release 2017.09.24

This fixes handling of non-UTF8 TTML subtitles

Closes #14191

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.08.18*. 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 Issues with outdated version will be rejected.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 **2017.08.18**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.09.24*. 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 Issues with outdated version will be rejected.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 **2017.09.24**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
 [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 2017.08.18
+[debug] youtube-dl version 2017.09.24
 [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: {}

.gitignore

@@ -22,6 +22,7 @@ cover/
 updates_key.pem
 *.egg-info
 *.srt
+*.ttml
 *.sbv
 *.vtt
 *.flv

AUTHORS

@@ -224,3 +224,9 @@ Giuseppe Fabiano
 Örn Guðjónsson
 Parmjit Virk
 Genki Sky
+Ľuboš Katrinec
+Corey Nicholson
+Ashutosh Chaudhary
+John Dong
+Tatsuyuki Ishi
+Daniel Weber

CONTRIBUTING.md

@@ -3,7 +3,7 @@
 $ 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] Command-line args: [u'-v', u'https://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
 [debug] youtube-dl version 2015.12.06
 [debug] Git HEAD: 135392e
@@ -34,7 +34,7 @@ For bug reports, this means that your report should contain the *complete* outpu
 
 If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
 
-**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `http://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `http://www.youtube.com/`) is *not* an example URL.
+**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `https://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `https://www.youtube.com/`) is *not* an example URL.
 
 ###  Are you using the latest version?
 
@@ -70,7 +70,7 @@ It may sound strange, but some bug reports we receive are completely unrelated t
 
 # DEVELOPER INSTRUCTIONS
 
-Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
+Most users do not need to build youtube-dl and can [download the builds](https://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
 
 To run youtube-dl as a developer, you don't need to build anything either. Simply execute
 
@@ -82,6 +82,8 @@ To run the test, simply invoke your favorite test runner, or execute a test file
     python test/test_download.py
     nosetests
 
+See item 6 of [new extractor tutorial](#adding-support-for-a-new-site) for how to run extractor specific test cases.
+
 If you want to create a build of youtube-dl yourself, you'll need
 
 * python
@@ -118,7 +120,7 @@ After you have ensured this site is distributing its content legally, you can fo
     class YourExtractorIE(InfoExtractor):
         _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
         _TEST = {
-            'url': 'http://yourextractor.com/watch/42',
+            'url': 'https://yourextractor.com/watch/42',
             'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
             'info_dict': {
                 'id': '42',
@@ -149,10 +151,10 @@ After you have ensured this site is distributing its content legally, you can fo
             }
     ```
 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.
+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. Note that tests with `only_matching` key in test's dict are not counted in.
 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want.
-8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](http://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
-9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
+8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
+9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
 
         $ git add youtube_dl/extractor/extractors.py
         $ git add youtube_dl/extractor/yourextractor.py

ChangeLog

@@ -1,3 +1,146 @@
+version 2017.09.24
+
+Core
++ [options] Accept lrc as a subtitle conversion target format (#14292)
+* [utils] Fix handling raw TTML subtitles (#14191)
+
+Extractors
+* [24video] Fix timestamp extraction and make non fatal (#14295)
++ [24video] Add support for 24video.adult (#14295)
++ [kakao] Add support for tv.kakao.com (#12298, #14007)
++ [twitter] Add support for URLs without user id (#14270)
++ [americastestkitchen] Add support for americastestkitchen.com (#10764,
+  #13996)
+* [generic] Fix support for multiple HTML5 videos on one page (#14080)
+* [mixcloud] Fix extraction (#14088, #14132)
++ [lynda] Add support for educourse.ga (#14286)
+* [beeg] Fix extraction (#14275)
+* [nbcsports:vplayer] Correct theplatform URL (#13873)
+* [twitter] Fix duration extraction (#14141)
+* [tvplay] Bypass geo restriction
++ [heise] Add support for YouTube embeds (#14109)
++ [popcorntv] Add support for popcorntv.it (#5914, #14211)
+* [viki] Update app data (#14181)
+* [morningstar] Relax URL regular expression (#14222)
+* [openload] Fix extraction (#14225, #14257)
+* [noovo] Fix extraction (#14214)
+* [dailymotion:playlist] Relax URL regular expression (#14219)
++ [twitch] Add support for go.twitch.tv URLs (#14215)
+* [vgtv] Relax URL regular expression (#14223)
+
+
+version 2017.09.15
+
+Core
+* [downloader/fragment] Restart inconsistent incomplete fragment downloads
+  (#13731)
+* [YoutubeDL] Download raw subtitles files (#12909, #14191)
+
+Extractors
+* [condenast] Fix extraction (#14196, #14207)
++ [orf] Add support for f4m stories
+* [tv4] Relax URL regular expression (#14206)
+* [animeondemand] Bypass geo restriction
++ [animeondemand] Add support for flash videos (#9944)
+
+
+version 2017.09.11
+
+Extractors
+* [rutube:playlist] Fix suitable (#14166)
+
+
+version 2017.09.10
+
+Core
++ [utils] Introduce bool_or_none
+* [YoutubeDL] Ensure dir existence for each requested format (#14116)
+
+Extractors
+* [fox] Fix extraction (#14147)
+* [rutube] Use bool_or_none
+* [rutube] Rework and generalize playlist extractors (#13565)
++ [rutube:playlist] Add support for playlists (#13534, #13565)
++ [radiocanada] Add fallback for title extraction (#14145)
+* [vk] Use dedicated YouTube embeds extraction routine
+* [vice] Use dedicated YouTube embeds extraction routine
+* [cracked] Use dedicated YouTube embeds extraction routine
+* [chilloutzone] Use dedicated YouTube embeds extraction routine
+* [abcnews] Use dedicated YouTube embeds extraction routine
+* [youtube] Separate methods for embeds extraction
+* [redtube] Fix formats extraction (#14122)
+* [arte] Relax unavailability check (#14112)
++ [manyvids] Add support for preview videos from manyvids.com (#14053, #14059)
+* [vidme:user] Relax URL regular expression (#14054)
+* [bpb] Fix extraction (#14043, #14086)
+* [soundcloud] Fix download URL with private tracks (#14093)
+* [aliexpress:live] Add support for live.aliexpress.com (#13698, #13707)
+* [viidea] Capture and output lecture error message (#14099)
+* [radiocanada] Skip unsupported platforms (#14100)
+
+
+version 2017.09.02
+
+Extractors
+* [youtube] Force old layout for each webpage (#14068, #14072, #14074, #14076,
+  #14077, #14079, #14082, #14083, #14094, #14095, #14096)
+* [youtube] Fix upload date extraction (#14065)
++ [charlierose] Add support for episodes (#14062)
++ [bbccouk] Add support for w-prefixed ids (#14056)
+* [googledrive] Extend URL regular expression (#9785)
++ [googledrive] Add support for source format (#14046)
+* [pornhd] Fix extraction (#14005)
+
+
+version 2017.08.27.1
+
+Extractors
+
+* [youtube] Fix extraction with --youtube-skip-dash-manifest enabled (#14037)
+
+
+version 2017.08.27
+
+Core
++ [extractor/common] Extract height and format id for HTML5 videos (#14034)
+* [downloader/http] Rework HTTP downloader (#506, #809, #2849, #4240, #6023,
+  #8625, #9483)
+    * Simplify code and split into separate routines to facilitate maintaining
+    * Make retry mechanism work on errors during actual download not only
+      during connection establishment phase
+    * Retry on ECONNRESET and ETIMEDOUT during reading data from network
+    * Retry on content too short
+    * Show error description on retry
+
+Extractors
+* [generic] Lower preference for extraction from LD-JSON
+* [rai] Fix audio formats extraction (#14024)
+* [youtube] Fix controversy videos extraction (#14027, #14029)
+* [mixcloud] Fix extraction (#14015, #14020)
+
+
+version 2017.08.23
+
+Core
++ [extractor/common] Introduce _parse_xml
+* [extractor/common] Make HLS and DASH extraction in_parse_html5_media_entries
+  non fatal (#13970)
+* [utils] Fix unescapeHTML for misformed string like "&a"" (#13935)
+
+Extractors
+* [cbc:watch] Bypass geo restriction (#13993)
+* [toutv] Relax DRM check (#13994)
++ [googledrive] Add support for subtitles (#13619, #13638)
+* [pornhub] Relax uploader regular expression (#13906, #13975)
+* [bandcamp:album] Extract track titles (#13962)
++ [bbccouk] Add support for events URLs (#13893)
++ [liveleak] Support multi-video pages (#6542)
++ [liveleak] Support another liveleak embedding pattern (#13336)
+* [cda] Fix extraction (#13935)
++ [laola1tv] Add support for tv.ittf.com (#13965)
+* [mixcloud] Fix extraction (#13958, #13974, #13980, #14003)
+
+
 version 2017.08.18
 
 Core
@@ -118,7 +261,7 @@ Extractors
 * [youku:show] Fix playlist extraction (#13248)
 + [dispeak] Recognize sevt subdomain (#13276)
 * [adn] Improve error reporting (#13663)
-* [crunchyroll] Relax series and season regex (#13659)
+* [crunchyroll] Relax series and season regular expression (#13659)
 + [spiegel:article] Add support for nexx iframe embeds (#13029)
 + [nexx:embed] Add support for iframe embeds
 * [nexx] Improve JS embed extraction

Makefile

@@ -46,8 +46,15 @@ tar: youtube-dl.tar.gz
 pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1 youtube-dl.fish
 
 youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
-	zip --quiet youtube-dl youtube_dl/*.py youtube_dl/*/*.py
-	zip --quiet --junk-paths youtube-dl youtube_dl/__main__.py
+	mkdir -p zip
+	for d in youtube_dl youtube_dl/downloader youtube_dl/extractor youtube_dl/postprocessor ; do \
+	  mkdir -p zip/$$d ;\
+	  cp -pPR $$d/*.py zip/$$d/ ;\
+	done
+	touch -t 200001010101 zip/youtube_dl/*.py zip/youtube_dl/*/*.py
+	mv zip/youtube_dl/__main__.py zip/
+	cd zip ; zip -q ../youtube-dl youtube_dl/*.py youtube_dl/*/*.py __main__.py
+	rm -rf zip
 	echo '#!$(PYTHON)' > youtube-dl
 	cat youtube-dl.zip >> youtube-dl
 	rm youtube-dl.zip

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 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`).
+Windows users can [download an .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in any location on their [PATH](https://en.wikipedia.org/wiki/PATH_%28variable%29) except for `%SYSTEMROOT%\System32` (e.g. **do not** put in `C:\Windows\System32`).
 
 You can also use pip:
 
@@ -33,7 +33,7 @@ You can also use pip:
     
 This command will update youtube-dl if you have already installed it. See the [pypi page](https://pypi.python.org/pypi/youtube_dl) for more information.
 
-OS X users can install youtube-dl with [Homebrew](http://brew.sh/):
+OS X users can install youtube-dl with [Homebrew](https://brew.sh/):
 
     brew install youtube-dl
 
@@ -427,7 +427,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                      syntax. Example: --exec 'adb push {}
                                      /sdcard/Music/ && rm {}'
     --convert-subs FORMAT            Convert the subtitles to other format
-                                     (currently supported: srt|ass|vtt)
+                                     (currently supported: srt|ass|vtt|lrc)
 
 # CONFIGURATION
 
@@ -458,7 +458,7 @@ You can also use `--config-location` if you want to use custom configuration fil
 
 ### 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 a per extractor basis. For that you will need to create a `.netrc` file in your `$HOME` and restrict permissions to read/write by only you:
+You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](https://stackoverflow.com/tags/.netrc/info) on a per extractor basis. For that you will need to create a `.netrc` file in your `$HOME` and restrict permissions to read/write by only you:
 ```
 touch $HOME/.netrc
 chmod a-rwx,u+rw $HOME/.netrc
@@ -485,7 +485,7 @@ The `-o` option allows users to indicate a template for the output file names.
 
 **tl;dr:** [navigate me to examples](#output-template-examples).
 
-The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a formatting operations. Allowed names along with sequence type are:
+The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a formatting operations. Allowed names along with sequence type are:
 
  - `id` (string): Video identifier
  - `title` (string): Video title
@@ -603,7 +603,7 @@ $ youtube-dl -o '%(uploader)s/%(playlist)s/%(playlist_index)s - %(title)s.%(ext)
 $ youtube-dl -u user -p password -o '~/MyVideos/%(playlist)s/%(chapter_number)s - %(chapter)s/%(title)s.%(ext)s' https://www.udemy.com/java-tutorial/
 
 # Download entire series season keeping each series and each season in separate directory under C:/MyVideos
-$ youtube-dl -o "C:/MyVideos/%(series)s/%(season_number)s - %(season)s/%(episode_number)s - %(episode)s.%(ext)s" http://videomore.ru/kino_v_detalayah/5_sezon/367617
+$ youtube-dl -o "C:/MyVideos/%(series)s/%(season_number)s - %(season)s/%(episode_number)s - %(episode)s.%(ext)s" https://videomore.ru/kino_v_detalayah/5_sezon/367617
 
 # Stream the video being downloaded to stdout
 $ youtube-dl -o - BaW_jenozKc
@@ -716,17 +716,17 @@ $ youtube-dl --dateafter 20000101 --datebefore 20091231
 
 ### How do I update youtube-dl?
 
-If you've followed [our manual installation instructions](http://rg3.github.io/youtube-dl/download.html), you can simply run `youtube-dl -U` (or, on Linux, `sudo youtube-dl -U`).
+If you've followed [our manual installation instructions](https://rg3.github.io/youtube-dl/download.html), you can simply run `youtube-dl -U` (or, on Linux, `sudo youtube-dl -U`).
 
 If you have used pip, a simple `sudo pip install -U youtube-dl` is sufficient to update.
 
-If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to http://yt-dl.org/ to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distribution serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum.
+If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to https://yt-dl.org to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distribution serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum.
 
 As a last resort, you can also uninstall the version installed by your package manager and follow our manual installation instructions. For that, remove the distribution's package, with a line like
 
     sudo apt-get remove -y youtube-dl
 
-Afterwards, simply follow [our manual installation instructions](http://rg3.github.io/youtube-dl/download.html):
+Afterwards, simply follow [our manual installation instructions](https://rg3.github.io/youtube-dl/download.html):
 
 ```
 sudo wget https://yt-dl.org/latest/youtube-dl -O /usr/local/bin/youtube-dl
@@ -766,11 +766,11 @@ Apparently YouTube requires you to pass a CAPTCHA test if you download too much.
 
 youtube-dl works fine on its own on most sites. However, if you want to convert video/audio, you'll need [avconv](https://libav.org/) or [ffmpeg](https://www.ffmpeg.org/). On some sites - most notably YouTube - videos can be retrieved in a higher quality format without sound. youtube-dl will detect whether avconv/ffmpeg is present and automatically pick the best option.
 
-Videos or video formats streamed via RTMP protocol can only be downloaded when [rtmpdump](https://rtmpdump.mplayerhq.hu/) is installed. Downloading MMS and RTSP videos requires either [mplayer](http://mplayerhq.hu/) or [mpv](https://mpv.io/) to be installed.
+Videos or video formats streamed via RTMP protocol can only be downloaded when [rtmpdump](https://rtmpdump.mplayerhq.hu/) is installed. Downloading MMS and RTSP videos requires either [mplayer](https://mplayerhq.hu/) or [mpv](https://mpv.io/) to be installed.
 
 ### I have downloaded a video but how can I play it?
 
-Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [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](https://www.videolan.org/) or [mplayer](https://www.mplayerhq.hu/).
 
 ### I extracted a video URL with `-g`, but it does not play on another machine / in my web browser.
 
@@ -845,10 +845,10 @@ Use the `-o` to specify an [output template](#output-template), for example `-o
 
 ### How do I download a video starting with a `-`?
 
-Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the options with `--`:
+Either prepend `https://www.youtube.com/watch?v=` or separate the ID from the options with `--`:
 
     youtube-dl -- -wNyEUrxzFU
-    youtube-dl "http://www.youtube.com/watch?v=-wNyEUrxzFU"
+    youtube-dl "https://www.youtube.com/watch?v=-wNyEUrxzFU"
 
 ### How do I pass cookies to youtube-dl?
 
@@ -862,9 +862,9 @@ Passing cookies to youtube-dl is a good way to workaround login when a particula
 
 ### How do I stream directly to media player?
 
-You will first need to tell youtube-dl to stream media to stdout with `-o -`, and also tell your media player to read from stdin (it must be capable of this for streaming) and then pipe former to latter. For example, streaming to [vlc](http://www.videolan.org/) can be achieved with:
+You will first need to tell youtube-dl to stream media to stdout with `-o -`, and also tell your media player to read from stdin (it must be capable of this for streaming) and then pipe former to latter. For example, streaming to [vlc](https://www.videolan.org/) can be achieved with:
 
-    youtube-dl -o - "http://www.youtube.com/watch?v=BaW_jenozKcj" | vlc -
+    youtube-dl -o - "https://www.youtube.com/watch?v=BaW_jenozKcj" | vlc -
 
 ### How do I download only new videos from a playlist?
 
@@ -884,7 +884,7 @@ When youtube-dl detects an HLS video, it can download it either with the built-i
 
 When youtube-dl knows that one particular downloader works better for a given website, that downloader will be picked. Otherwise, youtube-dl will pick the best downloader for general compatibility, which at the moment happens to be ffmpeg. This choice may change in future versions of youtube-dl, with improvements of the built-in downloader and/or ffmpeg.
 
-In particular, the generic extractor (used when your website is not in the [list of supported sites by youtube-dl](http://rg3.github.io/youtube-dl/supportedsites.html) cannot mandate one specific downloader.
+In particular, the generic extractor (used when your website is not in the [list of supported sites by youtube-dl](https://rg3.github.io/youtube-dl/supportedsites.html) cannot mandate one specific downloader.
 
 If you put either `--hls-prefer-native` or `--hls-prefer-ffmpeg` into your configuration, a different subset of videos will fail to download correctly. Instead, it is much better to [file an issue](https://yt-dl.org/bug) or a pull request which details why the native or the ffmpeg HLS downloader is a better choice for your use case.
 
@@ -910,7 +910,7 @@ Feel free to bump the issue from time to time by writing a small comment ("Issue
 
 ### How can I detect whether a given URL is supported by youtube-dl?
 
-For one, have a look at the [list of supported sites](docs/supportedsites.md). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/video/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
+For one, have a look at the [list of supported sites](docs/supportedsites.md). Note that it can sometimes happen that the site changes its URL scheme (say, from https://example.com/video/1234567 to https://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
 
 It is *not* possible to detect whether a URL is supported or not. That's because youtube-dl contains a generic extractor which matches **all** URLs. You may be tempted to disable, exclude, or remove the generic extractor, but the generic extractor not only allows users to extract videos from lots of websites that embed a video from another service, but may also be used to extract video from a service that it's hosting itself. Therefore, we neither recommend nor support disabling, excluding, or removing the generic extractor.
 
@@ -924,7 +924,7 @@ youtube-dl is an open-source project manned by too few volunteers, so we'd rathe
 
 # DEVELOPER INSTRUCTIONS
 
-Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
+Most users do not need to build youtube-dl and can [download the builds](https://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
 
 To run youtube-dl as a developer, you don't need to build anything either. Simply execute
 
@@ -936,6 +936,8 @@ To run the test, simply invoke your favorite test runner, or execute a test file
     python test/test_download.py
     nosetests
 
+See item 6 of [new extractor tutorial](#adding-support-for-a-new-site) for how to run extractor specific test cases.
+
 If you want to create a build of youtube-dl yourself, you'll need
 
 * python
@@ -972,7 +974,7 @@ After you have ensured this site is distributing its content legally, you can fo
     class YourExtractorIE(InfoExtractor):
         _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
         _TEST = {
-            'url': 'http://yourextractor.com/watch/42',
+            'url': 'https://yourextractor.com/watch/42',
             'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
             'info_dict': {
                 'id': '42',
@@ -1003,10 +1005,10 @@ After you have ensured this site is distributing its content legally, you can fo
             }
     ```
 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.
+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. Note that tests with `only_matching` key in test's dict are not counted in.
 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want.
-8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](http://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
-9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
+8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
+9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
 
         $ git add youtube_dl/extractor/extractors.py
         $ git add youtube_dl/extractor/yourextractor.py
@@ -1162,7 +1164,7 @@ import youtube_dl
 
 ydl_opts = {}
 with youtube_dl.YoutubeDL(ydl_opts) as ydl:
-    ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
+    ydl.download(['https://www.youtube.com/watch?v=BaW_jenozKc'])
 ```
 
 Most likely, you'll want to use various options. For a list of options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L129-L279). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
@@ -1201,19 +1203,19 @@ ydl_opts = {
     'progress_hooks': [my_hook],
 }
 with youtube_dl.YoutubeDL(ydl_opts) as ydl:
-    ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
+    ydl.download(['https://www.youtube.com/watch?v=BaW_jenozKc'])
 ```
 
 # BUGS
 
-Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>. Unless you were prompted to or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](http://webchat.freenode.net/?randomnick=1&channels=youtube-dl)).
+Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>. Unless you were prompted to or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](https://webchat.freenode.net/?randomnick=1&channels=youtube-dl)).
 
 **Please include the full output of youtube-dl when run with `-v`**, i.e. **add** `-v` flag to **your command line**, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this:
 ```
 $ 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] Command-line args: [u'-v', u'https://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
 [debug] youtube-dl version 2015.12.06
 [debug] Git HEAD: 135392e
@@ -1244,7 +1246,7 @@ For bug reports, this means that your report should contain the *complete* outpu
 
 If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
 
-**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `http://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `http://www.youtube.com/`) is *not* an example URL.
+**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `https://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `https://www.youtube.com/`) is *not* an example URL.
 
 ###  Are you using the latest version?
 

devscripts/check-porn.py

@@ -14,7 +14,7 @@ import os
 import sys
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from test.helper import get_testcases
+from test.helper import gettestcases
 from youtube_dl.utils import compat_urllib_parse_urlparse
 from youtube_dl.utils import compat_urllib_request
 
@@ -24,7 +24,7 @@ if len(sys.argv) > 1:
 else:
     METHOD = 'EURISTIC'
 
-for test in get_testcases():
+for test in gettestcases():
     if METHOD == 'EURISTIC':
         try:
             webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()

docs/supportedsites.md

@@ -38,10 +38,12 @@
  - **afreecatv**: afreecatv.com
  - **afreecatv:global**: afreecatv.com
  - **AirMozilla**
+ - **AliExpressLive**
  - **AlJazeera**
  - **Allocine**
  - **AlphaPorno**
  - **AMCNetworks**
+ - **AmericasTestKitchen**
  - **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
  - **AnimeOnDemand**
  - **anitube.se**
@@ -363,6 +365,7 @@
  - **IPrima**
  - **iqiyi**: 爱奇艺
  - **Ir90Tv**
+ - **ITTF**
  - **ITV**
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
@@ -376,6 +379,7 @@
  - **Jove**
  - **jpopsuki.tv**
  - **JWPlatform**
+ - **Kakao**
  - **Kaltura**
  - **Kamcord**
  - **KanalPlay**: Kanal 5/9/11 Play
@@ -419,6 +423,7 @@
  - **limelight:channel_list**
  - **LiTV**
  - **LiveLeak**
+ - **LiveLeakEmbed**
  - **livestream**
  - **livestream:original**
  - **LnkGo**
@@ -435,6 +440,7 @@
  - **MakerTV**
  - **mangomolo:live**
  - **mangomolo:video**
+ - **ManyVids**
  - **MatchTV**
  - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
@@ -589,6 +595,7 @@
  - **Openload**
  - **OraTV**
  - **orf:fm4**: radio FM4
+ - **orf:fm4:story**: fm4.orf.at stories
  - **orf:iptv**: iptv.ORF.at
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
@@ -622,6 +629,7 @@
  - **Pokemon**
  - **PolskieRadio**
  - **PolskieRadioCategory**
+ - **PopcornTV**
  - **PornCom**
  - **PornerBros**
  - **PornFlip**
@@ -699,6 +707,7 @@
  - **rutube:embed**: Rutube embedded videos
  - **rutube:movie**: Rutube movies
  - **rutube:person**: Rutube person videos
+ - **rutube:playlist**: Rutube playlists
  - **RUTV**: RUTV.RU
  - **Ruutu**
  - **Ruv**

test/test_utils.py

@@ -279,6 +279,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unescapeHTML('/'), '/')
         self.assertEqual(unescapeHTML('é'), 'é')
         self.assertEqual(unescapeHTML('�'), '�')
+        self.assertEqual(unescapeHTML('&a"'), '&a"')
         # HTML5 entities
         self.assertEqual(unescapeHTML('.''), '.\'')
 
@@ -1063,7 +1064,7 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
                     <p begin="3" dur="-1">Ignored, three</p>
                 </div>
             </body>
-            </tt>'''
+            </tt>'''.encode('utf-8')
         srt_data = '''1
 00:00:00,000 --> 00:00:01,000
 The following line contains Chinese characters and special symbols
@@ -1088,7 +1089,7 @@ Line
                     <p begin="0" end="1">The first line</p>
                 </div>
             </body>
-            </tt>'''
+            </tt>'''.encode('utf-8')
         srt_data = '''1
 00:00:00,000 --> 00:00:01,000
 The first line
@@ -1114,7 +1115,7 @@ The first line
       <p style="s1" tts:textDecoration="underline" begin="00:00:09.56" id="p2" end="00:00:12.36"><span style="s2" tts:color="lime">inner<br /> </span>style</p>
     </div>
   </body>
-</tt>'''
+</tt>'''.encode('utf-8')
         srt_data = '''1
 00:00:02,080 --> 00:00:05,839
 <font color="white" face="sansSerif" size="16">default style<font color="red">custom style</font></font>
@@ -1137,6 +1138,26 @@ part 3</font></u>
 '''
         self.assertEqual(dfxp2srt(dfxp_data_with_style), srt_data)
 
+        dfxp_data_non_utf8 = '''<?xml version="1.0" encoding="UTF-16"?>
+            <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
+            <body>
+                <div xml:lang="en">
+                    <p begin="0" end="1">Line 1</p>
+                    <p begin="1" end="2">第二行</p>
+                </div>
+            </body>
+            </tt>'''.encode('utf-16')
+        srt_data = '''1
+00:00:00,000 --> 00:00:01,000
+Line 1
+
+2
+00:00:01,000 --> 00:00:02,000
+第二行
+
+'''
+        self.assertEqual(dfxp2srt(dfxp_data_non_utf8), srt_data)
+
     def test_cli_option(self):
         self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
         self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])

youtube_dl/YoutubeDL.py

@@ -92,6 +92,7 @@ from .utils import (
 )
 from .cache import Cache
 from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER
+from .extractor.openload import PhantomJSwrapper
 from .downloader import get_suitable_downloader
 from .downloader.rtmp import rtmpdump_version
 from .postprocessor import (
@@ -1710,12 +1711,17 @@ class YoutubeDL(object):
         if filename is None:
             return
 
-        try:
-            dn = os.path.dirname(sanitize_path(encodeFilename(filename)))
-            if dn and not os.path.exists(dn):
-                os.makedirs(dn)
-        except (OSError, IOError) as err:
-            self.report_error('unable to create directory ' + error_to_compat_str(err))
+        def ensure_dir_exists(path):
+            try:
+                dn = os.path.dirname(path)
+                if dn and not os.path.exists(dn):
+                    os.makedirs(dn)
+                return True
+            except (OSError, IOError) as err:
+                self.report_error('unable to create directory ' + error_to_compat_str(err))
+                return False
+
+        if not ensure_dir_exists(sanitize_path(encodeFilename(filename))):
             return
 
         if self.params.get('writedescription', False):
@@ -1758,29 +1764,30 @@ class YoutubeDL(object):
             ie = self.get_info_extractor(info_dict['extractor_key'])
             for sub_lang, sub_info in subtitles.items():
                 sub_format = sub_info['ext']
-                if sub_info.get('data') is not None:
-                    sub_data = sub_info['data']
+                sub_filename = subtitles_filename(filename, sub_lang, sub_format)
+                if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)):
+                    self.to_screen('[info] Video subtitle %s.%s is already present' % (sub_lang, sub_format))
                 else:
-                    try:
-                        sub_data = ie._download_webpage(
-                            sub_info['url'], info_dict['id'], note=False)
-                    except ExtractorError as err:
-                        self.report_warning('Unable to download subtitle for "%s": %s' %
-                                            (sub_lang, error_to_compat_str(err.cause)))
-                        continue
-                try:
-                    sub_filename = subtitles_filename(filename, sub_lang, sub_format)
-                    if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)):
-                        self.to_screen('[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format))
+                    self.to_screen('[info] Writing video subtitles to: ' + sub_filename)
+                    if sub_info.get('data') is not None:
+                        try:
+                            # Use newline='' to prevent conversion of newline characters
+                            # See https://github.com/rg3/youtube-dl/issues/10268
+                            with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile:
+                                subfile.write(sub_info['data'])
+                        except (OSError, IOError):
+                            self.report_error('Cannot write subtitles file ' + sub_filename)
+                            return
                     else:
-                        self.to_screen('[info] Writing video subtitles to: ' + sub_filename)
-                        # Use newline='' to prevent conversion of newline characters
-                        # See https://github.com/rg3/youtube-dl/issues/10268
-                        with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile:
-                            subfile.write(sub_data)
-                except (OSError, IOError):
-                    self.report_error('Cannot write subtitles file ' + sub_filename)
-                    return
+                        try:
+                            sub_data = ie._request_webpage(
+                                sub_info['url'], info_dict['id'], note=False).read()
+                            with io.open(encodeFilename(sub_filename), 'wb') as subfile:
+                                subfile.write(sub_data)
+                        except (ExtractorError, IOError, OSError, ValueError) as err:
+                            self.report_warning('Unable to download subtitle for "%s": %s' %
+                                                (sub_lang, error_to_compat_str(err)))
+                            continue
 
         if self.params.get('writeinfojson', False):
             infofn = replace_extension(filename, 'info.json', info_dict.get('ext'))
@@ -1853,8 +1860,11 @@ class YoutubeDL(object):
                         for f in requested_formats:
                             new_info = dict(info_dict)
                             new_info.update(f)
-                            fname = self.prepare_filename(new_info)
-                            fname = prepend_extension(fname, 'f%s' % f['format_id'], new_info['ext'])
+                            fname = prepend_extension(
+                                self.prepare_filename(new_info),
+                                'f%s' % f['format_id'], new_info['ext'])
+                            if not ensure_dir_exists(fname):
+                                return
                             downloaded.append(fname)
                             partial_success = dl(fname, new_info)
                             success = success and partial_success
@@ -2208,6 +2218,7 @@ class YoutubeDL(object):
 
         exe_versions = FFmpegPostProcessor.get_versions(self)
         exe_versions['rtmpdump'] = rtmpdump_version()
+        exe_versions['phantomjs'] = PhantomJSwrapper._version()
         exe_str = ', '.join(
             '%s %s' % (exe, v)
             for exe, v in sorted(exe_versions.items())

youtube_dl/__init__.py

@@ -206,7 +206,7 @@ def _real_main(argv=None):
         if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
             parser.error('invalid video recode format specified')
     if opts.convertsubtitles is not None:
-        if opts.convertsubtitles not in ['srt', 'vtt', 'ass']:
+        if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
             parser.error('invalid subtitle format specified')
 
     if opts.date is not None:

youtube_dl/compat.py

@@ -6,6 +6,7 @@ import collections
 import email
 import getpass
 import io
+import itertools
 import optparse
 import os
 import re
@@ -15,7 +16,6 @@ import socket
 import struct
 import subprocess
 import sys
-import itertools
 import xml.etree.ElementTree
 
 
@@ -2898,6 +2898,13 @@ else:
     compat_struct_pack = struct.pack
     compat_struct_unpack = struct.unpack
 
+try:
+    from future_builtins import zip as compat_zip
+except ImportError:  # not 2.6+ or is 3.x
+    try:
+        from itertools import izip as compat_zip  # < 2.5 or 3.x
+    except ImportError:
+        compat_zip = zip
 
 __all__ = [
     'compat_HTMLParseError',
@@ -2948,5 +2955,6 @@ __all__ = [
     'compat_urlretrieve',
     'compat_xml_parse_error',
     'compat_xpath',
+    'compat_zip',
     'workaround_optparse_bug9161',
 ]

youtube_dl/downloader/common.py

@@ -304,11 +304,11 @@ class FileDownloader(object):
         """Report attempt to resume at given byte."""
         self.to_screen('[download] Resuming download at byte %s' % resume_len)
 
-    def report_retry(self, count, retries):
+    def report_retry(self, err, count, retries):
         """Report retry in case of HTTP error 5xx"""
         self.to_screen(
-            '[download] Got server HTTP error. Retrying (attempt %d of %s)...'
-            % (count, self.format_retries(retries)))
+            '[download] Got server HTTP error: %s. Retrying (attempt %d of %s)...'
+            % (error_to_compat_str(err), count, self.format_retries(retries)))
 
     def report_file_already_downloaded(self, file_name):
         """Report file has already been fully downloaded."""

youtube_dl/downloader/fragment.py

@@ -151,10 +151,15 @@ class FragmentFD(FileDownloader):
         if self.__do_ytdl_file(ctx):
             if os.path.isfile(encodeFilename(self.ytdl_filename(ctx['filename']))):
                 self._read_ytdl_file(ctx)
+                if ctx['fragment_index'] > 0 and resume_len == 0:
+                    self.report_error(
+                        'Inconsistent state of incomplete fragment download. '
+                        'Restarting from the beginning...')
+                    ctx['fragment_index'] = resume_len = 0
+                    self._write_ytdl_file(ctx)
             else:
                 self._write_ytdl_file(ctx)
-            if ctx['fragment_index'] > 0:
-                assert resume_len > 0
+                assert ctx['fragment_index'] == 0
 
         dest_stream, tmpfilename = sanitize_open(tmpfilename, open_mode)
 

youtube_dl/downloader/http.py

@@ -22,8 +22,16 @@ from ..utils import (
 class HttpFD(FileDownloader):
     def real_download(self, filename, info_dict):
         url = info_dict['url']
-        tmpfilename = self.temp_name(filename)
-        stream = None
+
+        class DownloadContext(dict):
+            __getattr__ = dict.get
+            __setattr__ = dict.__setitem__
+            __delattr__ = dict.__delitem__
+
+        ctx = DownloadContext()
+        ctx.filename = filename
+        ctx.tmpfilename = self.temp_name(filename)
+        ctx.stream = None
 
         # Do not include the Accept-Encoding header
         headers = {'Youtubedl-no-compression': 'True'}
@@ -38,46 +46,51 @@ class HttpFD(FileDownloader):
         if is_test:
             request.add_header('Range', 'bytes=0-%s' % str(self._TEST_FILE_SIZE - 1))
 
-        # Establish possible resume length
-        if os.path.isfile(encodeFilename(tmpfilename)):
-            resume_len = os.path.getsize(encodeFilename(tmpfilename))
-        else:
-            resume_len = 0
+        ctx.open_mode = 'wb'
+        ctx.resume_len = 0
 
-        open_mode = 'wb'
-        if resume_len != 0:
-            if self.params.get('continuedl', True):
-                self.report_resuming_byte(resume_len)
-                request.add_header('Range', 'bytes=%d-' % resume_len)
-                open_mode = 'ab'
-            else:
-                resume_len = 0
+        if self.params.get('continuedl', True):
+            # Establish possible resume length
+            if os.path.isfile(encodeFilename(ctx.tmpfilename)):
+                ctx.resume_len = os.path.getsize(encodeFilename(ctx.tmpfilename))
 
         count = 0
         retries = self.params.get('retries', 0)
-        while count <= retries:
+
+        class SucceedDownload(Exception):
+            pass
+
+        class RetryDownload(Exception):
+            def __init__(self, source_error):
+                self.source_error = source_error
+
+        def establish_connection():
+            if ctx.resume_len != 0:
+                self.report_resuming_byte(ctx.resume_len)
+                request.add_header('Range', 'bytes=%d-' % ctx.resume_len)
+                ctx.open_mode = 'ab'
             # Establish connection
             try:
-                data = self.ydl.urlopen(request)
+                ctx.data = self.ydl.urlopen(request)
                 # When trying to resume, Content-Range HTTP header of response has to be checked
                 # to match the value of requested Range HTTP header. This is due to a webservers
                 # that don't support resuming and serve a whole file with no Content-Range
                 # set in response despite of requested Range (see
                 # https://github.com/rg3/youtube-dl/issues/6057#issuecomment-126129799)
-                if resume_len > 0:
-                    content_range = data.headers.get('Content-Range')
+                if ctx.resume_len > 0:
+                    content_range = ctx.data.headers.get('Content-Range')
                     if content_range:
                         content_range_m = re.search(r'bytes (\d+)-', content_range)
                         # Content-Range is present and matches requested Range, resume is possible
-                        if content_range_m and resume_len == int(content_range_m.group(1)):
-                            break
+                        if content_range_m and ctx.resume_len == int(content_range_m.group(1)):
+                            return
                     # Content-Range is either not present or invalid. Assuming remote webserver is
                     # trying to send the whole file, resume is not possible, so wiping the local file
                     # and performing entire redownload
                     self.report_unable_to_resume()
-                    resume_len = 0
-                    open_mode = 'wb'
-                break
+                    ctx.resume_len = 0
+                    ctx.open_mode = 'wb'
+                return
             except (compat_urllib_error.HTTPError, ) as err:
                 if (err.code < 500 or err.code >= 600) and err.code != 416:
                     # Unexpected HTTP error
@@ -86,15 +99,15 @@ class HttpFD(FileDownloader):
                     # Unable to resume (requested range not satisfiable)
                     try:
                         # Open the connection again without the range header
-                        data = self.ydl.urlopen(basic_request)
-                        content_length = data.info()['Content-Length']
+                        ctx.data = self.ydl.urlopen(basic_request)
+                        content_length = ctx.data.info()['Content-Length']
                     except (compat_urllib_error.HTTPError, ) as err:
                         if err.code < 500 or err.code >= 600:
                             raise
                     else:
                         # Examine the reported length
                         if (content_length is not None and
-                                (resume_len - 100 < int(content_length) < resume_len + 100)):
+                                (ctx.resume_len - 100 < int(content_length) < ctx.resume_len + 100)):
                             # The file had already been fully downloaded.
                             # Explanation to the above condition: in issue #175 it was revealed that
                             # YouTube sometimes adds or removes a few bytes from the end of the file,
@@ -102,152 +115,184 @@ class HttpFD(FileDownloader):
                             # I decided to implement a suggested change and consider the file
                             # completely downloaded if the file size differs less than 100 bytes from
                             # the one in the hard drive.
-                            self.report_file_already_downloaded(filename)
-                            self.try_rename(tmpfilename, filename)
+                            self.report_file_already_downloaded(ctx.filename)
+                            self.try_rename(ctx.tmpfilename, ctx.filename)
                             self._hook_progress({
-                                'filename': filename,
+                                'filename': ctx.filename,
                                 'status': 'finished',
-                                'downloaded_bytes': resume_len,
-                                'total_bytes': resume_len,
+                                'downloaded_bytes': ctx.resume_len,
+                                'total_bytes': ctx.resume_len,
                             })
-                            return True
+                            raise SucceedDownload()
                         else:
                             # The length does not match, we start the download over
                             self.report_unable_to_resume()
-                            resume_len = 0
-                            open_mode = 'wb'
-                            break
-            except socket.error as e:
-                if e.errno != errno.ECONNRESET:
+                            ctx.resume_len = 0
+                            ctx.open_mode = 'wb'
+                            return
+                raise RetryDownload(err)
+            except socket.error as err:
+                if err.errno != errno.ECONNRESET:
                     # Connection reset is no problem, just retry
                     raise
+                raise RetryDownload(err)
 
-            # Retry
-            count += 1
-            if count <= retries:
-                self.report_retry(count, retries)
+        def download():
+            data_len = ctx.data.info().get('Content-length', None)
 
-        if count > retries:
-            self.report_error('giving up after %s retries' % retries)
-            return False
+            # Range HTTP header may be ignored/unsupported by a webserver
+            # (e.g. extractor/scivee.py, extractor/bambuser.py).
+            # However, for a test we still would like to download just a piece of a file.
+            # To achieve this we limit data_len to _TEST_FILE_SIZE and manually control
+            # block size when downloading a file.
+            if is_test and (data_len is None or int(data_len) > self._TEST_FILE_SIZE):
+                data_len = self._TEST_FILE_SIZE
 
-        data_len = data.info().get('Content-length', None)
-
-        # Range HTTP header may be ignored/unsupported by a webserver
-        # (e.g. extractor/scivee.py, extractor/bambuser.py).
-        # However, for a test we still would like to download just a piece of a file.
-        # To achieve this we limit data_len to _TEST_FILE_SIZE and manually control
-        # block size when downloading a file.
-        if is_test and (data_len is None or int(data_len) > self._TEST_FILE_SIZE):
-            data_len = self._TEST_FILE_SIZE
-
-        if data_len is not None:
-            data_len = int(data_len) + resume_len
-            min_data_len = self.params.get('min_filesize')
-            max_data_len = self.params.get('max_filesize')
-            if min_data_len is not None and data_len < min_data_len:
-                self.to_screen('\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
-                return False
-            if max_data_len is not None and data_len > max_data_len:
-                self.to_screen('\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
-                return False
-
-        byte_counter = 0 + resume_len
-        block_size = self.params.get('buffersize', 1024)
-        start = time.time()
-
-        # measure time over whole while-loop, so slow_down() and best_block_size() work together properly
-        now = None  # needed for slow_down() in the first loop run
-        before = start  # start measuring
-        while True:
-
-            # Download and write
-            data_block = data.read(block_size if not is_test else min(block_size, data_len - byte_counter))
-            byte_counter += len(data_block)
-
-            # exit loop when download is finished
-            if len(data_block) == 0:
-                break
-
-            # Open destination file just in time
-            if stream is None:
-                try:
-                    (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
-                    assert stream is not None
-                    filename = self.undo_temp_name(tmpfilename)
-                    self.report_destination(filename)
-                except (OSError, IOError) as err:
-                    self.report_error('unable to open for writing: %s' % str(err))
+            if data_len is not None:
+                data_len = int(data_len) + ctx.resume_len
+                min_data_len = self.params.get('min_filesize')
+                max_data_len = self.params.get('max_filesize')
+                if min_data_len is not None and data_len < min_data_len:
+                    self.to_screen('\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
+                    return False
+                if max_data_len is not None and data_len > max_data_len:
+                    self.to_screen('\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
                     return False
 
-                if self.params.get('xattr_set_filesize', False) and data_len is not None:
+            byte_counter = 0 + ctx.resume_len
+            block_size = self.params.get('buffersize', 1024)
+            start = time.time()
+
+            # measure time over whole while-loop, so slow_down() and best_block_size() work together properly
+            now = None  # needed for slow_down() in the first loop run
+            before = start  # start measuring
+
+            def retry(e):
+                if ctx.tmpfilename != '-':
+                    ctx.stream.close()
+                ctx.stream = None
+                ctx.resume_len = os.path.getsize(encodeFilename(ctx.tmpfilename))
+                raise RetryDownload(e)
+
+            while True:
+                try:
+                    # Download and write
+                    data_block = ctx.data.read(block_size if not is_test else min(block_size, data_len - byte_counter))
+                # socket.timeout is a subclass of socket.error but may not have
+                # errno set
+                except socket.timeout as e:
+                    retry(e)
+                except socket.error as e:
+                    if e.errno not in (errno.ECONNRESET, errno.ETIMEDOUT):
+                        raise
+                    retry(e)
+
+                byte_counter += len(data_block)
+
+                # exit loop when download is finished
+                if len(data_block) == 0:
+                    break
+
+                # Open destination file just in time
+                if ctx.stream is None:
                     try:
-                        write_xattr(tmpfilename, 'user.ytdl.filesize', str(data_len).encode('utf-8'))
-                    except (XAttrUnavailableError, XAttrMetadataError) as err:
-                        self.report_error('unable to set filesize xattr: %s' % str(err))
+                        ctx.stream, ctx.tmpfilename = sanitize_open(
+                            ctx.tmpfilename, ctx.open_mode)
+                        assert ctx.stream is not None
+                        ctx.filename = self.undo_temp_name(ctx.tmpfilename)
+                        self.report_destination(ctx.filename)
+                    except (OSError, IOError) as err:
+                        self.report_error('unable to open for writing: %s' % str(err))
+                        return False
 
-            try:
-                stream.write(data_block)
-            except (IOError, OSError) as err:
+                    if self.params.get('xattr_set_filesize', False) and data_len is not None:
+                        try:
+                            write_xattr(ctx.tmpfilename, 'user.ytdl.filesize', str(data_len).encode('utf-8'))
+                        except (XAttrUnavailableError, XAttrMetadataError) as err:
+                            self.report_error('unable to set filesize xattr: %s' % str(err))
+
+                try:
+                    ctx.stream.write(data_block)
+                except (IOError, OSError) as err:
+                    self.to_stderr('\n')
+                    self.report_error('unable to write data: %s' % str(err))
+                    return False
+
+                # Apply rate limit
+                self.slow_down(start, now, byte_counter - ctx.resume_len)
+
+                # end measuring of one loop run
+                now = time.time()
+                after = now
+
+                # Adjust block size
+                if not self.params.get('noresizebuffer', False):
+                    block_size = self.best_block_size(after - before, len(data_block))
+
+                before = after
+
+                # Progress message
+                speed = self.calc_speed(start, now, byte_counter - ctx.resume_len)
+                if data_len is None:
+                    eta = None
+                else:
+                    eta = self.calc_eta(start, time.time(), data_len - ctx.resume_len, byte_counter - ctx.resume_len)
+
+                self._hook_progress({
+                    'status': 'downloading',
+                    'downloaded_bytes': byte_counter,
+                    'total_bytes': data_len,
+                    'tmpfilename': ctx.tmpfilename,
+                    'filename': ctx.filename,
+                    'eta': eta,
+                    'speed': speed,
+                    'elapsed': now - start,
+                })
+
+                if is_test and byte_counter == data_len:
+                    break
+
+            if ctx.stream is None:
                 self.to_stderr('\n')
-                self.report_error('unable to write data: %s' % str(err))
+                self.report_error('Did not get any data blocks')
                 return False
+            if ctx.tmpfilename != '-':
+                ctx.stream.close()
 
-            # Apply rate limit
-            self.slow_down(start, now, byte_counter - resume_len)
+            if data_len is not None and byte_counter != data_len:
+                err = ContentTooShortError(byte_counter, int(data_len))
+                if count <= retries:
+                    retry(err)
+                raise err
 
-            # end measuring of one loop run
-            now = time.time()
-            after = now
+            self.try_rename(ctx.tmpfilename, ctx.filename)
 
-            # Adjust block size
-            if not self.params.get('noresizebuffer', False):
-                block_size = self.best_block_size(after - before, len(data_block))
-
-            before = after
-
-            # Progress message
-            speed = self.calc_speed(start, now, byte_counter - resume_len)
-            if data_len is None:
-                eta = None
-            else:
-                eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
+            # Update file modification time
+            if self.params.get('updatetime', True):
+                info_dict['filetime'] = self.try_utime(ctx.filename, ctx.data.info().get('last-modified', None))
 
             self._hook_progress({
-                'status': 'downloading',
                 'downloaded_bytes': byte_counter,
-                'total_bytes': data_len,
-                'tmpfilename': tmpfilename,
-                'filename': filename,
-                'eta': eta,
-                'speed': speed,
-                'elapsed': now - start,
+                'total_bytes': byte_counter,
+                'filename': ctx.filename,
+                'status': 'finished',
+                'elapsed': time.time() - start,
             })
 
-            if is_test and byte_counter == data_len:
-                break
+            return True
 
-        if stream is None:
-            self.to_stderr('\n')
-            self.report_error('Did not get any data blocks')
-            return False
-        if tmpfilename != '-':
-            stream.close()
+        while count <= retries:
+            try:
+                establish_connection()
+                download()
+                return True
+            except RetryDownload as e:
+                count += 1
+                if count <= retries:
+                    self.report_retry(e.source_error, count, retries)
+                continue
+            except SucceedDownload:
+                return True
 
-        if data_len is not None and byte_counter != data_len:
-            raise ContentTooShortError(byte_counter, int(data_len))
-        self.try_rename(tmpfilename, filename)
-
-        # Update file modification time
-        if self.params.get('updatetime', True):
-            info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None))
-
-        self._hook_progress({
-            'downloaded_bytes': byte_counter,
-            'total_bytes': byte_counter,
-            'filename': filename,
-            'status': 'finished',
-            'elapsed': time.time() - start,
-        })
-
-        return True
+        self.report_error('giving up after %s retries' % retries)
+        return False

youtube_dl/extractor/abcnews.py

@@ -7,6 +7,7 @@ import time
 
 from .amp import AMPIE
 from .common import InfoExtractor
+from .youtube import YoutubeIE
 from ..compat import compat_urlparse
 
 
@@ -108,9 +109,7 @@ class AbcNewsIE(InfoExtractor):
             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)
+        youtube_url = YoutubeIE._extract_url(webpage)
 
         timestamp = None
         date_str = self._html_search_regex(
@@ -140,7 +139,7 @@ class AbcNewsIE(InfoExtractor):
         }
 
         if youtube_url:
-            entries = [entry, self.url_result(youtube_url, 'Youtube')]
+            entries = [entry, self.url_result(youtube_url, ie=YoutubeIE.ie_key())]
             return self.playlist_result(entries)
 
         return entry

youtube_dl/extractor/aliexpress.py

@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    float_or_none,
+    try_get,
+)
+
+
+class AliExpressLiveIE(InfoExtractor):
+    _VALID_URL = r'https?://live\.aliexpress\.com/live/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://live.aliexpress.com/live/2800002704436634',
+        'md5': 'e729e25d47c5e557f2630eaf99b740a5',
+        'info_dict': {
+            'id': '2800002704436634',
+            'ext': 'mp4',
+            'title': 'CASIMA7.22',
+            'thumbnail': r're:http://.*\.jpg',
+            'uploader': 'CASIMA Official Store',
+            'timestamp': 1500717600,
+            'upload_date': '20170722',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        data = self._parse_json(
+            self._search_regex(
+                r'(?s)runParams\s*=\s*({.+?})\s*;?\s*var',
+                webpage, 'runParams'),
+            video_id)
+
+        title = data['title']
+
+        formats = self._extract_m3u8_formats(
+            data['replyStreamUrl'], video_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': data.get('coverUrl'),
+            'uploader': try_get(
+                data, lambda x: x['followBar']['name'], compat_str),
+            'timestamp': float_or_none(data.get('startTimeLong'), scale=1000),
+            'formats': formats,
+        }

youtube_dl/extractor/americastestkitchen.py

@@ -0,0 +1,85 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    int_or_none,
+    try_get,
+    unified_strdate,
+)
+
+
+class AmericasTestKitchenIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.americastestkitchen.com/episode/548-summer-dinner-party',
+        'md5': 'b861c3e365ac38ad319cfd509c30577f',
+        'info_dict': {
+            'id': '1_5g5zua6e',
+            'title': 'Summer Dinner Party',
+            'ext': 'mp4',
+            'description': 'md5:858d986e73a4826979b6a5d9f8f6a1ec',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'timestamp': 1497285541,
+            'upload_date': '20170612',
+            'uploader_id': 'roger.metcalf@americastestkitchen.com',
+            'release_date': '20170617',
+            'series': "America's Test Kitchen",
+            'season_number': 17,
+            'episode': 'Summer Dinner Party',
+            'episode_number': 24,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        partner_id = self._search_regex(
+            r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
+            webpage, 'kaltura partner id')
+
+        video_data = self._parse_json(
+            self._search_regex(
+                r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>',
+                webpage, 'initial context'),
+            video_id)
+
+        ep_data = try_get(
+            video_data,
+            (lambda x: x['episodeDetail']['content']['data'],
+             lambda x: x['videoDetail']['content']['data']), dict)
+        ep_meta = ep_data.get('full_video', {})
+        external_id = ep_data.get('external_id') or ep_meta['external_id']
+
+        title = ep_data.get('title') or ep_meta.get('title')
+        description = clean_html(ep_meta.get('episode_description') or ep_data.get(
+            'description') or ep_meta.get('description'))
+        thumbnail = try_get(ep_meta, lambda x: x['photo']['image_url'])
+        release_date = unified_strdate(ep_data.get('aired_at'))
+
+        season_number = int_or_none(ep_meta.get('season_number'))
+        episode = ep_meta.get('title')
+        episode_number = int_or_none(ep_meta.get('episode_number'))
+
+        return {
+            '_type': 'url_transparent',
+            'url': 'kaltura:%s:%s' % (partner_id, external_id),
+            'ie_key': 'Kaltura',
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'release_date': release_date,
+            'series': "America's Test Kitchen",
+            'season_number': season_number,
+            'episode': episode,
+            'episode_number': episode_number,
+        }

youtube_dl/extractor/animeondemand.py

@@ -3,16 +3,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urlparse,
-    compat_str,
-)
+from ..compat import compat_str
 from ..utils import (
     determine_ext,
     extract_attributes,
     ExtractorError,
-    sanitized_Request,
     urlencode_postdata,
+    urljoin,
 )
 
 
@@ -21,6 +18,8 @@ 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'
+    # German-speaking countries of Europe
+    _GEO_COUNTRIES = ['AT', 'CH', 'DE', 'LI', 'LU']
     _TESTS = [{
         # jap, OmU
         'url': 'https://www.anime-on-demand.de/anime/161',
@@ -46,6 +45,10 @@ class AnimeOnDemandIE(InfoExtractor):
         # Full length film, non-series, ger/jap, Dub/OmU, account required
         'url': 'https://www.anime-on-demand.de/anime/185',
         'only_matching': True,
+    }, {
+        # Flash videos
+        'url': 'https://www.anime-on-demand.de/anime/12',
+        'only_matching': True,
     }]
 
     def _login(self):
@@ -72,14 +75,13 @@ class AnimeOnDemandIE(InfoExtractor):
             'post url', default=self._LOGIN_URL, group='url')
 
         if not post_url.startswith('http'):
-            post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
-
-        request = sanitized_Request(
-            post_url, urlencode_postdata(login_form))
-        request.add_header('Referer', self._LOGIN_URL)
+            post_url = urljoin(self._LOGIN_URL, post_url)
 
         response = self._download_webpage(
-            request, None, 'Logging in as %s' % username)
+            post_url, None, 'Logging in as %s' % username,
+            data=urlencode_postdata(login_form), headers={
+                'Referer': self._LOGIN_URL,
+            })
 
         if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')):
             error = self._search_regex(
@@ -120,10 +122,11 @@ class AnimeOnDemandIE(InfoExtractor):
             formats = []
 
             for input_ in re.findall(
-                    r'<input[^>]+class=["\'].*?streamstarter_html5[^>]+>', html):
+                    r'<input[^>]+class=["\'].*?streamstarter[^>]+>', html):
                 attributes = extract_attributes(input_)
+                title = attributes.get('data-dialog-header')
                 playlist_urls = []
-                for playlist_key in ('data-playlist', 'data-otherplaylist'):
+                for playlist_key in ('data-playlist', 'data-otherplaylist', 'data-stream'):
                     playlist_url = attributes.get(playlist_key)
                     if isinstance(playlist_url, compat_str) and re.match(
                             r'/?[\da-zA-Z]+', playlist_url):
@@ -147,19 +150,38 @@ class AnimeOnDemandIE(InfoExtractor):
                         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),
+                    item_id_list = []
+                    if format_id:
+                        item_id_list.append(format_id)
+                    item_id_list.append('videomaterial')
+                    playlist = self._download_json(
+                        urljoin(url, playlist_url), video_id,
+                        'Downloading %s JSON' % ' '.join(item_id_list),
                         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)
+                        }, fatal=False)
                     if not playlist:
                         continue
+                    stream_url = playlist.get('streamurl')
+                    if stream_url:
+                        rtmp = re.search(
+                            r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+/))(?P<playpath>mp[34]:.+)',
+                            stream_url)
+                        if rtmp:
+                            formats.append({
+                                'url': rtmp.group('url'),
+                                'app': rtmp.group('app'),
+                                'play_path': rtmp.group('playpath'),
+                                'page_url': url,
+                                'player_url': 'https://www.anime-on-demand.de/assets/jwplayer.flash-55abfb34080700304d49125ce9ffb4a6.swf',
+                                'rtmp_real_time': True,
+                                'format_id': 'rtmp',
+                                'ext': 'flv',
+                            })
+                            continue
                     start_video = playlist.get('startvideo', 0)
                     playlist = playlist.get('playlist')
                     if not playlist or not isinstance(playlist, list):
@@ -222,7 +244,7 @@ class AnimeOnDemandIE(InfoExtractor):
                     f.update({
                         'id': '%s-%s' % (f['id'], m.group('kind').lower()),
                         'title': m.group('title'),
-                        'url': compat_urlparse.urljoin(url, m.group('href')),
+                        'url': urljoin(url, m.group('href')),
                     })
                     entries.append(f)
 

youtube_dl/extractor/arte.py

@@ -82,7 +82,7 @@ class ArteTVBaseIE(InfoExtractor):
 
         vsr = player_info['VSR']
 
-        if not vsr and not player_info.get('VRU'):
+        if not vsr:
             raise ExtractorError(
                 'Video %s is not available' % player_info.get('VID') or video_id,
                 expected=True)

youtube_dl/extractor/bandcamp.py

@@ -242,7 +242,12 @@ class BandcampAlbumIE(InfoExtractor):
             raise ExtractorError('The page doesn\'t contain any tracks')
         # Only tracks with duration info have songs
         entries = [
-            self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
+            self.url_result(
+                compat_urlparse.urljoin(url, t_path),
+                ie=BandcampIE.ie_key(),
+                video_title=self._search_regex(
+                    r'<span\b[^>]+\bitemprop=["\']name["\'][^>]*>([^<]+)',
+                    elem_content, 'track title', fatal=False))
             for elem_content, t_path in track_elements
             if self._html_search_meta('duration', elem_content, default=None)]
 

youtube_dl/extractor/bbc.py

@@ -29,7 +29,7 @@ from ..compat import (
 class BBCCoUkIE(InfoExtractor):
     IE_NAME = 'bbc.co.uk'
     IE_DESC = 'BBC iPlayer'
-    _ID_REGEX = r'[pb][\da-z]{7}'
+    _ID_REGEX = r'[pbw][\da-z]{7}'
     _VALID_URL = r'''(?x)
                     https?://
                         (?:www\.)?bbc\.co\.uk/
@@ -37,7 +37,8 @@ class BBCCoUkIE(InfoExtractor):
                             programmes/(?!articles/)|
                             iplayer(?:/[^/]+)?/(?:episode/|playlist/)|
                             music/(?:clips|audiovideo/popular)[/#]|
-                            radio/player/
+                            radio/player/|
+                            events/[^/]+/play/[^/]+/
                         )
                         (?P<id>%s)(?!/(?:episodes|broadcasts|clips))
                     ''' % _ID_REGEX
@@ -232,6 +233,9 @@ class BBCCoUkIE(InfoExtractor):
         }, {
             'url': 'https://www.bbc.co.uk/music/audiovideo/popular#p055bc55',
             'only_matching': True,
+        }, {
+            'url': 'http://www.bbc.co.uk/programmes/w3csv1y9',
+            'only_matching': True,
         }]
 
     _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'

youtube_dl/extractor/beeg.py

@@ -9,6 +9,7 @@ from ..compat import (
 from ..utils import (
     int_or_none,
     parse_iso8601,
+    urljoin,
 )
 
 
@@ -36,9 +37,11 @@ class BeegIE(InfoExtractor):
         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',
+            r'<script[^>]+src=(["\'])(?P<url>(?:/static|(?:https?:)?//static\.beeg\.com)/cpl/\d+\.js.*?)\1',
             webpage, 'cpl', default=None, group='url')
 
+        cpl_url = urljoin(url, cpl_url)
+
         beeg_version, beeg_salt = [None] * 2
 
         if cpl_url:
@@ -54,7 +57,7 @@ class BeegIE(InfoExtractor):
                     r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg salt',
                     default=None, group='beeg_salt')
 
-        beeg_version = beeg_version or '2000'
+        beeg_version = beeg_version or '2185'
         beeg_salt = beeg_salt or 'pmweAkq8lAYKdfWcFCUj0yoVgoPlinamH5UE1CB3H'
 
         video = self._download_json(

youtube_dl/extractor/bpb.py

@@ -33,13 +33,18 @@ class BpbIE(InfoExtractor):
         title = self._html_search_regex(
             r'<h2 class="white">(.*?)</h2>', webpage, 'title')
         video_info_dicts = re.findall(
-            r"({\s*src:\s*'http://film\.bpb\.de/[^}]+})", webpage)
+            r"({\s*src\s*:\s*'https?://film\.bpb\.de/[^}]+})", webpage)
 
         formats = []
         for video_info in video_info_dicts:
-            video_info = self._parse_json(video_info, video_id, transform_source=js_to_json)
-            quality = video_info['quality']
-            video_url = video_info['src']
+            video_info = self._parse_json(
+                video_info, video_id, transform_source=js_to_json, fatal=False)
+            if not video_info:
+                continue
+            video_url = video_info.get('src')
+            if not video_url:
+                continue
+            quality = 'high' if '_high' in video_url else 'low'
             formats.append({
                 'url': video_url,
                 'preference': 10 if quality == 'high' else 0,

youtube_dl/extractor/cbc.py

@@ -200,6 +200,7 @@ class CBCWatchBaseIE(InfoExtractor):
         'media': 'http://search.yahoo.com/mrss/',
         'clearleap': 'http://www.clearleap.com/namespace/clearleap/1.0/',
     }
+    _GEO_COUNTRIES = ['CA']
 
     def _call_api(self, path, video_id):
         url = path if path.startswith('http') else self._API_BASE_URL + path
@@ -287,6 +288,11 @@ class CBCWatchBaseIE(InfoExtractor):
 class CBCWatchVideoIE(CBCWatchBaseIE):
     IE_NAME = 'cbc.ca:watch:video'
     _VALID_URL = r'https?://api-cbc\.cloud\.clearleap\.com/cloffice/client/web/play/?\?.*?\bcontentId=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
+    _TEST = {
+        # geo-restricted to Canada, bypassable
+        'url': 'https://api-cbc.cloud.clearleap.com/cloffice/client/web/play/?contentId=3c84472a-1eea-4dee-9267-2655d5055dcf&categoryId=ebc258f5-ee40-4cca-b66b-ba6bd55b7235',
+        'only_matching': True,
+    }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -323,9 +329,10 @@ class CBCWatchIE(CBCWatchBaseIE):
     IE_NAME = 'cbc.ca:watch'
     _VALID_URL = r'https?://watch\.cbc\.ca/(?:[^/]+/)+(?P<id>[0-9a-f-]+)'
     _TESTS = [{
+        # geo-restricted to Canada, bypassable
         'url': 'http://watch.cbc.ca/doc-zone/season-6/customer-disservice/38e815a-009e3ab12e4',
         'info_dict': {
-            'id': '38e815a-009e3ab12e4',
+            'id': '9673749a-5e77-484c-8b62-a1092a6b5168',
             'ext': 'mp4',
             'title': 'Customer (Dis)Service',
             'description': 'md5:8bdd6913a0fe03d4b2a17ebe169c7c87',
@@ -337,8 +344,8 @@ class CBCWatchIE(CBCWatchBaseIE):
             'skip_download': True,
             'format': 'bestvideo',
         },
-        'skip': 'Geo-restricted to Canada',
     }, {
+        # geo-restricted to Canada, bypassable
         'url': 'http://watch.cbc.ca/arthur/all/1ed4b385-cd84-49cf-95f0-80f004680057',
         'info_dict': {
             'id': '1ed4b385-cd84-49cf-95f0-80f004680057',
@@ -346,7 +353,6 @@ class CBCWatchIE(CBCWatchBaseIE):
             'description': 'Arthur, the sweetest 8-year-old aardvark, and his pals solve all kinds of problems with humour, kindness and teamwork.',
         },
         'playlist_mincount': 30,
-        'skip': 'Geo-restricted to Canada',
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/cda.py

@@ -124,7 +124,7 @@ class CDAIE(InfoExtractor):
         }
 
         def extract_format(page, version):
-            json_str = self._search_regex(
+            json_str = self._html_search_regex(
                 r'player_data=(\\?["\'])(?P<player_data>.+?)\1', page,
                 '%s player_json' % version, fatal=False, group='player_data')
             if not json_str:

youtube_dl/extractor/charlierose.py

@@ -5,7 +5,7 @@ from ..utils import remove_end
 
 
 class CharlieRoseIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?charlierose\.com/video(?:s|/player)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?charlierose\.com/(?:video|episode)(?:s|/player)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://charlierose.com/videos/27996',
         'md5': 'fda41d49e67d4ce7c2411fd2c4702e09',
@@ -24,6 +24,9 @@ class CharlieRoseIE(InfoExtractor):
     }, {
         'url': 'https://charlierose.com/videos/27996',
         'only_matching': True,
+    }, {
+        'url': 'https://charlierose.com/episodes/30887?autoplay=true',
+        'only_matching': True,
     }]
 
     _PLAYER_BASE = 'https://charlierose.com/video/player/%s'

youtube_dl/extractor/chilloutzone.py

@@ -5,6 +5,7 @@ import base64
 import json
 
 from .common import InfoExtractor
+from .youtube import YoutubeIE
 from ..utils import (
     clean_html,
     ExtractorError
@@ -70,11 +71,9 @@ class ChilloutzoneIE(InfoExtractor):
 
         # If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
         if native_platform is None:
-            youtube_url = self._html_search_regex(
-                r'<iframe.* src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
-                webpage, 'fallback video URL', default=None)
-            if youtube_url is not None:
-                return self.url_result(youtube_url, ie='Youtube')
+            youtube_url = YoutubeIE._extract_url(webpage)
+            if youtube_url:
+                return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
 
         # Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
         # the own CDN

youtube_dl/extractor/common.py

@@ -27,6 +27,7 @@ from ..compat import (
     compat_urllib_parse_urlencode,
     compat_urllib_request,
     compat_urlparse,
+    compat_xml_parse_error,
 )
 from ..downloader.f4m import remove_encrypted_media
 from ..utils import (
@@ -646,15 +647,29 @@ 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, data=None, headers={}, query={}):
+                      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, data=data, headers=headers, query=query)
+            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
+        return self._parse_xml(
+            xml_string, video_id, transform_source=transform_source,
+            fatal=fatal)
+
+    def _parse_xml(self, xml_string, video_id, transform_source=None, fatal=True):
         if transform_source:
             xml_string = transform_source(xml_string)
-        return compat_etree_fromstring(xml_string.encode('utf-8'))
+        try:
+            return compat_etree_fromstring(xml_string.encode('utf-8'))
+        except compat_xml_parse_error as ve:
+            errmsg = '%s: Failed to parse XML ' % video_id
+            if fatal:
+                raise ExtractorError(errmsg, cause=ve)
+            else:
+                self.report_warning(errmsg + str(ve))
 
     def _download_json(self, url_or_request, video_id,
                        note='Downloading JSON metadata',
@@ -2123,11 +2138,11 @@ class InfoExtractor(object):
                 formats = self._extract_m3u8_formats(
                     full_url, video_id, ext='mp4',
                     entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id,
-                    preference=preference)
+                    preference=preference, fatal=False)
             elif ext == 'mpd':
                 is_plain_url = False
                 formats = self._extract_mpd_formats(
-                    full_url, video_id, mpd_id=mpd_id)
+                    full_url, video_id, mpd_id=mpd_id, fatal=False)
             else:
                 is_plain_url = True
                 formats = [{
@@ -2169,6 +2184,12 @@ class InfoExtractor(object):
                     f = parse_content_type(source_attributes.get('type'))
                     is_plain_url, formats = _media_formats(src, media_type, f)
                     if is_plain_url:
+                        # res attribute is not standard but seen several times
+                        # in the wild
+                        f.update({
+                            'height': int_or_none(source_attributes.get('res')),
+                            'format_id': source_attributes.get('label'),
+                        })
                         f.update(formats[0])
                         media_info['formats'].append(f)
                     else:
@@ -2428,10 +2449,12 @@ class InfoExtractor(object):
                 self._downloader.report_warning(msg)
         return res
 
-    def _set_cookie(self, domain, name, value, expire_time=None):
+    def _set_cookie(self, domain, name, value, expire_time=None, port=None,
+                    path='/', secure=False, discard=False, rest={}, **kwargs):
         cookie = compat_cookiejar.Cookie(
-            0, name, value, None, None, domain, None,
-            None, '/', True, False, expire_time, '', None, None, None)
+            0, name, value, port, port is not None, domain, True,
+            domain.startswith('.'), path, True, secure, expire_time,
+            discard, None, None, rest)
         self._downloader.cookiejar.set_cookie(cookie)
 
     def _get_cookies(self, url):

youtube_dl/extractor/condenast.py

@@ -116,16 +116,16 @@ class CondeNastIE(InfoExtractor):
         entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
         return self.playlist_result(entries, playlist_title=title)
 
-    def _extract_video_params(self, webpage):
-        query = {}
-        params = self._search_regex(
-            r'(?s)var params = {(.+?)}[;,]', webpage, 'player params', default=None)
-        if params:
-            query.update({
-                'videoId': self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id'),
-                'playerId': self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id'),
-                'target': self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target'),
-            })
+    def _extract_video_params(self, webpage, display_id):
+        query = self._parse_json(
+            self._search_regex(
+                r'(?s)var\s+params\s*=\s*({.+?})[;,]', webpage, 'player params',
+                default='{}'),
+            display_id, transform_source=js_to_json, fatal=False)
+        if query:
+            query['videoId'] = self._search_regex(
+                r'(?:data-video-id=|currentVideoId\s*=\s*)["\']([\da-f]+)',
+                webpage, 'video id', default=None)
         else:
             params = extract_attributes(self._search_regex(
                 r'(<[^>]+data-js="video-player"[^>]+>)',
@@ -141,17 +141,27 @@ class CondeNastIE(InfoExtractor):
         video_id = params['videoId']
 
         video_info = None
-        if params.get('playerId'):
-            info_page = self._download_json(
-                'http://player.cnevids.com/player/video.js',
-                video_id, 'Downloading video info', fatal=False, query=params)
-            if info_page:
-                video_info = info_page.get('video')
-            if not video_info:
-                info_page = self._download_webpage(
-                    'http://player.cnevids.com/player/loader.js',
-                    video_id, 'Downloading loader info', query=params)
-        else:
+
+        # New API path
+        query = params.copy()
+        query['embedType'] = 'inline'
+        info_page = self._download_json(
+            'http://player.cnevids.com/embed-api.json', video_id,
+            'Downloading embed info', fatal=False, query=query)
+
+        # Old fallbacks
+        if not info_page:
+            if params.get('playerId'):
+                info_page = self._download_json(
+                    'http://player.cnevids.com/player/video.js', video_id,
+                    'Downloading video info', fatal=False, query=params)
+        if info_page:
+            video_info = info_page.get('video')
+        if not video_info:
+            info_page = self._download_webpage(
+                'http://player.cnevids.com/player/loader.js',
+                video_id, 'Downloading loader info', query=params)
+        if not video_info:
             info_page = self._download_webpage(
                 'https://player.cnevids.com/inline/video/%s.js' % video_id,
                 video_id, 'Downloading inline info', query={
@@ -215,7 +225,7 @@ class CondeNastIE(InfoExtractor):
         if url_type == 'series':
             return self._extract_series(url, webpage)
         else:
-            params = self._extract_video_params(webpage)
+            params = self._extract_video_params(webpage, display_id)
             info = self._search_json_ld(
                 webpage, display_id, fatal=False)
             info.update(self._extract_video(params))

youtube_dl/extractor/cracked.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from .youtube import YoutubeIE
 from ..utils import (
     parse_iso8601,
     str_to_int,
@@ -41,11 +42,9 @@ class CrackedIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        youtube_url = self._search_regex(
-            r'<iframe[^>]+src="((?:https?:)?//www\.youtube\.com/embed/[^"]+)"',
-            webpage, 'youtube url', default=None)
+        youtube_url = YoutubeIE._extract_url(webpage)
         if youtube_url:
-            return self.url_result(youtube_url, 'Youtube')
+            return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
 
         video_url = self._html_search_regex(
             [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'],

youtube_dl/extractor/dailymotion.py

@@ -325,7 +325,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
 
 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
     IE_NAME = 'dailymotion:playlist'
-    _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
+    _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>[^/?#&]+)'
     _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
     _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
     _TESTS = [{

youtube_dl/extractor/extractors.py

@@ -39,12 +39,14 @@ from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
 from .amcnetworks import AMCNetworksIE
+from .americastestkitchen import AmericasTestKitchenIE
 from .animeondemand import AnimeOnDemandIE
 from .anitube import AnitubeIE
 from .anvato import AnvatoIE
 from .anysex import AnySexIE
 from .aol import AolIE
 from .allocine import AllocineIE
+from .aliexpress import AliExpressLiveIE
 from .aparat import AparatIE
 from .appleconnect import AppleConnectIE
 from .appletrailers import (
@@ -481,6 +483,7 @@ from .jove import JoveIE
 from .joj import JojIE
 from .jwplatform import JWPlatformIE
 from .jpopsukitv import JpopsukiIE
+from .kakao import KakaoIE
 from .kaltura import KalturaIE
 from .kamcord import KamcordIE
 from .kanalplay import KanalPlayIE
@@ -509,6 +512,7 @@ from .la7 import LA7IE
 from .laola1tv import (
     Laola1TvEmbedIE,
     Laola1TvIE,
+    ITTFIE,
 )
 from .lci import LCIIE
 from .lcp import (
@@ -536,7 +540,10 @@ from .limelight import (
     LimelightChannelListIE,
 )
 from .litv import LiTVIE
-from .liveleak import LiveLeakIE
+from .liveleak import (
+    LiveLeakIE,
+    LiveLeakEmbedIE,
+)
 from .livestream import (
     LivestreamIE,
     LivestreamOriginalIE,
@@ -559,6 +566,7 @@ from .mangomolo import (
     MangomoloVideoIE,
     MangomoloLiveIE,
 )
+from .manyvids import ManyVidsIE
 from .matchtv import MatchTVIE
 from .mdr import MDRIE
 from .mediaset import MediasetIE
@@ -762,6 +770,7 @@ from .ora import OraTVIE
 from .orf import (
     ORFTVthekIE,
     ORFFM4IE,
+    ORFFM4StoryIE,
     ORFOE1IE,
     ORFIPTVIE,
 )
@@ -801,6 +810,7 @@ from .polskieradio import (
     PolskieRadioIE,
     PolskieRadioCategoryIE,
 )
+from .popcorntv import PopcornTVIE
 from .porn91 import Porn91IE
 from .porncom import PornComIE
 from .pornflip import PornFlipIE
@@ -893,6 +903,7 @@ from .rutube import (
     RutubeEmbedIE,
     RutubeMovieIE,
     RutubePersonIE,
+    RutubePlaylistIE,
 )
 from .rutv import RUTVIE
 from .ruutu import RuutuIE

youtube_dl/extractor/fox.py

@@ -3,56 +3,99 @@ from __future__ import unicode_literals
 
 from .adobepass import AdobePassIE
 from ..utils import (
-    smuggle_url,
-    update_url_query,
+    int_or_none,
+    parse_age_limit,
+    parse_duration,
+    try_get,
+    unified_timestamp,
 )
 
 
 class FOXIE(AdobePassIE):
-    _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.fox.com/watch/255180355939/7684182528',
+    _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)'
+    _TESTS = [{
+        # clip
+        'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
         'md5': 'ebd296fcc41dd4b19f8115d8461a3165',
         'info_dict': {
-            'id': '255180355939',
+            'id': '4b765a60490325103ea69888fb2bd4e8',
             'ext': 'mp4',
-            'title': 'Official Trailer: Gotham',
-            'description': 'Tracing the rise of the great DC Comics Super-Villains and vigilantes, Gotham reveals an entirely new chapter that has never been told.',
-            'duration': 129,
-            'timestamp': 1400020798,
-            'upload_date': '20140513',
-            'uploader': 'NEWA-FNG-FOXCOM',
+            'title': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
+            'description': 'md5:549cd9c70d413adb32ce2a779b53b486',
+            'duration': 102,
+            'timestamp': 1504291893,
+            'upload_date': '20170901',
+            'creator': 'FOX',
+            'series': 'Gotham',
         },
-        'add_ie': ['ThePlatform'],
-    }
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # episode, geo-restricted
+        'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/',
+        'only_matching': True,
+    }, {
+        # episode, geo-restricted, tv provided required
+        'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
 
-        settings = self._parse_json(self._search_regex(
-            r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
-            webpage, 'drupal settings'), video_id)
-        fox_pdk_player = settings['fox_pdk_player']
-        release_url = fox_pdk_player['release_url']
-        query = {
-            'mbr': 'true',
-            'switch': 'http'
-        }
-        if fox_pdk_player.get('access') == 'locked':
-            ap_p = settings['foxAdobePassProvider']
-            rating = ap_p.get('videoRating')
-            if rating == 'n/a':
-                rating = None
-            resource = self._get_mvpd_resource('fbc-fox', None, ap_p['videoGUID'], rating)
-            query['auth'] = self._extract_mvpd_auth(url, video_id, 'fbc-fox', resource)
+        video = self._download_json(
+            'https://api.fox.com/fbc-content/v1_4/video/%s' % video_id,
+            video_id, headers={
+                'apikey': 'abdcbed02c124d393b39e818a4312055',
+                'Content-Type': 'application/json',
+                'Referer': url,
+            })
 
-        info = self._search_json_ld(webpage, video_id, fatal=False)
-        info.update({
-            '_type': 'url_transparent',
-            'ie_key': 'ThePlatform',
-            'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}),
+        title = video['name']
+
+        m3u8_url = self._download_json(
+            video['videoRelease']['url'], video_id)['playURL']
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        description = video.get('description')
+        duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
+            video.get('duration')) or parse_duration(video.get('duration'))
+        timestamp = unified_timestamp(video.get('datePublished'))
+        age_limit = parse_age_limit(video.get('contentRating'))
+
+        data = try_get(
+            video, lambda x: x['trackingData']['properties'], dict) or {}
+
+        creator = data.get('brand') or data.get('network') or video.get('network')
+
+        series = video.get('seriesName') or data.get(
+            'seriesName') or data.get('show')
+        season_number = int_or_none(video.get('seasonNumber'))
+        episode = video.get('name')
+        episode_number = int_or_none(video.get('episodeNumber'))
+        release_year = int_or_none(video.get('releaseYear'))
+
+        if data.get('authRequired'):
+            # TODO: AP
+            pass
+
+        return {
             'id': video_id,
-        })
-
-        return info
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'timestamp': timestamp,
+            'age_limit': age_limit,
+            'creator': creator,
+            'series': series,
+            'season_number': season_number,
+            'episode': episode,
+            'episode_number': episode_number,
+            'release_year': release_year,
+            'formats': formats,
+        }

youtube_dl/extractor/generic.py

@@ -1519,14 +1519,27 @@ class GenericIE(InfoExtractor):
         # LiveLeak embed
         {
             'url': 'http://www.wykop.pl/link/3088787/',
-            'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
+            'md5': '7619da8c820e835bef21a1efa2a0fc71',
             'info_dict': {
                 'id': '874_1459135191',
                 'ext': 'mp4',
                 'title': 'Man shows poor quality of new apartment building',
                 'description': 'The wall is like a sand pile.',
                 'uploader': 'Lake8737',
-            }
+            },
+            'add_ie': [LiveLeakIE.ie_key()],
+        },
+        # Another LiveLeak embed pattern (#13336)
+        {
+            'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
+            'info_dict': {
+                'id': '2eb_1496309988',
+                'ext': 'mp4',
+                'title': 'Thief robs place where everyone was armed',
+                'description': 'md5:694d73ee79e535953cf2488562288eee',
+                'uploader': 'brazilwtf',
+            },
+            'add_ie': [LiveLeakIE.ie_key()],
         },
         # Duplicated embedded video URLs
         {
@@ -1866,6 +1879,15 @@ class GenericIE(InfoExtractor):
                 'title': 'Building A Business Online: Principal Chairs Q & A',
             },
         },
+        {
+            # multiple HTML5 videos on one page
+            'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
+            'info_dict': {
+                'id': 'keyscenarios',
+                'title': 'Rescue Kit 14 Free Edition - Getting started',
+            },
+            'playlist_count': 4,
+        }
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject
@@ -2230,36 +2252,11 @@ class GenericIE(InfoExtractor):
         if vid_me_embed_url is not None:
             return self.url_result(vid_me_embed_url, 'Vidme')
 
-        # Look for embedded YouTube player
-        matches = re.findall(r'''(?x)
-            (?:
-                <iframe[^>]+?src=|
-                data-video-url=|
-                <embed[^>]+?src=|
-                embedSWF\(?:\s*|
-                <object[^>]+data=|
-                new\s+SWFObject\(
-            )
-            (["\'])
-                (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
-                (?:embed|v|p)/.+?)
-            \1''', webpage)
-        if matches:
+        # Look for YouTube embeds
+        youtube_urls = YoutubeIE._extract_urls(webpage)
+        if youtube_urls:
             return self.playlist_from_matches(
-                matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
-
-        # Look for lazyYT YouTube embed
-        matches = re.findall(
-            r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
-        if matches:
-            return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
-
-        # Look for Wordpress "YouTube Video Importer" plugin
-        matches = re.findall(r'''(?x)<div[^>]+
-            class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
-            data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
-        if matches:
-            return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
+                youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
 
         matches = DailymotionIE._extract_urls(webpage)
         if matches:
@@ -2757,9 +2754,9 @@ class GenericIE(InfoExtractor):
                 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
 
         # Look for LiveLeak embeds
-        liveleak_url = LiveLeakIE._extract_url(webpage)
-        if liveleak_url:
-            return self.url_result(liveleak_url, 'LiveLeak')
+        liveleak_urls = LiveLeakIE._extract_urls(webpage)
+        if liveleak_urls:
+            return self.playlist_from_matches(liveleak_urls, video_id, video_title)
 
         # Look for 3Q SDN embeds
         threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
@@ -2858,22 +2855,23 @@ class GenericIE(InfoExtractor):
                     merged[k] = v
             return merged
 
-        # Looking for http://schema.org/VideoObject
-        json_ld = self._search_json_ld(
-            webpage, video_id, default={}, expected_type='VideoObject')
-        if json_ld.get('url'):
-            return merge_dicts(json_ld, info_dict)
-
         # Look for HTML5 media
         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
         if entries:
-            for entry in entries:
-                entry.update({
+            if len(entries) == 1:
+                entries[0].update({
                     'id': video_id,
                     'title': video_title,
                 })
+            else:
+                for num, entry in enumerate(entries, start=1):
+                    entry.update({
+                        'id': '%s-%s' % (video_id, num),
+                        'title': '%s (%d)' % (video_title, num),
+                    })
+            for entry in entries:
                 self._sort_formats(entry['formats'])
-            return self.playlist_result(entries)
+            return self.playlist_result(entries, video_id, video_title)
 
         jwplayer_data = self._find_jwplayer_data(
             webpage, video_id, transform_source=js_to_json)
@@ -2882,6 +2880,12 @@ class GenericIE(InfoExtractor):
                 jwplayer_data, video_id, require_title=False, base_url=url)
             return merge_dicts(info, info_dict)
 
+        # Looking for http://schema.org/VideoObject
+        json_ld = self._search_json_ld(
+            webpage, video_id, default={}, expected_type='VideoObject')
+        if json_ld.get('url'):
+            return merge_dicts(json_ld, info_dict)
+
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True

youtube_dl/extractor/googledrive.py

@@ -4,26 +4,61 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     ExtractorError,
     int_or_none,
     lowercase_escape,
+    update_url_query,
 )
 
 
 class GoogleDriveIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28,})'
+    _VALID_URL = r'''(?x)
+                        https?://
+                            (?:
+                                (?:docs|drive)\.google\.com/
+                                (?:
+                                    (?:uc|open)\?.*?id=|
+                                    file/d/
+                                )|
+                                video\.google\.com/get_player\?.*?docid=
+                            )
+                            (?P<id>[a-zA-Z0-9_-]{28,})
+                    '''
     _TESTS = [{
         'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
-        'md5': 'd109872761f7e7ecf353fa108c0dbe1e',
+        'md5': '5c602afbbf2c1db91831f5d82f678554',
         'info_dict': {
             'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
             'ext': 'mp4',
             'title': 'Big Buck Bunny.mp4',
             'duration': 45,
         }
+    }, {
+        # video can't be watched anonymously due to view count limit reached,
+        # but can be downloaded (see https://github.com/rg3/youtube-dl/issues/14046)
+        'url': 'https://drive.google.com/file/d/0B-vUyvmDLdWDcEt4WjBqcmI2XzQ/view',
+        'md5': 'bfbd670d03a470bb1e6d4a257adec12e',
+        'info_dict': {
+            'id': '0B-vUyvmDLdWDcEt4WjBqcmI2XzQ',
+            'ext': 'mp4',
+            'title': 'Annabelle Creation (2017)- Z.V1 [TH].MP4',
+        }
     }, {
         # video id is longer than 28 characters
         'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit',
+        'info_dict': {
+            'id': '1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ',
+            'ext': 'mp4',
+            'title': 'Andreea Banica feat Smiley - Hooky Song (Official Video).mp4',
+            'duration': 189,
+        },
+        'only_matching': True,
+    }, {
+        'url': 'https://drive.google.com/open?id=0B2fjwgkl1A_CX083Tkowdmt6d28',
+        'only_matching': True,
+    }, {
+        'url': 'https://drive.google.com/uc?id=0B2fjwgkl1A_CX083Tkowdmt6d28',
         'only_matching': True,
     }]
     _FORMATS_EXT = {
@@ -44,6 +79,13 @@ class GoogleDriveIE(InfoExtractor):
         '46': 'webm',
         '59': 'mp4',
     }
+    _BASE_URL_CAPTIONS = 'https://drive.google.com/timedtext'
+    _CAPTIONS_ENTRY_TAG = {
+        'subtitles': 'track',
+        'automatic_captions': 'target',
+    }
+    _caption_formats_ext = []
+    _captions_xml = None
 
     @staticmethod
     def _extract_url(webpage):
@@ -53,54 +95,183 @@ class GoogleDriveIE(InfoExtractor):
         if mobj:
             return 'https://drive.google.com/file/d/%s' % mobj.group('id')
 
+    def _download_subtitles_xml(self, video_id, subtitles_id, hl):
+        if self._captions_xml:
+            return
+        self._captions_xml = self._download_xml(
+            self._BASE_URL_CAPTIONS, video_id, query={
+                'id': video_id,
+                'vid': subtitles_id,
+                'hl': hl,
+                'v': video_id,
+                'type': 'list',
+                'tlangs': '1',
+                'fmts': '1',
+                'vssids': '1',
+            }, note='Downloading subtitles XML',
+            errnote='Unable to download subtitles XML', fatal=False)
+        if self._captions_xml:
+            for f in self._captions_xml.findall('format'):
+                if f.attrib.get('fmt_code') and not f.attrib.get('default'):
+                    self._caption_formats_ext.append(f.attrib['fmt_code'])
+
+    def _get_captions_by_type(self, video_id, subtitles_id, caption_type,
+                              origin_lang_code=None):
+        if not subtitles_id or not caption_type:
+            return
+        captions = {}
+        for caption_entry in self._captions_xml.findall(
+                self._CAPTIONS_ENTRY_TAG[caption_type]):
+            caption_lang_code = caption_entry.attrib.get('lang_code')
+            if not caption_lang_code:
+                continue
+            caption_format_data = []
+            for caption_format in self._caption_formats_ext:
+                query = {
+                    'vid': subtitles_id,
+                    'v': video_id,
+                    'fmt': caption_format,
+                    'lang': (caption_lang_code if origin_lang_code is None
+                             else origin_lang_code),
+                    'type': 'track',
+                    'name': '',
+                    'kind': '',
+                }
+                if origin_lang_code is not None:
+                    query.update({'tlang': caption_lang_code})
+                caption_format_data.append({
+                    'url': update_url_query(self._BASE_URL_CAPTIONS, query),
+                    'ext': caption_format,
+                })
+            captions[caption_lang_code] = caption_format_data
+        return captions
+
+    def _get_subtitles(self, video_id, subtitles_id, hl):
+        if not subtitles_id or not hl:
+            return
+        self._download_subtitles_xml(video_id, subtitles_id, hl)
+        if not self._captions_xml:
+            return
+        return self._get_captions_by_type(video_id, subtitles_id, 'subtitles')
+
+    def _get_automatic_captions(self, video_id, subtitles_id, hl):
+        if not subtitles_id or not hl:
+            return
+        self._download_subtitles_xml(video_id, subtitles_id, hl)
+        if not self._captions_xml:
+            return
+        track = self._captions_xml.find('track')
+        if track is None:
+            return
+        origin_lang_code = track.attrib.get('lang_code')
+        if not origin_lang_code:
+            return
+        return self._get_captions_by_type(
+            video_id, subtitles_id, 'automatic_captions', origin_lang_code)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(
             'http://docs.google.com/file/d/%s' % video_id, video_id)
 
-        reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
-        if reason:
-            raise ExtractorError(reason)
-
-        title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title')
+        title = self._search_regex(
+            r'"title"\s*,\s*"([^"]+)', webpage, 'title',
+            default=None) or self._og_search_title(webpage)
         duration = int_or_none(self._search_regex(
-            r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', default=None))
-        fmt_stream_map = self._search_regex(
-            r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, 'fmt stream map').split(',')
-        fmt_list = self._search_regex(r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',')
-
-        resolutions = {}
-        for fmt in fmt_list:
-            mobj = re.search(
-                r'^(?P<format_id>\d+)/(?P<width>\d+)[xX](?P<height>\d+)', fmt)
-            if mobj:
-                resolutions[mobj.group('format_id')] = (
-                    int(mobj.group('width')), int(mobj.group('height')))
+            r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds',
+            default=None))
 
         formats = []
-        for fmt_stream in fmt_stream_map:
-            fmt_stream_split = fmt_stream.split('|')
-            if len(fmt_stream_split) < 2:
-                continue
-            format_id, format_url = fmt_stream_split[:2]
-            f = {
-                'url': lowercase_escape(format_url),
-                'format_id': format_id,
-                'ext': self._FORMATS_EXT[format_id],
-            }
-            resolution = resolutions.get(format_id)
-            if resolution:
-                f.update({
-                    'width': resolution[0],
-                    'height': resolution[1],
+        fmt_stream_map = self._search_regex(
+            r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage,
+            'fmt stream map', default='').split(',')
+        fmt_list = self._search_regex(
+            r'"fmt_list"\s*,\s*"([^"]+)', webpage,
+            'fmt_list', default='').split(',')
+        if fmt_stream_map and fmt_list:
+            resolutions = {}
+            for fmt in fmt_list:
+                mobj = re.search(
+                    r'^(?P<format_id>\d+)/(?P<width>\d+)[xX](?P<height>\d+)', fmt)
+                if mobj:
+                    resolutions[mobj.group('format_id')] = (
+                        int(mobj.group('width')), int(mobj.group('height')))
+
+            for fmt_stream in fmt_stream_map:
+                fmt_stream_split = fmt_stream.split('|')
+                if len(fmt_stream_split) < 2:
+                    continue
+                format_id, format_url = fmt_stream_split[:2]
+                f = {
+                    'url': lowercase_escape(format_url),
+                    'format_id': format_id,
+                    'ext': self._FORMATS_EXT[format_id],
+                }
+                resolution = resolutions.get(format_id)
+                if resolution:
+                    f.update({
+                        'width': resolution[0],
+                        'height': resolution[1],
+                    })
+                formats.append(f)
+
+        source_url = update_url_query(
+            'https://drive.google.com/uc', {
+                'id': video_id,
+                'export': 'download',
+            })
+        urlh = self._request_webpage(
+            source_url, video_id, note='Requesting source file',
+            errnote='Unable to request source file', fatal=False)
+        if urlh:
+            def add_source_format(src_url):
+                formats.append({
+                    'url': src_url,
+                    'ext': determine_ext(title, 'mp4').lower(),
+                    'format_id': 'source',
+                    'quality': 1,
                 })
-            formats.append(f)
+            if urlh.headers.get('Content-Disposition'):
+                add_source_format(source_url)
+            else:
+                confirmation_webpage = self._webpage_read_content(
+                    urlh, url, video_id, note='Downloading confirmation page',
+                    errnote='Unable to confirm download', fatal=False)
+                if confirmation_webpage:
+                    confirm = self._search_regex(
+                        r'confirm=([^&"\']+)', confirmation_webpage,
+                        'confirmation code', fatal=False)
+                    if confirm:
+                        add_source_format(update_url_query(source_url, {
+                            'confirm': confirm,
+                        }))
+
+        if not formats:
+            reason = self._search_regex(
+                r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
+            if reason:
+                raise ExtractorError(reason, expected=True)
+
         self._sort_formats(formats)
 
+        hl = self._search_regex(
+            r'"hl"\s*,\s*"([^"]+)', webpage, 'hl', default=None)
+        subtitles_id = None
+        ttsurl = self._search_regex(
+            r'"ttsurl"\s*,\s*"([^"]+)', webpage, 'ttsurl', default=None)
+        if ttsurl:
+            # the video Id for subtitles will be the last value in the ttsurl
+            # query string
+            subtitles_id = ttsurl.encode('utf-8').decode(
+                'unicode_escape').split('=')[-1]
+
         return {
             'id': video_id,
             'title': title,
             'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'duration': duration,
             'formats': formats,
+            'subtitles': self.extract_subtitles(video_id, subtitles_id, hl),
+            'automatic_captions': self.extract_automatic_captions(
+                video_id, subtitles_id, hl),
         }

youtube_dl/extractor/heise.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from .youtube import YoutubeIE
 from ..utils import (
     determine_ext,
     int_or_none,
@@ -25,6 +26,22 @@ class HeiseIE(InfoExtractor):
             'description': 'md5:c934cbfb326c669c2bcabcbe3d3fcd20',
             'thumbnail': r're:^https?://.*/gallery/$',
         }
+    }, {
+        # YouTube embed
+        'url': 'http://www.heise.de/newsticker/meldung/Netflix-In-20-Jahren-vom-Videoverleih-zum-TV-Revolutionaer-3814130.html',
+        'md5': 'e403d2b43fea8e405e88e3f8623909f1',
+        'info_dict': {
+            'id': '6kmWbXleKW4',
+            'ext': 'mp4',
+            'title': 'NEU IM SEPTEMBER | Netflix',
+            'description': 'md5:2131f3c7525e540d5fd841de938bd452',
+            'upload_date': '20170830',
+            'uploader': 'Netflix Deutschland, Österreich und Schweiz',
+            'uploader_id': 'netflixdach',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.heise.de/ct/artikel/c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2403911.html',
         'only_matching': True,
@@ -40,6 +57,16 @@ class HeiseIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
+        title = self._html_search_meta('fulltitle', webpage, default=None)
+        if not title or title == "c't":
+            title = self._search_regex(
+                r'<div[^>]+class="videoplayerjw"[^>]+data-title="([^"]+)"',
+                webpage, 'title')
+
+        yt_urls = YoutubeIE._extract_urls(webpage)
+        if yt_urls:
+            return self.playlist_from_matches(yt_urls, video_id, title, ie=YoutubeIE.ie_key())
+
         container_id = self._search_regex(
             r'<div class="videoplayerjw"[^>]+data-container="([0-9]+)"',
             webpage, 'container ID')
@@ -47,12 +74,6 @@ class HeiseIE(InfoExtractor):
             r'<div class="videoplayerjw"[^>]+data-sequenz="([0-9]+)"',
             webpage, 'sequenz ID')
 
-        title = self._html_search_meta('fulltitle', webpage, default=None)
-        if not title or title == "c't":
-            title = self._search_regex(
-                r'<div[^>]+class="videoplayerjw"[^>]+data-title="([^"]+)"',
-                webpage, 'title')
-
         doc = self._download_xml(
             'http://www.heise.de/videout/feed', video_id, query={
                 'container': container_id,

youtube_dl/extractor/kakao.py

@@ -0,0 +1,149 @@
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    unified_timestamp,
+    update_url_query,
+)
+
+
+class KakaoIE(InfoExtractor):
+    _VALID_URL = r'https?://tv\.kakao\.com/channel/(?P<channel>\d+)/cliplink/(?P<id>\d+)'
+    _API_BASE = 'http://tv.kakao.com/api/v1/ft/cliplinks'
+
+    _TESTS = [{
+        'url': 'http://tv.kakao.com/channel/2671005/cliplink/301965083',
+        'md5': '702b2fbdeb51ad82f5c904e8c0766340',
+        'info_dict': {
+            'id': '301965083',
+            'ext': 'mp4',
+            'title': '乃木坂46 バナナマン 「3期生紹介コーナーが始動！顔高低差GPも！」 『乃木坂工事中』',
+            'uploader_id': 2671005,
+            'uploader': '그랑그랑이',
+            'timestamp': 1488160199,
+            'upload_date': '20170227',
+        }
+    }, {
+        'url': 'http://tv.kakao.com/channel/2653210/cliplink/300103180',
+        'md5': 'a8917742069a4dd442516b86e7d66529',
+        'info_dict': {
+            'id': '300103180',
+            'ext': 'mp4',
+            'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
+            'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
+            'uploader_id': 2653210,
+            'uploader': '쇼 음악중심',
+            'timestamp': 1485684628,
+            'upload_date': '20170129',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        player_header = {
+            'Referer': update_url_query(
+                'http://tv.kakao.com/embed/player/cliplink/%s' % video_id, {
+                    'service': 'kakao_tv',
+                    'autoplay': '1',
+                    'profile': 'HIGH',
+                    'wmode': 'transparent',
+                })
+        }
+
+        QUERY_COMMON = {
+            'player': 'monet_html5',
+            'referer': url,
+            'uuid': '',
+            'service': 'kakao_tv',
+            'section': '',
+            'dteType': 'PC',
+        }
+
+        query = QUERY_COMMON.copy()
+        query['fields'] = 'clipLink,clip,channel,hasPlusFriend,-service,-tagList'
+        impress = self._download_json(
+            '%s/%s/impress' % (self._API_BASE, video_id),
+            video_id, 'Downloading video info',
+            query=query, headers=player_header)
+
+        clip_link = impress['clipLink']
+        clip = clip_link['clip']
+
+        title = clip.get('title') or clip_link.get('displayTitle')
+
+        tid = impress.get('tid', '')
+
+        query = QUERY_COMMON.copy()
+        query.update({
+            'tid': tid,
+            'profile': 'HIGH',
+        })
+        raw = self._download_json(
+            '%s/%s/raw' % (self._API_BASE, video_id),
+            video_id, 'Downloading video formats info',
+            query=query, headers=player_header)
+
+        formats = []
+        for fmt in raw.get('outputList', []):
+            try:
+                profile_name = fmt['profile']
+                fmt_url_json = self._download_json(
+                    '%s/%s/raw/videolocation' % (self._API_BASE, video_id),
+                    video_id,
+                    'Downloading video URL for profile %s' % profile_name,
+                    query={
+                        'service': 'kakao_tv',
+                        'section': '',
+                        'tid': tid,
+                        'profile': profile_name
+                    }, headers=player_header, fatal=False)
+
+                if fmt_url_json is None:
+                    continue
+
+                fmt_url = fmt_url_json['url']
+                formats.append({
+                    'url': fmt_url,
+                    'format_id': profile_name,
+                    'width': int_or_none(fmt.get('width')),
+                    'height': int_or_none(fmt.get('height')),
+                    'format_note': fmt.get('label'),
+                    'filesize': int_or_none(fmt.get('filesize'))
+                })
+            except KeyError:
+                pass
+        self._sort_formats(formats)
+
+        thumbs = []
+        for thumb in clip.get('clipChapterThumbnailList', []):
+            thumbs.append({
+                'url': thumb.get('thumbnailUrl'),
+                'id': compat_str(thumb.get('timeInSec')),
+                'preference': -1 if thumb.get('isDefault') else 0
+            })
+        top_thumbnail = clip.get('thumbnailUrl')
+        if top_thumbnail:
+            thumbs.append({
+                'url': top_thumbnail,
+                'preference': 10,
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': clip.get('description'),
+            'uploader': clip_link.get('channel', {}).get('name'),
+            'uploader_id': clip_link.get('channelId'),
+            'thumbnails': thumbs,
+            'timestamp': unified_timestamp(clip_link.get('createTime')),
+            'duration': int_or_none(clip.get('duration')),
+            'view_count': int_or_none(clip.get('playCount')),
+            'like_count': int_or_none(clip.get('likeCount')),
+            'comment_count': int_or_none(clip.get('commentCount')),
+            'formats': formats,
+        }

youtube_dl/extractor/laola1tv.py

@@ -215,3 +215,21 @@ class Laola1TvIE(Laola1TvEmbedIE):
             'formats': formats,
             'is_live': is_live,
         }
+
+
+class ITTFIE(InfoExtractor):
+    _VALID_URL = r'https?://tv\.ittf\.com/video/[^/]+/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://tv.ittf.com/video/peng-wang-wei-matsudaira-kenta/951802',
+        'only_matching': True,
+    }
+
+    def _real_extract(self, url):
+        return self.url_result(
+            update_url_query('https://www.laola1.tv/titanplayer.php', {
+                'videoid': self._match_id(url),
+                'type': 'V',
+                'lang': 'en',
+                'portal': 'int',
+                'customer': 1024,
+            }), Laola1TvEmbedIE.ie_key())

youtube_dl/extractor/liveleak.py

@@ -72,15 +72,20 @@ class LiveLeakIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        'url': 'https://www.liveleak.com/view?i=677_1439397581',
+        'info_dict': {
+            'id': '677_1439397581',
+            'title': 'Fuel Depot in China Explosion caught on video',
+        },
+        'playlist_count': 3,
     }]
 
     @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(
-            r'<iframe[^>]+src="https?://(?:\w+\.)?liveleak\.com/ll_embed\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)',
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[if]=[\w_]+[^"]+)"',
             webpage)
-        if mobj:
-            return 'http://www.liveleak.com/view?i=%s' % mobj.group('id')
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -111,23 +116,54 @@ class LiveLeakIE(InfoExtractor):
                 'age_limit': age_limit,
             }
 
-        info_dict = entries[0]
+        for idx, info_dict in enumerate(entries):
+            for a_format in info_dict['formats']:
+                if not a_format.get('height'):
+                    a_format['height'] = int_or_none(self._search_regex(
+                        r'([0-9]+)p\.mp4', a_format['url'], 'height label',
+                        default=None))
 
-        for a_format in info_dict['formats']:
-            if not a_format.get('height'):
-                a_format['height'] = int_or_none(self._search_regex(
-                    r'([0-9]+)p\.mp4', a_format['url'], 'height label',
-                    default=None))
+            self._sort_formats(info_dict['formats'])
 
-        self._sort_formats(info_dict['formats'])
+            # Don't append entry ID for one-video pages to keep backward compatibility
+            if len(entries) > 1:
+                info_dict['id'] = '%s_%s' % (video_id, idx + 1)
+            else:
+                info_dict['id'] = video_id
 
-        info_dict.update({
-            'id': video_id,
-            'title': video_title,
-            'description': video_description,
-            'uploader': video_uploader,
-            'age_limit': age_limit,
-            'thumbnail': video_thumbnail,
-        })
+            info_dict.update({
+                'title': video_title,
+                'description': video_description,
+                'uploader': video_uploader,
+                'age_limit': age_limit,
+                'thumbnail': video_thumbnail,
+            })
 
-        return info_dict
+        return self.playlist_result(entries, video_id, video_title)
+
+
+class LiveLeakEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P<kind>[if])=(?P<id>[\w_]+)'
+
+    # See generic.py for actual test cases
+    _TESTS = [{
+        'url': 'https://www.liveleak.com/ll_embed?i=874_1459135191',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.liveleak.com/ll_embed?f=ab065df993c1',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        kind, video_id = mobj.group('kind', 'id')
+
+        if kind == 'f':
+            webpage = self._download_webpage(url, video_id)
+            liveleak_url = self._search_regex(
+                r'logourl\s*:\s*(?P<q1>[\'"])(?P<url>%s)(?P=q1)' % LiveLeakIE._VALID_URL,
+                webpage, 'LiveLeak URL', group='url')
+        elif kind == 'i':
+            liveleak_url = 'http://www.liveleak.com/view?i=%s' % video_id
+
+        return self.url_result(liveleak_url, ie=LiveLeakIE.ie_key())

youtube_dl/extractor/lynda.py

@@ -94,7 +94,7 @@ class LyndaBaseIE(InfoExtractor):
 class LyndaIE(LyndaBaseIE):
     IE_NAME = 'lynda'
     IE_DESC = 'lynda.com videos'
-    _VALID_URL = r'https?://(?:www\.)?lynda\.com/(?:[^/]+/[^/]+/(?P<course_id>\d+)|player/embed)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:lynda\.com|educourse\.ga)/(?:[^/]+/[^/]+/(?P<course_id>\d+)|player/embed)/(?P<id>\d+)'
 
     _TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
 
@@ -110,6 +110,9 @@ class LyndaIE(LyndaBaseIE):
     }, {
         'url': 'https://www.lynda.com/player/embed/133770?tr=foo=1;bar=g;fizz=rt&fs=0',
         'only_matching': True,
+    }, {
+        'url': 'https://educourse.ga/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
+        'only_matching': True,
     }]
 
     def _raise_unavailable(self, video_id):
@@ -253,7 +256,7 @@ class LyndaCourseIE(LyndaBaseIE):
 
     # Course link equals to welcome/introduction video link of same course
     # We will recognize it as course link
-    _VALID_URL = r'https?://(?:www|m)\.lynda\.com/(?P<coursepath>[^/]+/[^/]+/(?P<courseid>\d+))-\d\.html'
+    _VALID_URL = r'https?://(?:www|m)\.(?:lynda\.com|educourse\.ga)/(?P<coursepath>[^/]+/[^/]+/(?P<courseid>\d+))-\d\.html'
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/manyvids.py

@@ -0,0 +1,48 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class ManyVidsIE(InfoExtractor):
+    _VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://www.manyvids.com/Video/133957/everthing-about-me/',
+        'md5': '03f11bb21c52dd12a05be21a5c7dcc97',
+        'info_dict': {
+            'id': '133957',
+            'ext': 'mp4',
+            'title': 'everthing about me (Preview)',
+            'view_count': int,
+            'like_count': int,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(
+            r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P<url>(?:(?!\1).)+)\1',
+            webpage, 'video URL', group='url')
+
+        title = '%s (Preview)' % self._html_search_regex(
+            r'<h2[^>]+class="m-a-0"[^>]*>([^<]+)', webpage, 'title')
+
+        like_count = int_or_none(self._search_regex(
+            r'data-likes=["\'](\d+)', webpage, 'like count', default=None))
+        view_count = int_or_none(self._html_search_regex(
+            r'(?s)<span[^>]+class="views-wrapper"[^>]*>(.+?)</span', webpage,
+            'view count', default=None))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'view_count': view_count,
+            'like_count': like_count,
+            'formats': [{
+                'url': video_url,
+            }],
+        }

youtube_dl/extractor/mixcloud.py

@@ -12,12 +12,16 @@ from ..compat import (
     compat_str,
     compat_urllib_parse_unquote,
     compat_urlparse,
+    compat_zip
 )
 from ..utils import (
     clean_html,
     ExtractorError,
+    int_or_none,
     OnDemandPagedList,
     str_to_int,
+    try_get,
+    urljoin,
 )
 
 
@@ -54,27 +58,12 @@ class MixcloudIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    _keys = [
-        'return { requestAnimationFrame: function(callback) { callback(); }, innerHeight: 500 };',
-        'pleasedontdownloadourmusictheartistswontgetpaid',
-        'window.addEventListener = window.addEventListener || function() {};',
-        '(function() { return new Date().toLocaleDateString(); })()'
-    ]
-    _current_key = None
-
-    # See https://www.mixcloud.com/media/js2/www_js_2.9e23256562c080482435196ca3975ab5.js
-    def _decrypt_play_info(self, play_info, video_id):
-        play_info = base64.b64decode(play_info.encode('ascii'))
-        for num, key in enumerate(self._keys, start=1):
-            try:
-                return self._parse_json(
-                    ''.join([
-                        compat_chr(compat_ord(ch) ^ compat_ord(key[idx % len(key)]))
-                        for idx, ch in enumerate(play_info)]),
-                    video_id)
-            except ExtractorError:
-                if num == len(self._keys):
-                    raise
+    @staticmethod
+    def _decrypt_xor_cipher(key, ciphertext):
+        """Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR."""
+        return ''.join([
+            compat_chr(compat_ord(ch) ^ compat_ord(k))
+            for ch, k in compat_zip(ciphertext, itertools.cycle(key))])
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -84,52 +73,119 @@ class MixcloudIE(InfoExtractor):
 
         webpage = self._download_webpage(url, track_id)
 
-        if not self._current_key:
-            js_url = self._search_regex(
-                r'<script[^>]+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/js2/www_js_4\.[^>]+\.js)',
-                webpage, 'js url', default=None)
-            if js_url:
-                js = self._download_webpage(js_url, track_id, fatal=False)
-                if js:
-                    key = self._search_regex(
-                        r'player\s*:\s*{.*?\bvalue\s*:\s*(["\'])(?P<key>(?:(?!\1).)+)\1',
-                        js, 'key', default=None, group='key')
-                    if key and isinstance(key, compat_str):
-                        self._keys.insert(0, key)
-                        self._current_key = key
+        # Legacy path
+        encrypted_play_info = self._search_regex(
+            r'm-play-info="([^"]+)"', webpage, 'play info', default=None)
+
+        if encrypted_play_info is not None:
+            # Decode
+            encrypted_play_info = base64.b64decode(encrypted_play_info)
+        else:
+            # New path
+            full_info_json = self._parse_json(self._html_search_regex(
+                r'<script id="relay-data" type="text/x-mixcloud">([^<]+)</script>',
+                webpage, 'play info'), 'play info')
+            for item in full_info_json:
+                item_data = try_get(
+                    item, lambda x: x['cloudcast']['data']['cloudcastLookup'],
+                    dict)
+                if try_get(item_data, lambda x: x['streamInfo']['url']):
+                    info_json = item_data
+                    break
+            else:
+                raise ExtractorError('Failed to extract matching stream info')
 
         message = self._html_search_regex(
             r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',
             webpage, 'error message', default=None)
 
-        encrypted_play_info = self._search_regex(
-            r'm-play-info="([^"]+)"', webpage, 'play info')
+        js_url = self._search_regex(
+            r'<script[^>]+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/(?:js2/www_js_4|js/www)\.[^>]+\.js)',
+            webpage, 'js url')
+        js = self._download_webpage(js_url, track_id, 'Downloading JS')
+        # Known plaintext attack
+        if encrypted_play_info:
+            kps = ['{"stream_url":']
+            kpa_target = encrypted_play_info
+        else:
+            kps = ['https://', 'http://']
+            kpa_target = base64.b64decode(info_json['streamInfo']['url'])
+        for kp in kps:
+            partial_key = self._decrypt_xor_cipher(kpa_target, kp)
+            for quote in ["'", '"']:
+                key = self._search_regex(
+                    r'{0}({1}[^{0}]*){0}'.format(quote, re.escape(partial_key)),
+                    js, 'encryption key', default=None)
+                if key is not None:
+                    break
+            else:
+                continue
+            break
+        else:
+            raise ExtractorError('Failed to extract encryption key')
 
-        play_info = self._decrypt_play_info(encrypted_play_info, track_id)
+        if encrypted_play_info is not None:
+            play_info = self._parse_json(self._decrypt_xor_cipher(key, encrypted_play_info), 'play info')
+            if message and 'stream_url' not in play_info:
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
+            song_url = play_info['stream_url']
+            formats = [{
+                'format_id': 'normal',
+                'url': song_url
+            }]
 
-        if message and 'stream_url' not in play_info:
-            raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
+            title = self._html_search_regex(r'm-title="([^"]+)"', webpage, 'title')
+            thumbnail = self._proto_relative_url(self._html_search_regex(
+                r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail', fatal=False))
+            uploader = self._html_search_regex(
+                r'm-owner-name="([^"]+)"', webpage, 'uploader', fatal=False)
+            uploader_id = self._search_regex(
+                r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
+            description = self._og_search_description(webpage)
+            view_count = str_to_int(self._search_regex(
+                [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
+                 r'/listeners/?">([0-9,.]+)</a>',
+                 r'(?:m|data)-tooltip=["\']([\d,.]+) plays'],
+                webpage, 'play count', default=None))
 
-        song_url = play_info['stream_url']
+        else:
+            title = info_json['name']
+            thumbnail = urljoin(
+                'https://thumbnailer.mixcloud.com/unsafe/600x600/',
+                try_get(info_json, lambda x: x['picture']['urlRoot'], compat_str))
+            uploader = try_get(info_json, lambda x: x['owner']['displayName'])
+            uploader_id = try_get(info_json, lambda x: x['owner']['username'])
+            description = try_get(info_json, lambda x: x['description'])
+            view_count = int_or_none(try_get(info_json, lambda x: x['plays']))
 
-        title = self._html_search_regex(r'm-title="([^"]+)"', webpage, 'title')
-        thumbnail = self._proto_relative_url(self._html_search_regex(
-            r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail', fatal=False))
-        uploader = self._html_search_regex(
-            r'm-owner-name="([^"]+)"', webpage, 'uploader', fatal=False)
-        uploader_id = self._search_regex(
-            r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
-        description = self._og_search_description(webpage)
-        view_count = str_to_int(self._search_regex(
-            [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
-             r'/listeners/?">([0-9,.]+)</a>',
-             r'(?:m|data)-tooltip=["\']([\d,.]+) plays'],
-            webpage, 'play count', default=None))
+            stream_info = info_json['streamInfo']
+            formats = []
+
+            for url_key in ('url', 'hlsUrl', 'dashUrl'):
+                format_url = stream_info.get(url_key)
+                if not format_url:
+                    continue
+                decrypted = self._decrypt_xor_cipher(key, base64.b64decode(format_url))
+                if not decrypted:
+                    continue
+                if url_key == 'hlsUrl':
+                    formats.extend(self._extract_m3u8_formats(
+                        decrypted, track_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id='hls', fatal=False))
+                elif url_key == 'dashUrl':
+                    formats.extend(self._extract_mpd_formats(
+                        decrypted, track_id, mpd_id='dash', fatal=False))
+                else:
+                    formats.append({
+                        'format_id': 'http',
+                        'url': decrypted,
+                    })
+            self._sort_formats(formats)
 
         return {
             'id': track_id,
             'title': title,
-            'url': song_url,
+            'formats': formats,
             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,

youtube_dl/extractor/morningstar.py

@@ -8,8 +8,8 @@ from .common import InfoExtractor
 
 class MorningstarIE(InfoExtractor):
     IE_DESC = 'morningstar.com'
-    _VALID_URL = r'https?://(?:www\.)?morningstar\.com/[cC]over/video[cC]enter\.aspx\?id=(?P<id>[0-9]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:(?:www|news)\.)morningstar\.com/[cC]over/video[cC]enter\.aspx\?id=(?P<id>[0-9]+)'
+    _TESTS = [{
         'url': 'http://www.morningstar.com/cover/videocenter.aspx?id=615869',
         'md5': '6c0acface7a787aadc8391e4bbf7b0f5',
         'info_dict': {
@@ -19,7 +19,10 @@ class MorningstarIE(InfoExtractor):
             'description': "Vanguard's Joel Dickson on managing higher tax rates for high-income earners and fund capital-gain distributions in 2013.",
             'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.jpg$'
         }
-    }
+    }, {
+        'url': 'http://news.morningstar.com/cover/videocenter.aspx?id=825556',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/nbc.py

@@ -109,10 +109,10 @@ class NBCSportsVPlayerIE(InfoExtractor):
     _VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
 
     _TESTS = [{
-        'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_share/select/9CsDKds0kvHI',
+        'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/9CsDKds0kvHI',
         'info_dict': {
             'id': '9CsDKds0kvHI',
-            'ext': 'flv',
+            'ext': 'mp4',
             'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
             'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
             'timestamp': 1426270238,
@@ -120,7 +120,7 @@ class NBCSportsVPlayerIE(InfoExtractor):
             'uploader': 'NBCU-SPORTS',
         }
     }, {
-        'url': 'http://vplayer.nbcsports.com/p/BxmELC/nbc_embedshare/select/_hqLjQ95yx8Z',
+        'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/_hqLjQ95yx8Z',
         'only_matching': True,
     }]
 
@@ -134,7 +134,8 @@ class NBCSportsVPlayerIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        theplatform_url = self._og_search_video_url(webpage)
+        theplatform_url = self._og_search_video_url(webpage).replace(
+            'vplayer.nbcsports.com', 'player.theplatform.com')
         return self.url_result(theplatform_url, 'ThePlatform')
 
 

youtube_dl/extractor/noovo.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
     int_or_none,
+    js_to_json,
     smuggle_url,
     try_get,
 )
@@ -24,8 +25,6 @@ class NoovoIE(InfoExtractor):
             'timestamp': 1491399228,
             'upload_date': '20170405',
             'uploader_id': '618566855001',
-            'creator': 'vtele',
-            'view_count': int,
             'series': 'RPM+',
         },
         'params': {
@@ -37,13 +36,11 @@ class NoovoIE(InfoExtractor):
         'info_dict': {
             'id': '5395865725001',
             'title': 'Épisode 13 : Les retrouvailles',
-            'description': 'md5:336d5ebc5436534e61d16e63ddfca327',
+            'description': 'md5:888c3330f0c1b4476c5bc99a1c040473',
             'ext': 'mp4',
             'timestamp': 1492019320,
             'upload_date': '20170412',
             'uploader_id': '618566855001',
-            'creator': 'vtele',
-            'view_count': int,
             'series': "L'amour est dans le pré",
             'season_number': 5,
             'episode': 'Épisode 13',
@@ -58,40 +55,46 @@ class NoovoIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        data = self._download_json(
-            'http://api.noovo.ca/api/v1/pages/single-episode/%s' % video_id,
-            video_id)['data']
+        webpage = self._download_webpage(url, video_id)
 
-        content = try_get(data, lambda x: x['contents'][0])
+        bc_url = BrightcoveNewIE._extract_url(self, webpage)
 
-        brightcove_id = data.get('brightcoveId') or content['brightcoveId']
+        data = self._parse_json(
+            self._search_regex(
+                r'(?s)dataLayer\.push\(\s*({.+?})\s*\);', webpage, 'data',
+                default='{}'),
+            video_id, transform_source=js_to_json, fatal=False)
+
+        title = try_get(
+            data, lambda x: x['video']['nom'],
+            compat_str) or self._html_search_meta(
+            'dcterms.Title', webpage, 'title', fatal=True)
+
+        description = self._html_search_meta(
+            ('dcterms.Description', 'description'), webpage, 'description')
 
         series = try_get(
-            data, (
-                lambda x: x['show']['title'],
-                lambda x: x['season']['show']['title']),
-            compat_str)
+            data, lambda x: x['emission']['nom']) or self._search_regex(
+            r'<div[^>]+class="banner-card__subtitle h4"[^>]*>([^<]+)',
+            webpage, 'series', default=None)
 
-        episode = None
-        og = data.get('og')
-        if isinstance(og, dict) and og.get('type') == 'video.episode':
-            episode = og.get('title')
+        season_el = try_get(data, lambda x: x['emission']['saison'], dict) or {}
+        season = try_get(season_el, lambda x: x['nom'], compat_str)
+        season_number = int_or_none(try_get(season_el, lambda x: x['numero']))
 
-        video = content or data
+        episode_el = try_get(season_el, lambda x: x['episode'], dict) or {}
+        episode = try_get(episode_el, lambda x: x['nom'], compat_str)
+        episode_number = int_or_none(try_get(episode_el, lambda x: x['numero']))
 
         return {
             '_type': 'url_transparent',
             'ie_key': BrightcoveNewIE.ie_key(),
-            'url': smuggle_url(
-                self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
-                {'geo_countries': ['CA']}),
-            'id': brightcove_id,
-            'title': video.get('title'),
-            'creator': video.get('source'),
-            'view_count': int_or_none(video.get('viewsCount')),
+            'url': smuggle_url(bc_url, {'geo_countries': ['CA']}),
+            'title': title,
+            'description': description,
             'series': series,
-            'season_number': int_or_none(try_get(
-                data, lambda x: x['season']['seasonNumber'])),
+            'season': season,
+            'season_number': season_number,
             'episode': episode,
-            'episode_number': int_or_none(data.get('episodeNumber')),
+            'episode_number': episode_number,
         }

youtube_dl/extractor/openload.py

@@ -1,14 +1,244 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
+import os
 import re
+import subprocess
+import tempfile
 
 from .common import InfoExtractor
-from ..compat import compat_chr
-from ..utils import (
-    determine_ext,
-    ExtractorError,
+from ..compat import (
+    compat_urlparse,
+    compat_kwargs,
 )
+from ..utils import (
+    check_executable,
+    determine_ext,
+    encodeArgument,
+    ExtractorError,
+    get_element_by_id,
+    get_exe_version,
+    is_outdated_version,
+    std_headers,
+)
+
+
+def cookie_to_dict(cookie):
+    cookie_dict = {
+        'name': cookie.name,
+        'value': cookie.value,
+    }
+    if cookie.port_specified:
+        cookie_dict['port'] = cookie.port
+    if cookie.domain_specified:
+        cookie_dict['domain'] = cookie.domain
+    if cookie.path_specified:
+        cookie_dict['path'] = cookie.path
+    if cookie.expires is not None:
+        cookie_dict['expires'] = cookie.expires
+    if cookie.secure is not None:
+        cookie_dict['secure'] = cookie.secure
+    if cookie.discard is not None:
+        cookie_dict['discard'] = cookie.discard
+    try:
+        if (cookie.has_nonstandard_attr('httpOnly') or
+                cookie.has_nonstandard_attr('httponly') or
+                cookie.has_nonstandard_attr('HttpOnly')):
+            cookie_dict['httponly'] = True
+    except TypeError:
+        pass
+    return cookie_dict
+
+
+def cookie_jar_to_list(cookie_jar):
+    return [cookie_to_dict(cookie) for cookie in cookie_jar]
+
+
+class PhantomJSwrapper(object):
+    """PhantomJS wrapper class
+
+    This class is experimental.
+    """
+
+    _TEMPLATE = r'''
+        phantom.onError = function(msg, trace) {{
+          var msgStack = ['PHANTOM ERROR: ' + msg];
+          if(trace && trace.length) {{
+            msgStack.push('TRACE:');
+            trace.forEach(function(t) {{
+              msgStack.push(' -> ' + (t.file || t.sourceURL) + ': ' + t.line
+                + (t.function ? ' (in function ' + t.function +')' : ''));
+            }});
+          }}
+          console.error(msgStack.join('\n'));
+          phantom.exit(1);
+        }};
+        var page = require('webpage').create();
+        var fs = require('fs');
+        var read = {{ mode: 'r', charset: 'utf-8' }};
+        var write = {{ mode: 'w', charset: 'utf-8' }};
+        JSON.parse(fs.read("{cookies}", read)).forEach(function(x) {{
+          phantom.addCookie(x);
+        }});
+        page.settings.resourceTimeout = {timeout};
+        page.settings.userAgent = "{ua}";
+        page.onLoadStarted = function() {{
+          page.evaluate(function() {{
+            delete window._phantom;
+            delete window.callPhantom;
+          }});
+        }};
+        var saveAndExit = function() {{
+          fs.write("{html}", page.content, write);
+          fs.write("{cookies}", JSON.stringify(phantom.cookies), write);
+          phantom.exit();
+        }};
+        page.onLoadFinished = function(status) {{
+          if(page.url === "") {{
+            page.setContent(fs.read("{html}", read), "{url}");
+          }}
+          else {{
+            {jscode}
+          }}
+        }};
+        page.open("");
+    '''
+
+    _TMP_FILE_NAMES = ['script', 'html', 'cookies']
+
+    @staticmethod
+    def _version():
+        return get_exe_version('phantomjs', version_re=r'([0-9.]+)')
+
+    def __init__(self, extractor, required_version=None, timeout=10000):
+        self.exe = check_executable('phantomjs', ['-v'])
+        if not self.exe:
+            raise ExtractorError('PhantomJS executable not found in PATH, '
+                                 'download it from http://phantomjs.org',
+                                 expected=True)
+
+        self.extractor = extractor
+
+        if required_version:
+            version = self._version()
+            if is_outdated_version(version, required_version):
+                self.extractor._downloader.report_warning(
+                    'Your copy of PhantomJS is outdated, update it to version '
+                    '%s or newer if you encounter any errors.' % required_version)
+
+        self.options = {
+            'timeout': timeout,
+        }
+        self._TMP_FILES = {}
+        for name in self._TMP_FILE_NAMES:
+            tmp = tempfile.NamedTemporaryFile(delete=False)
+            tmp.close()
+            self._TMP_FILES[name] = tmp
+
+    def __del__(self):
+        for name in self._TMP_FILE_NAMES:
+            try:
+                os.remove(self._TMP_FILES[name].name)
+            except:
+                pass
+
+    def _save_cookies(self, url):
+        cookies = cookie_jar_to_list(self.extractor._downloader.cookiejar)
+        for cookie in cookies:
+            if 'path' not in cookie:
+                cookie['path'] = '/'
+            if 'domain' not in cookie:
+                cookie['domain'] = compat_urlparse.urlparse(url).netloc
+        with open(self._TMP_FILES['cookies'].name, 'wb') as f:
+            f.write(json.dumps(cookies).encode('utf-8'))
+
+    def _load_cookies(self):
+        with open(self._TMP_FILES['cookies'].name, 'rb') as f:
+            cookies = json.loads(f.read().decode('utf-8'))
+        for cookie in cookies:
+            if cookie['httponly'] is True:
+                cookie['rest'] = {'httpOnly': None}
+            if 'expiry' in cookie:
+                cookie['expire_time'] = cookie['expiry']
+            self.extractor._set_cookie(**compat_kwargs(cookie))
+
+    def get(self, url, html=None, video_id=None, note=None, note2='Executing JS on webpage', headers={}, jscode='saveAndExit();'):
+        """
+        Downloads webpage (if needed) and executes JS
+
+        Params:
+            url: website url
+            html: optional, html code of website
+            video_id: video id
+            note: optional, displayed when downloading webpage
+            note2: optional, displayed when executing JS
+            headers: custom http headers
+            jscode: code to be executed when page is loaded
+
+        Returns tuple with:
+            * downloaded website (after JS execution)
+            * anything you print with `console.log` (but not inside `page.execute`!)
+
+        In most cases you don't need to add any `jscode`.
+        It is executed in `page.onLoadFinished`.
+        `saveAndExit();` is mandatory, use it instead of `phantom.exit()`
+        It is possible to wait for some element on the webpage, for example:
+            var check = function() {
+              var elementFound = page.evaluate(function() {
+                return document.querySelector('#b.done') !== null;
+              });
+              if(elementFound)
+                saveAndExit();
+              else
+                window.setTimeout(check, 500);
+            }
+
+            page.evaluate(function(){
+              document.querySelector('#a').click();
+            });
+            check();
+        """
+        if 'saveAndExit();' not in jscode:
+            raise ExtractorError('`saveAndExit();` not found in `jscode`')
+        if not html:
+            html = self.extractor._download_webpage(url, video_id, note=note, headers=headers)
+        with open(self._TMP_FILES['html'].name, 'wb') as f:
+            f.write(html.encode('utf-8'))
+
+        self._save_cookies(url)
+
+        replaces = self.options
+        replaces['url'] = url
+        user_agent = headers.get('User-Agent') or std_headers['User-Agent']
+        replaces['ua'] = user_agent.replace('"', '\\"')
+        replaces['jscode'] = jscode
+
+        for x in self._TMP_FILE_NAMES:
+            replaces[x] = self._TMP_FILES[x].name.replace('\\', '\\\\').replace('"', '\\"')
+
+        with open(self._TMP_FILES['script'].name, 'wb') as f:
+            f.write(self._TEMPLATE.format(**replaces).encode('utf-8'))
+
+        if video_id is None:
+            self.extractor.to_screen('%s' % (note2,))
+        else:
+            self.extractor.to_screen('%s: %s' % (video_id, note2))
+
+        p = subprocess.Popen([
+            self.exe, '--ssl-protocol=any',
+            self._TMP_FILES['script'].name
+        ], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        out, err = p.communicate()
+        if p.returncode != 0:
+            raise ExtractorError(
+                'Executing JS failed\n:' + encodeArgument(err))
+        with open(self._TMP_FILES['html'].name, 'rb') as f:
+            html = f.read().decode('utf-8')
+
+        self._load_cookies()
+
+        return (html, encodeArgument(out))
 
 
 class OpenloadIE(InfoExtractor):
@@ -58,6 +288,8 @@ class OpenloadIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
+
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
@@ -66,47 +298,22 @@ class OpenloadIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)
+        url = 'https://openload.co/embed/%s/' % video_id
+        headers = {
+            'User-Agent': self._USER_AGENT,
+        }
+
+        webpage = self._download_webpage(url, video_id, headers=headers)
 
         if 'File not found' in webpage or 'deleted by the owner' in webpage:
-            raise ExtractorError('File not found', expected=True)
+            raise ExtractorError('File not found', expected=True, video_id=video_id)
 
-        ol_id = self._search_regex(
-            '<span[^>]+id="[^"]+"[^>]*>([0-9A-Za-z]+)</span>',
-            webpage, 'openload ID')
+        phantom = PhantomJSwrapper(self, required_version='2.0')
+        webpage, _ = phantom.get(url, html=webpage, video_id=video_id, headers=headers)
 
-        decoded = ''
-        a = ol_id[0:24]
-        b = []
-        for i in range(0, len(a), 8):
-            b.append(int(a[i:i + 8] or '0', 16))
-        ol_id = ol_id[24:]
-        j = 0
-        k = 0
-        while j < len(ol_id):
-            c = 128
-            d = 0
-            e = 0
-            f = 0
-            _more = True
-            while _more:
-                if j + 1 >= len(ol_id):
-                    c = 143
-                f = int(ol_id[j:j + 2] or '0', 16)
-                j += 2
-                d += (f & 127) << e
-                e += 7
-                _more = f >= c
-            g = d ^ b[k % 3]
-            for i in range(4):
-                char_dec = (g >> 8 * i) & (c + 127)
-                char = compat_chr(char_dec)
-                if char != '#':
-                    decoded += char
-            k += 1
+        decoded_id = get_element_by_id('streamurl', webpage)
 
-        video_url = 'https://openload.co/stream/%s?mime=true'
-        video_url = video_url % decoded
+        video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id
 
         title = self._og_search_title(webpage, default=None) or self._search_regex(
             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
@@ -114,15 +321,17 @@ class OpenloadIE(InfoExtractor):
             'description', webpage, 'title', fatal=True)
 
         entries = self._parse_html5_media_entries(url, webpage, video_id)
-        subtitles = entries[0]['subtitles'] if entries else None
+        entry = entries[0] if entries else {}
+        subtitles = entry.get('subtitles')
 
         info_dict = {
             'id': video_id,
             'title': title,
-            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+            'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None),
             'url': video_url,
             # Seems all videos have extensions in their titles
             'ext': determine_ext(title, 'mp4'),
             'subtitles': subtitles,
+            'http_headers': headers,
         }
         return info_dict

youtube_dl/extractor/orf.py

@@ -6,14 +6,15 @@ import re
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
-    HEADRequest,
-    unified_strdate,
-    strip_jsonp,
-    int_or_none,
-    float_or_none,
     determine_ext,
+    float_or_none,
+    HEADRequest,
+    int_or_none,
+    orderedSet,
     remove_end,
+    strip_jsonp,
     unescapeHTML,
+    unified_strdate,
 )
 
 
@@ -307,3 +308,108 @@ class ORFIPTVIE(InfoExtractor):
             'upload_date': upload_date,
             'formats': formats,
         }
+
+
+class ORFFM4StoryIE(InfoExtractor):
+    IE_NAME = 'orf:fm4:story'
+    IE_DESC = 'fm4.orf.at stories'
+    _VALID_URL = r'https?://fm4\.orf\.at/stories/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://fm4.orf.at/stories/2865738/',
+        'playlist': [{
+            'md5': 'e1c2c706c45c7b34cf478bbf409907ca',
+            'info_dict': {
+                'id': '547792',
+                'ext': 'flv',
+                'title': 'Manu Delago und Inner Tongue live',
+                'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
+                'duration': 1748.52,
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'upload_date': '20170913',
+            },
+        }, {
+            'md5': 'c6dd2179731f86f4f55a7b49899d515f',
+            'info_dict': {
+                'id': '547798',
+                'ext': 'flv',
+                'title': 'Manu Delago und Inner Tongue live (2)',
+                'duration': 1504.08,
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'upload_date': '20170913',
+                'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
+            },
+        }],
+    }
+
+    def _real_extract(self, url):
+        story_id = self._match_id(url)
+        webpage = self._download_webpage(url, story_id)
+
+        entries = []
+        all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage))
+        for idx, video_id in enumerate(all_ids):
+            data = self._download_json(
+                'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
+                video_id)[0]
+
+            duration = float_or_none(data['duration'], 1000)
+
+            video = data['sources']['q8c']
+            load_balancer_url = video['loadBalancerUrl']
+            abr = int_or_none(video.get('audioBitrate'))
+            vbr = int_or_none(video.get('bitrate'))
+            fps = int_or_none(video.get('videoFps'))
+            width = int_or_none(video.get('videoWidth'))
+            height = int_or_none(video.get('videoHeight'))
+            thumbnail = video.get('preview')
+
+            rendition = self._download_json(
+                load_balancer_url, video_id, transform_source=strip_jsonp)
+
+            f = {
+                'abr': abr,
+                'vbr': vbr,
+                'fps': fps,
+                'width': width,
+                'height': height,
+            }
+
+            formats = []
+            for format_id, format_url in rendition['redirect'].items():
+                if format_id == 'rtmp':
+                    ff = f.copy()
+                    ff.update({
+                        'url': format_url,
+                        'format_id': format_id,
+                    })
+                    formats.append(ff)
+                elif determine_ext(format_url) == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        format_url, video_id, f4m_id=format_id))
+                elif determine_ext(format_url) == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, video_id, 'mp4', m3u8_id=format_id))
+                else:
+                    continue
+            self._sort_formats(formats)
+
+            title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at')
+            if idx >= 1:
+                # Titles are duplicates, make them unique
+                title += ' (' + str(idx + 1) + ')'
+            description = self._og_search_description(webpage)
+            upload_date = unified_strdate(self._html_search_meta(
+                'dc.date', webpage, 'upload date'))
+
+            entries.append({
+                'id': video_id,
+                'title': title,
+                'description': description,
+                'duration': duration,
+                'thumbnail': thumbnail,
+                'upload_date': upload_date,
+                'formats': formats,
+            })
+
+        return self.playlist_result(entries)

youtube_dl/extractor/popcorntv.py

@@ -0,0 +1,78 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    extract_attributes,
+    int_or_none,
+    unified_timestamp,
+)
+
+
+class PopcornTVIE(InfoExtractor):
+    _VALID_URL = r'https?://[^/]+\.popcorntv\.it/guarda/(?P<display_id>[^/]+)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://animemanga.popcorntv.it/guarda/food-wars-battaglie-culinarie-episodio-01/9183',
+        'md5': '47d65a48d147caf692ab8562fe630b45',
+        'info_dict': {
+            'id': '9183',
+            'display_id': 'food-wars-battaglie-culinarie-episodio-01',
+            'ext': 'mp4',
+            'title': 'Food Wars, Battaglie Culinarie | Episodio 01',
+            'description': 'md5:b8bea378faae4651d3b34c6e112463d0',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'timestamp': 1497610857,
+            'upload_date': '20170616',
+            'duration': 1440,
+            'view_count': int,
+        },
+    }, {
+        'url': 'https://cinema.popcorntv.it/guarda/smash-cut/10433',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id, video_id = mobj.group('display_id', 'id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        m3u8_url = extract_attributes(
+            self._search_regex(
+                r'(<link[^>]+itemprop=["\'](?:content|embed)Url[^>]*>)',
+                webpage, 'content'
+            ))['href']
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native',
+            m3u8_id='hls')
+
+        title = self._search_regex(
+            r'<h1[^>]+itemprop=["\']name[^>]*>([^<]+)', webpage,
+            'title', default=None) or self._og_search_title(webpage)
+
+        description = self._html_search_regex(
+            r'(?s)<article[^>]+itemprop=["\']description[^>]*>(.+?)</article>',
+            webpage, 'description', fatal=False)
+        thumbnail = self._og_search_thumbnail(webpage)
+        timestamp = unified_timestamp(self._html_search_meta(
+            'uploadDate', webpage, 'timestamp'))
+        print(self._html_search_meta(
+            'duration', webpage))
+        duration = int_or_none(self._html_search_meta(
+            'duration', webpage), invscale=60)
+        view_count = int_or_none(self._html_search_meta(
+            'interactionCount', webpage, 'view count'))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+        }

youtube_dl/extractor/pornhd.py

@@ -54,7 +54,7 @@ class PornHdIE(InfoExtractor):
              r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
 
         sources = self._parse_json(js_to_json(self._search_regex(
-            r"(?s)sources'?\s*:\s*(\{.+?\})\s*\}[;,)]",
+            r"(?s)sources'?\s*[:=]\s*(\{.+?\})",
             webpage, 'sources', default='{}')), video_id)
 
         if not sources:
@@ -82,7 +82,8 @@ class PornHdIE(InfoExtractor):
         view_count = int_or_none(self._html_search_regex(
             r'(\d+) views\s*<', webpage, 'view count', fatal=False))
         thumbnail = self._search_regex(
-            r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
+            r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
+            'thumbnail', fatal=False, group='url')
 
         return {
             'id': video_id,

youtube_dl/extractor/pornhub.py

@@ -186,7 +186,7 @@ class PornHubIE(InfoExtractor):
             title, thumbnail, duration = [None] * 3
 
         video_uploader = self._html_search_regex(
-            r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
+            r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:user|channel)s/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
             webpage, 'uploader', fatal=False)
 
         view_count = self._extract_count(

youtube_dl/extractor/radiocanada.py

@@ -20,20 +20,37 @@ from ..utils import (
 class RadioCanadaIE(InfoExtractor):
     IE_NAME = 'radiocanada'
     _VALID_URL = r'(?:radiocanada:|https?://ici\.radio-canada\.ca/widgets/mediaconsole/)(?P<app_code>[^:/]+)[:/](?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7184272',
-        'info_dict': {
-            'id': '7184272',
-            'ext': 'mp4',
-            'title': 'Le parcours du tireur capté sur vidéo',
-            'description': 'Images des caméras de surveillance fournies par la GRC montrant le parcours du tireur d\'Ottawa',
-            'upload_date': '20141023',
+    _TESTS = [
+        {
+            'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7184272',
+            'info_dict': {
+                'id': '7184272',
+                'ext': 'mp4',
+                'title': 'Le parcours du tireur capté sur vidéo',
+                'description': 'Images des caméras de surveillance fournies par la GRC montrant le parcours du tireur d\'Ottawa',
+                'upload_date': '20141023',
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            }
         },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }
+        {
+            # empty Title
+            'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7754998/',
+            'info_dict': {
+                'id': '7754998',
+                'ext': 'mp4',
+                'title': 'letelejournal22h',
+                'description': 'INTEGRALE WEB 22H-TJ',
+                'upload_date': '20170720',
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        }
+    ]
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
@@ -59,6 +76,7 @@ class RadioCanadaIE(InfoExtractor):
             device_types.append('android')
 
         formats = []
+        error = None
         # TODO: extract f4m formats
         # f4m formats can be extracted using flashhd device_type but they produce unplayable file
         for device_type in device_types:
@@ -84,8 +102,8 @@ class RadioCanadaIE(InfoExtractor):
             if not v_url:
                 continue
             if v_url == 'null':
-                raise ExtractorError('%s said: %s' % (
-                    self.IE_NAME, xpath_text(v_data, 'message')), expected=True)
+                error = xpath_text(v_data, 'message')
+                continue
             ext = determine_ext(v_url)
             if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
@@ -129,6 +147,9 @@ class RadioCanadaIE(InfoExtractor):
                             formats.extend(self._extract_f4m_formats(
                                 base_url + '/manifest.f4m', video_id,
                                 f4m_id='hds', fatal=False))
+        if not formats and error:
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, error), expected=True)
         self._sort_formats(formats)
 
         subtitles = {}
@@ -141,7 +162,7 @@ class RadioCanadaIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': get_meta('Title'),
+            'title': get_meta('Title') or get_meta('AV-nomEmission'),
             'description': get_meta('Description') or get_meta('ShortDescription'),
             'thumbnail': get_meta('imageHR') or get_meta('imageMR') or get_meta('imageBR'),
             'duration': int_or_none(get_meta('length')),

youtube_dl/extractor/rai.py

@@ -345,11 +345,11 @@ class RaiIE(RaiBaseIE):
         media_type = media['type']
         if 'Audio' in media_type:
             relinker_info = {
-                'formats': {
+                'formats': [{
                     'format_id': media.get('formatoAudio'),
                     'url': media['audioUrl'],
                     'ext': media.get('formatoAudio'),
-                }
+                }]
             }
         elif 'Video' in media_type:
             relinker_info = self._extract_relinker_info(media['mediaUri'], content_id)

youtube_dl/extractor/redtube.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     int_or_none,
@@ -62,7 +63,23 @@ class RedTubeIE(InfoExtractor):
                         'format_id': format_id,
                         'height': int_or_none(format_id),
                     })
-        else:
+        medias = self._parse_json(
+            self._search_regex(
+                r'mediaDefinition\s*:\s*(\[.+?\])', webpage,
+                'media definitions', default='{}'),
+            video_id, fatal=False)
+        if medias and isinstance(medias, list):
+            for media in medias:
+                format_url = media.get('videoUrl')
+                if not format_url or not isinstance(format_url, compat_str):
+                    continue
+                format_id = media.get('quality')
+                formats.append({
+                    'url': format_url,
+                    'format_id': format_id,
+                    'height': int_or_none(format_id),
+                })
+        if not formats:
             video_url = self._html_search_regex(
                 r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
             formats.append({'url': video_url})
@@ -73,7 +90,7 @@ class RedTubeIE(InfoExtractor):
             r'<span[^>]+class="added-time"[^>]*>ADDED ([^<]+)<',
             webpage, 'upload date', fatal=False))
         duration = int_or_none(self._search_regex(
-            r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
+            r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None))
         view_count = str_to_int(self._search_regex(
             r'<span[^>]*>VIEWS</span></td>\s*<td>([\d,.]+)',
             webpage, 'view count', fatal=False))

youtube_dl/extractor/rutube.py

@@ -7,43 +7,84 @@ import itertools
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
 )
 from ..utils import (
     determine_ext,
-    unified_strdate,
+    bool_or_none,
+    int_or_none,
+    try_get,
+    unified_timestamp,
 )
 
 
-class RutubeIE(InfoExtractor):
+class RutubeBaseIE(InfoExtractor):
+    def _extract_video(self, video, video_id=None, require_title=True):
+        title = video['title'] if require_title else video.get('title')
+
+        age_limit = video.get('is_adult')
+        if age_limit is not None:
+            age_limit = 18 if age_limit is True else 0
+
+        uploader_id = try_get(video, lambda x: x['author']['id'])
+        category = try_get(video, lambda x: x['category']['name'])
+
+        return {
+            'id': video.get('id') or video_id,
+            'title': title,
+            'description': video.get('description'),
+            'thumbnail': video.get('thumbnail_url'),
+            'duration': int_or_none(video.get('duration')),
+            'uploader': try_get(video, lambda x: x['author']['name']),
+            'uploader_id': compat_str(uploader_id) if uploader_id else None,
+            'timestamp': unified_timestamp(video.get('created_ts')),
+            'category': [category] if category else None,
+            'age_limit': age_limit,
+            'view_count': int_or_none(video.get('hits')),
+            'comment_count': int_or_none(video.get('comments_count')),
+            'is_live': bool_or_none(video.get('is_livestream')),
+        }
+
+
+class RutubeIE(RutubeBaseIE):
     IE_NAME = 'rutube'
     IE_DESC = 'Rutube videos'
     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'
 
     _TESTS = [{
         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
+        'md5': '79938ade01294ef7e27574890d0d3769',
         'info_dict': {
             'id': '3eac3b4561676c17df9132a9a1e62e3e',
-            'ext': 'mp4',
+            'ext': 'flv',
             'title': 'Раненный кенгуру забежал в аптеку',
             'description': 'http://www.ntdtv.ru ',
             'duration': 80,
             'uploader': 'NTDRussian',
             'uploader_id': '29790',
+            'timestamp': 1381943602,
             'upload_date': '20131016',
             'age_limit': 0,
         },
-        'params': {
-            # It requires ffmpeg (m3u8 download)
-            'skip_download': True,
-        },
     }, {
         'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
         'only_matching': True,
     }, {
         'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
         'only_matching': True,
+    }, {
+        'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
+        'only_matching': True,
+    }, {
+        'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
+        'only_matching': True,
     }]
 
+    @classmethod
+    def suitable(cls, url):
+        return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
+
     @staticmethod
     def _extract_urls(webpage):
         return [mobj.group('url') for mobj in re.finditer(
@@ -52,12 +93,12 @@ class RutubeIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+
         video = self._download_json(
             'http://rutube.ru/api/video/%s/?format=json' % video_id,
             video_id, 'Downloading video JSON')
 
-        # Some videos don't have the author field
-        author = video.get('author') or {}
+        info = self._extract_video(video, video_id)
 
         options = self._download_json(
             'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
@@ -79,19 +120,8 @@ class RutubeIE(InfoExtractor):
                 })
         self._sort_formats(formats)
 
-        return {
-            'id': video['id'],
-            'title': video['title'],
-            'description': video['description'],
-            'duration': video['duration'],
-            'view_count': video['hits'],
-            'formats': formats,
-            'thumbnail': video['thumbnail_url'],
-            'uploader': author.get('name'),
-            'uploader_id': compat_str(author['id']) if author else None,
-            'upload_date': unified_strdate(video['created_ts']),
-            'age_limit': 18 if video['is_adult'] else 0,
-        }
+        info['formats'] = formats
+        return info
 
 
 class RutubeEmbedIE(InfoExtractor):
@@ -103,7 +133,8 @@ class RutubeEmbedIE(InfoExtractor):
         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
         'info_dict': {
             'id': 'a10e53b86e8f349080f718582ce4c661',
-            'ext': 'mp4',
+            'ext': 'flv',
+            'timestamp': 1387830582,
             'upload_date': '20131223',
             'uploader_id': '297833',
             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
@@ -111,7 +142,7 @@ class RutubeEmbedIE(InfoExtractor):
             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
         },
         'params': {
-            'skip_download': 'Requires ffmpeg',
+            'skip_download': True,
         },
     }, {
         'url': 'http://rutube.ru/play/embed/8083783',
@@ -125,10 +156,51 @@ class RutubeEmbedIE(InfoExtractor):
         canonical_url = self._html_search_regex(
             r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
             'Canonical URL')
-        return self.url_result(canonical_url, 'Rutube')
+        return self.url_result(canonical_url, RutubeIE.ie_key())
 
 
-class RutubeChannelIE(InfoExtractor):
+class RutubePlaylistBaseIE(RutubeBaseIE):
+    def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
+        return self._PAGE_TEMPLATE % (playlist_id, page_num)
+
+    def _entries(self, playlist_id, *args, **kwargs):
+        next_page_url = None
+        for pagenum in itertools.count(1):
+            page = self._download_json(
+                next_page_url or self._next_page_url(
+                    pagenum, playlist_id, *args, **kwargs),
+                playlist_id, 'Downloading page %s' % pagenum)
+
+            results = page.get('results')
+            if not results or not isinstance(results, list):
+                break
+
+            for result in results:
+                video_url = result.get('video_url')
+                if not video_url or not isinstance(video_url, compat_str):
+                    continue
+                entry = self._extract_video(result, require_title=False)
+                entry.update({
+                    '_type': 'url',
+                    'url': video_url,
+                    'ie_key': RutubeIE.ie_key(),
+                })
+                yield entry
+
+            next_page_url = page.get('next')
+            if not next_page_url or not page.get('has_next'):
+                break
+
+    def _extract_playlist(self, playlist_id, *args, **kwargs):
+        return self.playlist_result(
+            self._entries(playlist_id, *args, **kwargs),
+            playlist_id, kwargs.get('playlist_name'))
+
+    def _real_extract(self, url):
+        return self._extract_playlist(self._match_id(url))
+
+
+class RutubeChannelIE(RutubePlaylistBaseIE):
     IE_NAME = 'rutube:channel'
     IE_DESC = 'Rutube channels'
     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
@@ -142,27 +214,8 @@ class RutubeChannelIE(InfoExtractor):
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 
-    def _extract_videos(self, channel_id, channel_title=None):
-        entries = []
-        for pagenum in itertools.count(1):
-            page = self._download_json(
-                self._PAGE_TEMPLATE % (channel_id, pagenum),
-                channel_id, 'Downloading page %s' % pagenum)
-            results = page['results']
-            if not results:
-                break
-            entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
-            if not page['has_next']:
-                break
-        return self.playlist_result(entries, channel_id, channel_title)
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        channel_id = mobj.group('id')
-        return self._extract_videos(channel_id)
-
-
-class RutubeMovieIE(RutubeChannelIE):
+class RutubeMovieIE(RutubePlaylistBaseIE):
     IE_NAME = 'rutube:movie'
     IE_DESC = 'Rutube movies'
     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
@@ -176,11 +229,11 @@ class RutubeMovieIE(RutubeChannelIE):
         movie = self._download_json(
             self._MOVIE_TEMPLATE % movie_id, movie_id,
             'Downloading movie JSON')
-        movie_name = movie['name']
-        return self._extract_videos(movie_id, movie_name)
+        return self._extract_playlist(
+            movie_id, playlist_name=movie.get('name'))
 
 
-class RutubePersonIE(RutubeChannelIE):
+class RutubePersonIE(RutubePlaylistBaseIE):
     IE_NAME = 'rutube:person'
     IE_DESC = 'Rutube person videos'
     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
@@ -193,3 +246,37 @@ class RutubePersonIE(RutubeChannelIE):
     }]
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
+
+
+class RutubePlaylistIE(RutubePlaylistBaseIE):
+    IE_NAME = 'rutube:playlist'
+    IE_DESC = 'Rutube playlists'
+    _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
+        'info_dict': {
+            'id': '3097',
+        },
+        'playlist_count': 27,
+    }, {
+        'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
+        'only_matching': True,
+    }]
+
+    _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
+
+    @classmethod
+    def suitable(cls, url):
+        if not super(RutubePlaylistIE, cls).suitable(url):
+            return False
+        params = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
+
+    def _next_page_url(self, page_num, playlist_id, item_kind):
+        return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
+
+    def _real_extract(self, url):
+        qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        playlist_kind = qs['pl_type'][0]
+        playlist_id = qs['pl_id'][0]
+        return self._extract_playlist(playlist_id, item_kind=playlist_kind)

youtube_dl/extractor/soundcloud.py

@@ -1,8 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
 import itertools
+import re
 
 from .common import (
     InfoExtractor,
@@ -17,6 +17,7 @@ from ..utils import (
     ExtractorError,
     int_or_none,
     unified_strdate,
+    update_url_query,
 )
 
 
@@ -120,6 +121,21 @@ class SoundcloudIE(InfoExtractor):
                 'license': 'cc-by-sa',
             },
         },
+        # private link, downloadable format
+        {
+            'url': 'https://soundcloud.com/oriuplift/uponly-238-no-talking-wav/s-AyZUd',
+            'md5': '64a60b16e617d41d0bef032b7f55441e',
+            'info_dict': {
+                'id': '340344461',
+                'ext': 'wav',
+                'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]',
+                'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366',
+                'uploader': 'Ori Uplift Music',
+                'upload_date': '20170831',
+                'duration': 7449,
+                'license': 'all-rights-reserved',
+            },
+        },
     ]
 
     _CLIENT_ID = 'JlZIsxg2hY5WnBgtn3jfS0UYCl0K8DOg'
@@ -160,11 +176,13 @@ class SoundcloudIE(InfoExtractor):
             'license': info.get('license'),
         }
         formats = []
+        query = {'client_id': self._CLIENT_ID}
+        if secret_token is not None:
+            query['secret_token'] = secret_token
         if info.get('downloadable', False):
             # We can build a direct link to the song
-            format_url = (
-                'https://api.soundcloud.com/tracks/{0}/download?client_id={1}'.format(
-                    track_id, self._CLIENT_ID))
+            format_url = update_url_query(
+                'https://api.soundcloud.com/tracks/%s/download' % track_id, query)
             formats.append({
                 'format_id': 'download',
                 'ext': info.get('original_format', 'mp3'),
@@ -176,10 +194,7 @@ class SoundcloudIE(InfoExtractor):
         # We have to retrieve the url
         format_dict = self._download_json(
             'https://api.soundcloud.com/i1/tracks/%s/streams' % track_id,
-            track_id, 'Downloading track url', query={
-                'client_id': self._CLIENT_ID,
-                'secret_token': secret_token,
-            })
+            track_id, 'Downloading track url', query=query)
 
         for key, stream_url in format_dict.items():
             abr = int_or_none(self._search_regex(
@@ -216,7 +231,7 @@ class SoundcloudIE(InfoExtractor):
             # cannot be always used, sometimes it can give an HTTP 404 error
             formats.append({
                 'format_id': 'fallback',
-                'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
+                'url': update_url_query(info['stream_url'], query),
                 'ext': ext,
             })
 

youtube_dl/extractor/toutv.py

@@ -5,7 +5,6 @@ from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     js_to_json,
-    ExtractorError,
     urlencode_postdata,
     extract_attributes,
     smuggle_url,
@@ -78,8 +77,10 @@ class TouTvIE(InfoExtractor):
     def _real_extract(self, url):
         path = self._match_id(url)
         metadata = self._download_json('http://ici.tou.tv/presentation/%s' % path, path)
+        # IsDrm does not necessarily mean the video is DRM protected (see
+        # https://github.com/rg3/youtube-dl/issues/13994).
         if metadata.get('IsDrm'):
-            raise ExtractorError('This video is DRM protected.', expected=True)
+            self.report_warning('This video is probably DRM protected.', path)
         video_id = metadata['IdMedia']
         details = metadata['Details']
         title = details['OriginalTitle']

youtube_dl/extractor/tv4.py

@@ -18,7 +18,7 @@ class TV4IE(InfoExtractor):
             tv4\.se/(?:[^/]+)/klipp/(?:.*)-|
             tv4play\.se/
             (?:
-                (?:program|barn)/(?:[^\?]+)\?video_id=|
+                (?:program|barn)/(?:[^/]+/|(?:[^\?]+)\?video_id=)|
                 iframe/video/|
                 film/|
                 sport/|
@@ -63,6 +63,10 @@ class TV4IE(InfoExtractor):
             'url': 'http://www.tv4play.se/barn/looney-tunes?video_id=3062412',
             'only_matching': True,
         },
+        {
+            'url': 'http://www.tv4play.se/program/farang/3922081',
+            'only_matching': True,
+        }
     ]
 
     def _real_extract(self, url):

youtube_dl/extractor/tvplay.py

@@ -15,7 +15,9 @@ from ..utils import (
     int_or_none,
     parse_iso8601,
     qualities,
+    smuggle_url,
     try_get,
+    unsmuggle_url,
     update_url_query,
 )
 
@@ -224,6 +226,9 @@ class TVPlayIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+        self._initialize_geo_bypass(smuggled_data.get('geo_countries'))
+
         video_id = self._match_id(url)
         geo_country = self._search_regex(
             r'https?://[^/]+\.([a-z]{2})', url,
@@ -426,4 +431,9 @@ class ViafreeIE(InfoExtractor):
                 r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](\d{6,})',
                 webpage, 'video id')
 
-        return self.url_result('mtg:%s' % video_id, TVPlayIE.ie_key())
+        return self.url_result(
+            smuggle_url(
+                'mtg:%s' % video_id,
+                {'geo_countries': [
+                    compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1]]}),
+            ie=TVPlayIE.ie_key(), video_id=video_id)

youtube_dl/extractor/twentyfourvideo.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 class TwentyFourVideoIE(InfoExtractor):
     IE_NAME = '24video'
-    _VALID_URL = r'https?://(?P<host>(?:www\.)?24video\.(?:net|me|xxx|sex|tube))/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
+    _VALID_URL = r'https?://(?P<host>(?:www\.)?24video\.(?:net|me|xxx|sex|tube|adult))/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.24video.net/video/view/1044982',
@@ -60,8 +60,8 @@ class TwentyFourVideoIE(InfoExtractor):
         duration = int_or_none(self._og_search_property(
             'duration', webpage, 'duration', fatal=False))
         timestamp = parse_iso8601(self._search_regex(
-            r'<time id="video-timeago" datetime="([^"]+)" itemprop="uploadDate">',
-            webpage, 'upload date'))
+            r'<time[^>]+\bdatetime="([^"]+)"[^>]+itemprop="uploadDate"',
+            webpage, 'upload date', fatal=False))
 
         uploader = self._html_search_regex(
             r'class="video-uploaded"[^>]*>\s*<a href="/jsecUser/movies/[^"]+"[^>]*>([^<]+)</a>',
@@ -72,7 +72,7 @@ class TwentyFourVideoIE(InfoExtractor):
             webpage, 'view count', fatal=False))
         comment_count = int_or_none(self._html_search_regex(
             r'<a[^>]+href="#tab-comments"[^>]*>(\d+) комментари',
-            webpage, 'comment count', fatal=False))
+            webpage, 'comment count', default=None))
 
         # Sets some cookies
         self._download_xml(

youtube_dl/extractor/twitch.py

@@ -28,7 +28,7 @@ from ..utils import (
 
 
 class TwitchBaseIE(InfoExtractor):
-    _VALID_URL_BASE = r'https?://(?:www\.)?twitch\.tv'
+    _VALID_URL_BASE = r'https?://(?:(?:www|go)\.)?twitch\.tv'
 
     _API_BASE = 'https://api.twitch.tv'
     _USHER_BASE = 'https://usher.ttvnw.net'
@@ -217,7 +217,7 @@ class TwitchVodIE(TwitchItemBaseIE):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:www\.)?twitch\.tv/(?:[^/]+/v|videos)/|
+                            (?:(?:www|go)\.)?twitch\.tv/(?:[^/]+/v|videos)/|
                             player\.twitch\.tv/\?.*?\bvideo=v
                         )
                         (?P<id>\d+)
@@ -458,7 +458,7 @@ class TwitchStreamIE(TwitchBaseIE):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:www\.)?twitch\.tv/|
+                            (?:(?:www|go)\.)?twitch\.tv/|
                             player\.twitch\.tv/\?.*?\bchannel=
                         )
                         (?P<id>[^/#?]+)
@@ -489,6 +489,9 @@ class TwitchStreamIE(TwitchBaseIE):
     }, {
         'url': 'https://player.twitch.tv/?channel=lotsofs',
         'only_matching': True,
+    }, {
+        'url': 'https://go.twitch.tv/food',
+        'only_matching': True,
     }]
 
     @classmethod

youtube_dl/extractor/twitter.py

@@ -229,7 +229,7 @@ class TwitterCardIE(TwitterBaseIE):
 
         title = self._search_regex(r'<title>([^<]+)</title>', webpage, 'title')
         thumbnail = config.get('posterImageUrl') or config.get('image_src')
-        duration = float_or_none(config.get('duration')) or duration
+        duration = float_or_none(config.get('duration'), scale=1000) or duration
 
         return {
             'id': video_id,
@@ -242,8 +242,9 @@ class TwitterCardIE(TwitterBaseIE):
 
 class TwitterIE(InfoExtractor):
     IE_NAME = 'twitter'
-    _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?P<user_id>[^/]+)/status/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?:i/web|(?P<user_id>[^/]+))/status/(?P<id>\d+)'
     _TEMPLATE_URL = 'https://twitter.com/%s/status/%s'
+    _TEMPLATE_STATUSES_URL = 'https://twitter.com/statuses/%s'
 
     _TESTS = [{
         'url': 'https://twitter.com/freethenipple/status/643211948184596480',
@@ -255,6 +256,7 @@ class TwitterIE(InfoExtractor):
             'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"',
             'uploader': 'FREE THE NIPPLE',
             'uploader_id': 'freethenipple',
+            'duration': 12.922,
         },
         'params': {
             'skip_download': True,  # requires ffmpeg
@@ -305,11 +307,12 @@ class TwitterIE(InfoExtractor):
         'info_dict': {
             'id': '700207533655363584',
             'ext': 'mp4',
-            'title': 'Donte - BEAT PROD: @suhmeduh #Damndaniel',
-            'description': 'Donte on Twitter: "BEAT PROD: @suhmeduh  https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
+            'title': 'あかさ - BEAT PROD: @suhmeduh #Damndaniel',
+            'description': 'あかさ on Twitter: "BEAT PROD: @suhmeduh  https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
             'thumbnail': r're:^https?://.*\.jpg',
-            'uploader': 'Donte',
+            'uploader': 'あかさ',
             'uploader_id': 'jaydingeer',
+            'duration': 30.0,
         },
         'params': {
             'skip_download': True,  # requires ffmpeg
@@ -320,9 +323,9 @@ class TwitterIE(InfoExtractor):
         'info_dict': {
             'id': 'MIOxnrUteUd',
             'ext': 'mp4',
-            'title': 'FilmDrunk - Vine of the day',
-            'description': 'FilmDrunk on Twitter: "Vine of the day https://t.co/xmTvRdqxWf"',
-            'uploader': 'FilmDrunk',
+            'title': 'Vince Mancini - Vine of the day',
+            'description': 'Vince Mancini on Twitter: "Vine of the day https://t.co/xmTvRdqxWf"',
+            'uploader': 'Vince Mancini',
             'uploader_id': 'Filmdrunk',
             'timestamp': 1402826626,
             'upload_date': '20140615',
@@ -337,6 +340,7 @@ class TwitterIE(InfoExtractor):
             'description': 'Captain America on Twitter: "@King0fNerd Are you sure you made the right choice? Find out in theaters. https://t.co/GpgYi9xMJI"',
             'uploader_id': 'captainamerica',
             'uploader': 'Captain America',
+            'duration': 3.17,
         },
         'params': {
             'skip_download': True,  # requires ffmpeg
@@ -364,10 +368,26 @@ class TwitterIE(InfoExtractor):
             'description': 'عالم الأخبار on Twitter: "كلمة تاريخية بجلسة الجناسي التاريخية.. النائب خالد مؤنس العتيبي للمعارضين : اتقوا الله .. الظلم ظلمات يوم القيامة   https://t.co/xg6OhpyKfN"',
             'uploader': 'عالم الأخبار',
             'uploader_id': 'news_al3alm',
+            'duration': 277.4,
         },
         'params': {
             'format': 'best[format_id^=http-]',
         },
+    }, {
+        'url': 'https://twitter.com/i/web/status/910031516746514432',
+        'info_dict': {
+            'id': '910031516746514432',
+            'ext': 'mp4',
+            'title': 'Préfet de Guadeloupe - [Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre.',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'description': 'Préfet de Guadeloupe on Twitter: "[Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre. https://t.co/mwx01Rs4lo"',
+            'uploader': 'Préfet de Guadeloupe',
+            'uploader_id': 'Prefet971',
+            'duration': 47.48,
+        },
+        'params': {
+            'skip_download': True,  # requires ffmpeg
+        },
     }]
 
     def _real_extract(self, url):
@@ -376,11 +396,15 @@ class TwitterIE(InfoExtractor):
         twid = mobj.group('id')
 
         webpage, urlh = self._download_webpage_handle(
-            self._TEMPLATE_URL % (user_id, twid), twid)
+            self._TEMPLATE_STATUSES_URL % twid, twid)
 
         if 'twitter.com/account/suspended' in urlh.geturl():
             raise ExtractorError('Account suspended by Twitter.', expected=True)
 
+        if user_id is None:
+            mobj = re.match(self._VALID_URL, urlh.geturl())
+            user_id = mobj.group('user_id')
+
         username = remove_end(self._og_search_title(webpage), ' on Twitter')
 
         title = description = self._og_search_description(webpage).strip('').replace('\n', ' ').strip('“”')

youtube_dl/extractor/vgtv.py

@@ -42,7 +42,7 @@ class VGTVIE(XstreamIE):
                     )
                     /?
                     (?:
-                        \#!/(?:video|live)/|
+                        (?:\#!/)?(?:video|live)/|
                         embed?.*id=|
                         articles/
                     )|
@@ -146,7 +146,11 @@ class VGTVIE(XstreamIE):
         {
             'url': 'abtv:140026',
             'only_matching': True,
-        }
+        },
+        {
+            'url': 'http://www.vgtv.no/video/84196/hevnen-er-soet-episode-10-abu',
+            'only_matching': True,
+        },
     ]
 
     def _real_extract(self, url):

youtube_dl/extractor/vice.py

@@ -7,6 +7,7 @@ import hashlib
 import json
 
 from .adobepass import AdobePassIE
+from .youtube import YoutubeIE
 from .common import InfoExtractor
 from ..compat import compat_HTTPError
 from ..utils import (
@@ -261,11 +262,9 @@ class ViceArticleIE(InfoExtractor):
         if embed_code:
             return _url_res('ooyala:%s' % embed_code, 'Ooyala')
 
-        youtube_url = self._html_search_regex(
-            r'<iframe[^>]+src="(.*youtube\.com/.*)"',
-            body, 'YouTube URL', default=None)
+        youtube_url = YoutubeIE._extract_url(body)
         if youtube_url:
-            return _url_res(youtube_url, 'Youtube')
+            return _url_res(youtube_url, YoutubeIE.ie_key())
 
         video_url = self._html_search_regex(
             r'data-video-url="([^"]+)"',

youtube_dl/extractor/vidme.py

@@ -263,29 +263,35 @@ class VidmeListBaseIE(InfoExtractor):
 
 class VidmeUserIE(VidmeListBaseIE):
     IE_NAME = 'vidme:user'
-    _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]{6,})(?!/likes)(?:[^\da-zA-Z]|$)'
+    _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z_-]{6,})(?!/likes)(?:[^\da-zA-Z_-]|$)'
     _API_ITEM = 'list'
     _TITLE = 'Videos'
-    _TEST = {
-        'url': 'https://vid.me/EFARCHIVE',
+    _TESTS = [{
+        'url': 'https://vid.me/MasakoX',
         'info_dict': {
-            'id': '3834632',
-            'title': 'EFARCHIVE - %s' % _TITLE,
+            'id': '16112341',
+            'title': 'MasakoX - %s' % _TITLE,
         },
-        'playlist_mincount': 238,
-    }
+        'playlist_mincount': 191,
+    }, {
+        'url': 'https://vid.me/unsQuare_netWork',
+        'only_matching': True,
+    }]
 
 
 class VidmeUserLikesIE(VidmeListBaseIE):
     IE_NAME = 'vidme:user:likes'
-    _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]{6,})/likes'
+    _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z_-]{6,})/likes'
     _API_ITEM = 'likes'
     _TITLE = 'Likes'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://vid.me/ErinAlexis/likes',
         'info_dict': {
             'id': '6483530',
             'title': 'ErinAlexis - %s' % _TITLE,
         },
         'playlist_mincount': 415,
-    }
+    }, {
+        'url': 'https://vid.me/Kaleidoscope-Ish/likes',
+        'only_matching': True,
+    }]

youtube_dl/extractor/viidea.py

@@ -4,12 +4,14 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urlparse,
+    compat_HTTPError,
     compat_str,
+    compat_urlparse,
 )
 from ..utils import (
-    parse_duration,
+    ExtractorError,
     js_to_json,
+    parse_duration,
     parse_iso8601,
 )
 
@@ -128,9 +130,16 @@ class ViideaIE(InfoExtractor):
 
         base_url = self._proto_relative_url(cfg['livepipe'], 'http:')
 
-        lecture_data = self._download_json(
-            '%s/site/api/lecture/%s?format=json' % (base_url, lecture_id),
-            lecture_id)['lecture'][0]
+        try:
+            lecture_data = self._download_json(
+                '%s/site/api/lecture/%s?format=json' % (base_url, lecture_id),
+                lecture_id)['lecture'][0]
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                msg = self._parse_json(
+                    e.cause.read().decode('utf-8'), lecture_id)
+                raise ExtractorError(msg['detail'], expected=True)
+            raise
 
         lecture_info = {
             'id': lecture_id,

youtube_dl/extractor/viki.py

@@ -23,9 +23,9 @@ class VikiBaseIE(InfoExtractor):
     _API_QUERY_TEMPLATE = '/v4/%sapp=%s&t=%s&site=www.viki.com'
     _API_URL_TEMPLATE = 'http://api.viki.io%s&sig=%s'
 
-    _APP = '65535a'
+    _APP = '100005a'
     _APP_VERSION = '2.2.5.1428709186'
-    _APP_SECRET = '-$iJ}@p7!G@SyU/je1bEyWg}upLu-6V6-Lg9VD(]siH,r.,m-r|ulZ,U4LC/SeR)'
+    _APP_SECRET = 'MM_d*yP@`&1@]@!AVrXf_o-HVEnoTnm$O-ti4[G~$JDI/Dc-&piU&z&5.;:}95=Iad'
 
     _GEO_BYPASS = False
     _NETRC_MACHINE = 'viki'

youtube_dl/extractor/vk.py

@@ -25,6 +25,7 @@ from ..utils import (
 from .dailymotion import DailymotionIE
 from .pladform import PladformIE
 from .vimeo import VimeoIE
+from .youtube import YoutubeIE
 
 
 class VKBaseIE(InfoExtractor):
@@ -345,11 +346,9 @@ class VKIE(VKBaseIE):
             if re.search(error_re, info_page):
                 raise ExtractorError(error_msg % video_id, expected=True)
 
-        youtube_url = self._search_regex(
-            r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
-            info_page, 'youtube iframe', default=None)
+        youtube_url = YoutubeIE._extract_url(info_page)
         if youtube_url:
-            return self.url_result(youtube_url, 'Youtube')
+            return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
 
         vimeo_url = VimeoIE._extract_url(url, info_page)
         if vimeo_url is not None:

youtube_dl/extractor/youtube.py

@@ -16,6 +16,7 @@ from ..jsinterp import JSInterpreter
 from ..swfinterp import SWFInterpreter
 from ..compat import (
     compat_chr,
+    compat_kwargs,
     compat_parse_qs,
     compat_urllib_parse_unquote,
     compat_urllib_parse_unquote_plus,
@@ -245,6 +246,11 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
         return True
 
+    def _download_webpage(self, *args, **kwargs):
+        kwargs.setdefault('query', {})['disable_polymer'] = 'true'
+        return super(YoutubeBaseInfoExtractor, self)._download_webpage(
+            *args, **compat_kwargs(kwargs))
+
     def _real_initialize(self):
         if self._downloader is None:
             return
@@ -1003,6 +1009,27 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'Skipping DASH manifest',
             ],
         },
+        {
+            # The following content has been identified by the YouTube community
+            # as inappropriate or offensive to some audiences.
+            'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
+            'info_dict': {
+                'id': '6SJNVb0GnPI',
+                'ext': 'mp4',
+                'title': 'Race Differences in Intelligence',
+                'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
+                'duration': 965,
+                'upload_date': '20140124',
+                'uploader': 'New Century Foundation',
+                'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
+                'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
+                'license': 'Standard YouTube License',
+                'view_count': int,
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
         {
             # itag 212
             'url': '1t24XAntNCY',
@@ -1347,6 +1374,43 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             playback_url, video_id, 'Marking watched',
             'Unable to mark watched', fatal=False)
 
+    @staticmethod
+    def _extract_urls(webpage):
+        # Embedded YouTube player
+        entries = [
+            unescapeHTML(mobj.group('url'))
+            for mobj in re.finditer(r'''(?x)
+            (?:
+                <iframe[^>]+?src=|
+                data-video-url=|
+                <embed[^>]+?src=|
+                embedSWF\(?:\s*|
+                <object[^>]+data=|
+                new\s+SWFObject\(
+            )
+            (["\'])
+                (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
+                (?:embed|v|p)/.+?)
+            \1''', webpage)]
+
+        # lazyYT YouTube embed
+        entries.extend(list(map(
+            unescapeHTML,
+            re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
+
+        # Wordpress "YouTube Video Importer" plugin
+        matches = re.findall(r'''(?x)<div[^>]+
+            class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
+            data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
+        entries.extend(m[-1] for m in matches)
+
+        return entries
+
+    @staticmethod
+    def _extract_url(webpage):
+        urls = YoutubeIE._extract_urls(webpage)
+        return urls[0] if urls else None
+
     @classmethod
     def extract_id(cls, url):
         mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
@@ -1437,9 +1501,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             if dash_mpd and dash_mpd[0] not in dash_mpds:
                 dash_mpds.append(dash_mpd[0])
 
+        is_live = None
+        view_count = None
+
+        def extract_view_count(v_info):
+            return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
+
         # Get video info
         embed_webpage = None
-        is_live = None
         if re.search(r'player-age-gate-content">', video_webpage) is not None:
             age_gate = True
             # We simulate the access to the video from www.youtube.com/v/{video_id}
@@ -1509,6 +1578,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         continue
                     get_video_info = compat_parse_qs(video_info_webpage)
                     add_dash_mpd(get_video_info)
+                    if view_count is None:
+                        view_count = extract_view_count(get_video_info)
                     if not video_info:
                         video_info = get_video_info
                     if 'token' in get_video_info:
@@ -1592,10 +1663,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 return self.playlist_result(entries, video_id, video_title, video_description)
             self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
 
-        if 'view_count' in video_info:
-            view_count = int(video_info['view_count'][0])
-        else:
-            view_count = None
+        if view_count is None:
+            view_count = extract_view_count(video_info)
 
         # Check for "rental" videos
         if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
@@ -1639,10 +1708,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         if not upload_date:
             upload_date = self._search_regex(
                 [r'(?s)id="eow-date.*?>(.*?)</span>',
-                 r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
+                 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
                 video_webpage, 'upload date', default=None)
-            if upload_date:
-                upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
         upload_date = unified_strdate(upload_date)
 
         video_license = self._html_search_regex(
@@ -2028,7 +2095,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
                      |
                         (%(playlist_id)s)
                      )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
-    _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
+    _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
     _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
     IE_NAME = 'youtube:playlist'
     _TESTS = [{

youtube_dl/options.py

@@ -847,7 +847,7 @@ def parseOpts(overrideArguments=None):
     postproc.add_option(
         '--convert-subs', '--convert-subtitles',
         metavar='FORMAT', dest='convertsubtitles', default=None,
-        help='Convert the subtitles to other format (currently supported: srt|ass|vtt)')
+        help='Convert the subtitles to other format (currently supported: srt|ass|vtt|lrc)')
 
     parser.add_option_group(general)
     parser.add_option_group(network)

youtube_dl/postprocessor/ffmpeg.py

@@ -585,7 +585,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
                 dfxp_file = old_file
                 srt_file = subtitles_filename(filename, lang, 'srt')
 
-                with io.open(dfxp_file, 'rt', encoding='utf-8') as f:
+                with open(dfxp_file, 'rb') as f:
                     srt_data = dfxp2srt(f.read())
 
                 with io.open(srt_file, 'wt', encoding='utf-8') as f:

youtube_dl/utils.py

@@ -596,7 +596,7 @@ def unescapeHTML(s):
     assert type(s) == compat_str
 
     return re.sub(
-        r'&([^;]+;)', lambda m: _htmlentity_transform(m.group(1)), s)
+        r'&([^&;]+;)', lambda m: _htmlentity_transform(m.group(1)), s)
 
 
 def get_subprocess_encoding():
@@ -1815,6 +1815,10 @@ def float_or_none(v, scale=1, invscale=1, default=None):
         return default
 
 
+def bool_or_none(v, default=None):
+    return v if isinstance(v, bool) else default
+
+
 def strip_or_none(v):
     return None if v is None else v.strip()
 
@@ -2568,14 +2572,18 @@ def srt_subtitles_timecode(seconds):
 
 
 def dfxp2srt(dfxp_data):
+    '''
+    @param dfxp_data A bytes-like object containing DFXP data
+    @returns A unicode object containing converted SRT data
+    '''
     LEGACY_NAMESPACES = (
-        ('http://www.w3.org/ns/ttml', [
-            'http://www.w3.org/2004/11/ttaf1',
-            'http://www.w3.org/2006/04/ttaf1',
-            'http://www.w3.org/2006/10/ttaf1',
+        (b'http://www.w3.org/ns/ttml', [
+            b'http://www.w3.org/2004/11/ttaf1',
+            b'http://www.w3.org/2006/04/ttaf1',
+            b'http://www.w3.org/2006/10/ttaf1',
         ]),
-        ('http://www.w3.org/ns/ttml#styling', [
-            'http://www.w3.org/ns/ttml#style',
+        (b'http://www.w3.org/ns/ttml#styling', [
+            b'http://www.w3.org/ns/ttml#style',
         ]),
     )
 
@@ -2670,7 +2678,7 @@ def dfxp2srt(dfxp_data):
         for ns in v:
             dfxp_data = dfxp_data.replace(ns, k)
 
-    dfxp = compat_etree_fromstring(dfxp_data.encode('utf-8'))
+    dfxp = compat_etree_fromstring(dfxp_data)
     out = []
     paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall('.//p')
 

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.08.18'
+__version__ = '2017.09.24'