extend(self._extract_m3u8_formats(
-                    format_url, video_id, 'mp4', preference=preference(format_id)))
+                    format_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
             elif format_id == 'HDS':
                 formats.extend(self._extract_f4m_formats(
-                    format_url + '?hdcore=2.11.3', video_id, preference=preference(format_id)))
+                    format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False))
             else:
                 formats.append({
-                    'url': format_url,
+                    # the secret extracted ya function in http://player.canalplus.fr/common/js/canalPlayer.js
+                    'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes',
                     'format_id': format_id,
                     'preference': preference(format_id),
                 })
         self._sort_formats(formats)
 
+        thumbnails = [{
+            'id': image_id,
+            'url': image_url,
+        } for image_id, image_url in media.get('images', {}).items()]
+
+        titrage = infos['TITRAGE']
+
         return {
             'id': video_id,
             'display_id': display_id,
-            'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
-                                  infos.find('TITRAGE/SOUS_TITRE').text),
-            'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
-            'thumbnail': media.find('IMAGES/GRAND').text,
-            'description': infos.find('DESCRIPTION').text,
-            'view_count': int(infos.find('NB_VUES').text),
-            'like_count': int(infos.find('NB_LIKES').text),
-            'comment_count': int(infos.find('NB_COMMENTS').text),
+            'title': '%s - %s' % (titrage['TITRE'],
+                                  titrage['SOUS_TITRE']),
+            'upload_date': unified_strdate(infos.get('PUBLICATION', {}).get('DATE')),
+            'thumbnails': thumbnails,
+            'description': infos.get('DESCRIPTION'),
+            'duration': int_or_none(infos.get('DURATION')),
+            'view_count': int_or_none(infos.get('NB_VUES')),
+            'like_count': int_or_none(infos.get('NB_LIKES')),
+            'comment_count': int_or_none(infos.get('NB_COMMENTS')),
             'formats': formats,
         }

youtube_dl/extractor/canvas.py

@@ -0,0 +1,65 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import float_or_none
+
+
+class CanvasIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?canvas\.be/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',
+        'md5': 'ea838375a547ac787d4064d8c7860a6c',
+        'info_dict': {
+            'id': 'mz-ast-5e5f90b6-2d72-4c40-82c2-e134f884e93e',
+            'display_id': 'de-afspraak-veilt-voor-de-warmste-week',
+            'ext': 'mp4',
+            'title': 'De afspraak veilt voor de Warmste Week',
+            'description': 'md5:24cb860c320dc2be7358e0e5aa317ba6',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 49.02,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._search_regex(
+            r'<h1[^>]+class="video__body__header__title"[^>]*>(.+?)</h1>',
+            webpage, 'title', default=None) or self._og_search_title(webpage)
+
+        video_id = self._html_search_regex(
+            r'data-video=(["\'])(?P<id>.+?)\1', webpage, 'video id', group='id')
+
+        data = self._download_json(
+            'https://mediazone.vrt.be/api/v1/canvas/assets/%s' % video_id, display_id)
+
+        formats = []
+        for target in data['targetUrls']:
+            format_url, format_type = target.get('url'), target.get('type')
+            if not format_url or not format_type:
+                continue
+            if format_type == 'HLS':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, display_id, entry_protocol='m3u8_native',
+                    ext='mp4', preference=0, fatal=False, m3u8_id=format_type))
+            elif format_type == 'HDS':
+                formats.extend(self._extract_f4m_formats(
+                    format_url, display_id, f4m_id=format_type, fatal=False))
+            else:
+                formats.append({
+                    'format_id': format_type,
+                    'url': format_url,
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'formats': formats,
+            'duration': float_or_none(data.get('duration'), 1000),
+            'thumbnail': data.get('posterImageUrl'),
+        }

youtube_dl/extractor/cbc.py

@@ -0,0 +1,113 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import js_to_json
+
+
+class CBCIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?:[^/]+/)+(?P<id>[^/?#]+)'
+    _TESTS = [{
+        # with mediaId
+        'url': 'http://www.cbc.ca/22minutes/videos/clips-season-23/don-cherry-play-offs',
+        'info_dict': {
+            'id': '2682904050',
+            'ext': 'flv',
+            'title': 'Don Cherry – All-Stars',
+            'description': 'Don Cherry has a bee in his bonnet about AHL player John Scott because that guy’s got heart.',
+            'timestamp': 1454475540,
+            'upload_date': '20160203',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }, {
+        # with clipId
+        'url': 'http://www.cbc.ca/archives/entry/1978-robin-williams-freestyles-on-90-minutes-live',
+        'info_dict': {
+            'id': '2487345465',
+            'ext': 'flv',
+            'title': 'Robin Williams freestyles on 90 Minutes Live',
+            'description': 'Wacky American comedian Robin Williams shows off his infamous "freestyle" comedic talents while being interviewed on CBC\'s 90 Minutes Live.',
+            'upload_date': '19700101',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }, {
+        # multiple iframes
+        'url': 'http://www.cbc.ca/natureofthings/blog/birds-eye-view-from-vancouvers-burrard-street-bridge-how-we-got-the-shot',
+        'playlist': [{
+            'info_dict': {
+                'id': '2680832926',
+                'ext': 'flv',
+                'title': 'An Eagle\'s-Eye View Off Burrard Bridge',
+                'description': 'Hercules the eagle flies from Vancouver\'s Burrard Bridge down to a nearby park with a mini-camera strapped to his back.',
+                'upload_date': '19700101',
+            },
+        }, {
+            'info_dict': {
+                'id': '2658915080',
+                'ext': 'flv',
+                'title': 'Fly like an eagle!',
+                'description': 'Eagle equipped with a mini camera flies from the world\'s tallest tower',
+                'upload_date': '19700101',
+            },
+        }],
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if CBCPlayerIE.suitable(url) else super(CBCIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        player_init = self._search_regex(
+            r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage, 'player init',
+            default=None)
+        if player_init:
+            player_info = self._parse_json(player_init, display_id, js_to_json)
+            media_id = player_info.get('mediaId')
+            if not media_id:
+                clip_id = player_info['clipId']
+                media_id = self._download_json(
+                    'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
+                    clip_id)['entries'][0]['id'].split('/')[-1]
+            return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
+        else:
+            entries = [self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)]
+            return self.playlist_result(entries)
+
+
+class CBCPlayerIE(InfoExtractor):
+    _VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.cbc.ca/player/play/2683190193',
+        'info_dict': {
+            'id': '2683190193',
+            'ext': 'flv',
+            'title': 'Gerry Runs a Sweat Shop',
+            'description': 'md5:b457e1c01e8ff408d9d801c1c2cd29b0',
+            'timestamp': 1455067800,
+            'upload_date': '20160210',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self.url_result(
+            'http://feed.theplatform.com/f/ExhSPC/vms_5akSXx4Ng_Zn?byGuid=%s' % video_id,
+            'ThePlatformFeed', video_id)

youtube_dl/extractor/cbs.py

@@ -1,6 +1,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import (
+    sanitized_Request,
+    smuggle_url,
+)
 
 
 class CBSIE(InfoExtractor):
@@ -46,13 +50,19 @@ class CBSIE(InfoExtractor):
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
+        request = sanitized_Request(url)
+        # Android UA is served with higher quality (720p) streams (see
+        # https://github.com/rg3/youtube-dl/issues/7490)
+        request.add_header('User-Agent', 'Mozilla/5.0 (Linux; Android 4.4; Nexus 5)')
+        webpage = self._download_webpage(request, display_id)
         real_id = self._search_regex(
             [r"video\.settings\.pid\s*=\s*'([^']+)';", r"cbsplayer\.pid\s*=\s*'([^']+)';"],
             webpage, 'real video ID')
         return {
             '_type': 'url_transparent',
             'ie_key': 'ThePlatform',
-            'url': 'theplatform:%s' % real_id,
+            'url': smuggle_url(
+                'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true&manifest=m3u' % real_id,
+                {'force_smil_url': True}),
             'display_id': display_id,
         }

youtube_dl/extractor/cbsnews.py

@@ -1,15 +1,14 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import re
-import json
-
 from .common import InfoExtractor
+from .theplatform import ThePlatformIE
+from ..utils import parse_duration
 
 
-class CBSNewsIE(InfoExtractor):
+class CBSNewsIE(ThePlatformIE):
     IE_DESC = 'CBS News'
-    _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:[^/]+/)+(?P<id>[\da-z_-]+)'
+    _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
 
     _TESTS = [
         {
@@ -30,53 +29,54 @@ class CBSNewsIE(InfoExtractor):
             'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
             'info_dict': {
                 'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'duration': 205,
+                'subtitles': {
+                    'en': [{
+                        'ext': 'ttml',
+                    }],
+                },
             },
             'params': {
-                # rtmp download
+                # m3u8 download
                 'skip_download': True,
             },
         },
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 
-        video_info = json.loads(self._html_search_regex(
+        video_info = self._parse_json(self._html_search_regex(
             r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
-            webpage, 'video JSON info'))
+            webpage, 'video JSON info'), video_id)
 
         item = video_info['item'] if 'item' in video_info else video_info
         title = item.get('articleTitle') or item.get('hed')
         duration = item.get('duration')
         thumbnail = item.get('mediaImage') or item.get('thumbnail')
 
+        subtitles = {}
+        if 'mpxRefId' in video_info:
+            subtitles['en'] = [{
+                'ext': 'ttml',
+                'url': 'http://www.cbsnews.com/videos/captions/%s.adb_xml' % video_info['mpxRefId'],
+            }]
+
         formats = []
         for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']:
-            uri = item.get('media' + format_id + 'URI')
-            if not uri:
+            pid = item.get('media' + format_id)
+            if not pid:
                 continue
-            fmt = {
-                'url': uri,
-                'format_id': format_id,
-            }
-            if uri.startswith('rtmp'):
-                fmt.update({
-                    'app': 'ondemand?auth=cbs',
-                    'play_path': 'mp4:' + uri.split('<break>')[-1],
-                    'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf',
-                    'page_url': 'http://www.cbsnews.com',
-                    'ext': 'flv',
-                })
-            elif uri.endswith('.m3u8'):
-                fmt['ext'] = 'mp4'
-            formats.append(fmt)
+            release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?format=SMIL&mbr=true' % pid
+            tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % pid)
+            formats.extend(tp_formats)
+            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
@@ -84,4 +84,43 @@ class CBSNewsIE(InfoExtractor):
             'thumbnail': thumbnail,
             'duration': duration,
             'formats': formats,
+            'subtitles': subtitles,
+        }
+
+
+class CBSNewsLiveVideoIE(InfoExtractor):
+    IE_DESC = 'CBS News Live Videos'
+    _VALID_URL = r'http://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
+
+    _TEST = {
+        'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
+        'info_dict': {
+            'id': 'clinton-sanders-prepare-to-face-off-in-nh',
+            'ext': 'flv',
+            'title': 'Clinton, Sanders Prepare To Face Off In NH',
+            'duration': 334,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_info = self._parse_json(self._html_search_regex(
+            r'data-story-obj=\'({.+?})\'', webpage, 'video JSON info'), video_id)['story']
+
+        hdcore_sign = 'hdcore=3.3.1'
+        f4m_formats = self._extract_f4m_formats(video_info['url'] + '&' + hdcore_sign, video_id)
+        if f4m_formats:
+            for entry in f4m_formats:
+                # URLs without the extra param induce an 404 error
+                entry.update({'extra_param_to_segment_url': hdcore_sign})
+
+        return {
+            'id': video_id,
+            'title': video_info['headline'],
+            'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
+            'duration': parse_duration(video_info.get('segmentDur')),
+            'formats': f4m_formats,
         }

youtube_dl/extractor/ccc.py

@@ -5,6 +5,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
+    parse_duration,
     qualities,
     unified_strdate,
 )
@@ -12,21 +13,25 @@ from ..utils import (
 
 class CCCIE(InfoExtractor):
     IE_NAME = 'media.ccc.de'
-    _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/[^?#]+/[^?#/]*?_(?P<id>[0-9]{8,})._[^?#/]*\.html'
+    _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/v/(?P<id>[^/?#&]+)'
 
-    _TEST = {
-        'url': 'http://media.ccc.de/browse/congress/2013/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor.html#video',
+    _TESTS = [{
+        'url': 'https://media.ccc.de/v/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor#video',
         'md5': '3a1eda8f3a29515d27f5adb967d7e740',
         'info_dict': {
-            'id': '20131228183',
+            'id': '30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor',
             'ext': 'mp4',
             'title': 'Introduction to Processor Design',
-            'description': 'md5:5ddbf8c734800267f2cee4eab187bc1b',
+            'description': 'md5:80be298773966f66d56cb11260b879af',
             'thumbnail': 're:^https?://.*\.jpg$',
             'view_count': int,
-            'upload_date': '20131229',
+            'upload_date': '20131228',
+            'duration': 3660,
         }
-    }
+    }, {
+        'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -40,21 +45,25 @@ class CCCIE(InfoExtractor):
         title = self._html_search_regex(
             r'(?s)<h1>(.*?)</h1>', webpage, 'title')
         description = self._html_search_regex(
-            r"(?s)<p class='description'>(.*?)</p>",
+            r"(?s)<h3>About</h3>(.+?)<h3>",
             webpage, 'description', fatal=False)
         upload_date = unified_strdate(self._html_search_regex(
-            r"(?s)<span class='[^']*fa-calendar-o'></span>(.*?)</li>",
+            r"(?s)<span[^>]+class='[^']*fa-calendar-o'[^>]*>(.+?)</span>",
             webpage, 'upload date', fatal=False))
         view_count = int_or_none(self._html_search_regex(
             r"(?s)<span class='[^']*fa-eye'></span>(.*?)</li>",
             webpage, 'view count', fatal=False))
+        duration = parse_duration(self._html_search_regex(
+            r'(?s)<span[^>]+class=(["\']).*?fa-clock-o.*?\1[^>]*></span>(?P<duration>.+?)</li',
+            webpage, 'duration', fatal=False, group='duration'))
 
         matches = re.finditer(r'''(?xs)
-            <(?:span|div)\s+class='label\s+filetype'>(?P<format>.*?)</(?:span|div)>\s*
+            <(?:span|div)\s+class='label\s+filetype'>(?P<format>[^<]*)</(?:span|div)>\s*
+            <(?:span|div)\s+class='label\s+filetype'>(?P<lang>[^<]*)</(?:span|div)>\s*
             <a\s+download\s+href='(?P<http_url>[^']+)'>\s*
             (?:
                 .*?
-                <a\s+href='(?P<torrent_url>[^']+\.torrent)'
+                <a\s+(?:download\s+)?href='(?P<torrent_url>[^']+\.torrent)'
             )?''', webpage)
         formats = []
         for m in matches:
@@ -62,12 +71,15 @@ class CCCIE(InfoExtractor):
             format_id = self._search_regex(
                 r'.*/([a-z0-9_-]+)/[^/]*$',
                 m.group('http_url'), 'format id', default=None)
+            if format_id:
+                format_id = m.group('lang') + '-' + format_id
             vcodec = 'h264' if 'h264' in format_id else (
                 'none' if format_id in ('mp3', 'opus') else None
             )
             formats.append({
                 'format_id': format_id,
                 'format': format,
+                'language': m.group('lang'),
                 'url': m.group('http_url'),
                 'vcodec': vcodec,
                 'preference': preference(format_id),
@@ -95,5 +107,6 @@ class CCCIE(InfoExtractor):
             'thumbnail': thumbnail,
             'view_count': view_count,
             'upload_date': upload_date,
+            'duration': duration,
             'formats': formats,
         }

youtube_dl/extractor/ceskatelevize.py

@@ -5,7 +5,6 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_request,
     compat_urllib_parse,
     compat_urllib_parse_unquote,
     compat_urllib_parse_urlparse,
@@ -13,6 +12,7 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     float_or_none,
+    sanitized_Request,
 )
 
 
@@ -100,7 +100,7 @@ class CeskaTelevizeIE(InfoExtractor):
             'requestSource': 'iVysilani',
         }
 
-        req = compat_urllib_request.Request(
+        req = sanitized_Request(
             'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
             data=compat_urllib_parse.urlencode(data))
 
@@ -115,7 +115,7 @@ class CeskaTelevizeIE(InfoExtractor):
         if playlist_url == 'error_region':
             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
 
-        req = compat_urllib_request.Request(compat_urllib_parse_unquote(playlist_url))
+        req = sanitized_Request(compat_urllib_parse_unquote(playlist_url))
         req.add_header('Referer', url)
 
         playlist_title = self._og_search_title(webpage)

youtube_dl/extractor/channel9.py

@@ -3,7 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    parse_filesize,
+    qualities,
+)
 
 
 class Channel9IE(InfoExtractor):
@@ -28,7 +32,7 @@ class Channel9IE(InfoExtractor):
                 'title': 'Developer Kick-Off Session: Stuff We Love',
                 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
                 'duration': 4576,
-                'thumbnail': 'http://video.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
+                'thumbnail': 're:http://.*\.jpg',
                 'session_code': 'KOS002',
                 'session_day': 'Day 1',
                 'session_room': 'Arena 1A',
@@ -44,31 +48,29 @@ class Channel9IE(InfoExtractor):
                 'title': 'Self-service BI with Power BI - nuclear testing',
                 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
                 'duration': 1540,
-                'thumbnail': 'http://video.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
+                'thumbnail': 're:http://.*\.jpg',
                 'authors': ['Mike Wilmot'],
             },
+        },
+        {
+            # low quality mp4 is best
+            'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
+            'info_dict': {
+                'id': 'Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
+                'ext': 'mp4',
+                'title': 'Ranges for the Standard Library',
+                'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d',
+                'duration': 5646,
+                'thumbnail': 're:http://.*\.jpg',
+            },
+            'params': {
+                'skip_download': True,
+            },
         }
     ]
 
     _RSS_URL = 'http://channel9.msdn.com/%s/RSS'
 
-    # Sorted by quality
-    _known_formats = ['MP3', 'MP4', 'Mid Quality WMV', 'Mid Quality MP4', 'High Quality WMV', 'High Quality MP4']
-
-    def _restore_bytes(self, formatted_size):
-        if not formatted_size:
-            return 0
-        m = re.match(r'^(?P<size>\d+(?:\.\d+)?)\s+(?P<units>[a-zA-Z]+)', formatted_size)
-        if not m:
-            return 0
-        units = m.group('units')
-        try:
-            exponent = ['B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB'].index(units.upper())
-        except ValueError:
-            return 0
-        size = float(m.group('size'))
-        return int(size * (1024 ** exponent))
-
     def _formats_from_html(self, html):
         FORMAT_REGEX = r'''
             (?x)
@@ -78,16 +80,20 @@ class Channel9IE(InfoExtractor):
             <h3>File\s+size</h3>\s*(?P<filesize>.*?)\s*
             </div>)?                                                # File size part may be missing
         '''
-        # Extract known formats
+        quality = qualities((
+            'MP3', 'MP4',
+            'Low Quality WMV', 'Low Quality MP4',
+            'Mid Quality WMV', 'Mid Quality MP4',
+            'High Quality WMV', 'High Quality MP4'))
         formats = [{
             'url': x.group('url'),
             'format_id': x.group('quality'),
             'format_note': x.group('note'),
             'format': '%s (%s)' % (x.group('quality'), x.group('note')),
-            'filesize': self._restore_bytes(x.group('filesize')),  # File size is approximate
-            'preference': self._known_formats.index(x.group('quality')),
+            'filesize_approx': parse_filesize(x.group('filesize')),
+            'quality': quality(x.group('quality')),
             'vcodec': 'none' if x.group('note') == 'Audio only' else None,
-        } for x in list(re.finditer(FORMAT_REGEX, html)) if x.group('quality') in self._known_formats]
+        } for x in list(re.finditer(FORMAT_REGEX, html))]
 
         self._sort_formats(formats)
 
@@ -158,7 +164,7 @@ class Channel9IE(InfoExtractor):
 
     def _extract_session_day(self, html):
         m = re.search(r'<li class="day">\s*<a href="/Events/[^"]+">(?P<day>[^<]+)</a>\s*</li>', html)
-        return m.group('day') if m is not None else None
+        return m.group('day').strip() if m is not None else None
 
     def _extract_session_room(self, html):
         m = re.search(r'<li class="room">\s*(?P<room>.+?)\s*</li>', html)
@@ -224,12 +230,12 @@ class Channel9IE(InfoExtractor):
         if contents is None:
             return contents
 
-        authors = self._extract_authors(html)
+        if len(contents) > 1:
+            raise ExtractorError('Got more than one entry')
+        result = contents[0]
+        result['authors'] = self._extract_authors(html)
 
-        for content in contents:
-            content['authors'] = authors
-
-        return contents
+        return result
 
     def _extract_session(self, html, content_path):
         contents = self._extract_content(html, content_path)

youtube_dl/extractor/chaturbate.py

@@ -0,0 +1,59 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class ChaturbateIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://www.chaturbate.com/siswet19/',
+        'info_dict': {
+            'id': 'siswet19',
+            'ext': 'mp4',
+            'title': 're:^siswet19 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'age_limit': 18,
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://en.chaturbate.com/siswet19/',
+        'only_matching': True,
+    }]
+
+    _ROOM_OFFLINE = 'Room is currently offline'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        m3u8_url = self._search_regex(
+            r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage,
+            'playlist', default=None, group='url')
+
+        if not m3u8_url:
+            error = self._search_regex(
+                [r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
+                 r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
+                webpage, 'error', group='error', default=None)
+            if not error:
+                if any(p not in webpage for p in (
+                        self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
+                    error = self._ROOM_OFFLINE
+            if error:
+                raise ExtractorError(error, expected=True)
+            raise ExtractorError('Unable to find stream URL')
+
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
+
+        return {
+            'id': video_id,
+            'title': self._live_title(video_id),
+            'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id,
+            'age_limit': self._rta_search(webpage),
+            'is_live': True,
+            'formats': formats,
+        }

youtube_dl/extractor/cinemassacre.py

@@ -5,7 +5,6 @@ import re
 
 from .common import InfoExtractor
 from ..utils import ExtractorError
-from .bliptv import BlipTVIE
 from .screenwavemedia import ScreenwaveMediaIE
 
 
@@ -34,18 +33,17 @@ class CinemassacreIE(InfoExtractor):
             },
         },
         {
-            # blip.tv embedded video
+            # Youtube embedded video
             'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/',
-            'md5': 'ca9b3c8dd5a66f9375daeb5135f5a3de',
+            'md5': 'df4cf8a1dcedaec79a73d96d83b99023',
             'info_dict': {
-                'id': '4065369',
-                'ext': 'flv',
+                'id': 'OEVzPCY2T-g',
+                'ext': 'mp4',
                 'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles',
                 'upload_date': '20061207',
-                'uploader': 'cinemassacre',
-                'uploader_id': '250778',
-                'timestamp': 1283233867,
-                'description': 'md5:0a108c78d130676b207d0f6d029ecffd',
+                'uploader': 'Cinemassacre',
+                'uploader_id': 'JamesNintendoNerd',
+                'description': 'md5:784734696c2b8b7f4b8625cc799e07f6',
             }
         },
         {
@@ -88,8 +86,6 @@ class CinemassacreIE(InfoExtractor):
                 r'<iframe[^>]+src="(?P<url>(?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
             ],
             webpage, 'player data URL', default=None, group='url')
-        if not playerdata_url:
-            playerdata_url = BlipTVIE._extract_url(webpage)
         if not playerdata_url:
             raise ExtractorError('Unable to find player data')
 

youtube_dl/extractor/clipfish.py

@@ -1,14 +1,9 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
-    determine_ext,
     int_or_none,
-    js_to_json,
-    parse_iso8601,
-    remove_end,
+    unified_strdate,
 )
 
 
@@ -21,48 +16,47 @@ class ClipfishIE(InfoExtractor):
             'id': '3966754',
             'ext': 'mp4',
             'title': 'FIFA 14 - E3 2013 Trailer',
-            'timestamp': 1370938118,
+            'description': 'Video zu FIFA 14: E3 2013 Trailer',
             'upload_date': '20130611',
             'duration': 82,
+            'view_count': int,
         }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
-
-        video_info = self._parse_json(
-            js_to_json(self._html_search_regex(
-                '(?s)videoObject\s*=\s*({.+?});', webpage, 'video object')),
-            video_id)
+        video_info = self._download_json(
+            'http://www.clipfish.de/devapi/id/%s?format=json&apikey=hbbtv' % video_id,
+            video_id)['items'][0]
 
         formats = []
-        for video_url in re.findall(r'var\s+videourl\s*=\s*"([^"]+)"', webpage):
-            ext = determine_ext(video_url)
-            if ext == 'm3u8':
-                formats.append({
-                    'url': video_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
-                    'ext': 'mp4',
-                    'format_id': 'hls',
-                })
-            else:
-                formats.append({
-                    'url': video_url,
-                    'format_id': ext,
-                })
-        self._sort_formats(formats)
 
-        title = remove_end(self._og_search_title(webpage), ' - Video')
-        thumbnail = self._og_search_thumbnail(webpage)
-        duration = int_or_none(video_info.get('length'))
-        timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date'))
+        m3u8_url = video_info.get('media_videourl_hls')
+        if m3u8_url:
+            formats.append({
+                'url': m3u8_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
+                'ext': 'mp4',
+                'format_id': 'hls',
+            })
+
+        mp4_url = video_info.get('media_videourl')
+        if mp4_url:
+            formats.append({
+                'url': mp4_url,
+                'format_id': 'mp4',
+                'width': int_or_none(video_info.get('width')),
+                'height': int_or_none(video_info.get('height')),
+                'tbr': int_or_none(video_info.get('bitrate')),
+            })
 
         return {
             'id': video_id,
-            'title': title,
+            'title': video_info['title'],
+            'description': video_info.get('descr'),
             'formats': formats,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'timestamp': timestamp,
+            'thumbnail': video_info.get('media_content_thumbnail_large') or video_info.get('media_thumbnail'),
+            'duration': int_or_none(video_info.get('media_length')),
+            'upload_date': unified_strdate(video_info.get('pubDate')),
+            'view_count': int_or_none(video_info.get('media_views'))
         }

youtube_dl/extractor/cliphunter.py

@@ -1,7 +1,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import determine_ext
+from ..utils import int_or_none
 
 
 _translation_table = {
@@ -42,31 +42,26 @@ class CliphunterIE(InfoExtractor):
         video_title = self._search_regex(
             r'mediaTitle = "([^"]+)"', webpage, 'title')
 
-        fmts = {}
-        for fmt in ('mp4', 'flv'):
-            fmt_list = self._parse_json(self._search_regex(
-                r'var %sjson\s*=\s*(\[.*?\]);' % fmt, webpage, '%s formats' % fmt), video_id)
-            for f in fmt_list:
-                fmts[f['fname']] = _decode(f['sUrl'])
-
-        qualities = self._parse_json(self._search_regex(
-            r'var player_btns\s*=\s*(.*?);\n', webpage, 'quality info'), video_id)
+        gexo_files = self._parse_json(
+            self._search_regex(
+                r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'),
+            video_id)
 
         formats = []
-        for fname, url in fmts.items():
-            f = {
-                'url': url,
-            }
-            if fname in qualities:
-                qual = qualities[fname]
-                f.update({
-                    'format_id': '%s_%sp' % (determine_ext(url), qual['h']),
-                    'width': qual['w'],
-                    'height': qual['h'],
-                    'tbr': qual['br'],
-                })
-            formats.append(f)
-
+        for format_id, f in gexo_files.items():
+            video_url = f.get('url')
+            if not video_url:
+                continue
+            fmt = f.get('fmt')
+            height = f.get('h')
+            format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id
+            formats.append({
+                'url': _decode(video_url),
+                'format_id': format_id,
+                'width': int_or_none(f.get('w')),
+                'height': int_or_none(height),
+                'tbr': int_or_none(f.get('br')),
+            })
         self._sort_formats(formats)
 
         thumbnail = self._search_regex(

youtube_dl/extractor/clyp.py

@@ -0,0 +1,57 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    parse_iso8601,
+)
+
+
+class ClypIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?clyp\.it/(?P<id>[a-z0-9]+)'
+    _TEST = {
+        'url': 'https://clyp.it/ojz2wfah',
+        'md5': '1d4961036c41247ecfdcc439c0cddcbb',
+        'info_dict': {
+            'id': 'ojz2wfah',
+            'ext': 'mp3',
+            'title': 'Krisson80 - bits wip wip',
+            'description': '#Krisson80BitsWipWip #chiptune\n#wip',
+            'duration': 263.21,
+            'timestamp': 1443515251,
+            'upload_date': '20150929',
+        },
+    }
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+
+        metadata = self._download_json(
+            'https://api.clyp.it/%s' % audio_id, audio_id)
+
+        formats = []
+        for secure in ('', 'Secure'):
+            for ext in ('Ogg', 'Mp3'):
+                format_id = '%s%s' % (secure, ext)
+                format_url = metadata.get('%sUrl' % format_id)
+                if format_url:
+                    formats.append({
+                        'url': format_url,
+                        'format_id': format_id,
+                        'vcodec': 'none',
+                    })
+        self._sort_formats(formats)
+
+        title = metadata['Title']
+        description = metadata.get('Description')
+        duration = float_or_none(metadata.get('Duration'))
+        timestamp = parse_iso8601(metadata.get('DateCreated'))
+
+        return {
+            'id': audio_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+        }

youtube_dl/extractor/cmt.py

@@ -4,7 +4,7 @@ from .mtv import MTVIE
 
 class CMTIE(MTVIE):
     IE_NAME = 'cmt.com'
-    _VALID_URL = r'https?://www\.cmt\.com/videos/.+?/(?P<videoid>[^/]+)\.jhtml'
+    _VALID_URL = r'https?://www\.cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
     _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
 
     _TESTS = [{
@@ -16,4 +16,7 @@ class CMTIE(MTVIE):
             'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"',
             'description': 'Blame It All On My Roots',
         },
+    }, {
+        'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172',
+        'only_matching': True,
     }]

youtube_dl/extractor/cnet.py

@@ -1,15 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
+from .theplatform import ThePlatformIE
+from ..utils import int_or_none
 
 
-class CNETIE(InfoExtractor):
+class CNETIE(ThePlatformIE):
     _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
     _TESTS = [{
         'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
@@ -18,25 +14,20 @@ class CNETIE(InfoExtractor):
             'ext': 'flv',
             'title': 'Hands-on with Microsoft Windows 8.1 Update',
             'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
-            'thumbnail': 're:^http://.*/flmswindows8.jpg$',
             'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
             'uploader': 'Sarah Mitroff',
+            'duration': 70,
         },
-        'params': {
-            'skip_download': 'requires rtmpdump',
-        }
     }, {
         'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
         'info_dict': {
             'id': '56527b93-d25d-44e3-b738-f989ce2e49ba',
             'ext': 'flv',
+            'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
             'description': 'Khail and Ashley wonder what other civic woes can be solved by self-tweeting objects, investigate a new kind of VR camera and watch an origami robot self-assemble, walk, climb, dig and dissolve. #TDPothole',
             'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
             'uploader': 'Ashley Esqueda',
-            'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
-        },
-        'params': {
-            'skip_download': True,  # requires rtmpdump
+            'duration': 1482,
         },
     }]
 
@@ -45,26 +36,13 @@ class CNETIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         data_json = self._html_search_regex(
-            r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'",
+            r"data-cnet-video(?:-uvp)?-options='([^']+)'",
             webpage, 'data json')
-        data = json.loads(data_json)
-        vdata = data['video']
-        if not vdata:
-            vdata = data['videos'][0]
-        if not vdata:
-            raise ExtractorError('Cannot find video data')
-
-        mpx_account = data['config']['players']['default']['mpx_account']
-        vid = vdata['files'].get('rtmp', vdata['files']['hds'])
-        tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid)
+        data = self._parse_json(data_json, display_id)
+        vdata = data.get('video') or data['videos'][0]
 
         video_id = vdata['id']
-        title = vdata.get('headline')
-        if title is None:
-            title = vdata.get('title')
-        if title is None:
-            raise ExtractorError('Cannot find title!')
-        thumbnail = vdata.get('image', {}).get('path')
+        title = vdata['title']
         author = vdata.get('author')
         if author:
             uploader = '%s %s' % (author['firstName'], author['lastName'])
@@ -73,13 +51,34 @@ class CNETIE(InfoExtractor):
             uploader = None
             uploader_id = None
 
+        mpx_account = data['config']['uvpConfig']['default']['mpx_account']
+
+        metadata = self.get_metadata('%s/%s' % (mpx_account, list(vdata['files'].values())[0]), video_id)
+        description = vdata.get('description') or metadata.get('description')
+        duration = int_or_none(vdata.get('duration')) or metadata.get('duration')
+
+        formats = []
+        subtitles = {}
+        for (fkey, vid) in vdata['files'].items():
+            if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']:
+                continue
+            release_url = 'http://link.theplatform.com/s/%s/%s?format=SMIL&mbr=true' % (mpx_account, vid)
+            if fkey == 'hds':
+                release_url += '&manifest=f4m'
+            tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % fkey)
+            formats.extend(tp_formats)
+            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
+        self._sort_formats(formats)
+
         return {
-            '_type': 'url_transparent',
-            'url': tp_link,
             'id': video_id,
             'display_id': display_id,
             'title': title,
+            'description': description,
+            'thumbnail': metadata.get('thumbnail'),
+            'duration': duration,
             'uploader': uploader,
             'uploader_id': uploader_id,
-            'thumbnail': thumbnail,
+            'subtitles': subtitles,
+            'formats': formats,
         }

youtube_dl/extractor/collegerama.py

@@ -3,10 +3,10 @@ from __future__ import unicode_literals
 import json
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_request
 from ..utils import (
     float_or_none,
     int_or_none,
+    sanitized_Request,
 )
 
 
@@ -52,7 +52,7 @@ class CollegeRamaIE(InfoExtractor):
             }
         }
 
-        request = compat_urllib_request.Request(
+        request = sanitized_Request(
             'http://collegerama.tudelft.nl/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions',
             json.dumps(player_options_request))
         request.add_header('Content-Type', 'application/json')

youtube_dl/extractor/comcarcoff.py

@@ -1,10 +1,13 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import json
-
 from .common import InfoExtractor
-from ..utils import parse_iso8601
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+)
 
 
 class ComCarCoffIE(InfoExtractor):
@@ -12,13 +15,13 @@ class ComCarCoffIE(InfoExtractor):
     _TESTS = [{
         'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/',
         'info_dict': {
-            'id': 'miranda-sings-happy-thanksgiving-miranda',
+            'id': '2494164',
             'ext': 'mp4',
             'upload_date': '20141127',
             'timestamp': 1417107600,
+            'duration': 1232,
             'title': 'Happy Thanksgiving Miranda',
             'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.',
-            'thumbnail': 'http://ccc.crackle.com/images/s5e4_thumb.jpg',
         },
         'params': {
             'skip_download': 'requires ffmpeg',
@@ -31,27 +34,36 @@ class ComCarCoffIE(InfoExtractor):
             display_id = 'comediansincarsgettingcoffee.com'
         webpage = self._download_webpage(url, display_id)
 
-        full_data = json.loads(self._search_regex(
-            r'<script type="application/json" id="videoData">(?P<json>.+?)</script>',
-            webpage, 'full data json'))
+        full_data = self._parse_json(
+            self._search_regex(
+                r'window\.app\s*=\s*({.+?});\n', webpage, 'full data json'),
+            display_id)['videoData']
 
-        video_id = full_data['activeVideo']['video']
-        video_data = full_data.get('videos', {}).get(video_id) or full_data['singleshots'][video_id]
+        display_id = full_data['activeVideo']['video']
+        video_data = full_data.get('videos', {}).get(display_id) or full_data['singleshots'][display_id]
+        video_id = compat_str(video_data['mediaId'])
         thumbnails = [{
             'url': video_data['images']['thumb'],
         }, {
             'url': video_data['images']['poster'],
         }]
-        formats = self._extract_m3u8_formats(
-            video_data['mediaUrl'], video_id, ext='mp4')
+
+        timestamp = int_or_none(video_data.get('pubDateTime')) or parse_iso8601(
+            video_data.get('pubDate'))
+        duration = int_or_none(video_data.get('durationSeconds')) or parse_duration(
+            video_data.get('duration'))
 
         return {
+            '_type': 'url_transparent',
+            'url': 'crackle:%s' % video_id,
             'id': video_id,
             'display_id': display_id,
             'title': video_data['title'],
             'description': video_data.get('description'),
-            'timestamp': parse_iso8601(video_data.get('pubDate')),
+            'timestamp': timestamp,
+            'duration': duration,
             'thumbnails': thumbnails,
-            'formats': formats,
+            'season_number': int_or_none(video_data.get('season')),
+            'episode_number': int_or_none(video_data.get('episode')),
             'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))),
         }

youtube_dl/extractor/common.py

@@ -10,20 +10,18 @@ import re
 import socket
 import sys
 import time
-import xml.etree.ElementTree
+import math
 
 from ..compat import (
     compat_cookiejar,
     compat_cookies,
     compat_getpass,
-    compat_HTTPError,
     compat_http_client,
     compat_urllib_error,
     compat_urllib_parse,
-    compat_urllib_parse_urlparse,
-    compat_urllib_request,
     compat_urlparse,
     compat_str,
+    compat_etree_fromstring,
 )
 from ..utils import (
     NO_DEFAULT,
@@ -32,17 +30,22 @@ from ..utils import (
     clean_html,
     compiled_regex_type,
     determine_ext,
+    error_to_compat_str,
     ExtractorError,
     fix_xml_ampersands,
     float_or_none,
     int_or_none,
+    parse_iso8601,
     RegexNotFoundError,
     sanitize_filename,
+    sanitized_Request,
     unescapeHTML,
     unified_strdate,
     url_basename,
     xpath_text,
     xpath_with_ns,
+    determine_protocol,
+    parse_duration,
 )
 
 
@@ -108,8 +111,9 @@ class InfoExtractor(object):
                                  -2 or smaller for less than default.
                                  < -1000 to hide the format (if there is
                                     another one which is strictly better)
-                    * language_preference  Is this in the correct requested
-                                 language?
+                    * language   Language code, e.g. "de" or "en-US".
+                    * language_preference  Is this in the language mentioned in
+                                 the URL?
                                  10 if it's what the URL is about,
                                  -1 for default (don't know),
                                  -10 otherwise, other values reserved for now.
@@ -168,10 +172,11 @@ class InfoExtractor(object):
                     "ext" will be calculated from URL if missing
     automatic_captions: Like 'subtitles', used by the YoutubeIE for
                     automatically generated captions
-    duration:       Length of the video in seconds, as an integer.
+    duration:       Length of the video in seconds, as an integer or float.
     view_count:     How many users have watched the video on the platform.
     like_count:     Number of positive ratings of the video
     dislike_count:  Number of negative ratings of the video
+    repost_count:   Number of reposts of the video
     average_rating: Average rating give by users, the scale used depends on the webpage
     comment_count:  Number of comments on the video
     comments:       A list of comments, each with one or more of the following
@@ -199,6 +204,26 @@ class InfoExtractor(object):
     end_time:       Time in seconds where the reproduction should end, as
                     specified in the URL.
 
+    The following fields should only be used when the video belongs to some logical
+    chapter or section:
+
+    chapter:        Name or title of the chapter the video belongs to.
+    chapter_number: Number of the chapter the video belongs to, as an integer.
+    chapter_id:     Id of the chapter the video belongs to, as a unicode string.
+
+    The following fields should only be used when the video is an episode of some
+    series or programme:
+
+    series:         Title of the series or programme the video episode belongs to.
+    season:         Title of the season the video episode belongs to.
+    season_number:  Number of the season the video episode belongs to, as an integer.
+    season_id:      Id of the season the video episode belongs to, as a unicode string.
+    episode:        Title of the video episode. Unlike mandatory video title field,
+                    this field should denote the exact title of the video episode
+                    without any kind of decoration.
+    episode_number: Number of the video episode within a season, as an integer.
+    episode_id:     Id of the video episode, as a unicode string.
+
     Unless mentioned otherwise, the fields should be Unicode strings.
 
     Unless mentioned otherwise, None is equivalent to absence of information.
@@ -291,9 +316,9 @@ class InfoExtractor(object):
         except ExtractorError:
             raise
         except compat_http_client.IncompleteRead as e:
-            raise ExtractorError('A network error has occured.', cause=e, expected=True)
+            raise ExtractorError('A network error has occurred.', cause=e, expected=True)
         except (KeyError, StopIteration) as e:
-            raise ExtractorError('An extractor error has occured.', cause=e)
+            raise ExtractorError('An extractor error has occurred.', cause=e)
 
     def set_downloader(self, downloader):
         """Sets the downloader for this IE."""
@@ -310,11 +335,11 @@ class InfoExtractor(object):
     @classmethod
     def ie_key(cls):
         """A string for getting the InfoExtractor with get_info_extractor"""
-        return cls.__name__[:-2]
+        return compat_str(cls.__name__[:-2])
 
     @property
     def IE_NAME(self):
-        return type(self).__name__[:-2]
+        return compat_str(type(self).__name__[:-2])
 
     def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
         """ Returns the response handle """
@@ -332,7 +357,8 @@ class InfoExtractor(object):
                 return False
             if errnote is None:
                 errnote = 'Unable to download webpage'
-            errmsg = '%s: %s' % (errnote, compat_str(err))
+
+            errmsg = '%s: %s' % (errnote, error_to_compat_str(err))
             if fatal:
                 raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
             else:
@@ -461,7 +487,7 @@ class InfoExtractor(object):
             return xml_string
         if transform_source:
             xml_string = transform_source(xml_string)
-        return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
+        return compat_etree_fromstring(xml_string.encode('utf-8'))
 
     def _download_json(self, url_or_request, video_id,
                        note='Downloading JSON metadata',
@@ -622,7 +648,7 @@ class InfoExtractor(object):
                 else:
                     raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
             except (IOError, netrc.NetrcParseError) as err:
-                self._downloader.report_warning('parsing .netrc: %s' % compat_str(err))
+                self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err))
 
         return (username, password)
 
@@ -645,8 +671,9 @@ class InfoExtractor(object):
     # Helper functions for extracting OpenGraph info
     @staticmethod
     def _og_regexes(prop):
-        content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\')'
-        property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop)
+        content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?))'
+        property_re = (r'(?:name|property)=(?:\'og:%(prop)s\'|"og:%(prop)s"|\s*og:%(prop)s\b)'
+                       % {'prop': re.escape(prop)})
         template = r'<meta[^>]+?%s[^>]+?%s'
         return [
             template % (property_re, content_re),
@@ -738,6 +765,42 @@ class InfoExtractor(object):
         return self._html_search_meta('twitter:player', html,
                                       'twitter card player')
 
+    def _search_json_ld(self, html, video_id, **kwargs):
+        json_ld = self._search_regex(
+            r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>',
+            html, 'JSON-LD', group='json_ld', **kwargs)
+        if not json_ld:
+            return {}
+        return self._json_ld(json_ld, video_id, fatal=kwargs.get('fatal', True))
+
+    def _json_ld(self, json_ld, video_id, fatal=True):
+        if isinstance(json_ld, compat_str):
+            json_ld = self._parse_json(json_ld, video_id, fatal=fatal)
+        if not json_ld:
+            return {}
+        info = {}
+        if json_ld.get('@context') == 'http://schema.org':
+            item_type = json_ld.get('@type')
+            if item_type == 'TVEpisode':
+                info.update({
+                    'episode': unescapeHTML(json_ld.get('name')),
+                    'episode_number': int_or_none(json_ld.get('episodeNumber')),
+                    'description': unescapeHTML(json_ld.get('description')),
+                })
+                part_of_season = json_ld.get('partOfSeason')
+                if isinstance(part_of_season, dict) and part_of_season.get('@type') == 'TVSeason':
+                    info['season_number'] = int_or_none(part_of_season.get('seasonNumber'))
+                part_of_series = json_ld.get('partOfSeries')
+                if isinstance(part_of_series, dict) and part_of_series.get('@type') == 'TVSeries':
+                    info['series'] = unescapeHTML(part_of_series.get('name'))
+            elif item_type == 'Article':
+                info.update({
+                    'timestamp': parse_iso8601(json_ld.get('datePublished')),
+                    'title': unescapeHTML(json_ld.get('headline')),
+                    'description': unescapeHTML(json_ld.get('articleBody')),
+                })
+        return dict((k, v) for k, v in info.items() if v is not None)
+
     @staticmethod
     def _hidden_inputs(html):
         html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html)
@@ -764,6 +827,12 @@ class InfoExtractor(object):
         if not formats:
             raise ExtractorError('No video formats found')
 
+        for f in formats:
+            # Automatically determine tbr when missing based on abr and vbr (improves
+            # formats sorting in some cases)
+            if 'tbr' not in f and f.get('abr') is not None and f.get('vbr') is not None:
+                f['tbr'] = f['abr'] + f['vbr']
+
         def _formats_key(f):
             # TODO remove the following workaround
             from ..utils import determine_ext
@@ -775,14 +844,12 @@ class InfoExtractor(object):
 
             preference = f.get('preference')
             if preference is None:
-                proto = f.get('protocol')
-                if proto is None:
-                    proto = compat_urllib_parse_urlparse(f.get('url', '')).scheme
-
-                preference = 0 if proto in ['http', 'https'] else -0.1
+                preference = 0
                 if f.get('ext') in ['f4f', 'f4m']:  # Not yet supported
                     preference -= 0.5
 
+            proto_preference = 0 if determine_protocol(f) in ['http', 'https'] else -0.1
+
             if f.get('vcodec') == 'none':  # audio only
                 if self._downloader.params.get('prefer_free_formats'):
                     ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus']
@@ -813,6 +880,7 @@ class InfoExtractor(object):
                 f.get('vbr') if f.get('vbr') is not None else -1,
                 f.get('height') if f.get('height') is not None else -1,
                 f.get('width') if f.get('width') is not None else -1,
+                proto_preference,
                 ext_preference,
                 f.get('abr') if f.get('abr') is not None else -1,
                 audio_ext_preference,
@@ -840,7 +908,7 @@ class InfoExtractor(object):
             self._request_webpage(url, video_id, 'Checking %s URL' % item)
             return True
         except ExtractorError as e:
-            if isinstance(e.cause, compat_HTTPError):
+            if isinstance(e.cause, compat_urllib_error.URLError):
                 self.to_screen(
                     '%s: %s URL is invalid, skipping' % (video_id, item))
                 return False
@@ -882,7 +950,7 @@ class InfoExtractor(object):
             fatal=fatal)
 
         if manifest is False:
-            return manifest
+            return []
 
         formats = []
         manifest_version = '1.0'
@@ -890,6 +958,11 @@ class InfoExtractor(object):
         if not media_nodes:
             manifest_version = '2.0'
             media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
+        base_url = xpath_text(
+            manifest, ['{http://ns.adobe.com/f4m/1.0}baseURL', '{http://ns.adobe.com/f4m/2.0}baseURL'],
+            'base URL', default=None)
+        if base_url:
+            base_url = base_url.strip()
         for i, media_el in enumerate(media_nodes):
             if manifest_version == '2.0':
                 media_url = media_el.attrib.get('href') or media_el.attrib.get('url')
@@ -897,16 +970,14 @@ class InfoExtractor(object):
                     continue
                 manifest_url = (
                     media_url if media_url.startswith('http://') or media_url.startswith('https://')
-                    else ('/'.join(manifest_url.split('/')[:-1]) + '/' + media_url))
+                    else ((base_url or '/'.join(manifest_url.split('/')[:-1])) + '/' + media_url))
                 # If media_url is itself a f4m manifest do the recursive extraction
                 # since bitrates in parent manifest (this one) and media_url manifest
                 # may differ leading to inability to resolve the format by requested
                 # bitrate in f4m downloader
                 if determine_ext(manifest_url) == 'f4m':
-                    f4m_formats = self._extract_f4m_formats(
-                        manifest_url, video_id, preference, f4m_id, fatal=fatal)
-                    if f4m_formats:
-                        formats.extend(f4m_formats)
+                    formats.extend(self._extract_f4m_formats(
+                        manifest_url, video_id, preference, f4m_id, fatal=fatal))
                     continue
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             formats.append({
@@ -942,13 +1013,27 @@ class InfoExtractor(object):
             if re.match(r'^https?://', u)
             else compat_urlparse.urljoin(m3u8_url, u))
 
-        m3u8_doc = self._download_webpage(
+        res = self._download_webpage_handle(
             m3u8_url, video_id,
             note=note or 'Downloading m3u8 information',
             errnote=errnote or 'Failed to download m3u8 information',
             fatal=fatal)
-        if m3u8_doc is False:
-            return m3u8_doc
+        if res is False:
+            return []
+        m3u8_doc, urlh = res
+        m3u8_url = urlh.geturl()
+        # A Media Playlist Tag MUST NOT appear in a Master Playlist
+        # https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3
+        # The EXT-X-TARGETDURATION tag is REQUIRED for every M3U8 Media Playlists
+        # https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.1
+        if '#EXT-X-TARGETDURATION' in m3u8_doc:
+            return [{
+                'url': m3u8_url,
+                'format_id': m3u8_id,
+                'ext': ext,
+                'protocol': entry_protocol,
+                'preference': preference,
+            }]
         last_info = None
         last_media = None
         kv_rex = re.compile(
@@ -993,9 +1078,9 @@ class InfoExtractor(object):
                     # TODO: looks like video codec is not always necessarily goes first
                     va_codecs = codecs.split(',')
                     if va_codecs[0]:
-                        f['vcodec'] = va_codecs[0].partition('.')[0]
+                        f['vcodec'] = va_codecs[0]
                     if len(va_codecs) > 1 and va_codecs[1]:
-                        f['acodec'] = va_codecs[1].partition('.')[0]
+                        f['acodec'] = va_codecs[1]
                 resolution = last_info.get('RESOLUTION')
                 if resolution:
                     width_str, height_str = resolution.split('x')
@@ -1099,12 +1184,15 @@ class InfoExtractor(object):
         formats = []
         rtmp_count = 0
         http_count = 0
+        m3u8_count = 0
 
+        srcs = []
         videos = smil.findall(self._xpath_ns('.//video', namespace))
         for video in videos:
             src = video.get('src')
-            if not src:
+            if not src or src in srcs:
                 continue
+            srcs.append(src)
 
             bitrate = float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
             filesize = int_or_none(video.get('size') or video.get('fileSize'))
@@ -1136,12 +1224,20 @@ class InfoExtractor(object):
                 continue
 
             src_url = src if src.startswith('http') else compat_urlparse.urljoin(base, src)
+            src_url = src_url.strip()
 
             if proto == 'm3u8' or src_ext == 'm3u8':
                 m3u8_formats = self._extract_m3u8_formats(
                     src_url, video_id, ext or 'mp4', m3u8_id='hls', fatal=False)
-                if m3u8_formats:
-                    formats.extend(m3u8_formats)
+                if len(m3u8_formats) == 1:
+                    m3u8_count += 1
+                    m3u8_formats[0].update({
+                        'format_id': 'hls-%d' % (m3u8_count if bitrate is None else bitrate),
+                        'tbr': bitrate,
+                        'width': width,
+                        'height': height,
+                    })
+                formats.extend(m3u8_formats)
                 continue
 
             if src_ext == 'f4m':
@@ -1153,9 +1249,7 @@ class InfoExtractor(object):
                     }
                 f4m_url += '&' if '?' in f4m_url else '?'
                 f4m_url += compat_urllib_parse.urlencode(f4m_params)
-                f4m_formats = self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False)
-                if f4m_formats:
-                    formats.extend(f4m_formats)
+                formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False))
                 continue
 
             if src_url.startswith('http') and self._is_valid_url(src, video_id):
@@ -1176,11 +1270,13 @@ class InfoExtractor(object):
         return formats
 
     def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
+        urls = []
         subtitles = {}
         for num, textstream in enumerate(smil.findall(self._xpath_ns('.//textstream', namespace))):
             src = textstream.get('src')
-            if not src:
+            if not src or src in urls:
                 continue
+            urls.append(src)
             ext = textstream.get('ext') or determine_ext(src)
             if not ext:
                 type_ = textstream.get('type')
@@ -1241,6 +1337,163 @@ class InfoExtractor(object):
             })
         return entries
 
+    def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}):
+        res = self._download_webpage_handle(
+            mpd_url, video_id,
+            note=note or 'Downloading MPD manifest',
+            errnote=errnote or 'Failed to download MPD manifest',
+            fatal=fatal)
+        if res is False:
+            return []
+        mpd, urlh = res
+        mpd_base_url = re.match(r'https?://.+/', urlh.geturl()).group()
+
+        return self._parse_mpd_formats(
+            compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url, formats_dict=formats_dict)
+
+    def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}):
+        if mpd_doc.get('type') == 'dynamic':
+            return []
+
+        namespace = self._search_regex(r'(?i)^{([^}]+)?}MPD$', mpd_doc.tag, 'namespace', default=None)
+
+        def _add_ns(path):
+            return self._xpath_ns(path, namespace)
+
+        def is_drm_protected(element):
+            return element.find(_add_ns('ContentProtection')) is not None
+
+        def extract_multisegment_info(element, ms_parent_info):
+            ms_info = ms_parent_info.copy()
+            segment_list = element.find(_add_ns('SegmentList'))
+            if segment_list is not None:
+                segment_urls_e = segment_list.findall(_add_ns('SegmentURL'))
+                if segment_urls_e:
+                    ms_info['segment_urls'] = [segment.attrib['media'] for segment in segment_urls_e]
+                initialization = segment_list.find(_add_ns('Initialization'))
+                if initialization is not None:
+                    ms_info['initialization_url'] = initialization.attrib['sourceURL']
+            else:
+                segment_template = element.find(_add_ns('SegmentTemplate'))
+                if segment_template is not None:
+                    start_number = segment_template.get('startNumber')
+                    if start_number:
+                        ms_info['start_number'] = int(start_number)
+                    segment_timeline = segment_template.find(_add_ns('SegmentTimeline'))
+                    if segment_timeline is not None:
+                        s_e = segment_timeline.findall(_add_ns('S'))
+                        if s_e:
+                            ms_info['total_number'] = 0
+                            for s in s_e:
+                                ms_info['total_number'] += 1 + int(s.get('r', '0'))
+                    else:
+                        timescale = segment_template.get('timescale')
+                        if timescale:
+                            ms_info['timescale'] = int(timescale)
+                        segment_duration = segment_template.get('duration')
+                        if segment_duration:
+                            ms_info['segment_duration'] = int(segment_duration)
+                    media_template = segment_template.get('media')
+                    if media_template:
+                        ms_info['media_template'] = media_template
+                    initialization = segment_template.get('initialization')
+                    if initialization:
+                        ms_info['initialization_url'] = initialization
+                    else:
+                        initialization = segment_template.find(_add_ns('Initialization'))
+                        if initialization is not None:
+                            ms_info['initialization_url'] = initialization.attrib['sourceURL']
+            return ms_info
+
+        mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration'))
+        formats = []
+        for period in mpd_doc.findall(_add_ns('Period')):
+            period_duration = parse_duration(period.get('duration')) or mpd_duration
+            period_ms_info = extract_multisegment_info(period, {
+                'start_number': 1,
+                'timescale': 1,
+            })
+            for adaptation_set in period.findall(_add_ns('AdaptationSet')):
+                if is_drm_protected(adaptation_set):
+                    continue
+                adaption_set_ms_info = extract_multisegment_info(adaptation_set, period_ms_info)
+                for representation in adaptation_set.findall(_add_ns('Representation')):
+                    if is_drm_protected(representation):
+                        continue
+                    representation_attrib = adaptation_set.attrib.copy()
+                    representation_attrib.update(representation.attrib)
+                    mime_type = representation_attrib.get('mimeType')
+                    content_type = mime_type.split('/')[0] if mime_type else representation_attrib.get('contentType')
+                    if content_type == 'text':
+                        # TODO implement WebVTT downloading
+                        pass
+                    elif content_type == 'video' or content_type == 'audio':
+                        base_url = ''
+                        for element in (representation, adaptation_set, period, mpd_doc):
+                            base_url_e = element.find(_add_ns('BaseURL'))
+                            if base_url_e is not None:
+                                base_url = base_url_e.text + base_url
+                                if re.match(r'^https?://', base_url):
+                                    break
+                        if mpd_base_url and not re.match(r'^https?://', base_url):
+                            if not mpd_base_url.endswith('/') and not base_url.startswith('/'):
+                                mpd_base_url += '/'
+                            base_url = mpd_base_url + base_url
+                        representation_id = representation_attrib.get('id')
+                        lang = representation_attrib.get('lang')
+                        url_el = representation.find(_add_ns('BaseURL'))
+                        filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength') if url_el is not None else None)
+                        f = {
+                            'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
+                            'url': base_url,
+                            'width': int_or_none(representation_attrib.get('width')),
+                            'height': int_or_none(representation_attrib.get('height')),
+                            'tbr': int_or_none(representation_attrib.get('bandwidth'), 1000),
+                            'asr': int_or_none(representation_attrib.get('audioSamplingRate')),
+                            'fps': int_or_none(representation_attrib.get('frameRate')),
+                            'vcodec': 'none' if content_type == 'audio' else representation_attrib.get('codecs'),
+                            'acodec': 'none' if content_type == 'video' else representation_attrib.get('codecs'),
+                            'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None,
+                            'format_note': 'DASH %s' % content_type,
+                            'filesize': filesize,
+                        }
+                        representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
+                        if 'segment_urls' not in representation_ms_info and 'media_template' in representation_ms_info:
+                            if 'total_number' not in representation_ms_info and 'segment_duration':
+                                segment_duration = float(representation_ms_info['segment_duration']) / float(representation_ms_info['timescale'])
+                                representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
+                            media_template = representation_ms_info['media_template']
+                            media_template = media_template.replace('$RepresentationID$', representation_id)
+                            media_template = re.sub(r'\$(Number|Bandwidth)(?:%(0\d+)d)?\$', r'%(\1)\2d', media_template)
+                            media_template.replace('$$', '$')
+                            representation_ms_info['segment_urls'] = [media_template % {'Number': segment_number, 'Bandwidth': representation_attrib.get('bandwidth')} for segment_number in range(representation_ms_info['start_number'], representation_ms_info['total_number'] + representation_ms_info['start_number'])]
+                        if 'segment_urls' in representation_ms_info:
+                            f.update({
+                                'segment_urls': representation_ms_info['segment_urls'],
+                                'protocol': 'http_dash_segments',
+                            })
+                            if 'initialization_url' in representation_ms_info:
+                                initialization_url = representation_ms_info['initialization_url'].replace('$RepresentationID$', representation_id)
+                                f.update({
+                                    'initialization_url': initialization_url,
+                                })
+                                if not f.get('url'):
+                                    f['url'] = initialization_url
+                        try:
+                            existing_format = next(
+                                fo for fo in formats
+                                if fo['format_id'] == representation_id)
+                        except StopIteration:
+                            full_info = formats_dict.get(representation_id, {}).copy()
+                            full_info.update(f)
+                            formats.append(full_info)
+                        else:
+                            existing_format.update(f)
+                    else:
+                        self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
+        self._sort_formats(formats)
+        return formats
+
     def _live_title(self, name):
         """ Generate the title for a live video """
         now = datetime.datetime.now()
@@ -1277,7 +1530,7 @@ class InfoExtractor(object):
 
     def _get_cookies(self, url):
         """ Return a compat_cookies.SimpleCookie with the cookies for the url """
-        req = compat_urllib_request.Request(url)
+        req = sanitized_Request(url)
         self._downloader.cookiejar.add_cookie_header(req)
         return compat_cookies.SimpleCookie(req.get_header('Cookie'))
 

youtube_dl/extractor/crackle.py

@@ -0,0 +1,95 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class CrackleIE(InfoExtractor):
+    _VALID_URL = r'(?:crackle:|https?://(?:www\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.crackle.com/the-art-of-more/2496419',
+        'info_dict': {
+            'id': '2496419',
+            'ext': 'mp4',
+            'title': 'Heavy Lies the Head',
+            'description': 'md5:bb56aa0708fe7b9a4861535f15c3abca',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }
+
+    # extracted from http://legacyweb-us.crackle.com/flash/QueryReferrer.ashx
+    _SUBTITLE_SERVER = 'http://web-us-az.crackle.com'
+    _UPLYNK_OWNER_ID = 'e8773f7770a44dbd886eee4fca16a66b'
+    _THUMBNAIL_TEMPLATE = 'http://images-us-am.crackle.com/%stnl_1920x1080.jpg?ts=20140107233116?c=635333335057637614'
+
+    # extracted from http://legacyweb-us.crackle.com/flash/ReferrerRedirect.ashx
+    _MEDIA_FILE_SLOTS = {
+        'c544.flv': {
+            'width': 544,
+            'height': 306,
+        },
+        '360p.mp4': {
+            'width': 640,
+            'height': 360,
+        },
+        '480p.mp4': {
+            'width': 852,
+            'height': 478,
+        },
+        '480p_1mbps.mp4': {
+            'width': 852,
+            'height': 478,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        item = self._download_xml(
+            'http://legacyweb-us.crackle.com/app/revamp/vidwallcache.aspx?flags=-1&fm=%s' % video_id,
+            video_id).find('i')
+        title = item.attrib['t']
+
+        thumbnail = None
+        subtitles = {}
+        formats = self._extract_m3u8_formats(
+            'http://content.uplynk.com/ext/%s/%s.m3u8' % (self._UPLYNK_OWNER_ID, video_id),
+            video_id, 'mp4', m3u8_id='hls', fatal=None)
+        path = item.attrib.get('p')
+        if path:
+            thumbnail = self._THUMBNAIL_TEMPLATE % path
+            http_base_url = 'http://ahttp.crackle.com/' + path
+            for mfs_path, mfs_info in self._MEDIA_FILE_SLOTS.items():
+                formats.append({
+                    'url': http_base_url + mfs_path,
+                    'format_id': 'http-' + mfs_path.split('.')[0],
+                    'width': mfs_info['width'],
+                    'height': mfs_info['height'],
+                })
+            for cc in item.findall('cc'):
+                locale = cc.attrib.get('l')
+                v = cc.attrib.get('v')
+                if locale and v:
+                    if locale not in subtitles:
+                        subtitles[locale] = []
+                    subtitles[locale] = [{
+                        'url': '%s/%s%s_%s.xml' % (self._SUBTITLE_SERVER, path, locale, v),
+                        'ext': 'ttml',
+                    }]
+        self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': item.attrib.get('d'),
+            'duration': int(item.attrib.get('r'), 16) if item.attrib.get('r') else None,
+            'series': item.attrib.get('sn'),
+            'season_number': int_or_none(item.attrib.get('se')),
+            'episode_number': int_or_none(item.attrib.get('ep')),
+            'thumbnail': thumbnail,
+            'subtitles': subtitles,
+            'formats': formats,
+        }

youtube_dl/extractor/criterion.py

@@ -27,9 +27,7 @@ class CriterionIE(InfoExtractor):
         final_url = self._search_regex(
             r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
         title = self._og_search_title(webpage)
-        description = self._html_search_regex(
-            r'<meta name="description" content="(.+?)" />',
-            webpage, 'video description')
+        description = self._html_search_meta('description', webpage)
         thumbnail = self._search_regex(
             r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
             webpage, 'thumbnail url')

youtube_dl/extractor/crunchyroll.py

@@ -5,12 +5,12 @@ import re
 import json
 import base64
 import zlib
-import xml.etree.ElementTree
 
 from hashlib import sha1
 from math import pow, sqrt, floor
 from .common import InfoExtractor
 from ..compat import (
+    compat_etree_fromstring,
     compat_urllib_parse,
     compat_urllib_parse_unquote,
     compat_urllib_request,
@@ -21,7 +21,9 @@ from ..utils import (
     bytes_to_intlist,
     intlist_to_bytes,
     int_or_none,
+    lowercase_escape,
     remove_end,
+    sanitized_Request,
     unified_strdate,
     urlencode_postdata,
     xpath_text,
@@ -32,9 +34,29 @@ from ..aes import (
 
 
 class CrunchyrollBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'crunchyroll'
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+        self.report_login()
+        login_url = 'https://www.crunchyroll.com/?a=formhandler'
+        data = urlencode_postdata({
+            'formname': 'RpcApiUser_Login',
+            'name': username,
+            'password': password,
+        })
+        login_request = sanitized_Request(login_url, data)
+        login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        self._download_webpage(login_request, None, False, 'Wrong login info')
+
+    def _real_initialize(self):
+        self._login()
+
     def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
         request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
-                   else compat_urllib_request.Request(url_or_request))
+                   else sanitized_Request(url_or_request))
         # Accept-Language must be set explicitly to accept any language to avoid issues
         # similar to https://github.com/rg3/youtube-dl/issues/6797.
         # Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
@@ -46,10 +68,22 @@ class CrunchyrollBaseIE(InfoExtractor):
         return super(CrunchyrollBaseIE, self)._download_webpage(
             request, video_id, note, errnote, fatal, tries, timeout, encoding)
 
+    @staticmethod
+    def _add_skip_wall(url):
+        parsed_url = compat_urlparse.urlparse(url)
+        qs = compat_urlparse.parse_qs(parsed_url.query)
+        # Always force skip_wall to bypass maturity wall, namely 18+ confirmation message:
+        # > This content may be inappropriate for some people.
+        # > Are you sure you want to continue?
+        # since it's not disabled by default in crunchyroll account's settings.
+        # See https://github.com/rg3/youtube-dl/issues/7202.
+        qs['skip_wall'] = ['1']
+        return compat_urlparse.urlunparse(
+            parsed_url._replace(query=compat_urllib_parse.urlencode(qs, True)))
+
 
 class CrunchyrollIE(CrunchyrollBaseIE):
     _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
-    _NETRC_MACHINE = 'crunchyroll'
     _TESTS = [{
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
         'info_dict': {
@@ -72,7 +106,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             'id': '589804',
             'ext': 'flv',
             'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
-            'description': 'md5:fe2743efedb49d279552926d0bd0cd9e',
+            'description': 'md5:2fbc01f90b87e8e9137296f37b461c12',
             'thumbnail': 're:^https?://.*\.jpg$',
             'uploader': 'Danny Choo Network',
             'upload_date': '20120213',
@@ -81,10 +115,13 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             # rtmp
             'skip_download': True,
         },
-
     }, {
         'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
         'only_matching': True,
+    }, {
+        # geo-restricted (US), 18+ maturity wall, non-premium available
+        'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617',
+        'only_matching': True,
     }]
 
     _FORMAT_IDS = {
@@ -94,24 +131,6 @@ class CrunchyrollIE(CrunchyrollBaseIE):
         '1080': ('80', '108'),
     }
 
-    def _login(self):
-        (username, password) = self._get_login_info()
-        if username is None:
-            return
-        self.report_login()
-        login_url = 'https://www.crunchyroll.com/?a=formhandler'
-        data = urlencode_postdata({
-            'formname': 'RpcApiUser_Login',
-            'name': username,
-            'password': password,
-        })
-        login_request = compat_urllib_request.Request(login_url, data)
-        login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        self._download_webpage(login_request, None, False, 'Wrong login info')
-
-    def _real_initialize(self):
-        self._login()
-
     def _decrypt_subtitles(self, data, iv, id):
         data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
         iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8')))
@@ -217,7 +236,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         return output
 
     def _extract_subtitles(self, subtitle):
-        sub_root = xml.etree.ElementTree.fromstring(subtitle)
+        sub_root = compat_etree_fromstring(subtitle)
         return [{
             'ext': 'srt',
             'data': self._convert_subtitles_to_srt(sub_root),
@@ -228,7 +247,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
     def _get_subtitles(self, video_id, webpage):
         subtitles = {}
-        for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
+        for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage):
             sub_page = self._download_webpage(
                 'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id,
                 video_id, note='Downloading subtitles for ' + sub_name)
@@ -254,7 +273,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         else:
             webpage_url = 'http://www.' + mobj.group('url')
 
-        webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage')
+        webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage')
         note_m = self._html_search_regex(
             r'<div class="showmedia-trailer-notice">(.+?)</div>',
             webpage, 'trailer-notice', default='')
@@ -270,11 +289,15 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         if 'To view this, please log in to verify you are 18 or older.' in webpage:
             self.raise_login_required()
 
-        video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
+        video_title = self._html_search_regex(
+            r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>',
+            webpage, 'video_title')
         video_title = re.sub(r' {2,}', ' ', video_title)
-        video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
-        if not video_description:
-            video_description = None
+        video_description = self._html_search_regex(
+            r'<script[^>]*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id,
+            webpage, 'description', default=None)
+        if video_description:
+            video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
         video_upload_date = self._html_search_regex(
             [r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'],
             webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
@@ -285,7 +308,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             'video_uploader', fatal=False)
 
         playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
-        playerdata_req = compat_urllib_request.Request(playerdata_url)
+        playerdata_req = sanitized_Request(playerdata_url)
         playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
         playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
         playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info')
@@ -297,7 +320,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
             stream_quality, stream_format = self._FORMAT_IDS[fmt]
             video_format = fmt + 'p'
-            streamdata_req = compat_urllib_request.Request(
+            streamdata_req = sanitized_Request(
                 'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
                 % (stream_id, stream_format, stream_quality),
                 compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8'))
@@ -306,8 +329,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                 streamdata_req, video_id,
                 note='Downloading media info for %s' % video_format)
             stream_info = streamdata.find('./{default}preload/stream_info')
-            video_url = stream_info.find('./host').text
-            video_play_path = stream_info.find('./file').text
+            video_url = xpath_text(stream_info, './host')
+            video_play_path = xpath_text(stream_info, './file')
+            if not video_url or not video_play_path:
+                continue
             metadata = stream_info.find('./metadata')
             format_info = {
                 'format': video_format,
@@ -352,7 +377,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
 class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
     IE_NAME = "crunchyroll:playlist"
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?$'
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?(?:\?|$)'
 
     _TESTS = [{
         'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
@@ -361,12 +386,25 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
             'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
         },
         'playlist_count': 13,
+    }, {
+        # geo-restricted (US), 18+ maturity wall, non-premium available
+        'url': 'http://www.crunchyroll.com/cosplay-complex-ova',
+        'info_dict': {
+            'id': 'cosplay-complex-ova',
+            'title': 'Cosplay Complex OVA'
+        },
+        'playlist_count': 3,
+        'skip': 'Georestricted',
+    }, {
+        # geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14
+        'url': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         show_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, show_id)
+        webpage = self._download_webpage(self._add_skip_wall(url), show_id)
         title = self._html_search_regex(
             r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
             webpage, 'title')

youtube_dl/extractor/cspan.py

@@ -9,6 +9,7 @@ from ..utils import (
     find_xpath_attr,
     smuggle_url,
     determine_ext,
+    ExtractorError,
 )
 from .senateisvp import SenateISVPIE
 
@@ -18,33 +19,32 @@ class CSpanIE(InfoExtractor):
     IE_DESC = 'C-SPAN'
     _TESTS = [{
         'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
-        'md5': '8e44ce11f0f725527daccc453f553eb0',
+        'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
         'info_dict': {
             'id': '315139',
             'ext': 'mp4',
             'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
-            'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in Shelby County v. Holder in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
+            'description': 'Attorney General Eric Holder speaks to reporters following the Supreme Court decision in [Shelby County v. Holder], in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced.',
         },
         'skip': 'Regularly fails on travis, for unknown reasons',
     }, {
         'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
-        # For whatever reason, the served video alternates between
-        # two different ones
+        'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
         'info_dict': {
-            'id': '340723',
+            'id': 'c4486943',
             'ext': 'mp4',
-            'title': 'International Health Care Models',
+            'title': 'CSPAN - International Health Care Models',
             'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
         }
     }, {
         'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
-        'md5': '446562a736c6bf97118e389433ed88d4',
+        'md5': '2ae5051559169baadba13fc35345ae74',
         'info_dict': {
             'id': '342759',
             'ext': 'mp4',
             'title': 'General Motors Ignition Switch Recall',
             'duration': 14848,
-            'description': 'md5:70c7c3b8fa63fa60d42772440596034c'
+            'description': 'md5:118081aedd24bf1d3b68b3803344e7f3'
         },
     }, {
         # Video from senate.gov
@@ -57,67 +57,94 @@ class CSpanIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        page_id = mobj.group('id')
-        webpage = self._download_webpage(url, page_id)
-        video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id')
+        video_id = self._match_id(url)
+        video_type = None
+        webpage = self._download_webpage(url, video_id)
+        # We first look for clipid, because clipprog always appears before
+        patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
+        results = list(filter(None, (re.search(p, webpage) for p in patterns)))
+        if results:
+            matches = results[0]
+            video_type, video_id = matches.groups()
+            video_type = 'clip' if video_type == 'id' else 'program'
+        else:
+            m = re.search(r'data-(?P<type>clip|prog)id=["\'](?P<id>\d+)', webpage)
+            if m:
+                video_id = m.group('id')
+                video_type = 'program' if m.group('type') == 'prog' else 'clip'
+            else:
+                senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
+                if senate_isvp_url:
+                    title = self._og_search_title(webpage)
+                    surl = smuggle_url(senate_isvp_url, {'force_title': title})
+                    return self.url_result(surl, 'SenateISVP', video_id, title)
+        if video_type is None or video_id is None:
+            raise ExtractorError('unable to find video id and type')
 
-        description = self._html_search_regex(
-            [
-                # The full description
-                r'<div class=\'expandable\'>(.*?)<a href=\'#\'',
-                # If the description is small enough the other div is not
-                # present, otherwise this is a stripped version
-                r'<p class=\'initial\'>(.*?)</p>'
-            ],
-            webpage, 'description', flags=re.DOTALL, default=None)
+        def get_text_attr(d, attr):
+            return d.get(attr, {}).get('#text')
 
-        info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
-        data = self._download_json(info_url, video_id)
+        data = self._download_json(
+            'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id),
+            video_id)['video']
+        if data['@status'] != 'Success':
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True)
 
         doc = self._download_xml(
-            'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
+            'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id),
             video_id)
 
+        description = self._html_search_meta('description', webpage)
+
         title = find_xpath_attr(doc, './/string', 'name', 'title').text
         thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
 
-        senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
-        if senate_isvp_url:
-            surl = smuggle_url(senate_isvp_url, {'force_title': title})
-            return self.url_result(surl, 'SenateISVP', video_id, title)
+        files = data['files']
+        capfile = get_text_attr(data, 'capfile')
 
-        files = data['video']['files']
-        try:
-            capfile = data['video']['capfile']['#text']
-        except KeyError:
-            capfile = None
-
-        entries = [{
-            'id': '%s_%d' % (video_id, partnum + 1),
-            'title': (
-                title if len(files) == 1 else
-                '%s part %d' % (title, partnum + 1)),
-            'url': unescapeHTML(f['path']['#text']),
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': int_or_none(f.get('length', {}).get('#text')),
-            'subtitles': {
-                'en': [{
-                    'url': capfile,
-                    'ext': determine_ext(capfile, 'dfxp')
-                }],
-            } if capfile else None,
-        } for partnum, f in enumerate(files)]
+        entries = []
+        for partnum, f in enumerate(files):
+            formats = []
+            for quality in f['qualities']:
+                formats.append({
+                    'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
+                    'url': unescapeHTML(get_text_attr(quality, 'file')),
+                    'height': int_or_none(get_text_attr(quality, 'height')),
+                    'tbr': int_or_none(get_text_attr(quality, 'bitrate')),
+                })
+            if not formats:
+                path = unescapeHTML(get_text_attr(f, 'path'))
+                if not path:
+                    continue
+                formats = self._extract_m3u8_formats(
+                    path, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls') if determine_ext(path) == 'm3u8' else [{'url': path, }]
+            self._sort_formats(formats)
+            entries.append({
+                'id': '%s_%d' % (video_id, partnum + 1),
+                'title': (
+                    title if len(files) == 1 else
+                    '%s part %d' % (title, partnum + 1)),
+                'formats': formats,
+                'description': description,
+                'thumbnail': thumbnail,
+                'duration': int_or_none(get_text_attr(f, 'length')),
+                'subtitles': {
+                    'en': [{
+                        'url': capfile,
+                        'ext': determine_ext(capfile, 'dfxp')
+                    }],
+                } if capfile else None,
+            })
 
         if len(entries) == 1:
             entry = dict(entries[0])
-            entry['id'] = video_id
+            entry['id'] = 'c' + video_id if video_type == 'clip' else video_id
             return entry
         else:
             return {
                 '_type': 'playlist',
                 'entries': entries,
                 'title': title,
-                'id': video_id,
+                'id': 'c' + video_id if video_type == 'clip' else video_id,
             }

youtube_dl/extractor/cultureunplugged.py

@@ -0,0 +1,63 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class CultureUnpluggedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cultureunplugged\.com/documentary/watch-online/play/(?P<id>\d+)(?:/(?P<display_id>[^/]+))?'
+    _TESTS = [{
+        'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662/The-Next--Best-West',
+        'md5': 'ac6c093b089f7d05e79934dcb3d228fc',
+        'info_dict': {
+            'id': '53662',
+            'display_id': 'The-Next--Best-West',
+            'ext': 'mp4',
+            'title': 'The Next, Best West',
+            'description': 'md5:0423cd00833dea1519cf014e9d0903b1',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'creator': 'Coldstream Creative',
+            'duration': 2203,
+            'view_count': int,
+        }
+    }, {
+        'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id') or video_id
+
+        movie_data = self._download_json(
+            'http://www.cultureunplugged.com/movie-data/cu-%s.json' % video_id, display_id)
+
+        video_url = movie_data['url']
+        title = movie_data['title']
+
+        description = movie_data.get('synopsis')
+        creator = movie_data.get('producer')
+        duration = int_or_none(movie_data.get('duration'))
+        view_count = int_or_none(movie_data.get('views'))
+
+        thumbnails = [{
+            'url': movie_data['%s_thumb' % size],
+            'id': size,
+            'preference': preference,
+        } for preference, size in enumerate((
+            'small', 'large')) if movie_data.get('%s_thumb' % size)]
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'creator': creator,
+            'duration': duration,
+            'view_count': view_count,
+            'thumbnails': thumbnails,
+        }

youtube_dl/extractor/cwtv.py

@@ -0,0 +1,88 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class CWTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cw(?:tv|seed)\.com/shows/(?:[^/]+/){2}\?play=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
+    _TESTS = [{
+        'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63',
+        'info_dict': {
+            'id': '6b15e985-9345-4f60-baf8-56e96be57c63',
+            'ext': 'mp4',
+            'title': 'Legends of Yesterday',
+            'description': 'Oliver and Barry Allen take Kendra Saunders and Carter Hall to a remote location to keep them hidden from Vandal Savage while they figure out how to defeat him.',
+            'duration': 2665,
+            'series': 'Arrow',
+            'season_number': 4,
+            'season': '4',
+            'episode_number': 8,
+            'upload_date': '20151203',
+            'timestamp': 1449122100,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://www.cwseed.com/shows/whose-line-is-it-anyway/jeff-davis-4/?play=24282b12-ead2-42f2-95ad-26770c2c6088',
+        'info_dict': {
+            'id': '24282b12-ead2-42f2-95ad-26770c2c6088',
+            'ext': 'mp4',
+            'title': 'Jeff Davis 4',
+            'description': 'Jeff Davis is back to make you laugh.',
+            'duration': 1263,
+            'series': 'Whose Line Is It Anyway?',
+            'season_number': 11,
+            'season': '11',
+            'episode_number': 20,
+            'upload_date': '20151006',
+            'timestamp': 1444107300,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._download_json(
+            'http://metaframe.digitalsmiths.tv/v2/CWtv/assets/%s/partner/132?format=json' % video_id, video_id)
+
+        formats = self._extract_m3u8_formats(
+            video_data['videos']['variantplaylist']['uri'], video_id, 'mp4')
+
+        thumbnails = [{
+            'url': image['uri'],
+            'width': image.get('width'),
+            'height': image.get('height'),
+        } for image_id, image in video_data['images'].items() if image.get('uri')] if video_data.get('images') else None
+
+        video_metadata = video_data['assetFields']
+
+        subtitles = {
+            'en': [{
+                'url': video_metadata['UnicornCcUrl'],
+            }],
+        } if video_metadata.get('UnicornCcUrl') else None
+
+        return {
+            'id': video_id,
+            'title': video_metadata['title'],
+            'description': video_metadata.get('description'),
+            'duration': int_or_none(video_metadata.get('duration')),
+            'series': video_metadata.get('seriesName'),
+            'season_number': int_or_none(video_metadata.get('seasonNumber')),
+            'season': video_metadata.get('seasonName'),
+            'episode_number': int_or_none(video_metadata.get('episodeNumber')),
+            'timestamp': parse_iso8601(video_data.get('startTime')),
+            'thumbnails': thumbnails,
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/dailymotion.py

@@ -7,15 +7,13 @@ import itertools
 
 from .common import InfoExtractor
 
-from ..compat import (
-    compat_str,
-    compat_urllib_request,
-)
 from ..utils import (
-    ExtractorError,
     determine_ext,
+    error_to_compat_str,
+    ExtractorError,
     int_or_none,
     parse_iso8601,
+    sanitized_Request,
     str_to_int,
     unescapeHTML,
 )
@@ -25,7 +23,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
     @staticmethod
     def _build_request(url):
         """Build a request with the family filter disabled"""
-        request = compat_urllib_request.Request(url)
+        request = sanitized_Request(url)
         request.add_header('Cookie', 'family_filter=off; ff=off')
         return request
 
@@ -39,7 +37,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
 
 
 class DailymotionIE(DailymotionBaseInfoExtractor):
-    _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'
+    _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:embed|swf|#)/)?video/(?P<id>[^/?_]+)'
     IE_NAME = 'dailymotion'
 
     _FORMATS = [
@@ -96,6 +94,20 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 'uploader': 'HotWaves1012',
                 'age_limit': 18,
             }
+        },
+        # geo-restricted, player v5
+        {
+            'url': 'http://www.dailymotion.com/video/xhza0o',
+            'only_matching': True,
+        },
+        # with subtitles
+        {
+            'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news',
+            'only_matching': True,
+        },
+        {
+            'url': 'http://www.dailymotion.com/swf/video/x3n92nf',
+            'only_matching': True,
         }
     ]
 
@@ -119,11 +131,16 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             webpage, 'comment count', fatal=False))
 
         player_v5 = self._search_regex(
-            r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);',
+            [r'buildPlayer\(({.+?})\);\n',  # See https://github.com/rg3/youtube-dl/issues/7826
+             r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);',
+             r'buildPlayer\(({.+?})\);'],
             webpage, 'player v5', default=None)
         if player_v5:
             player = self._parse_json(player_v5, video_id)
             metadata = player['metadata']
+
+            self._check_error(metadata)
+
             formats = []
             for quality, media_list in metadata['qualities'].items():
                 for media in media_list:
@@ -133,13 +150,18 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                     type_ = media.get('type')
                     if type_ == 'application/vnd.lumberjack.manifest':
                         continue
-                    if type_ == 'application/x-mpegURL' or determine_ext(media_url) == 'm3u8':
+                    ext = determine_ext(media_url)
+                    if type_ == 'application/x-mpegURL' or ext == 'm3u8':
                         formats.extend(self._extract_m3u8_formats(
-                            media_url, video_id, 'mp4', m3u8_id='hls'))
+                            media_url, video_id, 'mp4', preference=-1,
+                            m3u8_id='hls', fatal=False))
+                    elif type_ == 'application/f4m' or ext == 'f4m':
+                        formats.extend(self._extract_f4m_formats(
+                            media_url, video_id, preference=-1, f4m_id='hds', fatal=False))
                     else:
                         f = {
                             'url': media_url,
-                            'format_id': quality,
+                            'format_id': 'http-%s' % quality,
                         }
                         m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url)
                         if m:
@@ -158,11 +180,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             uploader_id = metadata.get('owner', {}).get('id')
 
             subtitles = {}
-            for subtitle_lang, subtitle in metadata.get('subtitles', {}).get('data', {}).items():
-                subtitles[subtitle_lang] = [{
-                    'ext': determine_ext(subtitle_url),
-                    'url': subtitle_url,
-                } for subtitle_url in subtitle.get('urls', [])]
+            subtitles_data = metadata.get('subtitles', {}).get('data', {})
+            if subtitles_data and isinstance(subtitles_data, dict):
+                for subtitle_lang, subtitle in subtitles_data.items():
+                    subtitles[subtitle_lang] = [{
+                        'ext': determine_ext(subtitle_url),
+                        'url': subtitle_url,
+                    } for subtitle_url in subtitle.get('urls', [])]
 
             return {
                 'id': video_id,
@@ -201,9 +225,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 'video info', flags=re.MULTILINE),
             video_id)
 
-        if info.get('error') is not None:
-            msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
-            raise ExtractorError(msg, expected=True)
+        self._check_error(info)
 
         formats = []
         for (key, format_id) in self._FORMATS:
@@ -246,13 +268,18 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             'duration': info['duration']
         }
 
+    def _check_error(self, info):
+        if info.get('error') is not None:
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, info['error']['title']), expected=True)
+
     def _get_subtitles(self, video_id, webpage):
         try:
             sub_list = self._download_webpage(
                 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
                 video_id, note=False)
         except ExtractorError as err:
-            self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err))
+            self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
             return {}
         info = json.loads(sub_list)
         if (info['total'] > 0):
@@ -313,7 +340,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 
 class DailymotionUserIE(DailymotionPlaylistIE):
     IE_NAME = 'dailymotion:user'
-    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)'
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
     _TESTS = [{
         'url': 'https://www.dailymotion.com/user/nqtv',

youtube_dl/extractor/daum.py

@@ -3,56 +3,91 @@
 from __future__ import unicode_literals
 
 import re
+import itertools
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_parse_qs,
     compat_urllib_parse,
+    compat_urllib_parse_unquote,
+    compat_urlparse,
+)
+from ..utils import (
+    int_or_none,
+    str_to_int,
+    xpath_text,
+    unescapeHTML,
 )
 
 
 class DaumIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:v/|.*?clipid=)(?P<id>[^?#&]+)'
+    _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)'
     IE_NAME = 'daum.net'
 
     _TESTS = [{
-        'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
+        'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
         'info_dict': {
-            'id': '52554690',
+            'id': 'vab4dyeDBysyBssyukBUjBz',
             'ext': 'mp4',
-            'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
-            'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
-            'upload_date': '20130831',
-            'duration': 3868,
+            'title': '마크 헌트 vs 안토니오 실바',
+            'description': 'Mark Hunt vs Antonio Silva',
+            'upload_date': '20131217',
+            'thumbnail': 're:^https?://.*\.(?:jpg|png)',
+            'duration': 2117,
+            'view_count': int,
+            'comment_count': int,
         },
     }, {
-        'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
-        'only_matching': True,
+        'url': 'http://m.tvpot.daum.net/v/65139429',
+        'info_dict': {
+            'id': '65139429',
+            'ext': 'mp4',
+            'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118',
+            'description': 'md5:79794514261164ff27e36a21ad229fc5',
+            'upload_date': '20150604',
+            'thumbnail': 're:^https?://.*\.(?:jpg|png)',
+            'duration': 154,
+            'view_count': int,
+            'comment_count': int,
+        },
     }, {
         'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
         'only_matching': True,
+    }, {
+        'url': 'http://videofarm.daum.net/controller/player/VodPlayer.swf?vid=vwIpVpCQsT8%24&ref=',
+        'info_dict': {
+            'id': 'vwIpVpCQsT8$',
+            'ext': 'flv',
+            'title': '01-Korean War ( Trouble on the horizon )',
+            'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름',
+            'upload_date': '20080223',
+            'thumbnail': 're:^https?://.*\.(?:jpg|png)',
+            'duration': 249,
+            'view_count': int,
+            'comment_count': int,
+        },
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
-        webpage = self._download_webpage(canonical_url, video_id)
-        full_id = self._search_regex(
-            r'src=["\']http://videofarm\.daum\.net/controller/video/viewer/Video\.html\?.*?vid=(.+?)[&"\']',
-            webpage, 'full id')
-        query = compat_urllib_parse.urlencode({'vid': full_id})
+        video_id = compat_urllib_parse_unquote(self._match_id(url))
+        query = compat_urllib_parse.urlencode({'vid': video_id})
+        movie_data = self._download_json(
+            'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json?' + query,
+            video_id, 'Downloading video formats info')
+
+        # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid
+        if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id):
+            return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id)
+
         info = self._download_xml(
             'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
             'Downloading video info')
-        urls = self._download_xml(
-            'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
-            video_id, 'Downloading video formats info')
 
         formats = []
-        for format_el in urls.findall('result/output_list/output_list'):
-            profile = format_el.attrib['profile']
+        for format_el in movie_data['output_list']['output_list']:
+            profile = format_el['profile']
             format_query = compat_urllib_parse.urlencode({
-                'vid': full_id,
+                'vid': video_id,
                 'profile': profile,
             })
             url_doc = self._download_xml(
@@ -62,14 +97,202 @@ class DaumIE(InfoExtractor):
             formats.append({
                 'url': format_url,
                 'format_id': profile,
+                'width': int_or_none(format_el.get('width')),
+                'height': int_or_none(format_el.get('height')),
+                'filesize': int_or_none(format_el.get('filesize')),
             })
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': info.find('TITLE').text,
             'formats': formats,
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'description': info.find('CONTENTS').text,
-            'duration': int(info.find('DURATION').text),
+            'thumbnail': xpath_text(info, 'THUMB_URL'),
+            'description': xpath_text(info, 'CONTENTS'),
+            'duration': int_or_none(xpath_text(info, 'DURATION')),
             'upload_date': info.find('REGDTTM').text[:8],
+            'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')),
+            'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')),
         }
+
+
+class DaumClipIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
+    IE_NAME = 'daum.net:clip'
+    _URL_TEMPLATE = 'http://tvpot.daum.net/clip/ClipView.do?clipid=%s'
+
+    _TESTS = [{
+        'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
+        'info_dict': {
+            'id': '52554690',
+            'ext': 'mp4',
+            'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
+            'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
+            'upload_date': '20130831',
+            'thumbnail': 're:^https?://.*\.(?:jpg|png)',
+            'duration': 3868,
+            'view_count': int,
+        },
+    }, {
+        'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if DaumPlaylistIE.suitable(url) or DaumUserIE.suitable(url) else super(DaumClipIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        clip_info = self._download_json(
+            'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id,
+            video_id, 'Downloading clip info')['clip_bean']
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
+            'title': unescapeHTML(clip_info['title']),
+            'thumbnail': clip_info.get('thumb_url'),
+            'description': clip_info.get('contents'),
+            'duration': int_or_none(clip_info.get('duration')),
+            'upload_date': clip_info.get('up_date')[:8],
+            'view_count': int_or_none(clip_info.get('play_count')),
+            'ie_key': 'Daum',
+        }
+
+
+class DaumListIE(InfoExtractor):
+    def _get_entries(self, list_id, list_id_type):
+        name = None
+        entries = []
+        for pagenum in itertools.count(1):
+            list_info = self._download_json(
+                'http://tvpot.daum.net/mypot/json/GetClipInfo.do?size=48&init=true&order=date&page=%d&%s=%s' % (
+                    pagenum, list_id_type, list_id), list_id, 'Downloading list info - %s' % pagenum)
+
+            entries.extend([
+                self.url_result(
+                    'http://tvpot.daum.net/v/%s' % clip['vid'])
+                for clip in list_info['clip_list']
+            ])
+
+            if not name:
+                name = list_info.get('playlist_bean', {}).get('name') or \
+                    list_info.get('potInfo', {}).get('name')
+
+            if not list_info.get('has_more'):
+                break
+
+        return name, entries
+
+    def _check_clip(self, url, list_id):
+        query_dict = compat_parse_qs(compat_urlparse.urlparse(url).query)
+        if 'clipid' in query_dict:
+            clip_id = query_dict['clipid'][0]
+            if self._downloader.params.get('noplaylist'):
+                self.to_screen('Downloading just video %s because of --no-playlist' % clip_id)
+                return self.url_result(DaumClipIE._URL_TEMPLATE % clip_id, 'DaumClip')
+            else:
+                self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id)
+
+
+class DaumPlaylistIE(DaumListIE):
+    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View\.do|Top\.tv)\?.*?playlistid=(?P<id>[0-9]+)'
+    IE_NAME = 'daum.net:playlist'
+    _URL_TEMPLATE = 'http://tvpot.daum.net/mypot/View.do?playlistid=%s'
+
+    _TESTS = [{
+        'note': 'Playlist url with clipid',
+        'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
+        'info_dict': {
+            'id': '6213966',
+            'title': 'Woorissica Official',
+        },
+        'playlist_mincount': 181
+    }, {
+        'note': 'Playlist url with clipid - noplaylist',
+        'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
+        'info_dict': {
+            'id': '73806844',
+            'ext': 'mp4',
+            'title': '151017 Airport',
+            'upload_date': '20160117',
+        },
+        'params': {
+            'noplaylist': True,
+            'skip_download': True,
+        }
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if DaumUserIE.suitable(url) else super(DaumPlaylistIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+
+        clip_result = self._check_clip(url, list_id)
+        if clip_result:
+            return clip_result
+
+        name, entries = self._get_entries(list_id, 'playlistid')
+
+        return self.playlist_result(entries, list_id, name)
+
+
+class DaumUserIE(DaumListIE):
+    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View|Top)\.(?:do|tv)\?.*?ownerid=(?P<id>[0-9a-zA-Z]+)'
+    IE_NAME = 'daum.net:user'
+
+    _TESTS = [{
+        'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0',
+        'info_dict': {
+            'id': 'o2scDLIVbHc0',
+            'title': '마이 리틀 텔레비전',
+        },
+        'playlist_mincount': 213
+    }, {
+        'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&clipid=73801156',
+        'info_dict': {
+            'id': '73801156',
+            'ext': 'mp4',
+            'title': '[미공개] 김구라, 오만석이 부릅니다 \'오케피\' - 마이 리틀 텔레비전 20160116',
+            'upload_date': '20160117',
+            'description': 'md5:5e91d2d6747f53575badd24bd62b9f36'
+        },
+        'params': {
+            'noplaylist': True,
+            'skip_download': True,
+        }
+    }, {
+        'note': 'Playlist url has ownerid and playlistid, playlistid takes precedence',
+        'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&playlistid=6196631',
+        'info_dict': {
+            'id': '6196631',
+            'title': '마이 리틀 텔레비전 - 20160109',
+        },
+        'playlist_count': 11
+    }, {
+        'url': 'http://tvpot.daum.net/mypot/Top.do?ownerid=o2scDLIVbHc0',
+        'only_matching': True,
+    }, {
+        'url': 'http://m.tvpot.daum.net/mypot/Top.tv?ownerid=45x1okb1If50&playlistid=3569733',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+
+        clip_result = self._check_clip(url, list_id)
+        if clip_result:
+            return clip_result
+
+        query_dict = compat_parse_qs(compat_urlparse.urlparse(url).query)
+        if 'playlistid' in query_dict:
+            playlist_id = query_dict['playlistid'][0]
+            return self.url_result(DaumPlaylistIE._URL_TEMPLATE % playlist_id, 'DaumPlaylist')
+
+        name, entries = self._get_entries(list_id, 'ownerid')
+
+        return self.playlist_result(entries, list_id, name)

youtube_dl/extractor/dbtv.py

@@ -13,8 +13,8 @@ from ..utils import (
 
 
 class DBTVIE(InfoExtractor):
-    _VALID_URL = r'http://dbtv\.no/(?P<id>[0-9]+)#(?P<display_id>.+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:(?:lazyplayer|player)/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?'
+    _TESTS = [{
         'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
         'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc',
         'info_dict': {
@@ -30,12 +30,18 @@ class DBTVIE(InfoExtractor):
             'view_count': int,
             'categories': list,
         }
-    }
+    }, {
+        'url': 'http://dbtv.no/3649835190001',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.dbtv.no/lazyplayer/4631135248001',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
+        display_id = mobj.group('display_id') or video_id
 
         data = self._download_json(
             'http://api.dbtv.no/discovery/%s' % video_id, display_id)

youtube_dl/extractor/dcn.py

@@ -1,28 +1,90 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+import base64
+
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
-    compat_urllib_request,
+    compat_str,
 )
 from ..utils import (
     int_or_none,
     parse_iso8601,
+    sanitized_Request,
+    smuggle_url,
+    unsmuggle_url,
 )
 
 
 class DCNIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
+
+    def _real_extract(self, url):
+        show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
+        if video_id and int(video_id) > 0:
+            return self.url_result(
+                'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo')
+        elif season_id and int(season_id) > 0:
+            return self.url_result(smuggle_url(
+                'http://www.dcndigital.ae/program/season/%s' % season_id,
+                {'show_id': show_id}), 'DCNSeason')
+        else:
+            return self.url_result(
+                'http://www.dcndigital.ae/program/%s' % show_id, 'DCNSeason')
+
+
+class DCNBaseIE(InfoExtractor):
+    def _extract_video_info(self, video_data, video_id, is_live):
+        title = video_data.get('title_en') or video_data['title_ar']
+        img = video_data.get('img')
+        thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
+        duration = int_or_none(video_data.get('duration'))
+        description = video_data.get('description_en') or video_data.get('description_ar')
+        timestamp = parse_iso8601(video_data.get('create_time'), ' ')
+
+        return {
+            'id': video_id,
+            'title': self._live_title(title) if is_live else title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'is_live': is_live,
+        }
+
+    def _extract_video_formats(self, webpage, video_id, entry_protocol):
+        formats = []
+        m3u8_url = self._html_search_regex(
+            r'file\s*:\s*"([^"]+)', webpage, 'm3u8 url', fatal=False)
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=None))
+
+        rtsp_url = self._search_regex(
+            r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
+        if rtsp_url:
+            formats.append({
+                'url': rtsp_url,
+                'format_id': 'rtsp',
+            })
+
+        self._sort_formats(formats)
+        return formats
+
+
+class DCNVideoIE(DCNBaseIE):
+    IE_NAME = 'dcn:video'
+    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
     _TEST = {
-        'url': 'http://www.dcndigital.ae/#/show/199074/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375/6887',
+        'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375',
         'info_dict':
         {
             'id': '17375',
             'ext': 'mp4',
             'title': 'رحلة العمر : الحلقة 1',
             'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
-            'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 2041,
             'timestamp': 1227504126,
             'upload_date': '20081124',
@@ -36,49 +98,99 @@ class DCNIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        request = compat_urllib_request.Request(
+        request = sanitized_Request(
             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
             headers={'Origin': 'http://www.dcndigital.ae'})
-
-        video = self._download_json(request, video_id)
-        title = video.get('title_en') or video['title_ar']
+        video_data = self._download_json(request, video_id)
+        info = self._extract_video_info(video_data, video_id, False)
 
         webpage = self._download_webpage(
             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
             compat_urllib_parse.urlencode({
-                'id': video['id'],
-                'user_id': video['user_id'],
-                'signature': video['signature'],
+                'id': video_data['id'],
+                'user_id': video_data['user_id'],
+                'signature': video_data['signature'],
                 'countries': 'Q0M=',
                 'filter': 'DENY',
             }), video_id)
+        info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native')
+        return info
 
-        m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
-        formats = self._extract_m3u8_formats(
-            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
 
-        rtsp_url = self._search_regex(
-            r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
-        if rtsp_url:
-            formats.append({
-                'url': rtsp_url,
-                'format_id': 'rtsp',
+class DCNLiveIE(DCNBaseIE):
+    IE_NAME = 'dcn:live'
+    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)'
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+
+        request = sanitized_Request(
+            'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
+            headers={'Origin': 'http://www.dcndigital.ae'})
+
+        channel_data = self._download_json(request, channel_id)
+        info = self._extract_video_info(channel_data, channel_id, True)
+
+        webpage = self._download_webpage(
+            'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
+            compat_urllib_parse.urlencode({
+                'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
+                'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
+                'signature': channel_data['signature'],
+                'countries': 'Q0M=',
+                'filter': 'DENY',
+            }), channel_id)
+        info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8')
+        return info
+
+
+class DCNSeasonIE(InfoExtractor):
+    IE_NAME = 'dcn:season'
+    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
+    _TEST = {
+        'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A',
+        'info_dict':
+        {
+            'id': '7910',
+            'title': 'محاضرات الشيخ الشعراوي',
+        },
+        'playlist_mincount': 27,
+    }
+
+    def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+        show_id, season_id = re.match(self._VALID_URL, url).groups()
+
+        data = {}
+        if season_id:
+            data['season'] = season_id
+            show_id = smuggled_data.get('show_id')
+            if show_id is None:
+                request = sanitized_Request(
+                    'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
+                    headers={'Origin': 'http://www.dcndigital.ae'})
+                season = self._download_json(request, season_id)
+                show_id = season['id']
+        data['show_id'] = show_id
+        request = sanitized_Request(
+            'http://admin.mangomolo.com/analytics/index.php/plus/show',
+            compat_urllib_parse.urlencode(data),
+            {
+                'Origin': 'http://www.dcndigital.ae',
+                'Content-Type': 'application/x-www-form-urlencoded'
             })
 
-        self._sort_formats(formats)
+        show = self._download_json(request, show_id)
+        if not season_id:
+            season_id = show['default_season']
+        for season in show['seasons']:
+            if season['id'] == season_id:
+                title = season.get('title_en') or season['title_ar']
 
-        img = video.get('img')
-        thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
-        duration = int_or_none(video.get('duration'))
-        description = video.get('description_en') or video.get('description_ar')
-        timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ')
+                entries = []
+                for video in show['videos']:
+                    video_id = compat_str(video['id'])
+                    entries.append(self.url_result(
+                        'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo', video_id))
 
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'timestamp': timestamp,
-            'formats': formats,
-        }
+                return self.playlist_result(entries, season_id, title)

youtube_dl/extractor/democracynow.py

@@ -0,0 +1,88 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import os.path
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+from ..utils import (
+    url_basename,
+    remove_start,
+)
+
+
+class DemocracynowIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?democracynow.org/(?P<id>[^\?]*)'
+    IE_NAME = 'democracynow'
+    _TESTS = [{
+        'url': 'http://www.democracynow.org/shows/2015/7/3',
+        'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d',
+        'info_dict': {
+            'id': '2015-0703-001',
+            'ext': 'mp4',
+            'title': 'July 03, 2015 - Democracy Now!',
+            'description': 'A daily independent global news hour with Amy Goodman & Juan González "What to the Slave is 4th of July?": James Earl Jones Reads Frederick Douglass\u2019 Historic Speech : "This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag : "We Shall Overcome": Remembering Folk Icon, Activist Pete Seeger in His Own Words & Songs',
+        },
+    }, {
+        'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree',
+        'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d',
+        'info_dict': {
+            'id': '2015-0703-001',
+            'ext': 'mp4',
+            'title': '"This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag',
+            'description': 'md5:4d2bc4f0d29f5553c2210a4bc7761a21',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        description = self._og_search_description(webpage)
+
+        json_data = self._parse_json(self._search_regex(
+            r'<script[^>]+type="text/json"[^>]*>\s*({[^>]+})', webpage, 'json'),
+            display_id)
+        video_id = None
+        formats = []
+
+        default_lang = 'en'
+
+        subtitles = {}
+
+        def add_subtitle_item(lang, info_dict):
+            if lang not in subtitles:
+                subtitles[lang] = []
+            subtitles[lang].append(info_dict)
+
+        # chapter_file are not subtitles
+        if 'caption_file' in json_data:
+            add_subtitle_item(default_lang, {
+                'url': compat_urlparse.urljoin(url, json_data['caption_file']),
+            })
+
+        for subtitle_item in json_data.get('captions', []):
+            lang = subtitle_item.get('language', '').lower() or default_lang
+            add_subtitle_item(lang, {
+                'url': compat_urlparse.urljoin(url, subtitle_item['url']),
+            })
+
+        for key in ('file', 'audio', 'video'):
+            media_url = json_data.get(key, '')
+            if not media_url:
+                continue
+            media_url = re.sub(r'\?.*', '', compat_urlparse.urljoin(url, media_url))
+            video_id = video_id or remove_start(os.path.splitext(url_basename(media_url))[0], 'dn')
+            formats.append({
+                'url': media_url,
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id or display_id,
+            'title': json_data['title'],
+            'description': description,
+            'subtitles': subtitles,
+            'formats': formats,
+        }

youtube_dl/extractor/digiteka.py

@@ -0,0 +1,112 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class DigitekaIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?(?:digiteka\.net|ultimedia\.com)/
+        (?:
+            deliver/
+            (?P<embed_type>
+                generic|
+                musique
+            )
+            (?:/[^/]+)*/
+            (?:
+                src|
+                article
+            )|
+            default/index/video
+            (?P<site_type>
+                generic|
+                music
+            )
+            /id
+        )/(?P<id>[\d+a-z]+)'''
+    _TESTS = [{
+        # news
+        'url': 'https://www.ultimedia.com/default/index/videogeneric/id/s8uk0r',
+        'md5': '276a0e49de58c7e85d32b057837952a2',
+        'info_dict': {
+            'id': 's8uk0r',
+            'ext': 'mp4',
+            'title': 'Loi sur la fin de vie: le texte prévoit un renforcement des directives anticipées',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 74,
+            'upload_date': '20150317',
+            'timestamp': 1426604939,
+            'uploader_id': '3fszv',
+        },
+    }, {
+        # music
+        'url': 'https://www.ultimedia.com/default/index/videomusic/id/xvpfp8',
+        'md5': '2ea3513813cf230605c7e2ffe7eca61c',
+        'info_dict': {
+            'id': 'xvpfp8',
+            'ext': 'mp4',
+            'title': 'Two - C\'est La Vie (clip)',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 233,
+            'upload_date': '20150224',
+            'timestamp': 1424760500,
+            'uploader_id': '3rfzk',
+        },
+    }, {
+        'url': 'https://www.digiteka.net/deliver/generic/iframe/mdtk/01637594/src/lqm3kl/zone/1/showtitle/1/autoplay/yes',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<(?:iframe|script)[^>]+src=["\'](?P<url>(?:https?:)?//(?:www\.)?ultimedia\.com/deliver/(?:generic|musique)(?:/[^/]+)*/(?:src|article)/[\d+a-z]+)',
+            webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        video_type = mobj.group('embed_type') or mobj.group('site_type')
+        if video_type == 'music':
+            video_type = 'musique'
+
+        deliver_info = self._download_json(
+            'http://www.ultimedia.com/deliver/video?video=%s&topic=%s' % (video_id, video_type),
+            video_id)
+
+        yt_id = deliver_info.get('yt_id')
+        if yt_id:
+            return self.url_result(yt_id, 'Youtube')
+
+        jwconf = deliver_info['jwconf']
+
+        formats = []
+        for source in jwconf['playlist'][0]['sources']:
+            formats.append({
+                'url': source['file'],
+                'format_id': source.get('label'),
+            })
+
+        self._sort_formats(formats)
+
+        title = deliver_info['title']
+        thumbnail = jwconf.get('image')
+        duration = int_or_none(deliver_info.get('duration'))
+        timestamp = int_or_none(deliver_info.get('release_time'))
+        uploader_id = deliver_info.get('owner_id')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'uploader_id': uploader_id,
+            'formats': formats,
+        }

youtube_dl/extractor/discovery.py

@@ -9,7 +9,17 @@ from ..compat import compat_str
 
 
 class DiscoveryIE(InfoExtractor):
-    _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?'
+    _VALID_URL = r'''(?x)http://(?:www\.)?(?:
+            discovery|
+            investigationdiscovery|
+            discoverylife|
+            animalplanet|
+            ahctv|
+            destinationamerica|
+            sciencechannel|
+            tlc|
+            velocity
+        )\.com/(?:[^/]+/)*(?P<id>[^./?#]+)'''
     _TESTS = [{
         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
         'info_dict': {
@@ -21,8 +31,8 @@ class DiscoveryIE(InfoExtractor):
                             'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
                             ' back.'),
             'duration': 156,
-            'timestamp': 1303099200,
-            'upload_date': '20110418',
+            'timestamp': 1302032462,
+            'upload_date': '20110405',
         },
         'params': {
             'skip_download': True,  # requires ffmpeg
@@ -33,27 +43,38 @@ class DiscoveryIE(InfoExtractor):
             'id': 'mythbusters-the-simpsons',
             'title': 'MythBusters: The Simpsons',
         },
-        'playlist_count': 9,
+        'playlist_mincount': 10,
+    }, {
+        'url': 'http://www.animalplanet.com/longfin-eels-maneaters/',
+        'info_dict': {
+            'id': '78326',
+            'ext': 'mp4',
+            'title': 'Longfin Eels: Maneaters?',
+            'description': 'Jeremy Wade tests whether or not New Zealand\'s longfin eels are man-eaters by covering himself in fish guts and getting in the water with them.',
+            'upload_date': '20140725',
+            'timestamp': 1406246400,
+            'duration': 116,
+        },
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        info = self._download_json(url + '?flat=1', video_id)
+        display_id = self._match_id(url)
+        info = self._download_json(url + '?flat=1', display_id)
 
         video_title = info.get('playlist_title') or info.get('video_title')
 
         entries = [{
             'id': compat_str(video_info['id']),
             'formats': self._extract_m3u8_formats(
-                video_info['src'], video_id, ext='mp4',
+                video_info['src'], display_id, 'mp4', 'm3u8_native', m3u8_id='hls',
                 note='Download m3u8 information for video %d' % (idx + 1)),
             'title': video_info['title'],
             'description': video_info.get('description'),
             'duration': parse_duration(video_info.get('video_length')),
-            'webpage_url': video_info.get('href'),
+            'webpage_url': video_info.get('href') or video_info.get('url'),
             'thumbnail': video_info.get('thumbnailURL'),
             'alt_title': video_info.get('secondary_title'),
             'timestamp': parse_iso8601(video_info.get('publishedDate')),
         } for idx, video_info in enumerate(info['playlist'])]
 
-        return self.playlist_result(entries, video_id, video_title)
+        return self.playlist_result(entries, display_id, video_title)

youtube_dl/extractor/dplay.py

@@ -0,0 +1,51 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import time
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class DPlayIE(InfoExtractor):
+    _VALID_URL = r'http://www\.dplay\.se/[^/]+/(?P<id>[^/?#]+)'
+
+    _TEST = {
+        'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/',
+        'info_dict': {
+            'id': '3172',
+            'ext': 'mp4',
+            'display_id': 'season-1-svensken-lar-sig-njuta-av-livet',
+            'title': 'Svensken lär sig njuta av livet',
+            'duration': 2650,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_id = self._search_regex(
+            r'data-video-id="(\d+)"', webpage, 'video id')
+
+        info = self._download_json(
+            'http://www.dplay.se/api/v2/ajax/videos?video_id=' + video_id,
+            video_id)['data'][0]
+
+        self._set_cookie(
+            'secure.dplay.se', 'dsc-geo',
+            '{"countryCode":"NL","expiry":%d}' % ((time.time() + 20 * 60) * 1000))
+        # TODO: consider adding support for 'stream_type=hds', it seems to
+        # require setting some cookies
+        manifest_url = self._download_json(
+            'https://secure.dplay.se/secure/api/v2/user/authorization/stream/%s?stream_type=hls' % video_id,
+            video_id, 'Getting manifest url for hls stream')['hls']
+        formats = self._extract_m3u8_formats(
+            manifest_url, video_id, ext='mp4', entry_protocol='m3u8_native')
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': info['title'],
+            'formats': formats,
+            'duration': int_or_none(info.get('video_metadata_length'), scale=1000),
+        }

youtube_dl/extractor/dramafever.py

@@ -3,23 +3,21 @@ from __future__ import unicode_literals
 
 import itertools
 
-from .common import InfoExtractor
+from .amp import AMPIE
 from ..compat import (
     compat_HTTPError,
     compat_urllib_parse,
-    compat_urllib_request,
     compat_urlparse,
 )
 from ..utils import (
     ExtractorError,
     clean_html,
-    determine_ext,
     int_or_none,
-    parse_iso8601,
+    sanitized_Request,
 )
 
 
-class DramaFeverBaseIE(InfoExtractor):
+class DramaFeverBaseIE(AMPIE):
     _LOGIN_URL = 'https://www.dramafever.com/accounts/login/'
     _NETRC_MACHINE = 'dramafever'
 
@@ -51,7 +49,7 @@ class DramaFeverBaseIE(InfoExtractor):
             'password': password,
         }
 
-        request = compat_urllib_request.Request(
+        request = sanitized_Request(
             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
         response = self._download_webpage(
             request, None, 'Logging in as %s' % username)
@@ -69,71 +67,56 @@ class DramaFeverBaseIE(InfoExtractor):
 class DramaFeverIE(DramaFeverBaseIE):
     IE_NAME = 'dramafever'
     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
         'info_dict': {
             'id': '4512.1',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Cooking with Shin 4512.1',
             'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0',
+            'episode': 'Episode 1',
+            'episode_number': 1,
             'thumbnail': 're:^https?://.*\.jpg',
             'timestamp': 1404336058,
             'upload_date': '20140702',
             'duration': 343,
-        }
-    }
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.dramafever.com/drama/4826/4/Mnet_Asian_Music_Awards_2015/?ap=1',
+        'info_dict': {
+            'id': '4826.4',
+            'ext': 'mp4',
+            'title': 'Mnet Asian Music Awards 2015 4826.4',
+            'description': 'md5:3ff2ee8fedaef86e076791c909cf2e91',
+            'episode': 'Mnet Asian Music Awards 2015 - Part 3',
+            'episode_number': 4,
+            'thumbnail': 're:^https?://.*\.jpg',
+            'timestamp': 1450213200,
+            'upload_date': '20151215',
+            'duration': 5602,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url).replace('/', '.')
 
         try:
-            feed = self._download_json(
-                'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id,
-                video_id, 'Downloading episode JSON')['channel']['item']
+            info = self._extract_feed_info(
+                'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id)
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError):
                 raise ExtractorError(
                     'Currently unavailable in your country.', expected=True)
             raise
 
-        media_group = feed.get('media-group', {})
-
-        formats = []
-        for media_content in media_group['media-content']:
-            src = media_content.get('@attributes', {}).get('url')
-            if not src:
-                continue
-            ext = determine_ext(src)
-            if ext == 'f4m':
-                formats.extend(self._extract_f4m_formats(
-                    src, video_id, f4m_id='hds'))
-            elif ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    src, video_id, 'mp4', m3u8_id='hls'))
-            else:
-                formats.append({
-                    'url': src,
-                })
-        self._sort_formats(formats)
-
-        title = media_group.get('media-title')
-        description = media_group.get('media-description')
-        duration = int_or_none(media_group['media-content'][0].get('@attributes', {}).get('duration'))
-        thumbnail = self._proto_relative_url(
-            media_group.get('media-thumbnail', {}).get('@attributes', {}).get('url'))
-        timestamp = parse_iso8601(feed.get('pubDate'), ' ')
-
-        subtitles = {}
-        for media_subtitle in media_group.get('media-subTitle', []):
-            lang = media_subtitle.get('@attributes', {}).get('lang')
-            href = media_subtitle.get('@attributes', {}).get('href')
-            if not lang or not href:
-                continue
-            subtitles[lang] = [{
-                'ext': 'ttml',
-                'url': href,
-            }]
-
         series_id, episode_number = video_id.split('.')
         episode_info = self._download_json(
             # We only need a single episode info, so restricting page size to one episode
@@ -143,24 +126,24 @@ class DramaFeverIE(DramaFeverBaseIE):
             video_id, 'Downloading episode info JSON', fatal=False)
         if episode_info:
             value = episode_info.get('value')
-            if value:
-                subfile = value[0].get('subfile') or value[0].get('new_subfile')
-                if subfile and subfile != 'http://www.dramafever.com/st/':
-                    subtitles.setdefault('English', []).append({
-                        'ext': 'srt',
-                        'url': subfile,
-                    })
+            if isinstance(value, list):
+                for v in value:
+                    if v.get('type') == 'Episode':
+                        subfile = v.get('subfile') or v.get('new_subfile')
+                        if subfile and subfile != 'http://www.dramafever.com/st/':
+                            info.setdefault('subtitles', {}).setdefault('English', []).append({
+                                'ext': 'srt',
+                                'url': subfile,
+                            })
+                        episode_number = int_or_none(v.get('number'))
+                        episode_fallback = 'Episode'
+                        if episode_number:
+                            episode_fallback += ' %d' % episode_number
+                        info['episode'] = v.get('title') or episode_fallback
+                        info['episode_number'] = episode_number
+                        break
 
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'timestamp': timestamp,
-            'duration': duration,
-            'formats': formats,
-            'subtitles': subtitles,
-        }
+        return info
 
 
 class DramaFeverSeriesIE(DramaFeverBaseIE):

youtube_dl/extractor/dreisat.py

@@ -2,14 +2,10 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    unified_strdate,
-)
+from .zdf import ZDFIE
 
 
-class DreiSatIE(InfoExtractor):
+class DreiSatIE(ZDFIE):
     IE_NAME = '3sat'
     _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php|mediathek\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
     _TESTS = [
@@ -35,53 +31,4 @@ class DreiSatIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
-        details_doc = self._download_xml(details_url, video_id, 'Downloading video details')
-
-        status_code = details_doc.find('./status/statuscode')
-        if status_code is not None and status_code.text != 'ok':
-            code = status_code.text
-            if code == 'notVisibleAnymore':
-                message = 'Video %s is not available' % video_id
-            else:
-                message = '%s returned error: %s' % (self.IE_NAME, code)
-            raise ExtractorError(message, expected=True)
-
-        thumbnail_els = details_doc.findall('.//teaserimage')
-        thumbnails = [{
-            'width': int(te.attrib['key'].partition('x')[0]),
-            'height': int(te.attrib['key'].partition('x')[2]),
-            'url': te.text,
-        } for te in thumbnail_els]
-
-        information_el = details_doc.find('.//information')
-        video_title = information_el.find('./title').text
-        video_description = information_el.find('./detail').text
-
-        details_el = details_doc.find('.//details')
-        video_uploader = details_el.find('./channel').text
-        upload_date = unified_strdate(details_el.find('./airtime').text)
-
-        format_els = details_doc.findall('.//formitaet')
-        formats = [{
-            'format_id': fe.attrib['basetype'],
-            'width': int(fe.find('./width').text),
-            'height': int(fe.find('./height').text),
-            'url': fe.find('./url').text,
-            'filesize': int(fe.find('./filesize').text),
-            'video_bitrate': int(fe.find('./videoBitrate').text),
-        } for fe in format_els
-            if not fe.find('./url').text.startswith('http://www.metafilegenerator.de/')]
-
-        self._sort_formats(formats)
-
-        return {
-            '_type': 'video',
-            'id': video_id,
-            'title': video_title,
-            'formats': formats,
-            'description': video_description,
-            'thumbnails': thumbnails,
-            'thumbnail': thumbnails[-1]['url'],
-            'uploader': video_uploader,
-            'upload_date': upload_date,
-        }
+        return self.extract_from_xml_url(video_id, details_url)

youtube_dl/extractor/drtv.py

@@ -91,7 +91,7 @@ class DRTVIE(InfoExtractor):
                 subtitles_list = asset.get('SubtitlesList')
                 if isinstance(subtitles_list, list):
                     LANGS = {
-                        'Danish': 'dk',
+                        'Danish': 'da',
                     }
                     for subs in subtitles_list:
                         lang = subs['Language']