release 2016.06.02

This is a Python bug fixed in 2.7.6 [1]

[1] https://github.com/rg3/youtube-dl/issues/9656#issuecomment-222968594

.github/ISSUE_TEMPLATE.md

@@ -0,0 +1,58 @@
+## Please follow the guide below
+
+- You will be asked some questions and requested to provide some information, please read them **carefully** and answer honestly
+- Put an `x` into all the boxes [ ] relevant to your *issue* (like that [x])
+- Use *Preview* tab to see how your issue will actually look like
+
+---
+
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.02*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.06.02**
+
+### Before submitting an *issue* make sure you have:
+- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
+- [ ] [Searched](https://github.com/rg3/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones
+
+### What is the purpose of your *issue*?
+- [ ] Bug report (encountered problems with youtube-dl)
+- [ ] Site support request (request for adding support for a new site)
+- [ ] Feature request (request for a new functionality)
+- [ ] Question
+- [ ] Other
+
+---
+
+### The following sections concretize particular purposed issues, you can erase any section (the contents between triple ---) not applicable to your *issue*
+
+---
+
+### If the purpose of this *issue* is a *bug report*, *site support request* or you are not completely sure provide the full verbose output as follows:
+
+Add `-v` flag to **your command line** you run youtube-dl with, copy the **whole** output and insert it here. It should look similar to one below (replace it with **your** log inserted between triple ```):
+```
+$ 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']
+[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
+[debug] youtube-dl version 2016.06.02
+[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
+[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
+[debug] Proxy map: {}
+...
+<end of log>
+```
+
+---
+
+### If the purpose of this *issue* is a *site support request* please provide all kinds of example URLs support for which should be included (replace following example URLs by **yours**):
+- Single video: https://www.youtube.com/watch?v=BaW_jenozKc
+- Single video: https://youtu.be/BaW_jenozKc
+- Playlist: https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc
+
+---
+
+### Description of your *issue*, suggested solution and other information
+
+Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
+If work on your *issue* required an account credentials please provide them or explain how one can obtain them.

.github/ISSUE_TEMPLATE_tmpl.md

@@ -0,0 +1,58 @@
+## Please follow the guide below
+
+- You will be asked some questions and requested to provide some information, please read them **carefully** and answer honestly
+- Put an `x` into all the boxes [ ] relevant to your *issue* (like that [x])
+- Use *Preview* tab to see how your issue will actually look like
+
+---
+
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *%(version)s*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **%(version)s**
+
+### Before submitting an *issue* make sure you have:
+- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
+- [ ] [Searched](https://github.com/rg3/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones
+
+### What is the purpose of your *issue*?
+- [ ] Bug report (encountered problems with youtube-dl)
+- [ ] Site support request (request for adding support for a new site)
+- [ ] Feature request (request for a new functionality)
+- [ ] Question
+- [ ] Other
+
+---
+
+### The following sections concretize particular purposed issues, you can erase any section (the contents between triple ---) not applicable to your *issue*
+
+---
+
+### If the purpose of this *issue* is a *bug report*, *site support request* or you are not completely sure provide the full verbose output as follows:
+
+Add `-v` flag to **your command line** you run youtube-dl with, copy the **whole** output and insert it here. It should look similar to one below (replace it with **your** log inserted between triple ```):
+```
+$ 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']
+[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
+[debug] youtube-dl version %(version)s
+[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
+[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
+[debug] Proxy map: {}
+...
+<end of log>
+```
+
+---
+
+### If the purpose of this *issue* is a *site support request* please provide all kinds of example URLs support for which should be included (replace following example URLs by **yours**):
+- Single video: https://www.youtube.com/watch?v=BaW_jenozKc
+- Single video: https://youtu.be/BaW_jenozKc
+- Playlist: https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc
+
+---
+
+### Description of your *issue*, suggested solution and other information
+
+Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
+If work on your *issue* required an account credentials please provide them or explain how one can obtain them.

.gitignore

@@ -1,5 +1,6 @@
 *.pyc
 *.pyo
+*.class
 *~
 *.DS_Store
 wine-py2exe/
@@ -12,6 +13,7 @@ README.txt
 youtube-dl.1
 youtube-dl.bash-completion
 youtube-dl.fish
+youtube_dl/extractor/lazy_extractors.py
 youtube-dl
 youtube-dl.exe
 youtube-dl.tar.gz
@@ -26,10 +28,16 @@ updates_key.pem
 *.mp4
 *.m4a
 *.m4v
+*.mp3
 *.part
 *.swp
 test/testdata
+test/local_parameters.json
 .tox
 youtube-dl.zsh
+
+# IntelliJ related files
 .idea
-.idea/*
+*.iml
+
+tmp/

.travis.yml

@@ -7,11 +7,13 @@ python:
   - "3.4"
   - "3.5"
 sudo: false
+install:
+  - bash ./devscripts/install_srelay.sh
+  - export PATH=$PATH:$(pwd)/tmp/srelay-0.4.8b6
 script: nosetests test --verbose
 notifications:
   email:
     - filippo.valsorda@gmail.com
-    - phihag@phihag.de
     - yasoob.khld@gmail.com
 #  irc:
 #    channels:

AUTHORS

@@ -161,3 +161,15 @@ Jens Wille
 Robin Houtevelts
 Patrick Griffis
 Aidan Rowe
+mutantmonkey
+Ben Congdon
+Kacper Michajłow
+José Joaquín Atria
+Viťas Strádal
+Kagami Hiiragi
+Philip Huppert
+blahgeek
+Kevin Deldycke
+inondle
+Tomáš Čech
+Déstin Reed

CONTRIBUTING.md

@@ -85,7 +85,7 @@ To run the test, simply invoke your favorite test runner, or execute a test file
 If you want to create a build of youtube-dl yourself, you'll need
 
 * python
-* make
+* make (both GNU make and BSD make are supported)
 * pandoc
 * zip
 * nosetests
@@ -140,14 +140,14 @@ After you have ensured this site is distributing it's content legally, you can f
                 # TODO more properties (see youtube_dl/extractor/common.py)
             }
     ```
-5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
+5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.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/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want.
 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. 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/extractors.py
         $ git add youtube_dl/extractor/yourextractor.py
         $ git commit -m '[yourextractor] Add new extractor'
         $ git push origin yourextractor

Makefile

@@ -1,8 +1,9 @@
 all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
 
 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
+	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 youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
 	find . -name "*.pyc" -delete
+	find . -name "*.class" -delete
 
 PREFIX ?= /usr/local
 BINDIR ?= $(PREFIX)/bin
@@ -11,15 +12,7 @@ SHAREDIR ?= $(PREFIX)/share
 PYTHON ?= /usr/bin/env python
 
 # set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
-ifeq ($(PREFIX),/usr)
-	SYSCONFDIR=/etc
-else
-	ifeq ($(PREFIX),/usr/local)
-		SYSCONFDIR=/etc
-	else
-		SYSCONFDIR=$(PREFIX)/etc
-	endif
-endif
+SYSCONFDIR != if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi
 
 install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
 	install -d $(DESTDIR)$(BINDIR)
@@ -44,7 +37,7 @@ 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 --exclude test_iqiyi_sdk_interpreter.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 --exclude test_socks.py
 
 tar: youtube-dl.tar.gz
 
@@ -66,6 +59,9 @@ README.md: youtube_dl/*.py youtube_dl/*/*.py
 CONTRIBUTING.md: README.md
 	$(PYTHON) devscripts/make_contributing.py README.md CONTRIBUTING.md
 
+.github/ISSUE_TEMPLATE.md: devscripts/make_issue_template.py .github/ISSUE_TEMPLATE_tmpl.md  youtube_dl/version.py
+	$(PYTHON) devscripts/make_issue_template.py .github/ISSUE_TEMPLATE_tmpl.md .github/ISSUE_TEMPLATE.md
+
 supportedsites:
 	$(PYTHON) devscripts/make_supportedsites.py docs/supportedsites.md
 
@@ -73,7 +69,7 @@ README.txt: README.md
 	pandoc -f markdown -t plain README.md -o README.txt
 
 youtube-dl.1: README.md
-	$(PYTHON) devscripts/prepare_manpage.py >youtube-dl.1.temp.md
+	$(PYTHON) devscripts/prepare_manpage.py youtube-dl.1.temp.md
 	pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1
 	rm -f youtube-dl.1.temp.md
 
@@ -92,6 +88,12 @@ youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in
 
 fish-completion: youtube-dl.fish
 
+lazy-extractors: youtube_dl/extractor/lazy_extractors.py
+
+_EXTRACTOR_FILES != find youtube_dl/extractor -iname '*.py' -and -not -iname 'lazy_extractors.py'
+youtube_dl/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
+	$(PYTHON) devscripts/make_lazy_extractors.py $@
+
 youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
 	@tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \
 		--exclude '*.DS_Store' \

README.md

@@ -25,7 +25,7 @@ If you do not have curl, you can alternatively use a recent wget:
     sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl
     sudo chmod a+rx /usr/local/bin/youtube-dl
 
-Windows users can [download a .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in their home directory or any other location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29).
+Windows users can [download an .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in any location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29) except for `%SYSTEMROOT%\System32` (e.g. **do not** put in `C:\Windows\System32`).
 
 OS X users can install **youtube-dl** with [Homebrew](http://brew.sh/).
 
@@ -73,19 +73,23 @@ which means you can modify it, redistribute it or use it however you like.
                                      repairs broken URLs, but emits an error if
                                      this is not possible instead of searching.
     --ignore-config                  Do not read configuration files. When given
-                                     in the global configuration file /etc
-                                     /youtube-dl.conf: Do not read the user
+                                     in the global configuration file
+                                     /etc/youtube-dl.conf: Do not read the user
                                      configuration in ~/.config/youtube-
                                      dl/config (%APPDATA%/youtube-dl/config.txt
                                      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:
-    --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in
-                                     an empty string (--proxy "") for direct
-                                     connection
+    --proxy URL                      Use the specified HTTP/HTTPS/SOCKS proxy.
+                                     To enable experimental SOCKS proxy, specify
+                                     a proper scheme. For example
+                                     socks5://127.0.0.1:1080/. Pass in an empty
+                                     string (--proxy "") for direct connection
     --socket-timeout SECONDS         Time to wait before giving up, in seconds
     --source-address IP              Client-side IP address to bind to
                                      (experimental)
@@ -158,10 +162,12 @@ which means you can modify it, redistribute it or use it however you like.
                                      (experimental)
 
 ## Download Options:
-    -r, --rate-limit LIMIT           Maximum download rate in bytes per second
+    -r, --limit-rate RATE            Maximum download rate in bytes per second
                                      (e.g. 50K or 4.2M)
     -R, --retries RETRIES            Number of retries (default is 10), or
                                      "infinite".
+    --fragment-retries RETRIES       Number of retries for a fragment (default
+                                     is 10), or "infinite" (DASH only)
     --buffer-size SIZE               Size of download buffer (e.g. 1024 or 16K)
                                      (default is 1024)
     --no-resize-buffer               Do not automatically adjust the buffer
@@ -172,14 +178,16 @@ which means you can modify it, redistribute it or use it however you like.
     --xattr-set-filesize             Set file xattribute ytdl.filesize with
                                      expected filesize (experimental)
     --hls-prefer-native              Use the native HLS downloader instead of
-                                     ffmpeg (experimental)
+                                     ffmpeg
+    --hls-prefer-ffmpeg              Use ffmpeg instead of the native HLS
+                                     downloader
     --hls-use-mpegts                 Use the mpegts container for HLS videos,
                                      allowing to play the video while
                                      downloading (some players may not be able
                                      to play it)
     --external-downloader COMMAND    Use the specified external downloader.
                                      Currently supports
-                                     aria2c,axel,curl,httpie,wget
+                                     aria2c,avconv,axel,curl,ffmpeg,httpie,wget
     --external-downloader-args ARGS  Give these arguments to the external
                                      downloader
 
@@ -248,11 +256,12 @@ which means you can modify it, redistribute it or use it however you like.
                                      jar in
     --cache-dir DIR                  Location in the filesystem where youtube-dl
                                      can store some downloaded information
-                                     permanently. By default $XDG_CACHE_HOME
-                                     /youtube-dl or ~/.cache/youtube-dl . At the
-                                     moment, only YouTube player files (for
-                                     videos with obfuscated signatures) are
-                                     cached, but that may change.
+                                     permanently. By default
+                                     $XDG_CACHE_HOME/youtube-dl or
+                                     ~/.cache/youtube-dl . At the moment, only
+                                     YouTube player files (for videos with
+                                     obfuscated signatures) are cached, but that
+                                     may change.
     --no-cache-dir                   Disable filesystem caching
     --rm-cache-dir                   Delete all filesystem cache files
 
@@ -374,8 +383,8 @@ which means you can modify it, redistribute it or use it however you like.
     --no-post-overwrites             Do not overwrite post-processed files; the
                                      post-processed files are overwritten by
                                      default
-    --embed-subs                     Embed subtitles in the video (only for mkv
-                                     and mp4 videos)
+    --embed-subs                     Embed subtitles in the video (only for mp4,
+                                     webm and mkv videos)
     --embed-thumbnail                Embed thumbnail in the audio as cover art
     --add-metadata                   Write metadata to the video file
     --metadata-from-title FORMAT     Parse additional metadata like song title /
@@ -409,18 +418,23 @@ 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 and OS X, 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
 
-You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create a`.netrc` file in your `$HOME` and restrict permissions to read/write by you only:
+You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create a `.netrc` file in your `$HOME` and restrict permissions to read/write by you only:
 ```
 touch $HOME/.netrc
 chmod a-rwx,u+rw $HOME/.netrc
@@ -453,7 +467,8 @@ The basic usage is not to set any template arguments when downloading a single f
  - `alt_title`: A secondary title of the video
  - `display_id`: An alternative identifier for the video
  - `uploader`: Full name of the video uploader
- - `creator`: The main artist who created the video
+ - `license`: License name the video is licensed under
+ - `creator`: The creator of 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)
@@ -505,6 +520,18 @@ Available for the video that is an episode of some series or programme:
  - `episode_number`: Number of the video episode within a season
  - `episode_id`: Id of the video episode
 
+Available for the media that is a track or a part of a music album:
+ - `track`: Title of the track
+ - `track_number`: Number of the track within an album or a disc
+ - `track_id`: Id of the track
+ - `artist`: Artist(s) of the track
+ - `genre`: Genre(s) of the track
+ - `album`: Title of the album the track belongs to
+ - `album_type`: Type of the album
+ - `album_artist`: List of all artists appeared on the album
+ - `disc_number`: Number of the disc or other physical medium the track belongs to
+ - `release_year`: Year (YYYY) when the album was released
+
 Each aforementioned sequence when referenced in output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by particular extractor, such sequences will be replaced with `NA`.
 
 For example for `-o %(title)s-%(id)s.%(ext)s` and mp4 video with title `youtube-dl test video` and id `BaW_jenozKcj` this will result in a `youtube-dl test video-BaW_jenozKcj.mp4` file created in the current directory.
@@ -590,6 +617,7 @@ Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begin
  - `vcodec`: Name of the video codec in use
  - `container`: Name of the container format
  - `protocol`: The protocol that will be used for the actual download, lower-case. `http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `m3u8`, or `m3u8_native`
+ - `format_id`: A short description of the format
 
 Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by video hoster.
 
@@ -666,12 +694,20 @@ hash -r
 
 Again, from then on you'll be able to update with `sudo youtube-dl -U`.
 
+### youtube-dl is extremely slow to start on Windows
+
+Add a file exclusion for `youtube-dl.exe` in Windows Defender settings.
+
 ### I'm getting an error `Unable to extract OpenGraph title` on YouTube playlists
 
 YouTube changed their playlist format in March 2014 and later on, so you'll need at least youtube-dl 2014.07.25 to download all YouTube videos.
 
 If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to [report bugs](https://bugs.launchpad.net/ubuntu/+source/youtube-dl/+filebug) to the [Ubuntu packaging guys](mailto:ubuntu-motu@lists.ubuntu.com?subject=outdated%20version%20of%20youtube-dl) - all they have to do is update the package to a somewhat recent version. See above for a way to update.
 
+### I'm getting an error when trying to use output template: `error: using output template conflicts with using title, video ID or auto number`
+
+Make sure you are not using `-o` with any of these options `-t`, `--title`, `--id`, `-A` or `--auto-number` set in command line or in a configuration file. Remove the latter if any.
+
 ### Do I always have to pass `-citw`?
 
 By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, the only option out of `-citw` that is regularly useful is `-i`.
@@ -692,7 +728,7 @@ Videos or video formats streamed via RTMP protocol can only be downloaded when [
 
 ### I have downloaded a video but how can I play it?
 
-Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
+Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
 
 ### I extracted a video URL with `-g`, but it does not play on another machine / in my webbrowser.
 
@@ -749,9 +785,9 @@ means you're using an outdated version of Python. Please update to Python 2.6 or
 
 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++*
+### The exe throws an error due to missing `MSVCR100.dll`
 
-To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29).
+To run the exe you need to install first the [Microsoft Visual C++ 2010 Redistributable Package (x86)](https://www.microsoft.com/en-US/download/details.aspx?id=5555).
 
 ### On Windows, how should I set up ffmpeg and youtube-dl? Where should I put the exe files?
 
@@ -823,7 +859,7 @@ To run the test, simply invoke your favorite test runner, or execute a test file
 If you want to create a build of youtube-dl yourself, you'll need
 
 * python
-* make
+* make (both GNU make and BSD make are supported)
 * pandoc
 * zip
 * nosetests
@@ -878,14 +914,14 @@ After you have ensured this site is distributing it's content legally, you can f
                 # TODO more properties (see youtube_dl/extractor/common.py)
             }
     ```
-5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
+5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.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/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want.
 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. 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/extractors.py
         $ git add youtube_dl/extractor/yourextractor.py
         $ git commit -m '[yourextractor] Add new extractor'
         $ git push origin yourextractor

devscripts/buildserver.py

@@ -1,17 +1,42 @@
 #!/usr/bin/python3
 
-from http.server import HTTPServer, BaseHTTPRequestHandler
-from socketserver import ThreadingMixIn
 import argparse
 import ctypes
 import functools
+import shutil
+import subprocess
 import sys
+import tempfile
 import threading
 import traceback
 import os.path
 
+sys.path.insert(0, os.path.dirname(os.path.dirname((os.path.abspath(__file__)))))
+from youtube_dl.compat import (
+    compat_http_server,
+    compat_str,
+    compat_urlparse,
+)
 
-class BuildHTTPServer(ThreadingMixIn, HTTPServer):
+# These are not used outside of buildserver.py thus not in compat.py
+
+try:
+    import winreg as compat_winreg
+except ImportError:  # Python 2
+    import _winreg as compat_winreg
+
+try:
+    import socketserver as compat_socketserver
+except ImportError:  # Python 2
+    import SocketServer as compat_socketserver
+
+try:
+    compat_input = raw_input
+except NameError:  # Python 3
+    compat_input = input
+
+
+class BuildHTTPServer(compat_socketserver.ThreadingMixIn, compat_http_server.HTTPServer):
     allow_reuse_address = True
 
 
@@ -191,7 +216,7 @@ def main(args=None):
                         action='store_const', dest='action', const='service',
                         help='Run as a Windows service')
     parser.add_argument('-b', '--bind', metavar='<host:port>',
-                        action='store', default='localhost:8142',
+                        action='store', default='0.0.0.0:8142',
                         help='Bind to host:port (default %default)')
     options = parser.parse_args(args=args)
 
@@ -216,7 +241,7 @@ def main(args=None):
     srv = BuildHTTPServer((host, port), BuildHTTPRequestHandler)
     thr = threading.Thread(target=srv.serve_forever)
     thr.start()
-    input('Press ENTER to shut down')
+    compat_input('Press ENTER to shut down')
     srv.shutdown()
     thr.join()
 
@@ -231,8 +256,6 @@ def rmtree(path):
             os.remove(fname)
     os.rmdir(path)
 
-#==============================================================================
-
 
 class BuildError(Exception):
     def __init__(self, output, code=500):
@@ -249,15 +272,25 @@ class HTTPError(BuildError):
 
 class PythonBuilder(object):
     def __init__(self, **kwargs):
-        pythonVersion = kwargs.pop('python', '2.7')
-        try:
-            key = _winreg.OpenKey(_winreg.HKEY_LOCAL_MACHINE, r'SOFTWARE\Python\PythonCore\%s\InstallPath' % pythonVersion)
+        python_version = kwargs.pop('python', '3.4')
+        python_path = None
+        for node in ('Wow6432Node\\', ''):
             try:
-                self.pythonPath, _ = _winreg.QueryValueEx(key, '')
-            finally:
-                _winreg.CloseKey(key)
-        except Exception:
-            raise BuildError('No such Python version: %s' % pythonVersion)
+                key = compat_winreg.OpenKey(
+                    compat_winreg.HKEY_LOCAL_MACHINE,
+                    r'SOFTWARE\%sPython\PythonCore\%s\InstallPath' % (node, python_version))
+                try:
+                    python_path, _ = compat_winreg.QueryValueEx(key, '')
+                finally:
+                    compat_winreg.CloseKey(key)
+                break
+            except Exception:
+                pass
+
+        if not python_path:
+            raise BuildError('No such Python version: %s' % python_version)
+
+        self.pythonPath = python_path
 
         super(PythonBuilder, self).__init__(**kwargs)
 
@@ -305,8 +338,10 @@ class YoutubeDLBuilder(object):
 
     def build(self):
         try:
-            subprocess.check_output([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'],
-                                    cwd=self.buildPath)
+            proc = subprocess.Popen([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'], stdin=subprocess.PIPE, cwd=self.buildPath)
+            proc.wait()
+            #subprocess.check_output([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'],
+            #                        cwd=self.buildPath)
         except subprocess.CalledProcessError as e:
             raise BuildError(e.output)
 
@@ -369,12 +404,12 @@ class Builder(PythonBuilder, GITBuilder, YoutubeDLBuilder, DownloadBuilder, Clea
     pass
 
 
-class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
+class BuildHTTPRequestHandler(compat_http_server.BaseHTTPRequestHandler):
     actionDict = {'build': Builder, 'download': Builder}  # They're the same, no more caching.
 
     def do_GET(self):
-        path = urlparse.urlparse(self.path)
-        paramDict = dict([(key, value[0]) for key, value in urlparse.parse_qs(path.query).items()])
+        path = compat_urlparse.urlparse(self.path)
+        paramDict = dict([(key, value[0]) for key, value in compat_urlparse.parse_qs(path.query).items()])
         action, _, path = path.path.strip('/').partition('/')
         if path:
             path = path.split('/')
@@ -388,7 +423,7 @@ class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
                         builder.close()
                 except BuildError as e:
                     self.send_response(e.code)
-                    msg = unicode(e).encode('UTF-8')
+                    msg = compat_str(e).encode('UTF-8')
                     self.send_header('Content-Type', 'text/plain; charset=UTF-8')
                     self.send_header('Content-Length', len(msg))
                     self.end_headers()
@@ -400,7 +435,5 @@ class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
         else:
             self.send_response(500, 'Malformed URL')
 
-#==============================================================================
-
 if __name__ == '__main__':
     main()

devscripts/install_srelay.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+mkdir -p tmp && cd tmp
+wget -N http://downloads.sourceforge.net/project/socks-relay/socks-relay/srelay-0.4.8/srelay-0.4.8b6.tar.gz
+tar zxvf srelay-0.4.8b6.tar.gz
+cd srelay-0.4.8b6
+./configure
+make

devscripts/lazy_load_template.py

@@ -0,0 +1,19 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+
+class LazyLoadExtractor(object):
+    _module = None
+
+    @classmethod
+    def ie_key(cls):
+        return cls.__name__[:-2]
+
+    def __new__(cls, *args, **kwargs):
+        mod = __import__(cls._module, fromlist=(cls.__name__,))
+        real_cls = getattr(mod, cls.__name__)
+        instance = real_cls.__new__(real_cls)
+        instance.__init__(*args, **kwargs)
+        return instance

devscripts/make_issue_template.py

@@ -0,0 +1,29 @@
+#!/usr/bin/env python
+from __future__ import unicode_literals
+
+import io
+import optparse
+
+
+def main():
+    parser = optparse.OptionParser(usage='%prog INFILE OUTFILE')
+    options, args = parser.parse_args()
+    if len(args) != 2:
+        parser.error('Expected an input and an output filename')
+
+    infile, outfile = args
+
+    with io.open(infile, encoding='utf-8') as inf:
+        issue_template_tmpl = inf.read()
+
+    # Get the version from youtube_dl/version.py without importing the package
+    exec(compile(open('youtube_dl/version.py').read(),
+                 'youtube_dl/version.py', 'exec'))
+
+    out = issue_template_tmpl % {'version': locals()['__version__']}
+
+    with io.open(outfile, 'w', encoding='utf-8') as outf:
+        outf.write(out)
+
+if __name__ == '__main__':
+    main()

devscripts/make_lazy_extractors.py

@@ -0,0 +1,63 @@
+from __future__ import unicode_literals, print_function
+
+from inspect import getsource
+import os
+from os.path import dirname as dirn
+import sys
+
+print('WARNING: Lazy loading extractors is an experimental feature that may not always work', file=sys.stderr)
+
+sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
+
+lazy_extractors_filename = sys.argv[1]
+if os.path.exists(lazy_extractors_filename):
+    os.remove(lazy_extractors_filename)
+
+from youtube_dl.extractor import _ALL_CLASSES
+from youtube_dl.extractor.common import InfoExtractor
+
+with open('devscripts/lazy_load_template.py', 'rt') as f:
+    module_template = f.read()
+
+module_contents = [module_template + '\n' + getsource(InfoExtractor.suitable)]
+
+ie_template = '''
+class {name}(LazyLoadExtractor):
+    _VALID_URL = {valid_url!r}
+    _module = '{module}'
+'''
+
+make_valid_template = '''
+    @classmethod
+    def _make_valid_url(cls):
+        return {valid_url!r}
+'''
+
+
+def build_lazy_ie(ie, name):
+    valid_url = getattr(ie, '_VALID_URL', None)
+    s = ie_template.format(
+        name=name,
+        valid_url=valid_url,
+        module=ie.__module__)
+    if ie.suitable.__func__ is not InfoExtractor.suitable.__func__:
+        s += '\n' + getsource(ie.suitable)
+    if hasattr(ie, '_make_valid_url'):
+        # search extractors
+        s += make_valid_template.format(valid_url=ie._make_valid_url())
+    return s
+
+names = []
+for ie in list(sorted(_ALL_CLASSES[:-1], key=lambda cls: cls.ie_key())) + _ALL_CLASSES[-1:]:
+    name = ie.ie_key() + 'IE'
+    src = build_lazy_ie(ie, name)
+    module_contents.append(src)
+    names.append(name)
+
+module_contents.append(
+    '_ALL_CLASSES = [{0}]'.format(', '.join(names)))
+
+module_src = '\n'.join(module_contents) + '\n'
+
+with open(lazy_extractors_filename, 'wt') as f:
+    f.write(module_src)

devscripts/prepare_manpage.py

@@ -1,13 +1,46 @@
 from __future__ import unicode_literals
 
 import io
+import optparse
 import os.path
-import sys
 import re
 
 ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 README_FILE = os.path.join(ROOT_DIR, 'README.md')
 
+PREFIX = '''%YOUTUBE-DL(1)
+
+# NAME
+
+youtube\-dl \- download videos from youtube.com or other video platforms
+
+# SYNOPSIS
+
+**youtube-dl** \[OPTIONS\] URL [URL...]
+
+'''
+
+
+def main():
+    parser = optparse.OptionParser(usage='%prog OUTFILE.md')
+    options, args = parser.parse_args()
+    if len(args) != 1:
+        parser.error('Expected an output filename')
+
+    outfile, = args
+
+    with io.open(README_FILE, encoding='utf-8') as f:
+        readme = f.read()
+
+    readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme)
+    readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme)
+    readme = PREFIX + readme
+
+    readme = filter_options(readme)
+
+    with io.open(outfile, 'w', encoding='utf-8') as outf:
+        outf.write(readme)
+
 
 def filter_options(readme):
     ret = ''
@@ -37,27 +70,5 @@ def filter_options(readme):
 
     return ret
 
-with io.open(README_FILE, encoding='utf-8') as f:
-    readme = f.read()
-
-PREFIX = '''%YOUTUBE-DL(1)
-
-# NAME
-
-youtube\-dl \- download videos from youtube.com or other video platforms
-
-# SYNOPSIS
-
-**youtube-dl** \[OPTIONS\] URL [URL...]
-
-'''
-readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme)
-readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme)
-readme = PREFIX + readme
-
-readme = filter_options(readme)
-
-if sys.version_info < (3, 0):
-    print(readme.encode('utf-8'))
-else:
-    print(readme)
+if __name__ == '__main__':
+    main()

devscripts/release.sh

@@ -6,7 +6,7 @@
 # * the git config user.signingkey is properly set
 
 # You will need
-# pip install coverage nose rsa
+# pip install coverage nose rsa wheel
 
 # TODO
 # release notes
@@ -15,10 +15,28 @@
 set -e
 
 skip_tests=true
-if [ "$1" = '--run-tests' ]; then
-    skip_tests=false
-    shift
-fi
+buildserver='localhost:8142'
+
+while true
+do
+case "$1" in
+    --run-tests)
+        skip_tests=false
+        shift
+    ;;
+    --buildserver)
+        buildserver="$2"
+        shift 2
+    ;;
+    --*)
+        echo "ERROR: unknown option $1"
+        exit 1
+    ;;
+    *)
+        break
+    ;;
+esac
+done
 
 if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi
 version="$1"
@@ -33,6 +51,9 @@ if [ ! -z "`git status --porcelain | grep -v CHANGELOG`" ]; then echo 'ERROR: th
 useless_files=$(find youtube_dl -type f -not -name '*.py')
 if [ ! -z "$useless_files" ]; then echo "ERROR: Non-.py files in youtube_dl: $useless_files"; exit 1; fi
 if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi
+if ! type pandoc >/dev/null 2>/dev/null; then echo 'ERROR: pandoc is missing'; exit 1; fi
+if ! python3 -c 'import rsa' 2>/dev/null; then echo 'ERROR: python3-rsa is missing'; exit 1; fi
+if ! python3 -c 'import wheel' 2>/dev/null; then echo 'ERROR: wheel is missing'; exit 1; fi
 
 /bin/echo -e "\n### First of all, testing..."
 make clean
@@ -45,9 +66,9 @@ fi
 /bin/echo -e "\n### Changing version in version.py..."
 sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
 
-/bin/echo -e "\n### Committing documentation and youtube_dl/version.py..."
-make README.md CONTRIBUTING.md supportedsites
-git add README.md CONTRIBUTING.md docs/supportedsites.md youtube_dl/version.py
+/bin/echo -e "\n### Committing documentation, templates and youtube_dl/version.py..."
+make README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md supportedsites
+git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md docs/supportedsites.md youtube_dl/version.py
 git commit -m "release $version"
 
 /bin/echo -e "\n### Now tagging, signing and pushing..."
@@ -64,7 +85,7 @@ git push origin "$version"
 REV=$(git rev-parse HEAD)
 make youtube-dl youtube-dl.tar.gz
 read -p "VM running? (y/n) " -n 1
-wget "http://localhost:8142/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe
+wget "http://$buildserver/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe
 mkdir -p "build/$version"
 mv youtube-dl youtube-dl.exe "build/$version"
 mv youtube-dl.tar.gz "build/$version/youtube-dl-$version.tar.gz"

docs/supportedsites.md

@@ -6,6 +6,7 @@
  - **22tracks:genre**
  - **22tracks:track**
  - **24video**
+ - **3qsdn**: 3Q SDN
  - **3sat**
  - **4tube**
  - **56.com**
@@ -15,6 +16,8 @@
  - **9gag**
  - **abc.net.au**
  - **Abc7News**
+ - **abcnews**
+ - **abcnews:video**
  - **AcademicEarth:Course**
  - **acast**
  - **acast:channel**
@@ -40,8 +43,8 @@
  - **appletrailers:section**
  - **archive.org**: archive.org videos
  - **ARD**
- - **ARD:mediathek**: Saarländischer Rundfunk
  - **ARD:mediathek**
+ - **ARD:mediathek**: Saarländischer Rundfunk
  - **arte.tv**
  - **arte.tv:+7**
  - **arte.tv:cinema**
@@ -50,12 +53,16 @@
  - **arte.tv:ddc**
  - **arte.tv:embed**
  - **arte.tv:future**
+ - **arte.tv:info**
  - **arte.tv:magazine**
+ - **arte.tv:playlist**
  - **AtresPlayer**
  - **ATTTechChannel**
  - **AudiMedia**
+ - **AudioBoom**
  - **audiomack**
  - **audiomack:album**
+ - **auroravid**: AuroraVid
  - **Azubu**
  - **AzubuLive**
  - **BaiduVideo**: 百度视频
@@ -73,6 +80,8 @@
  - **Bigflix**
  - **Bild**: Bild.de
  - **BiliBili**
+ - **BioBioChileTV**
+ - **BIQLE**
  - **BleacherReport**
  - **BleacherReportCMS**
  - **blinkx**
@@ -80,6 +89,7 @@
  - **BokeCC**
  - **Bpb**: Bundeszentrale für politische Bildung
  - **BR**: Bayerischer Rundfunk Mediathek
+ - **BravoTV**
  - **Break**
  - **brightcove:legacy**
  - **brightcove:new**
@@ -89,15 +99,19 @@
  - **BYUtv**
  - **Camdemy**
  - **CamdemyFolder**
+ - **CamWithHer**
  - **canalc2.tv**
  - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
  - **Canvas**
  - **CBC**
  - **CBCPlayer**
  - **CBS**
+ - **CBSInteractive**
+ - **CBSLocal**
  - **CBSNews**: CBS News
  - **CBSNewsLiveVideo**: CBS News Live Videos
  - **CBSSports**
+ - **CDA**
  - **CeskaTelevize**
  - **channel9**: Channel 9
  - **Chaturbate**
@@ -105,36 +119,38 @@
  - **chirbit**
  - **chirbit:profile**
  - **Cinchcast**
- - **Cinemassacre**
  - **Clipfish**
  - **cliphunter**
+ - **ClipRs**
  - **Clipsyndicate**
  - **cloudtime**: CloudTime
  - **Cloudy**
  - **Clubic**
  - **Clyp**
  - **cmt.com**
- - **CNET**
+ - **CNBC**
  - **CNN**
  - **CNNArticle**
  - **CNNBlogs**
- - **CollegeHumor**
  - **CollegeRama**
  - **ComCarCoff**
  - **ComedyCentral**
  - **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
+ - **Coub**
  - **Cracked**
  - **Crackle**
  - **Criterion**
  - **CrooksAndLiars**
  - **Crunchyroll**
  - **crunchyroll:playlist**
+ - **CSNNE**
  - **CSpan**: C-SPAN
  - **CtsNews**: 華視新聞
  - **culturebox.francetvinfo.fr**
  - **CultureUnplugged**
  - **CWTV**
+ - **DailyMail**
  - **dailymotion**
  - **dailymotion:playlist**
  - **dailymotion:user**
@@ -153,6 +169,7 @@
  - **defense.gouv.fr**
  - **democracynow**
  - **DHM**: Filmarchiv - Deutsches Historisches Museum
+ - **DigitallySpeaking**
  - **Digiteka**
  - **Discovery**
  - **Dotsub**
@@ -164,9 +181,10 @@
  - **Dropbox**
  - **DrTuber**
  - **DRTV**
- - **Dump**
  - **Dumpert**
  - **dvtv**: http://video.aktualne.cz/
+ - **dw**
+ - **dw:article**
  - **EaglePlatform**
  - **EbaumsWorld**
  - **EchoMsk**
@@ -189,17 +207,19 @@
  - **exfm**: ex.fm
  - **ExpoTV**
  - **ExtremeTube**
+ - **EyedoTV**
  - **facebook**
- - **facebook:post**
  - **faz.net**
  - **fc2**
  - **Fczenit**
+ - **features.aol.com**
  - **fernsehkritik.tv**
  - **Firstpost**
  - **FiveTV**
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
  - **FootyRoom**
+ - **Formula1**
  - **FOX**
  - **Foxgay**
  - **FoxNews**: Fox News and Fox Business Video
@@ -240,6 +260,7 @@
  - **GPUTechConf**
  - **Groupon**
  - **Hark**
+ - **HBO**
  - **HearThisAt**
  - **Heise**
  - **HellPorno**
@@ -275,7 +296,6 @@
  - **ivi:compilation**: ivi.ru compilations
  - **ivideon**: Ivideon TV
  - **Izlesene**
- - **JadoreCettePub**
  - **JeuxVideo**
  - **Jove**
  - **jpopsuki.tv**
@@ -293,6 +313,7 @@
  - **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
@@ -301,22 +322,24 @@
  - **kuwo:song**: 酷我音乐
  - **la7.tv**
  - **Laola1Tv**
+ - **Le**: 乐视网
+ - **Learnr**
  - **Lecture2Go**
  - **Lemonde**
- - **Letv**: 乐视网
+ - **LePlaylist**
  - **LetvCloud**: 乐视云
- - **LetvPlaylist**
- - **LetvTv**
  - **Libsyn**
+ - **life**: Life.ru
  - **life:embed**
- - **lifenews**: LIFE | NEWS
  - **limelight**
  - **limelight:channel**
  - **limelight:channel_list**
+ - **LiTV**
  - **LiveLeak**
  - **livestream**
  - **livestream:original**
  - **LnkGo**
+ - **LocalNews8**
  - **LoveHomePorn**
  - **lrt.lt**
  - **lynda**: lynda.com videos
@@ -324,25 +347,30 @@
  - **m6**
  - **macgamestore**: MacGameStore trailers
  - **mailru**: Видео@Mail.Ru
+ - **MakersChannel**
  - **MakerTV**
- - **Malemotion**
  - **MatchTV**
  - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
  - **metacafe**
  - **Metacritic**
  - **Mgoon**
+ - **MGTV**: 芒果TV
  - **Minhateca**
  - **MinistryGrid**
+ - **Minoto**
  - **miomio.tv**
  - **MiTele**: mitele.es
  - **mixcloud**
+ - **mixcloud:playlist**
+ - **mixcloud:stream**
+ - **mixcloud:user**
  - **MLB**
+ - **Mnet**
  - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
  - **Mofosex**
  - **Mojvideo**
  - **Moniker**: allmyvideos.net and vidspot.net
- - **mooshare**: Mooshare.biz
  - **Morningstar**: morningstar.com
  - **Motherless**
  - **Motorsport**: motorsport.com
@@ -357,8 +385,10 @@
  - **mtvservices:embedded**
  - **MuenchenTV**: münchen.tv
  - **MusicPlayOn**
- - **muzu.tv**
+ - **mva**: Microsoft Virtual Academy videos
+ - **mva:course**: Microsoft Virtual Academy courses
  - **Mwave**
+ - **MwaveMeetGreet**
  - **MySpace**
  - **MySpace:album**
  - **MySpass**
@@ -366,7 +396,8 @@
  - **myvideo** (Currently broken)
  - **MyVidster**
  - **n-tv.de**
- - **NationalGeographic**
+ - **natgeo**
+ - **natgeo:channel**
  - **Naver**
  - **NBA**
  - **NBC**
@@ -378,7 +409,6 @@
  - **ndr:embed:base**
  - **NDTV**
  - **NerdCubedFeed**
- - **Nerdist**
  - **netease:album**: 网易云音乐 - 专辑
  - **netease:djradio**: 网易云音乐 - 电台
  - **netease:mv**: 网易云音乐 - MV
@@ -396,7 +426,8 @@
  - **nfl.com**
  - **nhl.com**
  - **nhl.com:news**: NHL news
- - **nhl.com:videocenter**: NHL videocenter category
+ - **nhl.com:videocenter**
+ - **nhl.com:videocenter:category**: NHL videocenter category
  - **nick.com**
  - **niconico**: ニコニコ動画
  - **NiconicoPlaylist**
@@ -406,7 +437,6 @@
  - **Normalboots**
  - **NosVideo**
  - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
- - **novamov**: NovaMov
  - **nowness**
  - **nowness:playlist**
  - **nowness:series**
@@ -421,6 +451,7 @@
  - **Npr**
  - **NRK**
  - **NRKPlaylist**
+ - **NRKSkole**: NRK Skole
  - **NRKTV**: NRK TV and NRK Radio
  - **ntv.ru**
  - **Nuvid**
@@ -433,6 +464,7 @@
  - **OnionStudios**
  - **Ooyala**
  - **OoyalaExternal**
+ - **Openload**
  - **OraTV**
  - **orf:fm4**: radio FM4
  - **orf:iptv**: iptv.ORF.at
@@ -443,13 +475,14 @@
  - **Patreon**
  - **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET  (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC)
  - **pcmag**
- - **Periscope**: Periscope
+ - **People**
+ - **periscope**: Periscope
+ - **periscope:user**: Periscope user videos
  - **PhilharmonieDeParis**: Philharmonie de Paris
  - **phoenix.de**
  - **Photobucket**
  - **Pinkbike**
  - **Pladform**
- - **PlanetaPlay**
  - **play.fm**
  - **played.to**
  - **PlaysTV**
@@ -468,6 +501,7 @@
  - **Pornotube**
  - **PornoVoisines**
  - **PornoXO**
+ - **PressTV**
  - **PrimeShareTV**
  - **PromptFile**
  - **prosiebensat1**: ProSiebenSat.1 Digital
@@ -478,10 +512,11 @@
  - **qqmusic:playlist**: QQ音乐 - 歌单
  - **qqmusic:singer**: QQ音乐 - 歌手
  - **qqmusic:toplist**: QQ音乐 - 排行榜
- - **QuickVid**
  - **R7**
  - **radio.de**
  - **radiobremen**
+ - **radiocanada**
+ - **RadioCanadaAudioVideo**
  - **radiofrance**
  - **RadioJavan**
  - **Rai**
@@ -491,8 +526,10 @@
  - **RedTube**
  - **RegioTV**
  - **Restudy**
+ - **Reuters**
  - **ReverbNation**
  - **Revision3**
+ - **RICE**
  - **RingTV**
  - **RottenTomatoes**
  - **Roxwel**
@@ -517,6 +554,7 @@
  - **RUTV**: RUTV.RU
  - **Ruutu**
  - **safari**: safaribooksonline.com online video
+ - **safari:api**
  - **safari:course**: safaribooksonline.com online courses
  - **Sandia**: Sandia National Laboratories
  - **Sapo**: SAPO Vídeos
@@ -530,9 +568,9 @@
  - **ScreenJunkies**
  - **ScreenwaveMedia**
  - **SenateISVP**
+ - **SendtoNews**
  - **ServingSys**
  - **Sexu**
- - **SexyKarma**: Sexy Karma and Watch Indian Porn
  - **Shahid**
  - **Shared**: shared.sx and vivo.sx
  - **ShareSix**
@@ -545,8 +583,6 @@
  - **smotri:broadcast**: Smotri.com broadcasts
  - **smotri:community**: Smotri.com community videos
  - **smotri:user**: Smotri.com user videos
- - **SnagFilms**
- - **SnagFilmsEmbed**
  - **Snotr**
  - **Sohu**
  - **soundcloud**
@@ -588,8 +624,10 @@
  - **Syfy**
  - **SztvHu**
  - **Tagesschau**
+ - **tagesschau:player**
  - **Tapely**
  - **Tass**
+ - **TDSLifeway**
  - **teachertube**: teachertube.com videos
  - **teachertube:user:collection**: teachertube.com user and collection videos
  - **TeachingChannel**
@@ -604,13 +642,13 @@
  - **Telegraaf**
  - **TeleMB**
  - **TeleTask**
- - **TenPlay**
  - **TF1**
  - **TheIntercept**
- - **TheOnion**
  - **ThePlatform**
  - **ThePlatformFeed**
+ - **TheScene**
  - **TheSixtyOne**
+ - **TheStar**
  - **ThisAmericanLife**
  - **ThisAV**
  - **THVideo**
@@ -644,16 +682,16 @@
  - **tv.dfb.de**
  - **TV2**
  - **TV2Article**
+ - **TV3**
  - **TV4**: tv4.se and tv4play.se
  - **TVC**
  - **TVCArticle**
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvland.com**
- - **tvp.pl**
- - **tvp.pl:Series**
+ - **tvp**: Telewizja Polska
+ - **tvp:series**
  - **TVPlay**: TV3Play and related services
  - **Tweakers**
- - **twitch:bookmarks**
  - **twitch:chapter**
  - **twitch:past_broadcasts**
  - **twitch:profile**
@@ -663,15 +701,16 @@
  - **twitter**
  - **twitter:amplify**
  - **twitter:card**
- - **Ubu**
  - **udemy**
  - **udemy:course**
  - **UDNEmbed**: 聯合影音
  - **Unistra**
  - **Urort**: NRK P3 Urørt
+ - **USAToday**
  - **ustream**
  - **ustream:channel**
- - **Ustudio**
+ - **ustudio**
+ - **ustudio:embed**
  - **Varzesh3**
  - **Vbox7**
  - **VeeHD**
@@ -679,9 +718,11 @@
  - **Vessel**
  - **Vesti**: Вести.Ru
  - **Vevo**
+ - **VevoPlaylist**
  - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
  - **vh1.com**
  - **Vice**
+ - **ViceShow**
  - **Viddler**
  - **video.google:search**: Google Video search
  - **video.mit.edu**
@@ -700,6 +741,8 @@
  - **Vidzi**
  - **vier**
  - **vier:videos**
+ - **ViewLift**
+ - **ViewLiftEmbed**
  - **Viewster**
  - **Viidea**
  - **viki**
@@ -709,6 +752,7 @@
  - **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)
@@ -720,6 +764,7 @@
  - **vlive**
  - **Vodlocker**
  - **VoiceRepublic**
+ - **VoxMedia**
  - **Vporn**
  - **vpro**: npo.nl and ntr.nl
  - **VRT**
@@ -727,9 +772,10 @@
  - **VuClip**
  - **vulture.com**
  - **Walla**
- - **WashingtonPost**
+ - **washingtonpost**
+ - **washingtonpost:article**
  - **wat.tv**
- - **WayOfTheMaster**
+ - **WatchIndianPorn**: Watch Indian Porn
  - **WDR**
  - **wdr:mobile**
  - **WDRMaus**: Sendung mit der Maus
@@ -746,9 +792,13 @@
  - **WSJ**: Wall Street Journal
  - **XBef**
  - **XboxClips**
- - **XFileShare**: XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me
+ - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To
  - **XHamster**
  - **XHamsterEmbed**
+ - **xiami:album**: 虾米音乐 - 专辑
+ - **xiami:artist**: 虾米音乐 - 歌手
+ - **xiami:collection**: 虾米音乐 - 精选集
+ - **xiami:song**: 虾米音乐
  - **XMinus**
  - **XNXX**
  - **Xstream**
@@ -773,6 +823,7 @@
  - **youtube:channel**: YouTube.com channels
  - **youtube:favorites**: YouTube.com favourite videos, ":ytfav" for short (requires authentication)
  - **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication)
+ - **youtube:live**: YouTube.com live streams
  - **youtube:playlist**: YouTube.com playlists
  - **youtube:playlists**: YouTube.com user/channel playlists
  - **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication)

setup.cfg

@@ -2,5 +2,5 @@
 universal = True
 
 [flake8]
-exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,setup.py,build,.git
+exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,devscripts/lazy_load_template.py,devscripts/make_issue_template.py,setup.py,build,.git
 ignore = E402,E501,E731

setup.py

@@ -8,11 +8,12 @@ import warnings
 import sys
 
 try:
-    from setuptools import setup
+    from setuptools import setup, Command
     setuptools_available = True
 except ImportError:
-    from distutils.core import setup
+    from distutils.core import setup, Command
     setuptools_available = False
+from distutils.spawn import spawn
 
 try:
     # This will create an exe that needs Microsoft Visual C++ 2008
@@ -70,6 +71,22 @@ else:
     else:
         params['scripts'] = ['bin/youtube-dl']
 
+class build_lazy_extractors(Command):
+    description = "Build the extractor lazy loading module"
+    user_options = []
+
+    def initialize_options(self):
+        pass
+
+    def finalize_options(self):
+        pass
+
+    def run(self):
+        spawn(
+            [sys.executable, 'devscripts/make_lazy_extractors.py', 'youtube_dl/extractor/lazy_extractors.py'],
+            dry_run=self.dry_run,
+        )
+
 # Get the version from youtube_dl/version.py without importing the package
 exec(compile(open('youtube_dl/version.py').read(),
              'youtube_dl/version.py', 'exec'))
@@ -107,5 +124,6 @@ setup(
         "Programming Language :: Python :: 3.4",
     ],
 
+    cmdclass={'build_lazy_extractors': build_lazy_extractors},
     **params
 )

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,
 )
@@ -21,8 +24,13 @@ from youtube_dl.utils import (
 def get_params(override=None):
     PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)),
                                    "parameters.json")
+    LOCAL_PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)),
+                                         "local_parameters.json")
     with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
         parameters = json.load(pf)
+    if os.path.exists(LOCAL_PARAMETERS_FILE):
+        with io.open(LOCAL_PARAMETERS_FILE, encoding='utf-8') as pf:
+            parameters.update(json.load(pf))
     if override:
         parameters.update(override)
     return parameters
@@ -42,7 +50,7 @@ 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:'
@@ -140,6 +148,9 @@ def expect_value(self, got, expected, field):
             expect_value(self, item_got, item_expected, field)
     else:
         if isinstance(expected, compat_str) and expected.startswith('md5:'):
+            self.assertTrue(
+                isinstance(got, compat_str),
+                'Expected field %s to be a unicode object, but got value %r of type %r' % (field, got, type(got)))
             got = 'md5:' + md5(got)
         elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
             self.assertTrue(

test/test_InfoExtractor.py

@@ -11,6 +11,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 from test.helper import FakeYDL
 from youtube_dl.extractor.common import InfoExtractor
 from youtube_dl.extractor import YoutubeIE, get_info_extractor
+from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError
 
 
 class TestIE(InfoExtractor):
@@ -66,5 +67,14 @@ class TestInfoExtractor(unittest.TestCase):
         self.assertEqual(ie._html_search_meta('e', html), '5')
         self.assertEqual(ie._html_search_meta('f', html), '6')
 
+    def test_download_json(self):
+        uri = encode_data_uri(b'{"foo": "blah"}', 'application/json')
+        self.assertEqual(self.ie._download_json(uri, None), {'foo': 'blah'})
+        uri = encode_data_uri(b'callback({"foo": "blah"})', 'application/javascript')
+        self.assertEqual(self.ie._download_json(uri, None, transform_source=strip_jsonp), {'foo': 'blah'})
+        uri = encode_data_uri(b'{"foo": invalid}', 'application/json')
+        self.assertRaises(ExtractorError, self.ie._download_json, uri, None)
+        self.assertEqual(self.ie._download_json(uri, None, fatal=False), None)
+
 if __name__ == '__main__':
     unittest.main()

test/test_YoutubeDL.py

@@ -222,6 +222,11 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'dash-video-low')
 
+        ydl = YDL({'format': 'bestvideo[format_id^=dash][format_id$=low]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'dash-video-low')
+
         formats = [
             {'format_id': 'vid-vcodec-dot', 'ext': 'mp4', 'preference': 1, 'vcodec': 'avc1.123456', 'acodec': 'none', 'url': TEST_URL},
         ]
@@ -502,6 +507,9 @@ class TestYoutubeDL(unittest.TestCase):
         assertRegexpMatches(self, ydl._format_note({
             'vbr': 10,
         }), '^\s*10k$')
+        assertRegexpMatches(self, ydl._format_note({
+            'fps': 30,
+        }), '^30fps$')
 
     def test_postprocessors(self):
         filename = 'post-processor-testfile.mp4'

test/test_compat.py

@@ -10,34 +10,39 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
-from youtube_dl.utils import get_filesystem_encoding
 from youtube_dl.compat import (
     compat_getenv,
+    compat_setenv,
     compat_etree_fromstring,
     compat_expanduser,
     compat_shlex_split,
     compat_str,
+    compat_struct_unpack,
     compat_urllib_parse_unquote,
     compat_urllib_parse_unquote_plus,
+    compat_urllib_parse_urlencode,
 )
 
 
 class TestCompat(unittest.TestCase):
     def test_compat_getenv(self):
         test_str = 'тест'
-        os.environ['YOUTUBE-DL-TEST'] = (
-            test_str if sys.version_info >= (3, 0)
-            else test_str.encode(get_filesystem_encoding()))
+        compat_setenv('YOUTUBE-DL-TEST', test_str)
         self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str)
 
+    def test_compat_setenv(self):
+        test_var = 'YOUTUBE-DL-TEST'
+        test_str = 'тест'
+        compat_setenv(test_var, test_str)
+        compat_getenv(test_var)
+        self.assertEqual(compat_getenv(test_var), test_str)
+
     def test_compat_expanduser(self):
         old_home = os.environ.get('HOME')
         test_str = 'C:\Documents and Settings\тест\Application Data'
-        os.environ['HOME'] = (
-            test_str if sys.version_info >= (3, 0)
-            else test_str.encode(get_filesystem_encoding()))
+        compat_setenv('HOME', test_str)
         self.assertEqual(compat_expanduser('~'), test_str)
-        os.environ['HOME'] = old_home
+        compat_setenv('HOME', old_home or '')
 
     def test_all_present(self):
         import youtube_dl.compat
@@ -70,6 +75,16 @@ class TestCompat(unittest.TestCase):
         self.assertEqual(compat_urllib_parse_unquote_plus('abc%20def'), 'abc def')
         self.assertEqual(compat_urllib_parse_unquote_plus('%7e/abc+def'), '~/abc def')
 
+    def test_compat_urllib_parse_urlencode(self):
+        self.assertEqual(compat_urllib_parse_urlencode({'abc': 'def'}), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode({'abc': b'def'}), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode({b'abc': 'def'}), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode({b'abc': b'def'}), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode([('abc', 'def')]), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode([('abc', b'def')]), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode([(b'abc', 'def')]), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode([(b'abc', b'def')]), 'abc=def')
+
     def test_compat_shlex_split(self):
         self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two'])
 
@@ -88,5 +103,15 @@ class TestCompat(unittest.TestCase):
         self.assertTrue(isinstance(doc.find('chinese').text, compat_str))
         self.assertTrue(isinstance(doc.find('foo/bar').text, compat_str))
 
+    def test_compat_etree_fromstring_doctype(self):
+        xml = '''<?xml version="1.0"?>
+<!DOCTYPE smil PUBLIC "-//W3C//DTD SMIL 2.0//EN" "http://www.w3.org/2001/SMIL20/SMIL20.dtd">
+<smil xmlns="http://www.w3.org/2001/SMIL20/Language"></smil>'''
+        compat_etree_fromstring(xml)
+
+    def test_struct_unpack(self):
+        self.assertEqual(compat_struct_unpack('!B', b'\x00'), (0,))
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_http.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+# coding: utf-8
 from __future__ import unicode_literals
 
 # Allow direct execution
@@ -52,7 +53,12 @@ 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()
@@ -115,5 +121,14 @@ class TestProxy(unittest.TestCase):
         response = ydl.urlopen(req).read().decode('utf-8')
         self.assertEqual(response, 'cn: {0}'.format(url))
 
+    def test_proxy_with_idn(self):
+        ydl = YoutubeDL({
+            'proxy': 'localhost:{0}'.format(self.port),
+        })
+        url = 'http://中文.tw/'
+        response = ydl.urlopen(url).read().decode('utf-8')
+        # b'xn--fiq228c' is '中文'.encode('idna')
+        self.assertEqual(response, 'normal: http://xn--fiq228c.tw/')
+
 if __name__ == '__main__':
     unittest.main()

test/test_socks.py

@@ -0,0 +1,118 @@
+#!/usr/bin/env python
+# coding: utf-8
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+import random
+import subprocess
+
+from test.helper import (
+    FakeYDL,
+    get_params,
+)
+from youtube_dl.compat import (
+    compat_str,
+    compat_urllib_request,
+)
+
+
+class TestMultipleSocks(unittest.TestCase):
+    @staticmethod
+    def _check_params(attrs):
+        params = get_params()
+        for attr in attrs:
+            if attr not in params:
+                print('Missing %s. Skipping.' % attr)
+                return
+        return params
+
+    def test_proxy_http(self):
+        params = self._check_params(['primary_proxy', 'primary_server_ip'])
+        if params is None:
+            return
+        ydl = FakeYDL({
+            'proxy': params['primary_proxy']
+        })
+        self.assertEqual(
+            ydl.urlopen('http://yt-dl.org/ip').read().decode('utf-8'),
+            params['primary_server_ip'])
+
+    def test_proxy_https(self):
+        params = self._check_params(['primary_proxy', 'primary_server_ip'])
+        if params is None:
+            return
+        ydl = FakeYDL({
+            'proxy': params['primary_proxy']
+        })
+        self.assertEqual(
+            ydl.urlopen('https://yt-dl.org/ip').read().decode('utf-8'),
+            params['primary_server_ip'])
+
+    def test_secondary_proxy_http(self):
+        params = self._check_params(['secondary_proxy', 'secondary_server_ip'])
+        if params is None:
+            return
+        ydl = FakeYDL()
+        req = compat_urllib_request.Request('http://yt-dl.org/ip')
+        req.add_header('Ytdl-request-proxy', params['secondary_proxy'])
+        self.assertEqual(
+            ydl.urlopen(req).read().decode('utf-8'),
+            params['secondary_server_ip'])
+
+    def test_secondary_proxy_https(self):
+        params = self._check_params(['secondary_proxy', 'secondary_server_ip'])
+        if params is None:
+            return
+        ydl = FakeYDL()
+        req = compat_urllib_request.Request('https://yt-dl.org/ip')
+        req.add_header('Ytdl-request-proxy', params['secondary_proxy'])
+        self.assertEqual(
+            ydl.urlopen(req).read().decode('utf-8'),
+            params['secondary_server_ip'])
+
+
+class TestSocks(unittest.TestCase):
+    _SKIP_SOCKS_TEST = True
+
+    def setUp(self):
+        if self._SKIP_SOCKS_TEST:
+            return
+
+        self.port = random.randint(20000, 30000)
+        self.server_process = subprocess.Popen([
+            'srelay', '-f', '-i', '127.0.0.1:%d' % self.port],
+            stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+
+    def tearDown(self):
+        if self._SKIP_SOCKS_TEST:
+            return
+
+        self.server_process.terminate()
+        self.server_process.communicate()
+
+    def _get_ip(self, protocol):
+        if self._SKIP_SOCKS_TEST:
+            return '127.0.0.1'
+
+        ydl = FakeYDL({
+            'proxy': '%s://127.0.0.1:%d' % (protocol, self.port),
+        })
+        return ydl.urlopen('http://yt-dl.org/ip').read().decode('utf-8')
+
+    def test_socks4(self):
+        self.assertTrue(isinstance(self._get_ip('socks4'), compat_str))
+
+    def test_socks4a(self):
+        self.assertTrue(isinstance(self._get_ip('socks4a'), compat_str))
+
+    def test_socks5(self):
+        self.assertTrue(isinstance(self._get_ip('socks5'), compat_str))
+
+
+if __name__ == '__main__':
+    unittest.main()

test/test_utils.py

@@ -20,6 +20,7 @@ from youtube_dl.utils import (
     args_to_str,
     encode_base_n,
     clean_html,
+    date_from_str,
     DateRange,
     detect_exe_version,
     determine_ext,
@@ -28,6 +29,7 @@ from youtube_dl.utils import (
     encodeFilename,
     escape_rfc3986,
     escape_url,
+    extract_attributes,
     ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
@@ -41,18 +43,20 @@ from youtube_dl.utils import (
     orderedSet,
     parse_duration,
     parse_filesize,
+    parse_count,
     parse_iso8601,
     read_batch_urls,
     sanitize_filename,
     sanitize_path,
     prepend_extension,
     replace_extension,
+    remove_start,
+    remove_end,
     remove_quotes,
     shell_quote,
     smuggle_url,
     str_to_int,
     strip_jsonp,
-    struct_unpack,
     timeconvert,
     unescapeHTML,
     unified_strdate,
@@ -61,6 +65,7 @@ from youtube_dl.utils import (
     lowercase_escape,
     url_basename,
     urlencode_postdata,
+    update_url_query,
     version_tuple,
     xpath_with_ns,
     xpath_element,
@@ -75,7 +80,10 @@ from youtube_dl.utils import (
     cli_bool_option,
 )
 from youtube_dl.compat import (
+    compat_chr,
     compat_etree_fromstring,
+    compat_urlparse,
+    compat_parse_qs,
 )
 
 
@@ -132,8 +140,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
 
-        tests = 'a\xe4b\u4e2d\u56fd\u7684c'
-        self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
+        tests = 'aäb\u4e2d\u56fd\u7684c'
+        self.assertEqual(sanitize_filename(tests, restricted=True), 'aab_c')
         self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
 
         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
@@ -148,6 +156,10 @@ class TestUtil(unittest.TestCase):
         self.assertTrue(sanitize_filename('-', restricted=True) != '')
         self.assertTrue(sanitize_filename(':', restricted=True) != '')
 
+        self.assertEqual(sanitize_filename(
+            'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØŒÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøœùúûüýþÿ', restricted=True),
+            'AAAAAAAECEEEEIIIIDNOOOOOOOEUUUUYPssaaaaaaaeceeeeiiiionoooooooeuuuuypy')
+
     def test_sanitize_ids(self):
         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
@@ -205,6 +217,16 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
         self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
 
+    def test_remove_start(self):
+        self.assertEqual(remove_start(None, 'A - '), None)
+        self.assertEqual(remove_start('A - B', 'A - '), 'B')
+        self.assertEqual(remove_start('B - A', 'A - '), 'B - A')
+
+    def test_remove_end(self):
+        self.assertEqual(remove_end(None, ' - B'), None)
+        self.assertEqual(remove_end('A - B', ' - B'), 'A')
+        self.assertEqual(remove_end('B - A', ' - B'), 'B - A')
+
     def test_remove_quotes(self):
         self.assertEqual(remove_quotes(None), None)
         self.assertEqual(remove_quotes('"'), '"')
@@ -228,6 +250,13 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unescapeHTML('é'), 'é')
         self.assertEqual(unescapeHTML('�'), '�')
 
+    def test_date_from_str(self):
+        self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
+        self.assertEqual(date_from_str('now+7day'), date_from_str('now+1week'))
+        self.assertEqual(date_from_str('now+14day'), date_from_str('now+2week'))
+        self.assertEqual(date_from_str('now+365day'), date_from_str('now+1year'))
+        self.assertEqual(date_from_str('now+30day'), date_from_str('now+1month'))
+
     def test_daterange(self):
         _20century = DateRange("19000101", "20000101")
         self.assertFalse("17890714" in _20century)
@@ -399,6 +428,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('01:02:03:04'), 93784)
         self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
         self.assertEqual(parse_duration('87 Min.'), 5220)
+        self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -438,9 +468,6 @@ class TestUtil(unittest.TestCase):
         testPL(5, 2, (2, 99), [2, 3, 4])
         testPL(5, 2, (20, 99), [])
 
-    def test_struct_unpack(self):
-        self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
-
     def test_read_batch_urls(self):
         f = io.StringIO('''\xef\xbb\xbf foo
             bar\r
@@ -454,6 +481,40 @@ 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,
@@ -537,11 +598,11 @@ class TestUtil(unittest.TestCase):
         )
         self.assertEqual(
             escape_url('http://тест.рф/фрагмент'),
-            'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
+            'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
         )
         self.assertEqual(
             escape_url('http://тест.рф/абв?абв=абв#абв'),
-            'http://тест.рф/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
+            'http://xn--e1aybc.xn--p1ai/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
         )
         self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
 
@@ -568,6 +629,15 @@ class TestUtil(unittest.TestCase):
         json_code = js_to_json(inp)
         self.assertEqual(json.loads(json_code), json.loads(inp))
 
+        inp = '''{
+            0:{src:'skipped', type: 'application/dash+xml'},
+            1:{src:'skipped', type: 'application/vnd.apple.mpegURL'},
+        }'''
+        self.assertEqual(js_to_json(inp), '''{
+            "0":{"src":"skipped", "type": "application/dash+xml"},
+            "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"}
+        }''')
+
     def test_js_to_json_edgecases(self):
         on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
         self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
@@ -591,6 +661,65 @@ class TestUtil(unittest.TestCase):
         on = js_to_json('{"abc": "def",}')
         self.assertEqual(json.loads(on), {'abc': 'def'})
 
+        on = js_to_json('{ 0: /* " \n */ ",]" , }')
+        self.assertEqual(json.loads(on), {'0': ',]'})
+
+        on = js_to_json(r'["<p>x<\/p>"]')
+        self.assertEqual(json.loads(on), ['<p>x</p>'])
+
+        on = js_to_json(r'["\xaa"]')
+        self.assertEqual(json.loads(on), ['\u00aa'])
+
+        on = js_to_json("['a\\\nb']")
+        self.assertEqual(json.loads(on), ['ab'])
+
+        on = js_to_json('{0xff:0xff}')
+        self.assertEqual(json.loads(on), {'255': 255})
+
+        on = js_to_json('{077:077}')
+        self.assertEqual(json.loads(on), {'63': 63})
+
+        on = js_to_json('{42:42}')
+        self.assertEqual(json.loads(on), {'42': 42})
+
+    def test_extract_attributes(self):
+        self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
+        self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e x=y>'), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e x="a \'b\' c">'), {'x': "a 'b' c"})
+        self.assertEqual(extract_attributes('<e x=\'a "b" c\'>'), {'x': 'a "b" c'})
+        self.assertEqual(extract_attributes('<e x="&#121;">'), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e x="&#x79;">'), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e x="&amp;">'), {'x': '&'})  # XML
+        self.assertEqual(extract_attributes('<e x="&quot;">'), {'x': '"'})
+        self.assertEqual(extract_attributes('<e x="&pound;">'), {'x': '£'})  # HTML 3.2
+        self.assertEqual(extract_attributes('<e x="&lambda;">'), {'x': 'λ'})  # HTML 4.0
+        self.assertEqual(extract_attributes('<e x="&foo">'), {'x': '&foo'})
+        self.assertEqual(extract_attributes('<e x="\'">'), {'x': "'"})
+        self.assertEqual(extract_attributes('<e x=\'"\'>'), {'x': '"'})
+        self.assertEqual(extract_attributes('<e x >'), {'x': None})
+        self.assertEqual(extract_attributes('<e x=y a>'), {'x': 'y', 'a': None})
+        self.assertEqual(extract_attributes('<e x= y>'), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e x=1 y=2 x=3>'), {'y': '2', 'x': '3'})
+        self.assertEqual(extract_attributes('<e \nx=\ny\n>'), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e \nx=\n"y"\n>'), {'x': 'y'})
+        self.assertEqual(extract_attributes("<e \nx=\n'y'\n>"), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e \nx="\ny\n">'), {'x': '\ny\n'})
+        self.assertEqual(extract_attributes('<e CAPS=x>'), {'caps': 'x'})  # Names lowercased
+        self.assertEqual(extract_attributes('<e x=1 X=2>'), {'x': '2'})
+        self.assertEqual(extract_attributes('<e X=1 x=2>'), {'x': '2'})
+        self.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'})
+        self.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'})
+        self.assertEqual(extract_attributes('<e x="décompose&#769;">'), {'x': 'décompose\u0301'})
+        # "Narrow" Python builds don't support unicode code points outside BMP.
+        try:
+            compat_chr(0x10000)
+            supports_outside_bmp = True
+        except ValueError:
+            supports_outside_bmp = False
+        if supports_outside_bmp:
+            self.assertEqual(extract_attributes('<e x="Smile &#128512;!">'), {'x': 'Smile \U0001f600!'})
+
     def test_clean_html(self):
         self.assertEqual(clean_html('a:\nb'), 'a: b')
         self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
@@ -616,6 +745,17 @@ 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)
+        self.assertEqual(parse_count('1.1kk '), 1100000)
+        self.assertEqual(parse_count('1.1kk views'), 1100000)
+
     def test_version_tuple(self):
         self.assertEqual(version_tuple('1'), (1,))
         self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))

test/test_youtube_lists.py

@@ -44,7 +44,7 @@ class TestYoutubeLists(unittest.TestCase):
         ie = YoutubePlaylistIE(dl)
         result = ie.extract('https://www.youtube.com/watch?v=W01L70IGBgE&index=2&list=RDOQpdSVF_k_w')
         entries = result['entries']
-        self.assertTrue(len(entries) >= 20)
+        self.assertTrue(len(entries) >= 50)
         original_video = entries[0]
         self.assertEqual(original_video['id'], 'OQpdSVF_k_w')
 

tox.ini

@@ -8,6 +8,7 @@ deps =
 passenv = HOME
 defaultargs = 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_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py
+    --exclude test_socks.py
 commands = nosetests --verbose {posargs:{[testenv]defaultargs}}  # --with-coverage --cover-package=youtube_dl --cover-html
                                                # test.test_download:TestDownload.test_NowVideo

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,
@@ -41,6 +39,8 @@ from .compat import (
     compat_urllib_request_DataHandler,
 )
 from .utils import (
+    age_restricted,
+    args_to_str,
     ContentTooShortError,
     date_from_str,
     DateRange,
@@ -60,13 +60,17 @@ from .utils import (
     PagedList,
     parse_filesize,
     PerRequestProxyHandler,
-    PostProcessingError,
     platform_name,
+    PostProcessingError,
     preferredencoding,
+    prepend_extension,
+    register_socks_protocols,
     render_table,
+    replace_extension,
     SameFileError,
     sanitize_filename,
     sanitize_path,
+    sanitize_url,
     sanitized_Request,
     std_headers,
     subtitles_filename,
@@ -77,16 +81,13 @@ from .utils import (
     write_string,
     YoutubeDLCookieProcessor,
     YoutubeDLHandler,
-    prepend_extension,
-    replace_extension,
-    args_to_str,
-    age_restricted,
 )
 from .cache import Cache
-from .extractor import get_info_extractor, gen_extractors
+from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER
 from .downloader import get_suitable_downloader
 from .downloader.rtmp import rtmpdump_version
 from .postprocessor import (
+    FFmpegFixupM3u8PP,
     FFmpegFixupM4aPP,
     FFmpegFixupStretchedPP,
     FFmpegMergerPP,
@@ -95,6 +96,9 @@ from .postprocessor import (
 )
 from .version import __version__
 
+if compat_os_name == 'nt':
+    import ctypes
+
 
 class YoutubeDL(object):
     """YoutubeDL class.
@@ -257,7 +261,9 @@ class YoutubeDL(object):
     The following options determine which downloader is picked:
     external_downloader: Executable of the external downloader to call.
                        None or unset for standard (built-in) downloader.
-    hls_prefer_native: Use the native HLS downloader instead of ffmpeg/avconv.
+    hls_prefer_native: Use the native HLS downloader instead of ffmpeg/avconv
+                       if True, otherwise use ffmpeg/avconv if False, otherwise
+                       use downloader suggested by extractor if None.
 
     The following parameters are not used by YoutubeDL itself, they are used by
     the downloader (see youtube_dl/downloader/common.py):
@@ -320,7 +326,7 @@ class YoutubeDL(object):
                         ['fribidi', '-c', 'UTF-8'] + width_args, **sp_kwargs)
                 self._output_channel = os.fdopen(master, 'rb')
             except OSError as ose:
-                if ose.errno == 2:
+                if ose.errno == errno.ENOENT:
                     self.report_warning('Could not find fribidi executable, ignoring --bidi-workaround . Make sure that  fribidi  is an executable file in one of the directories in your $PATH.')
                 else:
                     raise
@@ -356,6 +362,8 @@ class YoutubeDL(object):
         for ph in self.params.get('progress_hooks', []):
             self.add_progress_hook(ph)
 
+        register_socks_protocols()
+
     def warn_if_short_id(self, argv):
         # short YouTube ID starting with dash?
         idxs = [
@@ -375,8 +383,9 @@ class YoutubeDL(object):
     def add_info_extractor(self, ie):
         """Add an InfoExtractor object to the end of the list."""
         self._ies.append(ie)
-        self._ies_instances[ie.ie_key()] = ie
-        ie.set_downloader(self)
+        if not isinstance(ie, type):
+            self._ies_instances[ie.ie_key()] = ie
+            ie.set_downloader(self)
 
     def get_info_extractor(self, ie_key):
         """
@@ -394,7 +403,7 @@ class YoutubeDL(object):
         """
         Add the InfoExtractors returned by gen_extractors to the end of the list
         """
-        for ie in gen_extractors():
+        for ie in gen_extractor_classes():
             self.add_info_extractor(ie)
 
     def add_post_processor(self, pp):
@@ -450,7 +459,7 @@ 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 +530,7 @@ 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 +542,7 @@ 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 +575,7 @@ 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),
@@ -574,7 +583,7 @@ class YoutubeDL(object):
                 is_id=(k == 'id'))
             template_dict = dict((k, sanitize(k, v))
                                  for k, v in template_dict.items()
-                                 if v is not None)
+                                 if v is not None and not isinstance(v, (list, tuple, dict)))
             template_dict = collections.defaultdict(lambda: 'NA', template_dict)
 
             outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
@@ -658,6 +667,7 @@ class YoutubeDL(object):
             if not ie.suitable(url):
                 continue
 
+            ie = self.get_info_extractor(ie.ie_key())
             if not ie.working():
                 self.report_warning('The program functionality for this site has been marked as broken, '
                                     'and will probably not work.')
@@ -710,6 +720,7 @@ class YoutubeDL(object):
         result_type = ie_result.get('_type', 'video')
 
         if result_type in ('url', 'url_transparent'):
+            ie_result['url'] = sanitize_url(ie_result['url'])
             extract_flat = self.params.get('extract_flat', False)
             if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) or
                     extract_flat is True):
@@ -903,7 +914,7 @@ class YoutubeDL(object):
                 '*=': lambda attr, value: value in attr,
             }
             str_operator_rex = re.compile(r'''(?x)
-                \s*(?P<key>ext|acodec|vcodec|container|protocol)
+                \s*(?P<key>ext|acodec|vcodec|container|protocol|format_id)
                 \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
                 \s*(?P<value>[a-zA-Z0-9._-]+)
                 \s*$
@@ -1227,12 +1238,20 @@ class YoutubeDL(object):
                 t.get('preference'), t.get('width'), t.get('height'),
                 t.get('id'), t.get('url')))
             for i, t in enumerate(thumbnails):
+                t['url'] = sanitize_url(t['url'])
                 if t.get('width') and t.get('height'):
                     t['resolution'] = '%dx%d' % (t['width'], t['height'])
                 if t.get('id') is None:
                     t['id'] = '%d' % i
 
-        if thumbnails and 'thumbnail' not in info_dict:
+        if self.params.get('list_thumbnails'):
+            self.list_thumbnails(info_dict)
+            return
+
+        thumbnail = info_dict.get('thumbnail')
+        if thumbnail:
+            info_dict['thumbnail'] = sanitize_url(thumbnail)
+        elif thumbnails:
             info_dict['thumbnail'] = thumbnails[-1]['url']
 
         if 'display_id' not in info_dict and 'id' in info_dict:
@@ -1257,6 +1276,8 @@ class YoutubeDL(object):
         if subtitles:
             for _, subtitle in subtitles.items():
                 for subtitle_format in subtitle:
+                    if subtitle_format.get('url'):
+                        subtitle_format['url'] = sanitize_url(subtitle_format['url'])
                     if 'ext' not in subtitle_format:
                         subtitle_format['ext'] = determine_ext(subtitle_format['url']).lower()
 
@@ -1286,6 +1307,8 @@ class YoutubeDL(object):
             if 'url' not in format:
                 raise ExtractorError('Missing "url" key in result (index %d)' % i)
 
+            format['url'] = sanitize_url(format['url'])
+
             if format.get('format_id') is None:
                 format['format_id'] = compat_str(i)
             else:
@@ -1333,9 +1356,6 @@ 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:
@@ -1623,7 +1643,7 @@ class YoutubeDL(object):
                     # Just a single file
                     success = dl(filename, info_dict)
             except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-                self.report_error('unable to download video data: %s' % str(err))
+                self.report_error('unable to download video data: %s' % error_to_compat_str(err))
                 return
             except (OSError, IOError) as err:
                 raise UnavailableVideoError(err)
@@ -1631,12 +1651,14 @@ 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':
@@ -1649,15 +1671,18 @@ 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.' % (
-                                    info_dict['id'], stretched_ratio))
+                                '%s: Non-uniform pixel ratio (%s). %s'
+                                % (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.' % (
-                            info_dict['id']))
+                        self.report_warning(
+                            '%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:
@@ -1665,8 +1690,27 @@ 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.' % (
-                                    info_dict['id']))
+                                '%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')
 
@@ -1809,7 +1853,7 @@ class YoutubeDL(object):
         if fdict.get('language'):
             if res:
                 res += ' '
-            res += '[%s]' % fdict['language']
+            res += '[%s] ' % fdict['language']
         if fdict.get('format_note') is not None:
             res += fdict['format_note'] + ' '
         if fdict.get('tbr') is not None:
@@ -1830,7 +1874,9 @@ 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 += ', '
@@ -1873,13 +1919,8 @@ class YoutubeDL(object):
     def list_thumbnails(self, info_dict):
         thumbnails = info_dict.get('thumbnails')
         if not thumbnails:
-            tn_url = info_dict.get('thumbnail')
-            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('[info] No thumbnails present for %s' % info_dict['id'])
+            return
 
         self.to_screen(
             '[info] Thumbnails for %s:' % info_dict['id'])
@@ -1924,6 +1965,8 @@ class YoutubeDL(object):
         write_string(encoding_str, encoding=None)
 
         self._write_string('[debug] youtube-dl version ' + __version__ + '\n')
+        if _LAZY_LOADER:
+            self._write_string('[debug] Lazy loading extractors enabled' + '\n')
         try:
             sp = subprocess.Popen(
                 ['git', 'rev-parse', '--short', 'HEAD'],
@@ -1979,6 +2022,7 @@ class YoutubeDL(object):
         if opts_cookiefile is None:
             self.cookiejar = compat_cookiejar.CookieJar()
         else:
+            opts_cookiefile = compat_expanduser(opts_cookiefile)
             self.cookiejar = compat_cookiejar.MozillaCookieJar(
                 opts_cookiefile)
             if os.access(opts_cookiefile, os.R_OK):

youtube_dl/__init__.py

@@ -67,9 +67,9 @@ def _real_main(argv=None):
     # Custom HTTP headers
     if opts.headers is not None:
         for h in opts.headers:
-            if h.find(':', 1) < 0:
+            if ':' not in h:
                 parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
-            key, value = h.split(':', 2)
+            key, value = h.split(':', 1)
             if opts.verbose:
                 write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
             std_headers[key] = value
@@ -86,7 +86,9 @@ def _real_main(argv=None):
             if opts.batchfile == '-':
                 batchfd = sys.stdin
             else:
-                batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
+                batchfd = io.open(
+                    compat_expanduser(opts.batchfile),
+                    'r', encoding='utf-8', errors='ignore')
             batch_urls = read_batch_urls(batchfd)
             if opts.verbose:
                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
@@ -144,14 +146,20 @@ def _real_main(argv=None):
         if numeric_limit is None:
             parser.error('invalid max_filesize specified')
         opts.max_filesize = numeric_limit
-    if opts.retries is not None:
-        if opts.retries in ('inf', 'infinite'):
-            opts_retries = float('inf')
+
+    def parse_retries(retries):
+        if retries in ('inf', 'infinite'):
+            parsed_retries = float('inf')
         else:
             try:
-                opts_retries = int(opts.retries)
+                parsed_retries = int(retries)
             except (TypeError, ValueError):
                 parser.error('invalid retry count specified')
+        return parsed_retries
+    if opts.retries is not None:
+        opts.retries = parse_retries(opts.retries)
+    if opts.fragment_retries is not None:
+        opts.fragment_retries = parse_retries(opts.fragment_retries)
     if opts.buffersize is not None:
         numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
         if numeric_buffersize is None:
@@ -299,7 +307,8 @@ def _real_main(argv=None):
         'force_generic_extractor': opts.force_generic_extractor,
         'ratelimit': opts.ratelimit,
         'nooverwrites': opts.nooverwrites,
-        'retries': opts_retries,
+        'retries': opts.retries,
+        'fragment_retries': opts.fragment_retries,
         'buffersize': opts.buffersize,
         'noresizebuffer': opts.noresizebuffer,
         'continuedl': opts.continue_dl,
@@ -355,6 +364,7 @@ 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,
@@ -396,7 +406,7 @@ def _real_main(argv=None):
 
         try:
             if opts.load_info_filename is not None:
-                retcode = ydl.download_with_info_file(opts.load_info_filename)
+                retcode = ydl.download_with_info_file(compat_expanduser(opts.load_info_filename))
             else:
                 retcode = ydl.download(all_urls)
         except MaxDownloadsReached:

youtube_dl/compat.py

@@ -11,6 +11,7 @@ import re
 import shlex
 import shutil
 import socket
+import struct
 import subprocess
 import sys
 import itertools
@@ -77,6 +78,11 @@ try:
 except ImportError:  # Python 2
     from urllib import urlretrieve as compat_urlretrieve
 
+try:
+    from html.parser import HTMLParser as compat_HTMLParser
+except ImportError:  # Python 2
+    from HTMLParser import HTMLParser as compat_HTMLParser
+
 
 try:
     from subprocess import DEVNULL
@@ -164,6 +170,32 @@ except ImportError:  # Python 2
         string = string.replace('+', ' ')
         return compat_urllib_parse_unquote(string, encoding, errors)
 
+try:
+    from urllib.parse import urlencode as compat_urllib_parse_urlencode
+except ImportError:  # Python 2
+    # Python 2 will choke in urlencode on mixture of byte and unicode strings.
+    # Possible solutions are to either port it from python 3 with all
+    # the friends or manually ensure input query contains only byte strings.
+    # We will stick with latter thus recursively encoding the whole query.
+    def compat_urllib_parse_urlencode(query, doseq=0, encoding='utf-8'):
+        def encode_elem(e):
+            if isinstance(e, dict):
+                e = encode_dict(e)
+            elif isinstance(e, (list, tuple,)):
+                list_e = encode_list(e)
+                e = tuple(list_e) if isinstance(e, tuple) else list_e
+            elif isinstance(e, compat_str):
+                e = e.encode(encoding)
+            return e
+
+        def encode_dict(d):
+            return dict((encode_elem(k), encode_elem(v)) for k, v in d.items())
+
+        def encode_list(l):
+            return [encode_elem(e) for e in l]
+
+        return compat_urllib_parse.urlencode(encode_elem(query), doseq=doseq)
+
 try:
     from urllib.request import DataHandler as compat_urllib_request_DataHandler
 except ImportError:  # Python < 3.4
@@ -213,13 +245,20 @@ try:
 except ImportError:  # Python 2.6
     from xml.parsers.expat import ExpatError as compat_xml_parse_error
 
+
+etree = xml.etree.ElementTree
+
+
+class _TreeBuilder(etree.TreeBuilder):
+    def doctype(self, name, pubid, system):
+        pass
+
 if sys.version_info[0] >= 3:
-    compat_etree_fromstring = xml.etree.ElementTree.fromstring
+    def compat_etree_fromstring(text):
+        return etree.XML(text, parser=etree.XMLParser(target=_TreeBuilder()))
 else:
     # python 2.x tries to encode unicode strings with ascii (see the
     # XMLParser._fixtext method)
-    etree = xml.etree.ElementTree
-
     try:
         _etree_iter = etree.Element.iter
     except AttributeError:  # Python <=2.6
@@ -233,7 +272,7 @@ else:
     # 2.7 source
     def _XML(text, parser=None):
         if not parser:
-            parser = etree.XMLParser(target=etree.TreeBuilder())
+            parser = etree.XMLParser(target=_TreeBuilder())
         parser.feed(text)
         return parser.close()
 
@@ -245,12 +284,22 @@ else:
         return el
 
     def compat_etree_fromstring(text):
-        doc = _XML(text, parser=etree.XMLParser(target=etree.TreeBuilder(element_factory=_element_factory)))
+        doc = _XML(text, parser=etree.XMLParser(target=_TreeBuilder(element_factory=_element_factory)))
         for el in _etree_iter(doc):
             if el.text is not None and isinstance(el.text, bytes):
                 el.text = el.text.decode('utf-8')
         return doc
 
+if sys.version_info < (2, 7):
+    # Here comes the crazy part: In 2.6, if the xpath is a unicode,
+    # .//node does not match if a node is a direct child of . !
+    def compat_xpath(xpath):
+        if isinstance(xpath, compat_str):
+            xpath = xpath.encode('ascii')
+        return xpath
+else:
+    compat_xpath = lambda xpath: xpath
+
 try:
     from urllib.parse import parse_qs as compat_parse_qs
 except ImportError:  # Python 2
@@ -299,9 +348,9 @@ except ImportError:  # Python 2
         return parsed_result
 
 try:
-    from shlex import quote as shlex_quote
+    from shlex import quote as compat_shlex_quote
 except ImportError:  # Python < 3.3
-    def shlex_quote(s):
+    def compat_shlex_quote(s):
         if re.match(r'^[-_\w./]+$', s):
             return s
         else:
@@ -326,9 +375,15 @@ 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
+
+    def compat_setenv(key, value, env=os.environ):
+        env[key] = value
 else:
     # Environment variables should be decoded with filesystem encoding.
     # Otherwise it will fail if any non-ASCII characters present (see #3854 #3217 #2918)
@@ -340,13 +395,19 @@ else:
             env = env.decode(get_filesystem_encoding())
         return env
 
+    def compat_setenv(key, value, env=os.environ):
+        def encode(v):
+            from .utils import get_filesystem_encoding
+            return v.encode(get_filesystem_encoding()) if isinstance(v, compat_str) else v
+        env[encode(key)] = encode(value)
+
     # HACK: The default implementations of os.path.expanduser from cpython do not decode
     # environment variables with filesystem encoding. We will work around this by
     # providing adjusted implementations.
     # 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 +431,7 @@ 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.
 
@@ -412,18 +473,6 @@ else:
         print(s)
 
 
-try:
-    subprocess_check_output = subprocess.check_output
-except AttributeError:
-    def subprocess_check_output(*args, **kwargs):
-        assert 'input' not in kwargs
-        p = subprocess.Popen(*args, stdout=subprocess.PIPE, **kwargs)
-        output, _ = p.communicate()
-        ret = p.poll()
-        if ret:
-            raise subprocess.CalledProcessError(ret, p.args, output=output)
-        return output
-
 if sys.version_info < (3, 0) and sys.platform == 'win32':
     def compat_getpass(prompt, *args, **kwargs):
         if isinstance(prompt, compat_str):
@@ -539,7 +588,28 @@ if sys.version_info >= (3, 0):
 else:
     from tokenize import generate_tokens as compat_tokenize_tokenize
 
+
+try:
+    struct.pack('!I', 0)
+except TypeError:
+    # In Python 2.6 and 2.7.x < 2.7.7, struct requires a bytes argument
+    # See https://bugs.python.org/issue19099
+    def compat_struct_pack(spec, *args):
+        if isinstance(spec, compat_str):
+            spec = spec.encode('ascii')
+        return struct.pack(spec, *args)
+
+    def compat_struct_unpack(spec, *args):
+        if isinstance(spec, compat_str):
+            spec = spec.encode('ascii')
+        return struct.unpack(spec, *args)
+else:
+    compat_struct_pack = struct.pack
+    compat_struct_unpack = struct.unpack
+
+
 __all__ = [
+    'compat_HTMLParser',
     'compat_HTTPError',
     'compat_basestring',
     'compat_chr',
@@ -556,11 +626,16 @@ __all__ = [
     'compat_itertools_count',
     'compat_kwargs',
     'compat_ord',
+    'compat_os_name',
     'compat_parse_qs',
     'compat_print',
+    'compat_setenv',
+    'compat_shlex_quote',
     'compat_shlex_split',
     'compat_socket_create_connection',
     'compat_str',
+    'compat_struct_pack',
+    'compat_struct_unpack',
     'compat_subprocess_get_DEVNULL',
     'compat_tokenize_tokenize',
     'compat_urllib_error',
@@ -568,6 +643,7 @@ __all__ = [
     'compat_urllib_parse_unquote',
     'compat_urllib_parse_unquote_plus',
     'compat_urllib_parse_unquote_to_bytes',
+    'compat_urllib_parse_urlencode',
     'compat_urllib_parse_urlparse',
     'compat_urllib_request',
     'compat_urllib_request_DataHandler',
@@ -575,7 +651,6 @@ __all__ = [
     'compat_urlparse',
     'compat_urlretrieve',
     'compat_xml_parse_error',
-    'shlex_quote',
-    'subprocess_check_output',
+    'compat_xpath',
     'workaround_optparse_bug9161',
 ]

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': HlsFD,
+    'm3u8_native': HlsFD,
+    'm3u8': FFmpegFD,
     'mms': RtspFD,
     'rtsp': RtspFD,
     'f4m': F4mFD,
@@ -30,14 +32,20 @@ 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
+    if protocol == 'm3u8' and params.get('hls_prefer_native') is True:
+        return HlsFD
+
+    if protocol == 'm3u8_native' and params.get('hls_prefer_native') is False:
+        return FFmpegFD
 
     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,
@@ -114,6 +115,10 @@ class FileDownloader(object):
             return '%10s' % '---b/s'
         return '%10s' % ('%s/s' % format_bytes(speed))
 
+    @staticmethod
+    def format_retries(retries):
+        return 'inf' if retries == float('inf') else '%.0f' % retries
+
     @staticmethod
     def best_block_size(elapsed_time, bytes):
         new_min = max(bytes / 2.0, 1.0)
@@ -219,7 +224,7 @@ 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):
@@ -296,7 +301,9 @@ class FileDownloader(object):
 
     def report_retry(self, count, retries):
         """Report retry in case of HTTP error 5xx"""
-        self.to_screen('[download] Got server HTTP error. Retrying (attempt %d of %.0f)...' % (count, retries))
+        self.to_screen(
+            '[download] Got server HTTP error. Retrying (attempt %d of %s)...'
+            % (count, self.format_retries(retries)))
 
     def report_file_already_downloaded(self, file_name):
         """Report file has already been fully downloaded."""

youtube_dl/downloader/dash.py

@@ -4,6 +4,7 @@ import os
 import re
 
 from .fragment import FragmentFD
+from ..compat import compat_urllib_error
 from ..utils import (
     sanitize_open,
     encodeFilename,
@@ -36,20 +37,41 @@ class DashSegmentsFD(FragmentFD):
 
         segments_filenames = []
 
-        def append_url_to_file(target_url, target_filename):
-            success = ctx['dl'].download(target_filename, {'url': combine_url(base_url, target_url)})
-            if not success:
+        fragment_retries = self.params.get('fragment_retries', 0)
+
+        def append_url_to_file(target_url, tmp_filename, segment_name):
+            target_filename = '%s-%s' % (tmp_filename, segment_name)
+            count = 0
+            while count <= fragment_retries:
+                try:
+                    success = ctx['dl'].download(target_filename, {'url': combine_url(base_url, target_url)})
+                    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)
+                    break
+                except (compat_urllib_error.HTTPError, ) as err:
+                    # YouTube may often return 404 HTTP error for a fragment causing the
+                    # whole download to fail. However if the same fragment is immediately
+                    # retried with the same request data this usually succeeds (1-2 attemps
+                    # is usually enough) thus allowing to download the whole file successfully.
+                    # So, we will retry all fragments that fail with 404 HTTP error for now.
+                    if err.code != 404:
+                        raise
+                    # Retry fragment
+                    count += 1
+                    if count <= fragment_retries:
+                        self.report_retry_fragment(segment_name, count, fragment_retries)
+            if count > fragment_retries:
+                self.report_error('giving up after %s fragment retries' % fragment_retries)
                 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')
+            append_url_to_file(initialization_url, ctx['tmpfilename'], 'Init')
         for i, segment_url in enumerate(segment_urls):
-            segment_filename = '%s-Seg%d' % (ctx['tmpfilename'], i)
-            append_url_to_file(segment_url, segment_filename)
+            append_url_to_file(segment_url, ctx['tmpfilename'], 'Seg%d' % i)
 
         self._finish_frag_download(ctx)
 

youtube_dl/downloader/external.py

@@ -2,8 +2,12 @@ from __future__ import unicode_literals
 
 import os.path
 import subprocess
+import sys
+import re
 
 from .common import FileDownloader
+from ..compat import compat_setenv
+from ..postprocessor.ffmpeg import FFmpegPostProcessor, EXT_TO_OUT_FORMATS
 from ..utils import (
     cli_option,
     cli_valueless_option,
@@ -11,6 +15,8 @@ from ..utils import (
     cli_configuration_args,
     encodeFilename,
     encodeArgument,
+    handle_youtubedl_headers,
+    check_executable,
 )
 
 
@@ -45,10 +51,18 @@ 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 +90,8 @@ 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 +105,8 @@ 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 +117,8 @@ 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 +132,8 @@ 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 +152,124 @@ 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())]
+
+        env = None
+        proxy = self.params.get('proxy')
+        if proxy:
+            if not re.match(r'^[\da-zA-Z]+://', proxy):
+                proxy = 'http://%s' % proxy
+            # Since December 2015 ffmpeg supports -http_proxy option (see
+            # http://git.videolan.org/?p=ffmpeg.git;a=commit;h=b4eb1f29ebddd60c41a2eb39f5af701e38e0d3fd)
+            # We could switch to the following code if we are able to detect version properly
+            # args += ['-http_proxy', proxy]
+            env = os.environ.copy()
+            compat_setenv('HTTP_PROXY', proxy, env=env)
+
+        protocol = info_dict.get('protocol')
+
+        if protocol == 'rtmp':
+            player_url = info_dict.get('player_url')
+            page_url = info_dict.get('page_url')
+            app = info_dict.get('app')
+            play_path = info_dict.get('play_path')
+            tc_url = info_dict.get('tc_url')
+            flash_version = info_dict.get('flash_version')
+            live = info_dict.get('rtmp_live', False)
+            if player_url is not None:
+                args += ['-rtmp_swfverify', player_url]
+            if page_url is not None:
+                args += ['-rtmp_pageurl', page_url]
+            if app is not None:
+                args += ['-rtmp_app', app]
+            if play_path is not None:
+                args += ['-rtmp_playpath', play_path]
+            if tc_url is not None:
+                args += ['-rtmp_tcurl', tc_url]
+            if flash_version is not None:
+                args += ['-rtmp_flashver', flash_version]
+            if live:
+                args += ['-rtmp_live', 'live']
+
+        args += ['-i', url, '-c', 'copy']
+        if protocol in ('m3u8', 'm3u8_native'):
+            if self.params.get('hls_use_mpegts', False) or tmpfilename == '-':
+                args += ['-f', 'mpegts']
+            else:
+                args += ['-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
+        elif protocol == 'rtmp':
+            args += ['-f', 'flv']
+        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, env=env)
+        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/f4m.py

@@ -12,37 +12,49 @@ from ..compat import (
     compat_urlparse,
     compat_urllib_error,
     compat_urllib_parse_urlparse,
+    compat_struct_pack,
+    compat_struct_unpack,
 )
 from ..utils import (
     encodeFilename,
     fix_xml_ampersands,
     sanitize_open,
-    struct_pack,
-    struct_unpack,
     xpath_text,
 )
 
 
+class DataTruncatedError(Exception):
+    pass
+
+
 class FlvReader(io.BytesIO):
     """
     Reader for Flv files
     The file format is documented in https://www.adobe.com/devnet/f4v.html
     """
 
+    def read_bytes(self, n):
+        data = self.read(n)
+        if len(data) < n:
+            raise DataTruncatedError(
+                'FlvReader error: need %d bytes while only %d bytes got' % (
+                    n, len(data)))
+        return data
+
     # Utility functions for reading numbers and strings
     def read_unsigned_long_long(self):
-        return struct_unpack('!Q', self.read(8))[0]
+        return compat_struct_unpack('!Q', self.read_bytes(8))[0]
 
     def read_unsigned_int(self):
-        return struct_unpack('!I', self.read(4))[0]
+        return compat_struct_unpack('!I', self.read_bytes(4))[0]
 
     def read_unsigned_char(self):
-        return struct_unpack('!B', self.read(1))[0]
+        return compat_struct_unpack('!B', self.read_bytes(1))[0]
 
     def read_string(self):
         res = b''
         while True:
-            char = self.read(1)
+            char = self.read_bytes(1)
             if char == b'\x00':
                 break
             res += char
@@ -53,18 +65,18 @@ class FlvReader(io.BytesIO):
         Read a box and return the info as a tuple: (box_size, box_type, box_data)
         """
         real_size = size = self.read_unsigned_int()
-        box_type = self.read(4)
+        box_type = self.read_bytes(4)
         header_end = 8
         if size == 1:
             real_size = self.read_unsigned_long_long()
             header_end = 16
-        return real_size, box_type, self.read(real_size - header_end)
+        return real_size, box_type, self.read_bytes(real_size - header_end)
 
     def read_asrt(self):
         # version
         self.read_unsigned_char()
         # flags
-        self.read(3)
+        self.read_bytes(3)
         quality_entry_count = self.read_unsigned_char()
         # QualityEntryCount
         for i in range(quality_entry_count):
@@ -85,7 +97,7 @@ class FlvReader(io.BytesIO):
         # version
         self.read_unsigned_char()
         # flags
-        self.read(3)
+        self.read_bytes(3)
         # time scale
         self.read_unsigned_int()
 
@@ -119,7 +131,7 @@ class FlvReader(io.BytesIO):
         # version
         self.read_unsigned_char()
         # flags
-        self.read(3)
+        self.read_bytes(3)
 
         self.read_unsigned_int()  # BootstrapinfoVersion
         # Profile,Live,Update,Reserved
@@ -194,11 +206,11 @@ def build_fragments_list(boot_info):
 
 
 def write_unsigned_int(stream, val):
-    stream.write(struct_pack('!I', val))
+    stream.write(compat_struct_pack('!I', val))
 
 
 def write_unsigned_int_24(stream, val):
-    stream.write(struct_pack('!I', val)[1:])
+    stream.write(compat_struct_pack('!I', val)[1:])
 
 
 def write_flv_header(stream):
@@ -223,6 +235,12 @@ def write_metadata_tag(stream, metadata):
         write_unsigned_int(stream, FLV_TAG_HEADER_LEN + len(metadata))
 
 
+def remove_encrypted_media(media):
+    return list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib and
+                                 'drmAdditionalHeaderSetId' not in e.attrib,
+                       media))
+
+
 def _add_ns(prop):
     return '{http://ns.adobe.com/f4m/1.0}%s' % prop
 
@@ -244,9 +262,7 @@ class F4mFD(FragmentFD):
             # without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
             if 'id' not in e.attrib:
                 self.report_error('Missing ID in f4m DRM')
-        media = list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib and
-                                      'drmAdditionalHeaderSetId' not in e.attrib,
-                            media))
+        media = remove_encrypted_media(media)
         if not media:
             self.report_error('Unsupported DRM')
         return media
@@ -303,7 +319,7 @@ class F4mFD(FragmentFD):
         doc = compat_etree_fromstring(manifest)
         formats = [(int(f.attrib.get('bitrate', -1)), f)
                    for f in self._get_unencrypted_media(doc)]
-        if requested_bitrate is None:
+        if requested_bitrate is None or len(formats) == 1:
             # get the best format
             formats = sorted(formats, key=lambda f: f[0])
             rate, media = formats[-1]
@@ -370,7 +386,17 @@ class F4mFD(FragmentFD):
                 down.close()
                 reader = FlvReader(down_data)
                 while True:
-                    _, box_type, box_data = reader.read_box_info()
+                    try:
+                        _, box_type, box_data = reader.read_box_info()
+                    except DataTruncatedError:
+                        if test:
+                            # In tests, segments may be truncated, and thus
+                            # FlvReader may not be able to parse the whole
+                            # chunk. If so, write the segment as is
+                            # See https://github.com/rg3/youtube-dl/issues/9214
+                            dest_stream.write(down_data)
+                            break
+                        raise
                     if box_type == b'mdat':
                         dest_stream.write(box_data)
                         break

youtube_dl/downloader/fragment.py

@@ -19,8 +19,17 @@ class HttpQuietDownloader(HttpFD):
 class FragmentFD(FileDownloader):
     """
     A base file downloader class for fragmented media (e.g. f4m/m3u8 manifests).
+
+    Available options:
+
+    fragment_retries:   Number of times to retry a fragment for HTTP error (DASH only)
     """
 
+    def report_retry_fragment(self, fragment_name, count, retries):
+        self.to_screen(
+            '[download] Got server HTTP error. Retrying fragment %s (attempt %d of %s)...'
+            % (fragment_name, count, self.format_retries(retries)))
+
     def _prepare_and_start_frag_download(self, ctx):
         self._prepare_frag_download(ctx)
         self._start_frag_download(ctx)
@@ -99,7 +108,8 @@ 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

@@ -1,96 +1,56 @@
 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 .external import FFmpegFD
 
 from ..compat import compat_urlparse
-from ..postprocessor.ffmpeg import FFmpegPostProcessor
 from ..utils import (
-    encodeArgument,
     encodeFilename,
     sanitize_open,
-    handle_youtubedl_headers,
 )
 
 
-class HlsFD(FileDownloader):
-    def real_download(self, filename, info_dict):
-        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 """
+class HlsFD(FragmentFD):
+    """ A limited implementation that does not require ffmpeg """
 
     FD_NAME = 'hlsnative'
 
+    @staticmethod
+    def can_download(manifest):
+        UNSUPPORTED_FEATURES = (
+            r'#EXT-X-KEY:METHOD=(?!NONE)',  # encrypted streams [1]
+            r'#EXT-X-BYTERANGE',  # playlists composed of byte ranges of media files [2]
+            # Live streams heuristic does not always work (e.g. geo restricted to Germany
+            # http://hls-geo.daserste.de/i/videoportal/Film/c_620000/622873/format,716451,716457,716450,716458,716459,.mp4.csmil/index_4_av.m3u8?null=0)
+            # r'#EXT-X-MEDIA-SEQUENCE:(?!0$)',  # live streams [3]
+            r'#EXT-X-PLAYLIST-TYPE:EVENT',  # media segments may be appended to the end of
+                                            # event media playlists [4]
+            # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.4
+            # 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.2
+            # 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.2
+            # 4. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.5
+        )
+        return all(not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES)
+
     def real_download(self, filename, info_dict):
         man_url = info_dict['url']
         self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME)
         manifest = self.ydl.urlopen(man_url).read()
 
         s = manifest.decode('utf-8', 'ignore')
+
+        if not self.can_download(s):
+            self.report_warning(
+                'hlsnative has detected features it does not support, '
+                'extraction will be delegated to ffmpeg')
+            fd = FFmpegFD(self.ydl, self.params)
+            for ph in self._progress_hooks:
+                fd.add_progress_hook(ph)
+            return fd.real_download(filename, info_dict)
+
         fragment_urls = []
         for line in s.splitlines():
             line = line.strip()

youtube_dl/downloader/rtsp.py

@@ -27,6 +27,8 @@ class RtspFD(FileDownloader):
             self.report_error('MMS or RTSP download detected but neither "mplayer" nor "mpv" could be run. Please install any.')
             return False
 
+        self._debug_cmd(args)
+
         retval = subprocess.call(args)
         if retval == 0:
             fsize = os.path.getsize(encodeFilename(tmpfilename))

youtube_dl/extractor/__init__.py

@@ -1,975 +1,33 @@
 from __future__ import unicode_literals
 
-from .abc import ABCIE
-from .abc7news import Abc7NewsIE
-from .academicearth import AcademicEarthCourseIE
-from .acast import (
-    ACastIE,
-    ACastChannelIE,
-)
-from .addanime import AddAnimeIE
-from .adobetv import (
-    AdobeTVIE,
-    AdobeTVShowIE,
-    AdobeTVChannelIE,
-    AdobeTVVideoIE,
-)
-from .adultswim import AdultSwimIE
-from .aenetworks import AENetworksIE
-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 .allocine import AllocineIE
-from .aparat import AparatIE
-from .appleconnect import AppleConnectIE
-from .appletrailers import (
-    AppleTrailersIE,
-    AppleTrailersSectionIE,
-)
-from .archiveorg import ArchiveOrgIE
-from .ard import (
-    ARDIE,
-    ARDMediathekIE,
-    SportschauIE,
-)
-from .arte import (
-    ArteTvIE,
-    ArteTVPlus7IE,
-    ArteTVCreativeIE,
-    ArteTVConcertIE,
-    ArteTVFutureIE,
-    ArteTVCinemaIE,
-    ArteTVDDCIE,
-    ArteTVMagazineIE,
-    ArteTVEmbedIE,
-)
-from .atresplayer import AtresPlayerIE
-from .atttechchannel import ATTTechChannelIE
-from .audimedia import AudiMediaIE
-from .audiomack import AudiomackIE, AudiomackAlbumIE
-from .azubu import AzubuIE, AzubuLiveIE
-from .baidu import BaiduVideoIE
-from .bambuser import BambuserIE, BambuserChannelIE
-from .bandcamp import BandcampIE, BandcampAlbumIE
-from .bbc import (
-    BBCCoUkIE,
-    BBCCoUkArticleIE,
-    BBCIE,
-)
-from .beeg import BeegIE
-from .behindkink import BehindKinkIE
-from .beatportpro import BeatportProIE
-from .bet import BetIE
-from .bigflix import BigflixIE
-from .bild import BildIE
-from .bilibili import BiliBiliIE
-from .bleacherreport import (
-    BleacherReportIE,
-    BleacherReportCMSIE,
-)
-from .blinkx import BlinkxIE
-from .bloomberg import BloombergIE
-from .bokecc import BokeCCIE
-from .bpb import BpbIE
-from .br import BRIE
-from .breakcom import BreakIE
-from .brightcove import (
-    BrightcoveLegacyIE,
-    BrightcoveNewIE,
-)
-from .buzzfeed import BuzzFeedIE
-from .byutv import BYUtvIE
-from .c56 import C56IE
-from .camdemy import (
-    CamdemyIE,
-    CamdemyFolderIE
-)
-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,
-    CBSNewsLiveVideoIE,
-)
-from .cbssports import CBSSportsIE
-from .ccc import CCCIE
-from .ceskatelevize import CeskaTelevizeIE
-from .channel9 import Channel9IE
-from .chaturbate import ChaturbateIE
-from .chilloutzone import ChilloutzoneIE
-from .chirbit import (
-    ChirbitIE,
-    ChirbitProfileIE,
-)
-from .cinchcast import CinchcastIE
-from .cinemassacre import CinemassacreIE
-from .clipfish import ClipfishIE
-from .cliphunter import CliphunterIE
-from .clipsyndicate import ClipsyndicateIE
-from .cloudy import CloudyIE
-from .clubic import ClubicIE
-from .clyp import ClypIE
-from .cmt import CMTIE
-from .cnet import CNETIE
-from .cnn import (
-    CNNIE,
-    CNNBlogsIE,
-    CNNArticleIE,
-)
-from .collegehumor import CollegeHumorIE
-from .collegerama import CollegeRamaIE
-from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
-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 (
-    CrunchyrollIE,
-    CrunchyrollShowPlaylistIE
-)
-from .cspan import CSpanIE
-from .ctsnews import CtsNewsIE
-from .cultureunplugged import CultureUnpluggedIE
-from .cwtv import CWTVIE
-from .dailymotion import (
-    DailymotionIE,
-    DailymotionPlaylistIE,
-    DailymotionUserIE,
-    DailymotionCloudIE,
-)
-from .daum import (
-    DaumIE,
-    DaumClipIE,
-    DaumPlaylistIE,
-    DaumUserIE,
-)
-from .dbtv import DBTVIE
-from .dcn import (
-    DCNIE,
-    DCNVideoIE,
-    DCNLiveIE,
-    DCNSeasonIE,
-)
-from .dctp import DctpTvIE
-from .deezer import DeezerPlaylistIE
-from .democracynow import DemocracynowIE
-from .dfb import DFBIE
-from .dhm import DHMIE
-from .dotsub import DotsubIE
-from .douyutv import DouyuTVIE
-from .dplay import DPlayIE
-from .dramafever import (
-    DramaFeverIE,
-    DramaFeverSeriesIE,
-)
-from .dreisat import DreiSatIE
-from .drbonanza import DRBonanzaIE
-from .drtuber import DrTuberIE
-from .drtv import DRTVIE
-from .dvtv import DVTVIE
-from .dump import DumpIE
-from .dumpert import DumpertIE
-from .defense import DefenseGouvFrIE
-from .discovery import DiscoveryIE
-from .dropbox import DropboxIE
-from .eagleplatform import EaglePlatformIE
-from .ebaumsworld import EbaumsWorldIE
-from .echomsk import EchoMskIE
-from .ehow import EHowIE
-from .eighttracks import EightTracksIE
-from .einthusan import EinthusanIE
-from .eitb import EitbIE
-from .ellentv import (
-    EllenTVIE,
-    EllenTVClipsIE,
-)
-from .elpais import ElPaisIE
-from .embedly import EmbedlyIE
-from .engadget import EngadgetIE
-from .eporner import EpornerIE
-from .eroprofile import EroProfileIE
-from .escapist import EscapistIE
-from .espn import ESPNIE
-from .esri import EsriVideoIE
-from .europa import EuropaIE
-from .everyonesmixtape import EveryonesMixtapeIE
-from .exfm import ExfmIE
-from .expotv import ExpoTVIE
-from .extremetube import ExtremeTubeIE
-from .facebook import (
-    FacebookIE,
-    FacebookPostIE,
-)
-from .faz import FazIE
-from .fc2 import FC2IE
-from .fczenit import FczenitIE
-from .firstpost import FirstpostIE
-from .firsttv import FirstTVIE
-from .fivemin import FiveMinIE
-from .fivetv import FiveTVIE
-from .fktv import FKTVIE
-from .flickr import FlickrIE
-from .folketinget import FolketingetIE
-from .footyroom import FootyRoomIE
-from .fourtube import FourTubeIE
-from .fox import FOXIE
-from .foxgay import FoxgayIE
-from .foxnews import FoxNewsIE
-from .foxsports import FoxSportsIE
-from .franceculture import (
-    FranceCultureIE,
-    FranceCultureEmissionIE,
-)
-from .franceinter import FranceInterIE
-from .francetv import (
-    PluzzIE,
-    FranceTvInfoIE,
-    FranceTVIE,
-    GenerationQuoiIE,
-    CultureboxIE,
-)
-from .freesound import FreesoundIE
-from .freespeech import FreespeechIE
-from .freevideo import FreeVideoIE
-from .funimation import FunimationIE
-from .funnyordie import FunnyOrDieIE
-from .gameinformer import GameInformerIE
-from .gamekings import GamekingsIE
-from .gameone import (
-    GameOneIE,
-    GameOnePlaylistIE,
-)
-from .gamersyde import GamersydeIE
-from .gamespot import GameSpotIE
-from .gamestar import GameStarIE
-from .gametrailers import GametrailersIE
-from .gazeta import GazetaIE
-from .gdcvault import GDCVaultIE
-from .generic import GenericIE
-from .gfycat import GfycatIE
-from .giantbomb import GiantBombIE
-from .giga import GigaIE
-from .glide import GlideIE
-from .globo import (
-    GloboIE,
-    GloboArticleIE,
-)
-from .godtube import GodTubeIE
-from .goldenmoustache import GoldenMoustacheIE
-from .golem import GolemIE
-from .googledrive import GoogleDriveIE
-from .googleplus import GooglePlusIE
-from .googlesearch import GoogleSearchIE
-from .goshgay import GoshgayIE
-from .gputechconf import GPUTechConfIE
-from .groupon import GrouponIE
-from .hark import HarkIE
-from .hearthisat import HearThisAtIE
-from .heise import HeiseIE
-from .hellporno import HellPornoIE
-from .helsinki import HelsinkiIE
-from .hentaistigma import HentaiStigmaIE
-from .historicfilms import HistoricFilmsIE
-from .hitbox import HitboxIE, HitboxLiveIE
-from .hornbunny import HornBunnyIE
-from .hotnewhiphop import HotNewHipHopIE
-from .hotstar import HotStarIE
-from .howcast import HowcastIE
-from .howstuffworks import HowStuffWorksIE
-from .huffpost import HuffPostIE
-from .hypem import HypemIE
-from .iconosquare import IconosquareIE
-from .ign import (
-    IGNIE,
-    OneUPIE,
-    PCMagIE,
-)
-from .imdb import (
-    ImdbIE,
-    ImdbListIE
-)
-from .imgur import (
-    ImgurIE,
-    ImgurAlbumIE,
-)
-from .ina import InaIE
-from .indavideo import (
-    IndavideoIE,
-    IndavideoEmbedIE,
-)
-from .infoq import InfoQIE
-from .instagram import InstagramIE, InstagramUserIE
-from .internetvideoarchive import InternetVideoArchiveIE
-from .iprima import IPrimaIE
-from .iqiyi import IqiyiIE
-from .ir90tv import Ir90TvIE
-from .ivi import (
-    IviIE,
-    IviCompilationIE
-)
-from .ivideon import IvideonIE
-from .izlesene import IzleseneIE
-from .jadorecettepub import JadoreCettePubIE
-from .jeuxvideo import JeuxVideoIE
-from .jove import JoveIE
-from .jwplatform import JWPlatformIE
-from .jpopsukitv import JpopsukiIE
-from .kaltura import KalturaIE
-from .kanalplay import KanalPlayIE
-from .kankan import KankanIE
-from .karaoketv import KaraoketvIE
-from .karrierevideos import KarriereVideosIE
-from .keezmovies import KeezMoviesIE
-from .khanacademy import KhanAcademyIE
-from .kickstarter import KickStarterIE
-from .keek import KeekIE
-from .konserthusetplay import KonserthusetPlayIE
-from .kontrtube import KontrTubeIE
-from .krasview import KrasViewIE
-from .ku6 import Ku6IE
-from .kuwo import (
-    KuwoIE,
-    KuwoAlbumIE,
-    KuwoChartIE,
-    KuwoSingerIE,
-    KuwoCategoryIE,
-    KuwoMvIE,
-)
-from .la7 import LA7IE
-from .laola1tv import Laola1TvIE
-from .lecture2go import Lecture2GoIE
-from .lemonde import LemondeIE
-from .letv import (
-    LetvIE,
-    LetvTvIE,
-    LetvPlaylistIE,
-    LetvCloudIE,
-)
-from .libsyn import LibsynIE
-from .lifenews import (
-    LifeNewsIE,
-    LifeEmbedIE,
-)
-from .limelight import (
-    LimelightMediaIE,
-    LimelightChannelIE,
-    LimelightChannelListIE,
-)
-from .liveleak import LiveLeakIE
-from .livestream import (
-    LivestreamIE,
-    LivestreamOriginalIE,
-    LivestreamShortenerIE,
-)
-from .lnkgo import LnkGoIE
-from .lovehomeporn import LoveHomePornIE
-from .lrt import LRTIE
-from .lynda import (
-    LyndaIE,
-    LyndaCourseIE
-)
-from .m6 import M6IE
-from .macgamestore import MacGameStoreIE
-from .mailru import MailRuIE
-from .makertv import MakerTVIE
-from .malemotion import MalemotionIE
-from .matchtv import MatchTVIE
-from .mdr import MDRIE
-from .metacafe import MetacafeIE
-from .metacritic import MetacriticIE
-from .mgoon import MgoonIE
-from .minhateca import MinhatecaIE
-from .ministrygrid import MinistryGridIE
-from .miomio import MioMioIE
-from .mit import TechTVMITIE, MITIE, OCWMITIE
-from .mitele import MiTeleIE
-from .mixcloud import MixcloudIE
-from .mlb import MLBIE
-from .mpora import MporaIE
-from .moevideo import MoeVideoIE
-from .mofosex import MofosexIE
-from .mojvideo import MojvideoIE
-from .moniker import MonikerIE
-from .mooshare import MooshareIE
-from .morningstar import MorningstarIE
-from .motherless import MotherlessIE
-from .motorsport import MotorsportIE
-from .movieclips import MovieClipsIE
-from .moviezine import MoviezineIE
-from .mtv import (
-    MTVIE,
-    MTVServicesEmbeddedIE,
-    MTVIggyIE,
-    MTVDEIE,
-)
-from .muenchentv import MuenchenTVIE
-from .musicplayon import MusicPlayOnIE
-from .muzu import MuzuTVIE
-from .mwave import MwaveIE
-from .myspace import MySpaceIE, MySpaceAlbumIE
-from .myspass import MySpassIE
-from .myvi import MyviIE
-from .myvideo import MyVideoIE
-from .myvidster import MyVidsterIE
-from .nationalgeographic import NationalGeographicIE
-from .naver import NaverIE
-from .nba import NBAIE
-from .nbc import (
-    NBCIE,
-    NBCNewsIE,
-    NBCSportsIE,
-    NBCSportsVPlayerIE,
-    MSNBCIE,
-)
-from .ndr import (
-    NDRIE,
-    NJoyIE,
-    NDREmbedBaseIE,
-    NDREmbedIE,
-    NJoyEmbedIE,
-)
-from .ndtv import NDTVIE
-from .netzkino import NetzkinoIE
-from .nerdcubed import NerdCubedFeedIE
-from .nerdist import NerdistIE
-from .neteasemusic import (
-    NetEaseMusicIE,
-    NetEaseMusicAlbumIE,
-    NetEaseMusicSingerIE,
-    NetEaseMusicListIE,
-    NetEaseMusicMvIE,
-    NetEaseMusicProgramIE,
-    NetEaseMusicDjRadioIE,
-)
-from .newgrounds import NewgroundsIE
-from .newstube import NewstubeIE
-from .nextmedia import (
-    NextMediaIE,
-    NextMediaActionNewsIE,
-    AppleDailyIE,
-)
-from .nextmovie import NextMovieIE
-from .nfb import NFBIE
-from .nfl import NFLIE
-from .nhl import (
-    NHLIE,
-    NHLNewsIE,
-    NHLVideocenterIE,
-)
-from .nick import NickIE
-from .niconico import NiconicoIE, NiconicoPlaylistIE
-from .ninegag import NineGagIE
-from .noco import NocoIE
-from .normalboots import NormalbootsIE
-from .nosvideo import NosVideoIE
-from .nova import NovaIE
-from .novamov import (
-    NovaMovIE,
-    WholeCloudIE,
-    NowVideoIE,
-    VideoWeedIE,
-    CloudTimeIE,
-)
-from .nowness import (
-    NownessIE,
-    NownessPlaylistIE,
-    NownessSeriesIE,
-)
-from .nowtv import (
-    NowTVIE,
-    NowTVListIE,
-)
-from .noz import NozIE
-from .npo import (
-    NPOIE,
-    NPOLiveIE,
-    NPORadioIE,
-    NPORadioFragmentIE,
-    SchoolTVIE,
-    VPROIE,
-    WNLIE
-)
-from .npr import NprIE
-from .nrk import (
-    NRKIE,
-    NRKPlaylistIE,
-    NRKTVIE,
-)
-from .ntvde import NTVDeIE
-from .ntvru import NTVRuIE
-from .nytimes import (
-    NYTimesIE,
-    NYTimesArticleIE,
-)
-from .nuvid import NuvidIE
-from .odnoklassniki import OdnoklassnikiIE
-from .oktoberfesttv import OktoberfestTVIE
-from .onionstudios import OnionStudiosIE
-from .ooyala import (
-    OoyalaIE,
-    OoyalaExternalIE,
-)
-from .ora import OraTVIE
-from .orf import (
-    ORFTVthekIE,
-    ORFOE1IE,
-    ORFFM4IE,
-    ORFIPTVIE,
-)
-from .pandoratv import PandoraTVIE
-from .parliamentliveuk import ParliamentLiveUKIE
-from .patreon import PatreonIE
-from .pbs import PBSIE
-from .periscope import PeriscopeIE
-from .philharmoniedeparis import PhilharmonieDeParisIE
-from .phoenix import PhoenixIE
-from .photobucket import PhotobucketIE
-from .pinkbike import PinkbikeIE
-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
-from .pluralsight import (
-    PluralsightIE,
-    PluralsightCourseIE,
-)
-from .podomatic import PodomaticIE
-from .porn91 import Porn91IE
-from .pornhd import PornHdIE
-from .pornhub import (
-    PornHubIE,
-    PornHubPlaylistIE,
-    PornHubUserVideosIE,
-)
-from .pornotube import PornotubeIE
-from .pornovoisines import PornoVoisinesIE
-from .pornoxo import PornoXOIE
-from .primesharetv import PrimeShareTVIE
-from .promptfile import PromptFileIE
-from .prosiebensat1 import ProSiebenSat1IE
-from .puls4 import Puls4IE
-from .pyvideo import PyvideoIE
-from .qqmusic import (
-    QQMusicIE,
-    QQMusicSingerIE,
-    QQMusicAlbumIE,
-    QQMusicToplistIE,
-    QQMusicPlaylistIE,
-)
-from .quickvid import QuickVidIE
-from .r7 import R7IE
-from .radiode import RadioDeIE
-from .radiojavan import RadioJavanIE
-from .radiobremen import RadioBremenIE
-from .radiofrance import RadioFranceIE
-from .rai import (
-    RaiTVIE,
-    RaiIE,
-)
-from .rbmaradio import RBMARadioIE
-from .rds import RDSIE
-from .redtube import RedTubeIE
-from .regiotv import RegioTVIE
-from .restudy import RestudyIE
-from .reverbnation import ReverbNationIE
-from .revision3 import Revision3IE
-from .ringtv import RingTVIE
-from .ro220 import Ro220IE
-from .rottentomatoes import RottenTomatoesIE
-from .roxwel import RoxwelIE
-from .rtbf import RTBFIE
-from .rte import RteIE, RteRadioIE
-from .rtlnl import RtlNlIE
-from .rtl2 import RTL2IE
-from .rtp import RTPIE
-from .rts import RTSIE
-from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
-from .rtvnh import RTVNHIE
-from .ruhd import RUHDIE
-from .ruleporn import RulePornIE
-from .rutube import (
-    RutubeIE,
-    RutubeChannelIE,
-    RutubeEmbedIE,
-    RutubeMovieIE,
-    RutubePersonIE,
-)
-from .rutv import RUTVIE
-from .ruutu import RuutuIE
-from .sandia import SandiaIE
-from .safari import (
-    SafariIE,
-    SafariCourseIE,
-)
-from .sapo import SapoIE
-from .savefrom import SaveFromIE
-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
-from .sexu import SexuIE
-from .sexykarma import SexyKarmaIE
-from .shahid import ShahidIE
-from .shared import SharedIE
-from .sharesix import ShareSixIE
-from .sina import SinaIE
-from .skynewsarabia import (
-    SkyNewsArabiaIE,
-    SkyNewsArabiaArticleIE,
-)
-from .slideshare import SlideshareIE
-from .slutload import SlutloadIE
-from .smotri import (
-    SmotriIE,
-    SmotriCommunityIE,
-    SmotriUserIE,
-    SmotriBroadcastIE,
-)
-from .snagfilms import (
-    SnagFilmsIE,
-    SnagFilmsEmbedIE,
-)
-from .snotr import SnotrIE
-from .sohu import SohuIE
-from .soundcloud import (
-    SoundcloudIE,
-    SoundcloudSetIE,
-    SoundcloudUserIE,
-    SoundcloudPlaylistIE,
-    SoundcloudSearchIE
-)
-from .soundgasm import (
-    SoundgasmIE,
-    SoundgasmProfileIE
-)
-from .southpark import (
-    SouthParkIE,
-    SouthParkDeIE,
-    SouthParkDkIE,
-    SouthParkEsIE,
-    SouthParkNlIE
-)
-from .spankbang import SpankBangIE
-from .spankwire import SpankwireIE
-from .spiegel import SpiegelIE, SpiegelArticleIE
-from .spiegeltv import SpiegeltvIE
-from .spike import SpikeIE
-from .stitcher import StitcherIE
-from .sport5 import Sport5IE
-from .sportbox import (
-    SportBoxIE,
-    SportBoxEmbedIE,
-)
-from .sportdeutschland import SportDeutschlandIE
-from .srgssr import (
-    SRGSSRIE,
-    SRGSSRPlayIE,
-)
-from .srmediathek import SRMediathekIE
-from .ssa import SSAIE
-from .stanfordoc import StanfordOpenClassroomIE
-from .steam import SteamIE
-from .streamcloud import StreamcloudIE
-from .streamcz import StreamCZIE
-from .streetvoice import StreetVoiceIE
-from .sunporno import SunPornoIE
-from .svt import (
-    SVTIE,
-    SVTPlayIE,
-)
-from .swrmediathek import SWRMediathekIE
-from .syfy import SyfyIE
-from .sztvhu import SztvHuIE
-from .tagesschau import TagesschauIE
-from .tapely import TapelyIE
-from .tass import TassIE
-from .teachertube import (
-    TeacherTubeIE,
-    TeacherTubeUserIE,
-)
-from .teachingchannel import TeachingChannelIE
-from .teamcoco import TeamcocoIE
-from .techtalks import TechTalksIE
-from .ted import TEDIE
-from .tele13 import Tele13IE
-from .telebruxelles import TeleBruxellesIE
-from .telecinco import TelecincoIE
-from .telegraaf import TelegraafIE
-from .telemb import TeleMBIE
-from .teletask import TeleTaskIE
-from .tenplay import TenPlayIE
-from .testurl import TestURLIE
-from .tf1 import TF1IE
-from .theintercept import TheInterceptIE
-from .theonion import TheOnionIE
-from .theplatform import (
-    ThePlatformIE,
-    ThePlatformFeedIE,
-)
-from .thesixtyone import TheSixtyOneIE
-from .thisamericanlife import ThisAmericanLifeIE
-from .thisav import ThisAVIE
-from .tinypic import TinyPicIE
-from .tlc import TlcDeIE
-from .tmz import (
-    TMZIE,
-    TMZArticleIE,
-)
-from .tnaflix import (
-    TNAFlixNetworkEmbedIE,
-    TNAFlixIE,
-    EMPFlixIE,
-    MovieFapIE,
-)
-from .toggle import ToggleIE
-from .thvideo import (
-    THVideoIE,
-    THVideoPlaylistIE
-)
-from .toutv import TouTvIE
-from .toypics import ToypicsUserIE, ToypicsIE
-from .traileraddict import TrailerAddictIE
-from .trilulilu import TriluliluIE
-from .trollvids import TrollvidsIE
-from .trutube import TruTubeIE
-from .tube8 import Tube8IE
-from .tubitv import TubiTvIE
-from .tudou import (
-    TudouIE,
-    TudouPlaylistIE,
-    TudouAlbumIE,
-)
-from .tumblr import TumblrIE
-from .tunein import (
-    TuneInClipIE,
-    TuneInStationIE,
-    TuneInProgramIE,
-    TuneInTopicIE,
-    TuneInShortenerIE,
-)
-from .turbo import TurboIE
-from .tutv import TutvIE
-from .tv2 import (
-    TV2IE,
-    TV2ArticleIE,
-)
-from .tv4 import TV4IE
-from .tvc import (
-    TVCIE,
-    TVCArticleIE,
-)
-from .tvigle import TvigleIE
-from .tvland import TVLandIE
-from .tvp import TvpIE, TvpSeriesIE
-from .tvplay import TVPlayIE
-from .tweakers import TweakersIE
-from .twentyfourvideo import TwentyFourVideoIE
-from .twentymin import TwentyMinutenIE
-from .twentytwotracks import (
-    TwentyTwoTracksIE,
-    TwentyTwoTracksGenreIE
-)
-from .twitch import (
-    TwitchVideoIE,
-    TwitchChapterIE,
-    TwitchVodIE,
-    TwitchProfileIE,
-    TwitchPastBroadcastsIE,
-    TwitchBookmarksIE,
-    TwitchStreamIE,
-)
-from .twitter import (
-    TwitterCardIE,
-    TwitterIE,
-    TwitterAmplifyIE,
-)
-from .ubu import UbuIE
-from .udemy import (
-    UdemyIE,
-    UdemyCourseIE
-)
-from .udn import UDNEmbedIE
-from .digiteka import DigitekaIE
-from .unistra import UnistraIE
-from .urort import UrortIE
-from .ustream import UstreamIE, UstreamChannelIE
-from .ustudio import UstudioIE
-from .varzesh3 import Varzesh3IE
-from .vbox7 import Vbox7IE
-from .veehd import VeeHDIE
-from .veoh import VeohIE
-from .vessel import VesselIE
-from .vesti import VestiIE
-from .vevo import VevoIE
-from .vgtv import (
-    BTArticleIE,
-    BTVestlendingenIE,
-    VGTVIE,
-)
-from .vh1 import VH1IE
-from .vice import ViceIE
-from .viddler import ViddlerIE
-from .videodetective import VideoDetectiveIE
-from .videofyme import VideofyMeIE
-from .videomega import VideoMegaIE
-from .videomore import (
-    VideomoreIE,
-    VideomoreVideoIE,
-    VideomoreSeasonIE,
-)
-from .videopremium import VideoPremiumIE
-from .videott import VideoTtIE
-from .vidme import (
-    VidmeIE,
-    VidmeUserIE,
-    VidmeUserLikesIE,
-)
-from .vidzi import VidziIE
-from .vier import VierIE, VierVideosIE
-from .viewster import ViewsterIE
-from .viidea import ViideaIE
-from .vimeo import (
-    VimeoIE,
-    VimeoAlbumIE,
-    VimeoChannelIE,
-    VimeoGroupsIE,
-    VimeoLikesIE,
-    VimeoReviewIE,
-    VimeoUserIE,
-    VimeoWatchLaterIE,
-)
-from .vimple import VimpleIE
-from .vine import (
-    VineIE,
-    VineUserIE,
-)
-from .viki import (
-    VikiIE,
-    VikiChannelIE,
-)
-from .vk import (
-    VKIE,
-    VKUserVideosIE,
-)
-from .vlive import VLiveIE
-from .vodlocker import VodlockerIE
-from .voicerepublic import VoiceRepublicIE
-from .vporn import VpornIE
-from .vrt import VRTIE
-from .vube import VubeIE
-from .vuclip import VuClipIE
-from .vulture import VultureIE
-from .walla import WallaIE
-from .washingtonpost import WashingtonPostIE
-from .wat import WatIE
-from .wayofthemaster import WayOfTheMasterIE
-from .wdr import (
-    WDRIE,
-    WDRMobileIE,
-    WDRMausIE,
-)
-from .webofstories import (
-    WebOfStoriesIE,
-    WebOfStoriesPlaylistIE,
-)
-from .weibo import WeiboIE
-from .weiqitv import WeiqiTVIE
-from .wimp import WimpIE
-from .wistia import WistiaIE
-from .worldstarhiphop import WorldStarHipHopIE
-from .wrzuta import WrzutaIE
-from .wsj import WSJIE
-from .xbef import XBefIE
-from .xboxclips import XboxClipsIE
-from .xfileshare import XFileShareIE
-from .xhamster import (
-    XHamsterIE,
-    XHamsterEmbedIE,
-)
-from .xminus import XMinusIE
-from .xnxx import XNXXIE
-from .xstream import XstreamIE
-from .xtube import XTubeUserIE, XTubeIE
-from .xuite import XuiteIE
-from .xvideos import XVideosIE
-from .xxxymovies import XXXYMoviesIE
-from .yahoo import (
-    YahooIE,
-    YahooSearchIE,
-)
-from .yam import YamIE
-from .yandexmusic import (
-    YandexMusicTrackIE,
-    YandexMusicAlbumIE,
-    YandexMusicPlaylistIE,
-)
-from .yesjapan import YesJapanIE
-from .yinyuetai import YinYueTaiIE
-from .ynet import YnetIE
-from .youjizz import YouJizzIE
-from .youku import YoukuIE
-from .youporn import YouPornIE
-from .yourupload import YourUploadIE
-from .youtube import (
-    YoutubeIE,
-    YoutubeChannelIE,
-    YoutubeFavouritesIE,
-    YoutubeHistoryIE,
-    YoutubePlaylistIE,
-    YoutubeRecommendedIE,
-    YoutubeSearchDateIE,
-    YoutubeSearchIE,
-    YoutubeSearchURLIE,
-    YoutubeShowIE,
-    YoutubeSubscriptionsIE,
-    YoutubeTruncatedIDIE,
-    YoutubeTruncatedURLIE,
-    YoutubeUserIE,
-    YoutubePlaylistsIE,
-    YoutubeWatchLaterIE,
-)
-from .zapiks import ZapiksIE
-from .zdf import ZDFIE, ZDFChannelIE
-from .zingmp3 import (
-    ZingMp3SongIE,
-    ZingMp3AlbumIE,
-)
-from .zippcast import ZippCastIE
+try:
+    from .lazy_extractors import *
+    from .lazy_extractors import _ALL_CLASSES
+    _LAZY_LOADER = True
+except ImportError:
+    _LAZY_LOADER = False
+    from .extractors import *
 
-_ALL_CLASSES = [
-    klass
-    for name, klass in globals().items()
-    if name.endswith('IE') and name != 'GenericIE'
-]
-_ALL_CLASSES.append(GenericIE)
+    _ALL_CLASSES = [
+        klass
+        for name, klass in globals().items()
+        if name.endswith('IE') and name != 'GenericIE'
+    ]
+    _ALL_CLASSES.append(GenericIE)
+
+
+def gen_extractor_classes():
+    """ Return a list of supported extractors.
+    The order does matter; the first extractor matched is the one handling the URL.
+    """
+    return _ALL_CLASSES
 
 
 def gen_extractors():
     """ Return a list of an instance of every supported extractor.
     The order does matter; the first extractor matched is the one handling the URL.
     """
-    return [klass() for klass in _ALL_CLASSES]
+    return [klass() for klass in gen_extractor_classes()]
 
 
 def list_extractors(age_limit):

youtube_dl/extractor/abc.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class ABCIE(InfoExtractor):
     IE_NAME = 'abc.net.au'
-    _VALID_URL = r'http://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
+    _VALID_URL = r'https?://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',

youtube_dl/extractor/abc7news.py

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

youtube_dl/extractor/abcnews.py

@@ -0,0 +1,135 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import calendar
+import re
+import time
+
+from .amp import AMPIE
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+
+
+class AbcNewsVideoIE(AMPIE):
+    IE_NAME = 'abcnews:video'
+    _VALID_URL = 'http://abcnews.go.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932',
+        'info_dict': {
+            'id': '20411932',
+            'ext': 'mp4',
+            'display_id': 'week-exclusive-irans-foreign-minister-zarif',
+            'title': '\'This Week\' Exclusive: Iran\'s Foreign Minister Zarif',
+            'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.',
+            'duration': 180,
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
+        video_id = mobj.group('id')
+        info_dict = self._extract_feed_info(
+            'http://abcnews.go.com/video/itemfeed?id=%s' % video_id)
+        info_dict.update({
+            'id': video_id,
+            'display_id': display_id,
+        })
+        return info_dict
+
+
+class AbcNewsIE(InfoExtractor):
+    IE_NAME = 'abcnews'
+    _VALID_URL = 'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY',
+        'info_dict': {
+            'id': '10498713',
+            'ext': 'flv',
+            'display_id': 'dramatic-video-rare-death-job-america',
+            'title': 'Occupational Hazards',
+            'description': 'Nightline investigates the dangers that lurk at various jobs.',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'upload_date': '20100428',
+            'timestamp': 1272412800,
+        },
+        'add_ie': ['AbcNewsVideo'],
+    }, {
+        'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818',
+        'info_dict': {
+            'id': '39125818',
+            'ext': 'mp4',
+            'display_id': 'justin-timberlake-performs-stop-feeling-eurovision-2016',
+            'title': 'Justin Timberlake Drops Hints For Secret Single',
+            'description': 'Lara Spencer reports the buzziest stories of the day in "GMA" Pop News.',
+            'upload_date': '20160515',
+            'timestamp': 1463329500,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+            # The embedded YouTube video is blocked due to copyright issues
+            'playlist_items': '1',
+        },
+        'add_ie': ['AbcNewsVideo'],
+    }, {
+        'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        video_url = self._search_regex(
+            r'window\.abcnvideo\.url\s*=\s*"([^"]+)"', webpage, 'video URL')
+        full_video_url = compat_urlparse.urljoin(url, video_url)
+
+        youtube_url = self._html_search_regex(
+            r'<iframe[^>]+src="(https://www\.youtube\.com/embed/[^"]+)"',
+            webpage, 'YouTube URL', default=None)
+
+        timestamp = None
+        date_str = self._html_search_regex(
+            r'<span[^>]+class="timestamp">([^<]+)</span>',
+            webpage, 'timestamp', fatal=False)
+        if date_str:
+            tz_offset = 0
+            if date_str.endswith(' ET'):  # Eastern Time
+                tz_offset = -5
+                date_str = date_str[:-3]
+            date_formats = ['%b. %d, %Y', '%b %d, %Y, %I:%M %p']
+            for date_format in date_formats:
+                try:
+                    timestamp = calendar.timegm(time.strptime(date_str.strip(), date_format))
+                except ValueError:
+                    continue
+            if timestamp is not None:
+                timestamp -= tz_offset * 3600
+
+        entry = {
+            '_type': 'url_transparent',
+            'ie_key': AbcNewsVideoIE.ie_key(),
+            'url': full_video_url,
+            'id': video_id,
+            'display_id': display_id,
+            'timestamp': timestamp,
+        }
+
+        if youtube_url:
+            entries = [entry, self.url_result(youtube_url, 'Youtube')]
+            return self.playlist_result(entries)
+
+        return entry

youtube_dl/extractor/acast.py

@@ -2,10 +2,14 @@
 from __future__ import unicode_literals
 
 import re
+import functools
 
 from .common import InfoExtractor
 from ..compat import compat_str
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    OnDemandPagedList,
+)
 
 
 class ACastIE(InfoExtractor):
@@ -26,13 +30,8 @@ class ACastIE(InfoExtractor):
 
     def _real_extract(self, url):
         channel, display_id = re.match(self._VALID_URL, url).groups()
-
-        embed_page = self._download_webpage(
-            re.sub('(?:www\.)?acast\.com', 'embedcdn.acast.com', url), display_id)
-        cast_data = self._parse_json(self._search_regex(
-            r'window\[\'acast/queries\'\]\s*=\s*([^;]+);', embed_page, 'acast data'),
-            display_id)['GetAcast/%s/%s' % (channel, display_id)]
-
+        cast_data = self._download_json(
+            'https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id)
         return {
             'id': compat_str(cast_data['id']),
             'display_id': display_id,
@@ -58,15 +57,26 @@ class ACastChannelIE(InfoExtractor):
         'playlist_mincount': 20,
     }
     _API_BASE_URL = 'https://www.acast.com/api/'
+    _PAGE_SIZE = 10
 
     @classmethod
     def suitable(cls, url):
         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
 
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id)
-        casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id)
-        entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts]
+    def _fetch_page(self, channel_slug, page):
+        casts = self._download_json(
+            self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
+            channel_slug, note='Download page %d of channel data' % page)
+        for cast in casts:
+            yield self.url_result(
+                'https://www.acast.com/%s/%s' % (channel_slug, cast['url']),
+                'ACast', cast['id'])
 
-        return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description'))
+    def _real_extract(self, url):
+        channel_slug = self._match_id(url)
+        channel_data = self._download_json(
+            self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug)
+        entries = OnDemandPagedList(functools.partial(
+            self._fetch_page, channel_slug), self._PAGE_SIZE)
+        return self.playlist_result(entries, compat_str(
+            channel_data['id']), channel_data['name'], channel_data.get('description'))

youtube_dl/extractor/addanime.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
     compat_str,
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
     compat_urllib_parse_urlparse,
 )
 from ..utils import (
@@ -16,7 +16,7 @@ from ..utils import (
 
 
 class AddAnimeIE(InfoExtractor):
-    _VALID_URL = r'http://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
+    _VALID_URL = r'https?://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
     _TESTS = [{
         'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
         'md5': '72954ea10bc979ab5e2eb288b21425a0',
@@ -60,7 +60,7 @@ class AddAnimeIE(InfoExtractor):
             confirm_url = (
                 parsed_url.scheme + '://' + parsed_url.netloc +
                 action + '?' +
-                compat_urllib_parse.urlencode({
+                compat_urllib_parse_urlencode({
                     'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
             self._download_webpage(
                 confirm_url, video_id,

youtube_dl/extractor/aenetworks.py

@@ -1,13 +1,19 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
-from ..utils import smuggle_url
+from ..utils import (
+    smuggle_url,
+    update_url_query,
+    unescapeHTML,
+)
 
 
 class AENetworksIE(InfoExtractor):
     IE_NAME = 'aenetworks'
     IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
-    _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])'
+    _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?P<type>[^/]+)/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])'
 
     _TESTS = [{
         'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
@@ -16,6 +22,9 @@ class AENetworksIE(InfoExtractor):
             'ext': 'mp4',
             'title': "Bet You Didn't Know: Valentine's Day",
             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
+            'timestamp': 1375819729,
+            'upload_date': '20130806',
+            'uploader': 'AENE-NEW',
         },
         'params': {
             # m3u8 download
@@ -25,15 +34,15 @@ class AENetworksIE(InfoExtractor):
         'expected_warnings': ['JSON-LD'],
     }, {
         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
+        'md5': '8ff93eb073449f151d6b90c0ae1ef0c7',
         'info_dict': {
             'id': 'eg47EERs_JsZ',
             'ext': 'mp4',
             'title': 'Winter Is Coming',
             'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
+            'timestamp': 1338306241,
+            'upload_date': '20120529',
+            'uploader': 'AENE-NEW',
         },
         'add_ie': ['ThePlatform'],
     }, {
@@ -48,7 +57,7 @@ class AENetworksIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        page_type, video_id = re.match(self._VALID_URL, url).groups()
 
         webpage = self._download_webpage(url, video_id)
 
@@ -56,11 +65,23 @@ class AENetworksIE(InfoExtractor):
             r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id,
             r"media_url\s*=\s*'([^']+)'"
         ]
-        video_url = self._search_regex(video_url_re, webpage, 'video url')
+        video_url = unescapeHTML(self._search_regex(video_url_re, webpage, 'video url'))
+        query = {'mbr': 'true'}
+        if page_type == 'shows':
+            query['assetTypes'] = 'medium_video_s3'
+        if 'switch=hds' in video_url:
+            query['switch'] = 'hls'
 
         info = self._search_json_ld(webpage, video_id, fatal=False)
         info.update({
             '_type': 'url_transparent',
-            'url': smuggle_url(video_url, {'sig': {'key': 'crazyjava', 'secret': 's3cr3t'}}),
+            'url': smuggle_url(
+                update_url_query(video_url, query),
+                {
+                    'sig': {
+                        'key': 'crazyjava',
+                        'secret': 's3cr3t'},
+                    'force_smil_url': True
+                }),
         })
         return info

youtube_dl/extractor/aftonbladet.py

@@ -6,7 +6,7 @@ from ..utils import int_or_none
 
 
 class AftonbladetIE(InfoExtractor):
-    _VALID_URL = r'http://tv\.aftonbladet\.se/abtv/articles/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://tv\.aftonbladet\.se/abtv/articles/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
         'info_dict': {

youtube_dl/extractor/aljazeera.py

@@ -4,7 +4,7 @@ from .common import InfoExtractor
 
 
 class AlJazeeraIE(InfoExtractor):
-    _VALID_URL = r'http://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
+    _VALID_URL = r'https?://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
 
     _TEST = {
         'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
@@ -13,24 +13,18 @@ class AlJazeeraIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'The Slum - Episode 1: Deliverance',
             'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.',
-            'uploader': 'Al Jazeera English',
+            'uploader_id': '665003303001',
+            'timestamp': 1411116829,
+            'upload_date': '20140919',
         },
-        'add_ie': ['BrightcoveLegacy'],
+        'add_ie': ['BrightcoveNew'],
         'skip': 'Not accessible from Travis CI server',
     }
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/665003303001/default_default/index.html?videoId=%s'
 
     def _real_extract(self, url):
         program_name = self._match_id(url)
         webpage = self._download_webpage(url, program_name)
         brightcove_id = self._search_regex(
             r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id')
-
-        return {
-            '_type': 'url',
-            'url': (
-                'brightcove:'
-                'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc'
-                '&%40videoPlayer={0}'.format(brightcove_id)
-            ),
-            'ie_key': 'BrightcoveLegacy',
-        }
+        return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)

youtube_dl/extractor/amp.py

@@ -52,7 +52,7 @@ class AMPIE(InfoExtractor):
         for media_data in media_content:
             media = media_data['@attributes']
             media_type = media['type']
-            if media_type == 'video/f4m':
+            if media_type in ('video/f4m', 'application/f4m+xml'):
                 formats.extend(self._extract_f4m_formats(
                     media['url'] + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124',
                     video_id, f4m_id='hds', fatal=False))
@@ -61,7 +61,7 @@ class AMPIE(InfoExtractor):
                     media['url'], video_id, 'mp4', m3u8_id='hls', fatal=False))
             else:
                 formats.append({
-                    'format_id': media_data['media-category']['@attributes']['label'],
+                    'format_id': media_data.get('media-category', {}).get('@attributes', {}).get('label'),
                     'url': media['url'],
                     'tbr': int_or_none(media.get('bitrate')),
                     'filesize': int_or_none(media.get('fileSize')),
@@ -69,12 +69,14 @@ class AMPIE(InfoExtractor):
 
         self._sort_formats(formats)
 
+        timestamp = parse_iso8601(item.get('pubDate'), ' ') or parse_iso8601(item.get('dc-date'))
+
         return {
             'id': video_id,
             'title': get_media_node('title'),
             'description': get_media_node('description'),
             'thumbnails': thumbnails,
-            'timestamp': parse_iso8601(item.get('pubDate'), ' '),
+            'timestamp': timestamp,
             'duration': int_or_none(media_content[0].get('@attributes', {}).get('duration')),
             'subtitles': subtitles,
             'formats': formats,

youtube_dl/extractor/animeondemand.py

@@ -3,10 +3,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..compat import (
+    compat_urlparse,
+    compat_str,
+)
 from ..utils import (
     determine_ext,
-    encode_dict,
+    extract_attributes,
     ExtractorError,
     sanitized_Request,
     urlencode_postdata,
@@ -18,7 +21,7 @@ class AnimeOnDemandIE(InfoExtractor):
     _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 = {
+    _TESTS = [{
         'url': 'https://www.anime-on-demand.de/anime/161',
         'info_dict': {
             'id': '161',
@@ -26,7 +29,19 @@ class AnimeOnDemandIE(InfoExtractor):
             'description': 'md5:6681ce3c07c7189d255ac6ab23812d31',
         },
         'playlist_mincount': 4,
-    }
+    }, {
+        # Film wording is used instead of Episode
+        'url': 'https://www.anime-on-demand.de/anime/39',
+        'only_matching': True,
+    }, {
+        # Episodes without titles
+        'url': 'https://www.anime-on-demand.de/anime/162',
+        'only_matching': True,
+    }, {
+        # ger/jap, Dub/OmU, account required
+        'url': 'https://www.anime-on-demand.de/anime/169',
+        'only_matching': True,
+    }]
 
     def _login(self):
         (username, password) = self._get_login_info()
@@ -36,6 +51,10 @@ class AnimeOnDemandIE(InfoExtractor):
         login_page = self._download_webpage(
             self._LOGIN_URL, None, 'Downloading login page')
 
+        if '>Our licensing terms allow the distribution of animes only to German-speaking countries of Europe' in login_page:
+            self.raise_geo_restricted(
+                '%s is only available in German-speaking countries of Europe' % self.IE_NAME)
+
         login_form = self._form_hidden_inputs('new_user', login_page)
 
         login_form.update({
@@ -51,7 +70,7 @@ class AnimeOnDemandIE(InfoExtractor):
             post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
 
         request = sanitized_Request(
-            post_url, urlencode_postdata(encode_dict(login_form)))
+            post_url, urlencode_postdata(login_form))
         request.add_header('Referer', self._LOGIN_URL)
 
         response = self._download_webpage(
@@ -91,14 +110,22 @@ class AnimeOnDemandIE(InfoExtractor):
 
         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:
+        for num, episode_html in enumerate(re.findall(
+                r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', webpage), 1):
+            episodebox_title = self._search_regex(
+                (r'class="episodebox-title"[^>]+title=(["\'])(?P<title>.+?)\1',
+                 r'class="episodebox-title"[^>]+>(?P<title>.+?)<'),
+                episode_html, 'episodebox title', default=None, group='title')
+            if not episodebox_title:
                 continue
 
-            episode_number = int(m.group('number'))
-            episode_title = m.group('title')
+            episode_number = int(self._search_regex(
+                r'(?:Episode|Film)\s*(\d+)',
+                episodebox_title, 'episode number', default=num))
+            episode_title = self._search_regex(
+                r'(?:Episode|Film)\s*\d+\s*-\s*(.+)',
+                episodebox_title, 'episode title', default=None)
+
             video_id = 'episode-%d' % episode_number
 
             common_info = {
@@ -110,33 +137,86 @@ class AnimeOnDemandIE(InfoExtractor):
 
             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',
-                    })
+            for input_ in re.findall(
+                    r'<input[^>]+class=["\'].*?streamstarter_html5[^>]+>', episode_html):
+                attributes = extract_attributes(input_)
+                playlist_urls = []
+                for playlist_key in ('data-playlist', 'data-otherplaylist'):
+                    playlist_url = attributes.get(playlist_key)
+                    if isinstance(playlist_url, compat_str) and re.match(
+                            r'/?[\da-zA-Z]+', playlist_url):
+                        playlist_urls.append(attributes[playlist_key])
+                if not playlist_urls:
+                    continue
 
-                playlist = self._download_json(
-                    request, video_id, 'Downloading playlist JSON', fatal=False)
-                if playlist:
-                    playlist = playlist['playlist'][0]
-                    title = playlist['title']
+                lang = attributes.get('data-lang')
+                lang_note = attributes.get('value')
+
+                for playlist_url in playlist_urls:
+                    kind = self._search_regex(
+                        r'videomaterialurl/\d+/([^/]+)/',
+                        playlist_url, 'media kind', default=None)
+                    format_id_list = []
+                    if lang:
+                        format_id_list.append(lang)
+                    if kind:
+                        format_id_list.append(kind)
+                    if not format_id_list:
+                        format_id_list.append(compat_str(num))
+                    format_id = '-'.join(format_id_list)
+                    format_note = ', '.join(filter(None, (kind, lang_note)))
+                    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 %s playlist JSON' % format_id,
+                        fatal=False)
+                    if not playlist:
+                        continue
+                    start_video = playlist.get('startvideo', 0)
+                    playlist = playlist.get('playlist')
+                    if not playlist or not isinstance(playlist, list):
+                        continue
+                    playlist = playlist[start_video]
+                    title = playlist.get('title')
+                    if not title:
+                        continue
                     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(
+                        if not file_:
+                            continue
+                        ext = determine_ext(file_)
+                        format_id_list = [lang, kind]
+                        if ext == 'm3u8':
+                            format_id_list.append('hls')
+                        elif source.get('type') == 'video/dash' or ext == 'mpd':
+                            format_id_list.append('dash')
+                        format_id = '-'.join(filter(None, format_id_list))
+                        if ext == 'm3u8':
+                            file_formats = self._extract_m3u8_formats(
                                 file_, video_id, 'mp4',
-                                entry_protocol='m3u8_native', m3u8_id='hls')
+                                entry_protocol='m3u8_native', m3u8_id=format_id, fatal=False)
+                        elif source.get('type') == 'video/dash' or ext == 'mpd':
+                            continue
+                            file_formats = self._extract_mpd_formats(
+                                file_, video_id, mpd_id=format_id, fatal=False)
+                        else:
+                            continue
+                        for f in file_formats:
+                            f.update({
+                                'language': lang,
+                                'format_note': format_note,
+                            })
+                        formats.extend(file_formats)
 
             if formats:
+                self._sort_formats(formats)
                 f = common_info.copy()
                 f.update({
                     'title': title,
@@ -145,16 +225,18 @@ class AnimeOnDemandIE(InfoExtractor):
                 })
                 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)
+            # Extract teaser only when full episode is not available
+            if not formats:
+                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/anvato.py

@@ -0,0 +1,224 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import base64
+import hashlib
+import json
+import random
+import time
+
+from .common import InfoExtractor
+from ..aes import aes_encrypt
+from ..compat import compat_str
+from ..utils import (
+    bytes_to_intlist,
+    determine_ext,
+    intlist_to_bytes,
+    int_or_none,
+    strip_jsonp,
+)
+
+
+def md5_text(s):
+    if not isinstance(s, compat_str):
+        s = compat_str(s)
+    return hashlib.md5(s.encode('utf-8')).hexdigest()
+
+
+class AnvatoIE(InfoExtractor):
+    # Copied from anvplayer.min.js
+    _ANVACK_TABLE = {
+        'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ',
+        'nbcu_nbcd_desktop_web_qa_1a6f01bdd0dc45a439043b694c8a031d': 'eSxJUbA2UUKBTXryyQ2d6NuM8oEqaPySvaPzfKNA',
+        'nbcu_nbcd_desktop_web_acc_eb2ff240a5d4ae9a63d4c297c32716b6c523a129': '89JR3RtUGbvKuuJIiKOMK0SoarLb5MUx8v89RcbP',
+        'nbcu_nbcd_watchvod_web_prod_e61107507180976724ec8e8319fe24ba5b4b60e1': 'Uc7dFt7MJ9GsBWB5T7iPvLaMSOt8BBxv4hAXk5vv',
+        'nbcu_nbcd_watchvod_web_qa_42afedba88a36203db5a4c09a5ba29d045302232': 'T12oDYVFP2IaFvxkmYMy5dKxswpLHtGZa4ZAXEi7',
+        'nbcu_nbcd_watchvod_web_acc_9193214448e2e636b0ffb78abacfd9c4f937c6ca': 'MmobcxUxMedUpohNWwXaOnMjlbiyTOBLL6d46ZpR',
+        'nbcu_local_monitor_web_acc_f998ad54eaf26acd8ee033eb36f39a7b791c6335': 'QvfIoPYrwsjUCcASiw3AIkVtQob2LtJHfidp9iWg',
+        'nbcu_cable_monitor_web_acc_a413759603e8bedfcd3c61b14767796e17834077': 'uwVPJLShvJWSs6sWEIuVem7MTF8A4IknMMzIlFto',
+        'nbcu_nbcd_mcpstage_web_qa_4c43a8f6e95a88dbb40276c0630ba9f693a63a4e': 'PxVYZVwjhgd5TeoPRxL3whssb5OUPnM3zyAzq8GY',
+        'nbcu_comcast_comcast_web_prod_074080762ad4ce956b26b43fb22abf153443a8c4': 'afnaRZfDyg1Z3WZHdupKfy6xrbAG2MHqe3VfuSwh',
+        'nbcu_comcast_comcast_web_qa_706103bb93ead3ef70b1de12a0e95e3c4481ade0': 'DcjsVbX9b3uoPlhdriIiovgFQZVxpISZwz0cx1ZK',
+        'nbcu_comcast_comcastcable_web_prod_669f04817536743563d7331c9293e59fbdbe3d07': '0RwMN2cWy10qhAhOscq3eK7aEe0wqnKt3vJ0WS4D',
+        'nbcu_comcast_comcastcable_web_qa_3d9d2d66219094127f0f6b09cc3c7bb076e3e1ca': '2r8G9DEya7PCqBceKZgrn2XkXgASjwLMuaFE1Aad',
+        'hearst_hearst_demo_web_stage_960726dfef3337059a01a78816e43b29ec04dfc7': 'cuZBPXTR6kSdoTCVXwk5KGA8rk3NrgGn4H6e9Dsp',
+        'anvato_mcpqa_demo_web_stage_18b55e00db5a13faa8d03ae6e41f6f5bcb15b922': 'IOaaLQ8ymqVyem14QuAvE5SndQynTcH5CrLkU2Ih',
+        'anvato_nextmedia_demo_web_stage_9787d56a02ff6b9f43e9a2b0920d8ca88beb5818': 'Pqu9zVzI1ApiIzbVA3VkGBEQHvdKSUuKpD6s2uaR',
+        'anvato_scripps_app_web_prod_0837996dbe373629133857ae9eb72e740424d80a': 'du1ccmn7RxzgizwbWU7hyUaGodNlJn7HtXI0WgXW',
+        'anvato_scripps_app_web_stage_360797e00fe2826be142155c4618cc52fce6c26c': '2PMrQ0BRoqCWl7nzphj0GouIMEh2mZYivAT0S1Su',
+        'fs2go_fs2go_go_all_prod_21934911ccfafc03a075894ead2260d11e2ddd24': 'RcuHlKikW2IJw6HvVoEkqq2UsuEJlbEl11pWXs4Q',
+        'fs2go_fs2go_go_web_prod_ead4b0eec7460c1a07783808db21b49cf1f2f9a7': '4K0HTT2u1zkQA2MaGaZmkLa1BthGSBdr7jllrhk5',
+        'fs2go_fs2go_go_web_stage_407585454a4400355d4391691c67f361': 'ftnc37VKRJBmHfoGGi3kT05bHyeJzilEzhKJCyl3',
+        'fs2go_fs2go_go_android_stage_44b714db6f8477f29afcba15a41e1d30': 'CtxpPvVpo6AbZGomYUhkKs7juHZwNml9b9J0J2gI',
+        'anvato_cbslocal_app_web_prod_547f3e49241ef0e5d30c79b2efbca5d92c698f67': 'Pw0XX5KBDsyRnPS0R2JrSrXftsy8Jnz5pAjaYC8s',
+        'anvato_cbslocal_app_web_stage_547a5f096594cd3e00620c6f825cad1096d28c80': '37OBUhX2uwNyKhhrNzSSNHSRPZpApC3trdqDBpuz',
+        'fs2go_att_att_web_prod_1042dddd089a05438b6a08f972941176f699ffd8': 'JLcF20JwYvpv6uAGcLWIaV12jKwaL1R8us4b6Zkg',
+        'fs2go_att_att_web_stage_807c5001955fc114a3331fe027ddc76e': 'gbu1oO1y0JiOFh4SUipt86P288JHpyjSqolrrT1x',
+        'fs2go_fs2go_tudor_web_prod_a7dd8e5a7cdc830cae55eae6f3e9fee5ee49eb9b': 'ipcp87VCEZXPPe868j3orLqzc03oTy7DXsGkAXXH',
+        'anvato_mhz_app_web_prod_b808218b30de7fdf60340cbd9831512bc1bf6d37': 'Stlm5Gs6BEhJLRTZHcNquyzxGqr23EuFmE5DCgjX',
+        'fs2go_charter_charter_web_stage_c2c6e5a68375a1bf00fff213d3ff8f61a835a54c': 'Lz4hbJp1fwL6jlcz4M2PMzghM4jp4aAmybtT5dPc',
+        'fs2go_charter_charter_web_prod_ebfe3b10f1af215a7321cd3d629e0b81dfa6fa8c': 'vUJsK345A1bVmyYDRhZX0lqFIgVXuqhmuyp1EtPK',
+        'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b': 'GDKq1ixvX3MoBNdU5IOYmYa2DTUXYOozPjrCJnW7',
+        'anvato_epfox_app_web_stage_a3c2ce60f8f83ef374a88b68ee73a950f8ab87ce': '2jz2NH4BsXMaDsoJ5qkHMbcczAfIReo2eFYuVC1C',
+        'fs2go_verizon_verizon_web_stage_08e6df0354a4803f1b1f2428b5a9a382e8dbcd62': 'rKTVapNaAcmnUbGL4ZcuOoY4SE7VmZSQsblPFr7e',
+        'fs2go_verizon_verizon_web_prod_f909564cb606eff1f731b5e22e0928676732c445': 'qLSUuHerM3u9eNPzaHyUK52obai5MvE4XDJfqYe1',
+        'fs2go_foxcom_synd_web_stage_f7b9091f00ea25a4fdaaae77fca5b54cdc7e7043': '96VKF2vLd24fFiDfwPFpzM5llFN4TiIGAlodE0Re',
+        'fs2go_foxcom_synd_web_prod_0f2cdd64d87e4ab6a1d54aada0ff7a7c8387a064': 'agiPjbXEyEZUkbuhcnmVPhe9NNVbDjCFq2xkcx51',
+        'anvato_own_app_web_stage_1214ade5d28422c4dae9d03c1243aba0563c4dba': 'mzhamNac3swG4WsJAiUTacnGIODi6SWeVWk5D7ho',
+        'anvato_own_app_web_prod_944e162ed927ec3e9ed13eb68ed2f1008ee7565e': '9TSxh6G2TXOLBoYm9ro3LdNjjvnXpKb8UR8KoIP9',
+        'anvato_scripps_app_ftv_prod_a10a10468edd5afb16fb48171c03b956176afad1': 'COJ2i2UIPK7xZqIWswxe7FaVBOVgRkP1F6O6qGoH',
+        'anvato_scripps_app_ftv_stage_77d3ad2bdb021ec37ca2e35eb09acd396a974c9a': 'Q7nnopNLe2PPfGLOTYBqxSaRpl209IhqaEuDZi1F',
+        'anvato_univision_app_web_stage_551236ef07a0e17718c3995c35586b5ed8cb5031': 'D92PoLS6UitwxDRA191HUGT9OYcOjV6mPMa5wNyo',
+        'anvato_univision_app_web_prod_039a5c0a6009e637ae8ac906718a79911e0e65e1': '5mVS5u4SQjtw6NGw2uhMbKEIONIiLqRKck5RwQLR',
+        'nbcu_cnbc_springfield_ios_prod_670207fae43d6e9a94c351688851a2ce': 'M7fqCCIP9lW53oJbHs19OlJlpDrVyc2OL8gNeuTa',
+        'nbcu_cnbc_springfieldvod_ios_prod_7a5f04b1ceceb0e9c9e2264a44aa236e08e034c2': 'Yia6QbJahW0S7K1I0drksimhZb4UFq92xLBmmMvk',
+        'anvato_cox_app_web_prod_ce45cda237969f93e7130f50ee8bb6280c1484ab': 'cc0miZexpFtdoqZGvdhfXsLy7FXjRAOgb9V0f5fZ',
+        'anvato_cox_app_web_stage_c23dbe016a8e9d8c7101d10172b92434f6088bf9': 'yivU3MYHd2eDZcOfmLbINVtqxyecKTOp8OjOuoGJ',
+        'anvato_chnzero_app_web_stage_b1164d1352b579e792e542fddf13ee34c0eeb46b': 'A76QkXMmVH8lTCfU15xva1mZnSVcqeY4Xb22Kp7m',
+        'anvato_chnzero_app_web_prod_253d358928dc08ec161eda2389d53707288a730c': 'OA5QI3ZWZZkdtUEDqh28AH8GedsF6FqzJI32596b',
+        'anvato_discovery_vodpoc_web_stage_9fa7077b5e8af1f8355f65d4fb8d2e0e9d54e2b7': 'q3oT191tTQ5g3JCP67PkjLASI9s16DuWZ6fYmry3',
+        'anvato_discovery_vodpoc_web_prod_688614983167a1af6cdf6d76343fda10a65223c1': 'qRvRQCTVHd0VVOHsMvvfidyWmlYVrTbjby7WqIuK',
+        'nbcu_cnbc_springfieldvod_ftv_stage_826040aad1925a46ac5dfb4b3c5143e648c6a30d': 'JQaSb5a8Tz0PT4ti329DNmzDO30TnngTHmvX8Vua',
+        'nbcu_cnbc_springfield_ftv_stage_826040aad1925a46ac5dfb4b3c5143e648c6a30d': 'JQaSb5a8Tz0PT4ti329DNmzDO30TnngTHmvX8Vua',
+        'nbcu_nbcd_capture_web_stage_4dd9d585bfb984ebf856dee35db027b2465cc4ae': '0j1Ov4Vopyi2HpBZJYdL2m8ERJVGYh3nNpzPiO8F',
+        'nbcu_nbcd_watch3_android_prod_7712ca5fcf1c22f19ec1870a9650f9c37db22dcf': '3LN2UB3rPUAMu7ZriWkHky9vpLMXYha8JbSnxBlx',
+        'nbcu_nbcd_watchvod3_android_prod_0910a3a4692d57c0b5ff4316075bc5d096be45b9': 'mJagcQ2II30vUOAauOXne7ERwbf5S9nlB3IP17lQ',
+        'anvato_scripps_app_atv_prod_790deda22e16e71e83df58f880cd389908a45d52': 'CB6trI1mpoDIM5o54DNTsji90NDBQPZ4z4RqBNSH',
+        'nbcu_nbcd_watchv4_android_prod_ff67cef9cb409158c6f8c3533edddadd0b750507': 'j8CHQCUWjlYERj4NFRmUYOND85QNbHViH09UwuKm',
+        'nbcu_nbcd_watchvodv4_android_prod_a814d781609989dea6a629d50ae4c7ad8cc8e907': 'rkVnUXxdA9rawVLUlDQtMue9Y4Q7lFEaIotcUhjt',
+        'rvVKpA50qlOPLFxMjrCGf5pdkdQDm7qn': '1J7ZkY5Qz5lMLi93QOH9IveE7EYB3rLl',
+        'nbcu_dtv_local_web_prod_b266cf49defe255fd4426a97e27c09e513e9f82f': 'HuLnJDqzLa4saCzYMJ79zDRSQpEduw1TzjMNQu2b',
+        'nbcu_att_local_web_prod_4cef038b2d969a6b7d700a56a599040b6a619f67': 'Q0Em5VDc2KpydUrVwzWRXAwoNBulWUxCq2faK0AV',
+        'nbcu_dish_local_web_prod_c56dcaf2da2e9157a4266c82a78195f1dd570f6b': 'bC1LWmRz9ayj2AlzizeJ1HuhTfIaJGsDBnZNgoRg',
+        'nbcu_verizon_local_web_prod_88bebd2ce006d4ed980de8133496f9a74cb9b3e1': 'wzhDKJZpgvUSS1EQvpCQP8Q59qVzcPixqDGJefSk',
+        'nbcu_charter_local_web_prod_9ad90f7fc4023643bb718f0fe0fd5beea2382a50': 'PyNbxNhEWLzy1ZvWEQelRuIQY88Eub7xbSVRMdfT',
+        'nbcu_suddenlink_local_web_prod_20fb711725cac224baa1c1cb0b1c324d25e97178': '0Rph41lPXZbb3fqeXtHjjbxfSrNbtZp1Ygq7Jypa',
+        'nbcu_wow_local_web_prod_652d9ce4f552d9c2e7b5b1ed37b8cb48155174ad': 'qayIBZ70w1dItm2zS42AptXnxW15mkjRrwnBjMPv',
+        'nbcu_centurylink_local_web_prod_2034402b029bf3e837ad46814d9e4b1d1345ccd5': 'StePcPMkjsX51PcizLdLRMzxMEl5k2FlsMLUNV4k',
+        'nbcu_atlanticbrd_local_web_prod_8d5f5ecbf7f7b2f5e6d908dd75d90ae3565f682e': 'NtYLb4TFUS0pRs3XTkyO5sbVGYjVf17bVbjaGscI',
+        'nbcu_nbcd_watchvod_web_dev_08bc05699be47c4f31d5080263a8cfadc16d0f7c': 'hwxi2dgDoSWgfmVVXOYZm14uuvku4QfopstXckhr',
+        'anvato_nextmedia_app_web_prod_a4fa8c7204aa65e71044b57aaf63711980cfe5a0': 'tQN1oGPYY1nM85rJYePWGcIb92TG0gSqoVpQTWOw',
+        'anvato_mcp_lin_web_prod_4c36fbfd4d8d8ecae6488656e21ac6d1ac972749': 'GUXNf5ZDX2jFUpu4WT2Go4DJ5nhUCzpnwDRRUx1K',
+        'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa': 'bLDYF8JqfG42b7bwKEgQiU9E2LTIAtnKzSgYpFUH',
+        'anvato_mcp_fs2go_web_prod_c7b90a93e171469cdca00a931211a2f556370d0a': 'icgGoYGipQMMSEvhplZX1pwbN69srwKYWksz3xWK',
+        'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336': 'fA2iQdI7RDpynqzQYIpXALVS83NTPr8LLFK4LFsu',
+        'anvato_mcp_anv_web_prod_791407490f4c1ef2a4bcb21103e0cb1bcb3352b3': 'rMOUZqe9lwcGq2mNgG3EDusm6lKgsUnczoOX3mbg',
+        'anvato_mcp_gray_web_prod_4c10f067c393ed8fc453d3930f8ab2b159973900': 'rMOUZqe9lwcGq2mNgG3EDusm6lKgsUnczoOX3mbg',
+        'anvato_mcp_hearst_web_prod_5356c3de0fc7c90a3727b4863ca7fec3a4524a99': 'P3uXJ0fXXditBPCGkfvlnVScpPEfKmc64Zv7ZgbK',
+        'anvato_mcp_cbs_web_prod_02f26581ff80e5bda7aad28226a8d369037f2cbe': 'mGPvo5ZA5SgjOFAPEPXv7AnOpFUICX8hvFQVz69n',
+        'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582': 'qyT6PXXLjVNCrHaRVj0ugAhalNRS7Ee9BP7LUokD',
+        'nbcu_nbcd_watchvodv4_web_stage_4108362fba2d4ede21f262fea3c4162cbafd66c7': 'DhaU5lj0W2gEdcSSsnxURq8t7KIWtJfD966crVDk',
+        'anvato_scripps_app_ios_prod_409c41960c60b308db43c3cc1da79cab9f1c3d93': 'WPxj5GraLTkYCyj3M7RozLqIycjrXOEcDGFMIJPn',
+        'EZqvRyKBJLrgpClDPDF8I7Xpdp40Vx73': '4OxGd2dEakylntVKjKF0UK9PDPYB6A9W',
+        'M2v78QkpleXm9hPp9jUXI63x5vA6BogR': 'ka6K32k7ZALmpINkjJUGUo0OE42Md1BQ',
+        'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ'
+    }
+
+    _AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce'
+
+    def __init__(self, *args, **kwargs):
+        super(AnvatoIE, self).__init__(*args, **kwargs)
+        self.__server_time = None
+
+    def _server_time(self, access_key, video_id):
+        if self.__server_time is not None:
+            return self.__server_time
+
+        self.__server_time = int(self._download_json(
+            self._api_prefix(access_key) + 'server_time?anvack=' + access_key, video_id,
+            note='Fetching server time')['server_time'])
+
+        return self.__server_time
+
+    def _api_prefix(self, access_key):
+        return 'https://tkx2-%s.anvato.net/rest/v2/' % ('prod' if 'prod' in access_key else 'stage')
+
+    def _get_video_json(self, access_key, video_id):
+        # See et() in anvplayer.min.js, which is an alias of getVideoJSON()
+        video_data_url = self._api_prefix(access_key) + 'mcp/video/%s?anvack=%s' % (video_id, access_key)
+        server_time = self._server_time(access_key, video_id)
+        input_data = '%d~%s~%s' % (server_time, md5_text(video_data_url), md5_text(server_time))
+
+        auth_secret = intlist_to_bytes(aes_encrypt(
+            bytes_to_intlist(input_data[:64]), bytes_to_intlist(self._AUTH_KEY)))
+
+        video_data_url += '&X-Anvato-Adst-Auth=' + base64.b64encode(auth_secret).decode('ascii')
+        anvrid = md5_text(time.time() * 1000 * random.random())[:30]
+        payload = {
+            'api': {
+                'anvrid': anvrid,
+                'anvstk': md5_text('%s|%s|%d|%s' % (
+                    access_key, anvrid, server_time, self._ANVACK_TABLE[access_key])),
+                'anvts': server_time,
+            },
+        }
+
+        return self._download_json(
+            video_data_url, video_id, transform_source=strip_jsonp,
+            data=json.dumps(payload).encode('utf-8'))
+
+    def _extract_anvato_videos(self, webpage, video_id):
+        anvplayer_data = self._parse_json(self._html_search_regex(
+            r'<script[^>]+data-anvp=\'([^\']+)\'', webpage,
+            'Anvato player data'), video_id)
+
+        video_id = anvplayer_data['video']
+        access_key = anvplayer_data['accessKey']
+
+        video_data = self._get_video_json(access_key, video_id)
+
+        formats = []
+        for published_url in video_data['published_urls']:
+            video_url = published_url['embed_url']
+            ext = determine_ext(video_url)
+
+            if ext == 'smil':
+                formats.extend(self._extract_smil_formats(video_url, video_id))
+                continue
+
+            tbr = int_or_none(published_url.get('kbps'))
+            a_format = {
+                'url': video_url,
+                'format_id': ('-'.join(filter(None, ['http', published_url.get('cdn_name')]))).lower(),
+                'tbr': tbr if tbr != 0 else None,
+            }
+
+            if ext == 'm3u8':
+                # Not using _extract_m3u8_formats here as individual media
+                # playlists are also included in published_urls.
+                if tbr is None:
+                    formats.append(self._m3u8_meta_format(video_url, ext='mp4', m3u8_id='hls'))
+                    continue
+                else:
+                    a_format.update({
+                        'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])),
+                        'ext': 'mp4',
+                    })
+            elif ext == 'mp3':
+                a_format['vcodec'] = 'none'
+            else:
+                a_format.update({
+                    'width': int_or_none(published_url.get('width')),
+                    'height': int_or_none(published_url.get('height')),
+                })
+            formats.append(a_format)
+
+        self._sort_formats(formats)
+
+        subtitles = {}
+        for caption in video_data.get('captions', []):
+            a_caption = {
+                'url': caption['url'],
+                'ext': 'tt' if caption.get('format') == 'SMPTE-TT' else None
+            }
+            subtitles.setdefault(caption['language'], []).append(a_caption)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': video_data.get('def_title'),
+            'description': video_data.get('def_description'),
+            'categories': video_data.get('categories'),
+            'thumbnail': video_data.get('thumbnail'),
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/aol.py

@@ -1,70 +1,133 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
 
 
 class AolIE(InfoExtractor):
     IE_NAME = 'on.aol.com'
-    _VALID_URL = r'''(?x)
-        (?:
-            aol-video:|
-            http://on\.aol\.com/
-            (?:
-                video/.*-|
-                playlist/(?P<playlist_display_id>[^/?#]+?)-(?P<playlist_id>[0-9]+)[?#].*_videoid=
-            )
-        )
-        (?P<id>[0-9]+)
-        (?:$|\?)
-    '''
+    _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/(?:[^/]+/)*(?:[^/?#&]+-)?)(?P<id>[^/?#&]+)'
 
     _TESTS = [{
+        # video with 5min ID
         'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
         'md5': '18ef68f48740e86ae94b98da815eec42',
         'info_dict': {
             'id': '518167793',
             'ext': 'mp4',
             'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
+            'description': 'A major phone scam has cost thousands of taxpayers more than $1 million, with less than a month until income tax returns are due to the IRS.',
+            'timestamp': 1395405060,
+            'upload_date': '20140321',
+            'uploader': 'Newsy Studio',
         },
-        'add_ie': ['FiveMin'],
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
     }, {
-        'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316',
+        # video with vidible ID
+        'url': 'http://on.aol.com/video/netflix-is-raising-rates-5707d6b8e4b090497b04f706?context=PC:homepage:PL1944:1460189336183',
         'info_dict': {
-            'id': '152147',
-            'title': 'Brace Yourself - Today\'s Weirdest News',
+            'id': '5707d6b8e4b090497b04f706',
+            'ext': 'mp4',
+            'title': 'Netflix is Raising Rates',
+            'description': 'Netflix is rewarding millions of it’s long-standing members with an increase in cost. Veuer’s Carly Figueroa has more.',
+            'upload_date': '20160408',
+            'timestamp': 1460123280,
+            'uploader': 'Veuer',
         },
-        'playlist_mincount': 10,
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://on.aol.com/partners/abc-551438d309eab105804dbfe8/sneak-peek-was-haley-really-framed-570eaebee4b0448640a5c944',
+        'only_matching': True,
+    }, {
+        'url': 'http://on.aol.com/shows/park-bench-shw518173474-559a1b9be4b0c3bfad3357a7?context=SH:SHW518173474:PL4327:1460619712763',
+        'only_matching': True,
+    }, {
+        'url': 'http://on.aol.com/video/519442220',
+        'only_matching': True,
+    }, {
+        'url': 'aol-video:5707d6b8e4b090497b04f706',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, 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)
+        video_id = self._match_id(url)
 
-        self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
+        response = self._download_json(
+            'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
+            video_id)['response']
+        if response['statusText'] != 'Ok':
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusText']), expected=True)
 
-        webpage = self._download_webpage(url, playlist_id)
-        title = self._html_search_regex(
-            r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title')
-        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)]
+        video_data = response['data']
+        formats = []
+        m3u8_url = video_data.get('videoMasterPlaylist')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+        for rendition in video_data.get('renditions', []):
+            video_url = rendition.get('url')
+            if not video_url:
+                continue
+            ext = rendition.get('format')
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+            else:
+                f = {
+                    'url': video_url,
+                    'format_id': rendition.get('quality'),
+                }
+                mobj = re.search(r'(\d+)x(\d+)', video_url)
+                if mobj:
+                    f.update({
+                        'width': int(mobj.group(1)),
+                        'height': int(mobj.group(2)),
+                    })
+                formats.append(f)
+        self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
 
         return {
-            '_type': 'playlist',
-            'id': playlist_id,
-            'display_id': mobj.group('playlist_display_id'),
-            'title': title,
-            'entries': entries,
+            'id': video_id,
+            'title': video_data['title'],
+            'duration': int_or_none(video_data.get('duration')),
+            'timestamp': int_or_none(video_data.get('publishDate')),
+            'view_count': int_or_none(video_data.get('views')),
+            'description': video_data.get('description'),
+            'uploader': video_data.get('videoOwner'),
+            'formats': formats,
         }
+
+
+class AolFeaturesIE(InfoExtractor):
+    IE_NAME = 'features.aol.com'
+    _VALID_URL = r'https?://features\.aol\.com/video/(?P<id>[^/?#]+)'
+
+    _TESTS = [{
+        'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts',
+        'md5': '7db483bb0c09c85e241f84a34238cc75',
+        'info_dict': {
+            'id': '519507715',
+            '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/ard.py

@@ -83,7 +83,7 @@ class ARDMediathekIE(InfoExtractor):
         subtitle_url = media_info.get('_subtitleUrl')
         if subtitle_url:
             subtitles['de'] = [{
-                'ext': 'srt',
+                'ext': 'ttml',
                 'url': subtitle_url,
             }]
 

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|en|es)/.*-(?P<id>.*?)\.html'
+    _VALID_URL = r'https?://videos\.arte\.tv/(?P<lang>fr|de|en|es)/.*-(?P<id>.*?)\.html'
     IE_NAME = 'arte.tv'
 
     def _real_extract(self, url):
@@ -61,10 +61,7 @@ class ArteTvIE(InfoExtractor):
         }
 
 
-class ArteTVPlus7IE(InfoExtractor):
-    IE_NAME = 'arte.tv:+7'
-    _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&+])'
-
+class ArteTVBaseIE(InfoExtractor):
     @classmethod
     def _extract_url_info(cls, url):
         mobj = re.match(cls._VALID_URL, url)
@@ -78,6 +75,122 @@ class ArteTVPlus7IE(InfoExtractor):
             video_id = mobj.group('id')
         return 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('VRA') or player_info.get('VDA') or '').split(' ')[0]
+
+        title = (player_info.get('VTI') or title or player_info['VID']).strip()
+        subtitle = player_info.get('VSU', '').strip()
+        if subtitle:
+            title += ' - %s' % subtitle
+
+        info_dict = {
+            'id': player_info['VID'],
+            'title': title,
+            'description': player_info.get('VDE'),
+            'upload_date': unified_strdate(upload_date_str),
+            'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
+        }
+        qfunc = qualities(['HQ', 'MQ', 'EQ', 'SQ'])
+
+        LANGS = {
+            'fr': 'F',
+            'de': 'A',
+            'en': 'E[ANG]',
+            'es': 'E[ESP]',
+        }
+
+        langcode = LANGS.get(lang, lang)
+
+        formats = []
+        for format_id, format_dict in player_info['VSR'].items():
+            f = dict(format_dict)
+            versionCode = f.get('versionCode')
+            l = re.escape(langcode)
+
+            # Language preference from most to least priority
+            # Reference: section 5.6.3 of
+            # http://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-05.pdf
+            PREFERENCES = (
+                # original version in requested language, without subtitles
+                r'VO{0}$'.format(l),
+                # original version in requested language, with partial subtitles in requested language
+                r'VO{0}-ST{0}$'.format(l),
+                # original version in requested language, with subtitles for the deaf and hard-of-hearing in requested language
+                r'VO{0}-STM{0}$'.format(l),
+                # non-original (dubbed) version in requested language, without subtitles
+                r'V{0}$'.format(l),
+                # non-original (dubbed) version in requested language, with subtitles partial subtitles in requested language
+                r'V{0}-ST{0}$'.format(l),
+                # non-original (dubbed) version in requested language, with subtitles for the deaf and hard-of-hearing in requested language
+                r'V{0}-STM{0}$'.format(l),
+                # original version in requested language, with partial subtitles in different language
+                r'VO{0}-ST(?!{0}).+?$'.format(l),
+                # original version in requested language, with subtitles for the deaf and hard-of-hearing in different language
+                r'VO{0}-STM(?!{0}).+?$'.format(l),
+                # original version in different language, with partial subtitles in requested language
+                r'VO(?:(?!{0}).+?)?-ST{0}$'.format(l),
+                # original version in different language, with subtitles for the deaf and hard-of-hearing in requested language
+                r'VO(?:(?!{0}).+?)?-STM{0}$'.format(l),
+                # original version in different language, without subtitles
+                r'VO(?:(?!{0}))?$'.format(l),
+                # original version in different language, with partial subtitles in different language
+                r'VO(?:(?!{0}).+?)?-ST(?!{0}).+?$'.format(l),
+                # original version in different language, with subtitles for the deaf and hard-of-hearing in different language
+                r'VO(?:(?!{0}).+?)?-STM(?!{0}).+?$'.format(l),
+            )
+
+            for pref, p in enumerate(PREFERENCES):
+                if re.match(p, versionCode):
+                    lang_pref = len(PREFERENCES) - pref
+                    break
+            else:
+                lang_pref = -1
+
+            format = {
+                'format_id': format_id,
+                'preference': -10 if f.get('videoFormat') == 'M3U8' else None,
+                'language_preference': lang_pref,
+                'format_note': '%s, %s' % (f.get('versionCode'), f.get('versionLibelle')),
+                'width': int_or_none(f.get('width')),
+                'height': int_or_none(f.get('height')),
+                'tbr': int_or_none(f.get('bitrate')),
+                'quality': qfunc(f.get('quality')),
+            }
+
+            if f.get('mediaType') == 'rtmp':
+                format['url'] = f['streamer']
+                format['play_path'] = 'mp4:' + f['url']
+                format['ext'] = 'flv'
+            else:
+                format['url'] = f['url']
+
+            formats.append(format)
+
+        self._check_formats(formats, video_id)
+        self._sort_formats(formats)
+
+        info_dict['formats'] = formats
+        return info_dict
+
+
+class ArteTVPlus7IE(ArteTVBaseIE):
+    IE_NAME = 'arte.tv:+7'
+    _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&]+)'
+
+    _TESTS = [{
+        'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if ArteTVPlaylistIE.suitable(url) else super(ArteTVPlus7IE, cls).suitable(url)
+
     def _real_extract(self, url):
         video_id, lang = self._extract_url_info(url)
         webpage = self._download_webpage(url, video_id)
@@ -121,93 +234,22 @@ class ArteTVPlus7IE(InfoExtractor):
                 json_url = compat_parse_qs(
                     compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
         if json_url:
-            return self._extract_from_json_url(json_url, video_id, lang)
-        # Differend kind of embed URL (e.g.
+            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):
-        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('VRA') or player_info.get('VDA') or '').split(' ')[0]
-
-        title = player_info['VTI'].strip()
-        subtitle = player_info.get('VSU', '').strip()
-        if subtitle:
-            title += ' - %s' % subtitle
-
-        info_dict = {
-            'id': player_info['VID'],
-            'title': title,
-            'description': player_info.get('VDE'),
-            'upload_date': unified_strdate(upload_date_str),
-            'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
-        }
-        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)
-            lang_rexs = [r'VO?%s-' % re.escape(langcode), r'VO?.-ST%s$' % re.escape(langcode)]
-            lang_pref = None
-            if versionCode:
-                matched_lang_rexs = [r for r in lang_rexs if re.match(r, versionCode)]
-                lang_pref = -10 if not matched_lang_rexs else 10 * len(matched_lang_rexs)
-            source_pref = 0
-            if versionCode is not None:
-                # The original version with subtitles has lower relevance
-                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|E)-STM\1', versionCode):
-                    source_pref -= 9
-            format = {
-                'format_id': format_id,
-                'preference': -10 if f.get('videoFormat') == 'M3U8' else None,
-                'language_preference': lang_pref,
-                'format_note': '%s, %s' % (f.get('versionCode'), f.get('versionLibelle')),
-                'width': int_or_none(f.get('width')),
-                'height': int_or_none(f.get('height')),
-                'tbr': int_or_none(f.get('bitrate')),
-                'quality': qfunc(f.get('quality')),
-                'source_preference': source_pref,
-            }
-
-            if f.get('mediaType') == 'rtmp':
-                format['url'] = f['streamer']
-                format['play_path'] = 'mp4:' + f['url']
-                format['ext'] = 'flv'
-            else:
-                format['url'] = f['url']
-
-            formats.append(format)
-
-        self._check_formats(formats, video_id)
-        self._sort_formats(formats)
-
-        info_dict['formats'] = formats
-        return info_dict
-
 
 # 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|en|es)/(?:magazine?/)?(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
 
     _TESTS = [{
         'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design',
@@ -226,6 +268,24 @@ class ArteTVCreativeIE(ArteTVPlus7IE):
             'description': 'Événement ! Quarante-cinq ans après leurs premiers succès, les légendaires Monty Python remontent sur scène.\n',
             'upload_date': '20140805',
         }
+    }, {
+        'url': 'http://creative.arte.tv/de/episode/agentur-amateur-4-der-erste-kunde',
+        'only_matching': True,
+    }]
+
+
+class ArteTVInfoIE(ArteTVPlus7IE):
+    IE_NAME = 'arte.tv:info'
+    _VALID_URL = r'https?://info\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+
+    _TESTS = [{
+        'url': 'http://info.arte.tv/fr/service-civique-un-cache-misere',
+        'info_dict': {
+            'id': '067528-000-A',
+            'ext': 'mp4',
+            'title': 'Service civique, un cache misère ?',
+            'upload_date': '20160403',
+        },
     }]
 
 
@@ -251,6 +311,8 @@ class ArteTVDDCIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:ddc'
     _VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>[^/?#&]+)'
 
+    _TESTS = []
+
     def _real_extract(self, url):
         video_id, lang = self._extract_url_info(url)
         if lang == 'folge':
@@ -269,7 +331,7 @@ class ArteTVConcertIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:concert'
     _VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde',
         'md5': '9ea035b7bd69696b67aa2ccaaa218161',
         'info_dict': {
@@ -279,14 +341,14 @@ class ArteTVConcertIE(ArteTVPlus7IE):
             'upload_date': '20140128',
             'description': 'md5:486eb08f991552ade77439fe6d82c305',
         },
-    }
+    }]
 
 
 class ArteTVCinemaIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:cinema'
     _VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>.+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://cinema.arte.tv/de/node/38291',
         'md5': '6b275511a5107c60bacbeeda368c3aa1',
         'info_dict': {
@@ -296,7 +358,7 @@ class ArteTVCinemaIE(ArteTVPlus7IE):
             'upload_date': '20160122',
             'description': 'md5:7f749bbb77d800ef2be11d54529b96bc',
         },
-    }
+    }]
 
 
 class ArteTVMagazineIE(ArteTVPlus7IE):
@@ -334,16 +396,48 @@ class ArteTVEmbedIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:embed'
     _VALID_URL = r'''(?x)
         http://www\.arte\.tv
-        /playerv2/embed\.php\?json_url=
+        /(?:playerv2/embed|arte_vp/index)\.php\?json_url=
         (?P<json_url>
             http://arte\.tv/papi/tvguide/videos/stream/player/
             (?P<lang>[^/]+)/(?P<id>[^/]+)[^&]*
         )
     '''
 
+    _TESTS = []
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         lang = mobj.group('lang')
         json_url = mobj.group('json_url')
         return self._extract_from_json_url(json_url, video_id, lang)
+
+
+class ArteTVPlaylistIE(ArteTVBaseIE):
+    IE_NAME = 'arte.tv:playlist'
+    _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/[^#]*#collection/(?P<id>PL-\d+)'
+
+    _TESTS = [{
+        'url': 'http://www.arte.tv/guide/de/plus7/?country=DE#collection/PL-013263/ARTETV',
+        'info_dict': {
+            'id': 'PL-013263',
+            'title': 'Areva & Uramin',
+        },
+        'playlist_mincount': 6,
+    }, {
+        'url': 'http://www.arte.tv/guide/de/playlists?country=DE#collection/PL-013190/ARTETV',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id, lang = self._extract_url_info(url)
+        collection = self._download_json(
+            'https://api.arte.tv/api/player/v1/collectionData/%s/%s?source=videos'
+            % (lang, playlist_id), playlist_id)
+        title = collection.get('title')
+        description = collection.get('shortDescription') or collection.get('teaserText')
+        entries = [
+            self._extract_from_json_url(
+                video['jsonUrl'], video.get('programId') or playlist_id, lang)
+            for video in collection['videos'] if video.get('jsonUrl')]
+        return self.playlist_result(entries, playlist_id, title, description)

youtube_dl/extractor/atresplayer.py

@@ -6,16 +6,14 @@ import hashlib
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_str,
-    compat_urllib_parse,
-)
+from ..compat import compat_str
 from ..utils import (
-    int_or_none,
-    float_or_none,
-    sanitized_Request,
-    xpath_text,
     ExtractorError,
+    float_or_none,
+    int_or_none,
+    sanitized_Request,
+    urlencode_postdata,
+    xpath_text,
 )
 
 
@@ -86,7 +84,7 @@ class AtresPlayerIE(InfoExtractor):
         }
 
         request = sanitized_Request(
-            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+            self._LOGIN_URL, urlencode_postdata(login_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         response = self._download_webpage(
             request, None, 'Logging in as %s' % username)

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/audiomack.py

@@ -30,14 +30,14 @@ class AudiomackIE(InfoExtractor):
         # audiomack wrapper around soundcloud song
         {
             'add_ie': ['Soundcloud'],
-            'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare',
+            'url': 'http://www.audiomack.com/song/hip-hop-daily/black-mamba-freestyle',
             'info_dict': {
-                'id': '172419696',
+                'id': '258901379',
                 'ext': 'mp3',
-                'description': 'md5:1fc3272ed7a635cce5be1568c2822997',
-                'title': 'Young Thug ft Lil Wayne - Take Kare',
-                'uploader': 'Young Thug World',
-                'upload_date': '20141016',
+                'description': 'mamba day freestyle for the legend Kobe Bryant ',
+                'title': 'Black Mamba Freestyle [Prod. By Danny Wolf]',
+                'uploader': 'ILOVEMAKONNEN',
+                'upload_date': '20160414',
             }
         },
     ]

youtube_dl/extractor/azubu.py

@@ -98,7 +98,7 @@ class AzubuIE(InfoExtractor):
 
 
 class AzubuLiveIE(InfoExtractor):
-    _VALID_URL = r'http://www.azubu.tv/(?P<id>[^/]+)$'
+    _VALID_URL = r'https?://www.azubu.tv/(?P<id>[^/]+)$'
 
     _TEST = {
         'url': 'http://www.azubu.tv/MarsTVMDLen',
@@ -120,6 +120,7 @@ class AzubuLiveIE(InfoExtractor):
         bc_info = self._download_json(req, user)
         m3u8_url = next(source['src'] for source in bc_info['sources'] if source['container'] == 'M2TS')
         formats = self._extract_m3u8_formats(m3u8_url, user, ext='mp4')
+        self._sort_formats(formats)
 
         return {
             'id': info['id'],

youtube_dl/extractor/baidu.py

@@ -9,7 +9,7 @@ from ..utils import unescapeHTML
 
 class BaiduVideoIE(InfoExtractor):
     IE_DESC = '百度视频'
-    _VALID_URL = r'http://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
+    _VALID_URL = r'https?://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
     _TESTS = [{
         'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
         'info_dict': {

youtube_dl/extractor/bambuser.py

@@ -4,15 +4,13 @@ import re
 import itertools
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
-    compat_str,
-)
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
-    int_or_none,
     float_or_none,
+    int_or_none,
     sanitized_Request,
+    urlencode_postdata,
 )
 
 
@@ -58,7 +56,7 @@ class BambuserIE(InfoExtractor):
         }
 
         request = sanitized_Request(
-            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+            self._LOGIN_URL, urlencode_postdata(login_form))
         request.add_header('Referer', self._LOGIN_URL)
         response = self._download_webpage(
             request, None, 'Logging in as %s' % username)

youtube_dl/extractor/bandcamp.py

@@ -29,7 +29,7 @@ class BandcampIE(InfoExtractor):
         '_skip': 'There is a limit of 200 free downloads / month for the test song'
     }, {
         'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
-        'md5': '2b68e5851514c20efdff2afc5603b8b4',
+        'md5': '73d0b3171568232574e45652f8720b5c',
         'info_dict': {
             'id': '2650410135',
             'ext': 'mp3',
@@ -48,6 +48,10 @@ class BandcampIE(InfoExtractor):
             if m_trackinfo:
                 json_code = m_trackinfo.group(1)
                 data = json.loads(json_code)[0]
+                track_id = compat_str(data['id'])
+
+                if not data.get('file'):
+                    raise ExtractorError('Not streamable', video_id=track_id, expected=True)
 
                 formats = []
                 for format_id, format_url in data['file'].items():
@@ -64,7 +68,7 @@ class BandcampIE(InfoExtractor):
                 self._sort_formats(formats)
 
                 return {
-                    'id': compat_str(data['id']),
+                    'id': track_id,
                     'title': data['title'],
                     'formats': formats,
                     'duration': float_or_none(data.get('duration')),

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 (
@@ -329,6 +328,7 @@ class BBCCoUkIE(InfoExtractor):
                     'format_id': '%s_%s' % (service, format['format_id']),
                     'abr': abr,
                     'acodec': acodec,
+                    'vcodec': 'none',
                 })
             formats.extend(conn_formats)
         return formats
@@ -561,7 +561,7 @@ 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 +670,18 @@ 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',
+            'description': 'Fast-paced football, wit, wisdom and a ready smile - why Liverpool fans should come to love new boss Jurgen Klopp.',
         },
         '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',
@@ -681,6 +690,10 @@ class BBCIE(BBCCoUkIE):
         # custom redirection to www.bbc.com
         'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
         'only_matching': True,
+    }, {
+        # single video article embedded with data-media-vpid
+        'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
+        'only_matching': True,
     }]
 
     @classmethod
@@ -735,8 +748,17 @@ 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(
@@ -797,13 +819,11 @@ 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)
         programme_id = self._search_regex(
-            [r'data-video-player-vpid="(%s)"' % self._ID_REGEX,
+            [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX,
              r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
              r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
             webpage, 'vpid', default=None)
@@ -829,10 +849,6 @@ 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),
@@ -932,7 +948,7 @@ class BBCIE(BBCCoUkIE):
 
 
 class BBCCoUkArticleIE(InfoExtractor):
-    _VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
     IE_NAME = 'bbc.co.uk:article'
     IE_DESC = 'BBC articles'
 

youtube_dl/extractor/beeg.py

@@ -33,8 +33,33 @@ class BeegIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
+        webpage = self._download_webpage(url, video_id)
+
+        cpl_url = self._search_regex(
+            r'<script[^>]+src=(["\'])(?P<url>(?:https?:)?//static\.beeg\.com/cpl/\d+\.js.*?)\1',
+            webpage, 'cpl', default=None, group='url')
+
+        beeg_version, beeg_salt = [None] * 2
+
+        if cpl_url:
+            cpl = self._download_webpage(
+                self._proto_relative_url(cpl_url), video_id,
+                'Downloading cpl JS', fatal=False)
+            if cpl:
+                beeg_version = self._search_regex(
+                    r'beeg_version\s*=\s*(\d+)', cpl,
+                    'beeg version', default=None) or self._search_regex(
+                    r'/(\d+)\.js', cpl_url, 'beeg version', default=None)
+                beeg_salt = self._search_regex(
+                    r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg beeg_salt',
+                    default=None, group='beeg_salt')
+
+        beeg_version = beeg_version or '1750'
+        beeg_salt = beeg_salt or 'MIDtGaw96f0N1kMMAM1DE46EC9pmFr'
+
         video = self._download_json(
-            'https://api.beeg.com/api/v5/video/%s' % video_id, video_id)
+            'http://api.beeg.com/api/v6/%s/video/%s' % (beeg_version, video_id),
+            video_id)
 
         def split(o, e):
             def cut(s, x):
@@ -50,8 +75,8 @@ class BeegIE(InfoExtractor):
             return n
 
         def decrypt_key(key):
-            # Reverse engineered from http://static.beeg.com/cpl/1105.js
-            a = '5ShMcIQlssOd7zChAIOlmeTZDaUxULbJRnywYaiB'
+            # Reverse engineered from http://static.beeg.com/cpl/1738.js
+            a = beeg_salt
             e = compat_urllib_parse_unquote(key)
             o = ''.join([
                 compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21)
@@ -101,5 +126,5 @@ class BeegIE(InfoExtractor):
             'duration': duration,
             'tags': tags,
             'formats': formats,
-            'age_limit': 18,
+            'age_limit': self._rta_search(webpage),
         }

youtube_dl/extractor/behindkink.py

@@ -8,7 +8,7 @@ from ..utils import url_basename
 
 
 class BehindKinkIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
+    _VALID_URL = r'https?://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
     _TEST = {
         'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/',
         'md5': '507b57d8fdcd75a41a9a7bdb7989c762',

youtube_dl/extractor/bet.py

@@ -94,6 +94,7 @@ class BetIE(InfoExtractor):
             xpath_with_ns('./media:thumbnail', NS_MAP)).get('url')
 
         formats = self._extract_smil_formats(smil_url, display_id)
+        self._sort_formats(formats)
 
         return {
             'id': video_id,

youtube_dl/extractor/bilibili.py

@@ -1,34 +1,42 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import calendar
+import datetime
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import (
+    compat_etree_fromstring,
+    compat_str,
+    compat_parse_qs,
+    compat_xml_parse_error,
+)
 from ..utils import (
-    int_or_none,
-    unescapeHTML,
     ExtractorError,
+    int_or_none,
+    float_or_none,
     xpath_text,
 )
 
 
 class BiliBiliIE(InfoExtractor):
-    _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?'
+    _VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.bilibili.tv/video/av1074402/',
-        'md5': '2c301e4dab317596e837c3e7633e7d86',
+        'md5': '5f7d29e1a2872f3df0cf76b1f87d3788',
         'info_dict': {
             'id': '1554319',
             'ext': 'flv',
             'title': '【金坷垃】金泡沫',
-            'duration': 308313,
+            'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
+            'duration': 308.067,
+            'timestamp': 1398012660,
             'upload_date': '20140420',
             'thumbnail': 're:^https?://.+\.jpg',
-            'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
-            'timestamp': 1397983878,
             'uploader': '菊子桑',
+            'uploader_id': '156160',
         },
     }, {
         'url': 'http://www.bilibili.com/video/av1041170/',
@@ -36,75 +44,110 @@ class BiliBiliIE(InfoExtractor):
             'id': '1041170',
             'title': '【BD1080P】刀语【诸神&异域】',
             'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
-            'uploader': '枫叶逝去',
-            'timestamp': 1396501299,
         },
         'playlist_count': 9,
     }]
 
+    # BiliBili blocks keys from time to time. The current key is extracted from
+    # the Android client
+    # TODO: find the sign algorithm used in the flash player
+    _APP_KEY = '86385cdc024c0f6c'
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        page_num = mobj.group('page_num') or '1'
 
-        view_data = self._download_json(
-            'http://api.bilibili.com/view?type=json&appkey=8e9fc618fbd41e28&id=%s&page=%s' % (video_id, page_num),
-            video_id)
-        if 'error' in view_data:
-            raise ExtractorError('%s said: %s' % (self.IE_NAME, view_data['error']), expected=True)
+        webpage = self._download_webpage(url, video_id)
 
-        cid = view_data['cid']
-        title = unescapeHTML(view_data['title'])
+        params = compat_parse_qs(self._search_regex(
+            [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
+             r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
+            webpage, 'player parameters'))
+        cid = params['cid'][0]
 
-        doc = self._download_xml(
-            'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid,
-            cid,
-            'Downloading page %s/%s' % (page_num, view_data['pages'])
-        )
+        info_xml_str = self._download_webpage(
+            'http://interface.bilibili.com/v_cdn_play',
+            cid, query={'appkey': self._APP_KEY, 'cid': cid},
+            note='Downloading video info page')
 
-        if xpath_text(doc, './result') == 'error':
-            raise ExtractorError('%s said: %s' % (self.IE_NAME, xpath_text(doc, './message')), expected=True)
+        err_msg = None
+        durls = None
+        info_xml = None
+        try:
+            info_xml = compat_etree_fromstring(info_xml_str.encode('utf-8'))
+        except compat_xml_parse_error:
+            info_json = self._parse_json(info_xml_str, video_id, fatal=False)
+            err_msg = (info_json or {}).get('error_text')
+        else:
+            err_msg = xpath_text(info_xml, './message')
+
+        if info_xml is not None:
+            durls = info_xml.findall('./durl')
+        if not durls:
+            if err_msg:
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, err_msg), expected=True)
+            else:
+                raise ExtractorError('No videos found!')
 
         entries = []
 
-        for durl in doc.findall('./durl'):
+        for durl in durls:
             size = xpath_text(durl, ['./filesize', './size'])
             formats = [{
                 'url': durl.find('./url').text,
                 'filesize': int_or_none(size),
-                'ext': 'flv',
             }]
-            backup_urls = durl.find('./backup_url')
-            if backup_urls is not None:
-                for backup_url in backup_urls.findall('./url'):
-                    formats.append({'url': backup_url.text})
-            formats.reverse()
+            for backup_url in durl.findall('./backup_url/url'):
+                formats.append({
+                    'url': backup_url.text,
+                    # backup URLs have lower priorities
+                    'preference': -2 if 'hd.mp4' in backup_url.text else -3,
+                })
+
+            self._sort_formats(formats)
 
             entries.append({
                 'id': '%s_part%s' % (cid, xpath_text(durl, './order')),
-                'title': title,
                 'duration': int_or_none(xpath_text(durl, './length'), 1000),
                 'formats': formats,
             })
 
+        title = self._html_search_regex('<h1[^>]+title="([^"]+)">', webpage, 'title')
+        description = self._html_search_meta('description', webpage)
+        datetime_str = self._html_search_regex(
+            r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False)
+        if datetime_str:
+            timestamp = calendar.timegm(datetime.datetime.strptime(datetime_str, '%Y-%m-%dT%H:%M').timetuple())
+
+        # TODO 'view_count' requires deobfuscating Javascript
         info = {
             'id': compat_str(cid),
             'title': title,
-            'description': view_data.get('description'),
-            'thumbnail': view_data.get('pic'),
-            'uploader': view_data.get('author'),
-            'timestamp': int_or_none(view_data.get('created')),
-            'view_count': int_or_none(view_data.get('play')),
-            'duration': int_or_none(xpath_text(doc, './timelength')),
+            'description': description,
+            'timestamp': timestamp,
+            'thumbnail': self._html_search_meta('thumbnailUrl', webpage),
+            'duration': float_or_none(xpath_text(info_xml, './timelength'), scale=1000),
         }
 
+        uploader_mobj = re.search(
+            r'<a[^>]+href="https?://space\.bilibili\.com/(?P<id>\d+)"[^>]+title="(?P<name>[^"]+)"',
+            webpage)
+        if uploader_mobj:
+            info.update({
+                'uploader': uploader_mobj.group('name'),
+                'uploader_id': uploader_mobj.group('id'),
+            })
+
+        for entry in entries:
+            entry.update(info)
+
         if len(entries) == 1:
-            entries[0].update(info)
             return entries[0]
         else:
-            info.update({
+            return {
                 '_type': 'multi_video',
                 'id': video_id,
+                'title': title,
+                'description': description,
                 'entries': entries,
-            })
-            return info
+            }

youtube_dl/extractor/biobiochiletv.py

@@ -0,0 +1,86 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import remove_end
+
+
+class BioBioChileTVIE(InfoExtractor):
+    _VALID_URL = r'https?://tv\.biobiochile\.cl/notas/(?:[^/]+/)+(?P<id>[^/]+)\.shtml'
+
+    _TESTS = [{
+        'url': 'http://tv.biobiochile.cl/notas/2015/10/21/sobre-camaras-y-camarillas-parlamentarias.shtml',
+        'md5': '26f51f03cf580265defefb4518faec09',
+        'info_dict': {
+            'id': 'sobre-camaras-y-camarillas-parlamentarias',
+            'ext': 'mp4',
+            'title': 'Sobre Cámaras y camarillas parlamentarias',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'Fernando Atria',
+        },
+    }, {
+        # different uploader layout
+        'url': 'http://tv.biobiochile.cl/notas/2016/03/18/natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades.shtml',
+        'md5': 'edc2e6b58974c46d5b047dea3c539ff3',
+        'info_dict': {
+            'id': 'natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades',
+            'ext': 'mp4',
+            'title': 'Natalia Valdebenito repasa a diputado Hasbún: Pasó a la categoría de hablar brutalidades',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'Piangella Obrador',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'http://tv.biobiochile.cl/notas/2015/10/21/exclusivo-hector-pinto-formador-de-chupete-revela-version-del-ex-delantero-albo.shtml',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = remove_end(self._og_search_title(webpage), ' - BioBioChile TV')
+
+        file_url = self._search_regex(
+            r'loadFWPlayerVideo\([^,]+,\s*(["\'])(?P<url>.+?)\1',
+            webpage, 'file url', group='url')
+
+        base_url = self._search_regex(
+            r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*fileURL', webpage,
+            'base url', default='http://unlimited2-cl.digitalproserver.com/bbtv/',
+            group='url')
+
+        formats = self._extract_m3u8_formats(
+            '%s%s/playlist.m3u8' % (base_url, file_url), video_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
+        f = {
+            'url': '%s%s' % (base_url, file_url),
+            'format_id': 'http',
+            'protocol': 'http',
+            'preference': 1,
+        }
+        if formats:
+            f_copy = formats[-1].copy()
+            f_copy.update(f)
+            f = f_copy
+        formats.append(f)
+        self._sort_formats(formats)
+
+        thumbnail = self._og_search_thumbnail(webpage)
+        uploader = self._html_search_regex(
+            r'<a[^>]+href=["\']https?://busca\.biobiochile\.cl/author[^>]+>(.+?)</a>',
+            webpage, 'uploader', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'formats': formats,
+        }

youtube_dl/extractor/biqle.py

@@ -0,0 +1,39 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class BIQLEIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?biqle\.(?:com|org|ru)/watch/(?P<id>-?\d+_\d+)'
+    _TESTS = [{
+        'url': 'http://www.biqle.ru/watch/847655_160197695',
+        'md5': 'ad5f746a874ccded7b8f211aeea96637',
+        'info_dict': {
+            'id': '160197695',
+            'ext': 'mp4',
+            'title': 'Foo Fighters - The Pretender (Live at Wembley Stadium)',
+            'uploader': 'Andrey Rogozin',
+            'upload_date': '20110605',
+        }
+    }, {
+        'url': 'https://biqle.org/watch/-44781847_168547604',
+        'md5': '7f24e72af1db0edf7c1aaba513174f97',
+        'info_dict': {
+            'id': '168547604',
+            'ext': 'mp4',
+            'title': 'Ребенок в шоке от автоматической мойки',
+            'uploader': 'Dmitry Kotov',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        embed_url = self._proto_relative_url(self._search_regex(
+            r'<iframe.+?src="((?:http:)?//daxab\.com/[^"]+)".*?></iframe>', webpage, 'embed url'))
+
+        return {
+            '_type': 'url_transparent',
+            'url': embed_url,
+        }

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/bloomberg.py

@@ -17,6 +17,9 @@ class BloombergIE(InfoExtractor):
             'title': 'Shah\'s Presentation on Foreign-Exchange Strategies',
             'description': 'md5:a8ba0302912d03d246979735c17d2761',
         },
+        'params': {
+            'format': 'best[format_id^=hds]',
+        },
     }, {
         'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
         'only_matching': True,

youtube_dl/extractor/bokecc.py

@@ -33,7 +33,7 @@ class BokeCCBaseIE(InfoExtractor):
 
 class BokeCCIE(BokeCCBaseIE):
     _IE_DESC = 'CC视频'
-    _VALID_URL = r'http://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
+    _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
 
     _TESTS = [{
         'url': 'http://union.bokecc.com/playvideo.bo?vid=E44D40C15E65EA30&uid=CD0C5D3C8614B28B',

youtube_dl/extractor/bpb.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class BpbIE(InfoExtractor):
     IE_DESC = 'Bundeszentrale für politische Bildung'
-    _VALID_URL = r'http://www\.bpb\.de/mediathek/(?P<id>[0-9]+)/'
+    _VALID_URL = r'https?://www\.bpb\.de/mediathek/(?P<id>[0-9]+)/'
 
     _TEST = {
         'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',

youtube_dl/extractor/bravotv.py

@@ -0,0 +1,31 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import smuggle_url
+
+
+class BravoTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bravotv\.com/(?:[^/]+/)+videos/(?P<id>[^/?]+)'
+    _TEST = {
+        'url': 'http://www.bravotv.com/last-chance-kitchen/season-5/videos/lck-ep-12-fishy-finale',
+        'md5': 'd60cdf68904e854fac669bd26cccf801',
+        'info_dict': {
+            'id': 'LitrBdX64qLn',
+            'ext': 'mp4',
+            'title': 'Last Chance Kitchen Returns',
+            'description': 'S13: Last Chance Kitchen Returns for Top Chef Season 13',
+            'timestamp': 1448926740,
+            'upload_date': '20151130',
+            'uploader': 'NBCU-BRAV',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        account_pid = self._search_regex(r'"account_pid"\s*:\s*"([^"]+)"', webpage, 'account pid')
+        release_pid = self._search_regex(r'"release_pid"\s*:\s*"([^"]+)"', webpage, 'release pid')
+        return self.url_result(smuggle_url(
+            'http://link.theplatform.com/s/%s/%s?mbr=true&switch=progressive' % (account_pid, release_pid),
+            {'force_smil_url': True}), 'ThePlatform', release_pid)

youtube_dl/extractor/breakcom.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class BreakIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
         'info_dict': {

youtube_dl/extractor/brightcove.py

@@ -9,10 +9,10 @@ from ..compat import (
     compat_etree_fromstring,
     compat_parse_qs,
     compat_str,
-    compat_urllib_parse,
     compat_urllib_parse_urlparse,
     compat_urlparse,
     compat_xml_parse_error,
+    compat_HTTPError,
 )
 from ..utils import (
     determine_ext,
@@ -23,16 +23,16 @@ from ..utils import (
     js_to_json,
     int_or_none,
     parse_iso8601,
-    sanitized_Request,
     unescapeHTML,
     unsmuggle_url,
+    update_url_query,
 )
 
 
 class BrightcoveLegacyIE(InfoExtractor):
     IE_NAME = 'brightcove:legacy'
     _VALID_URL = r'(?:https?://.*brightcove\.com/(services|viewer).*?\?|brightcove:)(?P<query>.*)'
-    _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
+    _FEDERATED_URL = 'http://c.brightcove.com/services/viewer/htmlFederated'
 
     _TESTS = [
         {
@@ -46,6 +46,9 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'title': 'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”',
                 'uploader': '8TV',
                 'description': 'md5:a950cc4285c43e44d763d036710cd9cd',
+                'timestamp': 1368213670,
+                'upload_date': '20130510',
+                'uploader_id': '1589608506001',
             }
         },
         {
@@ -57,6 +60,9 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'title': 'JVMLS 2012: Arrays 2.0 - Opportunities and Challenges',
                 'description': 'John Rose speaks at the JVM Language Summit, August 1, 2012.',
                 'uploader': 'Oracle',
+                'timestamp': 1344975024,
+                'upload_date': '20120814',
+                'uploader_id': '1460825906',
             },
         },
         {
@@ -68,6 +74,9 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'title': 'This Bracelet Acts as a Personal Thermostat',
                 'description': 'md5:547b78c64f4112766ccf4e151c20b6a0',
                 'uploader': 'Mashable',
+                'timestamp': 1382041798,
+                'upload_date': '20131017',
+                'uploader_id': '1130468786001',
             },
         },
         {
@@ -85,14 +94,17 @@ class BrightcoveLegacyIE(InfoExtractor):
         {
             # test flv videos served by akamaihd.net
             # From http://www.redbull.com/en/bike/stories/1331655643987/replay-uci-dh-world-cup-2014-from-fort-william
-            'url': 'http://c.brightcove.com/services/viewer/htmlFederated?%40videoPlayer=ref%3ABC2996102916001&linkBaseURL=http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fvideos%2F1331655630249%2Freplay-uci-fort-william-2014-dh&playerKey=AQ%7E%7E%2CAAAApYJ7UqE%7E%2Cxqr_zXk0I-zzNndy8NlHogrCb5QdyZRf&playerID=1398061561001#__youtubedl_smuggle=%7B%22Referer%22%3A+%22http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fstories%2F1331655643987%2Freplay-uci-dh-world-cup-2014-from-fort-william%22%7D',
+            'url': 'http://c.brightcove.com/services/viewer/htmlFederated?%40videoPlayer=ref%3Aevent-stream-356&linkBaseURL=http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fvideos%2F1331655630249%2Freplay-uci-fort-william-2014-dh&playerKey=AQ%7E%7E%2CAAAApYJ7UqE%7E%2Cxqr_zXk0I-zzNndy8NlHogrCb5QdyZRf&playerID=1398061561001#__youtubedl_smuggle=%7B%22Referer%22%3A+%22http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fstories%2F1331655643987%2Freplay-uci-dh-world-cup-2014-from-fort-william%22%7D',
             # The md5 checksum changes on each download
             'info_dict': {
-                'id': '2996102916001',
+                'id': '3750436379001',
                 'ext': 'flv',
                 'title': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
-                'uploader': 'Red Bull TV',
+                'uploader': 'RBTV Old (do not use)',
                 'description': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
+                'timestamp': 1409122195,
+                'upload_date': '20140827',
+                'uploader_id': '710858724001',
             },
         },
         {
@@ -106,6 +118,12 @@ class BrightcoveLegacyIE(InfoExtractor):
             'playlist_mincount': 7,
         },
     ]
+    FLV_VCODECS = {
+        1: 'SORENSON',
+        2: 'ON2',
+        3: 'H264',
+        4: 'VP8',
+    }
 
     @classmethod
     def _build_brighcove_url(cls, object_str):
@@ -136,13 +154,16 @@ class BrightcoveLegacyIE(InfoExtractor):
         else:
             flashvars = {}
 
+        data_url = object_doc.attrib.get('data', '')
+        data_url_params = compat_parse_qs(compat_urllib_parse_urlparse(data_url).query)
+
         def find_param(name):
             if name in flashvars:
                 return flashvars[name]
             node = find_xpath_attr(object_doc, './param', 'name', name)
             if node is not None:
                 return node.attrib['value']
-            return None
+            return data_url_params.get(name)
 
         params = {}
 
@@ -155,8 +176,8 @@ class BrightcoveLegacyIE(InfoExtractor):
         # Not all pages define this value
         if playerKey is not None:
             params['playerKey'] = playerKey
-        # The three fields hold the id of the video
-        videoPlayer = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID')
+        # These fields hold the id of the video
+        videoPlayer = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID') or find_param('@videoList')
         if videoPlayer is not None:
             params['@videoPlayer'] = videoPlayer
         linkBase = find_param('linkBaseURL')
@@ -184,8 +205,7 @@ class BrightcoveLegacyIE(InfoExtractor):
 
     @classmethod
     def _make_brightcove_url(cls, params):
-        data = compat_urllib_parse.urlencode(params)
-        return cls._FEDERATED_URL_TEMPLATE % data
+        return update_url_query(cls._FEDERATED_URL, params)
 
     @classmethod
     def _extract_brightcove_url(cls, webpage):
@@ -239,7 +259,7 @@ class BrightcoveLegacyIE(InfoExtractor):
             # We set the original url as the default 'Referer' header
             referer = smuggled_data.get('Referer', url)
             return self._get_video_info(
-                videoPlayer[0], query_str, query, referer=referer)
+                videoPlayer[0], query, referer=referer)
         elif 'playerKey' in query:
             player_key = query['playerKey']
             return self._get_playlist_info(player_key[0])
@@ -248,15 +268,14 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'Cannot find playerKey= variable. Did you forget quotes in a shell invocation?',
                 expected=True)
 
-    def _get_video_info(self, video_id, query_str, query, referer=None):
-        request_url = self._FEDERATED_URL_TEMPLATE % query_str
-        req = sanitized_Request(request_url)
+    def _get_video_info(self, video_id, query, referer=None):
+        headers = {}
         linkBase = query.get('linkBaseURL')
         if linkBase is not None:
             referer = linkBase[0]
         if referer is not None:
-            req.add_header('Referer', referer)
-        webpage = self._download_webpage(req, video_id)
+            headers['Referer'] = referer
+        webpage = self._download_webpage(self._FEDERATED_URL, video_id, headers=headers, query=query)
 
         error_msg = self._html_search_regex(
             r"<h1>We're sorry.</h1>([\s\n]*<p>.*?</p>)+", webpage,
@@ -288,15 +307,20 @@ class BrightcoveLegacyIE(InfoExtractor):
                                     playlist_title=playlist_info['mediaCollectionDTO']['displayName'])
 
     def _extract_video_info(self, video_info):
+        video_id = compat_str(video_info['id'])
+        publisher_id = video_info.get('publisherId')
         info = {
-            'id': compat_str(video_info['id']),
+            'id': video_id,
             'title': video_info['displayName'].strip(),
             'description': video_info.get('shortDescription'),
             'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
             'uploader': video_info.get('publisherName'),
+            'uploader_id': compat_str(publisher_id) if publisher_id else None,
+            'duration': float_or_none(video_info.get('length'), 1000),
+            'timestamp': int_or_none(video_info.get('creationDate'), 1000),
         }
 
-        renditions = video_info.get('renditions')
+        renditions = video_info.get('renditions', []) + video_info.get('IOSRenditions', [])
         if renditions:
             formats = []
             for rend in renditions:
@@ -308,7 +332,8 @@ class BrightcoveLegacyIE(InfoExtractor):
                     url_comp = compat_urllib_parse_urlparse(url)
                     if url_comp.path.endswith('.m3u8'):
                         formats.extend(
-                            self._extract_m3u8_formats(url, info['id'], 'mp4'))
+                            self._extract_m3u8_formats(
+                                url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
                         continue
                     elif 'akamaihd.net' in url_comp.netloc:
                         # This type of renditions are served through
@@ -317,19 +342,42 @@ class BrightcoveLegacyIE(InfoExtractor):
                         ext = 'flv'
                 if ext is None:
                     ext = determine_ext(url)
-                size = rend.get('size')
-                formats.append({
+                tbr = int_or_none(rend.get('encodingRate'), 1000)
+                a_format = {
+                    'format_id': 'http%s' % ('-%s' % tbr if tbr else ''),
                     'url': url,
                     'ext': ext,
-                    'height': rend.get('frameHeight'),
-                    'width': rend.get('frameWidth'),
-                    'filesize': size if size != 0 else None,
-                })
+                    'filesize': int_or_none(rend.get('size')) or None,
+                    'tbr': tbr,
+                }
+                if rend.get('audioOnly'):
+                    a_format.update({
+                        'vcodec': 'none',
+                    })
+                else:
+                    a_format.update({
+                        'height': int_or_none(rend.get('frameHeight')),
+                        'width': int_or_none(rend.get('frameWidth')),
+                        'vcodec': rend.get('videoCodec'),
+                    })
+
+                # m3u8 manifests with remote == false are media playlists
+                # Not calling _extract_m3u8_formats here to save network traffic
+                if ext == 'm3u8':
+                    a_format.update({
+                        'format_id': 'hls%s' % ('-%s' % tbr if tbr else ''),
+                        'ext': 'mp4',
+                        'protocol': 'm3u8_native',
+                    })
+
+                formats.append(a_format)
             self._sort_formats(formats)
             info['formats'] = formats
         elif video_info.get('FLVFullLengthURL') is not None:
             info.update({
                 'url': video_info['FLVFullLengthURL'],
+                'vcodec': self.FLV_VCODECS.get(video_info.get('FLVFullCodec')),
+                'filesize': int_or_none(video_info.get('FLVFullSize')),
             })
 
         if self._downloader.params.get('include_ads', False):
@@ -349,13 +397,13 @@ class BrightcoveLegacyIE(InfoExtractor):
                     return ad_info
 
         if 'url' not in info and not info.get('formats'):
-            raise ExtractorError('Unable to extract video url for %s' % info['id'])
+            raise ExtractorError('Unable to extract video url for %s' % video_id)
         return info
 
 
 class BrightcoveNewIE(InfoExtractor):
     IE_NAME = 'brightcove:new'
-    _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>(?:ref:)?\d+)'
+    _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>\d+|ref:[^&]+)'
     _TESTS = [{
         'url': 'http://players.brightcove.net/929656772001/e41d32dc-ec74-459e-a845-6c69f7b724ea_default/index.html?videoId=4463358922001',
         'md5': 'c8100925723840d4b0d243f7025703be',
@@ -385,12 +433,21 @@ class BrightcoveNewIE(InfoExtractor):
             'formats': 'mincount:41',
         },
         'params': {
+            # m3u8 download
             'skip_download': True,
         }
     }, {
         # ref: prefixed video id
         'url': 'http://players.brightcove.net/3910869709001/21519b5c-4b3b-4363-accb-bdc8f358f823_default/index.html?videoId=ref:7069442',
         'only_matching': True,
+    }, {
+        # non numeric ref: prefixed video id
+        'url': 'http://players.brightcove.net/710858724001/default_default/index.html?videoId=ref:event-stream-356',
+        'only_matching': True,
+    }, {
+        # unavailable video without message but with error_code
+        'url': 'http://players.brightcove.net/1305187701/c832abfb-641b-44eb-9da0-2fe76786505f_default/index.html?videoId=4377407326001',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -410,8 +467,8 @@ class BrightcoveNewIE(InfoExtractor):
 
         # Look for iframe embeds [1]
         for _, url in re.findall(
-                r'<iframe[^>]+src=(["\'])((?:https?:)//players\.brightcove\.net/\d+/[^/]+/index\.html.+?)\1', webpage):
-            entries.append(url)
+                r'<iframe[^>]+src=(["\'])((?:https?:)?//players\.brightcove\.net/\d+/[^/]+/index\.html.+?)\1', webpage):
+            entries.append(url if url.startswith('http') else 'http:' + url)
 
         # Look for embed_in_page embeds [2]
         for video_id, account_id, player_id, embed in re.findall(
@@ -420,11 +477,11 @@ class BrightcoveNewIE(InfoExtractor):
                 # According to [4] data-video-id may be prefixed with ref:
                 r'''(?sx)
                     <video[^>]+
-                        data-video-id=["\']((?:ref:)?\d+)["\'][^>]*>.*?
+                        data-video-id=["\'](\d+|ref:[^"\']+)["\'][^>]*>.*?
                     </video>.*?
                     <script[^>]+
                         src=["\'](?:https?:)?//players\.brightcove\.net/
-                        (\d+)/([\da-f-]+)_([^/]+)/index\.min\.js
+                        (\d+)/([^/]+)_([^/]+)/index(?:\.min)?\.js
                 ''', webpage):
             entries.append(
                 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
@@ -454,24 +511,34 @@ class BrightcoveNewIE(InfoExtractor):
                 r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
                 webpage, 'policy key', group='pk')
 
-        req = sanitized_Request(
-            'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s'
-            % (account_id, video_id),
-            headers={'Accept': 'application/json;pk=%s' % policy_key})
-        json_data = self._download_json(req, video_id)
+        api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' % (account_id, video_id)
+        try:
+            json_data = self._download_json(api_url, video_id, headers={
+                'Accept': 'application/json;pk=%s' % policy_key
+            })
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                json_data = self._parse_json(e.cause.read().decode(), video_id)[0]
+                raise ExtractorError(
+                    json_data.get('message') or json_data['error_code'], expected=True)
+            raise
 
-        title = json_data['name']
+        title = json_data['name'].strip()
 
         formats = []
         for source in json_data.get('sources', []):
+            container = source.get('container')
             source_type = source.get('type')
             src = source.get('src')
-            if source_type == 'application/x-mpegURL':
+            if source_type == 'application/x-mpegURL' or container == 'M2TS':
                 if not src:
                     continue
                 formats.extend(self._extract_m3u8_formats(
-                    src, video_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id='hls', fatal=False))
+                    src, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+            elif source_type == 'application/dash+xml':
+                if not src:
+                    continue
+                formats.extend(self._extract_mpd_formats(src, video_id, 'dash', fatal=False))
             else:
                 streaming_src = source.get('streaming_src')
                 stream_name, app_name = source.get('stream_name'), source.get('app_name')
@@ -479,15 +546,23 @@ class BrightcoveNewIE(InfoExtractor):
                     continue
                 tbr = float_or_none(source.get('avg_bitrate'), 1000)
                 height = int_or_none(source.get('height'))
+                width = int_or_none(source.get('width'))
                 f = {
                     'tbr': tbr,
-                    'width': int_or_none(source.get('width')),
-                    'height': height,
                     'filesize': int_or_none(source.get('size')),
-                    'container': source.get('container'),
-                    'vcodec': source.get('codec'),
-                    'ext': source.get('container').lower(),
+                    'container': container,
+                    'ext': container.lower(),
                 }
+                if width == 0 and height == 0:
+                    f.update({
+                        'vcodec': 'none',
+                    })
+                else:
+                    f.update({
+                        'width': width,
+                        'height': height,
+                        'vcodec': source.get('codec'),
+                    })
 
                 def build_format_id(kind):
                     format_id = kind
@@ -501,7 +576,7 @@ class BrightcoveNewIE(InfoExtractor):
                     f.update({
                         'url': src or streaming_src,
                         'format_id': build_format_id('http' if src else 'http-streaming'),
-                        'preference': 2 if src else 1,
+                        'source_preference': 0 if src else -1,
                     })
                 else:
                     f.update({
@@ -512,20 +587,22 @@ class BrightcoveNewIE(InfoExtractor):
                 formats.append(f)
         self._sort_formats(formats)
 
-        description = json_data.get('description')
-        thumbnail = json_data.get('thumbnail')
-        timestamp = parse_iso8601(json_data.get('published_at'))
-        duration = float_or_none(json_data.get('duration'), 1000)
-        tags = json_data.get('tags', [])
+        subtitles = {}
+        for text_track in json_data.get('text_tracks', []):
+            if text_track.get('src'):
+                subtitles.setdefault(text_track.get('srclang'), []).append({
+                    'url': text_track['src'],
+                })
 
         return {
             'id': video_id,
             'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'timestamp': timestamp,
+            'description': json_data.get('description'),
+            'thumbnail': json_data.get('thumbnail') or json_data.get('poster'),
+            'duration': float_or_none(json_data.get('duration'), 1000),
+            'timestamp': parse_iso8601(json_data.get('published_at')),
             'uploader_id': account_id,
             'formats': formats,
-            'tags': tags,
+            'subtitles': subtitles,
+            'tags': json_data.get('tags', []),
         }

youtube_dl/extractor/byutv.py

@@ -11,6 +11,7 @@ class BYUtvIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)'
     _TEST = {
         'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
+        'md5': '05850eb8c749e2ee05ad5a1c34668493',
         'info_dict': {
             'id': 'studio-c-season-5-episode-5',
             'ext': 'mp4',
@@ -21,7 +22,8 @@ class BYUtvIE(InfoExtractor):
         },
         'params': {
             'skip_download': True,
-        }
+        },
+        'add_ie': ['Ooyala'],
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/camdemy.py

@@ -6,7 +6,7 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
     compat_urlparse,
 )
 from ..utils import (
@@ -16,7 +16,7 @@ from ..utils import (
 
 
 class CamdemyIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?camdemy\.com/media/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?camdemy\.com/media/(?P<id>\d+)'
     _TESTS = [{
         # single file
         'url': 'http://www.camdemy.com/media/5181/',
@@ -104,7 +104,7 @@ class CamdemyIE(InfoExtractor):
 
 
 class CamdemyFolderIE(InfoExtractor):
-    _VALID_URL = r'http://www.camdemy.com/folder/(?P<id>\d+)'
+    _VALID_URL = r'https?://www.camdemy.com/folder/(?P<id>\d+)'
     _TESTS = [{
         # links with trailing slash
         'url': 'http://www.camdemy.com/folder/450',
@@ -139,7 +139,7 @@ class CamdemyFolderIE(InfoExtractor):
         parsed_url = list(compat_urlparse.urlparse(url))
         query = dict(compat_urlparse.parse_qsl(parsed_url[4]))
         query.update({'displayMode': 'list'})
-        parsed_url[4] = compat_urllib_parse.urlencode(query)
+        parsed_url[4] = compat_urllib_parse_urlencode(query)
         final_url = compat_urlparse.urlunparse(parsed_url)
 
         page = self._download_webpage(final_url, folder_id)

youtube_dl/extractor/camwithher.py

@@ -0,0 +1,87 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    unified_strdate,
+)
+
+
+class CamWithHerIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?camwithher\.tv/view_video\.php\?.*\bviewkey=(?P<id>\w+)'
+
+    _TESTS = [{
+        'url': 'http://camwithher.tv/view_video.php?viewkey=6e9a24e2c0e842e1f177&page=&viewtype=&category=',
+        'info_dict': {
+            'id': '5644',
+            'ext': 'flv',
+            'title': 'Periscope Tease',
+            'description': 'In the clouds teasing on periscope to my favorite song',
+            'duration': 240,
+            'view_count': int,
+            'comment_count': int,
+            'uploader': 'MileenaK',
+            'upload_date': '20160322',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://camwithher.tv/view_video.php?viewkey=6dfd8b7c97531a459937',
+        'only_matching': True,
+    }, {
+        'url': 'http://camwithher.tv/view_video.php?page=&viewkey=6e9a24e2c0e842e1f177&viewtype=&category=',
+        'only_matching': True,
+    }, {
+        'url': 'http://camwithher.tv/view_video.php?viewkey=b6c3b5bea9515d1a1fc4&page=&viewtype=&category=mv',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        flv_id = self._html_search_regex(
+            r'<a[^>]+href=["\']/download/\?v=(\d+)', webpage, 'video id')
+
+        # Video URL construction algorithm is reverse-engineered from cwhplayer.swf
+        rtmp_url = 'rtmp://camwithher.tv/clipshare/%s' % (
+            ('mp4:%s.mp4' % flv_id) if int(flv_id) > 2010 else flv_id)
+
+        title = self._html_search_regex(
+            r'<div[^>]+style="float:left"[^>]*>\s*<h2>(.+?)</h2>', webpage, 'title')
+        description = self._html_search_regex(
+            r'>Description:</span>(.+?)</div>', webpage, 'description', default=None)
+
+        runtime = self._search_regex(
+            r'Runtime\s*:\s*(.+?) \|', webpage, 'duration', default=None)
+        if runtime:
+            runtime = re.sub(r'[\s-]', '', runtime)
+        duration = parse_duration(runtime)
+        view_count = int_or_none(self._search_regex(
+            r'Views\s*:\s*(\d+)', webpage, 'view count', default=None))
+        comment_count = int_or_none(self._search_regex(
+            r'Comments\s*:\s*(\d+)', webpage, 'comment count', default=None))
+
+        uploader = self._search_regex(
+            r'Added by\s*:\s*<a[^>]+>([^<]+)</a>', webpage, 'uploader', default=None)
+        upload_date = unified_strdate(self._search_regex(
+            r'Added on\s*:\s*([\d-]+)', webpage, 'upload date', default=None))
+
+        return {
+            'id': flv_id,
+            'url': rtmp_url,
+            'ext': 'flv',
+            'no_resume': True,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'uploader': uploader,
+            'upload_date': upload_date,
+        }

youtube_dl/extractor/cbc.py

@@ -4,64 +4,66 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import js_to_json
+from ..utils import (
+    js_to_json,
+    smuggle_url,
+)
 
 
 class CBCIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?:[^/]+/)+(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?!player/)(?:[^/]+/)+(?P<id>[^/?#]+)'
     _TESTS = [{
         # with mediaId
         'url': 'http://www.cbc.ca/22minutes/videos/clips-season-23/don-cherry-play-offs',
+        'md5': '97e24d09672fc4cf56256d6faa6c25bc',
         'info_dict': {
             'id': '2682904050',
-            'ext': 'flv',
+            'ext': 'mp4',
             '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,
+            'timestamp': 1454463000,
             'upload_date': '20160203',
-        },
-        'params': {
-            # rtmp download
-            'skip_download': True,
+            'uploader': 'CBCC-NEW',
         },
     }, {
         # with clipId
         'url': 'http://www.cbc.ca/archives/entry/1978-robin-williams-freestyles-on-90-minutes-live',
+        'md5': '0274a90b51a9b4971fe005c63f592f12',
         'info_dict': {
             'id': '2487345465',
-            'ext': 'flv',
+            'ext': 'mp4',
             '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,
+            'upload_date': '19780210',
+            'uploader': 'CBCC-NEW',
+            'timestamp': 255977160,
         },
     }, {
         # multiple iframes
         'url': 'http://www.cbc.ca/natureofthings/blog/birds-eye-view-from-vancouvers-burrard-street-bridge-how-we-got-the-shot',
         'playlist': [{
+            'md5': '377572d0b49c4ce0c9ad77470e0b96b4',
             'info_dict': {
                 'id': '2680832926',
-                'ext': 'flv',
+                'ext': 'mp4',
                 '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',
+                'upload_date': '20160201',
+                'timestamp': 1454342820,
+                'uploader': 'CBCC-NEW',
             },
         }, {
+            'md5': '415a0e3f586113894174dfb31aa5bb1a',
             'info_dict': {
                 'id': '2658915080',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Fly like an eagle!',
                 'description': 'Eagle equipped with a mini camera flies from the world\'s tallest tower',
-                'upload_date': '19700101',
+                'upload_date': '20150315',
+                'timestamp': 1426443984,
+                'uploader': 'CBCC-NEW',
             },
         }],
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        },
     }]
 
     @classmethod
@@ -90,24 +92,54 @@ class CBCIE(InfoExtractor):
 
 class CBCPlayerIE(InfoExtractor):
     _VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>\d+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.cbc.ca/player/play/2683190193',
+        'md5': '64d25f841ddf4ddb28a235338af32e2c',
         'info_dict': {
             'id': '2683190193',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Gerry Runs a Sweat Shop',
             'description': 'md5:b457e1c01e8ff408d9d801c1c2cd29b0',
-            'timestamp': 1455067800,
+            'timestamp': 1455071400,
             'upload_date': '20160210',
+            'uploader': 'CBCC-NEW',
         },
-        'params': {
-            # rtmp download
-            'skip_download': True,
+    }, {
+        # Redirected from http://www.cbc.ca/player/AudioMobile/All%20in%20a%20Weekend%20Montreal/ID/2657632011/
+        'url': 'http://www.cbc.ca/player/play/2657631896',
+        'md5': 'e5e708c34ae6fca156aafe17c43e8b75',
+        'info_dict': {
+            'id': '2657631896',
+            'ext': 'mp3',
+            'title': 'CBC Montreal is organizing its first ever community hackathon!',
+            'description': 'The modern technology we tend to depend on so heavily, is never without it\'s share of hiccups and headaches. Next weekend - CBC Montreal will be getting members of the public for its first Hackathon.',
+            'timestamp': 1425704400,
+            'upload_date': '20150307',
+            'uploader': 'CBCC-NEW',
         },
-    }
+    }, {
+        # available only when we add `formats=MPEG4,FLV,MP3` to theplatform url
+        'url': 'http://www.cbc.ca/player/play/2164402062',
+        'md5': '17a61eb813539abea40618d6323a7f82',
+        'info_dict': {
+            'id': '2164402062',
+            'ext': 'flv',
+            'title': 'Cancer survivor four times over',
+            'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
+            'timestamp': 1320410746,
+            'upload_date': '20111104',
+            'uploader': 'CBCC-NEW',
+        },
+    }]
 
     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)
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'ThePlatform',
+            'url': smuggle_url(
+                'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/%s?mbr=true&formats=MPEG4,FLV,MP3' % video_id, {
+                    'force_smil_url': True
+                }),
+            'id': video_id,
+        }

youtube_dl/extractor/cbs.py

@@ -1,24 +1,42 @@
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
+import re
+
+from .theplatform import ThePlatformIE
 from ..utils import (
-    sanitized_Request,
-    smuggle_url,
+    xpath_text,
+    xpath_element,
+    int_or_none,
+    find_xpath_attr,
 )
 
 
-class CBSIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<id>[^/]+)'
+class CBSBaseIE(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 []
+
+
+class CBSIE(CBSBaseIE):
+    _VALID_URL = r'(?:cbs:(?P<content_id>\w+)|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<display_id>[^/]+))'
 
     _TESTS = [{
         'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
         'info_dict': {
-            'id': '4JUVEwq3wUT7',
+            'id': '_u7W953k6la293J7EPTd9oHkSPs6Xn6_',
             'display_id': 'connect-chat-feat-garth-brooks',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Connect Chat feat. Garth Brooks',
             'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
             'duration': 1495,
+            'timestamp': 1385585425,
+            'upload_date': '20131127',
+            'uploader': 'CBSI-NEW',
         },
         'params': {
             # rtmp download
@@ -47,22 +65,47 @@ class CBSIE(InfoExtractor):
         'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
         'only_matching': True,
     }]
+    TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true'
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
-        request = sanitized_Request(url)
-        # Android UA is served with higher quality (720p) streams (see
-        # https://github.com/rg3/youtube-dl/issues/7490)
-        request.add_header('User-Agent', 'Mozilla/5.0 (Linux; Android 4.4; Nexus 5)')
-        webpage = self._download_webpage(request, display_id)
-        real_id = self._search_regex(
-            [r"video\.settings\.pid\s*=\s*'([^']+)';", r"cbsplayer\.pid\s*=\s*'([^']+)';"],
-            webpage, 'real video ID')
-        return {
-            '_type': 'url_transparent',
-            'ie_key': 'ThePlatform',
-            'url': smuggle_url(
-                'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true&manifest=m3u' % real_id,
-                {'force_smil_url': True}),
+        content_id, display_id = re.match(self._VALID_URL, url).groups()
+        if not content_id:
+            webpage = self._download_webpage(url, display_id)
+            content_id = self._search_regex(
+                [r"video\.settings\.content_id\s*=\s*'([^']+)';", r"cbsplayer\.contentId\s*=\s*'([^']+)';"],
+                webpage, 'content id')
+        items_data = self._download_xml(
+            'http://can.cbs.com/thunder/player/videoPlayerService.php',
+            content_id, query={'partner': 'cbs', 'contentId': content_id})
+        video_data = xpath_element(items_data, './/item')
+        title = xpath_text(video_data, 'videoTitle', 'title', True)
+
+        subtitles = {}
+        formats = []
+        for item in items_data.findall('.//item'):
+            pid = xpath_text(item, 'pid')
+            if not pid:
+                continue
+            tp_release_url = self.TP_RELEASE_URL_TEMPLATE % pid
+            if '.m3u8' in xpath_text(item, 'contentUrl', default=''):
+                tp_release_url += '&manifest=m3u'
+            tp_formats, tp_subtitles = self._extract_theplatform_smil(
+                tp_release_url, content_id, 'Downloading %s SMIL data' % pid)
+            formats.extend(tp_formats)
+            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
+        self._sort_formats(formats)
+
+        info = self.get_metadata('dJ5BDC/media/guid/2198311517/%s' % content_id, content_id)
+        info.update({
+            'id': content_id,
             'display_id': display_id,
-        }
+            'title': title,
+            'series': xpath_text(video_data, 'seriesTitle'),
+            'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
+            'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
+            'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
+            'thumbnail': xpath_text(video_data, 'previewImageURL'),
+            'formats': formats,
+            'subtitles': subtitles,
+        })
+        return info

youtube_dl/extractor/cbsinteractive.py

@@ -1,12 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .theplatform import ThePlatformIE
 from ..utils import int_or_none
 
 
-class CNETIE(ThePlatformIE):
-    _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
+class CBSInteractiveIE(ThePlatformIE):
+    _VALID_URL = r'https?://(?:www\.)?(?P<site>cnet|zdnet)\.com/(?:videos|video/share)/(?P<id>[^/?]+)'
     _TESTS = [{
         'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
         'info_dict': {
@@ -17,6 +19,8 @@ class CNETIE(ThePlatformIE):
             'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
             'uploader': 'Sarah Mitroff',
             'duration': 70,
+            'timestamp': 1396479627,
+            'upload_date': '20140402',
         },
     }, {
         'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
@@ -28,15 +32,38 @@ class CNETIE(ThePlatformIE):
             'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
             'uploader': 'Ashley Esqueda',
             'duration': 1482,
+            'timestamp': 1433289889,
+            'upload_date': '20150603',
         },
+    }, {
+        'url': 'http://www.zdnet.com/video/share/video-keeping-android-smartphones-and-tablets-secure/',
+        'info_dict': {
+            'id': 'bc1af9f0-a2b5-4e54-880d-0d95525781c0',
+            'ext': 'mp4',
+            'title': 'Video: Keeping Android smartphones and tablets secure',
+            'description': 'Here\'s the best way to keep Android devices secure, and what you do when they\'ve come to the end of their lives.',
+            'uploader_id': 'f2d97ea2-8175-11e2-9d12-0018fe8a00b0',
+            'uploader': 'Adrian Kingsley-Hughes',
+            'timestamp': 1448961720,
+            'upload_date': '20151201',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
     }]
+    TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/kYEXFC/%s?mbr=true'
+    MPX_ACCOUNTS = {
+        'cnet': 2288573011,
+        'zdnet': 2387448114,
+    }
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        site, display_id = re.match(self._VALID_URL, url).groups()
         webpage = self._download_webpage(url, display_id)
 
         data_json = self._html_search_regex(
-            r"data-cnet-video(?:-uvp)?-options='([^']+)'",
+            r"data-(?:cnet|zdnet)-video(?:-uvp)?-options='([^']+)'",
             webpage, 'data json')
         data = self._parse_json(data_json, display_id)
         vdata = data.get('video') or data['videos'][0]
@@ -51,18 +78,15 @@ class CNETIE(ThePlatformIE):
             uploader = None
             uploader_id = None
 
-        mpx_account = data['config']['uvpConfig']['default']['mpx_account']
-
-        metadata = self.get_metadata('%s/%s' % (mpx_account, list(vdata['files'].values())[0]), video_id)
-        description = vdata.get('description') or metadata.get('description')
-        duration = int_or_none(vdata.get('duration')) or metadata.get('duration')
-
-        formats = []
-        subtitles = {}
+        media_guid_path = 'media/guid/%d/%s' % (self.MPX_ACCOUNTS[site], vdata['mpxRefId'])
+        formats, subtitles = [], {}
+        if site == 'cnet':
+            formats, subtitles = self._extract_theplatform_smil(
+                self.TP_RELEASE_URL_TEMPLATE % media_guid_path, video_id)
         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 = self.TP_RELEASE_URL_TEMPLATE % 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)
@@ -70,15 +94,15 @@ class CNETIE(ThePlatformIE):
             subtitles = self._merge_subtitles(subtitles, tp_subtitles)
         self._sort_formats(formats)
 
-        return {
+        info = self.get_metadata('kYEXFC/%s' % media_guid_path, video_id)
+        info.update({
             'id': video_id,
             'display_id': display_id,
             'title': title,
-            'description': description,
-            'thumbnail': metadata.get('thumbnail'),
-            'duration': duration,
+            'duration': int_or_none(vdata.get('duration')),
             'uploader': uploader,
             'uploader_id': uploader_id,
             'subtitles': subtitles,
             'formats': formats,
-        }
+        })
+        return info

youtube_dl/extractor/cbslocal.py

@@ -0,0 +1,84 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import calendar
+import datetime
+
+from .anvato import AnvatoIE
+from .sendtonews import SendtoNewsIE
+from ..compat import compat_urlparse
+
+
+class CBSLocalIE(AnvatoIE):
+    _VALID_URL = r'https?://[a-z]+\.cbslocal\.com/\d+/\d+/\d+/(?P<id>[0-9a-z-]+)'
+
+    _TESTS = [{
+        # Anvato backend
+        'url': 'http://losangeles.cbslocal.com/2016/05/16/safety-advocates-say-fatal-car-seat-failures-are-public-health-crisis',
+        'md5': 'f0ee3081e3843f575fccef901199b212',
+        'info_dict': {
+            'id': '3401037',
+            'ext': 'mp4',
+            'title': 'Safety Advocates Say Fatal Car Seat Failures Are \'Public Health Crisis\'',
+            'description': 'Collapsing seats have been the focus of scrutiny for decades, though experts say remarkably little has been done to address the issue. Randy Paige reports.',
+            'thumbnail': 're:^https?://.*',
+            'timestamp': 1463440500,
+            'upload_date': '20160516',
+            'subtitles': {
+                'en': 'mincount:5',
+            },
+            'categories': [
+                'Stations\\Spoken Word\\KCBSTV',
+                'Syndication\\MSN',
+                'Syndication\\NDN',
+                'Syndication\\AOL',
+                'Syndication\\Yahoo',
+                'Syndication\\Tribune',
+                'Syndication\\Curb.tv',
+                'Content\\News'
+            ],
+        },
+    }, {
+        # SendtoNews embed
+        'url': 'http://cleveland.cbslocal.com/2016/05/16/indians-score-season-high-15-runs-in-blowout-win-over-reds-rapid-reaction/',
+        'info_dict': {
+            'id': 'GxfCe0Zo7D-175909-5588',
+            'ext': 'mp4',
+            'title': 'Recap: CLE 15, CIN 6',
+            'description': '5/16/16: Indians\' bats explode for 15 runs in a win',
+            'upload_date': '20160516',
+            'timestamp': 1463433840,
+            'duration': 49,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        sendtonews_url = SendtoNewsIE._extract_url(webpage)
+        if sendtonews_url:
+            info_dict = {
+                '_type': 'url_transparent',
+                'url': compat_urlparse.urljoin(url, sendtonews_url),
+            }
+        else:
+            info_dict = self._extract_anvato_videos(webpage, display_id)
+
+        time_str = self._html_search_regex(
+            r'class="entry-date">([^<]+)<', webpage, 'released date', fatal=False)
+        timestamp = None
+        if time_str:
+            timestamp = calendar.timegm(datetime.datetime.strptime(
+                time_str, '%b %d, %Y %I:%M %p').timetuple())
+
+        info_dict.update({
+            'display_id': display_id,
+            'timestamp': timestamp,
+        })
+
+        return info_dict

youtube_dl/extractor/cbsnews.py

@@ -2,16 +2,15 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from .theplatform import ThePlatformIE
+from .cbs import CBSBaseIE
 from ..utils import (
     parse_duration,
-    find_xpath_attr,
 )
 
 
-class CBSNewsIE(ThePlatformIE):
+class CBSNewsIE(CBSBaseIE):
     IE_DESC = 'CBS News'
-    _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
+    _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
 
     _TESTS = [
         {
@@ -49,15 +48,6 @@ 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)
 
@@ -78,7 +68,7 @@ class CBSNewsIE(ThePlatformIE):
             pid = item.get('media' + format_id)
             if not pid:
                 continue
-            release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?format=SMIL&mbr=true' % pid
+            release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true' % pid
             tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % pid)
             formats.extend(tp_formats)
             subtitles = self._merge_subtitles(subtitles, tp_subtitles)
@@ -96,7 +86,7 @@ class CBSNewsIE(ThePlatformIE):
 
 class CBSNewsLiveVideoIE(InfoExtractor):
     IE_DESC = 'CBS News Live Videos'
-    _VALID_URL = r'http://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
+    _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
 
     _TEST = {
         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
@@ -122,6 +112,7 @@ class CBSNewsLiveVideoIE(InfoExtractor):
             for entry in f4m_formats:
                 # URLs without the extra param induce an 404 error
                 entry.update({'extra_param_to_segment_url': hdcore_sign})
+        self._sort_formats(f4m_formats)
 
         return {
             'id': video_id,

youtube_dl/extractor/cbssports.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 
 
 class CBSSportsIE(InfoExtractor):
-    _VALID_URL = r'http://www\.cbssports\.com/video/player/(?P<section>[^/]+)/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://www\.cbssports\.com/video/player/(?P<section>[^/]+)/(?P<id>[^/]+)'
 
     _TEST = {
         'url': 'http://www.cbssports.com/video/player/tennis/318462531970/0/us-open-flashbacks-1990s',

youtube_dl/extractor/ccc.py

@@ -1,13 +1,9 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
-    parse_duration,
-    qualities,
-    unified_strdate,
+    parse_iso8601,
 )
 
 
@@ -19,14 +15,14 @@ class CCCIE(InfoExtractor):
         'url': 'https://media.ccc.de/v/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor#video',
         'md5': '3a1eda8f3a29515d27f5adb967d7e740',
         'info_dict': {
-            'id': '30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor',
+            'id': '1839',
             'ext': 'mp4',
             'title': 'Introduction to Processor Design',
-            'description': 'md5:80be298773966f66d56cb11260b879af',
+            'description': 'md5:df55f6d073d4ceae55aae6f2fd98a0ac',
             'thumbnail': 're:^https?://.*\.jpg$',
-            'view_count': int,
             'upload_date': '20131228',
-            'duration': 3660,
+            'timestamp': 1388188800,
+            'duration': 3710,
         }
     }, {
         'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
@@ -34,79 +30,48 @@ class CCCIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        event_id = self._search_regex("data-id='(\d+)'", webpage, 'event id')
+        event_data = self._download_json('https://media.ccc.de/public/events/%s' % event_id, event_id)
 
-        if self._downloader.params.get('prefer_free_formats'):
-            preference = qualities(['mp3', 'opus', 'mp4-lq', 'webm-lq', 'h264-sd', 'mp4-sd', 'webm-sd', 'mp4', 'webm', 'mp4-hd', 'h264-hd', 'webm-hd'])
-        else:
-            preference = qualities(['opus', 'mp3', 'webm-lq', 'mp4-lq', 'webm-sd', 'h264-sd', 'mp4-sd', 'webm', 'mp4', 'webm-hd', 'mp4-hd', 'h264-hd'])
-
-        title = self._html_search_regex(
-            r'(?s)<h1>(.*?)</h1>', webpage, 'title')
-        description = self._html_search_regex(
-            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>",
-            webpage, 'upload date', fatal=False))
-        view_count = int_or_none(self._html_search_regex(
-            r"(?s)<span class='[^']*fa-eye'></span>(.*?)</li>",
-            webpage, 'view count', fatal=False))
-        duration = parse_duration(self._html_search_regex(
-            r'(?s)<span[^>]+class=(["\']).*?fa-clock-o.*?\1[^>]*></span>(?P<duration>.+?)</li',
-            webpage, 'duration', fatal=False, group='duration'))
-
-        matches = re.finditer(r'''(?xs)
-            <(?:span|div)\s+class='label\s+filetype'>(?P<format>[^<]*)</(?:span|div)>\s*
-            <(?:span|div)\s+class='label\s+filetype'>(?P<lang>[^<]*)</(?:span|div)>\s*
-            <a\s+download\s+href='(?P<http_url>[^']+)'>\s*
-            (?:
-                .*?
-                <a\s+(?:download\s+)?href='(?P<torrent_url>[^']+\.torrent)'
-            )?''', webpage)
         formats = []
-        for m in matches:
-            format = m.group('format')
-            format_id = self._search_regex(
-                r'.*/([a-z0-9_-]+)/[^/]*$',
-                m.group('http_url'), 'format id', default=None)
-            if format_id:
-                format_id = m.group('lang') + '-' + format_id
-            vcodec = 'h264' if 'h264' in format_id else (
-                'none' if format_id in ('mp3', 'opus') else None
+        for recording in event_data.get('recordings', []):
+            recording_url = recording.get('recording_url')
+            if not recording_url:
+                continue
+            language = recording.get('language')
+            folder = recording.get('folder')
+            format_id = None
+            if language:
+                format_id = language
+            if folder:
+                if language:
+                    format_id += '-' + folder
+                else:
+                    format_id = folder
+            vcodec = 'h264' if 'h264' in folder else (
+                'none' if folder in ('mp3', 'opus') else None
             )
             formats.append({
                 'format_id': format_id,
-                'format': format,
-                'language': m.group('lang'),
-                'url': m.group('http_url'),
+                'url': recording_url,
+                'width': int_or_none(recording.get('width')),
+                'height': int_or_none(recording.get('height')),
+                'filesize': int_or_none(recording.get('size'), invscale=1024 * 1024),
+                'language': language,
                 'vcodec': vcodec,
-                'preference': preference(format_id),
             })
-
-            if m.group('torrent_url'):
-                formats.append({
-                    'format_id': 'torrent-%s' % (format if format_id is None else format_id),
-                    'format': '%s (torrent)' % format,
-                    'proto': 'torrent',
-                    'format_note': '(unsupported; will just download the .torrent file)',
-                    'vcodec': vcodec,
-                    'preference': -100 + preference(format_id),
-                    'url': m.group('torrent_url'),
-                })
         self._sort_formats(formats)
 
-        thumbnail = self._html_search_regex(
-            r"<video.*?poster='([^']+)'", webpage, 'thumbnail', fatal=False)
-
         return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'view_count': view_count,
-            'upload_date': upload_date,
-            'duration': duration,
+            'id': event_id,
+            'display_id': display_id,
+            'title': event_data['title'],
+            'description': event_data.get('description'),
+            'thumbnail': event_data.get('thumb_url'),
+            'timestamp': parse_iso8601(event_data.get('date')),
+            'duration': int_or_none(event_data.get('length')),
+            'tags': event_data.get('tags'),
             'formats': formats,
         }

youtube_dl/extractor/cda.py

@@ -0,0 +1,96 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    decode_packed_codes,
+    ExtractorError,
+    parse_duration
+)
+
+
+class CDAIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
+    _TESTS = [{
+        'url': 'http://www.cda.pl/video/5749950c',
+        'md5': '6f844bf51b15f31fae165365707ae970',
+        'info_dict': {
+            'id': '5749950c',
+            'ext': 'mp4',
+            'height': 720,
+            'title': 'Oto dlaczego przed zakrętem należy zwolnić.',
+            'duration': 39
+        }
+    }, {
+        'url': 'http://www.cda.pl/video/57413289',
+        'md5': 'a88828770a8310fc00be6c95faf7f4d5',
+        'info_dict': {
+            'id': '57413289',
+            'ext': 'mp4',
+            'title': 'Lądowanie na lotnisku na Maderze',
+            'duration': 137
+        }
+    }, {
+        'url': 'http://ebd.cda.pl/0x0/5749950c',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage('http://ebd.cda.pl/0x0/' + video_id, video_id)
+
+        if 'Ten film jest dostępny dla użytkowników premium' in webpage:
+            raise ExtractorError('This video is only available for premium users.', expected=True)
+
+        title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
+
+        formats = []
+
+        info_dict = {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'duration': None,
+        }
+
+        def extract_format(page, version):
+            unpacked = decode_packed_codes(page)
+            format_url = self._search_regex(
+                r"url:\\'(.+?)\\'", unpacked, '%s url' % version, fatal=False)
+            if not format_url:
+                return
+            f = {
+                'url': format_url,
+            }
+            m = re.search(
+                r'<a[^>]+data-quality="(?P<format_id>[^"]+)"[^>]+href="[^"]+"[^>]+class="[^"]*quality-btn-active[^"]*">(?P<height>[0-9]+)p',
+                page)
+            if m:
+                f.update({
+                    'format_id': m.group('format_id'),
+                    'height': int(m.group('height')),
+                })
+            info_dict['formats'].append(f)
+            if not info_dict['duration']:
+                info_dict['duration'] = parse_duration(self._search_regex(
+                    r"duration:\\'(.+?)\\'", unpacked, 'duration', fatal=False))
+
+        extract_format(webpage, 'default')
+
+        for href, resolution in re.findall(
+                r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
+                webpage):
+            webpage = self._download_webpage(
+                href, video_id, 'Downloading %s version information' % resolution, fatal=False)
+            if not webpage:
+                # Manually report warning because empty page is returned when
+                # invalid version is requested.
+                self.report_warning('Unable to download %s version information' % resolution)
+                continue
+            extract_format(webpage, resolution)
+
+        self._sort_formats(formats)
+
+        return info_dict

youtube_dl/extractor/ceskatelevize.py

@@ -5,7 +5,6 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
     compat_urllib_parse_unquote,
     compat_urllib_parse_urlparse,
 )
@@ -13,6 +12,7 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     sanitized_Request,
+    urlencode_postdata,
 )
 
 
@@ -33,19 +33,33 @@ class CeskaTelevizeIE(InfoExtractor):
             'skip_download': True,
         },
     }, {
-        'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
+        'url': 'http://www.ceskatelevize.cz/ivysilani/10441294653-hyde-park-civilizace/215411058090502/bonus/20641-bonus-01-en',
         'info_dict': {
-            'id': '61924494876844374',
+            'id': '61924494877028507',
             'ext': 'mp4',
-            'title': 'První republika: Zpěvačka z Dupárny Bobina',
-            'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
+            'title': 'Hyde Park Civilizace: Bonus 01 - En',
+            'description': 'English Subtittles',
             'thumbnail': 're:^https?://.*\.jpg',
-            'duration': 88.4,
+            'duration': 81.3,
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
+    }, {
+        # live stream
+        'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
+        'info_dict': {
+            'id': 402,
+            'ext': 'mp4',
+            'title': 're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'is_live': True,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'skip': 'Georestricted to Czech Republic',
     }, {
         # video with 18+ caution trailer
         'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
@@ -102,7 +116,7 @@ class CeskaTelevizeIE(InfoExtractor):
 
         req = sanitized_Request(
             'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
-            data=compat_urllib_parse.urlencode(data))
+            data=urlencode_postdata(data))
 
         req.add_header('Content-type', 'application/x-www-form-urlencoded')
         req.add_header('x-addr', '127.0.0.1')
@@ -118,18 +132,21 @@ class CeskaTelevizeIE(InfoExtractor):
         req = sanitized_Request(compat_urllib_parse_unquote(playlist_url))
         req.add_header('Referer', url)
 
-        playlist_title = self._og_search_title(webpage)
-        playlist_description = self._og_search_description(webpage)
+        playlist_title = self._og_search_title(webpage, default=None)
+        playlist_description = self._og_search_description(webpage, default=None)
 
         playlist = self._download_json(req, playlist_id)['playlist']
         playlist_len = len(playlist)
 
         entries = []
         for item in playlist:
+            is_live = item.get('type') == 'LIVE'
             formats = []
             for format_id, stream_url in item['streamUrls'].items():
                 formats.extend(self._extract_m3u8_formats(
-                    stream_url, playlist_id, 'mp4', entry_protocol='m3u8_native'))
+                    stream_url, playlist_id, 'mp4',
+                    entry_protocol='m3u8' if is_live else 'm3u8_native',
+                    fatal=False))
             self._sort_formats(formats)
 
             item_id = item.get('id') or item['assetId']
@@ -144,14 +161,22 @@ class CeskaTelevizeIE(InfoExtractor):
                 if subs:
                     subtitles = self.extract_subtitles(episode_id, subs)
 
+            if playlist_len == 1:
+                final_title = playlist_title or title
+                if is_live:
+                    final_title = self._live_title(final_title)
+            else:
+                final_title = '%s (%s)' % (playlist_title, title)
+
             entries.append({
                 'id': item_id,
-                'title': playlist_title if playlist_len == 1 else '%s (%s)' % (playlist_title, title),
+                'title': final_title,
                 'description': playlist_description if playlist_len == 1 else None,
                 'thumbnail': thumbnail,
                 'duration': duration,
                 'formats': formats,
                 'subtitles': subtitles,
+                'is_live': is_live,
             })
 
         return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)

youtube_dl/extractor/chaturbate.py

@@ -48,6 +48,7 @@ class ChaturbateIE(InfoExtractor):
             raise ExtractorError('Unable to find stream URL')
 
         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
+        self._sort_formats(formats)
 
         return {
             'id': video_id,

youtube_dl/extractor/cinemassacre.py

@@ -1,107 +0,0 @@
-# encoding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import ExtractorError
-from .screenwavemedia import ScreenwaveMediaIE
-
-
-class CinemassacreIE(InfoExtractor):
-    _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
-    _TESTS = [
-        {
-            'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
-            'md5': 'fde81fbafaee331785f58cd6c0d46190',
-            'info_dict': {
-                'id': 'Cinemassacre-19911',
-                'ext': 'mp4',
-                'upload_date': '20121110',
-                'title': '“Angry Video Game Nerd: The Movie” – Trailer',
-                'description': 'md5:fb87405fcb42a331742a0dce2708560b',
-            },
-        },
-        {
-            'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
-            'md5': 'd72f10cd39eac4215048f62ab477a511',
-            'info_dict': {
-                'id': 'Cinemassacre-521be8ef82b16',
-                'ext': 'mp4',
-                'upload_date': '20131002',
-                'title': 'The Mummy’s Hand (1940)',
-            },
-        },
-        {
-            # Youtube embedded video
-            'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/',
-            'md5': 'df4cf8a1dcedaec79a73d96d83b99023',
-            'info_dict': {
-                'id': 'OEVzPCY2T-g',
-                'ext': 'mp4',
-                'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles',
-                'upload_date': '20061207',
-                'uploader': 'Cinemassacre',
-                'uploader_id': 'JamesNintendoNerd',
-                'description': 'md5:784734696c2b8b7f4b8625cc799e07f6',
-            }
-        },
-        {
-            # Youtube embedded video
-            'url': 'http://cinemassacre.com/2006/09/01/mckids/',
-            'md5': '6eb30961fa795fedc750eac4881ad2e1',
-            'info_dict': {
-                'id': 'FnxsNhuikpo',
-                'ext': 'mp4',
-                'upload_date': '20060901',
-                'uploader': 'Cinemassacre Extras',
-                'description': 'md5:de9b751efa9e45fbaafd9c8a1123ed53',
-                'uploader_id': 'Cinemassacre',
-                'title': 'AVGN: McKids',
-            }
-        },
-        {
-            'url': 'http://cinemassacre.com/2015/05/25/mario-kart-64-nintendo-64-james-mike-mondays/',
-            'md5': '1376908e49572389e7b06251a53cdd08',
-            'info_dict': {
-                'id': 'Cinemassacre-555779690c440',
-                'ext': 'mp4',
-                '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',
-            }
-        }
-    ]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('display_id')
-        video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d')
-
-        webpage = self._download_webpage(url, display_id)
-
-        playerdata_url = self._search_regex(
-            [
-                ScreenwaveMediaIE.EMBED_PATTERN,
-                r'<iframe[^>]+src="(?P<url>(?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
-            ],
-            webpage, 'player data URL', default=None, group='url')
-        if not playerdata_url:
-            raise ExtractorError('Unable to find player data')
-
-        video_title = self._html_search_regex(
-            r'<title>(?P<title>.+?)\|', webpage, 'title')
-        video_description = self._html_search_regex(
-            r'<div class="entry-content">(?P<description>.+?)</div>',
-            webpage, 'description', flags=re.DOTALL, fatal=False)
-        video_thumbnail = self._og_search_thumbnail(webpage)
-
-        return {
-            '_type': 'url_transparent',
-            'display_id': display_id,
-            'title': video_title,
-            'description': video_description,
-            'upload_date': video_date,
-            'thumbnail': video_thumbnail,
-            'url': playerdata_url,
-        }

youtube_dl/extractor/cliphunter.py

@@ -19,7 +19,7 @@ def _decode(s):
 class CliphunterIE(InfoExtractor):
     IE_NAME = 'cliphunter'
 
-    _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/
+    _VALID_URL = r'''(?x)https?://(?:www\.)?cliphunter\.com/w/
         (?P<id>[0-9]+)/
         (?P<seo>.+?)(?:$|[#\?])
     '''

youtube_dl/extractor/cliprs.py

@@ -0,0 +1,90 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class ClipRsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?clip\.rs/(?P<id>[^/]+)/\d+'
+    _TEST = {
+        'url': 'http://www.clip.rs/premijera-frajle-predstavljaju-novi-spot-za-pesmu-moli-me-moli/3732',
+        'md5': 'c412d57815ba07b56f9edc7b5d6a14e5',
+        'info_dict': {
+            'id': '1488842.1399140381',
+            'ext': 'mp4',
+            'title': 'PREMIJERA Frajle predstavljaju novi spot za pesmu Moli me, moli',
+            'description': 'md5:56ce2c3b4ab31c5a2e0b17cb9a453026',
+            'duration': 229,
+            'timestamp': 1459850243,
+            'upload_date': '20160405',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_id = self._search_regex(
+            r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id')
+
+        response = self._download_json(
+            'http://qi.ckm.onetapi.pl/', video_id,
+            query={
+                'body[id]': video_id,
+                'body[jsonrpc]': '2.0',
+                'body[method]': 'get_asset_detail',
+                'body[params][ID_Publikacji]': video_id,
+                'body[params][Service]': 'www.onet.pl',
+                'content-type': 'application/jsonp',
+                'x-onet-app': 'player.front.onetapi.pl',
+            })
+
+        error = response.get('error')
+        if error:
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, error['message']), expected=True)
+
+        video = response['result'].get('0')
+
+        formats = []
+        for _, formats_dict in video['formats'].items():
+            if not isinstance(formats_dict, dict):
+                continue
+            for format_id, format_list in formats_dict.items():
+                if not isinstance(format_list, list):
+                    continue
+                for f in format_list:
+                    if not f.get('url'):
+                        continue
+                    formats.append({
+                        'url': f['url'],
+                        'format_id': format_id,
+                        'height': int_or_none(f.get('vertical_resolution')),
+                        'width': int_or_none(f.get('horizontal_resolution')),
+                        'abr': float_or_none(f.get('audio_bitrate')),
+                        'vbr': float_or_none(f.get('video_bitrate')),
+                    })
+        self._sort_formats(formats)
+
+        meta = video.get('meta', {})
+
+        title = self._og_search_title(webpage, default=None) or meta['title']
+        description = self._og_search_description(webpage, default=None) or meta.get('description')
+        duration = meta.get('length') or meta.get('lenght')
+        timestamp = parse_iso8601(meta.get('addDate'), ' ')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+        }

youtube_dl/extractor/clipsyndicate.py

@@ -8,7 +8,7 @@ from ..utils import (
 
 
 class ClipsyndicateIE(InfoExtractor):
-    _VALID_URL = r'http://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',

youtube_dl/extractor/cloudy.py

@@ -6,7 +6,7 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
     compat_HTTPError,
 )
 from ..utils import (
@@ -19,7 +19,7 @@ from ..utils import (
 class CloudyIE(InfoExtractor):
     _IE_DESC = 'cloudy.ec and videoraj.ch'
     _VALID_URL = r'''(?x)
-        https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.ch)/
+        https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.(?:ch|to))/
         (?:v/|embed\.php\?id=)
         (?P<id>[A-Za-z0-9]+)
         '''
@@ -37,7 +37,7 @@ class CloudyIE(InfoExtractor):
             }
         },
         {
-            'url': 'http://www.videoraj.ch/v/47f399fd8bb60',
+            'url': 'http://www.videoraj.to/v/47f399fd8bb60',
             'md5': '7d0f8799d91efd4eda26587421c3c3b0',
             'info_dict': {
                 'id': '47f399fd8bb60',
@@ -64,7 +64,7 @@ class CloudyIE(InfoExtractor):
                 'errorUrl': error_url,
             })
 
-        data_url = self._API_URL % (video_host, compat_urllib_parse.urlencode(form))
+        data_url = self._API_URL % (video_host, compat_urllib_parse_urlencode(form))
         player_data = self._download_webpage(
             data_url, video_id, 'Downloading player data')
         data = compat_parse_qs(player_data)

youtube_dl/extractor/clubic.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class ClubicIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?clubic\.com/video/(?:[^/]+/)*video.*-(?P<id>[0-9]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?clubic\.com/video/(?:[^/]+/)*video.*-(?P<id>[0-9]+)\.html'
 
     _TESTS = [{
         'url': 'http://www.clubic.com/video/clubic-week/video-clubic-week-2-0-le-fbi-se-lance-dans-la-photo-d-identite-448474.html',

youtube_dl/extractor/cnbc.py

@@ -0,0 +1,36 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import smuggle_url
+
+
+class CNBCIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.cnbc\.com/gallery/\?video=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://video.cnbc.com/gallery/?video=3000503714',
+        'info_dict': {
+            'id': '3000503714',
+            'ext': 'mp4',
+            'title': 'Fighting zombies is big business',
+            'description': 'md5:0c100d8e1a7947bd2feec9a5550e519e',
+            'timestamp': 1459332000,
+            'upload_date': '20160330',
+            'uploader': 'NBCU-CNBC',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'ThePlatform',
+            'url': smuggle_url(
+                'http://link.theplatform.com/s/gZWlPC/media/guid/2408950221/%s?mbr=true&manifest=m3u' % video_id,
+                {'force_smil_url': True}),
+            'id': video_id,
+        }

youtube_dl/extractor/collegehumor.py

@@ -1,101 +0,0 @@
-from __future__ import unicode_literals
-
-import json
-import re
-
-from .common import InfoExtractor
-from ..utils import int_or_none
-
-
-class CollegeHumorIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
-
-    _TESTS = [
-        {
-            'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
-            'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
-            'info_dict': {
-                'id': '6902724',
-                'ext': 'mp4',
-                'title': 'Comic-Con Cosplay Catastrophe',
-                'description': "Fans get creative this year at San Diego.  Too creative.  And yes, that's really Joss Whedon.",
-                'age_limit': 13,
-                'duration': 187,
-            },
-        }, {
-            'url': 'http://www.collegehumor.com/video/3505939/font-conference',
-            'md5': '72fa701d8ef38664a4dbb9e2ab721816',
-            'info_dict': {
-                'id': '3505939',
-                'ext': 'mp4',
-                'title': 'Font Conference',
-                'description': "This video wasn't long enough, so we made it double-spaced.",
-                'age_limit': 10,
-                'duration': 179,
-            },
-        }, {
-            # embedded youtube video
-            'url': 'http://www.collegehumor.com/embed/6950306',
-            'info_dict': {
-                'id': 'Z-bao9fg6Yc',
-                'ext': 'mp4',
-                'title': 'Young Americans Think President John F. Kennedy Died THIS MORNING IN A CAR ACCIDENT!!!',
-                'uploader': 'Mark Dice',
-                'uploader_id': 'MarkDice',
-                'description': 'md5:62c3dab9351fac7bb44b53b69511d87f',
-                'upload_date': '20140127',
-            },
-            'params': {
-                'skip_download': True,
-            },
-            'add_ie': ['Youtube'],
-        },
-    ]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
-
-        jsonUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id + '.json'
-        data = json.loads(self._download_webpage(
-            jsonUrl, video_id, 'Downloading info JSON'))
-        vdata = data['video']
-        if vdata.get('youtubeId') is not None:
-            return {
-                '_type': 'url',
-                'url': vdata['youtubeId'],
-                'ie_key': 'Youtube',
-            }
-
-        AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0}
-        rating = vdata.get('rating')
-        if rating:
-            age_limit = AGE_LIMITS.get(rating.lower())
-        else:
-            age_limit = None  # None = No idea
-
-        PREFS = {'high_quality': 2, 'low_quality': 0}
-        formats = []
-        for format_key in ('mp4', 'webm'):
-            for qname, qurl in vdata.get(format_key, {}).items():
-                formats.append({
-                    'format_id': format_key + '_' + qname,
-                    'url': qurl,
-                    'format': format_key,
-                    'preference': PREFS.get(qname),
-                })
-        self._sort_formats(formats)
-
-        duration = int_or_none(vdata.get('duration'), 1000)
-        like_count = int_or_none(vdata.get('likes'))
-
-        return {
-            'id': video_id,
-            'title': vdata['title'],
-            'description': vdata.get('description'),
-            'thumbnail': vdata.get('thumbnail'),
-            'formats': formats,
-            'age_limit': age_limit,
-            'duration': duration,
-            'like_count': like_count,
-        }

youtube_dl/extractor/comcarcoff.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class ComCarCoffIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)'
+    _VALID_URL = r'https?://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)'
     _TESTS = [{
         'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/',
         'info_dict': {
@@ -41,7 +41,13 @@ class ComCarCoffIE(InfoExtractor):
 
         display_id = full_data['activeVideo']['video']
         video_data = full_data.get('videos', {}).get(display_id) or full_data['singleshots'][display_id]
+
         video_id = compat_str(video_data['mediaId'])
+        title = video_data['title']
+        formats = self._extract_m3u8_formats(
+            video_data['mediaUrl'], video_id, 'mp4')
+        self._sort_formats(formats)
+
         thumbnails = [{
             'url': video_data['images']['thumb'],
         }, {
@@ -54,15 +60,14 @@ 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'],
+            'title': title,
             'description': video_data.get('description'),
             '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

@@ -5,7 +5,7 @@ import re
 from .mtv import MTVServicesInfoExtractor
 from ..compat import (
     compat_str,
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
 )
 from ..utils import (
     ExtractorError,
@@ -44,10 +44,10 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
     #                     or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
     _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow)
                       |https?://(:www\.)?
-                          (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
+                          (?P<showname>thedailyshow|thecolbertreport|tosh)\.(?:cc\.)?com/
                          ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
                           (?P<clip>
-                              (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+))
+                              (?:(?:guests/[^/]+|videos|video-(?:clips|playlists)|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+))
                               |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
                               |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
                           )|
@@ -129,6 +129,9 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
     }, {
         'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel',
         'only_matching': True,
+    }, {
+        'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
+        'only_matching': True,
     }]
 
     _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
@@ -201,7 +204,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
         # Correct cc.com in uri
         uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.com', uri)
 
-        index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
+        index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse_urlencode({'uri': uri}))
         idoc = self._download_xml(
             index_url, epTitle,
             'Downloading show index', 'Unable to download episode index')

youtube_dl/extractor/common.py

@@ -15,14 +15,17 @@ import math
 from ..compat import (
     compat_cookiejar,
     compat_cookies,
+    compat_etree_fromstring,
     compat_getpass,
     compat_http_client,
-    compat_urllib_error,
-    compat_urllib_parse,
-    compat_urlparse,
+    compat_os_name,
     compat_str,
-    compat_etree_fromstring,
+    compat_urllib_error,
+    compat_urllib_parse_urlencode,
+    compat_urllib_request,
+    compat_urlparse,
 )
+from ..downloader.f4m import remove_encrypted_media
 from ..utils import (
     NO_DEFAULT,
     age_restricted,
@@ -47,6 +50,8 @@ from ..utils import (
     determine_protocol,
     parse_duration,
     mimetype2ext,
+    update_Request,
+    update_url_query,
 )
 
 
@@ -104,7 +109,7 @@ 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.
@@ -157,12 +162,14 @@ class InfoExtractor(object):
     thumbnail:      Full URL to a video thumbnail image.
     description:    Full video description.
     uploader:       Full name of the video uploader.
-    creator:        The main artist who created the video.
+    license:        License name the video is licensed under.
+    creator:        The creator of 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
@@ -225,6 +232,24 @@ class InfoExtractor(object):
     episode_number: Number of the video episode within a season, as an integer.
     episode_id:     Id of the video episode, as a unicode string.
 
+    The following fields should only be used when the media is a track or a part of
+    a music album:
+
+    track:          Title of the track.
+    track_number:   Number of the track within an album or a disc, as an integer.
+    track_id:       Id of the track (useful in case of custom indexing, e.g. 6.iii),
+                    as a unicode string.
+    artist:         Artist(s) of the track.
+    genre:          Genre(s) of the track.
+    album:          Title of the album the track belongs to.
+    album_type:     Type of the album (e.g. "Demo", "Full-length", "Split", "Compilation", etc).
+    album_artist:   List of all artists appeared on the album (e.g.
+                    "Ash Borer / Fell Voices" or "Various Artists", useful for splits
+                    and compilations).
+    disc_number:    Number of the disc or other physical medium the track belongs to,
+                    as an integer.
+    release_year:   Year (YYYY) when the album was released.
+
     Unless mentioned otherwise, the fields should be Unicode strings.
 
     Unless mentioned otherwise, None is equivalent to absence of information.
@@ -342,7 +367,7 @@ 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={}, query={}):
         """ Returns the response handle """
         if note is None:
             self.report_download_webpage(video_id)
@@ -351,6 +376,14 @@ class InfoExtractor(object):
                 self.to_screen('%s' % (note,))
             else:
                 self.to_screen('%s: %s' % (video_id, note))
+        if isinstance(url_or_request, compat_urllib_request.Request):
+            url_or_request = update_Request(
+                url_or_request, data=data, headers=headers, query=query)
+        else:
+            if query:
+                url_or_request = update_url_query(url_or_request, query)
+            if data is not None or headers:
+                url_or_request = sanitized_Request(url_or_request, data, headers)
         try:
             return self._downloader.urlopen(url_or_request)
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
@@ -366,13 +399,13 @@ 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={}, query={}):
         """ 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
@@ -425,7 +458,7 @@ 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
@@ -459,13 +492,13 @@ 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={}, query={}):
         """ 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
@@ -480,10 +513,10 @@ 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={}, query={}):
         """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:
@@ -494,10 +527,10 @@ 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={}, query={}):
         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(
@@ -594,7 +627,7 @@ 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
@@ -809,7 +842,7 @@ class InfoExtractor(object):
         for input in re.findall(r'(?i)<input([^>]+)>', html):
             if not re.search(r'type=(["\'])(?:hidden|submit)\1', input):
                 continue
-            name = re.search(r'name=(["\'])(?P<value>.+?)\1', input)
+            name = re.search(r'(?:name|id)=(["\'])(?P<value>.+?)\1', input)
             if not name:
                 continue
             value = re.search(r'value=(["\'])(?P<value>.*?)\1', input)
@@ -852,6 +885,7 @@ class InfoExtractor(object):
             proto_preference = 0 if determine_protocol(f) in ['http', 'https'] else -0.1
 
             if f.get('vcodec') == 'none':  # audio only
+                preference -= 50
                 if self._downloader.params.get('prefer_free_formats'):
                     ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus']
                 else:
@@ -862,6 +896,8 @@ class InfoExtractor(object):
                 except ValueError:
                     audio_ext_preference = -1
             else:
+                if f.get('acodec') == 'none':  # video only
+                    preference -= 40
                 if self._downloader.params.get('prefer_free_formats'):
                     ORDER = ['flv', 'mp4', 'webm']
                 else:
@@ -951,7 +987,7 @@ class InfoExtractor(object):
 
     def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None,
                              transform_source=lambda s: fix_xml_ampersands(s).strip(),
-                             fatal=True):
+                             fatal=True, m3u8_id=None):
         manifest = self._download_xml(
             manifest_url, video_id, 'Downloading f4m manifest',
             'Unable to download f4m manifest',
@@ -963,20 +999,56 @@ 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, m3u8_id=m3u8_id)
+
+    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, m3u8_id=None):
+        # currently youtube-dl cannot decode the playerVerificationChallenge as Akamai uses Adobe Alchemy
+        akamai_pv = manifest.find('{http://ns.adobe.com/f4m/1.0}pv-2.0')
+        if akamai_pv is not None and ';' in akamai_pv.text:
+            playerVerificationChallenge = akamai_pv.text.split(';')[0]
+            if playerVerificationChallenge.strip() != '':
+                return []
+
         formats = []
         manifest_version = '1.0'
         media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
         if not media_nodes:
             manifest_version = '2.0'
             media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
+        # Remove unsupported DRM protected media from final formats
+        # rendition (see https://github.com/rg3/youtube-dl/issues/8573).
+        media_nodes = remove_encrypted_media(media_nodes)
+        if not media_nodes:
+            return formats
         base_url = xpath_text(
             manifest, ['{http://ns.adobe.com/f4m/1.0}baseURL', '{http://ns.adobe.com/f4m/2.0}baseURL'],
             'base URL', default=None)
         if base_url:
             base_url = base_url.strip()
+
+        bootstrap_info = xpath_text(
+            manifest, ['{http://ns.adobe.com/f4m/1.0}bootstrapInfo', '{http://ns.adobe.com/f4m/2.0}bootstrapInfo'],
+            'bootstrap info', default=None)
+
         for i, media_el in enumerate(media_nodes):
-            if manifest_version == '2.0':
-                media_url = media_el.attrib.get('href') or media_el.attrib.get('url')
+            tbr = int_or_none(media_el.attrib.get('bitrate'))
+            width = int_or_none(media_el.attrib.get('width'))
+            height = int_or_none(media_el.attrib.get('height'))
+            format_id = '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)]))
+            # If <bootstrapInfo> is present, the specified f4m is a
+            # stream-level manifest, and only set-level manifests may refer to
+            # external resources.  See section 11.4 and section 4 of F4M spec
+            if bootstrap_info is None:
+                media_url = None
+                # @href is introduced in 2.0, see section 11.6 of F4M spec
+                if manifest_version == '2.0':
+                    media_url = media_el.attrib.get('href')
+                if media_url is None:
+                    media_url = media_el.attrib.get('url')
                 if not media_url:
                     continue
                 manifest_url = (
@@ -986,30 +1058,43 @@ class InfoExtractor(object):
                 # since bitrates in parent manifest (this one) and media_url manifest
                 # may differ leading to inability to resolve the format by requested
                 # bitrate in f4m downloader
-                if determine_ext(manifest_url) == 'f4m':
-                    formats.extend(self._extract_f4m_formats(
-                        manifest_url, video_id, preference, f4m_id, fatal=fatal))
+                ext = determine_ext(manifest_url)
+                if ext == 'f4m':
+                    f4m_formats = self._extract_f4m_formats(
+                        manifest_url, video_id, preference=preference, f4m_id=f4m_id,
+                        transform_source=transform_source, fatal=fatal)
+                    # Sometimes stream-level manifest contains single media entry that
+                    # does not contain any quality metadata (e.g. http://matchtv.ru/#live-player).
+                    # At the same time parent's media entry in set-level manifest may
+                    # contain it. We will copy it from parent in such cases.
+                    if len(f4m_formats) == 1:
+                        f = f4m_formats[0]
+                        f.update({
+                            'tbr': f.get('tbr') or tbr,
+                            'width': f.get('width') or width,
+                            'height': f.get('height') or height,
+                            'format_id': f.get('format_id') if not tbr else format_id,
+                        })
+                    formats.extend(f4m_formats)
+                    continue
+                elif ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        manifest_url, video_id, 'mp4', preference=preference,
+                        m3u8_id=m3u8_id, fatal=fatal))
                     continue
-            tbr = int_or_none(media_el.attrib.get('bitrate'))
             formats.append({
-                'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])),
+                'format_id': format_id,
                 'url': manifest_url,
-                'ext': 'flv',
+                'ext': 'flv' if bootstrap_info else None,
                 'tbr': tbr,
-                'width': int_or_none(media_el.attrib.get('width')),
-                'height': int_or_none(media_el.attrib.get('height')),
+                'width': width,
+                'height': height,
                 'preference': preference,
             })
-        self._sort_formats(formats)
-
         return formats
 
-    def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
-                              entry_protocol='m3u8', preference=None,
-                              m3u8_id=None, note=None, errnote=None,
-                              fatal=True):
-
-        formats = [{
+    def _m3u8_meta_format(self, m3u8_url, ext=None, preference=None, m3u8_id=None):
+        return {
             'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])),
             'url': m3u8_url,
             'ext': ext,
@@ -1017,7 +1102,14 @@ class InfoExtractor(object):
             'preference': preference - 1 if preference else -1,
             'resolution': 'multiple',
             'format_note': 'Quality selection URL',
-        }]
+        }
+
+    def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
+                              entry_protocol='m3u8', preference=None,
+                              m3u8_id=None, note=None, errnote=None,
+                              fatal=True, live=False):
+
+        formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
 
         format_url = lambda u: (
             u
@@ -1084,8 +1176,15 @@ class InfoExtractor(object):
                 format_id = []
                 if m3u8_id:
                     format_id.append(m3u8_id)
-                last_media_name = last_media.get('NAME') if last_media and last_media.get('TYPE') != 'SUBTITLES' else None
-                format_id.append(last_media_name if last_media_name else '%d' % (tbr if tbr else len(formats)))
+                last_media_name = last_media.get('NAME') if last_media and last_media.get('TYPE') not in ('SUBTITLES', 'CLOSED-CAPTIONS') else None
+                # Despite specification does not mention NAME attribute for
+                # EXT-X-STREAM-INF it still sometimes may be present
+                stream_name = last_info.get('NAME') or last_media_name
+                # Bandwidth of live streams may differ over time thus making
+                # format_id unpredictable. So it's better to keep provided
+                # format_id intact.
+                if not live:
+                    format_id.append(stream_name if stream_name else '%d' % (tbr if tbr else len(formats)))
                 f = {
                     'format_id': '-'.join(format_id),
                     'url': format_url(line.strip()),
@@ -1122,7 +1221,6 @@ class InfoExtractor(object):
                     last_media = None
                 formats.append(f)
                 last_info = {}
-        self._sort_formats(formats)
         return formats
 
     @staticmethod
@@ -1137,8 +1235,8 @@ 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):
-        smil = self._download_smil(smil_url, video_id, fatal=fatal)
+    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, transform_source=transform_source)
 
         if smil is False:
             assert not fatal
@@ -1155,10 +1253,10 @@ 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)
@@ -1218,21 +1316,21 @@ class InfoExtractor(object):
         m3u8_count = 0
 
         srcs = []
-        videos = smil.findall(self._xpath_ns('.//video', namespace))
-        for video in videos:
-            src = video.get('src')
+        media = smil.findall(self._xpath_ns('.//video', namespace)) + smil.findall(self._xpath_ns('.//audio', namespace))
+        for medium in media:
+            src = medium.get('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'))
-            width = int_or_none(video.get('width'))
-            height = int_or_none(video.get('height'))
-            proto = video.get('proto')
-            ext = video.get('ext')
+            bitrate = float_or_none(medium.get('system-bitrate') or medium.get('systemBitrate'), 1000)
+            filesize = int_or_none(medium.get('size') or medium.get('fileSize'))
+            width = int_or_none(medium.get('width'))
+            height = int_or_none(medium.get('height'))
+            proto = medium.get('proto')
+            ext = medium.get('ext')
             src_ext = determine_ext(src)
-            streamer = video.get('streamer') or base
+            streamer = medium.get('streamer') or base
 
             if proto == 'rtmp' or streamer.startswith('rtmp'):
                 rtmp_count += 1
@@ -1279,7 +1377,7 @@ class InfoExtractor(object):
                         'plugin': 'flowplayer-3.2.0.1',
                     }
                 f4m_url += '&' if '?' in f4m_url else '?'
-                f4m_url += compat_urllib_parse.urlencode(f4m_params)
+                f4m_url += compat_urllib_parse_urlencode(f4m_params)
                 formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False))
                 continue
 
@@ -1296,8 +1394,6 @@ class InfoExtractor(object):
                 })
                 continue
 
-        self._sort_formats(formats)
-
         return formats
 
     def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
@@ -1308,7 +1404,7 @@ class InfoExtractor(object):
             if not src or src in urls:
                 continue
             urls.append(src)
-            ext = textstream.get('ext') or determine_ext(src) or mimetype2ext(textstream.get('type'))
+            ext = textstream.get('ext') or mimetype2ext(textstream.get('type')) or determine_ext(src)
             lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') or textstream.get('lang') or subtitles_lang
             subtitles.setdefault(lang, []).append({
                 'url': src,
@@ -1444,8 +1540,9 @@ class InfoExtractor(object):
                         continue
                     representation_attrib = adaptation_set.attrib.copy()
                     representation_attrib.update(representation.attrib)
-                    mime_type = representation_attrib.get('mimeType')
-                    content_type = mime_type.split('/')[0] if mime_type else representation_attrib.get('contentType')
+                    # According to page 41 of ISO/IEC 29001-1:2014, @mimeType is mandatory
+                    mime_type = representation_attrib['mimeType']
+                    content_type = mime_type.split('/')[0]
                     if content_type == 'text':
                         # TODO implement WebVTT downloading
                         pass
@@ -1468,6 +1565,7 @@ class InfoExtractor(object):
                         f = {
                             '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),
@@ -1486,9 +1584,16 @@ class InfoExtractor(object):
                                 representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
                             media_template = representation_ms_info['media_template']
                             media_template = media_template.replace('$RepresentationID$', representation_id)
-                            media_template = re.sub(r'\$(Number|Bandwidth)(?:%(0\d+)d)?\$', r'%(\1)\2d', media_template)
+                            media_template = re.sub(r'\$(Number|Bandwidth)\$', r'%(\1)d', media_template)
+                            media_template = re.sub(r'\$(Number|Bandwidth)%([^$]+)\$', r'%(\1)\2', media_template)
                             media_template.replace('$$', '$')
-                            representation_ms_info['segment_urls'] = [media_template % {'Number': segment_number, 'Bandwidth': representation_attrib.get('bandwidth')} for segment_number in range(representation_ms_info['start_number'], representation_ms_info['total_number'] + representation_ms_info['start_number'])]
+                            representation_ms_info['segment_urls'] = [
+                                media_template % {
+                                    'Number': segment_number,
+                                    'Bandwidth': representation_attrib.get('bandwidth')}
+                                for segment_number in range(
+                                    representation_ms_info['start_number'],
+                                    representation_ms_info['total_number'] + representation_ms_info['start_number'])]
                         if 'segment_urls' in representation_ms_info:
                             f.update({
                                 'segment_urls': representation_ms_info['segment_urls'],
@@ -1513,7 +1618,6 @@ class InfoExtractor(object):
                             existing_format.update(f)
                     else:
                         self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
-        self._sort_formats(formats)
         return formats
 
     def _live_title(self, name):
@@ -1620,6 +1724,15 @@ class InfoExtractor(object):
     def _get_automatic_captions(self, *args, **kwargs):
         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):
     """

youtube_dl/extractor/commonprotocols.py

@@ -0,0 +1,36 @@
+from __future__ import unicode_literals
+
+import os
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse_unquote,
+    compat_urlparse,
+)
+from ..utils import url_basename
+
+
+class RtmpIE(InfoExtractor):
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'(?i)rtmp[est]?://.+'
+
+    _TESTS = [{
+        'url': 'rtmp://cp44293.edgefcs.net/ondemand?auth=daEcTdydfdqcsb8cZcDbAaCbhamacbbawaS-bw7dBb-bWG-GqpGFqCpNCnGoyL&aifp=v001&slist=public/unsecure/audio/2c97899446428e4301471a8cb72b4b97--audio--pmg-20110908-0900a_flv_aac_med_int.mp4',
+        'only_matching': True,
+    }, {
+        'url': 'rtmp://edge.live.hitbox.tv/live/dimak',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
+        title = compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': [{
+                'url': url,
+                'ext': 'flv',
+                'format_id': compat_urlparse.urlparse(url).scheme,
+            }],
+        }