release 2016.03.14

[downloader/external] Add FFmpegFD

.gitignore

@@ -1,5 +1,6 @@
 *.pyc
 *.pyo
+*.class
 *~
 *.DS_Store
 wine-py2exe/

AUTHORS

@@ -157,3 +157,9 @@ Founder Fang
 Andrew Alexeyew
 Saso Bezlaj
 Erwin de Haan
+Jens Wille
+Robin Houtevelts
+Patrick Griffis
+Aidan Rowe
+mutantmonkey
+Ben Congdon

CONTRIBUTING.md

@@ -1,6 +1,6 @@
-**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:
+**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
+$ youtube-dl -v <your command line>
 [debug] System config: []
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
@@ -92,7 +92,9 @@ If you want to create a build of youtube-dl yourself, you'll need
 
 ### Adding support for a new site
 
-If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`):
+If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
+
+After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`):
 
 1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
 2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git`
@@ -140,16 +142,17 @@ If you want to add support for a new site, you can follow this quick list (assum
     ```
 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 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.
+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/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). 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).
+8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`.
-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:
+9. Check the code with [flake8](https://pypi.python.org/pypi/flake8).
+10. 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:
 
         $ git add youtube_dl/extractor/__init__.py
         $ git add youtube_dl/extractor/yourextractor.py
         $ git commit -m '[yourextractor] Add new extractor'
         $ git push origin yourextractor
 
-10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
+11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
 
 In any case, thank you very much for your contributions!
 

Makefile

@@ -3,6 +3,7 @@ all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bas
 clean:
 	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp youtube-dl youtube-dl.exe
 	find . -name "*.pyc" -delete
+	find . -name "*.class" -delete
 
 PREFIX ?= /usr/local
 BINDIR ?= $(PREFIX)/bin
@@ -44,7 +45,7 @@ test:
 ot: offlinetest
 
 offlinetest: codetest
-	nosetests --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py
+	$(PYTHON) -m nose --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py
 
 tar: youtube-dl.tar.gz
 

README.md

@@ -80,6 +80,8 @@ which means you can modify it, redistribute it or use it however you like.
                                      on Windows)
     --flat-playlist                  Do not extract the videos of a playlist,
                                      only list them.
+    --mark-watched                   Mark videos watched (YouTube only)
+    --no-mark-watched                Do not mark videos watched (YouTube only)
     --no-color                       Do not emit color codes in output
 
 ## Network Options:
@@ -179,7 +181,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      to play it)
     --external-downloader COMMAND    Use the specified external downloader.
                                      Currently supports
-                                     aria2c,axel,curl,httpie,wget
+                                     aria2c,avconv,axel,curl,ffmpeg,httpie,wget
     --external-downloader-args ARGS  Give these arguments to the external
                                      downloader
 
@@ -409,13 +411,18 @@ which means you can modify it, redistribute it or use it however you like.
 
 # CONFIGURATION
 
-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:
+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, use a proxy and save all videos under `Movies` directory in your home directory:
 ```
---extract-audio
+-x
 --no-mtime
 --proxy 127.0.0.1:3128
+-o ~/Movies/%(title)s.%(ext)s
 ```
 
+Note that options in configuration file are just the same options aka switches used in regular command line calls thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`.
+
 You can use `--ignore-config` if you want to disable the configuration file for a particular youtube-dl run.
 
 ### Authentication with `.netrc` file
@@ -440,7 +447,11 @@ 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 parentheses, followed by a lowercase S. Allowed names are:
+The `-o` option allows users to indicate a template for the output file names.
+
+**tl;dr:** [navigate me to examples](#output-template-examples).
+
+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`: Video identifier
  - `title`: Video title
@@ -449,6 +460,7 @@ The `-o` option allows users to indicate a template for the output file names. T
  - `alt_title`: A secondary title of the video
  - `display_id`: An alternative identifier for the video
  - `uploader`: Full name of the video uploader
+ - `license`: License name the video is licensed under
  - `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
@@ -513,7 +525,9 @@ 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):
+#### Output template 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
@@ -525,6 +539,9 @@ 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 all playlists of YouTube channel/user keeping each playlist in separate directory:
+$ youtube-dl -o '%(uploader)s/%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/user/TheLinuxFoundation/playlists
+
 # 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/
 
@@ -543,6 +560,8 @@ But sometimes you may want to download in a different format, for example when y
 
 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.
 
+**tl;dr:** [navigate me to examples](#format-selection-examples).
+
 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.
@@ -588,11 +607,14 @@ You can merge the video and audio of two formats into a single file using `-f <v
 
 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.
+Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see [#5447](https://github.com/rg3/youtube-dl/issues/5447), [#5456](https://github.com/rg3/youtube-dl/issues/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):
+#### Format selection 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'
@@ -733,7 +755,7 @@ means you're using an outdated version of Python. Please update to Python 2.6 or
 
 ### What is this binary file? Where has the code gone?
 
-Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`.
+Since June 2012 ([#342](https://github.com/rg3/youtube-dl/issues/342)) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`.
 
 ### The exe throws a *Runtime error from Visual C++*
 
@@ -816,7 +838,9 @@ If you want to create a build of youtube-dl yourself, you'll need
 
 ### Adding support for a new site
 
-If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`):
+If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
+
+After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`):
 
 1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
 2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git`
@@ -864,16 +888,17 @@ If you want to add support for a new site, you can follow this quick list (assum
     ```
 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 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.
+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/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). 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).
+8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`.
-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:
+9. Check the code with [flake8](https://pypi.python.org/pypi/flake8).
+10. 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:
 
         $ git add youtube_dl/extractor/__init__.py
         $ git add youtube_dl/extractor/yourextractor.py
         $ git commit -m '[yourextractor] Add new extractor'
         $ git push origin yourextractor
 
-10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
+11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
 
 In any case, thank you very much for your contributions!
 
@@ -935,9 +960,9 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
 
 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`**, 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:
+**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
+$ youtube-dl -v <your command line>
 [debug] System config: []
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']

docs/supportedsites.md

@@ -30,6 +30,7 @@
  - **AlJazeera**
  - **Allocine**
  - **AlphaPorno**
+ - **AnimeOnDemand**
  - **anitube.se**
  - **AnySex**
  - **Aparat**
@@ -49,9 +50,11 @@
  - **arte.tv:ddc**
  - **arte.tv:embed**
  - **arte.tv:future**
+ - **arte.tv:magazine**
  - **AtresPlayer**
  - **ATTTechChannel**
  - **AudiMedia**
+ - **AudioBoom**
  - **audiomack**
  - **audiomack:album**
  - **Azubu**
@@ -75,6 +78,7 @@
  - **BleacherReportCMS**
  - **blinkx**
  - **Bloomberg**
+ - **BokeCC**
  - **Bpb**: Bundeszentrale für politische Bildung
  - **BR**: Bayerischer Rundfunk Mediathek
  - **Break**
@@ -89,6 +93,8 @@
  - **canalc2.tv**
  - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
  - **Canvas**
+ - **CBC**
+ - **CBCPlayer**
  - **CBS**
  - **CBSNews**: CBS News
  - **CBSNewsLiveVideo**: CBS News Live Videos
@@ -120,6 +126,7 @@
  - **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**
@@ -161,6 +168,8 @@
  - **Dump**
  - **Dumpert**
  - **dvtv**: http://video.aktualne.cz/
+ - **dw**
+ - **dw:article**
  - **EaglePlatform**
  - **EbaumsWorld**
  - **EchoMsk**
@@ -184,10 +193,10 @@
  - **ExpoTV**
  - **ExtremeTube**
  - **facebook**
- - **facebook:post**
  - **faz.net**
  - **fc2**
  - **Fczenit**
+ - **features.aol.com**
  - **fernsehkritik.tv**
  - **Firstpost**
  - **FiveTV**
@@ -287,6 +296,7 @@
  - **kontrtube**: KontrTube.ru - Труба зовёт
  - **KrasView**: Красвью
  - **Ku6**
+ - **KUSI**
  - **kuwo:album**: 酷我音乐 - 专辑
  - **kuwo:category**: 酷我音乐 - 分类
  - **kuwo:chart**: 酷我音乐 - 排行榜
@@ -295,12 +305,11 @@
  - **kuwo:song**: 酷我音乐
  - **la7.tv**
  - **Laola1Tv**
+ - **Le**: 乐视网
  - **Lecture2Go**
  - **Lemonde**
- - **Letv**: 乐视网
+ - **LePlaylist**
  - **LetvCloud**: 乐视云
- - **LetvPlaylist**
- - **LetvTv**
  - **Libsyn**
  - **life:embed**
  - **lifenews**: LIFE | NEWS
@@ -318,6 +327,7 @@
  - **m6**
  - **macgamestore**: MacGameStore trailers
  - **mailru**: Видео@Mail.Ru
+ - **MakersChannel**
  - **MakerTV**
  - **Malemotion**
  - **MatchTV**
@@ -328,6 +338,7 @@
  - **Mgoon**
  - **Minhateca**
  - **MinistryGrid**
+ - **Minoto**
  - **miomio.tv**
  - **MiTele**: mitele.es
  - **mixcloud**
@@ -357,7 +368,7 @@
  - **MySpace:album**
  - **MySpass**
  - **Myvi**
- - **myvideo**
+ - **myvideo** (Currently broken)
  - **MyVidster**
  - **n-tv.de**
  - **NationalGeographic**
@@ -407,6 +418,7 @@
  - **NowTV** (Currently broken)
  - **NowTVList**
  - **nowvideo**: NowVideo
+ - **Noz**
  - **npo**: npo.nl and ntr.nl
  - **npo.nl:live**
  - **npo.nl:radio**
@@ -414,6 +426,7 @@
  - **Npr**
  - **NRK**
  - **NRKPlaylist**
+ - **NRKSkole**: NRK Skole
  - **NRKTV**: NRK TV and NRK Radio
  - **ntv.ru**
  - **Nuvid**
@@ -445,6 +458,7 @@
  - **PlanetaPlay**
  - **play.fm**
  - **played.to**
+ - **PlaysTV**
  - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
  - **Playvid**
  - **Playwire**
@@ -456,6 +470,7 @@
  - **PornHd**
  - **PornHub**
  - **PornHubPlaylist**
+ - **PornHubUserVideos**
  - **Pornotube**
  - **PornoVoisines**
  - **PornoXO**
@@ -518,6 +533,7 @@
  - **screen.yahoo:search**: Yahoo screen search
  - **Screencast**
  - **ScreencastOMatic**
+ - **ScreenJunkies**
  - **ScreenwaveMedia**
  - **SenateISVP**
  - **ServingSys**
@@ -551,7 +567,6 @@
  - **southpark.de**
  - **southpark.nl**
  - **southparkstudios.dk**
- - **Space**
  - **SpankBang**
  - **Spankwire**
  - **Spiegel**
@@ -611,6 +626,7 @@
  - **TMZ**
  - **TMZArticle**
  - **TNAFlix**
+ - **TNAFlixNetworkEmbed**
  - **toggle**
  - **tou.tv**
  - **Toypics**: Toypics user profile
@@ -651,6 +667,7 @@
  - **twitch:video**
  - **twitch:vod**
  - **twitter**
+ - **twitter:amplify**
  - **twitter:card**
  - **Ubu**
  - **udemy**
@@ -658,8 +675,10 @@
  - **UDNEmbed**: 聯合影音
  - **Unistra**
  - **Urort**: NRK P3 Urørt
+ - **USAToday**
  - **ustream**
  - **ustream:channel**
+ - **Ustudio**
  - **Varzesh3**
  - **Vbox7**
  - **VeeHD**
@@ -670,12 +689,13 @@
  - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
  - **vh1.com**
  - **Vice**
+ - **ViceShow**
  - **Viddler**
  - **video.google:search**: Google Video search
  - **video.mit.edu**
  - **VideoDetective**
  - **videofy.me**
- - **VideoMega** (Currently broken)
+ - **VideoMega**
  - **videomore**
  - **videomore:season**
  - **videomore:video**
@@ -697,6 +717,7 @@
  - **vimeo:channel**
  - **vimeo:group**
  - **vimeo:likes**: Vimeo user likes
+ - **vimeo:ondemand**
  - **vimeo:review**: Review pages on vimeo
  - **vimeo:user**
  - **vimeo:watchlater**: Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)

test/helper.py

@@ -11,8 +11,11 @@ import sys
 
 import youtube_dl.extractor
 from youtube_dl import YoutubeDL
-from youtube_dl.utils import (
+from youtube_dl.compat import (
+    compat_os_name,
     compat_str,
+)
+from youtube_dl.utils import (
     preferredencoding,
     write_string,
 )
@@ -42,7 +45,7 @@ def report_warning(message):
     Print the message to stderr, it will be prefixed with 'WARNING:'
     If stderr is a tty file the 'WARNING:' will be colored
     '''
-    if sys.stderr.isatty() and os.name != 'nt':
+    if sys.stderr.isatty() and compat_os_name != 'nt':
         _msg_header = '\033[0;33mWARNING:\033[0m'
     else:
         _msg_header = 'WARNING:'

test/test_YoutubeDL.py

@@ -234,7 +234,7 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_youtube_format_selection(self):
         order = [
-            '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '36', '17', '13',
+            '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13',
             # Apple HTTP Live Streaming
             '96', '95', '94', '93', '92', '132', '151',
             # 3D
@@ -502,6 +502,9 @@ class TestYoutubeDL(unittest.TestCase):
         assertRegexpMatches(self, ydl._format_note({
             'vbr': 10,
         }), '^\s*10k$')
+        assertRegexpMatches(self, ydl._format_note({
+            'fps': 30,
+        }), '^30fps$')
 
     def test_postprocessors(self):
         filename = 'post-processor-testfile.mp4'

test/test_http.py

@@ -52,7 +52,12 @@ class TestHTTP(unittest.TestCase):
             ('localhost', 0), HTTPTestRequestHandler)
         self.httpd.socket = ssl.wrap_socket(
             self.httpd.socket, certfile=certfn, server_side=True)
-        self.port = self.httpd.socket.getsockname()[1]
+        if os.name == 'java':
+            # In Jython SSLSocket is not a subclass of socket.socket
+            sock = self.httpd.socket.sock
+        else:
+            sock = self.httpd.socket
+        self.port = sock.getsockname()[1]
         self.server_thread = threading.Thread(target=self.httpd.serve_forever)
         self.server_thread.daemon = True
         self.server_thread.start()

test/test_iqiyi_sdk_interpreter.py

@@ -0,0 +1,47 @@
+#!/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__))))
+
+from test.helper import FakeYDL
+from youtube_dl.extractor import IqiyiIE
+
+
+class IqiyiIEWithCredentials(IqiyiIE):
+    def _get_login_info(self):
+        return 'foo', 'bar'
+
+
+class WarningLogger(object):
+    def __init__(self):
+        self.messages = []
+
+    def warning(self, msg):
+        self.messages.append(msg)
+
+    def debug(self, msg):
+        pass
+
+    def error(self, msg):
+        pass
+
+
+class TestIqiyiSDKInterpreter(unittest.TestCase):
+    def test_iqiyi_sdk_interpreter(self):
+        '''
+        Test the functionality of IqiyiSDKInterpreter by trying to log in
+
+        If `sign` is incorrect, /validate call throws an HTTP 556 error
+        '''
+        logger = WarningLogger()
+        ie = IqiyiIEWithCredentials(FakeYDL({'logger': logger}))
+        ie._login()
+        self.assertTrue('unable to log in:' in logger.messages[0])
+
+if __name__ == '__main__':
+    unittest.main()

test/test_utils.py

@@ -18,6 +18,7 @@ import xml.etree.ElementTree
 from youtube_dl.utils import (
     age_restricted,
     args_to_str,
+    encode_base_n,
     clean_html,
     DateRange,
     detect_exe_version,
@@ -35,10 +36,12 @@ from youtube_dl.utils import (
     is_html,
     js_to_json,
     limit_length,
+    ohdave_rsa_encrypt,
     OnDemandPagedList,
     orderedSet,
     parse_duration,
     parse_filesize,
+    parse_count,
     parse_iso8601,
     read_batch_urls,
     sanitize_filename,
@@ -59,6 +62,7 @@ from youtube_dl.utils import (
     lowercase_escape,
     url_basename,
     urlencode_postdata,
+    update_url_query,
     version_tuple,
     xpath_with_ns,
     xpath_element,
@@ -74,6 +78,8 @@ from youtube_dl.utils import (
 )
 from youtube_dl.compat import (
     compat_etree_fromstring,
+    compat_urlparse,
+    compat_parse_qs,
 )
 
 
@@ -248,6 +254,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(
             unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
             '20150202')
+        self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
         self.assertEqual(unified_strdate('25-09-2014'), '20140925')
         self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
 
@@ -451,6 +458,40 @@ class TestUtil(unittest.TestCase):
         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
         self.assertTrue(isinstance(data, bytes))
 
+    def test_update_url_query(self):
+        def query_dict(url):
+            return compat_parse_qs(compat_urlparse.urlparse(url).query)
+        self.assertEqual(query_dict(update_url_query(
+            'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})),
+            query_dict('http://example.com/path?quality=HD&format=mp4'))
+        self.assertEqual(query_dict(update_url_query(
+            'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})),
+            query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
+        self.assertEqual(query_dict(update_url_query(
+            'http://example.com/path', {'fields': 'id,formats,subtitles'})),
+            query_dict('http://example.com/path?fields=id,formats,subtitles'))
+        self.assertEqual(query_dict(update_url_query(
+            'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})),
+            query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
+        self.assertEqual(query_dict(update_url_query(
+            'http://example.com/path?manifest=f4m', {'manifest': []})),
+            query_dict('http://example.com/path'))
+        self.assertEqual(query_dict(update_url_query(
+            'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})),
+            query_dict('http://example.com/path?system=LINUX'))
+        self.assertEqual(query_dict(update_url_query(
+            'http://example.com/path', {'fields': b'id,formats,subtitles'})),
+            query_dict('http://example.com/path?fields=id,formats,subtitles'))
+        self.assertEqual(query_dict(update_url_query(
+            'http://example.com/path', {'width': 1080, 'height': 720})),
+            query_dict('http://example.com/path?width=1080&height=720'))
+        self.assertEqual(query_dict(update_url_query(
+            'http://example.com/path', {'bitrate': 5020.43})),
+            query_dict('http://example.com/path?bitrate=5020.43'))
+        self.assertEqual(query_dict(update_url_query(
+            'http://example.com/path', {'test': '第二行тест'})),
+            query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
+
     def test_dict_get(self):
         FALSE_VALUES = {
             'none': None,
@@ -613,6 +654,15 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
         self.assertEqual(parse_filesize('1,24 KB'), 1240)
 
+    def test_parse_count(self):
+        self.assertEqual(parse_count(None), None)
+        self.assertEqual(parse_count(''), None)
+        self.assertEqual(parse_count('0'), 0)
+        self.assertEqual(parse_count('1000'), 1000)
+        self.assertEqual(parse_count('1.000'), 1000)
+        self.assertEqual(parse_count('1.1k'), 1100)
+        self.assertEqual(parse_count('1.1kk'), 1100000)
+
     def test_version_tuple(self):
         self.assertEqual(version_tuple('1'), (1,))
         self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
@@ -792,6 +842,24 @@ The first line
                 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
             ['--check-certificate=true'])
 
+    def test_ohdave_rsa_encrypt(self):
+        N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
+        e = 65537
+
+        self.assertEqual(
+            ohdave_rsa_encrypt(b'aa111222', e, N),
+            '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
+
+    def test_encode_base_n(self):
+        self.assertEqual(encode_base_n(0, 30), '0')
+        self.assertEqual(encode_base_n(80, 30), '2k')
+
+        custom_table = '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA'
+        self.assertEqual(encode_base_n(0, 30, custom_table), '9')
+        self.assertEqual(encode_base_n(80, 30, custom_table), '7P')
+
+        self.assertRaises(ValueError, encode_base_n, 0, 70)
+        self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table)
 
 if __name__ == '__main__':
     unittest.main()

youtube_dl/YoutubeDL.py

@@ -24,9 +24,6 @@ import time
 import tokenize
 import traceback
 
-if os.name == 'nt':
-    import ctypes
-
 from .compat import (
     compat_basestring,
     compat_cookiejar,
@@ -34,6 +31,7 @@ from .compat import (
     compat_get_terminal_size,
     compat_http_client,
     compat_kwargs,
+    compat_os_name,
     compat_str,
     compat_tokenize_tokenize,
     compat_urllib_error,
@@ -87,6 +85,7 @@ from .extractor import get_info_extractor, gen_extractors
 from .downloader import get_suitable_downloader
 from .downloader.rtmp import rtmpdump_version
 from .postprocessor import (
+    FFmpegFixupM3u8PP,
     FFmpegFixupM4aPP,
     FFmpegFixupStretchedPP,
     FFmpegMergerPP,
@@ -95,6 +94,9 @@ from .postprocessor import (
 )
 from .version import __version__
 
+if compat_os_name == 'nt':
+    import ctypes
+
 
 class YoutubeDL(object):
     """YoutubeDL class.
@@ -450,7 +452,7 @@ class YoutubeDL(object):
     def to_console_title(self, message):
         if not self.params.get('consoletitle', False):
             return
-        if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
+        if compat_os_name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
             # c_wchar_p() might not be necessary if `message` is
             # already of type unicode()
             ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
@@ -521,7 +523,7 @@ class YoutubeDL(object):
         else:
             if self.params.get('no_warnings'):
                 return
-            if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt':
+            if not self.params.get('no_color') and self._err_file.isatty() and compat_os_name != 'nt':
                 _msg_header = '\033[0;33mWARNING:\033[0m'
             else:
                 _msg_header = 'WARNING:'
@@ -533,7 +535,7 @@ class YoutubeDL(object):
         Do the same as trouble, but prefixes the message with 'ERROR:', colored
         in red if stderr is a tty file.
         '''
-        if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt':
+        if not self.params.get('no_color') and self._err_file.isatty() and compat_os_name != 'nt':
             _msg_header = '\033[0;31mERROR:\033[0m'
         else:
             _msg_header = 'ERROR:'
@@ -566,7 +568,7 @@ class YoutubeDL(object):
                 elif template_dict.get('height'):
                     template_dict['resolution'] = '%sp' % template_dict['height']
                 elif template_dict.get('width'):
-                    template_dict['resolution'] = '?x%d' % template_dict['width']
+                    template_dict['resolution'] = '%dx?' % template_dict['width']
 
             sanitize = lambda k, v: sanitize_filename(
                 compat_str(v),
@@ -605,12 +607,12 @@ class YoutubeDL(object):
             if rejecttitle:
                 if re.search(rejecttitle, title, re.IGNORECASE):
                     return '"' + title + '" title matched reject pattern "' + rejecttitle + '"'
-        date = info_dict.get('upload_date', None)
+        date = info_dict.get('upload_date')
         if date is not None:
             dateRange = self.params.get('daterange', DateRange())
             if date not in dateRange:
                 return '%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
-        view_count = info_dict.get('view_count', None)
+        view_count = info_dict.get('view_count')
         if view_count is not None:
             min_views = self.params.get('min_views')
             if min_views is not None and view_count < min_views:
@@ -747,18 +749,18 @@ class YoutubeDL(object):
                 new_result, download=download, extra_info=extra_info)
         elif result_type == 'playlist' or result_type == 'multi_video':
             # We process each entry in the playlist
-            playlist = ie_result.get('title', None) or ie_result.get('id', None)
+            playlist = ie_result.get('title') or ie_result.get('id')
             self.to_screen('[download] Downloading playlist: %s' % playlist)
 
             playlist_results = []
 
             playliststart = self.params.get('playliststart', 1) - 1
-            playlistend = self.params.get('playlistend', None)
+            playlistend = self.params.get('playlistend')
             # For backwards compatibility, interpret -1 as whole list
             if playlistend == -1:
                 playlistend = None
 
-            playlistitems_str = self.params.get('playlist_items', None)
+            playlistitems_str = self.params.get('playlist_items')
             playlistitems = None
             if playlistitems_str is not None:
                 def iter_playlistitems(format):
@@ -782,7 +784,7 @@ class YoutubeDL(object):
                     entries = ie_entries[playliststart:playlistend]
                 n_entries = len(entries)
                 self.to_screen(
-                    "[%s] playlist %s: Collected %d video ids (downloading %d of them)" %
+                    '[%s] playlist %s: Collected %d video ids (downloading %d of them)' %
                     (ie_result['extractor'], playlist, n_all_entries, n_entries))
             elif isinstance(ie_entries, PagedList):
                 if playlistitems:
@@ -796,7 +798,7 @@ class YoutubeDL(object):
                         playliststart, playlistend)
                 n_entries = len(entries)
                 self.to_screen(
-                    "[%s] playlist %s: Downloading %d videos" %
+                    '[%s] playlist %s: Downloading %d videos' %
                     (ie_result['extractor'], playlist, n_entries))
             else:  # iterable
                 if playlistitems:
@@ -807,7 +809,7 @@ class YoutubeDL(object):
                         ie_entries, playliststart, playlistend))
                 n_entries = len(entries)
                 self.to_screen(
-                    "[%s] playlist %s: Downloading %d videos" %
+                    '[%s] playlist %s: Downloading %d videos' %
                     (ie_result['extractor'], playlist, n_entries))
 
             if self.params.get('playlistreverse', False):
@@ -1232,6 +1234,10 @@ class YoutubeDL(object):
                 if t.get('id') is None:
                     t['id'] = '%d' % i
 
+        if self.params.get('list_thumbnails'):
+            self.list_thumbnails(info_dict)
+            return
+
         if thumbnails and 'thumbnail' not in info_dict:
             info_dict['thumbnail'] = thumbnails[-1]['url']
 
@@ -1288,6 +1294,9 @@ 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] = []
@@ -1330,15 +1339,11 @@ class YoutubeDL(object):
         if self.params.get('listformats'):
             self.list_formats(info_dict)
             return
-        if self.params.get('list_thumbnails'):
-            self.list_thumbnails(info_dict)
-            return
 
         req_format = self.params.get('format')
         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():
@@ -1629,12 +1634,14 @@ class YoutubeDL(object):
                 self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
                 return
 
-            if success:
+            if success and filename != '-':
                 # Fixup content
                 fixup_policy = self.params.get('fixup')
                 if fixup_policy is None:
                     fixup_policy = 'detect_or_warn'
 
+                INSTALL_FFMPEG_MESSAGE = 'Install ffmpeg or avconv to fix this automatically.'
+
                 stretched_ratio = info_dict.get('stretched_ratio')
                 if stretched_ratio is not None and stretched_ratio != 1:
                     if fixup_policy == 'warn':
@@ -1647,15 +1654,18 @@ class YoutubeDL(object):
                             info_dict['__postprocessors'].append(stretched_pp)
                         else:
                             self.report_warning(
-                                '%s: Non-uniform pixel ratio (%s). Install ffmpeg or avconv to fix this automatically.' % (
+                                '%s: Non-uniform pixel ratio (%s). %s'
-                                    info_dict['id'], stretched_ratio))
+                                % (info_dict['id'], stretched_ratio, INSTALL_FFMPEG_MESSAGE))
                     else:
                         assert fixup_policy in ('ignore', 'never')
 
-                if info_dict.get('requested_formats') is None and info_dict.get('container') == 'm4a_dash':
+                if (info_dict.get('requested_formats') is None and
+                        info_dict.get('container') == 'm4a_dash'):
                     if fixup_policy == 'warn':
-                        self.report_warning('%s: writing DASH m4a. Only some players support this container.' % (
+                        self.report_warning(
-                            info_dict['id']))
+                            '%s: writing DASH m4a. '
+                            'Only some players support this container.'
+                            % info_dict['id'])
                     elif fixup_policy == 'detect_or_warn':
                         fixup_pp = FFmpegFixupM4aPP(self)
                         if fixup_pp.available:
@@ -1663,8 +1673,27 @@ class YoutubeDL(object):
                             info_dict['__postprocessors'].append(fixup_pp)
                         else:
                             self.report_warning(
-                                '%s: writing DASH m4a. Only some players support this container. Install ffmpeg or avconv to fix this automatically.' % (
+                                '%s: writing DASH m4a. '
+                                'Only some players support this container. %s'
+                                % (info_dict['id'], INSTALL_FFMPEG_MESSAGE))
+                    else:
+                        assert fixup_policy in ('ignore', 'never')
+
+                if (info_dict.get('protocol') == 'm3u8_native' or
+                        info_dict.get('protocol') == 'm3u8' and
+                        self.params.get('hls_prefer_native')):
+                    if fixup_policy == 'warn':
+                        self.report_warning('%s: malformated aac bitstream.' % (
                             info_dict['id']))
+                    elif fixup_policy == 'detect_or_warn':
+                        fixup_pp = FFmpegFixupM3u8PP(self)
+                        if fixup_pp.available:
+                            info_dict.setdefault('__postprocessors', [])
+                            info_dict['__postprocessors'].append(fixup_pp)
+                        else:
+                            self.report_warning(
+                                '%s: malformated aac bitstream. %s'
+                                % (info_dict['id'], INSTALL_FFMPEG_MESSAGE))
                     else:
                         assert fixup_policy in ('ignore', 'never')
 
@@ -1795,7 +1824,7 @@ 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
@@ -1828,7 +1857,9 @@ class YoutubeDL(object):
         if fdict.get('vbr') is not None:
             res += '%4dk' % fdict['vbr']
         if fdict.get('fps') is not None:
-            res += ', %sfps' % fdict['fps']
+            if res:
+                res += ', '
+            res += '%sfps' % fdict['fps']
         if fdict.get('acodec') is not None:
             if res:
                 res += ', '
@@ -1871,12 +1902,7 @@ class YoutubeDL(object):
     def list_thumbnails(self, info_dict):
         thumbnails = info_dict.get('thumbnails')
         if not thumbnails:
-            tn_url = info_dict.get('thumbnail')
+            self.to_screen('[info] No thumbnails present for %s' % info_dict['id'])
-            if tn_url:
-                thumbnails = [{'id': '0', 'url': tn_url}]
-            else:
-                self.to_screen(
-                    '[info] No thumbnails present for %s' % info_dict['id'])
             return
 
         self.to_screen(

youtube_dl/__init__.py

@@ -355,6 +355,7 @@ def _real_main(argv=None):
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
         'encoding': opts.encoding,
         'extract_flat': opts.extract_flat,
+        'mark_watched': opts.mark_watched,
         'merge_output_format': opts.merge_output_format,
         'postprocessors': postprocessors,
         'fixup': opts.fixup,

youtube_dl/__main__.py

@@ -7,7 +7,7 @@ from __future__ import unicode_literals
 
 import sys
 
-if __package__ is None and not hasattr(sys, "frozen"):
+if __package__ is None and not hasattr(sys, 'frozen'):
     # direct call of __main__.py
     import os.path
     path = os.path.realpath(os.path.abspath(__file__))

youtube_dl/aes.py

@@ -161,7 +161,7 @@ def aes_decrypt_text(data, password, key_size_bytes):
     nonce = data[:NONCE_LENGTH_BYTES]
     cipher = data[NONCE_LENGTH_BYTES:]
 
-    class Counter:
+    class Counter(object):
         __value = nonce + [0] * (BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES)
 
         def next_value(self):

youtube_dl/compat.py

@@ -181,20 +181,20 @@ except ImportError:  # Python < 3.4
             # parameter := attribute "=" value
             url = req.get_full_url()
 
-            scheme, data = url.split(":", 1)
+            scheme, data = url.split(':', 1)
-            mediatype, data = data.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"):
+            if mediatype.endswith(';base64'):
                 data = binascii.a2b_base64(data)
                 mediatype = mediatype[:-7]
 
             if not mediatype:
-                mediatype = "text/plain;charset=US-ASCII"
+                mediatype = 'text/plain;charset=US-ASCII'
 
             headers = email.message_from_string(
-                "Content-type: %s\nContent-length: %d\n" % (mediatype, len(data)))
+                'Content-type: %s\nContent-length: %d\n' % (mediatype, len(data)))
 
             return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
 
@@ -268,7 +268,7 @@ except ImportError:  # Python 2
             nv = name_value.split('=', 1)
             if len(nv) != 2:
                 if strict_parsing:
-                    raise ValueError("bad query field: %r" % (name_value,))
+                    raise ValueError('bad query field: %r' % (name_value,))
                 # Handle case of a control-name with no equal sign
                 if keep_blank_values:
                     nv.append('')
@@ -326,6 +326,9 @@ def compat_ord(c):
         return ord(c)
 
 
+compat_os_name = os._name if os.name == 'java' else os.name
+
+
 if sys.version_info >= (3, 0):
     compat_getenv = os.getenv
     compat_expanduser = os.path.expanduser
@@ -346,7 +349,7 @@ else:
     # The following are os.path.expanduser implementations from cpython 2.7.8 stdlib
     # for different platforms with correct environment variables decoding.
 
-    if os.name == 'posix':
+    if compat_os_name == 'posix':
         def compat_expanduser(path):
             """Expand ~ and ~user constructions.  If user or $HOME is unknown,
             do nothing."""
@@ -370,7 +373,7 @@ else:
                 userhome = pwent.pw_dir
             userhome = userhome.rstrip('/')
             return (userhome + path[i:]) or '/'
-    elif os.name == 'nt' or os.name == 'ce':
+    elif compat_os_name == 'nt' or compat_os_name == 'ce':
         def compat_expanduser(path):
             """Expand ~ and ~user constructs.
 
@@ -466,7 +469,7 @@ if sys.version_info < (2, 7):
         if err is not None:
             raise err
         else:
-            raise socket.error("getaddrinfo returns an empty list")
+            raise socket.error('getaddrinfo returns an empty list')
 else:
     compat_socket_create_connection = socket.create_connection
 
@@ -556,6 +559,7 @@ __all__ = [
     'compat_itertools_count',
     'compat_kwargs',
     'compat_ord',
+    'compat_os_name',
     'compat_parse_qs',
     'compat_print',
     'compat_shlex_split',

youtube_dl/downloader/__init__.py

@@ -1,14 +1,16 @@
 from __future__ import unicode_literals
 
 from .common import FileDownloader
-from .external import get_external_downloader
 from .f4m import F4mFD
 from .hls import HlsFD
-from .hls import NativeHlsFD
 from .http import HttpFD
-from .rtsp import RtspFD
 from .rtmp import RtmpFD
 from .dash import DashSegmentsFD
+from .rtsp import RtspFD
+from .external import (
+    get_external_downloader,
+    FFmpegFD,
+)
 
 from ..utils import (
     determine_protocol,
@@ -16,8 +18,8 @@ from ..utils import (
 
 PROTOCOL_MAP = {
     'rtmp': RtmpFD,
-    'm3u8_native': NativeHlsFD,
+    'm3u8_native': HlsFD,
-    'm3u8': HlsFD,
+    'm3u8': FFmpegFD,
     'mms': RtspFD,
     'rtsp': RtspFD,
     'f4m': F4mFD,
@@ -30,14 +32,17 @@ def get_suitable_downloader(info_dict, params={}):
     protocol = determine_protocol(info_dict)
     info_dict['protocol'] = protocol
 
+    # if (info_dict.get('start_time') or info_dict.get('end_time')) and not info_dict.get('requested_formats') and FFmpegFD.can_download(info_dict):
+    #     return FFmpegFD
+
     external_downloader = params.get('external_downloader')
     if external_downloader is not None:
         ed = get_external_downloader(external_downloader)
-        if ed.supports(info_dict):
+        if ed.can_download(info_dict):
             return ed
 
     if protocol == 'm3u8' and params.get('hls_prefer_native'):
-        return NativeHlsFD
+        return HlsFD
 
     return PROTOCOL_MAP.get(protocol, HttpFD)
 

youtube_dl/downloader/common.py

@@ -5,6 +5,7 @@ import re
 import sys
 import time
 
+from ..compat import compat_os_name
 from ..utils import (
     encodeFilename,
     error_to_compat_str,
@@ -157,7 +158,7 @@ class FileDownloader(object):
 
     def slow_down(self, start_time, now, byte_counter):
         """Sleep if the download speed is over the rate limit."""
-        rate_limit = self.params.get('ratelimit', None)
+        rate_limit = self.params.get('ratelimit')
         if rate_limit is None or byte_counter == 0:
             return
         if now is None:
@@ -219,7 +220,7 @@ class FileDownloader(object):
         if self.params.get('progress_with_newline', False):
             self.to_screen(fullmsg)
         else:
-            if os.name == 'nt':
+            if compat_os_name == 'nt':
                 prev_len = getattr(self, '_report_progress_prev_line_length',
                                    0)
                 if prev_len > len(fullmsg):

youtube_dl/downloader/dash.py

@@ -1,67 +1,59 @@
 from __future__ import unicode_literals
 
+import os
 import re
 
-from .common import FileDownloader
+from .fragment import FragmentFD
-from ..utils import sanitized_Request
+from ..utils import (
+    sanitize_open,
+    encodeFilename,
+)
 
 
-class DashSegmentsFD(FileDownloader):
+class DashSegmentsFD(FragmentFD):
     """
     Download segments in a DASH manifest
     """
+
+    FD_NAME = 'dashsegments'
+
     def real_download(self, filename, info_dict):
-        self.report_destination(filename)
-        tmpfilename = self.temp_name(filename)
         base_url = info_dict['url']
-        segment_urls = info_dict['segment_urls']
+        segment_urls = [info_dict['segment_urls'][0]] if self.params.get('test', False) else info_dict['segment_urls']
+        initialization_url = info_dict.get('initialization_url')
 
-        is_test = self.params.get('test', False)
+        ctx = {
-        remaining_bytes = self._TEST_FILE_SIZE if is_test else None
+            'filename': filename,
-        byte_counter = 0
+            'total_frags': len(segment_urls) + (1 if initialization_url else 0),
+        }
 
-        def append_url_to_file(outf, target_url, target_name, remaining_bytes=None):
+        self._prepare_and_start_frag_download(ctx)
-            self.to_screen('[DashSegments] %s: Downloading %s' % (info_dict['id'], target_name))
-            req = sanitized_Request(target_url)
-            if remaining_bytes is not None:
-                req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
-
-            data = self.ydl.urlopen(req).read()
-
-            if remaining_bytes is not None:
-                data = data[:remaining_bytes]
-
-            outf.write(data)
-            return len(data)
 
         def combine_url(base_url, target_url):
             if re.match(r'^https?://', target_url):
                 return target_url
             return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', target_url)
 
-        with open(tmpfilename, 'wb') as outf:
+        segments_filenames = []
-            if info_dict.get('initialization_url'):
+
-                append_url_to_file(
+        def append_url_to_file(target_url, target_filename):
-                    outf, combine_url(base_url, info_dict['initialization_url']),
+            success = ctx['dl'].download(target_filename, {'url': combine_url(base_url, target_url)})
-                    'initialization segment')
+            if not success:
+                return False
+            down, target_sanitized = sanitize_open(target_filename, 'rb')
+            ctx['dest_stream'].write(down.read())
+            down.close()
+            segments_filenames.append(target_sanitized)
+
+        if initialization_url:
+            append_url_to_file(initialization_url, ctx['tmpfilename'] + '-Init')
         for i, segment_url in enumerate(segment_urls):
-                segment_len = append_url_to_file(
+            segment_filename = '%s-Seg%d' % (ctx['tmpfilename'], i)
-                    outf, combine_url(base_url, segment_url),
+            append_url_to_file(segment_url, segment_filename)
-                    'segment %d / %d' % (i + 1, len(segment_urls)),
-                    remaining_bytes)
-                byte_counter += segment_len
-                if remaining_bytes is not None:
-                    remaining_bytes -= segment_len
-                    if remaining_bytes <= 0:
-                        break
 
-        self.try_rename(tmpfilename, filename)
+        self._finish_frag_download(ctx)
 
-        self._hook_progress({
+        for segment_file in segments_filenames:
-            'downloaded_bytes': byte_counter,
+            os.remove(encodeFilename(segment_file))
-            'total_bytes': byte_counter,
-            'filename': filename,
-            'status': 'finished',
-        })
 
         return True

youtube_dl/downloader/external.py

@@ -2,8 +2,11 @@ from __future__ import unicode_literals
 
 import os.path
 import subprocess
+import sys
+import re
 
 from .common import FileDownloader
+from ..postprocessor.ffmpeg import FFmpegPostProcessor, EXT_TO_OUT_FORMATS
 from ..utils import (
     cli_option,
     cli_valueless_option,
@@ -11,6 +14,8 @@ from ..utils import (
     cli_configuration_args,
     encodeFilename,
     encodeArgument,
+    handle_youtubedl_headers,
+    check_executable,
 )
 
 
@@ -45,10 +50,18 @@ class ExternalFD(FileDownloader):
     def exe(self):
         return self.params.get('external_downloader')
 
+    @classmethod
+    def available(cls):
+        return check_executable(cls.get_basename(), [cls.AVAILABLE_OPT])
+
     @classmethod
     def supports(cls, info_dict):
         return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps')
 
+    @classmethod
+    def can_download(cls, info_dict):
+        return cls.available() and cls.supports(info_dict)
+
     def _option(self, command_option, param):
         return cli_option(self.params, command_option, param)
 
@@ -76,6 +89,8 @@ class ExternalFD(FileDownloader):
 
 
 class CurlFD(ExternalFD):
+    AVAILABLE_OPT = '-V'
+
     def _make_cmd(self, tmpfilename, info_dict):
         cmd = [self.exe, '--location', '-o', tmpfilename]
         for key, val in info_dict['http_headers'].items():
@@ -89,6 +104,8 @@ class CurlFD(ExternalFD):
 
 
 class AxelFD(ExternalFD):
+    AVAILABLE_OPT = '-V'
+
     def _make_cmd(self, tmpfilename, info_dict):
         cmd = [self.exe, '-o', tmpfilename]
         for key, val in info_dict['http_headers'].items():
@@ -99,6 +116,8 @@ class AxelFD(ExternalFD):
 
 
 class WgetFD(ExternalFD):
+    AVAILABLE_OPT = '--version'
+
     def _make_cmd(self, tmpfilename, info_dict):
         cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
         for key, val in info_dict['http_headers'].items():
@@ -112,6 +131,8 @@ class WgetFD(ExternalFD):
 
 
 class Aria2cFD(ExternalFD):
+    AVAILABLE_OPT = '-v'
+
     def _make_cmd(self, tmpfilename, info_dict):
         cmd = [self.exe, '-c']
         cmd += self._configuration_args([
@@ -130,12 +151,85 @@ class Aria2cFD(ExternalFD):
 
 
 class HttpieFD(ExternalFD):
+    @classmethod
+    def available(cls):
+        return check_executable('http', ['--version'])
+
     def _make_cmd(self, tmpfilename, info_dict):
         cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
         for key, val in info_dict['http_headers'].items():
             cmd += ['%s:%s' % (key, val)]
         return cmd
 
+
+class FFmpegFD(ExternalFD):
+    @classmethod
+    def supports(cls, info_dict):
+        return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps', 'm3u8', 'rtsp', 'rtmp', 'mms')
+
+    @classmethod
+    def available(cls):
+        return FFmpegPostProcessor().available
+
+    def _call_downloader(self, tmpfilename, info_dict):
+        url = info_dict['url']
+        ffpp = FFmpegPostProcessor(downloader=self)
+        if not ffpp.available:
+            self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
+            return False
+        ffpp.check_version()
+
+        args = [ffpp.executable, '-y']
+
+        args += self._configuration_args()
+
+        # start_time = info_dict.get('start_time') or 0
+        # if start_time:
+        #     args += ['-ss', compat_str(start_time)]
+        # end_time = info_dict.get('end_time')
+        # if end_time:
+        #     args += ['-t', compat_str(end_time - start_time)]
+
+        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 headers.items())]
+
+        args += ['-i', url, '-c', 'copy']
+        if info_dict.get('protocol') == 'm3u8':
+            if self.params.get('hls_use_mpegts', False):
+                args += ['-f', 'mpegts']
+            else:
+                args += ['-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
+        else:
+            args += ['-f', EXT_TO_OUT_FORMATS.get(info_dict['ext'], info_dict['ext'])]
+
+        args = [encodeArgument(opt) for opt in args]
+        args.append(encodeFilename(ffpp._ffmpeg_filename_argument(tmpfilename), True))
+
+        self._debug_cmd(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
+        return retval
+
+
+class AVconvFD(FFmpegFD):
+    pass
+
 _BY_NAME = dict(
     (klass.get_basename(), klass)
     for name, klass in globals().items()

youtube_dl/downloader/fragment.py

@@ -38,7 +38,7 @@ class FragmentFD(FileDownloader):
                 'continuedl': True,
                 'quiet': True,
                 'noprogress': True,
-                'ratelimit': self.params.get('ratelimit', None),
+                'ratelimit': self.params.get('ratelimit'),
                 'retries': self.params.get('retries', 0),
                 'test': self.params.get('test', False),
             }
@@ -99,7 +99,8 @@ class FragmentFD(FileDownloader):
                     state['eta'] = self.calc_eta(
                         start, time_now, estimated_size,
                         state['downloaded_bytes'])
-                state['speed'] = s.get('speed')
+                state['speed'] = s.get('speed') or ctx.get('speed')
+                ctx['speed'] = state['speed']
                 ctx['prev_frag_downloaded_bytes'] = frag_downloaded_bytes
             self._hook_progress(state)
 

youtube_dl/downloader/hls.py

@@ -1,87 +1,19 @@
 from __future__ import unicode_literals
 
-import os
+import os.path
 import re
-import subprocess
-import sys
 
-from .common import FileDownloader
 from .fragment import FragmentFD
 
 from ..compat import compat_urlparse
-from ..postprocessor.ffmpeg import FFmpegPostProcessor
 from ..utils import (
-    encodeArgument,
     encodeFilename,
     sanitize_open,
-    handle_youtubedl_headers,
 )
 
 
-class HlsFD(FileDownloader):
+class HlsFD(FragmentFD):
-    def real_download(self, filename, info_dict):
+    """ A limited implementation that does not require ffmpeg """
-        url = info_dict['url']
-        self.report_destination(filename)
-        tmpfilename = self.temp_name(filename)
-
-        ffpp = FFmpegPostProcessor(downloader=self)
-        if not ffpp.available:
-            self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
-            return False
-        ffpp.check_version()
-
-        args = [ffpp.executable, '-y']
-
-        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 headers.items())]
-
-        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)
-
-        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))
-            self.try_rename(tmpfilename, filename)
-            self._hook_progress({
-                'downloaded_bytes': fsize,
-                'total_bytes': fsize,
-                'filename': filename,
-                'status': 'finished',
-            })
-            return True
-        else:
-            self.to_stderr('\n')
-            self.report_error('%s exited with code %d' % (ffpp.basename, retval))
-            return False
-
-
-class NativeHlsFD(FragmentFD):
-    """ A more limited implementation that does not require ffmpeg """
 
     FD_NAME = 'hlsnative'
 

youtube_dl/downloader/http.py

@@ -140,8 +140,8 @@ class HttpFD(FileDownloader):
 
         if data_len is not None:
             data_len = int(data_len) + resume_len
-            min_data_len = self.params.get("min_filesize", None)
+            min_data_len = self.params.get('min_filesize')
-            max_data_len = self.params.get("max_filesize", None)
+            max_data_len = self.params.get('max_filesize')
             if min_data_len is not None and data_len < min_data_len:
                 self.to_screen('\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
                 return False

youtube_dl/downloader/rtmp.py

@@ -94,15 +94,15 @@ class RtmpFD(FileDownloader):
             return proc.returncode
 
         url = info_dict['url']
-        player_url = info_dict.get('player_url', None)
+        player_url = info_dict.get('player_url')
-        page_url = info_dict.get('page_url', None)
+        page_url = info_dict.get('page_url')
-        app = info_dict.get('app', None)
+        app = info_dict.get('app')
-        play_path = info_dict.get('play_path', None)
+        play_path = info_dict.get('play_path')
-        tc_url = info_dict.get('tc_url', None)
+        tc_url = info_dict.get('tc_url')
-        flash_version = info_dict.get('flash_version', None)
+        flash_version = info_dict.get('flash_version')
         live = info_dict.get('rtmp_live', False)
-        conn = info_dict.get('rtmp_conn', None)
+        conn = info_dict.get('rtmp_conn')
-        protocol = info_dict.get('rtmp_protocol', None)
+        protocol = info_dict.get('rtmp_protocol')
         real_time = info_dict.get('rtmp_real_time', False)
         no_resume = info_dict.get('no_resume', False)
         continue_dl = self.params.get('continuedl', True)

youtube_dl/extractor/__init__.py

@@ -20,9 +20,13 @@ from .aftonbladet import AftonbladetIE
 from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
+from .animeondemand import AnimeOnDemandIE
 from .anitube import AnitubeIE
 from .anysex import AnySexIE
-from .aol import AolIE
+from .aol import (
+    AolIE,
+    AolFeaturesIE,
+)
 from .allocine import AllocineIE
 from .aparat import AparatIE
 from .appleconnect import AppleConnectIE
@@ -44,11 +48,13 @@ from .arte import (
     ArteTVFutureIE,
     ArteTVCinemaIE,
     ArteTVDDCIE,
+    ArteTVMagazineIE,
     ArteTVEmbedIE,
 )
 from .atresplayer import AtresPlayerIE
 from .atttechchannel import ATTTechChannelIE
 from .audimedia import AudiMediaIE
+from .audioboom import AudioBoomIE
 from .audiomack import AudiomackIE, AudiomackAlbumIE
 from .azubu import AzubuIE, AzubuLiveIE
 from .baidu import BaiduVideoIE
@@ -72,6 +78,7 @@ from .bleacherreport import (
 )
 from .blinkx import BlinkxIE
 from .bloomberg import BloombergIE
+from .bokecc import BokeCCIE
 from .bpb import BpbIE
 from .br import BRIE
 from .breakcom import BreakIE
@@ -89,6 +96,10 @@ from .camdemy import (
 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,
@@ -126,6 +137,7 @@ 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 (
@@ -177,6 +189,10 @@ from .dumpert import DumpertIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .dropbox import DropboxIE
+from .dw import (
+    DWIE,
+    DWArticleIE,
+)
 from .eagleplatform import EaglePlatformIE
 from .ebaumsworld import EbaumsWorldIE
 from .echomsk import EchoMskIE
@@ -201,10 +217,7 @@ from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
 from .expotv import ExpoTVIE
 from .extremetube import ExtremeTubeIE
-from .facebook import (
+from .facebook import FacebookIE
-    FacebookIE,
-    FacebookPostIE,
-)
 from .faz import FazIE
 from .fc2 import FC2IE
 from .fczenit import FczenitIE
@@ -332,6 +345,7 @@ from .konserthusetplay import KonserthusetPlayIE
 from .kontrtube import KontrTubeIE
 from .krasview import KrasViewIE
 from .ku6 import Ku6IE
+from .kusi import KUSIIE
 from .kuwo import (
     KuwoIE,
     KuwoAlbumIE,
@@ -344,10 +358,9 @@ from .la7 import LA7IE
 from .laola1tv import Laola1TvIE
 from .lecture2go import Lecture2GoIE
 from .lemonde import LemondeIE
-from .letv import (
+from .leeco import (
-    LetvIE,
+    LeIE,
-    LetvTvIE,
+    LePlaylistIE,
-    LetvPlaylistIE,
     LetvCloudIE,
 )
 from .libsyn import LibsynIE
@@ -376,6 +389,7 @@ from .lynda import (
 from .m6 import M6IE
 from .macgamestore import MacGameStoreIE
 from .mailru import MailRuIE
+from .makerschannel import MakersChannelIE
 from .makertv import MakerTVIE
 from .malemotion import MalemotionIE
 from .matchtv import MatchTVIE
@@ -385,6 +399,7 @@ from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
 from .minhateca import MinhatecaIE
 from .ministrygrid import MinistryGridIE
+from .minoto import MinotoIE
 from .miomio import MioMioIE
 from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mitele import MiTeleIE
@@ -484,6 +499,7 @@ from .nowtv import (
     NowTVIE,
     NowTVListIE,
 )
+from .noz import NozIE
 from .npo import (
     NPOIE,
     NPOLiveIE,
@@ -497,6 +513,7 @@ from .npr import NprIE
 from .nrk import (
     NRKIE,
     NRKPlaylistIE,
+    NRKSkoleIE,
     NRKTVIE,
 )
 from .ntvde import NTVDeIE
@@ -533,6 +550,7 @@ 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
@@ -546,6 +564,7 @@ from .pornhd import PornHdIE
 from .pornhub import (
     PornHubIE,
     PornHubPlaylistIE,
+    PornHubUserVideosIE,
 )
 from .pornotube import PornotubeIE
 from .pornovoisines import PornoVoisinesIE
@@ -613,6 +632,7 @@ from .sbs import SBSIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .screencastomatic import ScreencastOMaticIE
+from .screenjunkies import ScreenJunkiesIE
 from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
 from .senateisvp import SenateISVPIE
 from .servingsys import ServingSysIE
@@ -658,7 +678,6 @@ from .southpark import (
     SouthParkEsIE,
     SouthParkNlIE
 )
-from .space import SpaceIE
 from .spankbang import SpankBangIE
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE, SpiegelArticleIE
@@ -726,6 +745,7 @@ from .tmz import (
     TMZArticleIE,
 )
 from .tnaflix import (
+    TNAFlixNetworkEmbedIE,
     TNAFlixIE,
     EMPFlixIE,
     MovieFapIE,
@@ -787,7 +807,11 @@ from .twitch import (
     TwitchBookmarksIE,
     TwitchStreamIE,
 )
-from .twitter import TwitterCardIE, TwitterIE
+from .twitter import (
+    TwitterCardIE,
+    TwitterIE,
+    TwitterAmplifyIE,
+)
 from .ubu import UbuIE
 from .udemy import (
     UdemyIE,
@@ -797,7 +821,9 @@ from .udn import UDNEmbedIE
 from .digiteka import DigitekaIE
 from .unistra import UnistraIE
 from .urort import UrortIE
+from .usatoday import USATodayIE
 from .ustream import UstreamIE, UstreamChannelIE
+from .ustudio import UstudioIE
 from .varzesh3 import Varzesh3IE
 from .vbox7 import Vbox7IE
 from .veehd import VeeHDIE
@@ -811,7 +837,10 @@ from .vgtv import (
     VGTVIE,
 )
 from .vh1 import VH1IE
-from .vice import ViceIE
+from .vice import (
+    ViceIE,
+    ViceShowIE,
+)
 from .viddler import ViddlerIE
 from .videodetective import VideoDetectiveIE
 from .videofyme import VideofyMeIE
@@ -838,6 +867,7 @@ from .vimeo import (
     VimeoChannelIE,
     VimeoGroupsIE,
     VimeoLikesIE,
+    VimeoOndemandIE,
     VimeoReviewIE,
     VimeoUserIE,
     VimeoWatchLaterIE,

youtube_dl/extractor/aenetworks.py

@@ -28,7 +28,7 @@ class AENetworksIE(InfoExtractor):
         'info_dict': {
             'id': 'eg47EERs_JsZ',
             'ext': 'mp4',
-            'title': "Winter Is Coming",
+            'title': 'Winter Is Coming',
             'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
         },
         'params': {

youtube_dl/extractor/animeondemand.py

@@ -0,0 +1,160 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+from ..utils import (
+    determine_ext,
+    encode_dict,
+    ExtractorError,
+    sanitized_Request,
+    urlencode_postdata,
+)
+
+
+class AnimeOnDemandIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?anime-on-demand\.de/anime/(?P<id>\d+)'
+    _LOGIN_URL = 'https://www.anime-on-demand.de/users/sign_in'
+    _APPLY_HTML5_URL = 'https://www.anime-on-demand.de/html5apply'
+    _NETRC_MACHINE = 'animeondemand'
+    _TEST = {
+        'url': 'https://www.anime-on-demand.de/anime/161',
+        'info_dict': {
+            'id': '161',
+            'title': 'Grimgar, Ashes and Illusions (OmU)',
+            'description': 'md5:6681ce3c07c7189d255ac6ab23812d31',
+        },
+        'playlist_mincount': 4,
+    }
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_page = self._download_webpage(
+            self._LOGIN_URL, None, 'Downloading login page')
+
+        login_form = self._form_hidden_inputs('new_user', login_page)
+
+        login_form.update({
+            'user[login]': username,
+            'user[password]': password,
+        })
+
+        post_url = self._search_regex(
+            r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
+            'post url', default=self._LOGIN_URL, group='url')
+
+        if not post_url.startswith('http'):
+            post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
+
+        request = sanitized_Request(
+            post_url, urlencode_postdata(encode_dict(login_form)))
+        request.add_header('Referer', self._LOGIN_URL)
+
+        response = self._download_webpage(
+            request, None, 'Logging in as %s' % username)
+
+        if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')):
+            error = self._search_regex(
+                r'<p class="alert alert-danger">(.+?)</p>',
+                response, 'error', default=None)
+            if error:
+                raise ExtractorError('Unable to login: %s' % error, expected=True)
+            raise ExtractorError('Unable to log in')
+
+    def _real_initialize(self):
+        self._login()
+
+    def _real_extract(self, url):
+        anime_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, anime_id)
+
+        if 'data-playlist=' not in webpage:
+            self._download_webpage(
+                self._APPLY_HTML5_URL, anime_id,
+                'Activating HTML5 beta', 'Unable to apply HTML5 beta')
+            webpage = self._download_webpage(url, anime_id)
+
+        csrf_token = self._html_search_meta(
+            'csrf-token', webpage, 'csrf token', fatal=True)
+
+        anime_title = self._html_search_regex(
+            r'(?s)<h1[^>]+itemprop="name"[^>]*>(.+?)</h1>',
+            webpage, 'anime name')
+        anime_description = self._html_search_regex(
+            r'(?s)<div[^>]+itemprop="description"[^>]*>(.+?)</div>',
+            webpage, 'anime description', default=None)
+
+        entries = []
+
+        for episode_html in re.findall(r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', webpage):
+            m = re.search(
+                r'class="episodebox-title"[^>]+title="Episode (?P<number>\d+) - (?P<title>.+?)"', episode_html)
+            if not m:
+                continue
+
+            episode_number = int(m.group('number'))
+            episode_title = m.group('title')
+            video_id = 'episode-%d' % episode_number
+
+            common_info = {
+                'id': video_id,
+                'series': anime_title,
+                'episode': episode_title,
+                'episode_number': episode_number,
+            }
+
+            formats = []
+
+            playlist_url = self._search_regex(
+                r'data-playlist=(["\'])(?P<url>.+?)\1',
+                episode_html, 'data playlist', default=None, group='url')
+            if playlist_url:
+                request = sanitized_Request(
+                    compat_urlparse.urljoin(url, playlist_url),
+                    headers={
+                        'X-Requested-With': 'XMLHttpRequest',
+                        'X-CSRF-Token': csrf_token,
+                        'Referer': url,
+                        'Accept': 'application/json, text/javascript, */*; q=0.01',
+                    })
+
+                playlist = self._download_json(
+                    request, video_id, 'Downloading playlist JSON', fatal=False)
+                if playlist:
+                    playlist = playlist['playlist'][0]
+                    title = playlist['title']
+                    description = playlist.get('description')
+                    for source in playlist.get('sources', []):
+                        file_ = source.get('file')
+                        if file_ and determine_ext(file_) == 'm3u8':
+                            formats = self._extract_m3u8_formats(
+                                file_, video_id, 'mp4',
+                                entry_protocol='m3u8_native', m3u8_id='hls')
+
+            if formats:
+                f = common_info.copy()
+                f.update({
+                    'title': title,
+                    'description': description,
+                    'formats': formats,
+                })
+                entries.append(f)
+
+            m = re.search(
+                r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>Teaser<',
+                episode_html)
+            if m:
+                f = common_info.copy()
+                f.update({
+                    'id': '%s-teaser' % f['id'],
+                    'title': m.group('title'),
+                    'url': compat_urlparse.urljoin(url, m.group('href')),
+                })
+                entries.append(f)
+
+        return self.playlist_result(entries, anime_id, anime_title, anime_description)

youtube_dl/extractor/aol.py

@@ -1,24 +1,11 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
 class AolIE(InfoExtractor):
     IE_NAME = 'on.aol.com'
-    _VALID_URL = r'''(?x)
+    _VALID_URL = r'(?:aol-video:|http://on\.aol\.com/video/.*-)(?P<id>[0-9]+)(?:$|\?)'
-        (?:
-            aol-video:|
-            http://on\.aol\.com/
-            (?:
-                video/.*-|
-                playlist/(?P<playlist_display_id>[^/?#]+?)-(?P<playlist_id>[0-9]+)[?#].*_videoid=
-            )
-        )
-        (?P<id>[0-9]+)
-        (?:$|\?)
-    '''
 
     _TESTS = [{
         'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
@@ -29,42 +16,31 @@ class AolIE(InfoExtractor):
             'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
         },
         'add_ie': ['FiveMin'],
-    }, {
-        'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316',
-        'info_dict': {
-            'id': '152147',
-            'title': 'Brace Yourself - Today\'s Weirdest News',
-        },
-        'playlist_mincount': 10,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = mobj.group('id')
-        playlist_id = mobj.group('playlist_id')
-        if not playlist_id or self._downloader.params.get('noplaylist'):
         return self.url_result('5min:%s' % video_id)
 
-        self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
 
-        webpage = self._download_webpage(url, playlist_id)
+class AolFeaturesIE(InfoExtractor):
-        title = self._html_search_regex(
+    IE_NAME = 'features.aol.com'
-            r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title')
+    _VALID_URL = r'http://features\.aol\.com/video/(?P<id>[^/?#]+)'
-        playlist_html = self._search_regex(
-            r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage,
-            'playlist HTML')
-        entries = [{
-            '_type': 'url',
-            'url': 'aol-video:%s' % m.group('id'),
-            'ie_key': 'Aol',
-        } for m in re.finditer(
-            r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>",
-            playlist_html)]
 
-        return {
+    _TESTS = [{
-            '_type': 'playlist',
+        'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts',
-            'id': playlist_id,
+        'md5': '7db483bb0c09c85e241f84a34238cc75',
-            'display_id': mobj.group('playlist_display_id'),
+        'info_dict': {
-            'title': title,
+            'id': '519507715',
-            'entries': entries,
+            'ext': 'mp4',
-        }
+            'title': 'What To Watch - February 17, 2016',
+        },
+        'add_ie': ['FiveMin'],
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        return self.url_result(self._search_regex(
+            r'<script type="text/javascript" src="(https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js[^"]+)"',
+            webpage, '5min embed url'), 'FiveMin')

youtube_dl/extractor/appletrailers.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class AppleTrailersIE(InfoExtractor):
     IE_NAME = 'appletrailers'
-    _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.|movie)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)'
     _TESTS = [{
         'url': 'http://trailers.apple.com/trailers/wb/manofsteel/',
         'info_dict': {
@@ -73,6 +73,9 @@ class AppleTrailersIE(InfoExtractor):
     }, {
         'url': 'http://trailers.apple.com/ca/metropole/autrui/',
         'only_matching': True,
+    }, {
+        'url': 'http://movietrailers.apple.com/trailers/focus_features/kuboandthetwostrings/',
+        'only_matching': True,
     }]
 
     _JSON_RE = r'iTunes.playURL\((.*?)\);'

youtube_dl/extractor/arte.py

@@ -23,7 +23,7 @@ from ..utils import (
 
 
 class ArteTvIE(InfoExtractor):
-    _VALID_URL = r'http://videos\.arte\.tv/(?P<lang>fr|de)/.*-(?P<id>.*?)\.html'
+    _VALID_URL = r'http://videos\.arte\.tv/(?P<lang>fr|de|en|es)/.*-(?P<id>.*?)\.html'
     IE_NAME = 'arte.tv'
 
     def _real_extract(self, url):
@@ -63,7 +63,7 @@ class ArteTvIE(InfoExtractor):
 
 class ArteTVPlus7IE(InfoExtractor):
     IE_NAME = 'arte.tv:+7'
-    _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
+    _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&+])'
 
     @classmethod
     def _extract_url_info(cls, url):
@@ -102,23 +102,45 @@ class ArteTVPlus7IE(InfoExtractor):
             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')
+                    r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None)
+                if embed_url:
                     player = self._download_json(
                         embed_url, video_id, 'Downloading player page')
                     iframe_url = find_iframe_url(player['html'])
+            # en and es URLs produce react-based pages with different layout (e.g.
+            # http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world)
+            if not iframe_url:
+                program = self._search_regex(
+                    r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n',
+                    webpage, 'program', default=None)
+                if program:
+                    embed_html = self._parse_json(program, video_id)
+                    if embed_html:
+                        iframe_url = find_iframe_url(embed_html['embed_html'])
+            if iframe_url:
                 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)
+        if json_url:
+            title = self._search_regex(
+                r'<h3[^>]+title=(["\'])(?P<title>.+?)\1',
+                webpage, 'title', default=None, group='title')
+            return self._extract_from_json_url(json_url, video_id, lang, title=title)
+        # Different kind of embed URL (e.g.
+        # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium)
+        embed_url = self._search_regex(
+            r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1',
+            webpage, 'embed url', group='url')
+        return self.url_result(embed_url)
 
-    def _extract_from_json_url(self, json_url, video_id, lang):
+    def _extract_from_json_url(self, json_url, video_id, lang, title=None):
         info = self._download_json(json_url, video_id)
         player_info = info['videoJsonPlayer']
 
         upload_date_str = player_info.get('shootingDate')
         if not upload_date_str:
-            upload_date_str = player_info.get('VDA', '').split(' ')[0]
+            upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0]
 
-        title = player_info['VTI'].strip()
+        title = (player_info.get('VTI') or title or player_info['VID']).strip()
         subtitle = player_info.get('VSU', '').strip()
         if subtitle:
             title += ' - %s' % subtitle
@@ -132,27 +154,30 @@ class ArteTVPlus7IE(InfoExtractor):
         }
         qfunc = qualities(['HQ', 'MQ', 'EQ', 'SQ'])
 
+        LANGS = {
+            'fr': 'F',
+            'de': 'A',
+            'en': 'E[ANG]',
+            'es': 'E[ESP]',
+        }
+
         formats = []
         for format_id, format_dict in player_info['VSR'].items():
             f = dict(format_dict)
             versionCode = f.get('versionCode')
-
+            langcode = LANGS.get(lang, lang)
-            langcode = {
+            lang_rexs = [r'VO?%s-' % re.escape(langcode), r'VO?.-ST%s$' % re.escape(langcode)]
-                'fr': 'F',
+            lang_pref = None
-                'de': 'A',
+            if versionCode:
-            }.get(lang, lang)
+                matched_lang_rexs = [r for r in lang_rexs if re.match(r, versionCode)]
-            lang_rexs = [r'VO?%s' % langcode, r'VO?.-ST%s' % langcode]
+                lang_pref = -10 if not matched_lang_rexs else 10 * len(matched_lang_rexs)
-            lang_pref = (
-                None if versionCode is None else (
-                    10 if any(re.match(r, versionCode) for r in lang_rexs)
-                    else -10))
             source_pref = 0
             if versionCode is not None:
                 # The original version with subtitles has lower relevance
-                if re.match(r'VO-ST(F|A)', versionCode):
+                if re.match(r'VO-ST(F|A|E)', versionCode):
                     source_pref -= 10
                 # The version with sourds/mal subtitles has also lower relevance
-                elif re.match(r'VO?(F|A)-STM\1', versionCode):
+                elif re.match(r'VO?(F|A|E)-STM\1', versionCode):
                     source_pref -= 9
             format = {
                 'format_id': format_id,
@@ -185,7 +210,7 @@ class ArteTVPlus7IE(InfoExtractor):
 # It also uses the arte_vp_url url from the webpage to extract the information
 class ArteTVCreativeIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:creative'
-    _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/(?:magazine?/)?(?P<id>[^?#]+)'
+    _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de|en|es)/(?:magazine?/)?(?P<id>[^/?#&]+)'
 
     _TESTS = [{
         'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design',
@@ -209,7 +234,7 @@ class ArteTVCreativeIE(ArteTVPlus7IE):
 
 class ArteTVFutureIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:future'
-    _VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de)/(?P<id>.+)'
+    _VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
 
     _TESTS = [{
         'url': 'http://future.arte.tv/fr/info-sciences/les-ecrevisses-aussi-sont-anxieuses',
@@ -217,6 +242,7 @@ class ArteTVFutureIE(ArteTVPlus7IE):
             'id': '050940-028-A',
             'ext': 'mp4',
             'title': 'Les écrevisses aussi peuvent être anxieuses',
+            'upload_date': '20140902',
         },
     }, {
         'url': 'http://future.arte.tv/fr/la-science-est-elle-responsable',
@@ -226,7 +252,7 @@ class ArteTVFutureIE(ArteTVPlus7IE):
 
 class ArteTVDDCIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:ddc'
-    _VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)'
+    _VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>[^/?#&]+)'
 
     def _real_extract(self, url):
         video_id, lang = self._extract_url_info(url)
@@ -244,7 +270,7 @@ class ArteTVDDCIE(ArteTVPlus7IE):
 
 class ArteTVConcertIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:concert'
-    _VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>de|fr)/(?P<id>.+)'
+    _VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
 
     _TEST = {
         'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde',
@@ -261,7 +287,7 @@ class ArteTVConcertIE(ArteTVPlus7IE):
 
 class ArteTVCinemaIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:cinema'
-    _VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>de|fr)/(?P<id>.+)'
+    _VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>.+)'
 
     _TEST = {
         'url': 'http://cinema.arte.tv/de/node/38291',
@@ -276,6 +302,37 @@ class ArteTVCinemaIE(ArteTVPlus7IE):
     }
 
 
+class ArteTVMagazineIE(ArteTVPlus7IE):
+    IE_NAME = 'arte.tv:magazine'
+    _VALID_URL = r'https?://(?:www\.)?arte\.tv/magazine/[^/]+/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
+
+    _TESTS = [{
+        # Embedded via <iframe src="http://www.arte.tv/arte_vp/index.php?json_url=..."
+        'url': 'http://www.arte.tv/magazine/trepalium/fr/entretien-avec-le-realisateur-vincent-lannoo-trepalium',
+        'md5': '2a9369bcccf847d1c741e51416299f25',
+        'info_dict': {
+            'id': '065965-000-A',
+            'ext': 'mp4',
+            'title': 'Trepalium - Extrait Ep.01',
+            'upload_date': '20160121',
+        },
+    }, {
+        # Embedded via <iframe src="http://www.arte.tv/guide/fr/embed/054813-004-A/medium"
+        'url': 'http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium',
+        'md5': 'fedc64fc7a946110fe311634e79782ca',
+        'info_dict': {
+            'id': '054813-004_PLUS7-F',
+            'ext': 'mp4',
+            'title': 'Trepalium (4/6)',
+            'description': 'md5:10057003c34d54e95350be4f9b05cb40',
+            'upload_date': '20160218',
+        },
+    }, {
+        'url': 'http://www.arte.tv/magazine/metropolis/de/frank-woeste-german-paris-metropolis',
+        'only_matching': True,
+    }]
+
+
 class ArteTVEmbedIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:embed'
     _VALID_URL = r'''(?x)

youtube_dl/extractor/audimedia.py

@@ -10,9 +10,9 @@ from ..utils import (
 
 
 class AudiMediaIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?audimedia\.tv/(?:en|de)/vid/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?audi-mediacenter\.com/(?:en|de)/audimediatv/(?P<id>[^/?#]+)'
     _TEST = {
-        'url': 'https://audimedia.tv/en/vid/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test',
+        'url': 'https://www.audi-mediacenter.com/en/audimediatv/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-1467',
         'md5': '79a8b71c46d49042609795ab59779b66',
         'info_dict': {
             'id': '1565',
@@ -32,7 +32,10 @@ class AudiMediaIE(InfoExtractor):
         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')
+        raw_payload = self._search_regex([
+            r'class="amtv-embed"[^>]+id="([^"]+)"',
+            r'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)
@@ -59,13 +62,19 @@ class AudiMediaIE(InfoExtractor):
                 video_version_url = video_version.get('download_url') or video_version.get('stream_url')
                 if not video_version_url:
                     continue
-                formats.append({
+                f = {
                     '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')),
+                }
+                bitrate = self._search_regex(r'(\d+)k', video_version_url, 'bitrate', default=None)
+                if bitrate:
+                    f.update({
+                        'format_id': 'http-%s' % bitrate,
                     })
+                formats.append(f)
             self._sort_formats(formats)
 
             return {

youtube_dl/extractor/audioboom.py

@@ -0,0 +1,66 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import float_or_none
+
+
+class AudioBoomIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?audioboom\.com/boos/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0',
+        'md5': '63a8d73a055c6ed0f1e51921a10a5a76',
+        'info_dict': {
+            'id': '4279833',
+            'ext': 'mp3',
+            'title': '3/09/2016 Czaban Hour 3',
+            'description': 'Guest:   Nate Davis - NFL free agency,   Guest:   Stan Gans',
+            'duration': 2245.72,
+            'uploader': 'Steve Czaban',
+            'uploader_url': 're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        clip = None
+
+        clip_store = self._parse_json(
+            self._search_regex(
+                r'data-new-clip-store=(["\'])(?P<json>{.*?"clipId"\s*:\s*%s.*?})\1' % video_id,
+                webpage, 'clip store', default='{}', group='json'),
+            video_id, fatal=False)
+        if clip_store:
+            clips = clip_store.get('clips')
+            if clips and isinstance(clips, list) and isinstance(clips[0], dict):
+                clip = clips[0]
+
+        def from_clip(field):
+            if clip:
+                clip.get(field)
+
+        audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property(
+            'audio', webpage, 'audio url')
+        title = from_clip('title') or self._og_search_title(webpage)
+        description = from_clip('description') or self._og_search_description(webpage)
+
+        duration = float_or_none(from_clip('duration') or self._html_search_meta(
+            'weibo:audio:duration', webpage))
+
+        uploader = from_clip('author') or self._og_search_property(
+            'audio:artist', webpage, 'uploader', fatal=False)
+        uploader_url = from_clip('author_url') or self._html_search_meta(
+            'audioboo:channel', webpage, 'uploader url')
+
+        return {
+            'id': video_id,
+            'url': audio_url,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'uploader': uploader,
+            'uploader_url': uploader_url,
+        }

youtube_dl/extractor/bbc.py

@@ -10,7 +10,6 @@ from ..utils import (
     int_or_none,
     parse_duration,
     parse_iso8601,
-    remove_end,
     unescapeHTML,
 )
 from ..compat import (
@@ -86,7 +85,7 @@ class BBCCoUkIE(InfoExtractor):
                 'id': 'b00yng1d',
                 'ext': 'flv',
                 'title': 'The Voice UK: Series 3: Blind Auditions 5',
-                'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.",
+                'description': 'Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.',
                 'duration': 5100,
             },
             'params': {
@@ -561,7 +560,7 @@ class BBCIE(BBCCoUkIE):
         'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
         'info_dict': {
             'id': '3662a707-0af9-3149-963f-47bea720b460',
-            'title': 'BBC Blogs - Adam Curtis - BUGGER',
+            'title': 'BUGGER',
         },
         'playlist_count': 18,
     }, {
@@ -670,9 +669,17 @@ class BBCIE(BBCCoUkIE):
         'url': 'http://www.bbc.com/sport/0/football/34475836',
         'info_dict': {
             'id': '34475836',
-            'title': 'What Liverpool can expect from Klopp',
+            'title': 'Jurgen Klopp: Furious football from a witty and winning coach',
         },
         'playlist_count': 3,
+    }, {
+        # school report article with single video
+        'url': 'http://www.bbc.co.uk/schoolreport/35744779',
+        'info_dict': {
+            'id': '35744779',
+            'title': 'School which breaks down barriers in Jerusalem',
+        },
+        'playlist_count': 1,
     }, {
         # single video with playlist URL from weather section
         'url': 'http://www.bbc.com/weather/features/33601775',
@@ -735,8 +742,17 @@ class BBCIE(BBCCoUkIE):
 
         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')
+        if not playlist_title:
+            playlist_title = self._og_search_title(
+                webpage, default=None) or self._html_search_regex(
+                r'<title>(.+?)</title>', webpage, 'playlist title', default=None)
+            if playlist_title:
+                playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip()
+
+        playlist_description = json_ld_info.get(
+            'description') or self._og_search_description(webpage, default=None)
 
         if not timestamp:
             timestamp = parse_iso8601(self._search_regex(
@@ -797,8 +813,6 @@ class BBCIE(BBCCoUkIE):
                                 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)
@@ -829,10 +843,6 @@ class BBCIE(BBCCoUkIE):
                 'subtitles': subtitles,
             }
 
-        playlist_title = self._html_search_regex(
-            r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title')
-        playlist_description = self._og_search_description(webpage, default=None)
-
         def extract_all(pattern):
             return list(filter(None, map(
                 lambda s: self._parse_json(s, playlist_id, fatal=False),

youtube_dl/extractor/bleacherreport.py

@@ -28,10 +28,10 @@ class BleacherReportIE(InfoExtractor):
         'add_ie': ['Ooyala'],
     }, {
         'url': 'http://bleacherreport.com/articles/2586817-aussie-golfers-get-fright-of-their-lives-after-being-chased-by-angry-kangaroo',
-        'md5': 'af5f90dc9c7ba1c19d0a3eac806bbf50',
+        'md5': '6a5cd403418c7b01719248ca97fb0692',
         'info_dict': {
             'id': '2586817',
-            'ext': 'mp4',
+            'ext': 'webm',
             'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo',
             'timestamp': 1446839961,
             'uploader': 'Sean Fay',
@@ -93,10 +93,14 @@ class BleacherReportCMSIE(AMPIE):
         'md5': '8c2c12e3af7805152675446c905d159b',
         'info_dict': {
             'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Cena vs. Rollins Would Expose the Heavyweight Division',
             'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e',
         },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/bokecc.py

@@ -0,0 +1,60 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_parse_qs
+from ..utils import ExtractorError
+
+
+class BokeCCBaseIE(InfoExtractor):
+    def _extract_bokecc_formats(self, webpage, video_id, format_id=None):
+        player_params_str = self._html_search_regex(
+            r'<(?:script|embed)[^>]+src="http://p\.bokecc\.com/player\?([^"]+)',
+            webpage, 'player params')
+
+        player_params = compat_parse_qs(player_params_str)
+
+        info_xml = self._download_xml(
+            'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % (
+                player_params['siteid'][0], player_params['vid'][0]), video_id)
+
+        formats = [{
+            'format_id': format_id,
+            'url': quality.find('./copy').attrib['playurl'],
+            'preference': int(quality.attrib['value']),
+        } for quality in info_xml.findall('./video/quality')]
+
+        self._sort_formats(formats)
+
+        return formats
+
+
+class BokeCCIE(BokeCCBaseIE):
+    _IE_DESC = 'CC视频'
+    _VALID_URL = r'http://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
+
+    _TESTS = [{
+        'url': 'http://union.bokecc.com/playvideo.bo?vid=E44D40C15E65EA30&uid=CD0C5D3C8614B28B',
+        'info_dict': {
+            'id': 'CD0C5D3C8614B28B_E44D40C15E65EA30',
+            'ext': 'flv',
+            'title': 'BokeCC Video',
+        },
+    }]
+
+    def _real_extract(self, url):
+        qs = compat_parse_qs(re.match(self._VALID_URL, url).group('query'))
+        if not qs.get('vid') or not qs.get('uid'):
+            raise ExtractorError('Invalid URL', expected=True)
+
+        video_id = '%s_%s' % (qs['uid'][0], qs['vid'][0])
+
+        webpage = self._download_webpage(url, video_id)
+
+        return {
+            'id': video_id,
+            'title': 'BokeCC Video',  # no title provided in the webpage
+            'formats': self._extract_bokecc_formats(webpage, video_id),
+        }

youtube_dl/extractor/c56.py

@@ -4,12 +4,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import js_to_json
 
 
 class C56IE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
     IE_NAME = '56.com'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
         'md5': 'e59995ac63d0457783ea05f93f12a866',
         'info_dict': {
@@ -18,12 +19,29 @@ class C56IE(InfoExtractor):
             'title': '网事知多少 第32期：车怒',
             'duration': 283.813,
         },
-    }
+    }, {
+        'url': 'http://www.56.com/u47/v_MTM5NjQ5ODc2.html',
+        'md5': '',
+        'info_dict': {
+            'id': '82247482',
+            'title': '爱的诅咒之杜鹃花开',
+        },
+        'playlist_count': 7,
+        'add_ie': ['Sohu'],
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
         text_id = mobj.group('textid')
 
+        webpage = self._download_webpage(url, text_id)
+        sohu_video_info_str = self._search_regex(
+            r'var\s+sohuVideoInfo\s*=\s*({[^}]+});', webpage, 'Sohu video info', default=None)
+        if sohu_video_info_str:
+            sohu_video_info = self._parse_json(
+                sohu_video_info_str, text_id, transform_source=js_to_json)
+            return self.url_result(sohu_video_info['url'], 'Sohu')
+
         page = self._download_json(
             'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')
 

youtube_dl/extractor/canvas.py

@@ -6,7 +6,7 @@ from ..utils import float_or_none
 
 class CanvasIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?canvas\.be/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',
         'md5': 'ea838375a547ac787d4064d8c7860a6c',
         'info_dict': {
@@ -18,7 +18,27 @@ class CanvasIE(InfoExtractor):
             'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 49.02,
         }
+    }, {
+        # with subtitles
+        'url': 'http://www.canvas.be/video/panorama/2016/pieter-0167',
+        'info_dict': {
+            'id': 'mz-ast-5240ff21-2d30-4101-bba6-92b5ec67c625',
+            'display_id': 'pieter-0167',
+            'ext': 'mp4',
+            'title': 'Pieter 0167',
+            'description': 'md5:943cd30f48a5d29ba02c3a104dc4ec4e',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 2553.08,
+            'subtitles': {
+                'nl': [{
+                    'ext': 'vtt',
+                }],
+            },
+        },
+        'params': {
+            'skip_download': True,
         }
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -54,6 +74,14 @@ class CanvasIE(InfoExtractor):
                 })
         self._sort_formats(formats)
 
+        subtitles = {}
+        subtitle_urls = data.get('subtitleUrls')
+        if isinstance(subtitle_urls, list):
+            for subtitle in subtitle_urls:
+                subtitle_url = subtitle.get('url')
+                if subtitle_url and subtitle.get('type') == 'CLOSED':
+                    subtitles.setdefault('nl', []).append({'url': subtitle_url})
+
         return {
             'id': video_id,
             'display_id': display_id,
@@ -62,4 +90,5 @@ class CanvasIE(InfoExtractor):
             'formats': formats,
             'duration': float_or_none(data.get('duration'), 1000),
             'thumbnail': data.get('posterImageUrl'),
+            'subtitles': subtitles,
         }

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/cbsnews.py

@@ -3,7 +3,10 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from .theplatform import ThePlatformIE
-from ..utils import parse_duration
+from ..utils import (
+    parse_duration,
+    find_xpath_attr,
+)
 
 
 class CBSNewsIE(ThePlatformIE):
@@ -46,6 +49,15 @@ class CBSNewsIE(ThePlatformIE):
         },
     ]
 
+    def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
+        closed_caption_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', 'ClosedCaptionURL')
+        return {
+            'en': [{
+                'ext': 'ttml',
+                'url': closed_caption_e.attrib['value'],
+            }]
+        } if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
@@ -61,12 +73,6 @@ class CBSNewsIE(ThePlatformIE):
         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']:
             pid = item.get('media' + format_id)

youtube_dl/extractor/ccc.py

@@ -45,7 +45,7 @@ class CCCIE(InfoExtractor):
         title = self._html_search_regex(
             r'(?s)<h1>(.*?)</h1>', webpage, 'title')
         description = self._html_search_regex(
-            r"(?s)<h3>About</h3>(.+?)<h3>",
+            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>",

youtube_dl/extractor/ceskatelevize.py

@@ -177,16 +177,16 @@ class CeskaTelevizeIE(InfoExtractor):
             for divider in [1000, 60, 60, 100]:
                 components.append(msec % divider)
                 msec //= divider
-            return "{3:02}:{2:02}:{1:02},{0:03}".format(*components)
+            return '{3:02}:{2:02}:{1:02},{0:03}'.format(*components)
 
         def _fix_subtitle(subtitle):
             for line in subtitle.splitlines():
-                m = re.match(r"^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$", line)
+                m = re.match(r'^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$', line)
                 if m:
                     yield m.group(1)
                     start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:])
-                    yield "{0} --> {1}".format(start, stop)
+                    yield '{0} --> {1}'.format(start, stop)
                 else:
                     yield line
 
-        return "\r\n".join(_fix_subtitle(subtitles))
+        return '\r\n'.join(_fix_subtitle(subtitles))

youtube_dl/extractor/cinemassacre.py

@@ -21,6 +21,10 @@ class CinemassacreIE(InfoExtractor):
                 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
                 'description': 'md5:fb87405fcb42a331742a0dce2708560b',
             },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
         },
         {
             'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
@@ -31,14 +35,18 @@ class CinemassacreIE(InfoExtractor):
                 'upload_date': '20131002',
                 'title': 'The Mummy’s Hand (1940)',
             },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
         },
         {
             # Youtube embedded video
             'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/',
-            'md5': 'df4cf8a1dcedaec79a73d96d83b99023',
+            'md5': 'ec9838a5520ef5409b3e4e42fcb0a3b9',
             'info_dict': {
                 'id': 'OEVzPCY2T-g',
-                'ext': 'mp4',
+                'ext': 'webm',
                 'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles',
                 'upload_date': '20061207',
                 'uploader': 'Cinemassacre',
@@ -49,12 +57,12 @@ class CinemassacreIE(InfoExtractor):
         {
             # Youtube embedded video
             'url': 'http://cinemassacre.com/2006/09/01/mckids/',
-            'md5': '6eb30961fa795fedc750eac4881ad2e1',
+            'md5': '7393c4e0f54602ad110c793eb7a6513a',
             'info_dict': {
                 'id': 'FnxsNhuikpo',
-                'ext': 'mp4',
+                'ext': 'webm',
                 'upload_date': '20060901',
-                'uploader': 'Cinemassacre Extras',
+                'uploader': 'Cinemassacre Extra',
                 'description': 'md5:de9b751efa9e45fbaafd9c8a1123ed53',
                 'uploader_id': 'Cinemassacre',
                 'title': 'AVGN: McKids',
@@ -69,7 +77,11 @@ class CinemassacreIE(InfoExtractor):
                 'description': 'Let’s Play Mario Kart 64 !! Mario Kart 64 is a classic go-kart racing game released for the Nintendo 64 (N64). Today James & Mike do 4 player Battle Mode with Kyle and Bootsy!',
                 'title': 'Mario Kart 64 (Nintendo 64) James & Mike Mondays',
                 'upload_date': '20150525',
-            }
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
         }
     ]
 

youtube_dl/extractor/cnet.py

@@ -51,9 +51,7 @@ class CNETIE(ThePlatformIE):
             uploader = None
             uploader_id = None
 
-        mpx_account = data['config']['uvpConfig']['default']['mpx_account']
+        metadata = self.get_metadata('kYEXFC/%s' % list(vdata['files'].values())[0], video_id)
-
-        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')
 
@@ -62,7 +60,7 @@ class CNETIE(ThePlatformIE):
         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)
+            release_url = 'http://link.theplatform.com/s/kYEXFC/%s?format=SMIL&mbr=true' % 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)

youtube_dl/extractor/cnn.py

@@ -26,14 +26,14 @@ class CNNIE(InfoExtractor):
             'upload_date': '20130609',
         },
     }, {
-        "url": "http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29",
+        'url': 'http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29',
-        "md5": "b5cc60c60a3477d185af8f19a2a26f4e",
+        'md5': 'b5cc60c60a3477d185af8f19a2a26f4e',
-        "info_dict": {
+        'info_dict': {
             'id': 'us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology',
             'ext': 'mp4',
-            "title": "Student's epic speech stuns new freshmen",
+            'title': "Student's epic speech stuns new freshmen",
-            "description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
+            'description': "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
-            "upload_date": "20130821",
+            'upload_date': '20130821',
         }
     }, {
         'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html',

youtube_dl/extractor/collegerama.py

@@ -46,9 +46,9 @@ class CollegeRamaIE(InfoExtractor):
         video_id = self._match_id(url)
 
         player_options_request = {
-            "getPlayerOptionsRequest": {
+            'getPlayerOptionsRequest': {
-                "ResourceId": video_id,
+                'ResourceId': video_id,
-                "QueryString": "",
+                'QueryString': '',
             }
         }
 

youtube_dl/extractor/comcarcoff.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
     parse_duration,
@@ -14,14 +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',
@@ -39,15 +39,14 @@ class ComCarCoffIE(InfoExtractor):
                 r'window\.app\s*=\s*({.+?});\n', webpage, 'full data json'),
             display_id)['videoData']
 
-        video_id = full_data['activeVideo']['video']
+        display_id = full_data['activeVideo']['video']
-        video_data = full_data.get('videos', {}).get(video_id) or full_data['singleshots'][video_id]
+        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'))
@@ -55,6 +54,8 @@ class ComCarCoffIE(InfoExtractor):
             video_data.get('duration'))
 
         return {
+            '_type': 'url_transparent',
+            'url': 'crackle:%s' % video_id,
             'id': video_id,
             'display_id': display_id,
             'title': video_data['title'],
@@ -62,6 +63,7 @@ class ComCarCoffIE(InfoExtractor):
             '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/comedycentral.py

@@ -16,11 +16,11 @@ from ..utils import (
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
-        (video-clips|episodes|cc-studios|video-collections|full-episodes)
+        (video-clips|episodes|cc-studios|video-collections|full-episodes|shows)
         /(?P<title>.*)'''
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
         'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
         'info_dict': {
@@ -29,7 +29,10 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
             'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
             'description': 'After a certain point, breastfeeding becomes c**kblocking.',
         },
-    }
+    }, {
+        'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview',
+        'only_matching': True,
+    }]
 
 
 class ComedyCentralShowsIE(MTVServicesInfoExtractor):
@@ -192,7 +195,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
             if len(altMovieParams) == 0:
                 raise ExtractorError('unable to find Flash URL in webpage ' + url)
             else:
-                mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
+                mMovieParams = [('http://media.mtvnservices.com/' + altMovieParams[0], altMovieParams[0])]
 
         uri = mMovieParams[0][1]
         # Correct cc.com in uri

youtube_dl/extractor/common.py

@@ -15,13 +15,14 @@ import math
 from ..compat import (
     compat_cookiejar,
     compat_cookies,
+    compat_etree_fromstring,
     compat_getpass,
     compat_http_client,
+    compat_os_name,
+    compat_str,
     compat_urllib_error,
     compat_urllib_parse,
     compat_urlparse,
-    compat_str,
-    compat_etree_fromstring,
 )
 from ..utils import (
     NO_DEFAULT,
@@ -46,6 +47,8 @@ from ..utils import (
     xpath_with_ns,
     determine_protocol,
     parse_duration,
+    mimetype2ext,
+    update_url_query,
 )
 
 
@@ -103,7 +106,7 @@ class InfoExtractor(object):
                     * protocol   The protocol that will be used for the actual
                                  download, lower-case.
                                  "http", "https", "rtsp", "rtmp", "rtmpe",
-                                 "m3u8", or "m3u8_native".
+                                 "m3u8", "m3u8_native" or "http_dash_segments".
                     * preference Order number of this format. If this field is
                                  present and not None, the formats get sorted
                                  by this field, regardless of all other values.
@@ -156,12 +159,14 @@ class InfoExtractor(object):
     thumbnail:      Full URL to a video thumbnail image.
     description:    Full video description.
     uploader:       Full name of the video uploader.
+    license:        License name the video is licensed under.
     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).
                     If not explicitly set, calculated from timestamp.
     uploader_id:    Nickname or id of the video uploader.
+    uploader_url:   Full URL to a personal webpage of the video uploader.
     location:       Physical location where the video was filmed.
     subtitles:      The available subtitles as a dictionary in the format
                     {language: subformats}. "subformats" is a list sorted from
@@ -341,7 +346,7 @@ class InfoExtractor(object):
     def IE_NAME(self):
         return compat_str(type(self).__name__[:-2])
 
-    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
+    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers=None, query=None):
         """ Returns the response handle """
         if note is None:
             self.report_download_webpage(video_id)
@@ -350,6 +355,12 @@ class InfoExtractor(object):
                 self.to_screen('%s' % (note,))
             else:
                 self.to_screen('%s: %s' % (video_id, note))
+        # data, headers and query params will be ignored for `Request` objects
+        if isinstance(url_or_request, compat_str):
+            if query:
+                url_or_request = update_url_query(url_or_request, query)
+            if data or headers:
+                url_or_request = sanitized_Request(url_or_request, data, headers or {})
         try:
             return self._downloader.urlopen(url_or_request)
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
@@ -365,13 +376,13 @@ class InfoExtractor(object):
                 self._downloader.report_warning(errmsg)
                 return False
 
-    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None):
+    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers=None, query=None):
         """ Returns a tuple (page content as string, URL handle) """
         # Strip hashes from the URL (#1038)
         if isinstance(url_or_request, (compat_str, str)):
             url_or_request = url_or_request.partition('#')[0]
 
-        urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal)
+        urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query)
         if urlh is False:
             assert not fatal
             return False
@@ -424,7 +435,7 @@ class InfoExtractor(object):
             self.to_screen('Saving request to ' + filename)
             # Working around MAX_PATH limitation on Windows (see
             # http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx)
-            if os.name == 'nt':
+            if compat_os_name == 'nt':
                 absfilepath = os.path.abspath(filename)
                 if len(absfilepath) > 259:
                     filename = '\\\\?\\' + absfilepath
@@ -458,13 +469,13 @@ class InfoExtractor(object):
 
         return content
 
-    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
+    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None, data=None, headers=None, query=None):
         """ Returns the data of the page as a string """
         success = False
         try_count = 0
         while success is False:
             try:
-                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding)
+                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding, data=data, headers=headers, query=query)
                 success = True
             except compat_http_client.IncompleteRead as e:
                 try_count += 1
@@ -479,10 +490,10 @@ class InfoExtractor(object):
 
     def _download_xml(self, url_or_request, video_id,
                       note='Downloading XML', errnote='Unable to download XML',
-                      transform_source=None, fatal=True, encoding=None):
+                      transform_source=None, fatal=True, encoding=None, data=None, headers=None, query=None):
         """Return the xml as an xml.etree.ElementTree.Element"""
         xml_string = self._download_webpage(
-            url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding)
+            url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding, data=data, headers=headers, query=query)
         if xml_string is False:
             return xml_string
         if transform_source:
@@ -493,10 +504,10 @@ class InfoExtractor(object):
                        note='Downloading JSON metadata',
                        errnote='Unable to download JSON metadata',
                        transform_source=None,
-                       fatal=True, encoding=None):
+                       fatal=True, encoding=None, data=None, headers=None, query=None):
         json_string = self._download_webpage(
             url_or_request, video_id, note, errnote, fatal=fatal,
-            encoding=encoding)
+            encoding=encoding, data=data, headers=headers, query=query)
         if (not fatal) and json_string is False:
             return None
         return self._parse_json(
@@ -593,7 +604,7 @@ class InfoExtractor(object):
                 if mobj:
                     break
 
-        if not self._downloader.params.get('no_color') and os.name != 'nt' and sys.stderr.isatty():
+        if not self._downloader.params.get('no_color') and compat_os_name != 'nt' and sys.stderr.isatty():
             _name = '\033[0;34m%s\033[0m' % name
         else:
             _name = name
@@ -636,7 +647,7 @@ class InfoExtractor(object):
         downloader_params = self._downloader.params
 
         # Attempt to use provided username and password or .netrc data
-        if downloader_params.get('username', None) is not None:
+        if downloader_params.get('username') is not None:
             username = downloader_params['username']
             password = downloader_params['password']
         elif downloader_params.get('usenetrc', False):
@@ -663,7 +674,7 @@ class InfoExtractor(object):
             return None
         downloader_params = self._downloader.params
 
-        if downloader_params.get('twofactor', None) is not None:
+        if downloader_params.get('twofactor') is not None:
             return downloader_params['twofactor']
 
         return compat_getpass('Type %s and press [Return]: ' % note)
@@ -744,7 +755,7 @@ class InfoExtractor(object):
             'mature': 17,
             'restricted': 19,
         }
-        return RATING_TABLE.get(rating.lower(), None)
+        return RATING_TABLE.get(rating.lower())
 
     def _family_friendly_search(self, html):
         # See http://schema.org/VideoObject
@@ -759,7 +770,7 @@ class InfoExtractor(object):
             '0': 18,
             'false': 18,
         }
-        return RATING_TABLE.get(family_friendly.lower(), None)
+        return RATING_TABLE.get(family_friendly.lower())
 
     def _twitter_search_player(self, html):
         return self._html_search_meta('twitter:player', html,
@@ -899,6 +910,16 @@ class InfoExtractor(object):
                     item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'),
                 formats)
 
+    @staticmethod
+    def _remove_duplicate_formats(formats):
+        format_urls = set()
+        unique_formats = []
+        for f in formats:
+            if f['url'] not in format_urls:
+                format_urls.add(f['url'])
+                unique_formats.append(f)
+        formats[:] = unique_formats
+
     def _is_valid_url(self, url, video_id, item='video'):
         url = self._proto_relative_url(url, scheme='http:')
         # For now assume non HTTP(S) URLs always valid
@@ -952,6 +973,13 @@ class InfoExtractor(object):
         if manifest is False:
             return []
 
+        return self._parse_f4m_formats(
+            manifest, manifest_url, video_id, preference=preference, f4m_id=f4m_id,
+            transform_source=transform_source, fatal=fatal)
+
+    def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, f4m_id=None,
+                           transform_source=lambda s: fix_xml_ampersands(s).strip(),
+                           fatal=True):
         formats = []
         manifest_version = '1.0'
         media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
@@ -977,7 +1005,8 @@ class InfoExtractor(object):
                 # bitrate in f4m downloader
                 if determine_ext(manifest_url) == 'f4m':
                     formats.extend(self._extract_f4m_formats(
-                        manifest_url, video_id, preference, f4m_id, fatal=fatal))
+                        manifest_url, video_id, preference=preference, f4m_id=f4m_id,
+                        transform_source=transform_source, fatal=fatal))
                     continue
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             formats.append({
@@ -1022,11 +1051,21 @@ class InfoExtractor(object):
             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
+        # We should try extracting formats only from master playlists [1], i.e.
-        # The EXT-X-TARGETDURATION tag is REQUIRED for every M3U8 Media Playlists
+        # playlists that describe available qualities. On the other hand media
-        # https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.1
+        # playlists [2] should be returned as is since they contain just the media
-        if '#EXT-X-TARGETDURATION' in m3u8_doc:
+        # without qualities renditions.
+        # Fortunately, master playlist can be easily distinguished from media
+        # playlist based on particular tags availability. As of [1, 2] master
+        # playlist tags MUST NOT appear in a media playist and vice versa.
+        # As of [3] #EXT-X-TARGETDURATION tag is REQUIRED for every media playlist
+        # and MUST NOT appear in master playlist thus we can clearly detect media
+        # playlist with this criterion.
+        # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.4
+        # 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3
+        # 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.1
+        if '#EXT-X-TARGETDURATION' in m3u8_doc:  # media playlist, return as is
             return [{
                 'url': m3u8_url,
                 'format_id': m3u8_id,
@@ -1073,19 +1112,29 @@ class InfoExtractor(object):
                     'protocol': entry_protocol,
                     'preference': preference,
                 }
-                codecs = last_info.get('CODECS')
-                if codecs:
-                    # TODO: looks like video codec is not always necessarily goes first
-                    va_codecs = codecs.split(',')
-                    if va_codecs[0]:
-                        f['vcodec'] = va_codecs[0]
-                    if len(va_codecs) > 1 and va_codecs[1]:
-                        f['acodec'] = va_codecs[1]
                 resolution = last_info.get('RESOLUTION')
                 if resolution:
                     width_str, height_str = resolution.split('x')
                     f['width'] = int(width_str)
                     f['height'] = int(height_str)
+                codecs = last_info.get('CODECS')
+                if codecs:
+                    vcodec, acodec = [None] * 2
+                    va_codecs = codecs.split(',')
+                    if len(va_codecs) == 1:
+                        # Audio only entries usually come with single codec and
+                        # no resolution. For more robustness we also check it to
+                        # be mp4 audio.
+                        if not resolution and va_codecs[0].startswith('mp4a'):
+                            vcodec, acodec = 'none', va_codecs[0]
+                        else:
+                            vcodec = va_codecs[0]
+                    else:
+                        vcodec, acodec = va_codecs[:2]
+                    f.update({
+                        'acodec': acodec,
+                        'vcodec': vcodec,
+                    })
                 if last_media is not None:
                     f['m3u8_media'] = last_media
                     last_media = None
@@ -1106,8 +1155,8 @@ class InfoExtractor(object):
                 out.append('{%s}%s' % (namespace, c))
         return '/'.join(out)
 
-    def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None):
+    def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None, transform_source=None):
-        smil = self._download_smil(smil_url, video_id, fatal=fatal)
+        smil = self._download_smil(smil_url, video_id, fatal=fatal, transform_source=transform_source)
 
         if smil is False:
             assert not fatal
@@ -1124,10 +1173,10 @@ class InfoExtractor(object):
             return {}
         return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params)
 
-    def _download_smil(self, smil_url, video_id, fatal=True):
+    def _download_smil(self, smil_url, video_id, fatal=True, transform_source=None):
         return self._download_xml(
             smil_url, video_id, 'Downloading SMIL file',
-            'Unable to download SMIL file', fatal=fatal)
+            'Unable to download SMIL file', fatal=fatal, transform_source=transform_source)
 
     def _parse_smil(self, smil, smil_url, video_id, f4m_params=None):
         namespace = self._parse_smil_namespace(smil)
@@ -1186,12 +1235,13 @@ class InfoExtractor(object):
         http_count = 0
         m3u8_count = 0
 
-        src_urls = []
+        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'))
@@ -1223,9 +1273,7 @@ class InfoExtractor(object):
                 continue
 
             src_url = src if src.startswith('http') else compat_urlparse.urljoin(base, src)
-            if src_url in src_urls:
+            src_url = src_url.strip()
-                continue
-            src_urls.append(src_url)
 
             if proto == 'm3u8' or src_ext == 'm3u8':
                 m3u8_formats = self._extract_m3u8_formats(
@@ -1278,16 +1326,7 @@ class InfoExtractor(object):
             if not src or src in urls:
                 continue
             urls.append(src)
-            ext = textstream.get('ext') or determine_ext(src)
+            ext = textstream.get('ext') or determine_ext(src) or mimetype2ext(textstream.get('type'))
-            if not ext:
-                type_ = textstream.get('type')
-                SUBTITLES_TYPES = {
-                    'text/vtt': 'vtt',
-                    'text/srt': 'srt',
-                    'application/smptett+xml': 'tt',
-                }
-                if type_ in SUBTITLES_TYPES:
-                    ext = SUBTITLES_TYPES[type_]
             lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') or textstream.get('lang') or subtitles_lang
             subtitles.setdefault(lang, []).append({
                 'url': src,
@@ -1423,8 +1462,9 @@ class InfoExtractor(object):
                         continue
                     representation_attrib = adaptation_set.attrib.copy()
                     representation_attrib.update(representation.attrib)
-                    mime_type = representation_attrib.get('mimeType')
+                    # According to page 41 of ISO/IEC 29001-1:2014, @mimeType is mandatory
-                    content_type = mime_type.split('/')[0] if mime_type else representation_attrib.get('contentType')
+                    mime_type = representation_attrib['mimeType']
+                    content_type = mime_type.split('/')[0]
                     if content_type == 'text':
                         # TODO implement WebVTT downloading
                         pass
@@ -1436,15 +1476,18 @@ class InfoExtractor(object):
                                 base_url = base_url_e.text + base_url
                                 if re.match(r'^https?://', base_url):
                                     break
-                        if not re.match(r'^https?://', base_url):
+                        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': mpd_id or representation_id,
+                            'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
                             'url': base_url,
+                            'ext': mimetype2ext(mime_type),
                             '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),
@@ -1496,7 +1539,7 @@ class InfoExtractor(object):
     def _live_title(self, name):
         """ Generate the title for a live video """
         now = datetime.datetime.now()
-        now_str = now.strftime("%Y-%m-%d %H:%M")
+        now_str = now.strftime('%Y-%m-%d %H:%M')
         return name + ' ' + now_str
 
     def _int(self, v, name, fatal=False, **kwargs):
@@ -1569,7 +1612,7 @@ class InfoExtractor(object):
         return {}
 
     def _get_subtitles(self, *args, **kwargs):
-        raise NotImplementedError("This method must be implemented by subclasses")
+        raise NotImplementedError('This method must be implemented by subclasses')
 
     @staticmethod
     def _merge_subtitle_items(subtitle_list1, subtitle_list2):
@@ -1595,7 +1638,16 @@ class InfoExtractor(object):
         return {}
 
     def _get_automatic_captions(self, *args, **kwargs):
-        raise NotImplementedError("This method must be implemented by subclasses")
+        raise NotImplementedError('This method must be implemented by subclasses')
+
+    def mark_watched(self, *args, **kwargs):
+        if (self._downloader.params.get('mark_watched', False) and
+                (self._get_login_info()[0] is not None or
+                    self._downloader.params.get('cookiefile') is not None)):
+            self._mark_watched(*args, **kwargs)
+
+    def _mark_watched(self, *args, **kwargs):
+        raise NotImplementedError('This method must be implemented by subclasses')
 
 
 class SearchInfoExtractor(InfoExtractor):
@@ -1635,7 +1687,7 @@ class SearchInfoExtractor(InfoExtractor):
 
     def _get_n_results(self, query, n):
         """Get a specified number of results for a query"""
-        raise NotImplementedError("This method must be implemented by subclasses")
+        raise NotImplementedError('This method must be implemented by subclasses')
 
     @property
     def SEARCH_KEY(self):

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/crunchyroll.py

@@ -180,40 +180,40 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             return assvalue
 
         output = '[Script Info]\n'
-        output += 'Title: %s\n' % sub_root.attrib["title"]
+        output += 'Title: %s\n' % sub_root.attrib['title']
         output += 'ScriptType: v4.00+\n'
-        output += 'WrapStyle: %s\n' % sub_root.attrib["wrap_style"]
+        output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style']
-        output += 'PlayResX: %s\n' % sub_root.attrib["play_res_x"]
+        output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x']
-        output += 'PlayResY: %s\n' % sub_root.attrib["play_res_y"]
+        output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y']
         output += """ScaledBorderAndShadow: yes
 
 [V4+ Styles]
 Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
 """
         for style in sub_root.findall('./styles/style'):
-            output += 'Style: ' + style.attrib["name"]
+            output += 'Style: ' + style.attrib['name']
-            output += ',' + style.attrib["font_name"]
+            output += ',' + style.attrib['font_name']
-            output += ',' + style.attrib["font_size"]
+            output += ',' + style.attrib['font_size']
-            output += ',' + style.attrib["primary_colour"]
+            output += ',' + style.attrib['primary_colour']
-            output += ',' + style.attrib["secondary_colour"]
+            output += ',' + style.attrib['secondary_colour']
-            output += ',' + style.attrib["outline_colour"]
+            output += ',' + style.attrib['outline_colour']
-            output += ',' + style.attrib["back_colour"]
+            output += ',' + style.attrib['back_colour']
-            output += ',' + ass_bool(style.attrib["bold"])
+            output += ',' + ass_bool(style.attrib['bold'])
-            output += ',' + ass_bool(style.attrib["italic"])
+            output += ',' + ass_bool(style.attrib['italic'])
-            output += ',' + ass_bool(style.attrib["underline"])
+            output += ',' + ass_bool(style.attrib['underline'])
-            output += ',' + ass_bool(style.attrib["strikeout"])
+            output += ',' + ass_bool(style.attrib['strikeout'])
-            output += ',' + style.attrib["scale_x"]
+            output += ',' + style.attrib['scale_x']
-            output += ',' + style.attrib["scale_y"]
+            output += ',' + style.attrib['scale_y']
-            output += ',' + style.attrib["spacing"]
+            output += ',' + style.attrib['spacing']
-            output += ',' + style.attrib["angle"]
+            output += ',' + style.attrib['angle']
-            output += ',' + style.attrib["border_style"]
+            output += ',' + style.attrib['border_style']
-            output += ',' + style.attrib["outline"]
+            output += ',' + style.attrib['outline']
-            output += ',' + style.attrib["shadow"]
+            output += ',' + style.attrib['shadow']
-            output += ',' + style.attrib["alignment"]
+            output += ',' + style.attrib['alignment']
-            output += ',' + style.attrib["margin_l"]
+            output += ',' + style.attrib['margin_l']
-            output += ',' + style.attrib["margin_r"]
+            output += ',' + style.attrib['margin_r']
-            output += ',' + style.attrib["margin_v"]
+            output += ',' + style.attrib['margin_v']
-            output += ',' + style.attrib["encoding"]
+            output += ',' + style.attrib['encoding']
             output += '\n'
 
         output += """
@@ -222,15 +222,15 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 """
         for event in sub_root.findall('./events/event'):
             output += 'Dialogue: 0'
-            output += ',' + event.attrib["start"]
+            output += ',' + event.attrib['start']
-            output += ',' + event.attrib["end"]
+            output += ',' + event.attrib['end']
-            output += ',' + event.attrib["style"]
+            output += ',' + event.attrib['style']
-            output += ',' + event.attrib["name"]
+            output += ',' + event.attrib['name']
-            output += ',' + event.attrib["margin_l"]
+            output += ',' + event.attrib['margin_l']
-            output += ',' + event.attrib["margin_r"]
+            output += ',' + event.attrib['margin_r']
-            output += ',' + event.attrib["margin_v"]
+            output += ',' + event.attrib['margin_v']
-            output += ',' + event.attrib["effect"]
+            output += ',' + event.attrib['effect']
-            output += ',' + event.attrib["text"]
+            output += ',' + event.attrib['text']
             output += '\n'
 
         return output
@@ -376,7 +376,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
 
 class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
-    IE_NAME = "crunchyroll:playlist"
+    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\-]+))/?(?:\?|$)'
 
     _TESTS = [{

youtube_dl/extractor/dailymotion.py

@@ -122,10 +122,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
         description = self._og_search_description(webpage) or self._html_search_meta(
             'description', webpage, 'description')
 
-        view_count = str_to_int(self._search_regex(
+        view_count_str = self._search_regex(
-            [r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:(\d+)"',
+            (r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:([\s\d,.]+)"',
-             r'video_views_count[^>]+>\s+([\d\.,]+)'],
+             r'video_views_count[^>]+>\s+([\s\d\,.]+)'),
-            webpage, 'view count', fatal=False))
+            webpage, 'view count', fatal=False)
+        if view_count_str:
+            view_count_str = re.sub(r'\s', '', view_count_str)
+        view_count = str_to_int(view_count_str)
         comment_count = int_or_none(self._search_regex(
             r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"',
             webpage, 'comment count', fatal=False))
@@ -396,13 +399,13 @@ class DailymotionCloudIE(DailymotionBaseInfoExtractor):
     }]
 
     @classmethod
-    def _extract_dmcloud_url(self, webpage):
+    def _extract_dmcloud_url(cls, webpage):
-        mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % self._VALID_EMBED_URL, webpage)
+        mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL, webpage)
         if mobj:
             return mobj.group(1)
 
         mobj = re.search(
-            r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % self._VALID_EMBED_URL,
+            r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL,
             webpage)
         if mobj:
             return mobj.group(1)

youtube_dl/extractor/douyutv.py

@@ -18,7 +18,7 @@ class DouyuTVIE(InfoExtractor):
             'display_id': 'iseven',
             'ext': 'flv',
             'title': 're:^清晨醒脑！T-ara根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
-            'description': 'md5:c93d6692dde6fe33809a46edcbecca44',
+            'description': 'md5:f34981259a03e980a3c6404190a3ed61',
             'thumbnail': 're:^https?://.*\.jpg$',
             'uploader': '7师傅',
             'uploader_id': '431925',
@@ -26,7 +26,7 @@ class DouyuTVIE(InfoExtractor):
         },
         'params': {
             'skip_download': True,
-        }
+        },
     }, {
         'url': 'http://www.douyutv.com/85982',
         'info_dict': {
@@ -42,7 +42,24 @@ class DouyuTVIE(InfoExtractor):
         },
         'params': {
             'skip_download': True,
-        }
+        },
+        'skip': 'Romm not found',
+    }, {
+        'url': 'http://www.douyutv.com/17732',
+        'info_dict': {
+            'id': '17732',
+            'display_id': '17732',
+            'ext': 'flv',
+            'title': 're:^清晨醒脑！T-ara根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'description': 'md5:f34981259a03e980a3c6404190a3ed61',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': '7师傅',
+            'uploader_id': '431925',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/dplay.py

@@ -1,6 +1,8 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
+import json
+import re
 import time
 
 from .common import InfoExtractor
@@ -8,44 +10,125 @@ from ..utils import int_or_none
 
 
 class DPlayIE(InfoExtractor):
-    _VALID_URL = r'http://www\.dplay\.se/[^/]+/(?P<id>[^/?#]+)'
+    _VALID_URL = r'http://(?P<domain>it\.dplay\.com|www\.dplay\.(?:dk|se|no))/[^/]+/(?P<id>[^/?#]+)'
 
-    _TEST = {
+    _TESTS = [{
+        'url': 'http://it.dplay.com/take-me-out/stagione-1-episodio-25/',
+        'info_dict': {
+            'id': '1255600',
+            'display_id': 'stagione-1-episodio-25',
+            'ext': 'mp4',
+            'title': 'Episodio 25',
+            'description': 'md5:cae5f40ad988811b197d2d27a53227eb',
+            'duration': 2761,
+            'timestamp': 1454701800,
+            'upload_date': '20160205',
+            'creator': 'RTIT',
+            'series': 'Take me out',
+            'season_number': 1,
+            'episode_number': 25,
+            'age_limit': 0,
+        },
+        'expected_warnings': ['Unable to download f4m manifest'],
+    }, {
         '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',
+            'ext': 'flv',
             'title': 'Svensken lär sig njuta av livet',
+            'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8',
             'duration': 2650,
+            'timestamp': 1365454320,
+            'upload_date': '20130408',
+            'creator': 'Kanal 5 (Home)',
+            'series': 'Nugammalt - 77 händelser som format Sverige',
+            'season_number': 1,
+            'episode_number': 1,
+            'age_limit': 0,
         },
-    }
+    }, {
+        'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/',
+        'info_dict': {
+            'id': '70816',
+            'display_id': 'season-6-episode-12',
+            'ext': 'flv',
+            'title': 'Episode 12',
+            'description': 'md5:9c86e51a93f8a4401fc9641ef9894c90',
+            'duration': 2563,
+            'timestamp': 1429696800,
+            'upload_date': '20150422',
+            'creator': 'Kanal 4',
+            'series': 'Mig og min mor',
+            'season_number': 6,
+            'episode_number': 12,
+            'age_limit': 0,
+        },
+    }, {
+        'url': 'http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+        domain = mobj.group('domain')
+
         webpage = self._download_webpage(url, display_id)
+
         video_id = self._search_regex(
-            r'data-video-id="(\d+)"', webpage, 'video id')
+            r'data-video-id=["\'](\d+)', webpage, 'video id')
 
         info = self._download_json(
-            'http://www.dplay.se/api/v2/ajax/videos?video_id=' + video_id,
+            'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id),
             video_id)['data'][0]
 
+        title = info['title']
+
+        PROTOCOLS = ('hls', 'hds')
+        formats = []
+
+        def extract_formats(protocol, manifest_url):
+            if protocol == 'hls':
+                formats.extend(self._extract_m3u8_formats(
+                    manifest_url, video_id, ext='mp4',
+                    entry_protocol='m3u8_native', m3u8_id=protocol, fatal=False))
+            elif protocol == 'hds':
+                formats.extend(self._extract_f4m_formats(
+                    manifest_url + '&hdcore=3.8.0&plugin=flowplayer-3.8.0.0',
+                    video_id, f4m_id=protocol, fatal=False))
+
+        domain_tld = domain.split('.')[-1]
+        if domain_tld in ('se', 'dk'):
+            for protocol in PROTOCOLS:
                 self._set_cookie(
-            'secure.dplay.se', 'dsc-geo',
+                    'secure.dplay.%s' % domain_tld, 'dsc-geo',
-            '{"countryCode":"NL","expiry":%d}' % ((time.time() + 20 * 60) * 1000))
+                    json.dumps({
-        # TODO: consider adding support for 'stream_type=hds', it seems to
+                        'countryCode': domain_tld.upper(),
-        # require setting some cookies
+                        'expiry': (time.time() + 20 * 60) * 1000,
-        manifest_url = self._download_json(
+                    }))
-            'https://secure.dplay.se/secure/api/v2/user/authorization/stream/%s?stream_type=hls' % video_id,
+                stream = self._download_json(
-            video_id, 'Getting manifest url for hls stream')['hls']
+                    'https://secure.dplay.%s/secure/api/v2/user/authorization/stream/%s?stream_type=%s'
-        formats = self._extract_m3u8_formats(
+                    % (domain_tld, video_id, protocol), video_id,
-            manifest_url, video_id, ext='mp4', entry_protocol='m3u8_native')
+                    'Downloading %s stream JSON' % protocol, fatal=False)
+                if stream and stream.get(protocol):
+                    extract_formats(protocol, stream[protocol])
+        else:
+            for protocol in PROTOCOLS:
+                if info.get(protocol):
+                    extract_formats(protocol, info[protocol])
 
         return {
             'id': video_id,
             'display_id': display_id,
-            'title': info['title'],
+            'title': title,
-            'formats': formats,
+            'description': info.get('video_metadata_longDescription'),
             'duration': int_or_none(info.get('video_metadata_length'), scale=1000),
+            'timestamp': int_or_none(info.get('video_publish_date')),
+            'creator': info.get('video_metadata_homeChannel'),
+            'series': info.get('video_metadata_show'),
+            'season_number': int_or_none(info.get('season')),
+            'episode_number': int_or_none(info.get('episode')),
+            'age_limit': int_or_none(info.get('minimum_age')),
+            'formats': formats,
         }

youtube_dl/extractor/drbonanza.py

@@ -87,7 +87,7 @@ class DRBonanzaIE(InfoExtractor):
 
         formats = []
         for file in info['Files']:
-            if info['Type'] == "Video":
+            if info['Type'] == 'Video':
                 if file['Type'] in video_types:
                     format = parse_filename_info(file['Location'])
                     format.update({
@@ -101,10 +101,10 @@ class DRBonanzaIE(InfoExtractor):
                         if '/bonanza/' in rtmp_url:
                             format['play_path'] = rtmp_url.split('/bonanza/')[1]
                     formats.append(format)
-                elif file['Type'] == "Thumb":
+                elif file['Type'] == 'Thumb':
                     thumbnail = file['Location']
-            elif info['Type'] == "Audio":
+            elif info['Type'] == 'Audio':
-                if file['Type'] == "Audio":
+                if file['Type'] == 'Audio':
                     format = parse_filename_info(file['Location'])
                     format.update({
                         'url': file['Location'],
@@ -112,7 +112,7 @@ class DRBonanzaIE(InfoExtractor):
                         'vcodec': 'none',
                     })
                     formats.append(format)
-                elif file['Type'] == "Thumb":
+                elif file['Type'] == 'Thumb':
                     thumbnail = file['Location']
 
         description = '%s\n%s\n%s\n' % (

youtube_dl/extractor/dw.py

@@ -0,0 +1,85 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+from ..compat import compat_urlparse
+
+
+class DWIE(InfoExtractor):
+    IE_NAME = 'dw'
+    _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+av-(?P<id>\d+)'
+    _TESTS = [{
+        # video
+        'url': 'http://www.dw.com/en/intelligent-light/av-19112290',
+        'md5': '7372046e1815c5a534b43f3c3c36e6e9',
+        'info_dict': {
+            'id': '19112290',
+            'ext': 'mp4',
+            'title': 'Intelligent light',
+            'description': 'md5:90e00d5881719f2a6a5827cb74985af1',
+            'upload_date': '20160311',
+        }
+    }, {
+        # audio
+        'url': 'http://www.dw.com/en/worldlink-my-business/av-19111941',
+        'md5': '2814c9a1321c3a51f8a7aeb067a360dd',
+        'info_dict': {
+            'id': '19111941',
+            'ext': 'mp3',
+            'title': 'WorldLink: My business',
+            'description': 'md5:bc9ca6e4e063361e21c920c53af12405',
+            'upload_date': '20160311',
+        }
+    }]
+
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+        webpage = self._download_webpage(url, media_id)
+        hidden_inputs = self._hidden_inputs(webpage)
+        title = hidden_inputs['media_title']
+
+        formats = []
+        if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1':
+            formats = self._extract_smil_formats(
+                'http://www.dw.com/smil/v-%s' % media_id, media_id,
+                transform_source=lambda s: s.replace(
+                    'rtmp://tv-od.dw.de/flash/',
+                    'http://tv-download.dw.de/dwtv_video/flv/'))
+        else:
+            formats = [{'url': hidden_inputs['file_name']}]
+
+        return {
+            'id': media_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'thumbnail': hidden_inputs.get('preview_image'),
+            'duration': int_or_none(hidden_inputs.get('file_duration')),
+            'upload_date': hidden_inputs.get('display_date'),
+            'formats': formats,
+        }
+
+
+class DWArticleIE(InfoExtractor):
+    IE_NAME = 'dw:article'
+    _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.dw.com/en/no-hope-limited-options-for-refugees-in-idomeni/a-19111009',
+        'md5': '8ca657f9d068bbef74d6fc38b97fc869',
+        'info_dict': {
+            'id': '19105868',
+            'ext': 'mp4',
+            'title': 'The harsh life of refugees in Idomeni',
+            'description': 'md5:196015cc7e48ebf474db9399420043c7',
+            'upload_date': '20160310',
+        }
+    }
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+        webpage = self._download_webpage(url, article_id)
+        hidden_inputs = self._hidden_inputs(webpage)
+        media_id = hidden_inputs['media_id']
+        media_path = self._search_regex(r'href="([^"]+av-%s)"\s+class="overlayLink"' % media_id, webpage, 'media url')
+        media_url = compat_urlparse.urljoin(url, media_path)
+        return self.url_result(media_url, 'DW', media_id)

youtube_dl/extractor/eighttracks.py

@@ -17,85 +17,85 @@ class EightTracksIE(InfoExtractor):
     IE_NAME = '8tracks'
     _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
     _TEST = {
-        "name": "EightTracks",
+        'name': 'EightTracks',
-        "url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
+        'url': 'http://8tracks.com/ytdl/youtube-dl-test-tracks-a',
-        "info_dict": {
+        'info_dict': {
             'id': '1336550',
             'display_id': 'youtube-dl-test-tracks-a',
-            "description": "test chars:  \"'/\\ä↭",
+            'description': "test chars:  \"'/\\ä↭",
-            "title": "youtube-dl test tracks \"'/\\ä↭<>",
+            'title': "youtube-dl test tracks \"'/\\ä↭<>",
         },
-        "playlist": [
+        'playlist': [
             {
-                "md5": "96ce57f24389fc8734ce47f4c1abcc55",
+                'md5': '96ce57f24389fc8734ce47f4c1abcc55',
-                "info_dict": {
+                'info_dict': {
-                    "id": "11885610",
+                    'id': '11885610',
-                    "ext": "m4a",
+                    'ext': 'm4a',
-                    "title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
+                    'title': "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
-                    "uploader_id": "ytdl"
+                    'uploader_id': 'ytdl'
                 }
             },
             {
-                "md5": "4ab26f05c1f7291ea460a3920be8021f",
+                'md5': '4ab26f05c1f7291ea460a3920be8021f',
-                "info_dict": {
+                'info_dict': {
-                    "id": "11885608",
+                    'id': '11885608',
-                    "ext": "m4a",
+                    'ext': 'm4a',
-                    "title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
+                    'title': "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
-                    "uploader_id": "ytdl"
+                    'uploader_id': 'ytdl'
                 }
             },
             {
-                "md5": "d30b5b5f74217410f4689605c35d1fd7",
+                'md5': 'd30b5b5f74217410f4689605c35d1fd7',
-                "info_dict": {
+                'info_dict': {
-                    "id": "11885679",
+                    'id': '11885679',
-                    "ext": "m4a",
+                    'ext': 'm4a',
-                    "title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
+                    'title': "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
-                    "uploader_id": "ytdl"
+                    'uploader_id': 'ytdl'
                 }
             },
             {
-                "md5": "4eb0a669317cd725f6bbd336a29f923a",
+                'md5': '4eb0a669317cd725f6bbd336a29f923a',
-                "info_dict": {
+                'info_dict': {
-                    "id": "11885680",
+                    'id': '11885680',
-                    "ext": "m4a",
+                    'ext': 'm4a',
-                    "title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
+                    'title': "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
-                    "uploader_id": "ytdl"
+                    'uploader_id': 'ytdl'
                 }
             },
             {
-                "md5": "1893e872e263a2705558d1d319ad19e8",
+                'md5': '1893e872e263a2705558d1d319ad19e8',
-                "info_dict": {
+                'info_dict': {
-                    "id": "11885682",
+                    'id': '11885682',
-                    "ext": "m4a",
+                    'ext': 'm4a',
-                    "title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
+                    'title': "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
-                    "uploader_id": "ytdl"
+                    'uploader_id': 'ytdl'
                 }
             },
             {
-                "md5": "b673c46f47a216ab1741ae8836af5899",
+                'md5': 'b673c46f47a216ab1741ae8836af5899',
-                "info_dict": {
+                'info_dict': {
-                    "id": "11885683",
+                    'id': '11885683',
-                    "ext": "m4a",
+                    'ext': 'm4a',
-                    "title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
+                    'title': "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
-                    "uploader_id": "ytdl"
+                    'uploader_id': 'ytdl'
                 }
             },
             {
-                "md5": "1d74534e95df54986da7f5abf7d842b7",
+                'md5': '1d74534e95df54986da7f5abf7d842b7',
-                "info_dict": {
+                'info_dict': {
-                    "id": "11885684",
+                    'id': '11885684',
-                    "ext": "m4a",
+                    'ext': 'm4a',
-                    "title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
+                    'title': "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
-                    "uploader_id": "ytdl"
+                    'uploader_id': 'ytdl'
                 }
             },
             {
-                "md5": "f081f47af8f6ae782ed131d38b9cd1c0",
+                'md5': 'f081f47af8f6ae782ed131d38b9cd1c0',
-                "info_dict": {
+                'info_dict': {
-                    "id": "11885685",
+                    'id': '11885685',
-                    "ext": "m4a",
+                    'ext': 'm4a',
-                    "title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
+                    'title': "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
-                    "uploader_id": "ytdl"
+                    'uploader_id': 'ytdl'
                 }
             }
         ]

youtube_dl/extractor/ellentv.py

@@ -72,7 +72,7 @@ class EllenTVClipsIE(InfoExtractor):
     def _extract_playlist(self, webpage):
         json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
         try:
-            return json.loads("[{" + json_string + "}]")
+            return json.loads('[{' + json_string + '}]')
         except ValueError as ve:
             raise ExtractorError('Failed to download JSON', cause=ve)
 

youtube_dl/extractor/elpais.py

@@ -9,7 +9,7 @@ class ElPaisIE(InfoExtractor):
     _VALID_URL = r'https?://(?:[^.]+\.)?elpais\.com/.*/(?P<id>[^/#?]+)\.html(?:$|[?#])'
     IE_DESC = 'El País'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://blogs.elpais.com/la-voz-de-inaki/2014/02/tiempo-nuevo-recetas-viejas.html',
         'md5': '98406f301f19562170ec071b83433d55',
         'info_dict': {
@@ -19,30 +19,41 @@ class ElPaisIE(InfoExtractor):
             'description': 'De lunes a viernes, a partir de las ocho de la mañana, Iñaki Gabilondo nos cuenta su visión de la actualidad nacional e internacional.',
             'upload_date': '20140206',
         }
+    }, {
+        'url': 'http://elcomidista.elpais.com/elcomidista/2016/02/24/articulo/1456340311_668921.html#?id_externo_nwl=newsletter_diaria20160303t',
+        'md5': '3bd5b09509f3519d7d9e763179b013de',
+        'info_dict': {
+            'id': '1456340311_668921',
+            'ext': 'mp4',
+            'title': 'Cómo hacer el mejor café con cafetera italiana',
+            'description': 'Que sí, que las cápsulas son cómodas. Pero si le pides algo más a la vida, quizá deberías aprender a usar bien la cafetera italiana. No tienes más que ver este vídeo y seguir sus siete normas básicas.',
+            'upload_date': '20160303',
         }
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         prefix = self._html_search_regex(
-            r'var url_cache = "([^"]+)";', webpage, 'URL prefix')
+            r'var\s+url_cache\s*=\s*"([^"]+)";', webpage, 'URL prefix')
         video_suffix = self._search_regex(
-            r"URLMediaFile = url_cache \+ '([^']+)'", webpage, 'video URL')
+            r"(?:URLMediaFile|urlVideo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'", webpage, 'video URL')
         video_url = prefix + video_suffix
         thumbnail_suffix = self._search_regex(
-            r"URLMediaStill = url_cache \+ '([^']+)'", webpage, 'thumbnail URL',
+            r"(?:URLMediaStill|urlFotogramaFijo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'",
-            fatal=False)
+            webpage, 'thumbnail URL', fatal=False)
         thumbnail = (
             None if thumbnail_suffix is None
             else prefix + thumbnail_suffix)
         title = self._html_search_regex(
-            '<h2 class="entry-header entry-title.*?>(.*?)</h2>',
+            (r"tituloVideo\s*=\s*'([^']+)'", webpage, 'title',
+             r'<h2 class="entry-header entry-title.*?>(.*?)</h2>'),
             webpage, 'title')
-        date_str = self._search_regex(
+        upload_date = unified_strdate(self._search_regex(
             r'<p class="date-header date-int updated"\s+title="([^"]+)">',
-            webpage, 'upload date', fatal=False)
+            webpage, 'upload date', default=None) or self._html_search_meta(
-        upload_date = (None if date_str is None else unified_strdate(date_str))
+            'datePublished', webpage, 'timestamp'))
 
         return {
             'id': video_id,

youtube_dl/extractor/engadget.py

@@ -1,21 +1,13 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import (
-    url_basename,
-)
 
 
 class EngadgetIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://www.engadget.com/
+    _VALID_URL = r'https?://www.engadget.com/video/(?P<id>\d+)'
-        (?:video(?:/5min)?/(?P<id>\d+)|
-            [\d/]+/.*?)
-        '''
 
     _TEST = {
-        'url': 'http://www.engadget.com/video/5min/518153925/',
+        'url': 'http://www.engadget.com/video/518153925/',
         'md5': 'c6820d4828a5064447a4d9fc73f312c9',
         'info_dict': {
             'id': '518153925',
@@ -27,15 +19,4 @@ class EngadgetIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
-        if video_id is not None:
         return self.url_result('5min:%s' % video_id)
-        else:
-            title = url_basename(url)
-            webpage = self._download_webpage(url, title)
-            ids = re.findall(r'<iframe[^>]+?playList=(\d+)', webpage)
-            return {
-                '_type': 'playlist',
-                'title': title,
-                'entries': [self.url_result('5min:%s' % vid) for vid in ids]
-            }

youtube_dl/extractor/everyonesmixtape.py

@@ -14,14 +14,14 @@ class EveryonesMixtapeIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi/5',
-        "info_dict": {
+        'info_dict': {
             'id': '5bfseWNmlds',
             'ext': 'mp4',
-            "title": "Passion Pit - \"Sleepyhead\" (Official Music Video)",
+            'title': "Passion Pit - \"Sleepyhead\" (Official Music Video)",
-            "uploader": "FKR.TV",
+            'uploader': 'FKR.TV',
-            "uploader_id": "frenchkissrecords",
+            'uploader_id': 'frenchkissrecords',
-            "description": "Music video for \"Sleepyhead\" from Passion Pit's debut EP Chunk Of Change.\nBuy on iTunes: https://itunes.apple.com/us/album/chunk-of-change-ep/id300087641\n\nDirected by The Wilderness.\n\nhttp://www.passionpitmusic.com\nhttp://www.frenchkissrecords.com",
+            'description': "Music video for \"Sleepyhead\" from Passion Pit's debut EP Chunk Of Change.\nBuy on iTunes: https://itunes.apple.com/us/album/chunk-of-change-ep/id300087641\n\nDirected by The Wilderness.\n\nhttp://www.passionpitmusic.com\nhttp://www.frenchkissrecords.com",
-            "upload_date": "20081015"
+            'upload_date': '20081015'
         },
         'params': {
             'skip_download': True,  # This is simply YouTube

youtube_dl/extractor/exfm.py

@@ -41,7 +41,7 @@ class ExfmIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         song_id = mobj.group('id')
-        info_url = "http://ex.fm/api/v3/song/%s" % song_id
+        info_url = 'http://ex.fm/api/v3/song/%s' % song_id
         info = self._download_json(info_url, song_id)['song']
         song_url = info['url']
         if re.match(self._SOUNDCLOUD_URL, song_url) is not None:

youtube_dl/extractor/facebook.py

@@ -34,9 +34,12 @@ class FacebookIE(InfoExtractor):
                                 video/video\.php|
                                 photo\.php|
                                 video\.php|
-                                video/embed
+                                video/embed|
-                            )\?(?:.*?)(?:v|video_id)=|
+                                story\.php
-                            [^/]+/videos/(?:[^/]+/)?
+                            )\?(?:.*?)(?:v|video_id|story_fbid)=|
+                            [^/]+/videos/(?:[^/]+/)?|
+                            [^/]+/posts/|
+                            groups/[^/]+/permalink/
                         )|
                     facebook:
                 )
@@ -49,6 +52,8 @@ class FacebookIE(InfoExtractor):
 
     _CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36'
 
+    _VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s'
+
     _TESTS = [{
         'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
         'md5': '6a40d33c0eccbb1af76cf0485a052659',
@@ -80,6 +85,33 @@ class FacebookIE(InfoExtractor):
             'title': 'When you post epic content on instagram.com/433 8 million followers, this is ...',
             'uploader': 'Demy de Zeeuw',
         },
+    }, {
+        'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
+        'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6',
+        'info_dict': {
+            'id': '544765982287235',
+            'ext': 'mp4',
+            'title': '"What are you doing running in the snow?"',
+            'uploader': 'FailArmy',
+        }
+    }, {
+        'url': 'https://m.facebook.com/story.php?story_fbid=1035862816472149&id=116132035111903',
+        'md5': '1deb90b6ac27f7efcf6d747c8a27f5e3',
+        'info_dict': {
+            'id': '1035862816472149',
+            'ext': 'mp4',
+            'title': 'What the Flock Is Going On In New Zealand  Credit: ViralHog',
+            'uploader': 'S. Saint',
+        },
+    }, {
+        'note': 'swf params escaped',
+        'url': 'https://www.facebook.com/barackobama/posts/10153664894881749',
+        'md5': '97ba073838964d12c70566e0085c2b91',
+        'info_dict': {
+            'id': '10153664894881749',
+            'ext': 'mp4',
+            'title': 'Facebook video #10153664894881749',
+        },
     }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',
         'only_matching': True,
@@ -92,6 +124,9 @@ class FacebookIE(InfoExtractor):
     }, {
         'url': 'facebook:544765982287235',
         'only_matching': True,
+    }, {
+        'url': 'https://www.facebook.com/groups/164828000315060/permalink/764967300301124/',
+        'only_matching': True,
     }]
 
     def _login(self):
@@ -160,19 +195,19 @@ class FacebookIE(InfoExtractor):
     def _real_initialize(self):
         self._login()
 
-    def _real_extract(self, url):
+    def _extract_from_url(self, url, video_id, fatal_if_no_video=True):
-        video_id = self._match_id(url)
+        req = sanitized_Request(url)
-        req = sanitized_Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
         req.add_header('User-Agent', self._CHROME_USER_AGENT)
         webpage = self._download_webpage(req, video_id)
 
         video_data = None
 
-        BEFORE = '{swf.addParam(param[0], param[1]);});\n'
+        BEFORE = '{swf.addParam(param[0], param[1]);});'
         AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
-        m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage)
+        m = re.search(re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER), webpage)
         if m:
-            data = dict(json.loads(m.group(1)))
+            swf_params = m.group(1).replace('\\\\', '\\').replace('\\"', '"')
+            data = dict(json.loads(swf_params))
             params_raw = compat_urllib_parse_unquote(data['params'])
             video_data = json.loads(params_raw)['video_data']
 
@@ -185,13 +220,15 @@ class FacebookIE(InfoExtractor):
 
         if not video_data:
             server_js_data = self._parse_json(self._search_regex(
-                r'handleServerJS\(({.+})\);', webpage, 'server js data'), video_id)
+                r'handleServerJS\(({.+})\);', webpage, 'server js data', default='{}'), video_id)
-            for item in server_js_data['instances']:
+            for item in server_js_data.get('instances', []):
                 if item[1][0] == 'VideoConfig':
                     video_data = video_data_list2dict(item[2][0]['videoData'])
                     break
 
         if not video_data:
+            if not fatal_if_no_video:
+                return webpage, False
             m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
             if m_msg is not None:
                 raise ExtractorError(
@@ -208,10 +245,13 @@ class FacebookIE(InfoExtractor):
                 for src_type in ('src', 'src_no_ratelimit'):
                     src = f[0].get('%s_%s' % (quality, src_type))
                     if src:
+                        preference = -10 if format_id == 'progressive' else 0
+                        if quality == 'hd':
+                            preference += 5
                         formats.append({
                             'format_id': '%s_%s_%s' % (format_id, quality, src_type),
                             'url': src,
-                            'preference': -10 if format_id == 'progressive' else 0,
+                            'preference': preference,
                         })
             dash_manifest = f[0].get('dash_manifest')
             if dash_manifest:
@@ -234,39 +274,36 @@ class FacebookIE(InfoExtractor):
             video_title = 'Facebook video #%s' % video_id
         uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
 
-        return {
+        info_dict = {
             'id': video_id,
             'title': video_title,
             'formats': formats,
             'uploader': uploader,
         }
 
-
+        return webpage, info_dict
-class FacebookPostIE(InfoExtractor):
-    IE_NAME = 'facebook:post'
-    _VALID_URL = r'https?://(?:\w+\.)?facebook\.com/[^/]+/posts/(?P<id>\d+)'
-    _TEST = {
-        'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
-        'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6',
-        'info_dict': {
-            'id': '544765982287235',
-            'ext': 'mp4',
-            'title': '"What are you doing running in the snow?"',
-            'uploader': 'FailArmy',
-        }
-    }
 
     def _real_extract(self, url):
-        post_id = self._match_id(url)
+        video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, post_id)
+        real_url = self._VIDEO_PAGE_TEMPLATE % video_id if url.startswith('facebook:') else url
+        webpage, info_dict = self._extract_from_url(real_url, video_id, fatal_if_no_video=False)
 
+        if info_dict:
+            return info_dict
+
+        if '/posts/' in url:
             entries = [
-            self.url_result('facebook:%s' % video_id, FacebookIE.ie_key())
+                self.url_result('facebook:%s' % vid, FacebookIE.ie_key())
-            for video_id in self._parse_json(
+                for vid in self._parse_json(
                     self._search_regex(
                         r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])',
                         webpage, 'video ids', group='ids'),
-                post_id)]
+                    video_id)]
 
-        return self.playlist_result(entries, post_id)
+            return self.playlist_result(entries, video_id)
+        else:
+            _, info_dict = self._extract_from_url(
+                self._VIDEO_PAGE_TEMPLATE % video_id,
+                video_id, fatal_if_no_video=True)
+            return info_dict

youtube_dl/extractor/faz.py

@@ -52,7 +52,7 @@ class FazIE(InfoExtractor):
         formats = []
         for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
             encoding = xpath_element(encodings, code)
-            if encoding:
+            if encoding is not None:
                 encoding_url = xpath_text(encoding, 'FILENAME')
                 if encoding_url:
                     formats.append({

youtube_dl/extractor/fc2.py

@@ -87,7 +87,7 @@ class FC2IE(InfoExtractor):
         mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
 
         info_url = (
-            "http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&".
+            'http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&'.
             format(video_id, mimi, compat_urllib_request.quote(refer, safe=b'').replace('.', '%2E')))
 
         info_webpage = self._download_webpage(

youtube_dl/extractor/fivemin.py

@@ -1,5 +1,7 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
@@ -16,12 +18,7 @@ from ..utils import (
 
 class FiveMinIE(InfoExtractor):
     IE_NAME = '5min'
-    _VALID_URL = r'''(?x)
+    _VALID_URL = r'(?:5min:(?P<id>\d+)(?::(?P<sid>\d+))?|https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?P<query>.*))'
-        (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?:.*?&)?playList=|
-            https?://(?:(?:massively|www)\.)?joystiq\.com/video/|
-            5min:)
-        (?P<id>\d+)
-        '''
 
     _TESTS = [
         {
@@ -45,6 +42,7 @@ class FiveMinIE(InfoExtractor):
                 'title': 'How to Make a Next-Level Fruit Salad',
                 'duration': 184,
             },
+            'skip': 'no longer available',
         },
     ]
     _ERRORS = {
@@ -91,20 +89,33 @@ class FiveMinIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        sid = mobj.group('sid')
+
+        if mobj.group('query'):
+            qs = compat_parse_qs(mobj.group('query'))
+            if not qs.get('playList'):
+                raise ExtractorError('Invalid URL', expected=True)
+            video_id = qs['playList'][0]
+            if qs.get('sid'):
+                sid = qs['sid'][0]
+
         embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id
+        if not sid:
             embed_page = self._download_webpage(embed_url, video_id,
                                                 'Downloading embed page')
             sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid')
-        query = compat_urllib_parse.urlencode({
+
+        response = self._download_json(
+            'https://syn.5min.com/handlers/SenseHandler.ashx?' +
+            compat_urllib_parse.urlencode({
                 'func': 'GetResults',
                 'playlist': video_id,
                 'sid': sid,
                 'isPlayerSeed': 'true',
                 'url': embed_url,
-        })
+            }),
-        response = self._download_json(
-            'https://syn.5min.com/handlers/SenseHandler.ashx?' + query,
             video_id)
         if not response['success']:
             raise ExtractorError(
@@ -118,9 +129,7 @@ class FiveMinIE(InfoExtractor):
         parsed_video_url = compat_urllib_parse_urlparse(compat_parse_qs(
             compat_urllib_parse_urlparse(info['EmbededURL']).query)['videoUrl'][0])
         for rendition in info['Renditions']:
-            if rendition['RenditionType'] == 'm3u8':
+            if rendition['RenditionType'] == 'aac' or rendition['RenditionType'] == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(rendition['Url'], video_id, m3u8_id='hls'))
-            elif rendition['RenditionType'] == 'aac':
                 continue
             else:
                 rendition_url = compat_urlparse.urlunparse(parsed_video_url._replace(path=replace_extension(parsed_video_url.path.replace('//', '/%s/' % rendition['ID']), rendition['RenditionType'])))

youtube_dl/extractor/foxnews.py

@@ -36,6 +36,10 @@ class FoxNewsIE(AMPIE):
                 # 'upload_date': '20141204',
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
         },
         {
             'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com',

youtube_dl/extractor/franceinter.py

@@ -10,7 +10,7 @@ class FranceInterIE(InfoExtractor):
     _TEST = {
         'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
         'md5': '4764932e466e6f6c79c317d2e74f6884',
-        "info_dict": {
+        'info_dict': {
             'id': '793962',
             'ext': 'mp3',
             'title': 'L’Histoire dans les jeux vidéo',

youtube_dl/extractor/francetv.py

@@ -289,7 +289,7 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         video_id, catalogue = self._html_search_regex(
-            r'href="http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
+            r'(?:href=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
             webpage, 'video ID').split('@')
         return self._extract_video(video_id, catalogue)
 

youtube_dl/extractor/freespeech.py

@@ -14,7 +14,7 @@ class FreespeechIE(InfoExtractor):
         'url': 'https://www.freespeech.org/video/obama-romney-campaign-colorado-ahead-debate-0',
         'info_dict': {
             'id': 'poKsVCZ64uU',
-            'ext': 'mp4',
+            'ext': 'webm',
             'title': 'Obama, Romney Campaign in Colorado Ahead of Debate',
             'description': 'Obama, Romney Campaign in Colorado Ahead of Debate',
             'uploader': 'freespeechtv',

youtube_dl/extractor/freevideo.py

@@ -12,8 +12,8 @@ class FreeVideoIE(InfoExtractor):
         'info_dict': {
             'id': 'vysukany-zadecek-22033',
             'ext': 'mp4',
-            "title": "vysukany-zadecek-22033",
+            'title': 'vysukany-zadecek-22033',
-            "age_limit": 18,
+            'age_limit': 18,
         },
         'skip': 'Blocked outside .cz',
     }

youtube_dl/extractor/generic.py

@@ -47,6 +47,7 @@ from .senateisvp import SenateISVPIE
 from .svt import SVTIE
 from .pornhub import PornHubIE
 from .xhamster import XHamsterEmbedIE
+from .tnaflix import TNAFlixNetworkEmbedIE
 from .vimeo import VimeoIE
 from .dailymotion import DailymotionCloudIE
 from .onionstudios import OnionStudiosIE
@@ -224,6 +225,20 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        # MPD from http://dash-mse-test.appspot.com/media.html
+        {
+            'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
+            'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
+            'info_dict': {
+                'id': 'car-20120827-manifest',
+                'ext': 'mp4',
+                'title': 'car-20120827-manifest',
+                'formats': 'mincount:9',
+            },
+            'params': {
+                'format': 'bestvideo',
+            },
+        },
         # google redirect
         {
             'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
@@ -1227,28 +1242,34 @@ class GenericIE(InfoExtractor):
             full_response = self._request_webpage(request, video_id)
             head_response = full_response
 
+        info_dict = {
+            'id': video_id,
+            'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
+        }
+
         # Check for direct link to a video
         content_type = head_response.headers.get('Content-Type', '')
         m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type)
         if m:
             upload_date = unified_strdate(
                 head_response.headers.get('Last-Modified'))
-            formats = []
+            format_id = m.group('format_id')
-            if m.group('format_id').endswith('mpegurl'):
+            if format_id.endswith('mpegurl'):
                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
+            elif format_id == 'f4m':
+                formats = self._extract_f4m_formats(url, video_id)
             else:
                 formats = [{
                     'format_id': m.group('format_id'),
                     'url': url,
                     'vcodec': 'none' if m.group('type') == 'audio' else None
                 }]
-            return {
+            info_dict.update({
-                'id': video_id,
-                'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
                 'direct': True,
                 'formats': formats,
                 'upload_date': upload_date,
-            }
+            })
+            return info_dict
 
         if not self._downloader.params.get('test', False) and not is_intentional:
             force = self._downloader.params.get('force_generic_extractor', False)
@@ -1276,13 +1297,12 @@ class GenericIE(InfoExtractor):
                 'URL could be a direct video link, returning it as such.')
             upload_date = unified_strdate(
                 head_response.headers.get('Last-Modified'))
-            return {
+            info_dict.update({
-                'id': video_id,
-                'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
                 'direct': True,
                 'url': url,
                 'upload_date': upload_date,
-            }
+            })
+            return info_dict
 
         webpage = self._webpage_read_content(
             full_response, url, video_id, prefix=first_bytes)
@@ -1299,11 +1319,12 @@ class GenericIE(InfoExtractor):
             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
-                return {
+                info_dict['formats'] = self._parse_mpd_formats(
-                    'id': video_id,
+                    doc, video_id, mpd_base_url=url.rpartition('/')[0])
-                    'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
+                return info_dict
-                    'formats': self._parse_mpd_formats(doc, video_id),
+            elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
-                }
+                info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
+                return info_dict
         except compat_xml_parse_error:
             pass
 
@@ -1413,7 +1434,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded Dailymotion player
         matches = re.findall(
-            r'<(?:embed|iframe)[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
+            r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
         if matches:
             return _playlist_from_matches(
                 matches, lambda m: unescapeHTML(m[1]))
@@ -1558,6 +1579,11 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'VK')
 
+        # Look for embedded Odnoklassniki player
+        mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Odnoklassniki')
+
         # Look for embedded ivi player
         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
         if mobj is not None:
@@ -1613,6 +1639,11 @@ class GenericIE(InfoExtractor):
         if xhamster_urls:
             return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
 
+        # Look for embedded TNAFlixNetwork player
+        tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
+        if tnaflix_urls:
+            return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
+
         # Look for embedded Tvigle player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
@@ -1959,6 +1990,8 @@ class GenericIE(InfoExtractor):
                 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
             elif ext == 'mpd':
                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
+            elif ext == 'f4m':
+                entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
             else:
                 entry_info_dict['url'] = video_url
 

youtube_dl/extractor/globo.py

@@ -65,7 +65,7 @@ class GloboIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    class MD5:
+    class MD5(object):
         HEX_FORMAT_LOWERCASE = 0
         HEX_FORMAT_UPPERCASE = 1
         BASE64_PAD_CHARACTER_DEFAULT_COMPLIANCE = ''

youtube_dl/extractor/googledrive.py

@@ -10,8 +10,8 @@ from ..utils import (
 
 
 class GoogleDriveIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28})'
+    _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28,})'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
         'md5': '881f7700aec4f538571fa1e0eed4a7b6',
         'info_dict': {
@@ -20,7 +20,11 @@ class GoogleDriveIE(InfoExtractor):
             'title': 'Big Buck Bunny.mp4',
             'duration': 46,
         }
-    }
+    }, {
+        # video id is longer than 28 characters
+        'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit',
+        'only_matching': True,
+    }]
     _FORMATS_EXT = {
         '5': 'flv',
         '6': 'flv',
@@ -43,7 +47,7 @@ class GoogleDriveIE(InfoExtractor):
     @staticmethod
     def _extract_url(webpage):
         mobj = re.search(
-            r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28})',
+            r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})',
             webpage)
         if mobj:
             return 'https://drive.google.com/file/d/%s' % mobj.group('id')
@@ -82,7 +86,7 @@ class GoogleDriveIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'duration': duration,
             'formats': formats,
         }

youtube_dl/extractor/hentaistigma.py

@@ -11,8 +11,8 @@ class HentaiStigmaIE(InfoExtractor):
         'info_dict': {
             'id': 'inyouchuu-etsu-bonus',
             'ext': 'mp4',
-            "title": "Inyouchuu Etsu Bonus",
+            'title': 'Inyouchuu Etsu Bonus',
-            "age_limit": 18,
+            'age_limit': 18,
         }
     }
 

youtube_dl/extractor/hotstar.py

@@ -10,8 +10,8 @@ from ..utils import (
 
 
 class HotStarIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?hotstar\.com/.*?[/-](?P<id>\d{10})'
+    _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273',
         'info_dict': {
             'id': '1000076273',
@@ -26,7 +26,13 @@ class HotStarIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         }
-    }
+    }, {
+        'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.hotstar.com/1000000515',
+        'only_matching': True,
+    }]
 
     _GET_CONTENT_TEMPLATE = 'http://account.hotstar.com/AVS/besc?action=GetAggregatedContentDetails&channel=PCTV&contentId=%s'
     _GET_CDN_TEMPLATE = 'http://getcdn.hotstar.com/AVS/besc?action=GetCDN&asJson=Y&channel=%s&id=%s&type=%s'

youtube_dl/extractor/imdb.py

@@ -42,7 +42,7 @@ class ImdbIE(InfoExtractor):
             for f_url, f_name in extra_formats]
         format_pages.append(player_page)
 
-        quality = qualities(['SD', '480p', '720p'])
+        quality = qualities(('SD', '480p', '720p', '1080p'))
         formats = []
         for format_page in format_pages:
             json_data = self._search_regex(

youtube_dl/extractor/indavideo.py

@@ -73,7 +73,7 @@ class IndavideoEmbedIE(InfoExtractor):
             'url': self._proto_relative_url(thumbnail)
         } for thumbnail in video.get('thumbnails', [])]
 
-        tags = [tag['title'] for tag in video.get('tags', [])]
+        tags = [tag['title'] for tag in video.get('tags') or []]
 
         return {
             'id': video.get('id') or video_id,

youtube_dl/extractor/infoq.py

@@ -4,15 +4,12 @@ from __future__ import unicode_literals
 
 import base64
 
-from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
-from ..compat import (
-    compat_urllib_parse_unquote,
-    compat_parse_qs,
-)
 from ..utils import determine_ext
+from .bokecc import BokeCCBaseIE
 
 
-class InfoQIE(InfoExtractor):
+class InfoQIE(BokeCCBaseIE):
     _VALID_URL = r'https?://(?:www\.)?infoq\.com/(?:[^/]+/)+(?P<id>[^/]+)'
 
     _TESTS = [{
@@ -38,26 +35,6 @@ class InfoQIE(InfoExtractor):
         },
     }]
 
-    def _extract_bokecc_videos(self, webpage, video_id):
-        # TODO: bokecc.com is a Chinese video cloud platform
-        # It should have an independent extractor but I don't have other
-        # examples using bokecc
-        player_params_str = self._html_search_regex(
-            r'<script[^>]+src="http://p\.bokecc\.com/player\?([^"]+)',
-            webpage, 'player params', default=None)
-
-        player_params = compat_parse_qs(player_params_str)
-
-        info_xml = self._download_xml(
-            'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % (
-                player_params['siteid'][0], player_params['vid'][0]), video_id)
-
-        return [{
-            'format_id': 'bokecc',
-            'url': quality.find('./copy').attrib['playurl'],
-            'preference': int(quality.attrib['value']),
-        } for quality in info_xml.findall('./video/quality')]
-
     def _extract_rtmp_videos(self, webpage):
         # The server URL is hardcoded
         video_url = 'rtmpe://video.infoq.com/cfx/st/'
@@ -101,7 +78,7 @@ class InfoQIE(InfoExtractor):
 
         if '/cn/' in url:
             # for China videos, HTTP video URL exists but always fails with 403
-            formats = self._extract_bokecc_videos(webpage, video_id)
+            formats = self._extract_bokecc_formats(webpage, video_id)
         else:
             formats = self._extract_rtmp_videos(webpage) + self._extract_http_videos(webpage)
 

youtube_dl/extractor/iqiyi.py

@@ -2,14 +2,163 @@
 from __future__ import unicode_literals
 
 import hashlib
+import itertools
 import math
+import os
 import random
+import re
 import time
 import uuid
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import (
-from ..utils import ExtractorError
+    compat_parse_qs,
+    compat_str,
+    compat_urllib_parse,
+    compat_urllib_parse_urlparse,
+)
+from ..utils import (
+    decode_packed_codes,
+    ExtractorError,
+    ohdave_rsa_encrypt,
+    remove_start,
+    sanitized_Request,
+    urlencode_postdata,
+    url_basename,
+)
+
+
+def md5_text(text):
+    return hashlib.md5(text.encode('utf-8')).hexdigest()
+
+
+class IqiyiSDK(object):
+    def __init__(self, target, ip, timestamp):
+        self.target = target
+        self.ip = ip
+        self.timestamp = timestamp
+
+    @staticmethod
+    def split_sum(data):
+        return compat_str(sum(map(lambda p: int(p, 16), list(data))))
+
+    @staticmethod
+    def digit_sum(num):
+        if isinstance(num, int):
+            num = compat_str(num)
+        return compat_str(sum(map(int, num)))
+
+    def even_odd(self):
+        even = self.digit_sum(compat_str(self.timestamp)[::2])
+        odd = self.digit_sum(compat_str(self.timestamp)[1::2])
+        return even, odd
+
+    def preprocess(self, chunksize):
+        self.target = md5_text(self.target)
+        chunks = []
+        for i in range(32 // chunksize):
+            chunks.append(self.target[chunksize * i:chunksize * (i + 1)])
+        if 32 % chunksize:
+            chunks.append(self.target[32 - 32 % chunksize:])
+        return chunks, list(map(int, self.ip.split('.')))
+
+    def mod(self, modulus):
+        chunks, ip = self.preprocess(32)
+        self.target = chunks[0] + ''.join(map(lambda p: compat_str(p % modulus), ip))
+
+    def split(self, chunksize):
+        modulus_map = {
+            4: 256,
+            5: 10,
+            8: 100,
+        }
+
+        chunks, ip = self.preprocess(chunksize)
+        ret = ''
+        for i in range(len(chunks)):
+            ip_part = compat_str(ip[i] % modulus_map[chunksize]) if i < 4 else ''
+            if chunksize == 8:
+                ret += ip_part + chunks[i]
+            else:
+                ret += chunks[i] + ip_part
+        self.target = ret
+
+    def handle_input16(self):
+        self.target = md5_text(self.target)
+        self.target = self.split_sum(self.target[:16]) + self.target + self.split_sum(self.target[16:])
+
+    def handle_input8(self):
+        self.target = md5_text(self.target)
+        ret = ''
+        for i in range(4):
+            part = self.target[8 * i:8 * (i + 1)]
+            ret += self.split_sum(part) + part
+        self.target = ret
+
+    def handleSum(self):
+        self.target = md5_text(self.target)
+        self.target = self.split_sum(self.target) + self.target
+
+    def date(self, scheme):
+        self.target = md5_text(self.target)
+        d = time.localtime(self.timestamp)
+        strings = {
+            'y': compat_str(d.tm_year),
+            'm': '%02d' % d.tm_mon,
+            'd': '%02d' % d.tm_mday,
+        }
+        self.target += ''.join(map(lambda c: strings[c], list(scheme)))
+
+    def split_time_even_odd(self):
+        even, odd = self.even_odd()
+        self.target = odd + md5_text(self.target) + even
+
+    def split_time_odd_even(self):
+        even, odd = self.even_odd()
+        self.target = even + md5_text(self.target) + odd
+
+    def split_ip_time_sum(self):
+        chunks, ip = self.preprocess(32)
+        self.target = compat_str(sum(ip)) + chunks[0] + self.digit_sum(self.timestamp)
+
+    def split_time_ip_sum(self):
+        chunks, ip = self.preprocess(32)
+        self.target = self.digit_sum(self.timestamp) + chunks[0] + compat_str(sum(ip))
+
+
+class IqiyiSDKInterpreter(object):
+    def __init__(self, sdk_code):
+        self.sdk_code = sdk_code
+
+    def run(self, target, ip, timestamp):
+        self.sdk_code = decode_packed_codes(self.sdk_code)
+
+        functions = re.findall(r'input=([a-zA-Z0-9]+)\(input', self.sdk_code)
+
+        sdk = IqiyiSDK(target, ip, timestamp)
+
+        other_functions = {
+            'handleSum': sdk.handleSum,
+            'handleInput8': sdk.handle_input8,
+            'handleInput16': sdk.handle_input16,
+            'splitTimeEvenOdd': sdk.split_time_even_odd,
+            'splitTimeOddEven': sdk.split_time_odd_even,
+            'splitIpTimeSum': sdk.split_ip_time_sum,
+            'splitTimeIpSum': sdk.split_time_ip_sum,
+        }
+        for function in functions:
+            if re.match(r'mod\d+', function):
+                sdk.mod(int(function[3:]))
+            elif re.match(r'date[ymd]{3}', function):
+                sdk.date(function[4:])
+            elif re.match(r'split\d+', function):
+                sdk.split(int(function[5:]))
+            elif function in other_functions:
+                other_functions[function]()
+            else:
+                raise ExtractorError('Unknown funcion %s' % function)
+
+        return sdk.target
 
 
 class IqiyiIE(InfoExtractor):
@@ -18,6 +167,8 @@ class IqiyiIE(InfoExtractor):
 
     _VALID_URL = r'http://(?:[^.]+\.)?iqiyi\.com/.+\.html'
 
+    _NETRC_MACHINE = 'iqiyi'
+
     _TESTS = [{
         'url': 'http://www.iqiyi.com/v_19rrojlavg.html',
         'md5': '2cb594dc2781e6c941a110d8f358118b',
@@ -93,6 +244,35 @@ class IqiyiIE(InfoExtractor):
     }, {
         'url': 'http://yule.iqiyi.com/pcb.html',
         'only_matching': True,
+    }, {
+        # VIP-only video. The first 2 parts (6 minutes) are available without login
+        # MD5 sums omitted as values are different on Travis CI and my machine
+        'url': 'http://www.iqiyi.com/v_19rrny4w8w.html',
+        'info_dict': {
+            'id': 'f3cf468b39dddb30d676f89a91200dc1',
+            'title': '泰坦尼克号',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'f3cf468b39dddb30d676f89a91200dc1_part1',
+                'ext': 'f4v',
+                'title': '泰坦尼克号',
+            },
+        }, {
+            'info_dict': {
+                'id': 'f3cf468b39dddb30d676f89a91200dc1_part2',
+                'ext': 'f4v',
+                'title': '泰坦尼克号',
+            },
+        }],
+        'expected_warnings': ['Needs a VIP account for full video'],
+    }, {
+        'url': 'http://www.iqiyi.com/a_19rrhb8ce1.html',
+        'info_dict': {
+            'id': '202918101',
+            'title': '灌篮高手 国语版',
+        },
+        'playlist_count': 101,
     }]
 
     _FORMATS_MAP = [
@@ -104,11 +284,98 @@ class IqiyiIE(InfoExtractor):
         ('10', 'h1'),
     ]
 
-    @staticmethod
+    def _real_initialize(self):
-    def md5_text(text):
+        self._login()
-        return hashlib.md5(text.encode('utf-8')).hexdigest()
 
-    def construct_video_urls(self, data, video_id, _uuid):
+    @staticmethod
+    def _rsa_fun(data):
+        # public key extracted from http://static.iqiyi.com/js/qiyiV2/20160129180840/jobs/i18n/i18nIndex.js
+        N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
+        e = 65537
+
+        return ohdave_rsa_encrypt(data, e, N)
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+
+        # No authentication to be performed
+        if not username:
+            return True
+
+        data = self._download_json(
+            'http://kylin.iqiyi.com/get_token', None,
+            note='Get token for logging', errnote='Unable to get token for logging')
+        sdk = data['sdk']
+        timestamp = int(time.time())
+        target = '/apis/reglogin/login.action?lang=zh_TW&area_code=null&email=%s&passwd=%s&agenttype=1&from=undefined&keeplogin=0&piccode=&fromurl=&_pos=1' % (
+            username, self._rsa_fun(password.encode('utf-8')))
+
+        interp = IqiyiSDKInterpreter(sdk)
+        sign = interp.run(target, data['ip'], timestamp)
+
+        validation_params = {
+            'target': target,
+            'server': 'BEA3AA1908656AABCCFF76582C4C6660',
+            'token': data['token'],
+            'bird_src': 'f8d91d57af224da7893dd397d52d811a',
+            'sign': sign,
+            'bird_t': timestamp,
+        }
+        validation_result = self._download_json(
+            'http://kylin.iqiyi.com/validate?' + compat_urllib_parse.urlencode(validation_params), None,
+            note='Validate credentials', errnote='Unable to validate credentials')
+
+        MSG_MAP = {
+            'P00107': 'please login via the web interface and enter the CAPTCHA code',
+            'P00117': 'bad username or password',
+        }
+
+        code = validation_result['code']
+        if code != 'A00000':
+            msg = MSG_MAP.get(code)
+            if not msg:
+                msg = 'error %s' % code
+                if validation_result.get('msg'):
+                    msg += ': ' + validation_result['msg']
+            self._downloader.report_warning('unable to log in: ' + msg)
+            return False
+
+        return True
+
+    def _authenticate_vip_video(self, api_video_url, video_id, tvid, _uuid, do_report_warning):
+        auth_params = {
+            # version and platform hard-coded in com/qiyi/player/core/model/remote/AuthenticationRemote.as
+            'version': '2.0',
+            'platform': 'b6c13e26323c537d',
+            'aid': tvid,
+            'tvid': tvid,
+            'uid': '',
+            'deviceId': _uuid,
+            'playType': 'main',  # XXX: always main?
+            'filename': os.path.splitext(url_basename(api_video_url))[0],
+        }
+
+        qd_items = compat_parse_qs(compat_urllib_parse_urlparse(api_video_url).query)
+        for key, val in qd_items.items():
+            auth_params[key] = val[0]
+
+        auth_req = sanitized_Request(
+            'http://api.vip.iqiyi.com/services/ckn.action',
+            urlencode_postdata(auth_params))
+        # iQiyi server throws HTTP 405 error without the following header
+        auth_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        auth_result = self._download_json(
+            auth_req, video_id,
+            note='Downloading video authentication JSON',
+            errnote='Unable to download video authentication JSON')
+        if auth_result['code'] == 'Q00506':  # requires a VIP account
+            if do_report_warning:
+                self.report_warning('Needs a VIP account for full video')
+            return False
+
+        return auth_result
+
+    def construct_video_urls(self, data, video_id, _uuid, tvid):
         def do_xor(x, y):
             a = y % 3
             if a == 1:
@@ -134,9 +401,10 @@ class IqiyiIE(InfoExtractor):
                 note='Download path key of segment %d for format %s' % (segment_index + 1, format_id)
             )['t']
             t = str(int(math.floor(int(tm) / (600.0))))
-            return self.md5_text(t + mg + x)
+            return md5_text(t + mg + x)
 
         video_urls_dict = {}
+        need_vip_warning_report = True
         for format_item in data['vp']['tkl'][0]['vs']:
             if 0 < int(format_item['bid']) <= 10:
                 format_id = self.get_format(format_item['bid'])
@@ -155,10 +423,12 @@ class IqiyiIE(InfoExtractor):
                 vl = segment['l']
                 if not vl.startswith('/'):
                     vl = get_encode_code(vl)
-                key = get_path_key(
+                is_vip_video = '/vip/' in vl
-                    vl.split('/')[-1].split('.')[0], format_id, segment_index)
                 filesize = segment['b']
                 base_url = data['vp']['du'].split('/')
+                if not is_vip_video:
+                    key = get_path_key(
+                        vl.split('/')[-1].split('.')[0], format_id, segment_index)
                     base_url.insert(-1, key)
                 base_url = '/'.join(base_url)
                 param = {
@@ -170,8 +440,23 @@ class IqiyiIE(InfoExtractor):
                     'ct': '',
                     'tn': str(int(time.time()))
                 }
-                api_video_url = base_url + vl + '?' + \
+                api_video_url = base_url + vl
-                    compat_urllib_parse.urlencode(param)
+                if is_vip_video:
+                    api_video_url = api_video_url.replace('.f4v', '.hml')
+                    auth_result = self._authenticate_vip_video(
+                        api_video_url, video_id, tvid, _uuid, need_vip_warning_report)
+                    if auth_result is False:
+                        need_vip_warning_report = False
+                        break
+                    param.update({
+                        't': auth_result['data']['t'],
+                        # cid is hard-coded in com/qiyi/player/core/player/RuntimeData.as
+                        'cid': 'afbe8fd3d73448c9',
+                        'vid': video_id,
+                        'QY00001': auth_result['data']['u'],
+                    })
+                api_video_url += '?' if '?' not in api_video_url else '&'
+                api_video_url += compat_urllib_parse.urlencode(param)
                 js = self._download_json(
                     api_video_url, video_id,
                     note='Download video info of segment %d for format %s' % (segment_index + 1, format_id))
@@ -195,16 +480,17 @@ class IqiyiIE(InfoExtractor):
         tail = tm + tvid
         param = {
             'key': 'fvip',
-            'src': self.md5_text('youtube-dl'),
+            'src': md5_text('youtube-dl'),
             'tvId': tvid,
             'vid': video_id,
             'vinfo': 1,
             'tm': tm,
-            'enc': self.md5_text(enc_key + tail),
+            'enc': md5_text(enc_key + tail),
             'qyid': _uuid,
             'tn': random.random(),
             'um': 0,
-            'authkey': self.md5_text(self.md5_text('') + tail),
+            'authkey': md5_text(md5_text('') + tail),
+            'k_tag': 1,
         }
 
         api_url = 'http://cache.video.qiyi.com/vms' + '?' + \
@@ -212,40 +498,75 @@ class IqiyiIE(InfoExtractor):
         raw_data = self._download_json(api_url, video_id)
         return raw_data
 
-    def get_enc_key(self, swf_url, video_id):
+    def get_enc_key(self, video_id):
         # TODO: automatic key extraction
         # last update at 2016-01-22 for Zombie::bite
-        enc_key = '6ab6d0280511493ba85594779759d4ed'
+        enc_key = '8ed797d224d043e7ac23d95b70227d32'
         return enc_key
 
+    def _extract_playlist(self, webpage):
+        PAGE_SIZE = 50
+
+        links = re.findall(
+            r'<a[^>]+class="site-piclist_pic_link"[^>]+href="(http://www\.iqiyi\.com/.+\.html)"',
+            webpage)
+        if not links:
+            return
+
+        album_id = self._search_regex(
+            r'albumId\s*:\s*(\d+),', webpage, 'album ID')
+        album_title = self._search_regex(
+            r'data-share-title="([^"]+)"', webpage, 'album title', fatal=False)
+
+        entries = list(map(self.url_result, links))
+
+        # Start from 2 because links in the first page are already on webpage
+        for page_num in itertools.count(2):
+            pagelist_page = self._download_webpage(
+                'http://cache.video.qiyi.com/jp/avlist/%s/%d/%d/' % (album_id, page_num, PAGE_SIZE),
+                album_id,
+                note='Download playlist page %d' % page_num,
+                errnote='Failed to download playlist page %d' % page_num)
+            pagelist = self._parse_json(
+                remove_start(pagelist_page, 'var tvInfoJs='), album_id)
+            vlist = pagelist['data']['vlist']
+            for item in vlist:
+                entries.append(self.url_result(item['vurl']))
+            if len(vlist) < PAGE_SIZE:
+                break
+
+        return self.playlist_result(entries, album_id, album_title)
+
     def _real_extract(self, url):
         webpage = self._download_webpage(
             url, 'temp_id', note='download video page')
+
+        # There's no simple way to determine whether an URL is a playlist or not
+        # So detect it
+        playlist_result = self._extract_playlist(webpage)
+        if playlist_result:
+            return playlist_result
+
         tvid = self._search_regex(
             r'data-player-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid')
         video_id = self._search_regex(
             r'data-player-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id')
-        swf_url = self._search_regex(
-            r'(http://[^\'"]+MainPlayer[^.]+\.swf)', webpage, 'swf player URL')
         _uuid = uuid.uuid4().hex
 
-        enc_key = self.get_enc_key(swf_url, video_id)
+        enc_key = self.get_enc_key(video_id)
 
         raw_data = self.get_raw_data(tvid, video_id, enc_key, _uuid)
 
         if raw_data['code'] != 'A000000':
             raise ExtractorError('Unable to load data. Error code: ' + raw_data['code'])
 
-        if not raw_data['data']['vp']['tkl']:
-            raise ExtractorError('No support iQiqy VIP video')
-
         data = raw_data['data']
 
         title = data['vi']['vn']
 
         # generate video_urls_dict
         video_urls_dict = self.construct_video_urls(
-            data, video_id, _uuid)
+            data, video_id, _uuid, tvid)
 
         # construct info
         entries = []

youtube_dl/extractor/jeuxvideo.py

@@ -30,7 +30,7 @@ class JeuxVideoIE(InfoExtractor):
         webpage = self._download_webpage(url, title)
         title = self._html_search_meta('name', webpage) or self._og_search_title(webpage)
         config_url = self._html_search_regex(
-            r'data-src="(/contenu/medias/video.php.*?)"',
+            r'data-src(?:set-video)?="(/contenu/medias/video.php.*?)"',
             webpage, 'config URL')
         config_url = 'http://www.jeuxvideo.com' + config_url
 

youtube_dl/extractor/jwplatform.py

@@ -7,7 +7,46 @@ from .common import InfoExtractor
 from ..utils import int_or_none
 
 
-class JWPlatformIE(InfoExtractor):
+class JWPlatformBaseIE(InfoExtractor):
+    def _parse_jwplayer_data(self, jwplayer_data, video_id, require_title=True):
+        video_data = jwplayer_data['playlist'][0]
+        subtitles = {}
+        for track in video_data['tracks']:
+            if track['kind'] == 'captions':
+                subtitles[track['label']] = [{'url': self._proto_relative_url(track['file'])}]
+
+        formats = []
+        for source in video_data['sources']:
+            source_url = self._proto_relative_url(source['file'])
+            source_type = source.get('type') or ''
+            if source_type in ('application/vnd.apple.mpegurl', 'hls'):
+                formats.extend(self._extract_m3u8_formats(
+                    source_url, video_id, 'mp4', 'm3u8_native', fatal=False))
+            elif source_type.startswith('audio'):
+                formats.append({
+                    'url': source_url,
+                    'vcodec': 'none',
+                })
+            else:
+                formats.append({
+                    'url': source_url,
+                    'width': int_or_none(source.get('width')),
+                    'height': int_or_none(source.get('height')),
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_data['title'] if require_title else video_data.get('title'),
+            'description': video_data.get('description'),
+            'thumbnail': self._proto_relative_url(video_data.get('image')),
+            'timestamp': int_or_none(video_data.get('pubdate')),
+            'subtitles': subtitles,
+            'formats': formats,
+        }
+
+
+class JWPlatformIE(JWPlatformBaseIE):
     _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
     _TEST = {
         'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
@@ -33,38 +72,4 @@ class JWPlatformIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         json_data = self._download_json('http://content.jwplatform.com/feeds/%s.json' % video_id, video_id)
-        video_data = json_data['playlist'][0]
+        return self._parse_jwplayer_data(json_data, video_id)
-        subtitles = {}
-        for track in video_data['tracks']:
-            if track['kind'] == 'captions':
-                subtitles[track['label']] = [{'url': self._proto_relative_url(track['file'])}]
-
-        formats = []
-        for source in video_data['sources']:
-            source_url = self._proto_relative_url(source['file'])
-            source_type = source.get('type') or ''
-            if source_type == 'application/vnd.apple.mpegurl':
-                formats.extend(self._extract_m3u8_formats(
-                    source_url, video_id, 'mp4', 'm3u8_native', fatal=False))
-            elif source_type.startswith('audio'):
-                formats.append({
-                    'url': source_url,
-                    'vcodec': 'none',
-                })
-            else:
-                formats.append({
-                    'url': source_url,
-                    'width': int_or_none(source.get('width')),
-                    'height': int_or_none(source.get('height')),
-                })
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': video_data['title'],
-            'description': video_data.get('description'),
-            'thumbnail': self._proto_relative_url(video_data.get('image')),
-            'timestamp': int_or_none(video_data.get('pubdate')),
-            'subtitles': subtitles,
-            'formats': formats,
-        }

youtube_dl/extractor/kaltura.py

@@ -8,6 +8,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
     compat_urlparse,
+    compat_parse_qs,
 )
 from ..utils import (
     clean_html,
@@ -20,21 +21,17 @@ from ..utils import (
 class KalturaIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                 (?:
-                    kaltura:(?P<partner_id_s>\d+):(?P<id_s>[0-9a-z_]+)|
+                    kaltura:(?P<partner_id>\d+):(?P<id>[0-9a-z_]+)|
                     https?://
                         (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/
                         (?:
                             (?:
                                 # flash player
-                                index\.php/kwidget/
+                                index\.php/kwidget|
-                                (?:[^/]+/)*?wid/_(?P<partner_id>\d+)/
-                                (?:[^/]+/)*?entry_id/(?P<id>[0-9a-z_]+)|
                                 # html5 player
-                                html5/html5lib/
+                                html5/html5lib/[^/]+/mwEmbedFrame\.php
-                                (?:[^/]+/)*?entry_id/(?P<id_html5>[0-9a-z_]+)
-                                .*\?.*\bwid=_(?P<partner_id_html5>\d+)
-                            )
                             )
+                        )(?:/(?P<path>[^?]+))?(?:\?(?P<query>.*))?
                 )
                 '''
     _API_BASE = 'http://cdnapi.kaltura.com/api_v3/index.php?'
@@ -127,10 +124,41 @@ class KalturaIE(InfoExtractor):
         url, smuggled_data = unsmuggle_url(url, {})
 
         mobj = re.match(self._VALID_URL, url)
-        partner_id = mobj.group('partner_id_s') or mobj.group('partner_id') or mobj.group('partner_id_html5')
+        partner_id, entry_id = mobj.group('partner_id', 'id')
-        entry_id = mobj.group('id_s') or mobj.group('id') or mobj.group('id_html5')
+        ks = None
-
+        if partner_id and entry_id:
             info, flavor_assets = self._get_video_info(entry_id, partner_id)
+        else:
+            path, query = mobj.group('path', 'query')
+            if not path and not query:
+                raise ExtractorError('Invalid URL', expected=True)
+            params = {}
+            if query:
+                params = compat_parse_qs(query)
+            if path:
+                splitted_path = path.split('/')
+                params.update(dict((zip(splitted_path[::2], [[v] for v in splitted_path[1::2]]))))
+            if 'wid' in params:
+                partner_id = params['wid'][0][1:]
+            elif 'p' in params:
+                partner_id = params['p'][0]
+            else:
+                raise ExtractorError('Invalid URL', expected=True)
+            if 'entry_id' in params:
+                entry_id = params['entry_id'][0]
+                info, flavor_assets = self._get_video_info(entry_id, partner_id)
+            elif 'uiconf_id' in params and 'flashvars[referenceId]' in params:
+                reference_id = params['flashvars[referenceId]'][0]
+                webpage = self._download_webpage(url, reference_id)
+                entry_data = self._parse_json(self._search_regex(
+                    r'window\.kalturaIframePackageData\s*=\s*({.*});',
+                    webpage, 'kalturaIframePackageData'),
+                    reference_id)['entryResult']
+                info, flavor_assets = entry_data['meta'], entry_data['contextData']['flavorAssets']
+                entry_id = info['id']
+            else:
+                raise ExtractorError('Invalid URL', expected=True)
+            ks = params.get('flashvars[ks]', [None])[0]
 
         source_url = smuggled_data.get('source_url')
         if source_url:
@@ -140,14 +168,19 @@ class KalturaIE(InfoExtractor):
         else:
             referrer = None
 
+        def sign_url(unsigned_url):
+            if ks:
+                unsigned_url += '/ks/%s' % ks
+            if referrer:
+                unsigned_url += '?referrer=%s' % referrer
+            return unsigned_url
+
         formats = []
         for f in flavor_assets:
             # Continue if asset is not ready
             if f['status'] != 2:
                 continue
-            video_url = '%s/flavorId/%s' % (info['dataUrl'], f['id'])
+            video_url = sign_url('%s/flavorId/%s' % (info['dataUrl'], f['id']))
-            if referrer:
-                video_url += '?referrer=%s' % referrer
             formats.append({
                 'format_id': '%(fileExt)s-%(bitrate)s' % f,
                 'ext': f.get('fileExt'),
@@ -160,9 +193,7 @@ class KalturaIE(InfoExtractor):
                 'width': int_or_none(f.get('width')),
                 'url': video_url,
             })
-        m3u8_url = info['dataUrl'].replace('format/url', 'format/applehttp')
+        m3u8_url = sign_url(info['dataUrl'].replace('format/url', 'format/applehttp'))
-        if referrer:
-            m3u8_url += '?referrer=%s' % referrer
         formats.extend(self._extract_m3u8_formats(
             m3u8_url, entry_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
 

youtube_dl/extractor/kankan.py

@@ -28,7 +28,7 @@ class KankanIE(InfoExtractor):
 
         title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, 'video title')
         surls = re.search(r'surls:\[\'.+?\'\]|lurl:\'.+?\.flv\'', webpage).group(0)
-        gcids = re.findall(r"http://.+?/.+?/(.+?)/", surls)
+        gcids = re.findall(r'http://.+?/.+?/(.+?)/', surls)
         gcid = gcids[-1]
 
         info_url = 'http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid

youtube_dl/extractor/khanacademy.py

@@ -14,10 +14,10 @@ class KhanAcademyIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.khanacademy.org/video/one-time-pad',
-        'md5': '7021db7f2d47d4fff89b13177cb1e8f4',
+        'md5': '7b391cce85e758fb94f763ddc1bbb979',
         'info_dict': {
             'id': 'one-time-pad',
-            'ext': 'mp4',
+            'ext': 'webm',
             'title': 'The one-time pad',
             'description': 'The perfect cipher',
             'duration': 176,

youtube_dl/extractor/kusi.py

@@ -0,0 +1,99 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import random
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote_plus
+from ..utils import (
+    int_or_none,
+    float_or_none,
+    timeconvert,
+    update_url_query,
+    xpath_text,
+)
+
+
+class KUSIIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?kusi\.com/(?P<path>story/.+|video\?clipId=(?P<clipId>\d+))'
+    _TESTS = [{
+        'url': 'http://www.kusi.com/story/31183873/turko-files-case-closed-put-on-hold',
+        'md5': 'f926e7684294cf8cb7bdf8858e1b3988',
+        'info_dict': {
+            'id': '12203019',
+            'ext': 'mp4',
+            'title': 'Turko Files: Case Closed! & Put On Hold!',
+            'duration': 231.0,
+            'upload_date': '20160210',
+            'timestamp': 1455087571,
+            'thumbnail': 're:^https?://.*\.jpg$'
+        },
+    }, {
+        'url': 'http://kusi.com/video?clipId=12203019',
+        'info_dict': {
+            'id': '12203019',
+            'ext': 'mp4',
+            'title': 'Turko Files: Case Closed! & Put On Hold!',
+            'duration': 231.0,
+            'upload_date': '20160210',
+            'timestamp': 1455087571,
+            'thumbnail': 're:^https?://.*\.jpg$'
+        },
+        'params': {
+            'skip_download': True,  # Same as previous one
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        clip_id = mobj.group('clipId')
+        video_id = clip_id or mobj.group('path')
+
+        webpage = self._download_webpage(url, video_id)
+
+        if clip_id is None:
+            video_id = clip_id = self._html_search_regex(
+                r'"clipId"\s*,\s*"(\d+)"', webpage, 'clip id')
+
+        affiliate_id = self._search_regex(
+            r'affiliateId\s*:\s*\'([^\']+)\'', webpage, 'affiliate id')
+
+        # See __Packages/worldnow/model/GalleryModel.as of WNGallery.swf
+        xml_url = update_url_query('http://www.kusi.com/build.asp', {
+            'buildtype': 'buildfeaturexmlrequest',
+            'featureType': 'Clip',
+            'featureid': clip_id,
+            'affiliateno': affiliate_id,
+            'clientgroupid': '1',
+            'rnd': int(round(random.random() * 1000000)),
+        })
+
+        doc = self._download_xml(xml_url, video_id)
+
+        video_title = xpath_text(doc, 'HEADLINE', fatal=True)
+        duration = float_or_none(xpath_text(doc, 'DURATION'), scale=1000)
+        description = xpath_text(doc, 'ABSTRACT')
+        thumbnail = xpath_text(doc, './THUMBNAILIMAGE/FILENAME')
+        createtion_time = timeconvert(xpath_text(doc, 'rfc822creationdate'))
+
+        quality_options = doc.find('{http://search.yahoo.com/mrss/}group').findall('{http://search.yahoo.com/mrss/}content')
+        formats = []
+        for quality in quality_options:
+            formats.append({
+                'url': compat_urllib_parse_unquote_plus(quality.attrib['url']),
+                'height': int_or_none(quality.attrib.get('height')),
+                'width': int_or_none(quality.attrib.get('width')),
+                'vbr': float_or_none(quality.attrib.get('bitratebits'), scale=1000),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'description': description,
+            'duration': duration,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'timestamp': createtion_time,
+        }

youtube_dl/extractor/kuwo.py

@@ -68,6 +68,7 @@ class KuwoIE(KuwoBaseIE):
             'id': '6446136',
             'ext': 'mp3',
             'title': '心',
+            'description': 'md5:b2ab6295d014005bfc607525bfc1e38a',
             'creator': 'IU',
             'upload_date': '20150518',
         },

youtube_dl/extractor/laola1tv.py

@@ -1,86 +1,125 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
-import random
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urlparse,
+)
 from ..utils import (
     ExtractorError,
+    sanitized_Request,
+    unified_strdate,
+    urlencode_postdata,
+    xpath_element,
     xpath_text,
 )
 
 
 class Laola1TvIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/.*?/(?P<id>[0-9]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/[^/]+/(?P<slug>[^/?#&]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
         'info_dict': {
             'id': '227883',
-            'ext': 'mp4',
+            'display_id': 'straubing-tigers-koelner-haie',
+            'ext': 'flv',
             'title': 'Straubing Tigers - Kölner Haie',
-            'categories': ['Eishockey'],
+            'upload_date': '20140912',
             'is_live': False,
+            'categories': ['Eishockey'],
         },
         'params': {
             'skip_download': True,
         }
+    }, {
+        'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie',
+        'info_dict': {
+            'id': '464602',
+            'display_id': 'straubing-tigers-koelner-haie',
+            'ext': 'flv',
+            'title': 'Straubing Tigers - Kölner Haie',
+            'upload_date': '20160129',
+            'is_live': False,
+            'categories': ['Eishockey'],
+        },
+        'params': {
+            'skip_download': True,
         }
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        display_id = mobj.group('slug')
         lang = mobj.group('lang')
         portal = mobj.group('portal')
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, display_id)
-        iframe_url = self._search_regex(
-            r'<iframe[^>]*?class="main_tv_player"[^>]*?src="([^"]+)"',
-            webpage, 'iframe URL')
 
-        iframe = self._download_webpage(
+        iframe_url = self._search_regex(
-            iframe_url, video_id, note='Downloading iframe')
+            r'<iframe[^>]*?id="videoplayer"[^>]*?src="([^"]+)"',
-        flashvars_m = re.findall(
+            webpage, 'iframe url')
-            r'flashvars\.([_a-zA-Z0-9]+)\s*=\s*"([^"]*)";', iframe)
+
-        flashvars = dict((m[0], m[1]) for m in flashvars_m)
+        video_id = self._search_regex(
+            r'videoid=(\d+)', iframe_url, 'video id')
+
+        iframe = self._download_webpage(compat_urlparse.urljoin(
+            url, iframe_url), display_id, 'Downloading iframe')
 
         partner_id = self._search_regex(
-            r'partnerid\s*:\s*"([^"]+)"', iframe, 'partner id')
+            r'partnerid\s*:\s*(["\'])(?P<partner_id>.+?)\1',
+            iframe, 'partner id', group='partner_id')
 
-        xml_url = ('http://www.laola1.tv/server/hd_video.php?' +
+        hd_doc = self._download_xml(
-                   'play=%s&partner=%s&portal=%s&v5ident=&lang=%s' % (
+            'http://www.laola1.tv/server/hd_video.php?%s'
-                       video_id, partner_id, portal, lang))
+            % compat_urllib_parse.urlencode({
-        hd_doc = self._download_xml(xml_url, video_id)
+                'play': video_id,
+                'partner': partner_id,
+                'portal': portal,
+                'lang': lang,
+                'v5ident': '',
+            }), display_id)
 
-        title = xpath_text(hd_doc, './/video/title', fatal=True)
+        _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k)
-        flash_url = xpath_text(hd_doc, './/video/url', fatal=True)
+        title = _v('title', fatal=True)
-        uploader = xpath_text(hd_doc, './/video/meta_organistation')
-        is_live = xpath_text(hd_doc, './/video/islive') == 'true'
 
-        categories = xpath_text(hd_doc, './/video/meta_sports')
+        req = sanitized_Request(
-        if categories:
+            'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access?%s' %
-            categories = categories.split(',')
+            compat_urllib_parse.urlencode({
+                'videoId': video_id,
+                'target': '2',
+                'label': 'laola1tv',
+                'area': _v('area'),
+            }),
+            urlencode_postdata(
+                dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(',')))))
 
-        ident = random.randint(10000000, 99999999)
+        token_url = self._download_json(req, display_id)['data']['stream-access'][0]
-        token_url = '%s&ident=%s&klub=0&unikey=0&timestamp=%s&auth=%s' % (
+        token_doc = self._download_xml(token_url, display_id, 'Downloading token')
-            flash_url, ident, flashvars['timestamp'], flashvars['auth'])
 
-        token_doc = self._download_xml(
+        token_attrib = xpath_element(token_doc, './/token').attrib
-            token_url, video_id, note='Downloading token')
+        token_auth = token_attrib['auth']
-        token_attrib = token_doc.find('.//token').attrib
+
-        if token_attrib.get('auth') in ('blocked', 'restricted'):
+        if token_auth in ('blocked', 'restricted', 'error'):
             raise ExtractorError(
-                'Token error: %s' % token_attrib.get('comment'), expected=True)
+                'Token error: %s' % token_attrib['comment'], expected=True)
 
-        video_url = '%s?hdnea=%s&hdcore=3.2.0' % (
+        formats = self._extract_f4m_formats(
-            token_attrib['url'], token_attrib['auth'])
+            '%s?hdnea=%s&hdcore=3.2.0' % (token_attrib['url'], token_auth),
+            video_id, f4m_id='hds')
+
+        categories_str = _v('meta_sports')
+        categories = categories_str.split(',') if categories_str else []
 
         return {
             'id': video_id,
-            'is_live': is_live,
+            'display_id': display_id,
             'title': title,
-            'url': video_url,
+            'upload_date': unified_strdate(_v('time_date')),
-            'uploader': uploader,
+            'uploader': _v('meta_organisation'),
             'categories': categories,
-            'ext': 'mp4',
+            'is_live': _v('islive') == 'true',
+            'formats': formats,
         }

youtube_dl/extractor/leeco.py

@@ -1,36 +1,39 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import base64
 import datetime
+import hashlib
 import re
 import time
-import base64
-import hashlib
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
     compat_ord,
     compat_str,
+    compat_urllib_parse,
 )
 from ..utils import (
     determine_ext,
+    encode_data_uri,
     ExtractorError,
+    int_or_none,
+    orderedSet,
     parse_iso8601,
     sanitized_Request,
-    int_or_none,
     str_or_none,
-    encode_data_uri,
     url_basename,
 )
 
 
-class LetvIE(InfoExtractor):
+class LeIE(InfoExtractor):
     IE_DESC = '乐视网'
-    _VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P<id>\d+).html'
+    _VALID_URL = r'http://www\.le\.com/ptv/vplay/(?P<id>\d+)\.html'
+
+    _URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html'
 
     _TESTS = [{
-        'url': 'http://www.letv.com/ptv/vplay/22005890.html',
+        'url': 'http://www.le.com/ptv/vplay/22005890.html',
         'md5': 'edadcfe5406976f42f9f266057ee5e40',
         'info_dict': {
             'id': '22005890',
@@ -42,7 +45,7 @@ class LetvIE(InfoExtractor):
             'hls_prefer_native': True,
         },
     }, {
-        'url': 'http://www.letv.com/ptv/vplay/1415246.html',
+        'url': 'http://www.le.com/ptv/vplay/1415246.html',
         'info_dict': {
             'id': '1415246',
             'ext': 'mp4',
@@ -54,7 +57,7 @@ class LetvIE(InfoExtractor):
         },
     }, {
         'note': 'This video is available only in Mainland China, thus a proxy is needed',
-        'url': 'http://www.letv.com/ptv/vplay/1118082.html',
+        'url': 'http://www.le.com/ptv/vplay/1118082.html',
         'md5': '2424c74948a62e5f31988438979c5ad1',
         'info_dict': {
             'id': '1118082',
@@ -94,17 +97,16 @@ class LetvIE(InfoExtractor):
             return encrypted_data
         encrypted_data = encrypted_data[5:]
 
-        _loc4_ = bytearray()
+        _loc4_ = bytearray(2 * len(encrypted_data))
-        while encrypted_data:
+        for idx, val in enumerate(encrypted_data):
-            b = compat_ord(encrypted_data[0])
+            b = compat_ord(val)
-            _loc4_.extend([b // 16, b & 0x0f])
+            _loc4_[2 * idx] = b // 16
-            encrypted_data = encrypted_data[1:]
+            _loc4_[2 * idx + 1] = b % 16
         idx = len(_loc4_) - 11
         _loc4_ = _loc4_[idx:] + _loc4_[:idx]
-        _loc7_ = bytearray()
+        _loc7_ = bytearray(len(encrypted_data))
-        while _loc4_:
+        for i in range(len(encrypted_data)):
-            _loc7_.append(_loc4_[0] * 16 + _loc4_[1])
+            _loc7_[i] = _loc4_[2 * i] * 16 + _loc4_[2 * i + 1]
-            _loc4_ = _loc4_[2:]
 
         return bytes(_loc7_)
 
@@ -117,10 +119,10 @@ class LetvIE(InfoExtractor):
             'splatid': 101,
             'format': 1,
             'tkey': self.calc_time_key(int(time.time())),
-            'domain': 'www.letv.com'
+            'domain': 'www.le.com'
         }
         play_json_req = sanitized_Request(
-            'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
+            'http://api.le.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
         )
         cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
         if cn_verification_proxy:
@@ -193,26 +195,51 @@ class LetvIE(InfoExtractor):
         }
 
 
-class LetvTvIE(InfoExtractor):
+class LePlaylistIE(InfoExtractor):
-    _VALID_URL = r'http://www.letv.com/tv/(?P<id>\d+).html'
+    _VALID_URL = r'http://[a-z]+\.le\.com/[a-z]+/(?P<id>[a-z0-9_]+)'
+
     _TESTS = [{
-        'url': 'http://www.letv.com/tv/46177.html',
+        'url': 'http://www.le.com/tv/46177.html',
         'info_dict': {
             'id': '46177',
             'title': '美人天下',
             'description': 'md5:395666ff41b44080396e59570dbac01c'
         },
         'playlist_count': 35
+    }, {
+        'url': 'http://tv.le.com/izt/wuzetian/index.html',
+        'info_dict': {
+            'id': 'wuzetian',
+            'title': '武媚娘传奇',
+            'description': 'md5:e12499475ab3d50219e5bba00b3cb248'
+        },
+        # This playlist contains some extra videos other than the drama itself
+        'playlist_mincount': 96
+    }, {
+        'url': 'http://tv.le.com/pzt/lswjzzjc/index.shtml',
+        # This series is moved to http://www.le.com/tv/10005297.html
+        'only_matching': True,
+    }, {
+        'url': 'http://www.le.com/comic/92063.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://list.le.com/listn/c1009_sc532002_d2_p1_o1.html',
+        'only_matching': True,
     }]
 
+    @classmethod
+    def suitable(cls, url):
+        return False if LeIE.suitable(url) else super(LePlaylistIE, cls).suitable(url)
+
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
         page = self._download_webpage(url, playlist_id)
 
-        media_urls = list(set(re.findall(
+        # Currently old domain names are still used in playlists
-            r'http://www.letv.com/ptv/vplay/\d+.html', page)))
+        media_ids = orderedSet(re.findall(
-        entries = [self.url_result(media_url, ie='Letv')
+            r'<a[^>]+href="http://www\.letv\.com/ptv/vplay/(\d+)\.html', page))
-                   for media_url in media_urls]
+        entries = [self.url_result(LeIE._URL_TEMPLATE % media_id, ie='Le')
+                   for media_id in media_ids]
 
         title = self._html_search_meta('keywords', page,
                                        fatal=False).split('，')[0]
@@ -222,31 +249,9 @@ class LetvTvIE(InfoExtractor):
                                     playlist_description=description)
 
 
-class LetvPlaylistIE(LetvTvIE):
-    _VALID_URL = r'http://tv.letv.com/[a-z]+/(?P<id>[a-z]+)/index.s?html'
-    _TESTS = [{
-        'url': 'http://tv.letv.com/izt/wuzetian/index.html',
-        'info_dict': {
-            'id': 'wuzetian',
-            'title': '武媚娘传奇',
-            'description': 'md5:e12499475ab3d50219e5bba00b3cb248'
-        },
-        # This playlist contains some extra videos other than the drama itself
-        'playlist_mincount': 96
-    }, {
-        'url': 'http://tv.letv.com/pzt/lswjzzjc/index.shtml',
-        'info_dict': {
-            'id': 'lswjzzjc',
-            # The title should be "劲舞青春", but I can't find a simple way to
-            # determine the playlist title
-            'title': '乐视午间自制剧场',
-            'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489'
-        },
-        'playlist_mincount': 7
-    }]
-
-
 class LetvCloudIE(InfoExtractor):
+    # Most of *.letv.com is changed to *.le.com on 2016/01/02
+    # but yuntv.letv.com is kept, so also keep the extractor name
     IE_DESC = '乐视云'
     _VALID_URL = r'https?://yuntv\.letv\.com/bcloud.html\?.+'
 
@@ -327,7 +332,7 @@ class LetvCloudIE(InfoExtractor):
             formats.append({
                 'url': url,
                 'ext': determine_ext(decoded_url),
-                'format_id': int_or_none(play_url.get('vtype')),
+                'format_id': str_or_none(play_url.get('vtype')),
                 'format_note': str_or_none(play_url.get('definition')),
                 'width': int_or_none(play_url.get('vwidth')),
                 'height': int_or_none(play_url.get('vheight')),

youtube_dl/extractor/lifenews.py

@@ -20,18 +20,18 @@ class LifeNewsIE(InfoExtractor):
     _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?(?P<section>news|video)/(?P<id>\d+)'
 
     _TESTS = [{
-        'url': 'http://lifenews.ru/news/126342',
+        # single video embedded via video/source
-        'md5': 'e1b50a5c5fb98a6a544250f2e0db570a',
+        'url': 'http://lifenews.ru/news/98736',
+        'md5': '77c95eaefaca216e32a76a343ad89d23',
         'info_dict': {
-            'id': '126342',
+            'id': '98736',
             'ext': 'mp4',
-            'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом',
+            'title': 'Мужчина нашел дома архив оборонного завода',
-            'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.',
+            'description': 'md5:3b06b1b39b5e2bea548e403d99b8bf26',
-            'thumbnail': 're:http://.*\.jpg',
+            'upload_date': '20120805',
-            'upload_date': '20140130',
         }
     }, {
-        # video in <iframe>
+        # single video embedded via iframe
         'url': 'http://lifenews.ru/news/152125',
         'md5': '77d19a6f0886cd76bdbf44b4d971a273',
         'info_dict': {
@@ -42,15 +42,33 @@ class LifeNewsIE(InfoExtractor):
             'upload_date': '20150402',
         }
     }, {
+        # two videos embedded via iframe
         'url': 'http://lifenews.ru/news/153461',
-        'md5': '9b6ef8bc0ffa25aebc8bdb40d89ab795',
         'info_dict': {
             'id': '153461',
-            'ext': 'mp4',
             'title': 'В Москве спасли потерявшегося медвежонка, который спрятался на дереве',
             'description': 'Маленький хищник не смог найти дорогу домой и обрел временное убежище на тополе недалеко от жилого массива, пока его не нашла соседская собака.',
             'upload_date': '20150505',
-        }
+        },
+        'playlist': [{
+            'md5': '9b6ef8bc0ffa25aebc8bdb40d89ab795',
+            'info_dict': {
+                'id': '153461-video1',
+                'ext': 'mp4',
+                'title': 'В Москве спасли потерявшегося медвежонка, который спрятался на дереве (Видео 1)',
+                'description': 'Маленький хищник не смог найти дорогу домой и обрел временное убежище на тополе недалеко от жилого массива, пока его не нашла соседская собака.',
+                'upload_date': '20150505',
+            },
+        }, {
+            'md5': 'ebb3bf3b1ce40e878d0d628e93eb0322',
+            'info_dict': {
+                'id': '153461-video2',
+                'ext': 'mp4',
+                'title': 'В Москве спасли потерявшегося медвежонка, который спрятался на дереве (Видео 2)',
+                'description': 'Маленький хищник не смог найти дорогу домой и обрел временное убежище на тополе недалеко от жилого массива, пока его не нашла соседская собака.',
+                'upload_date': '20150505',
+            },
+        }],
     }, {
         'url': 'http://lifenews.ru/video/13035',
         'only_matching': True,
@@ -65,10 +83,14 @@ class LifeNewsIE(InfoExtractor):
             'http://lifenews.ru/%s/%s' % (section, video_id),
             video_id, 'Downloading page')
 
-        videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage)
+        video_urls = re.findall(
-        iframe_link = self._html_search_regex(
+            r'<video[^>]+><source[^>]+src=["\'](.+?)["\']', webpage)
-            '<iframe[^>]+src=["\']([^"\']+)["\']', webpage, 'iframe link', default=None)
+
-        if not videos and not iframe_link:
+        iframe_links = re.findall(
+            r'<iframe[^>]+src=["\']((?:https?:)?//embed\.life\.ru/embed/.+?)["\']',
+            webpage)
+
+        if not video_urls and not iframe_links:
             raise ExtractorError('No media links available for %s' % video_id)
 
         title = remove_end(
@@ -95,31 +117,44 @@ class LifeNewsIE(InfoExtractor):
             'upload_date': upload_date,
         }
 
-        def make_entry(video_id, media, video_number=None):
+        def make_entry(video_id, video_url, index=None):
             cur_info = dict(common_info)
             cur_info.update({
-                'id': video_id,
+                'id': video_id if not index else '%s-video%s' % (video_id, index),
-                'url': media[1],
+                'url': video_url,
-                'thumbnail': media[0],
+                'title': title if not index else '%s (Видео %s)' % (title, index),
-                'title': title if video_number is None else '%s-video%s' % (title, video_number),
             })
             return cur_info
 
-        if iframe_link:
+        def make_video_entry(video_id, video_url, index=None):
-            iframe_link = self._proto_relative_url(iframe_link, 'http:')
+            video_url = compat_urlparse.urljoin(url, video_url)
-            cur_info = dict(common_info)
+            return make_entry(video_id, video_url, index)
-            cur_info.update({
+
-                '_type': 'url_transparent',
+        def make_iframe_entry(video_id, video_url, index=None):
-                'id': video_id,
+            video_url = self._proto_relative_url(video_url, 'http:')
-                'title': title,
+            cur_info = make_entry(video_id, video_url, index)
-                'url': iframe_link,
+            cur_info['_type'] = 'url_transparent'
-            })
             return cur_info
 
-        if len(videos) == 1:
+        if len(video_urls) == 1 and not iframe_links:
-            return make_entry(video_id, videos[0])
+            return make_video_entry(video_id, video_urls[0])
-        else:
+
-            return [make_entry(video_id, media, video_number + 1) for video_number, media in enumerate(videos)]
+        if len(iframe_links) == 1 and not video_urls:
+            return make_iframe_entry(video_id, iframe_links[0])
+
+        entries = []
+
+        if video_urls:
+            for num, video_url in enumerate(video_urls, 1):
+                entries.append(make_video_entry(video_id, video_url, num))
+
+        if iframe_links:
+            for num, iframe_link in enumerate(iframe_links, len(video_urls) + 1):
+                entries.append(make_iframe_entry(video_id, iframe_link, num))
+
+        playlist = common_info.copy()
+        playlist.update(self.playlist_result(entries, video_id, title, description))
+        return playlist
 
 
 class LifeEmbedIE(InfoExtractor):

youtube_dl/extractor/liveleak.py

@@ -47,7 +47,7 @@ class LiveLeakIE(InfoExtractor):
         'info_dict': {
             'id': '801_1409392012',
             'ext': 'mp4',
-            'description': "Happened on 27.7.2014. \r\nAt 0:53 you can see people still swimming at near beach.",
+            'description': 'Happened on 27.7.2014. \r\nAt 0:53 you can see people still swimming at near beach.',
             'uploader': 'bony333',
             'title': 'Crazy Hungarian tourist films close call waterspout in Croatia'
         }

youtube_dl/extractor/livestream.py

@@ -14,6 +14,7 @@ from ..utils import (
     xpath_with_ns,
     xpath_text,
     orderedSet,
+    update_url_query,
     int_or_none,
     float_or_none,
     parse_iso8601,
@@ -64,7 +65,7 @@ class LivestreamIE(InfoExtractor):
     def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
         base_ele = find_xpath_attr(
             smil, self._xpath_ns('.//meta', namespace), 'name', 'httpBase')
-        base = base_ele.get('content') if base_ele else 'http://livestreamvod-f.akamaihd.net/'
+        base = base_ele.get('content') if base_ele is not None else 'http://livestreamvod-f.akamaihd.net/'
 
         formats = []
         video_nodes = smil.findall(self._xpath_ns('.//video', namespace))
@@ -72,7 +73,10 @@ class LivestreamIE(InfoExtractor):
         for vn in video_nodes:
             tbr = int_or_none(vn.attrib.get('system-bitrate'), 1000)
             furl = (
-                '%s%s?v=3.0.3&fp=WIN%%2014,0,0,145' % (base, vn.attrib['src']))
+                update_url_query(compat_urlparse.urljoin(base, vn.attrib['src']), {
+                    'v': '3.0.3',
+                    'fp': 'WIN% 14,0,0,145',
+                }))
             if 'clipBegin' in vn.attrib:
                 furl += '&ssek=' + vn.attrib['clipBegin']
             formats.append({

youtube_dl/extractor/makerschannel.py

@@ -0,0 +1,40 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class MakersChannelIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?makerschannel\.com/.*(?P<id_type>video|production)_id=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://makerschannel.com/en/zoomin/community-highlights?video_id=849',
+        'md5': '624a512c6969236b5967bf9286345ad1',
+        'info_dict': {
+            'id': '849',
+            'ext': 'mp4',
+            'title': 'Landing a bus on a plane is an epic win',
+            'uploader': 'ZoomIn',
+            'description': 'md5:cd9cca2ea7b69b78be81d07020c97139',
+        }
+    }
+
+    def _real_extract(self, url):
+        id_type, url_id = re.match(self._VALID_URL, url).groups()
+        webpage = self._download_webpage(url, url_id)
+        video_data = self._html_search_regex(r'<div([^>]+data-%s-id="%s"[^>]+)>' % (id_type, url_id), webpage, 'video data')
+
+        def extract_data_val(attr, fatal=False):
+            return self._html_search_regex(r'data-%s\s*=\s*"([^"]+)"' % attr, video_data, attr, fatal=fatal)
+        minoto_id = self._search_regex(r'/id/([a-zA-Z0-9]+)', extract_data_val('video-src', True), 'minoto id')
+
+        return {
+            '_type': 'url_transparent',
+            'url': 'minoto:%s' % minoto_id,
+            'id': extract_data_val('video-id', True),
+            'title': extract_data_val('title', True),
+            'description': extract_data_val('description'),
+            'thumbnail': extract_data_val('image'),
+            'uploader': extract_data_val('channel'),
+        }

youtube_dl/extractor/mdr.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 class MDRIE(InfoExtractor):
     IE_DESC = 'MDR.DE and KiKA'
-    _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+(?P<id>\d+)(?:_.+?)?\.html'
+    _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+-?(?P<id>\d+)(?:_.+?)?\.html'
 
     _TESTS = [{
         # MDR regularly deletes its videos
@@ -60,6 +60,9 @@ class MDRIE(InfoExtractor):
     }, {
         'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html',
         'only_matching': True,
+    }, {
+        'url': 'http://www.mdr.de/mediathek/mdr-videos/a/video-1334.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -68,8 +71,8 @@ class MDRIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         data_url = self._search_regex(
-            r'dataURL\s*:\s*(["\'])(?P<url>/.+/(?:video|audio)[0-9]+-avCustom\.xml)\1',
+            r'(?:dataURL|playerXml(?:["\'])?)\s*:\s*(["\'])(?P<url>\\?/.+/(?:video|audio)-?[0-9]+-avCustom\.xml)\1',
-            webpage, 'data url', group='url')
+            webpage, 'data url', default=None, group='url').replace('\/', '/')
 
         doc = self._download_xml(
             compat_urlparse.urljoin(url, data_url), video_id)

youtube_dl/extractor/minoto.py

@@ -0,0 +1,56 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class MinotoIE(InfoExtractor):
+    _VALID_URL = r'(?:minoto:|https?://(?:play|iframe|embed)\.minoto-video\.com/(?P<player_id>[0-9]+)/)(?P<id>[a-zA-Z0-9]+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        player_id = mobj.group('player_id') or '1'
+        video_id = mobj.group('id')
+        video_data = self._download_json('http://play.minoto-video.com/%s/%s.js' % (player_id, video_id), video_id)
+        video_metadata = video_data['video-metadata']
+        formats = []
+        for fmt in video_data['video-files']:
+            fmt_url = fmt.get('url')
+            if not fmt_url:
+                continue
+            container = fmt.get('container')
+            if container == 'hls':
+                formats.extend(fmt_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+            else:
+                fmt_profile = fmt.get('profile') or {}
+                f = {
+                    'format_id': fmt_profile.get('name-short'),
+                    'format_note': fmt_profile.get('name'),
+                    'url': fmt_url,
+                    'container': container,
+                    'tbr': int_or_none(fmt.get('bitrate')),
+                    'filesize': int_or_none(fmt.get('filesize')),
+                    'width': int_or_none(fmt.get('width')),
+                    'height': int_or_none(fmt.get('height')),
+                }
+                codecs = fmt.get('codecs')
+                if codecs:
+                    codecs = codecs.split(',')
+                    if len(codecs) == 2:
+                        f.update({
+                            'vcodec': codecs[0],
+                            'acodec': codecs[1],
+                        })
+                formats.append(f)
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_metadata['title'],
+            'description': video_metadata.get('description'),
+            'thumbnail': video_metadata.get('video-poster', {}).get('url'),
+            'formats': formats,
+        }

youtube_dl/extractor/mit.py

@@ -99,7 +99,7 @@ class OCWMITIE(InfoExtractor):
             'url': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/',
             'info_dict': {
                 'id': 'EObHWIEKGjA',
-                'ext': 'mp4',
+                'ext': 'webm',
                 'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence',
                 'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
                 'upload_date': '20121109',

youtube_dl/extractor/mixcloud.py

@@ -7,6 +7,7 @@ from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     ExtractorError,
     HEADRequest,
+    parse_count,
     str_to_int,
 )
 
@@ -85,8 +86,8 @@ class MixcloudIE(InfoExtractor):
         uploader_id = self._search_regex(
             r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
         description = self._og_search_description(webpage)
-        like_count = str_to_int(self._search_regex(
+        like_count = parse_count(self._search_regex(
-            r'\bbutton-favorite\b[^>]+m-ajax-toggle-count="([^"]+)"',
+            r'\bbutton-favorite[^>]+>.*?<span[^>]+class=["\']toggle-number[^>]+>\s*([^<]+)',
             webpage, 'like count', fatal=False))
         view_count = str_to_int(self._search_regex(
             [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',

youtube_dl/extractor/mofosex.py

@@ -38,7 +38,7 @@ class MofosexIE(InfoExtractor):
         path = compat_urllib_parse_urlparse(video_url).path
         extension = os.path.splitext(path)[1][1:]
         format = path.split('/')[5].split('_')[:2]
-        format = "-".join(format)
+        format = '-'.join(format)
 
         age_limit = self._rta_search(webpage)
 

youtube_dl/extractor/motherless.py

@@ -5,6 +5,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     str_to_int,
     unified_strdate,
 )
@@ -12,8 +13,7 @@ from ..utils import (
 
 class MotherlessIE(InfoExtractor):
     _VALID_URL = r'http://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
-    _TESTS = [
+    _TESTS = [{
-        {
         'url': 'http://motherless.com/AC3FFE1',
         'md5': '310f62e325a9fafe64f68c0bccb6e75f',
         'info_dict': {
@@ -26,22 +26,22 @@ class MotherlessIE(InfoExtractor):
             'thumbnail': 're:http://.*\.jpg',
             'age_limit': 18,
         }
-        },
+    }, {
-        {
         'url': 'http://motherless.com/532291B',
         'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
         'info_dict': {
             'id': '532291B',
             'ext': 'mp4',
             'title': 'Amazing girl playing the omegle game, PERFECT!',
-                'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', 'game', 'hairy'],
+            'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen',
+                           'game', 'hairy'],
             'upload_date': '20140622',
             'uploader_id': 'Sulivana7x',
             'thumbnail': 're:http://.*\.jpg',
             'age_limit': 18,
-            }
         },
-        {
+        'skip': '404',
+    }, {
         'url': 'http://motherless.com/g/cosplay/633979F',
         'md5': '0b2a43f447a49c3e649c93ad1fafa4a0',
         'info_dict': {
@@ -54,13 +54,21 @@ class MotherlessIE(InfoExtractor):
             'thumbnail': 're:http://.*\.jpg',
             'age_limit': 18,
         }
-        }
+    }, {
-    ]
+        # no keywords
+        'url': 'http://motherless.com/8B4BBC1',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
+        if any(p in webpage for p in (
+                '<title>404 - MOTHERLESS.COM<',
+                ">The page you're looking for cannot be found.<")):
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
         title = self._html_search_regex(
             r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
         video_url = self._html_search_regex(
@@ -86,7 +94,7 @@ class MotherlessIE(InfoExtractor):
             r'"thumb-member-username">\s+<a href="/m/([^"]+)"',
             webpage, 'uploader_id')
 
-        categories = self._html_search_meta('keywords', webpage)
+        categories = self._html_search_meta('keywords', webpage, default=None)
         if categories:
             categories = [cat.strip() for cat in categories.split(',')]
 

youtube_dl/extractor/mtv.py

@@ -11,6 +11,7 @@ from ..utils import (
     ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
+    float_or_none,
     HEADRequest,
     sanitized_Request,
     unescapeHTML,
@@ -110,7 +111,8 @@ class MTVServicesInfoExtractor(InfoExtractor):
         uri = itemdoc.find('guid').text
         video_id = self._id_from_uri(uri)
         self.report_extraction(video_id)
-        mediagen_url = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content'))).attrib['url']
+        content_el = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content')))
+        mediagen_url = content_el.attrib['url']
         # Remove the templates, like &device={device}
         mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', mediagen_url)
         if 'acceptMethods' not in mediagen_url:
@@ -165,6 +167,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
             'id': video_id,
             'thumbnail': self._get_thumbnail_url(uri, itemdoc),
             'description': description,
+            'duration': float_or_none(content_el.attrib.get('duration')),
         }
 
     def _get_feed_query(self, uri):

youtube_dl/extractor/myspass.py

@@ -18,8 +18,8 @@ class MySpassIE(InfoExtractor):
         'info_dict': {
             'id': '11741',
             'ext': 'mp4',
-            "description": "Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?",
+            'description': 'Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?',
-            "title": "Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2",
+            'title': 'Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2',
         },
     }