release 2015.01.23.4

This fixes #2288, #2506, #2607, #3681, #4741, #4767.

.gitignore

@@ -31,3 +31,5 @@ updates_key.pem
 test/testdata
 .tox
 youtube-dl.zsh
+.idea
+.idea/*

.travis.yml

@@ -9,7 +9,6 @@ notifications:
   email:
     - filippo.valsorda@gmail.com
     - phihag@phihag.de
-    - jaime.marquinez.ferrandiz+travis@gmail.com
     - yasoob.khld@gmail.com
 #  irc:
 #    channels:

AUTHORS

@@ -93,3 +93,14 @@ Zack Fernandes
 cryptonaut
 Adrian Kretz
 Mathias Rav
+Petr Kutalek
+Will Glynn
+Max Reimann
+Cédric Luthi
+Thijs Vermeir
+Joel Leclerc
+Christopher Krooss
+Ondřej Caletka
+Dinesh S
+Johan K. Jensen
+Yen Chi Hsuan

CONTRIBUTING.md

@@ -44,7 +44,7 @@ In particular, every site support request issue should only pertain to services
 
 ###  Is anyone going to need the feature?
 
-Only post features that you (or an incapicated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
+Only post features that you (or an incapacitated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
 
 ###  Is your question about youtube-dl?
 

Makefile

@@ -1,4 +1,4 @@
-all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
+all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
 
 clean:
 	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json CONTRIBUTING.md.tmp
@@ -36,12 +36,7 @@ install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtu
 	install -m 644 youtube-dl.fish $(DESTDIR)$(SYSCONFDIR)/fish/completions/youtube-dl.fish
 
 codetest:
-	PYFLAKES_OUT=$$(pyflakes youtube_dl | grep -v youtube_dl/extractor/__init__.py); \
-	if test -n "$$PYFLAKES_OUT"; then \
-		echo "$$PYFLAKES_OUT"; \
-		exit 1; \
-	fi
-	pep8 . --ignore E501
+	flake8 .
 
 test:
 	#nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose --processes 4 test
@@ -51,11 +46,11 @@ test:
 ot: offlinetest
 
 offlinetest: codetest
-	nosetests --verbose test --exclude test_download --exclude test_age_restriction --exclude test_subtitles --exclude test_write_annotations
+	nosetests --verbose test --exclude test_download --exclude test_age_restriction --exclude test_subtitles --exclude test_write_annotations --exclude test_youtube_lists
 
 tar: youtube-dl.tar.gz
 
-.PHONY: all clean install test tar bash-completion pypi-files zsh-completion fish-completion ot offlinetest codetest
+.PHONY: all clean install test tar bash-completion pypi-files zsh-completion fish-completion ot offlinetest codetest supportedsites
 
 pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1 youtube-dl.fish
 
@@ -68,11 +63,14 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
 	chmod a+x youtube-dl
 
 README.md: youtube_dl/*.py youtube_dl/*/*.py
-	COLUMNS=80 python -m youtube_dl --help | python devscripts/make_readme.py
+	COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py
 
 CONTRIBUTING.md: README.md
 	python devscripts/make_contributing.py README.md CONTRIBUTING.md
 
+supportedsites:
+	python devscripts/make_supportedsites.py docs/supportedsites.md
+
 README.txt: README.md
 	pandoc -f markdown -t plain README.md -o README.txt
 

README.md

@@ -1,7 +1,15 @@
 youtube-dl - download videos from youtube.com or other video platforms
 
-# SYNOPSIS
-**youtube-dl** [OPTIONS] URL [URL...]
+- [INSTALLATION](#installation)
+- [DESCRIPTION](#description)
+- [OPTIONS](#options)
+- [CONFIGURATION](#configuration)
+- [OUTPUT TEMPLATE](#output-template)
+- [VIDEO SELECTION](#video-selection)
+- [FAQ](#faq)
+- [DEVELOPER INSTRUCTIONS](#developer-instructions)
+- [BUGS](#bugs)
+- [COPYRIGHT](#copyright)
 
 # INSTALLATION
 
@@ -34,6 +42,8 @@ YouTube.com and a few more sites. It requires the Python interpreter, version
 your Unix box, on Windows or on Mac OS X. It is released to the public domain,
 which means you can modify it, redistribute it or use it however you like.
 
+    youtube-dl [OPTIONS] URL [URL...]
+
 # OPTIONS
     -h, --help                       print this help text and exit
     --version                        print program version and exit
@@ -50,10 +60,6 @@ which means you can modify it, redistribute it or use it however you like.
                                      they would handle
     --extractor-descriptions         Output descriptions of all supported
                                      extractors
-    --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in
-                                     an empty string (--proxy "") for direct
-                                     connection
-    --socket-timeout None            Time to wait before giving up, in seconds
     --default-search PREFIX          Use this prefix for unqualified URLs. For
                                      example "gvsearch2:" downloads two videos
                                      from google videos for  youtube-dl "large
@@ -72,6 +78,18 @@ which means you can modify it, redistribute it or use it however you like.
     --flat-playlist                  Do not extract the videos of a playlist,
                                      only list them.
 
+## Network Options:
+    --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in
+                                     an empty string (--proxy "") for direct
+                                     connection
+    --socket-timeout SECONDS         Time to wait before giving up, in seconds
+    --source-address IP              Client-side IP address to bind to
+                                     (experimental)
+    -4, --force-ipv4                 Make all connections via IPv4
+                                     (experimental)
+    -6, --force-ipv6                 Make all connections via IPv6
+                                     (experimental)
+
 ## Video Selection:
     --playlist-start NUMBER          playlist video to start at (default is 1)
     --playlist-end NUMBER            playlist video to end at (default is last)
@@ -209,6 +227,8 @@ which means you can modify it, redistribute it or use it however you like.
                                      for each command-line argument. If the URL
                                      refers to a playlist, dump the whole
                                      playlist information in a single line.
+    --print-json                     Be quiet and print the video information as
+                                     JSON (video is still being downloaded).
     --newline                        output progress bar as new lines
     --no-progress                    do not print progress bar
     --console-title                  display progress in console titlebar
@@ -219,6 +239,10 @@ which means you can modify it, redistribute it or use it however you like.
                                      files in the current directory to debug
                                      problems
     --print-traffic                  Display sent and read HTTP traffic
+    -C, --call-home                  Contact the youtube-dl server for
+                                     debugging.
+    --no-call-home                   Do NOT contact the youtube-dl server for
+                                     debugging.
 
 ## Workarounds:
     --encoding ENCODING              Force the specified encoding (experimental)
@@ -235,14 +259,29 @@ which means you can modify it, redistribute it or use it however you like.
     --bidi-workaround                Work around terminals that lack
                                      bidirectional text support. Requires bidiv
                                      or fribidi executable in PATH
+    --sleep-interval SECONDS         Number of seconds to sleep before each
+                                     download.
 
 ## Video Format Options:
     -f, --format FORMAT              video format code, specify the order of
-                                     preference using slashes: -f 22/17/18 .  -f
-                                     mp4 , -f m4a and  -f flv  are also
-                                     supported. You can also use the special
-                                     names "best", "bestvideo", "bestaudio",
-                                     "worst", "worstvideo" and "worstaudio". By
+                                     preference using slashes, as in -f 22/17/18
+                                     .  Instead of format codes, you can select
+                                     by extension for the extensions aac, m4a,
+                                     mp3, mp4, ogg, wav, webm. You can also use
+                                     the special names "best", "bestvideo",
+                                     "bestaudio", "worst".  You can filter the
+                                     video results by putting a condition in
+                                     brackets, as in -f "best[height=720]" (or
+                                     -f "[filesize>10M]").  This works for
+                                     filesize, height, width, tbr, abr, and vbr
+                                     and the comparisons <, <=, >, >=, =, != .
+                                     Formats for which the value is not known
+                                     are excluded unless you put a question mark
+                                     (?) after the operator. You can combine
+                                     format filters, so  -f "[height <=?
+                                     720][tbr>500]" selects up to 720p videos
+                                     (or videos where the height is not known)
+                                     with a bitrate of at least 500 KBit/s. By
                                      default, youtube-dl will pick the best
                                      quality. Use commas to download multiple
                                      audio formats, such as -f
@@ -259,6 +298,10 @@ which means you can modify it, redistribute it or use it however you like.
     -F, --list-formats               list all available formats
     --youtube-skip-dash-manifest     Do not download the DASH manifest on
                                      YouTube videos
+    --merge-output-format FORMAT     If a merge is required (e.g.
+                                     bestvideo+bestaudio), output to given
+                                     container format. One of mkv, mp4, ogg,
+                                     webm, flv.Ignored if no merge is required
 
 ## Subtitle Options:
     --write-sub                      write subtitle file
@@ -275,7 +318,8 @@ which means you can modify it, redistribute it or use it however you like.
 
 ## Authentication Options:
     -u, --username USERNAME          login with this account ID
-    -p, --password PASSWORD          account password
+    -p, --password PASSWORD          account password. If this option is left
+                                     out, youtube-dl will ask interactively.
     -2, --twofactor TWOFACTOR        two-factor auth code
     -n, --netrc                      use .netrc authentication data
     --video-password PASSWORD        video password (vimeo, smotri)
@@ -305,6 +349,11 @@ which means you can modify it, redistribute it or use it however you like.
     --add-metadata                   write metadata to the video file
     --xattrs                         write metadata to the video file's xattrs
                                      (using dublin core and xdg standards)
+    --fixup POLICY                   (experimental) Automatically correct known
+                                     faults of the file. One of never (do
+                                     nothing), warn (only emit a warning),
+                                     detect_or_warn(check whether we can do
+                                     anything about it, warn otherwise
     --prefer-avconv                  Prefer avconv over ffmpeg for running the
                                      postprocessors (default)
     --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
@@ -316,7 +365,7 @@ which means you can modify it, redistribute it or use it however you like.
 
 # CONFIGURATION
 
-You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
+You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<user name>\youtube-dl.conf`.
 
 # OUTPUT TEMPLATE
 
@@ -410,9 +459,15 @@ Apparently YouTube requires you to pass a CAPTCHA test if you download too much.
 
 Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
 
-### The links provided by youtube-dl -g are not working anymore
+### I extracted a video URL with -g, but it does not play on another machine / in my webbrowser.
 
-The URLs youtube-dl outputs require the downloader to have the correct cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
+It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies.  Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
+
+It may be beneficial to use IPv6; in some cases, the restrictions are only applied to IPv4. Some services (sometimes only for a subset of videos) do not restrict the video URL by IP address, cookie, or user-agent, but these are the exception rather than the rule.
+
+Please bear in mind that some URL protocols are **not** supported by browsers out of the box, including RTMP. If you are using -g, your own downloader must support these as well.
+
+If you want to play the video on a machine that is not running youtube-dl, you can relay the video content from the machine that runs youtube-dl. You can use `-o -` to let youtube-dl stream a video to stdout, or simply allow the player to download the files written by youtube-dl in turn.
 
 ### ERROR: no fmt_url_map or conn information found in video info
 
@@ -439,6 +494,26 @@ Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unz
 
 To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29).
 
+### On Windows, how should I set up ffmpeg and youtube-dl? Where should I put the exe files?
+
+If you put youtube-dl and ffmpeg in the same directory that you're running the command from, it will work, but that's rather cumbersome.
+
+To make a different directory work - either for ffmpeg, or for youtube-dl, or for both - simply create the directory (say, `C:\bin`, or `C:\Users\<User name>\bin`), put all the executables directly in there, and then [set your PATH environment variable](https://www.java.com/en/download/help/path.xml) to include that directory.
+
+From then on, after restarting your shell, you will be able to access both youtube-dl and ffmpeg (and youtube-dl will be able to find ffmpeg) by simply typing `youtube-dl` or `ffmpeg`, no matter what directory you're in.
+
+### How do I put downloads into a specific folder?
+
+Use the `-o` to specify an [output template](#output-template), for example `-o "/home/user/videos/%(title)s-%(id)s.%(ext)s"`. If you want this for all of your downloads, put the option into your [configuration file](#configuration).
+
+### How 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). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/v/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.
+
+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.
+
+If you want to find out whether a given URL is supported, simply call youtube-dl with it. If you get no videos back, chances are the URL is either not referring to a video or unsupported. You can find out which by examining the output (if you run youtube-dl on the console) or catching an `UnsupportedError` exception if you run it from a Python program.
+
 # 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.
@@ -529,54 +604,59 @@ youtube-dl makes the best effort to be a good command-line program, and thus sho
 
 From a Python program, you can embed youtube-dl in a more powerful fashion, like this:
 
-    import youtube_dl
+```python
+import youtube_dl
 
-    ydl_opts = {}
-    with youtube_dl.YoutubeDL(ydl_opts) as ydl:
-        ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
+ydl_opts = {}
+with youtube_dl.YoutubeDL(ydl_opts) as ydl:
+    ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
+```
 
 Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L69). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
 
 Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
 
-
-    import youtube_dl
+```python
+import youtube_dl
 
 
-    class MyLogger(object):
-        def debug(self, msg):
-            pass
+class MyLogger(object):
+    def debug(self, msg):
+        pass
 
-        def warning(self, msg):
-            pass
+    def warning(self, msg):
+        pass
 
-        def error(self, msg):
-            print(msg)
+    def error(self, msg):
+        print(msg)
 
 
-    def my_hook(d):
-        if d['status'] == 'finished':
-            print('Done downloading, now converting ...')
+def my_hook(d):
+    if d['status'] == 'finished':
+        print('Done downloading, now converting ...')
 
 
-    ydl_opts = {
-        'format': 'bestaudio/best',
-        'postprocessors': [{
-            'key': 'FFmpegExtractAudio',
-            'preferredcodec': 'mp3',
-            'preferredquality': '192',
-        }],
-        'logger': MyLogger(),
-        'progress_hooks': [my_hook],
-    }
-    with youtube_dl.YoutubeDL(ydl_opts) as ydl:
-        ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
+ydl_opts = {
+    'format': 'bestaudio/best',
+    'postprocessors': [{
+        'key': 'FFmpegExtractAudio',
+        'preferredcodec': 'mp3',
+        'preferredquality': '192',
+    }],
+    'logger': MyLogger(),
+    'progress_hooks': [my_hook],
+}
+with youtube_dl.YoutubeDL(ydl_opts) as ydl:
+    ydl.download(['http://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 so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the irc channel #youtube-dl on freenode.
 
-Please include the full output of the command when run with `--verbose`. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
+**Please include the full output of youtube-dl when run with `-v`**.
+
+The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
 
 Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
 

devscripts/gh-pages/update-sites.py

@@ -16,7 +16,7 @@ def main():
         template = tmplf.read()
 
     ie_htmls = []
-    for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower()):
+    for ie in youtube_dl.list_extractors(age_limit=None):
         ie_html = '<b>{}</b>'.format(ie.IE_NAME)
         ie_desc = getattr(ie, 'IE_DESC', None)
         if ie_desc is False:

devscripts/make_contributing.py

@@ -1,20 +1,20 @@
 #!/usr/bin/env python
 from __future__ import unicode_literals
 
-import argparse
 import io
+import optparse
 import re
 
 
 def main():
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        'INFILE', help='README.md file name to read from')
-    parser.add_argument(
-        'OUTFILE', help='CONTRIBUTING.md file name to write to')
-    args = parser.parse_args()
+    parser = optparse.OptionParser(usage='%prog INFILE OUTFILE')
+    options, args = parser.parse_args()
+    if len(args) != 2:
+        parser.error('Expected an input and an output filename')
 
-    with io.open(args.INFILE, encoding='utf-8') as inf:
+    infile, outfile = args
+
+    with io.open(infile, encoding='utf-8') as inf:
         readme = inf.read()
 
     bug_text = re.search(
@@ -25,7 +25,7 @@ def main():
 
     out = bug_text + dev_text
 
-    with io.open(args.OUTFILE, 'w', encoding='utf-8') as outf:
+    with io.open(outfile, 'w', encoding='utf-8') as outf:
         outf.write(out)
 
 if __name__ == '__main__':

devscripts/make_supportedsites.py

@@ -0,0 +1,45 @@
+#!/usr/bin/env python
+from __future__ import unicode_literals
+
+import io
+import optparse
+import os
+import sys
+
+
+# Import youtube_dl
+ROOT_DIR = os.path.join(os.path.dirname(__file__), '..')
+sys.path.append(ROOT_DIR)
+import youtube_dl
+
+
+def main():
+    parser = optparse.OptionParser(usage='%prog OUTFILE.md')
+    options, args = parser.parse_args()
+    if len(args) != 1:
+        parser.error('Expected an output filename')
+
+    outfile, = args
+
+    def gen_ies_md(ies):
+        for ie in ies:
+            ie_md = '**{0}**'.format(ie.IE_NAME)
+            ie_desc = getattr(ie, 'IE_DESC', None)
+            if ie_desc is False:
+                continue
+            if ie_desc is not None:
+                ie_md += ': {0}'.format(ie.IE_DESC)
+            if not ie.working():
+                ie_md += ' (Currently broken)'
+            yield ie_md
+
+    ies = sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower())
+    out = '# Supported sites\n' + ''.join(
+        ' - ' + md + '\n'
+        for md in gen_ies_md(ies))
+
+    with io.open(outfile, 'w', encoding='utf-8') as outf:
+        outf.write(out)
+
+if __name__ == '__main__':
+    main()

devscripts/prepare_manpage.py

@@ -11,8 +11,19 @@ README_FILE = os.path.join(ROOT_DIR, 'README.md')
 with io.open(README_FILE, encoding='utf-8') as f:
     readme = f.read()
 
-PREFIX = '%YOUTUBE-DL(1)\n\n# NAME\n'
-readme = re.sub(r'(?s)# INSTALLATION.*?(?=# DESCRIPTION)', '', readme)
+PREFIX = '''%YOUTUBE-DL(1)
+
+# NAME
+
+youtube\-dl \- download videos from youtube.com or other video platforms
+
+# SYNOPSIS
+
+**youtube-dl** \[OPTIONS\] URL [URL...]
+
+'''
+readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme)
+readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme)
 readme = PREFIX + readme
 
 if sys.version_info < (3, 0):

docs/supportedsites.md

@@ -0,0 +1,500 @@
+# Supported sites
+ - **1up.com**
+ - **220.ro**
+ - **24video**
+ - **3sat**
+ - **4tube**
+ - **56.com**
+ - **5min**
+ - **8tracks**
+ - **9gag**
+ - **abc.net.au**
+ - **AcademicEarth:Course**
+ - **AddAnime**
+ - **AdobeTV**
+ - **AdultSwim**
+ - **Aftonbladet**
+ - **AlJazeera**
+ - **Allocine**
+ - **anitube.se**
+ - **AnySex**
+ - **Aparat**
+ - **AppleTrailers**
+ - **archive.org**: archive.org videos
+ - **ARD**
+ - **ARD:mediathek**
+ - **arte.tv**
+ - **arte.tv:+7**
+ - **arte.tv:concert**
+ - **arte.tv:creative**
+ - **arte.tv:ddc**
+ - **arte.tv:embed**
+ - **arte.tv:future**
+ - **audiomack**
+ - **AUEngine**
+ - **Azubu**
+ - **bambuser**
+ - **bambuser:channel**
+ - **Bandcamp**
+ - **Bandcamp:album**
+ - **bbc.co.uk**: BBC iPlayer
+ - **Beeg**
+ - **BehindKink**
+ - **Bet**
+ - **Bild**: Bild.de
+ - **BiliBili**
+ - **blinkx**
+ - **blip.tv:user**
+ - **BlipTV**
+ - **Bloomberg**
+ - **Bpb**: Bundeszentrale für politische Bildung
+ - **BR**: Bayerischer Rundfunk Mediathek
+ - **Break**
+ - **Brightcove**
+ - **BuzzFeed**
+ - **BYUtv**
+ - **Canal13cl**
+ - **canalc2.tv**
+ - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
+ - **CBS**
+ - **CBSNews**: CBS News
+ - **CeskaTelevize**
+ - **channel9**: Channel 9
+ - **Chilloutzone**
+ - **Cinchcast**
+ - **Cinemassacre**
+ - **clipfish**
+ - **cliphunter**
+ - **Clipsyndicate**
+ - **Cloudy**
+ - **Clubic**
+ - **cmt.com**
+ - **CNET**
+ - **CNN**
+ - **CNNBlogs**
+ - **CollegeHumor**
+ - **ComCarCoff**
+ - **ComedyCentral**
+ - **ComedyCentralShows**: The Daily Show / The Colbert Report
+ - **CondeNast**: Condé Nast media group: Condé Nast, GQ, Glamour, Vanity Fair, Vogue, W Magazine, WIRED
+ - **Cracked**
+ - **Criterion**
+ - **Crunchyroll**
+ - **crunchyroll:playlist**
+ - **CSpan**: C-SPAN
+ - **culturebox.francetvinfo.fr**
+ - **dailymotion**
+ - **dailymotion:playlist**
+ - **dailymotion:user**
+ - **daum.net**
+ - **DBTV**
+ - **DeezerPlaylist**
+ - **defense.gouv.fr**
+ - **Discovery**
+ - **divxstage**: DivxStage
+ - **Dotsub**
+ - **Dropbox**
+ - **DrTuber**
+ - **DRTV**
+ - **Dump**
+ - **dvtv**: http://video.aktualne.cz/
+ - **EbaumsWorld**
+ - **eHow**
+ - **Einthusan**
+ - **eitb.tv**
+ - **EllenTV**
+ - **EllenTV:clips**
+ - **ElPais**: El País
+ - **EMPFlix**
+ - **Engadget**
+ - **Eporner**
+ - **Escapist**
+ - **EveryonesMixtape**
+ - **exfm**: ex.fm
+ - **ExpoTV**
+ - **ExtremeTube**
+ - **facebook**
+ - **faz.net**
+ - **fc2**
+ - **fernsehkritik.tv**
+ - **fernsehkritik.tv:postecke**
+ - **Firedrive**
+ - **Firstpost**
+ - **firsttv**: Видеоархив - Первый канал
+ - **Flickr**
+ - **Folketinget**: Folketinget (ft.dk; Danish parliament)
+ - **Foxgay**
+ - **FoxNews**
+ - **france2.fr:generation-quoi**
+ - **FranceCulture**
+ - **FranceInter**
+ - **francetv**: France 2, 3, 4, 5 and Ô
+ - **francetvinfo.fr**
+ - **Freesound**
+ - **freespeech.org**
+ - **FreeVideo**
+ - **FunnyOrDie**
+ - **Gamekings**
+ - **GameOne**
+ - **gameone:playlist**
+ - **GameSpot**
+ - **GameStar**
+ - **Gametrailers**
+ - **GDCVault**
+ - **generic**: Generic downloader that works on some sites
+ - **GiantBomb**
+ - **Glide**: Glide mobile video messages (glide.me)
+ - **Globo**
+ - **GodTube**
+ - **GoldenMoustache**
+ - **Golem**
+ - **GorillaVid**: GorillaVid.in, daclips.in, movpod.in and fastvideo.in
+ - **Goshgay**
+ - **Grooveshark**
+ - **Groupon**
+ - **Hark**
+ - **Heise**
+ - **Helsinki**: helsinki.fi
+ - **HentaiStigma**
+ - **HornBunny**
+ - **HostingBulk**
+ - **HotNewHipHop**
+ - **Howcast**
+ - **HowStuffWorks**
+ - **HuffPost**: Huffington Post
+ - **Hypem**
+ - **Iconosquare**
+ - **ign.com**
+ - **imdb**: Internet Movie Database trailers
+ - **imdb:list**: Internet Movie Database lists
+ - **Ina**
+ - **InfoQ**
+ - **Instagram**
+ - **instagram:user**: Instagram user profile
+ - **InternetVideoArchive**
+ - **IPrima**
+ - **ivi**: ivi.ru
+ - **ivi:compilation**: ivi.ru compilations
+ - **Izlesene**
+ - **JadoreCettePub**
+ - **JeuxVideo**
+ - **Jove**
+ - **jpopsuki.tv**
+ - **Jukebox**
+ - **Kankan**
+ - **keek**
+ - **KeezMovies**
+ - **KhanAcademy**
+ - **KickStarter**
+ - **kontrtube**: KontrTube.ru - Труба зовёт
+ - **KrasView**: Красвью
+ - **Ku6**
+ - **la7.tv**
+ - **Laola1Tv**
+ - **lifenews**: LIFE | NEWS
+ - **LiveLeak**
+ - **livestream**
+ - **livestream:original**
+ - **lrt.lt**
+ - **lynda**: lynda.com videos
+ - **lynda:course**: lynda.com online courses
+ - **m6**
+ - **macgamestore**: MacGameStore trailers
+ - **mailru**: Видео@Mail.Ru
+ - **Malemotion**
+ - **MDR**
+ - **metacafe**
+ - **Metacritic**
+ - **Mgoon**
+ - **Minhateca**
+ - **MinistryGrid**
+ - **mitele.es**
+ - **mixcloud**
+ - **MLB**
+ - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
+ - **Mofosex**
+ - **Mojvideo**
+ - **Moniker**: allmyvideos.net and vidspot.net
+ - **mooshare**: Mooshare.biz
+ - **Morningstar**: morningstar.com
+ - **Motherless**
+ - **Motorsport**: motorsport.com
+ - **MovieClips**
+ - **Moviezine**
+ - **movshare**: MovShare
+ - **MPORA**
+ - **MTV**
+ - **mtviggy.com**
+ - **mtvservices:embedded**
+ - **MuenchenTV**: münchen.tv
+ - **MusicPlayOn**
+ - **MusicVault**
+ - **muzu.tv**
+ - **MySpace**
+ - **MySpace:album**
+ - **MySpass**
+ - **myvideo**
+ - **MyVidster**
+ - **Naver**
+ - **NBA**
+ - **NBC**
+ - **NBCNews**
+ - **ndr**: NDR.de - Mediathek
+ - **NDTV**
+ - **NerdCubedFeed**
+ - **Newgrounds**
+ - **Newstube**
+ - **nfb**: National Film Board of Canada
+ - **nfl.com**
+ - **nhl.com**
+ - **nhl.com:videocenter**: NHL videocenter category
+ - **niconico**: ニコニコ動画
+ - **NiconicoPlaylist**
+ - **Noco**
+ - **Normalboots**
+ - **NosVideo**
+ - **novamov**: NovaMov
+ - **Nowness**
+ - **nowvideo**: NowVideo
+ - **npo.nl**
+ - **NRK**
+ - **NRKTV**
+ - **NTV**
+ - **Nuvid**
+ - **NYTimes**
+ - **ocw.mit.edu**
+ - **OktoberfestTV**
+ - **on.aol.com**
+ - **Ooyala**
+ - **orf:oe1**: Radio Österreich 1
+ - **orf:tvthek**: ORF TVthek
+ - **ORFFM4**: radio FM4
+ - **parliamentlive.tv**: UK parliament videos
+ - **Patreon**
+ - **PBS**
+ - **Phoenix**
+ - **Photobucket**
+ - **PlanetaPlay**
+ - **play.fm**
+ - **played.to**
+ - **Playvid**
+ - **plus.google**: Google Plus
+ - **pluzz.francetv.fr**
+ - **podomatic**
+ - **PornHd**
+ - **PornHub**
+ - **Pornotube**
+ - **PornoXO**
+ - **PromptFile**
+ - **prosiebensat1**: ProSiebenSat.1 Digital
+ - **Pyvideo**
+ - **QuickVid**
+ - **radio.de**
+ - **radiofrance**
+ - **Rai**
+ - **RBMARadio**
+ - **RedTube**
+ - **Restudy**
+ - **ReverbNation**
+ - **RingTV**
+ - **RottenTomatoes**
+ - **Roxwel**
+ - **RTBF**
+ - **RTLnow**
+ - **rtlxl.nl**
+ - **RTP**
+ - **RTS**: RTS.ch
+ - **rtve.es:alacarta**: RTVE a la carta
+ - **rtve.es:live**: RTVE.es live streams
+ - **RUHD**
+ - **rutube**: Rutube videos
+ - **rutube:channel**: Rutube channels
+ - **rutube:movie**: Rutube movies
+ - **rutube:person**: Rutube person videos
+ - **RUTV**: RUTV.RU
+ - **Sapo**: SAPO Vídeos
+ - **savefrom.net**
+ - **SBS**: sbs.com.au
+ - **SciVee**
+ - **screen.yahoo:search**: Yahoo screen search
+ - **Screencast**
+ - **ScreencastOMatic**
+ - **ScreenwaveMedia**
+ - **ServingSys**
+ - **Sexu**
+ - **SexyKarma**: Sexy Karma and Watch Indian Porn
+ - **Shared**
+ - **ShareSix**
+ - **Sina**
+ - **Slideshare**
+ - **Slutload**
+ - **smotri**: Smotri.com
+ - **smotri:broadcast**: Smotri.com broadcasts
+ - **smotri:community**: Smotri.com community videos
+ - **smotri:user**: Smotri.com user videos
+ - **Snotr**
+ - **Sockshare**
+ - **Sohu**
+ - **soundcloud**
+ - **soundcloud:playlist**
+ - **soundcloud:set**
+ - **soundcloud:user**
+ - **Soundgasm**
+ - **southpark.cc.com**
+ - **southpark.de**
+ - **Space**
+ - **Spankwire**
+ - **Spiegel**
+ - **Spiegel:Article**: Articles on spiegel.de
+ - **Spiegeltv**
+ - **Spike**
+ - **Sport5**
+ - **SportBox**
+ - **SportDeutschland**
+ - **SRMediathek**: Süddeutscher Rundfunk
+ - **stanfordoc**: Stanford Open ClassRoom
+ - **Steam**
+ - **streamcloud.eu**
+ - **StreamCZ**
+ - **SunPorno**
+ - **SWRMediathek**
+ - **Syfy**
+ - **SztvHu**
+ - **Tagesschau**
+ - **Tapely**
+ - **Tass**
+ - **teachertube**: teachertube.com videos
+ - **teachertube:user:collection**: teachertube.com user and collection videos
+ - **TeachingChannel**
+ - **Teamcoco**
+ - **TeamFour**
+ - **TechTalks**
+ - **techtv.mit.edu**
+ - **TED**
+ - **tegenlicht.vpro.nl**
+ - **TeleBruxelles**
+ - **telecinco.es**
+ - **TeleMB**
+ - **TenPlay**
+ - **TF1**
+ - **TheOnion**
+ - **ThePlatform**
+ - **TheSixtyOne**
+ - **ThisAV**
+ - **THVideo**
+ - **THVideoPlaylist**
+ - **tinypic**: tinypic.com videos
+ - **tlc.com**
+ - **tlc.de**
+ - **TMZ**
+ - **TNAFlix**
+ - **tou.tv**
+ - **Toypics**: Toypics user profile
+ - **ToypicsUser**: Toypics user profile
+ - **TrailerAddict** (Currently broken)
+ - **Trilulilu**
+ - **TruTube**
+ - **Tube8**
+ - **Tudou**
+ - **Tumblr**
+ - **TuneIn**
+ - **Turbo**
+ - **Tutv**
+ - **tv.dfb.de**
+ - **tvigle**: Интернет-телевидение Tvigle.ru
+ - **tvp.pl**
+ - **TVPlay**: TV3Play and related services
+ - **Twitch**
+ - **Ubu**
+ - **udemy**
+ - **udemy:course**
+ - **Unistra**
+ - **Urort**: NRK P3 Urørt
+ - **ustream**
+ - **ustream:channel**
+ - **Vbox7**
+ - **VeeHD**
+ - **Veoh**
+ - **Vesti**: Вести.Ru
+ - **Vevo**
+ - **VGTV**
+ - **vh1.com**
+ - **Vice**
+ - **Viddler**
+ - **video.google:search**: Google Video search
+ - **video.mit.edu**
+ - **VideoBam**
+ - **VideoDetective**
+ - **videofy.me**
+ - **videolectures.net**
+ - **VideoMega**
+ - **VideoPremium**
+ - **VideoTt**: video.tt - Your True Tube
+ - **videoweed**: VideoWeed
+ - **Vidme**
+ - **Vidzi**
+ - **viki**
+ - **vimeo**
+ - **vimeo:album**
+ - **vimeo:channel**
+ - **vimeo:group**
+ - **vimeo:likes**: Vimeo user likes
+ - **vimeo:review**: Review pages on vimeo
+ - **vimeo:user**
+ - **vimeo:watchlater**: Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)
+ - **Vimple**: Vimple.ru
+ - **Vine**
+ - **vine:user**
+ - **vk.com**
+ - **vk.com:user-videos**: vk.com:All of a user's videos
+ - **Vodlocker**
+ - **Vporn**
+ - **VRT**
+ - **vube**: Vube.com
+ - **VuClip**
+ - **vulture.com**
+ - **Walla**
+ - **WashingtonPost**
+ - **wat.tv**
+ - **WayOfTheMaster**
+ - **WDR**
+ - **wdr:mobile**
+ - **WDRMaus**: Sendung mit der Maus
+ - **Weibo**
+ - **Wimp**
+ - **Wistia**
+ - **WorldStarHipHop**
+ - **wrzuta.pl**
+ - **XBef**
+ - **XboxClips**
+ - **XHamster**
+ - **XMinus**
+ - **XNXX**
+ - **XTube**
+ - **XTubeUser**: XTube user profile
+ - **XVideos**
+ - **Yahoo**: Yahoo screen and movies
+ - **YesJapan**
+ - **Ynet**
+ - **YouJizz**
+ - **Youku**
+ - **YouPorn**
+ - **YourUpload**
+ - **youtube**: YouTube.com
+ - **youtube:channel**: YouTube.com channels
+ - **youtube:favorites**: YouTube.com favourite videos, ":ytfav" for short (requires authentication)
+ - **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication)
+ - **youtube:playlist**: YouTube.com playlists
+ - **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication)
+ - **youtube:search**: YouTube.com searches
+ - **youtube:search:date**: YouTube.com searches, newest videos first
+ - **youtube:search_url**: YouTube.com search URLs
+ - **youtube:show**: YouTube.com (multi-season) shows
+ - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
+ - **youtube:toplist**: YouTube.com top lists, "yttoplist:{channel}:{list title}" (Example: "yttoplist:music:Top Tracks")
+ - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
+ - **youtube:watch_later**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
+ - **ZDF**
+ - **ZDFChannel**
+ - **zingmp3:album**: mp3.zing.vn albums
+ - **zingmp3:song**: mp3.zing.vn songs

setup.cfg

@@ -1,2 +1,6 @@
 [wheel]
 universal = True
+
+[flake8]
+exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,setup.py,build
+ignore = E501

test/helper.py

@@ -82,24 +82,14 @@ class FakeYDL(YoutubeDL):
 
 def gettestcases(include_onlymatching=False):
     for ie in youtube_dl.extractor.gen_extractors():
-        t = getattr(ie, '_TEST', None)
-        if t:
-            assert not hasattr(ie, '_TESTS'), \
-                '%s has _TEST and _TESTS' % type(ie).__name__
-            tests = [t]
-        else:
-            tests = getattr(ie, '_TESTS', [])
-        for t in tests:
-            if not include_onlymatching and t.get('only_matching', False):
-                continue
-            t['name'] = type(ie).__name__[:-len('IE')]
-            yield t
+        for tc in ie.get_testcases(include_onlymatching):
+            yield tc
 
 
 md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
 
 
-def expect_info_dict(self, expected_dict, got_dict):
+def expect_info_dict(self, got_dict, expected_dict):
     for info_field, expected in expected_dict.items():
         if isinstance(expected, compat_str) and expected.startswith('re:'):
             got = got_dict.get(info_field)
@@ -120,6 +110,20 @@ def expect_info_dict(self, expected_dict, got_dict):
         else:
             if isinstance(expected, compat_str) and expected.startswith('md5:'):
                 got = 'md5:' + md5(got_dict.get(info_field))
+            elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
+                got = got_dict.get(info_field)
+                self.assertTrue(
+                    isinstance(got, list),
+                    'Expected field %s to be a list, but it is of type %s' % (
+                        info_field, type(got).__name__))
+                expected_num = int(expected.partition(':')[2])
+                assertGreaterEqual(
+                    self, len(got), expected_num,
+                    'Expected %d items in field %s, but only got %d' % (
+                        expected_num, info_field, len(got)
+                    )
+                )
+                continue
             else:
                 got = got_dict.get(info_field)
             self.assertEqual(expected, got,

test/test_InfoExtractor.py

@@ -40,5 +40,23 @@ class TestInfoExtractor(unittest.TestCase):
         self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
         self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
 
+    def test_html_search_meta(self):
+        ie = self.ie
+        html = '''
+            <meta name="a" content="1" />
+            <meta name='b' content='2'>
+            <meta name="c" content='3'>
+            <meta name=d content='4'>
+            <meta property="e" content='5' >
+            <meta content="6" name="f">
+        '''
+
+        self.assertEqual(ie._html_search_meta('a', html), '1')
+        self.assertEqual(ie._html_search_meta('b', html), '2')
+        self.assertEqual(ie._html_search_meta('c', html), '3')
+        self.assertEqual(ie._html_search_meta('d', html), '4')
+        self.assertEqual(ie._html_search_meta('e', html), '5')
+        self.assertEqual(ie._html_search_meta('f', html), '6')
+
 if __name__ == '__main__':
     unittest.main()

test/test_YoutubeDL.py

@@ -8,6 +8,8 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
+import copy
+
 from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
 from youtube_dl.extractor import YoutubeIE
@@ -192,6 +194,37 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'vid-high')
 
+    def test_format_selection_audio_exts(self):
+        formats = [
+            {'format_id': 'mp3-64', 'ext': 'mp3', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
+            {'format_id': 'ogg-64', 'ext': 'ogg', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
+            {'format_id': 'aac-64', 'ext': 'aac', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
+            {'format_id': 'mp3-32', 'ext': 'mp3', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
+            {'format_id': 'aac-32', 'ext': 'aac', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
+        ]
+
+        info_dict = _make_result(formats)
+        ydl = YDL({'format': 'best'})
+        ie = YoutubeIE(ydl)
+        ie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(copy.deepcopy(info_dict))
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'aac-64')
+
+        ydl = YDL({'format': 'mp3'})
+        ie = YoutubeIE(ydl)
+        ie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(copy.deepcopy(info_dict))
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'mp3-64')
+
+        ydl = YDL({'prefer_free_formats': True})
+        ie = YoutubeIE(ydl)
+        ie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(copy.deepcopy(info_dict))
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'ogg-64')
+
     def test_format_selection_video(self):
         formats = [
             {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
@@ -218,7 +251,7 @@ class TestFormatSelection(unittest.TestCase):
             # 3D
             '85', '84', '102', '83', '101', '82', '100',
             # Dash video
-            '138', '137', '248', '136', '247', '135', '246',
+            '137', '248', '136', '247', '135', '246',
             '245', '244', '134', '243', '133', '242', '160',
             # Dash audio
             '141', '172', '140', '171', '139',
@@ -248,6 +281,61 @@ class TestFormatSelection(unittest.TestCase):
             downloaded = ydl.downloaded_info_dicts[0]
             self.assertEqual(downloaded['format_id'], f1id)
 
+    def test_format_filtering(self):
+        formats = [
+            {'format_id': 'A', 'filesize': 500, 'width': 1000},
+            {'format_id': 'B', 'filesize': 1000, 'width': 500},
+            {'format_id': 'C', 'filesize': 1000, 'width': 400},
+            {'format_id': 'D', 'filesize': 2000, 'width': 600},
+            {'format_id': 'E', 'filesize': 3000},
+            {'format_id': 'F'},
+            {'format_id': 'G', 'filesize': 1000000},
+        ]
+        for f in formats:
+            f['url'] = 'http://_/'
+            f['ext'] = 'unknown'
+        info_dict = _make_result(formats)
+
+        ydl = YDL({'format': 'best[filesize<3000]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'D')
+
+        ydl = YDL({'format': 'best[filesize<=3000]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'E')
+
+        ydl = YDL({'format': 'best[filesize <= ? 3000]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'F')
+
+        ydl = YDL({'format': 'best [filesize = 1000] [width>450]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'B')
+
+        ydl = YDL({'format': 'best [filesize = 1000] [width!=450]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'C')
+
+        ydl = YDL({'format': '[filesize>?1]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'G')
+
+        ydl = YDL({'format': '[filesize<1M]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'E')
+
+        ydl = YDL({'format': '[filesize<1MiB]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'G')
+
     def test_add_extra_info(self):
         test_dict = {
             'extractor': 'Foo',

test/test_age_restriction.py

@@ -45,11 +45,6 @@ class TestAgeRestriction(unittest.TestCase):
             'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
             '505835.mp4', 2, old_age=25)
 
-    def test_pornotube(self):
-        self._assert_restricted(
-            'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
-            '1689755.flv', 13)
-
 
 if __name__ == '__main__':
     unittest.main()

test/test_all_urls.py

@@ -14,7 +14,6 @@ from test.helper import gettestcases
 from youtube_dl.extractor import (
     FacebookIE,
     gen_extractors,
-    TwitchIE,
     YoutubeIE,
 )
 
@@ -72,18 +71,6 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
         self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
 
-    def test_twitch_channelid_matching(self):
-        self.assertTrue(TwitchIE.suitable('twitch.tv/vanillatv'))
-        self.assertTrue(TwitchIE.suitable('www.twitch.tv/vanillatv'))
-        self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv'))
-        self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/'))
-
-    def test_twitch_videoid_matching(self):
-        self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
-
-    def test_twitch_chapterid_matching(self):
-        self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
-
     def test_youtube_extract(self):
         assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
         assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
@@ -115,8 +102,6 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch(':ythistory', ['youtube:history'])
         self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
         self.assertMatch(':tds', ['ComedyCentralShows'])
-        self.assertMatch(':colbertreport', ['ComedyCentralShows'])
-        self.assertMatch(':cr', ['ComedyCentralShows'])
 
     def test_vimeo_matching(self):
         self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])

test/test_download.py

@@ -155,7 +155,7 @@ def generator(test_case):
             if is_playlist:
                 self.assertEqual(res_dict['_type'], 'playlist')
                 self.assertTrue('entries' in res_dict)
-                expect_info_dict(self, test_case.get('info_dict', {}), res_dict)
+                expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
 
             if 'playlist_mincount' in test_case:
                 assertGreaterEqual(
@@ -204,7 +204,7 @@ def generator(test_case):
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
 
-                expect_info_dict(self, tc.get('info_dict', {}), info_dict)
+                expect_info_dict(self, info_dict, tc.get('info_dict', {}))
         finally:
             try_rm_tcs_files()
             if is_playlist and res_dict is not None and res_dict.get('entries'):

test/test_subtitles.py

@@ -17,6 +17,7 @@ from youtube_dl.extractor import (
     TEDIE,
     VimeoIE,
     WallaIE,
+    CeskaTelevizeIE,
 )
 
 
@@ -88,6 +89,14 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
         subtitles = self.getSubtitles()
         self.assertTrue(subtitles['it'] is not None)
 
+    def test_youtube_translated_subtitles(self):
+        # This video has a subtitles track, which can be translated
+        self.url = 'Ky9eprVWzlI'
+        self.DL.params['writeautomaticsub'] = True
+        self.DL.params['subtitleslangs'] = ['it']
+        subtitles = self.getSubtitles()
+        self.assertTrue(subtitles['it'] is not None)
+
     def test_youtube_nosubtitles(self):
         self.DL.expect_warning('video doesn\'t have subtitles')
         self.url = 'n5BB19UTcdA'
@@ -309,5 +318,32 @@ class TestWallaSubtitles(BaseTestSubtitles):
         self.assertEqual(len(subtitles), 0)
 
 
+class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
+    url = 'http://www.ceskatelevize.cz/ivysilani/10600540290-u6-uzasny-svet-techniky'
+    IE = CeskaTelevizeIE
+
+    def test_list_subtitles(self):
+        self.DL.expect_warning('Automatic Captions not supported by this server')
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
+        self.assertEqual(info_dict, None)
+
+    def test_allsubtitles(self):
+        self.DL.expect_warning('Automatic Captions not supported by this server')
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['cs']))
+        self.assertEqual(md5(subtitles['cs']), '9bf52d9549533c32c427e264bf0847d4')
+
+    def test_nosubtitles(self):
+        self.DL.expect_warning('video doesn\'t have subtitles')
+        self.url = 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220'
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(len(subtitles), 0)
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_unicode_literals.py

@@ -7,9 +7,7 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 import io
-import os
 import re
-import unittest
 
 rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 

test/test_utils.py

@@ -16,6 +16,7 @@ import json
 import xml.etree.ElementTree
 
 from youtube_dl.utils import (
+    age_restricted,
     args_to_str,
     clean_html,
     DateRange,
@@ -27,6 +28,7 @@ from youtube_dl.utils import (
     fix_xml_ampersands,
     InAdvancePagedList,
     intlist_to_bytes,
+    is_html,
     js_to_json,
     limit_length,
     OnDemandPagedList,
@@ -78,6 +80,10 @@ class TestUtil(unittest.TestCase):
         tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
         self.assertEqual(sanitize_filename(tests), tests)
 
+        self.assertEqual(
+            sanitize_filename('New World record at 0:12:34'),
+            'New World record at 0_12_34')
+
         forbidden = '"\0\\/'
         for fc in forbidden:
             for fbc in forbidden:
@@ -143,6 +149,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
+        self.assertEqual(unified_strdate('1968 12 10'), '19681210')
         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
         self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
         self.assertEqual(
@@ -207,6 +214,8 @@ class TestUtil(unittest.TestCase):
 
     def test_parse_duration(self):
         self.assertEqual(parse_duration(None), None)
+        self.assertEqual(parse_duration(False), None)
+        self.assertEqual(parse_duration('invalid'), None)
         self.assertEqual(parse_duration('1'), 1)
         self.assertEqual(parse_duration('1337:12'), 80232)
         self.assertEqual(parse_duration('9:12:43'), 33163)
@@ -402,5 +411,28 @@ Trying to open render node...
 Success at /dev/dri/renderD128.
 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
 
+    def test_age_restricted(self):
+        self.assertFalse(age_restricted(None, 10))  # unrestricted content
+        self.assertFalse(age_restricted(1, None))  # unrestricted policy
+        self.assertFalse(age_restricted(8, 10))
+        self.assertTrue(age_restricted(18, 14))
+        self.assertFalse(age_restricted(18, 18))
+
+    def test_is_html(self):
+        self.assertFalse(is_html(b'\x49\x44\x43<html'))
+        self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
+        self.assertTrue(is_html(  # UTF-8 with BOM
+            b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
+        self.assertTrue(is_html(  # UTF-16-LE
+            b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
+        ))
+        self.assertTrue(is_html(  # UTF-16-BE
+            b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
+        ))
+        self.assertTrue(is_html(  # UTF-32-BE
+            b'\x00\x00\xFE\xFF\x00\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4'))
+        self.assertTrue(is_html(  # UTF-32-LE
+            b'\xFF\xFE\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4\x00\x00\x00'))
+
 if __name__ == '__main__':
     unittest.main()

youtube_dl/YoutubeDL.py

@@ -10,6 +10,7 @@ import io
 import itertools
 import json
 import locale
+import operator
 import os
 import platform
 import re
@@ -49,6 +50,7 @@ from .utils import (
     make_HTTPS_handler,
     MaxDownloadsReached,
     PagedList,
+    parse_filesize,
     PostProcessingError,
     platform_name,
     preferredencoding,
@@ -58,17 +60,21 @@ from .utils import (
     takewhile_inclusive,
     UnavailableVideoError,
     url_basename,
+    version_tuple,
     write_json_file,
     write_string,
     YoutubeDLHandler,
     prepend_extension,
     args_to_str,
+    age_restricted,
 )
 from .cache import Cache
 from .extractor import get_info_extractor, gen_extractors
 from .downloader import get_suitable_downloader
 from .downloader.rtmp import rtmpdump_version
 from .postprocessor import (
+    FFmpegFixupM4aPP,
+    FFmpegFixupStretchedPP,
     FFmpegMergerPP,
     FFmpegPostProcessor,
     get_postprocessor,
@@ -121,7 +127,7 @@ class YoutubeDL(object):
     dump_single_json:  Force printing the info_dict of the whole playlist
                        (or video) as a single JSON line.
     simulate:          Do not download the video files.
-    format:            Video format code.
+    format:            Video format code. See options.py for more information.
     format_limit:      Highest quality format to try.
     outtmpl:           Template for output names.
     restrictfilenames: Do not allow "&" and spaces in file names
@@ -202,6 +208,17 @@ class YoutubeDL(object):
 
                        Progress hooks are guaranteed to be called at least once
                        (with status "finished") if the download is successful.
+    merge_output_format: Extension to use when merging formats.
+    fixup:             Automatically correct known faults of the file.
+                       One of:
+                       - "never": do nothing
+                       - "warn": only emit a warning
+                       - "detect_or_warn": check whether we can do anything
+                                           about it, warn otherwise (default)
+    source_address:    (Experimental) Client-side IP address to bind to.
+    call_home:         Boolean, true iff we are allowed to contact the
+                       youtube-dl servers for debugging.
+    sleep_interval:    Number of seconds to sleep before each download.
 
 
     The following parameters are not used by YoutubeDL itself, they are used by
@@ -550,13 +567,8 @@ class YoutubeDL(object):
             max_views = self.params.get('max_views')
             if max_views is not None and view_count > max_views:
                 return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
-        age_limit = self.params.get('age_limit')
-        if age_limit is not None:
-            actual_age_limit = info_dict.get('age_limit')
-            if actual_age_limit is None:
-                actual_age_limit = 0
-            if age_limit < actual_age_limit:
-                return 'Skipping "' + title + '" because it is age restricted'
+        if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')):
+            return 'Skipping "%s" because it is age restricted' % title
         if self.in_download_archive(info_dict):
             return '%s has already been recorded in archive' % video_title
         return None
@@ -712,7 +724,7 @@ class YoutubeDL(object):
                 entries = entries[::-1]
 
             for i, entry in enumerate(entries, 1):
-                self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries))
+                self.to_screen('[download] Downloading video %s of %s' % (i, n_entries))
                 extra = {
                     'n_entries': n_entries,
                     'playlist': playlist,
@@ -760,7 +772,59 @@ class YoutubeDL(object):
         else:
             raise Exception('Invalid result type: %s' % result_type)
 
+    def _apply_format_filter(self, format_spec, available_formats):
+        " Returns a tuple of the remaining format_spec and filtered formats "
+
+        OPERATORS = {
+            '<': operator.lt,
+            '<=': operator.le,
+            '>': operator.gt,
+            '>=': operator.ge,
+            '=': operator.eq,
+            '!=': operator.ne,
+        }
+        operator_rex = re.compile(r'''(?x)\s*\[
+            (?P<key>width|height|tbr|abr|vbr|filesize)
+            \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
+            (?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)
+            \]$
+            ''' % '|'.join(map(re.escape, OPERATORS.keys())))
+        m = operator_rex.search(format_spec)
+        if not m:
+            raise ValueError('Invalid format specification %r' % format_spec)
+
+        try:
+            comparison_value = int(m.group('value'))
+        except ValueError:
+            comparison_value = parse_filesize(m.group('value'))
+            if comparison_value is None:
+                comparison_value = parse_filesize(m.group('value') + 'B')
+            if comparison_value is None:
+                raise ValueError(
+                    'Invalid value %r in format specification %r' % (
+                        m.group('value'), format_spec))
+        op = OPERATORS[m.group('op')]
+
+        def _filter(f):
+            actual_value = f.get(m.group('key'))
+            if actual_value is None:
+                return m.group('none_inclusive')
+            return op(actual_value, comparison_value)
+        new_formats = [f for f in available_formats if _filter(f)]
+
+        new_format_spec = format_spec[:-len(m.group(0))]
+        if not new_format_spec:
+            new_format_spec = 'best'
+
+        return (new_format_spec, new_formats)
+
     def select_format(self, format_spec, available_formats):
+        while format_spec.endswith(']'):
+            format_spec, available_formats = self._apply_format_filter(
+                format_spec, available_formats)
+        if not available_formats:
+            return None
+
         if format_spec == 'best' or format_spec is None:
             return available_formats[-1]
         elif format_spec == 'worst':
@@ -790,7 +854,7 @@ class YoutubeDL(object):
             if video_formats:
                 return video_formats[0]
         else:
-            extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a']
+            extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav']
             if format_spec in extensions:
                 filter_f = lambda f: f['ext'] == format_spec
             else:
@@ -913,10 +977,24 @@ class YoutubeDL(object):
                                                   'contain the video, try using '
                                                   '"-f %s+%s"' % (format_2, format_1))
                                 return
+                            output_ext = (
+                                formats_info[0]['ext']
+                                if self.params.get('merge_output_format') is None
+                                else self.params['merge_output_format'])
                             selected_format = {
                                 'requested_formats': formats_info,
                                 'format': rf,
                                 'ext': formats_info[0]['ext'],
+                                'width': formats_info[0].get('width'),
+                                'height': formats_info[0].get('height'),
+                                'resolution': formats_info[0].get('resolution'),
+                                'fps': formats_info[0].get('fps'),
+                                'vcodec': formats_info[0].get('vcodec'),
+                                'vbr': formats_info[0].get('vbr'),
+                                'stretched_ratio': formats_info[0].get('stretched_ratio'),
+                                'acodec': formats_info[1].get('acodec'),
+                                'abr': formats_info[1].get('abr'),
+                                'ext': output_ext,
                             }
                         else:
                             selected_format = None
@@ -1016,13 +1094,13 @@ class YoutubeDL(object):
             descfn = filename + '.description'
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)):
                 self.to_screen('[info] Video description is already present')
+            elif info_dict.get('description') is None:
+                self.report_warning('There\'s no description to write.')
             else:
                 try:
                     self.to_screen('[info] Writing video description to: ' + descfn)
                     with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
                         descfile.write(info_dict['description'])
-                except (KeyError, TypeError):
-                    self.report_warning('There\'s no description to write.')
                 except (OSError, IOError):
                     self.report_error('Cannot write description file ' + descfn)
                     return
@@ -1099,58 +1177,92 @@ class YoutubeDL(object):
                                             (info_dict['thumbnail'], compat_str(err)))
 
         if not self.params.get('skip_download', False):
-            if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
-                success = True
-            else:
-                try:
-                    def dl(name, info):
-                        fd = get_suitable_downloader(info)(self, self.params)
-                        for ph in self._progress_hooks:
-                            fd.add_progress_hook(ph)
-                        if self.params.get('verbose'):
-                            self.to_stdout('[debug] Invoking downloader on %r' % info.get('url'))
-                        return fd.download(name, info)
-                    if info_dict.get('requested_formats') is not None:
-                        downloaded = []
-                        success = True
-                        merger = FFmpegMergerPP(self, not self.params.get('keepvideo'))
-                        if not merger._executable:
-                            postprocessors = []
-                            self.report_warning('You have requested multiple '
-                                                'formats but ffmpeg or avconv are not installed.'
-                                                ' The formats won\'t be merged')
-                        else:
-                            postprocessors = [merger]
-                        for f in info_dict['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'])
-                            downloaded.append(fname)
-                            partial_success = dl(fname, new_info)
-                            success = success and partial_success
-                        info_dict['__postprocessors'] = postprocessors
-                        info_dict['__files_to_merge'] = downloaded
+            try:
+                def dl(name, info):
+                    fd = get_suitable_downloader(info)(self, self.params)
+                    for ph in self._progress_hooks:
+                        fd.add_progress_hook(ph)
+                    if self.params.get('verbose'):
+                        self.to_stdout('[debug] Invoking downloader on %r' % info.get('url'))
+                    return fd.download(name, info)
+                if info_dict.get('requested_formats') is not None:
+                    downloaded = []
+                    success = True
+                    merger = FFmpegMergerPP(self, not self.params.get('keepvideo'))
+                    if not merger._executable:
+                        postprocessors = []
+                        self.report_warning('You have requested multiple '
+                                            'formats but ffmpeg or avconv are not installed.'
+                                            ' The formats won\'t be merged')
                     else:
-                        # Just a single file
-                        success = dl(filename, info_dict)
-                except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-                    self.report_error('unable to download video data: %s' % str(err))
-                    return
-                except (OSError, IOError) as err:
-                    raise UnavailableVideoError(err)
-                except (ContentTooShortError, ) as err:
-                    self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
-                    return
+                        postprocessors = [merger]
+                    for f in info_dict['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'])
+                        downloaded.append(fname)
+                        partial_success = dl(fname, new_info)
+                        success = success and partial_success
+                    info_dict['__postprocessors'] = postprocessors
+                    info_dict['__files_to_merge'] = downloaded
+                else:
+                    # Just a single file
+                    success = dl(filename, info_dict)
+            except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+                self.report_error('unable to download video data: %s' % str(err))
+                return
+            except (OSError, IOError) as err:
+                raise UnavailableVideoError(err)
+            except (ContentTooShortError, ) as err:
+                self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
+                return
 
             if success:
+                # Fixup content
+                fixup_policy = self.params.get('fixup')
+                if fixup_policy is None:
+                    fixup_policy = 'detect_or_warn'
+
+                stretched_ratio = info_dict.get('stretched_ratio')
+                if stretched_ratio is not None and stretched_ratio != 1:
+                    if fixup_policy == 'warn':
+                        self.report_warning('%s: Non-uniform pixel ratio (%s)' % (
+                            info_dict['id'], stretched_ratio))
+                    elif fixup_policy == 'detect_or_warn':
+                        stretched_pp = FFmpegFixupStretchedPP(self)
+                        if stretched_pp.available:
+                            info_dict.setdefault('__postprocessors', [])
+                            info_dict['__postprocessors'].append(stretched_pp)
+                        else:
+                            self.report_warning(
+                                '%s: Non-uniform pixel ratio (%s). Install ffmpeg or avconv to fix this automatically.' % (
+                                    info_dict['id'], stretched_ratio))
+                    else:
+                        assert fixup_policy in ('ignore', 'never')
+
+                if info_dict.get('requested_formats') is None and info_dict.get('container') == 'm4a_dash':
+                    if fixup_policy == 'warn':
+                        self.report_warning('%s: writing DASH m4a. Only some players support this container.' % (
+                            info_dict['id']))
+                    elif fixup_policy == 'detect_or_warn':
+                        fixup_pp = FFmpegFixupM4aPP(self)
+                        if fixup_pp.available:
+                            info_dict.setdefault('__postprocessors', [])
+                            info_dict['__postprocessors'].append(fixup_pp)
+                        else:
+                            self.report_warning(
+                                '%s: writing DASH m4a. Only some players support this container. Install ffmpeg or avconv to fix this automatically.' % (
+                                    info_dict['id']))
+                    else:
+                        assert fixup_policy in ('ignore', 'never')
+
                 try:
                     self.post_process(filename, info_dict)
                 except (PostProcessingError) as err:
                     self.report_error('postprocessing: %s' % str(err))
                     return
-
-        self.record_download_archive(info_dict)
+                self.record_download_archive(info_dict)
 
     def download(self, url_list):
         """Download a given list of URLs."""
@@ -1193,14 +1305,15 @@ class YoutubeDL(object):
         """Run all the postprocessors on the given file."""
         info = dict(ie_info)
         info['filepath'] = filename
-        keep_video = None
         pps_chain = []
         if ie_info.get('__postprocessors') is not None:
             pps_chain.extend(ie_info['__postprocessors'])
         pps_chain.extend(self._pps)
         for pp in pps_chain:
+            keep_video = None
+            old_filename = info['filepath']
             try:
-                keep_video_wish, new_info = pp.run(info)
+                keep_video_wish, info = pp.run(info)
                 if keep_video_wish is not None:
                     if keep_video_wish:
                         keep_video = keep_video_wish
@@ -1209,12 +1322,12 @@ class YoutubeDL(object):
                         keep_video = keep_video_wish
             except PostProcessingError as e:
                 self.report_error(e.msg)
-        if keep_video is False and not self.params.get('keepvideo', False):
-            try:
-                self.to_screen('Deleting original file %s (pass -k to keep)' % filename)
-                os.remove(encodeFilename(filename))
-            except (IOError, OSError):
-                self.report_warning('Unable to remove downloaded video file')
+            if keep_video is False and not self.params.get('keepvideo', False):
+                try:
+                    self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
+                    os.remove(encodeFilename(old_filename))
+                except (IOError, OSError):
+                    self.report_warning('Unable to remove downloaded video file')
 
     def _make_archive_id(self, info_dict):
         # Future-proof against any change in case
@@ -1334,7 +1447,9 @@ class YoutubeDL(object):
         formats = info_dict.get('formats', [info_dict])
         idlen = max(len('format code'),
                     max(len(f['format_id']) for f in formats))
-        formats_s = [line(f, idlen) for f in formats]
+        formats_s = [
+            line(f, idlen) for f in formats
+            if f.get('preference') is None or f['preference'] >= -1000]
         if len(formats) > 1:
             formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)'
             formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)'
@@ -1423,6 +1538,17 @@ class YoutubeDL(object):
                 proxy_map.update(handler.proxies)
         self._write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n')
 
+        if self.params.get('call_home', False):
+            ipaddr = self.urlopen('https://yt-dl.org/ip').read().decode('utf-8')
+            self._write_string('[debug] Public IP address: %s\n' % ipaddr)
+            latest_version = self.urlopen(
+                'https://yt-dl.org/latest/version').read().decode('utf-8')
+            if version_tuple(latest_version) > version_tuple(__version__):
+                self.report_warning(
+                    'You are using an outdated version (newest version: %s)! '
+                    'See https://yt-dl.org/update if you need help updating.' %
+                    latest_version)
+
     def _setup_opener(self):
         timeout_val = self.params.get('socket_timeout')
         self._socket_timeout = 600 if timeout_val is None else float(timeout_val)
@@ -1453,9 +1579,8 @@ class YoutubeDL(object):
         proxy_handler = compat_urllib_request.ProxyHandler(proxies)
 
         debuglevel = 1 if self.params.get('debug_printtraffic') else 0
-        https_handler = make_HTTPS_handler(
-            self.params.get('nocheckcertificate', False), debuglevel=debuglevel)
-        ydlh = YoutubeDLHandler(debuglevel=debuglevel)
+        https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
+        ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
         opener = compat_urllib_request.build_opener(
             https_handler, proxy_handler, cookie_processor, ydlh)
         # Delete the default user-agent header, which would otherwise apply in

youtube_dl/__init__.py

@@ -38,7 +38,7 @@ from .update import update_self
 from .downloader import (
     FileDownloader,
 )
-from .extractor import gen_extractors
+from .extractor import gen_extractors, list_extractors
 from .YoutubeDL import YoutubeDL
 
 
@@ -95,24 +95,22 @@ def _real_main(argv=None):
     _enc = preferredencoding()
     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
 
-    extractors = gen_extractors()
-
     if opts.list_extractors:
-        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
+        for ie in list_extractors(opts.age_limit):
             compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
             matchedUrls = [url for url in all_urls if ie.suitable(url)]
             for mu in matchedUrls:
                 compat_print('  ' + mu)
         sys.exit(0)
     if opts.list_extractor_descriptions:
-        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
+        for ie in list_extractors(opts.age_limit):
             if not ie._WORKING:
                 continue
             desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
             if desc is False:
                 continue
             if hasattr(ie, 'SEARCH_KEY'):
-                _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny')
+                _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
                 _COUNTS = ('', '5', '10', 'all')
                 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
             compat_print(desc)
@@ -168,6 +166,7 @@ def _real_main(argv=None):
     if opts.recodevideo is not None:
         if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
             parser.error('invalid video recode format specified')
+
     if opts.date is not None:
         date = DateRange.day(opts.date)
     else:
@@ -199,7 +198,8 @@ def _real_main(argv=None):
                      ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
                      ' template'.format(outtmpl))
 
-    any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
+    any_getting = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
+    any_printing = opts.print_json
     download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 
     # PostProcessors
@@ -245,7 +245,7 @@ def _real_main(argv=None):
         'password': opts.password,
         'twofactor': opts.twofactor,
         'videopassword': opts.videopassword,
-        'quiet': (opts.quiet or any_printing),
+        'quiet': (opts.quiet or any_getting or any_printing),
         'no_warnings': opts.no_warnings,
         'forceurl': opts.geturl,
         'forcetitle': opts.gettitle,
@@ -255,9 +255,9 @@ def _real_main(argv=None):
         'forceduration': opts.getduration,
         'forcefilename': opts.getfilename,
         'forceformat': opts.getformat,
-        'forcejson': opts.dumpjson,
+        'forcejson': opts.dumpjson or opts.print_json,
         'dump_single_json': opts.dump_single_json,
-        'simulate': opts.simulate or any_printing,
+        'simulate': opts.simulate or any_getting,
         'skip_download': opts.skip_download,
         'format': opts.format,
         'format_limit': opts.format_limit,
@@ -324,7 +324,12 @@ def _real_main(argv=None):
         'encoding': opts.encoding,
         'exec_cmd': opts.exec_cmd,
         'extract_flat': opts.extract_flat,
+        'merge_output_format': opts.merge_output_format,
         'postprocessors': postprocessors,
+        'fixup': opts.fixup,
+        'source_address': opts.source_address,
+        'call_home': opts.call_home,
+        'sleep_interval': opts.sleep_interval,
     }
 
     with YoutubeDL(ydl_opts) as ydl:
@@ -365,3 +370,5 @@ def main(argv=None):
         sys.exit('ERROR: fixed output name but more than one file to download')
     except KeyboardInterrupt:
         sys.exit('\nERROR: Interrupted by user')
+
+__all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']

youtube_dl/compat.py

@@ -4,6 +4,7 @@ import getpass
 import optparse
 import os
 import re
+import socket
 import subprocess
 import sys
 
@@ -307,6 +308,32 @@ else:
     compat_kwargs = lambda kwargs: kwargs
 
 
+if sys.version_info < (2, 7):
+    def compat_socket_create_connection(address, timeout, source_address=None):
+        host, port = address
+        err = None
+        for res in socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM):
+            af, socktype, proto, canonname, sa = res
+            sock = None
+            try:
+                sock = socket.socket(af, socktype, proto)
+                sock.settimeout(timeout)
+                if source_address:
+                    sock.bind(source_address)
+                sock.connect(sa)
+                return sock
+            except socket.error as _:
+                err = _
+                if sock is not None:
+                    sock.close()
+        if err is not None:
+            raise err
+        else:
+            raise socket.error("getaddrinfo returns an empty list")
+else:
+    compat_socket_create_connection = socket.create_connection
+
+
 # Fix https://github.com/rg3/youtube-dl/issues/4223
 # See http://bugs.python.org/issue9161 for what is broken
 def workaround_optparse_bug9161():
@@ -342,6 +369,7 @@ __all__ = [
     'compat_ord',
     'compat_parse_qs',
     'compat_print',
+    'compat_socket_create_connection',
     'compat_str',
     'compat_subprocess_get_DEVNULL',
     'compat_urllib_error',

youtube_dl/downloader/common.py

@@ -284,8 +284,20 @@ class FileDownloader(object):
         """Download to a filename using the info from info_dict
         Return True on success and False otherwise
         """
+
+        nooverwrites_and_exists = (
+            self.params.get('nooverwrites', False)
+            and os.path.exists(encodeFilename(filename))
+        )
+
+        continuedl_and_exists = (
+            self.params.get('continuedl', False)
+            and os.path.isfile(encodeFilename(filename))
+            and not self.params.get('nopart', False)
+        )
+
         # Check file already present
-        if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False):
+        if filename != '-' and nooverwrites_and_exists or continuedl_and_exists:
             self.report_file_already_downloaded(filename)
             self._hook_progress({
                 'filename': filename,
@@ -294,6 +306,11 @@ class FileDownloader(object):
             })
             return True
 
+        sleep_interval = self.params.get('sleep_interval')
+        if sleep_interval:
+            self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
+            time.sleep(sleep_interval)
+
         return self.real_download(filename, info_dict)
 
     def real_download(self, filename, info_dict):

youtube_dl/downloader/f4m.py

@@ -177,34 +177,43 @@ def build_fragments_list(boot_info):
     """ Return a list of (segment, fragment) for each fragment in the video """
     res = []
     segment_run_table = boot_info['segments'][0]
-    # I've only found videos with one segment
-    segment_run_entry = segment_run_table['segment_run'][0]
-    n_frags = segment_run_entry[1]
     fragment_run_entry_table = boot_info['fragments'][0]['fragments']
     first_frag_number = fragment_run_entry_table[0]['first']
-    for (i, frag_number) in zip(range(1, n_frags + 1), itertools.count(first_frag_number)):
-        res.append((1, frag_number))
+    fragments_counter = itertools.count(first_frag_number)
+    for segment, fragments_count in segment_run_table['segment_run']:
+        for _ in range(fragments_count):
+            res.append((segment, next(fragments_counter)))
     return res
 
 
-def write_flv_header(stream, metadata):
-    """Writes the FLV header and the metadata to stream"""
+def write_unsigned_int(stream, val):
+    stream.write(struct_pack('!I', val))
+
+
+def write_unsigned_int_24(stream, val):
+    stream.write(struct_pack('!I', val)[1:])
+
+
+def write_flv_header(stream):
+    """Writes the FLV header to stream"""
     # FLV header
     stream.write(b'FLV\x01')
     stream.write(b'\x05')
     stream.write(b'\x00\x00\x00\x09')
-    # FLV File body
     stream.write(b'\x00\x00\x00\x00')
-    # FLVTAG
-    # Script data
-    stream.write(b'\x12')
-    # Size of the metadata with 3 bytes
-    stream.write(struct_pack('!L', len(metadata))[1:])
-    stream.write(b'\x00\x00\x00\x00\x00\x00\x00')
-    stream.write(metadata)
-    # Magic numbers extracted from the output files produced by AdobeHDS.php
-    #(https://github.com/K-S-V/Scripts)
-    stream.write(b'\x00\x00\x01\x73')
+
+
+def write_metadata_tag(stream, metadata):
+    """Writes optional metadata tag to stream"""
+    SCRIPT_TAG = b'\x12'
+    FLV_TAG_HEADER_LEN = 11
+
+    if metadata:
+        stream.write(SCRIPT_TAG)
+        write_unsigned_int_24(stream, len(metadata))
+        stream.write(b'\x00\x00\x00\x00\x00\x00\x00')
+        stream.write(metadata)
+        write_unsigned_int(stream, FLV_TAG_HEADER_LEN + len(metadata))
 
 
 def _add_ns(prop):
@@ -256,7 +265,11 @@ class F4mFD(FileDownloader):
             bootstrap = self.ydl.urlopen(bootstrap_url).read()
         else:
             bootstrap = base64.b64decode(bootstrap_node.text)
-        metadata = base64.b64decode(media.find(_add_ns('metadata')).text)
+        metadata_node = media.find(_add_ns('metadata'))
+        if metadata_node is not None:
+            metadata = base64.b64decode(metadata_node.text)
+        else:
+            metadata = None
         boot_info = read_bootstrap_info(bootstrap)
 
         fragments_list = build_fragments_list(boot_info)
@@ -269,7 +282,8 @@ class F4mFD(FileDownloader):
 
         tmpfilename = self.temp_name(filename)
         (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
-        write_flv_header(dest_stream, metadata)
+        write_flv_header(dest_stream)
+        write_metadata_tag(dest_stream, metadata)
 
         # This dict stores the download progress, it's updated by the progress
         # hook

youtube_dl/downloader/hls.py

@@ -11,7 +11,6 @@ from ..compat import (
     compat_urllib_request,
 )
 from ..utils import (
-    check_executable,
     encodeFilename,
 )
 
@@ -27,16 +26,13 @@ class HlsFD(FileDownloader):
             '-bsf:a', 'aac_adtstoasc',
             encodeFilename(tmpfilename, for_subprocess=True)]
 
-        for program in ['avconv', 'ffmpeg']:
-            if check_executable(program, ['-version']):
-                break
-        else:
+        ffpp = FFmpegPostProcessor(downloader=self)
+        program = ffpp._executable
+        if program is None:
             self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
             return False
-        cmd = [program] + args
-
-        ffpp = FFmpegPostProcessor(downloader=self)
         ffpp.check_version()
+        cmd = [program] + args
 
         retval = subprocess.call(cmd)
         if retval == 0:

youtube_dl/downloader/mplayer.py

@@ -4,8 +4,8 @@ import os
 import subprocess
 
 from .common import FileDownloader
-from ..compat import compat_subprocess_get_DEVNULL
 from ..utils import (
+    check_executable,
     encodeFilename,
 )
 
@@ -20,11 +20,7 @@ class MplayerFD(FileDownloader):
             'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
             '-dumpstream', '-dumpfile', tmpfilename, url]
         # Check for mplayer first
-        try:
-            subprocess.call(
-                ['mplayer', '-h'],
-                stdout=compat_subprocess_get_DEVNULL(), stderr=subprocess.STDOUT)
-        except (OSError, IOError):
+        if not check_executable('mplayer', ['-h']):
             self.report_error('MMS or RTSP download detected but "%s" could not be run' % args[0])
             return False
 

youtube_dl/downloader/rtmp.py

@@ -185,7 +185,7 @@ class RtmpFD(FileDownloader):
             cursize = os.path.getsize(encodeFilename(tmpfilename))
             if prevsize == cursize and retval == RD_FAILED:
                 break
-             # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
+            # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
             if prevsize == cursize and retval == RD_INCOMPLETE and cursize > 1024:
                 self.to_screen('[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
                 retval = RD_SUCCESS

youtube_dl/extractor/__init__.py

@@ -1,10 +1,14 @@
 from __future__ import unicode_literals
 
 from .abc import ABCIE
+from .abc7news import Abc7NewsIE
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
+from .adobetv import AdobeTVIE
 from .adultswim import AdultSwimIE
 from .aftonbladet import AftonbladetIE
+from .aljazeera import AlJazeeraIE
+from .alphaporno import AlphaPornoIE
 from .anitube import AnitubeIE
 from .anysex import AnySexIE
 from .aol import AolIE
@@ -22,7 +26,9 @@ from .arte import (
     ArteTVDDCIE,
     ArteTVEmbedIE,
 )
-from .audiomack import AudiomackIE
+from .atresplayer import AtresPlayerIE
+from .atttechchannel import ATTTechChannelIE
+from .audiomack import AudiomackIE, AudiomackAlbumIE
 from .auengine import AUEngineIE
 from .azubu import AzubuIE
 from .bambuser import BambuserIE, BambuserChannelIE
@@ -62,10 +68,13 @@ from .cnet import CNETIE
 from .cnn import (
     CNNIE,
     CNNBlogsIE,
+    CNNArticleIE,
 )
 from .collegehumor import CollegeHumorIE
+from .collegerama import CollegeRamaIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .comcarcoff import ComCarCoffIE
+from .commonmistakes import CommonMistakesIE
 from .condenast import CondeNastIE
 from .cracked import CrackedIE
 from .criterion import CriterionIE
@@ -85,14 +94,17 @@ from .deezer import DeezerPlaylistIE
 from .dfb import DFBIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
+from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
 from .drtv import DRTVIE
+from .dvtv import DVTVIE
 from .dump import DumpIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .divxstage import DivxStageIE
 from .dropbox import DropboxIE
 from .ebaumsworld import EbaumsWorldIE
+from .echomsk import EchoMskIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .einthusan import EinthusanIE
@@ -105,6 +117,7 @@ from .elpais import ElPaisIE
 from .empflix import EMPFlixIE
 from .engadget import EngadgetIE
 from .eporner import EpornerIE
+from .eroprofile import EroProfileIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
@@ -150,6 +163,7 @@ from .gametrailers import GametrailersIE
 from .gdcvault import GDCVaultIE
 from .generic import GenericIE
 from .giantbomb import GiantBombIE
+from .giga import GigaIE
 from .glide import GlideIE
 from .globo import GloboIE
 from .godtube import GodTubeIE
@@ -162,9 +176,12 @@ from .goshgay import GoshgayIE
 from .grooveshark import GroovesharkIE
 from .groupon import GrouponIE
 from .hark import HarkIE
+from .hearthisat import HearThisAtIE
 from .heise import HeiseIE
+from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
+from .hitbox import HitboxIE, HitboxLiveIE
 from .hornbunny import HornBunnyIE
 from .hostingbulk import HostingBulkIE
 from .hotnewhiphop import HotNewHipHopIE
@@ -194,6 +211,7 @@ from .jove import JoveIE
 from .jukebox import JukeboxIE
 from .jpopsukitv import JpopsukiIE
 from .kankan import KankanIE
+from .karaoketv import KaraoketvIE
 from .keezmovies import KeezMoviesIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
@@ -210,6 +228,7 @@ from .livestream import (
     LivestreamOriginalIE,
     LivestreamShortenerIE,
 )
+from .lnkgo import LnkGoIE
 from .lrt import LRTIE
 from .lynda import (
     LyndaIE,
@@ -262,6 +281,8 @@ from .nbc import (
 )
 from .ndr import NDRIE
 from .ndtv import NDTVIE
+from .netzkino import NetzkinoIE
+from .nerdcubed import NerdCubedFeedIE
 from .newgrounds import NewgroundsIE
 from .newstube import NewstubeIE
 from .nfb import NFBIE
@@ -277,6 +298,7 @@ from .nowness import NownessIE
 from .nowvideo import NowVideoIE
 from .npo import (
     NPOIE,
+    NPOLiveIE,
     TegenlichtVproIE,
 )
 from .nrk import (
@@ -288,6 +310,7 @@ from .nytimes import NYTimesIE
 from .nuvid import NuvidIE
 from .oktoberfesttv import OktoberfestTVIE
 from .ooyala import OoyalaIE
+from .openfilm import OpenFilmIE
 from .orf import (
     ORFTVthekIE,
     ORFOE1IE,
@@ -312,6 +335,7 @@ from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
 from .quickvid import QuickVidIE
 from .radiode import RadioDeIE
+from .radiobremen import RadioBremenIE
 from .radiofrance import RadioFranceIE
 from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
@@ -323,6 +347,7 @@ from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtbf import RTBFIE
+from .rte import RteIE
 from .rtlnl import RtlXlIE
 from .rtlnow import RTLnowIE
 from .rtp import RTPIE
@@ -332,6 +357,7 @@ from .ruhd import RUHDIE
 from .rutube import (
     RutubeIE,
     RutubeChannelIE,
+    RutubeEmbedIE,
     RutubeMovieIE,
     RutubePersonIE,
 )
@@ -341,6 +367,7 @@ from .savefrom import SaveFromIE
 from .sbs import SBSIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
+from .screencastomatic import ScreencastOMaticIE
 from .screenwavemedia import CinemassacreIE, ScreenwaveMediaIE, TeamFourIE
 from .servingsys import ServingSysIE
 from .sexu import SexuIE
@@ -383,6 +410,7 @@ from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
+from .streetvoice import StreetVoiceIE
 from .sunporno import SunPornoIE
 from .swrmediathek import SWRMediathekIE
 from .syfy import SyfyIE
@@ -401,8 +429,10 @@ from .ted import TEDIE
 from .telebruxelles import TeleBruxellesIE
 from .telecinco import TelecincoIE
 from .telemb import TeleMBIE
+from .teletask import TeleTaskIE
 from .tenplay import TenPlayIE
 from .testurl import TestURLIE
+from .testtube import TestTubeIE
 from .tf1 import TF1IE
 from .theonion import TheOnionIE
 from .theplatform import ThePlatformIE
@@ -428,10 +458,18 @@ from .tunein import TuneInIE
 from .turbo import TurboIE
 from .tutv import TutvIE
 from .tvigle import TvigleIE
-from .tvp import TvpIE
+from .tvp import TvpIE, TvpSeriesIE
 from .tvplay import TVPlayIE
 from .twentyfourvideo import TwentyFourVideoIE
-from .twitch import TwitchIE
+from .twitch import (
+    TwitchVideoIE,
+    TwitchChapterIE,
+    TwitchVodIE,
+    TwitchProfileIE,
+    TwitchPastBroadcastsIE,
+    TwitchBookmarksIE,
+    TwitchStreamIE,
+)
 from .ubu import UbuIE
 from .udemy import (
     UdemyIE,
@@ -459,6 +497,7 @@ from .videott import VideoTtIE
 from .videoweed import VideoWeedIE
 from .vidme import VidmeIE
 from .vidzi import VidziIE
+from .vier import VierIE, VierVideosIE
 from .vimeo import (
     VimeoIE,
     VimeoAlbumIE,
@@ -494,6 +533,7 @@ from .wdr import (
     WDRMobileIE,
     WDRMausIE,
 )
+from .webofstories import WebOfStoriesIE
 from .weibo import WeiboIE
 from .wimp import WimpIE
 from .wistia import WistiaIE
@@ -506,6 +546,7 @@ from .xminus import XMinusIE
 from .xnxx import XNXXIE
 from .xvideos import XVideosIE
 from .xtube import XTubeUserIE, XTubeIE
+from .xxxymovies import XXXYMoviesIE
 from .yahoo import (
     YahooIE,
     YahooSearchIE,
@@ -528,7 +569,7 @@ from .youtube import (
     YoutubeSearchURLIE,
     YoutubeShowIE,
     YoutubeSubscriptionsIE,
-    YoutubeTopListIE,
+    YoutubeTruncatedIDIE,
     YoutubeTruncatedURLIE,
     YoutubeUserIE,
     YoutubeWatchLaterIE,
@@ -554,6 +595,17 @@ def gen_extractors():
     return [klass() for klass in _ALL_CLASSES]
 
 
+def list_extractors(age_limit):
+    """
+    Return a list of extractors that are suitable for the given age,
+    sorted by extractor ID.
+    """
+
+    return sorted(
+        filter(lambda ie: ie.is_suitable(age_limit), gen_extractors()),
+        key=lambda ie: ie.IE_NAME.lower())
+
+
 def get_info_extractor(ie_name):
     """Returns the info extractor class with the given ie_name"""
     return globals()[ie_name + 'IE']

youtube_dl/extractor/abc7news.py

@@ -0,0 +1,68 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import parse_iso8601
+
+
+class Abc7NewsIE(InfoExtractor):
+    _VALID_URL = r'https?://abc7news\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
+    _TESTS = [
+        {
+            'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
+            'info_dict': {
+                'id': '472581',
+                'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
+                'ext': 'mp4',
+                'title': 'East Bay museum celebrates history of synthesized music',
+                'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'timestamp': 1421123075,
+                'upload_date': '20150113',
+                'uploader': 'Jonathan Bloom',
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://abc7news.com/472581',
+            'only_matching': True,
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id') or video_id
+
+        webpage = self._download_webpage(url, display_id)
+
+        m3u8 = self._html_search_meta(
+            'contentURL', webpage, 'm3u8 url', fatal=True)
+
+        formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
+        self._sort_formats(formats)
+
+        title = self._og_search_title(webpage).strip()
+        description = self._og_search_description(webpage).strip()
+        thumbnail = self._og_search_thumbnail(webpage)
+        timestamp = parse_iso8601(self._search_regex(
+            r'<div class="meta">\s*<time class="timeago" datetime="([^"]+)">',
+            webpage, 'upload date', fatal=False))
+        uploader = self._search_regex(
+            r'rel="author">([^<]+)</a>',
+            webpage, 'uploader', default=None)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'formats': formats,
+        }

youtube_dl/extractor/adobetv.py

@@ -0,0 +1,70 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    unified_strdate,
+    str_to_int,
+)
+
+
+class AdobeTVIE(InfoExtractor):
+    _VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)'
+
+    _TEST = {
+        'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
+        'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
+        'info_dict': {
+            'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop',
+            'ext': 'mp4',
+            'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
+            'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'upload_date': '20110914',
+            'duration': 60,
+            'view_count': int,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        player = self._parse_json(
+            self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'),
+            video_id)
+
+        title = player.get('title') or self._search_regex(
+            r'data-title="([^"]+)"', webpage, 'title')
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        upload_date = unified_strdate(
+            self._html_search_meta('datepublished', webpage, 'upload date'))
+
+        duration = parse_duration(
+            self._html_search_meta('duration', webpage, 'duration')
+            or self._search_regex(r'Runtime:\s*(\d{2}:\d{2}:\d{2})', webpage, 'duration'))
+
+        view_count = str_to_int(self._search_regex(
+            r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>',
+            webpage, 'view count'))
+
+        formats = [{
+            'url': source['src'],
+            'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None,
+            'tbr': source.get('bitrate'),
+        } for source in player['sources']]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+        }

youtube_dl/extractor/aljazeera.py

@@ -0,0 +1,35 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class AlJazeeraIE(InfoExtractor):
+    _VALID_URL = r'http://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
+
+    _TEST = {
+        'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
+        'info_dict': {
+            'id': '3792260579001',
+            'ext': 'mp4',
+            'title': 'The Slum - Episode 1: Deliverance',
+            'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.',
+            'uploader': 'Al Jazeera English',
+        },
+        'add_ie': ['Brightcove'],
+    }
+
+    def _real_extract(self, url):
+        program_name = self._match_id(url)
+        webpage = self._download_webpage(url, program_name)
+        brightcove_id = self._search_regex(
+            r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id')
+
+        return {
+            '_type': 'url',
+            'url': (
+                'brightcove:'
+                'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc'
+                '&%40videoPlayer={0}'.format(brightcove_id)
+            ),
+            'ie_key': 'Brightcove',
+        }

youtube_dl/extractor/allocine.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class AllocineIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=)(?P<id>[0-9]+)(?:\.html)?'
+    _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'
 
     _TESTS = [{
         'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
@@ -44,6 +44,9 @@ class AllocineIE(InfoExtractor):
             'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac',
             'thumbnail': 're:http://.*\.jpg',
         },
+    }, {
+        'url': 'http://www.allocine.fr/video/video-19550147/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/alphaporno.py

@@ -0,0 +1,77 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_iso8601,
+    parse_duration,
+    parse_filesize,
+    int_or_none,
+)
+
+
+class AlphaPornoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/',
+        'md5': 'feb6d3bba8848cd54467a87ad34bd38e',
+        'info_dict': {
+            'id': '258807',
+            'display_id': 'sensual-striptease-porn-with-samantha-alexandra',
+            'ext': 'mp4',
+            'title': 'Sensual striptease porn with Samantha Alexandra',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'timestamp': 1418694611,
+            'upload_date': '20141216',
+            'duration': 387,
+            'filesize_approx': 54120000,
+            'tbr': 1145,
+            'categories': list,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None)
+
+        video_url = self._search_regex(
+            r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
+        ext = self._html_search_meta(
+            'encodingFormat', webpage, 'ext', default='.mp4')[1:]
+
+        title = self._search_regex(
+            [r'<meta content="([^"]+)" itemprop="description">',
+             r'class="title" itemprop="name">([^<]+)<'],
+            webpage, 'title')
+        thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail')
+        timestamp = parse_iso8601(self._html_search_meta(
+            'uploadDate', webpage, 'upload date'))
+        duration = parse_duration(self._html_search_meta(
+            'duration', webpage, 'duration'))
+        filesize_approx = parse_filesize(self._html_search_meta(
+            'contentSize', webpage, 'file size'))
+        bitrate = int_or_none(self._html_search_meta(
+            'bitrate', webpage, 'bitrate'))
+        categories = self._html_search_meta(
+            'keywords', webpage, 'categories', default='').split(',')
+
+        age_limit = self._rta_search(webpage)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'ext': ext,
+            'title': title,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'filesize_approx': filesize_approx,
+            'tbr': bitrate,
+            'categories': categories,
+            'age_limit': age_limit,
+        }

youtube_dl/extractor/archiveorg.py

@@ -1,42 +1,48 @@
 from __future__ import unicode_literals
 
-import json
-import re
-
 from .common import InfoExtractor
-from ..utils import (
-    unified_strdate,
-)
+from ..utils import unified_strdate
 
 
 class ArchiveOrgIE(InfoExtractor):
     IE_NAME = 'archive.org'
     IE_DESC = 'archive.org videos'
-    _VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
-    _TEST = {
-        "url": "http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect",
-        'file': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',
+    _VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
+    _TESTS = [{
+        'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
         'md5': '8af1d4cf447933ed3c7f4871162602db',
         'info_dict': {
-            "title": "1968 Demo - FJCC Conference Presentation Reel #1",
-            "description": "Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also <a href=\"http://dougengelbart.org/firsts/dougs-1968-demo.html\" rel=\"nofollow\">Doug's 1968 Demo page</a> for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | <a href=\"http://www.archive.org/details/XD300-24_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 2</a> | <a href=\"http://www.archive.org/details/XD300-25_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 3</a>",
-            "upload_date": "19681210",
-            "uploader": "SRI International"
+            'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
+            'ext': 'ogv',
+            'title': '1968 Demo - FJCC Conference Presentation Reel #1',
+            'description': 'md5:1780b464abaca9991d8968c877bb53ed',
+            'upload_date': '19681210',
+            'uploader': 'SRI International'
         }
-    }
+    }, {
+        'url': 'https://archive.org/details/Cops1922',
+        'md5': '18f2a19e6d89af8425671da1cf3d4e04',
+        'info_dict': {
+            'id': 'Cops1922',
+            'ext': 'ogv',
+            'title': 'Buster Keaton\'s "Cops" (1922)',
+            'description': 'md5:70f72ee70882f713d4578725461ffcc3',
+        }
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         json_url = url + ('?' if '?' in url else '&') + 'output=json'
-        json_data = self._download_webpage(json_url, video_id)
-        data = json.loads(json_data)
+        data = self._download_json(json_url, video_id)
 
-        title = data['metadata']['title'][0]
-        description = data['metadata']['description'][0]
-        uploader = data['metadata']['creator'][0]
-        upload_date = unified_strdate(data['metadata']['date'][0])
+        def get_optional(data_dict, field):
+            return data_dict['metadata'].get(field, [None])[0]
+
+        title = get_optional(data, 'title')
+        description = get_optional(data, 'description')
+        uploader = get_optional(data, 'creator')
+        upload_date = unified_strdate(get_optional(data, 'date'))
 
         formats = [
             {

youtube_dl/extractor/arte.py

@@ -37,7 +37,7 @@ class ArteTvIE(InfoExtractor):
             config_xml_url, video_id, note='Downloading configuration')
 
         formats = [{
-            'forma_id': q.attrib['quality'],
+            'format_id': q.attrib['quality'],
             # The playpath starts at 'mp4:', if we don't manually
             # split the url, rtmpdump will incorrectly parse them
             'url': q.text.split('mp4:', 1)[0],
@@ -133,7 +133,7 @@ class ArteTVPlus7IE(InfoExtractor):
                 'width': int_or_none(f.get('width')),
                 'height': int_or_none(f.get('height')),
                 'tbr': int_or_none(f.get('bitrate')),
-                'quality': qfunc(f['quality']),
+                'quality': qfunc(f.get('quality')),
                 'source_preference': source_pref,
             }
 

youtube_dl/extractor/atresplayer.py

@@ -0,0 +1,163 @@
+from __future__ import unicode_literals
+
+import time
+import hmac
+
+from .subtitles import SubtitlesInfoExtractor
+from ..compat import (
+    compat_str,
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+from ..utils import (
+    int_or_none,
+    float_or_none,
+    xpath_text,
+    ExtractorError,
+)
+
+
+class AtresPlayerIE(SubtitlesInfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
+    _TESTS = [
+        {
+            'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html',
+            'md5': 'efd56753cda1bb64df52a3074f62e38a',
+            'info_dict': {
+                'id': 'capitulo-10-especial-solidario-nochebuena',
+                'ext': 'mp4',
+                'title': 'Especial Solidario de Nochebuena',
+                'description': 'md5:e2d52ff12214fa937107d21064075bf1',
+                'duration': 5527.6,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
+        {
+            'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html',
+            'only_matching': True,
+        },
+    ]
+
+    _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J'
+    _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)'
+    _TIMESTAMP_SHIFT = 30000
+
+    _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json'
+    _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json'
+    _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
+    _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
+
+    _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
+
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_form = {
+            'j_username': username,
+            'j_password': password,
+        }
+
+        request = compat_urllib_request.Request(
+            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        response = self._download_webpage(
+            request, None, 'Logging in as %s' % username)
+
+        error = self._html_search_regex(
+            r'(?s)<ul class="list_error">(.+?)</ul>', response, 'error', default=None)
+        if error:
+            raise ExtractorError(
+                'Unable to login: %s' % error, expected=True)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        episode_id = self._search_regex(
+            r'episode="([^"]+)"', webpage, 'episode id')
+
+        timestamp = int_or_none(self._download_webpage(
+            self._TIME_API_URL,
+            video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
+        timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
+        token = hmac.new(
+            self._MAGIC.encode('ascii'),
+            (episode_id + timestamp_shifted).encode('utf-8')
+        ).hexdigest()
+
+        formats = []
+        for fmt in ['windows', 'android_tablet']:
+            request = compat_urllib_request.Request(
+                self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
+            request.add_header('Youtubedl-user-agent', self._USER_AGENT)
+
+            fmt_json = self._download_json(
+                request, video_id, 'Downloading %s video JSON' % fmt)
+
+            result = fmt_json.get('resultDes')
+            if result.lower() != 'ok':
+                raise ExtractorError(
+                    '%s returned error: %s' % (self.IE_NAME, result), expected=True)
+
+            for format_id, video_url in fmt_json['resultObject'].items():
+                if format_id == 'token' or not video_url.startswith('http'):
+                    continue
+                if video_url.endswith('/Manifest'):
+                    if 'geodeswowsmpra3player' in video_url:
+                        f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
+                        f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
+                        # this videos are protected by DRM, the f4m downloader doesn't support them
+                        continue
+                    else:
+                        f4m_url = video_url[:-9] + '/manifest.f4m'
+                    formats.extend(self._extract_f4m_formats(f4m_url, video_id))
+                else:
+                    formats.append({
+                        'url': video_url,
+                        'format_id': 'android-%s' % format_id,
+                        'preference': 1,
+                    })
+        self._sort_formats(formats)
+
+        player = self._download_json(
+            self._PLAYER_URL_TEMPLATE % episode_id,
+            episode_id)
+
+        path_data = player.get('pathData')
+
+        episode = self._download_xml(
+            self._EPISODE_URL_TEMPLATE % path_data,
+            video_id, 'Downloading episode XML')
+
+        duration = float_or_none(xpath_text(
+            episode, './media/asset/info/technical/contentDuration', 'duration'))
+
+        art = episode.find('./media/asset/info/art')
+        title = xpath_text(art, './name', 'title')
+        description = xpath_text(art, './description', 'description')
+        thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
+
+        subtitles = {}
+        subtitle = xpath_text(episode, './media/asset/files/subtitle', 'subtitle')
+        if subtitle:
+            subtitles['es'] = subtitle
+
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': self.extract_subtitles(video_id, subtitles),
+        }

youtube_dl/extractor/atttechchannel.py

@@ -0,0 +1,55 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+
+class ATTTechChannelIE(InfoExtractor):
+    _VALID_URL = r'https?://techchannel\.att\.com/play-video\.cfm/([^/]+/)*(?P<id>.+)'
+    _TEST = {
+        'url': 'http://techchannel.att.com/play-video.cfm/2014/1/27/ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
+        'info_dict': {
+            'id': '11316',
+            'display_id': 'ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
+            'ext': 'flv',
+            'title': 'AT&T Archives : The UNIX System: Making Computers Easier to Use',
+            'description': 'A 1982 film about UNIX is the foundation for software in use around Bell Labs and AT&T.',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'upload_date': '20140127',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_url = self._search_regex(
+            r"url\s*:\s*'(rtmp://[^']+)'",
+            webpage, 'video URL')
+
+        video_id = self._search_regex(
+            r'mediaid\s*=\s*(\d+)',
+            webpage, 'video id', fatal=False)
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+        upload_date = unified_strdate(self._search_regex(
+            r'[Rr]elease\s+date:\s*(\d{1,2}/\d{1,2}/\d{4})',
+            webpage, 'upload date', fatal=False), False)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'ext': 'flv',
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+        }

youtube_dl/extractor/audiomack.py

@@ -1,11 +1,15 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import itertools
+import time
+
 from .common import InfoExtractor
 from .soundcloud import SoundcloudIE
-from ..utils import ExtractorError
-
-import time
+from ..utils import (
+    ExtractorError,
+    url_basename,
+)
 
 
 class AudiomackIE(InfoExtractor):
@@ -17,12 +21,13 @@ class AudiomackIE(InfoExtractor):
             'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary',
             'info_dict':
             {
-                'id': 'roosh-williams/extraordinary',
+                'id': '310086',
                 'ext': 'mp3',
-                'title': 'Roosh Williams - Extraordinary'
+                'uploader': 'Roosh Williams',
+                'title': 'Extraordinary'
             }
         },
-        # hosted on soundcloud via audiomack
+        # audiomack wrapper around soundcloud song
         {
             'add_ie': ['Soundcloud'],
             'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare',
@@ -38,32 +43,97 @@ class AudiomackIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        # URLs end with [uploader name]/[uploader title]
+        # this title is whatever the user types in, and is rarely
+        # the proper song title.  Real metadata is in the api response
+        album_url_tag = self._match_id(url)
 
+        # Request the extended version of the api for extra fields like artist and title
         api_response = self._download_json(
-            "http://www.audiomack.com/api/music/url/song/%s?_=%d" % (
-                video_id, time.time()),
-            video_id)
+            'http://www.audiomack.com/api/music/url/song/%s?extended=1&_=%d' % (
+                album_url_tag, time.time()),
+            album_url_tag)
 
-        if "url" not in api_response:
-            raise ExtractorError("Unable to deduce api url of song")
-        realurl = api_response["url"]
+        # API is inconsistent with errors
+        if 'url' not in api_response or not api_response['url'] or 'error' in api_response:
+            raise ExtractorError('Invalid url %s', url)
 
         # Audiomack wraps a lot of soundcloud tracks in their branded wrapper
-        # - if so, pass the work off to the soundcloud extractor
-        if SoundcloudIE.suitable(realurl):
-            return {'_type': 'url', 'url': realurl, 'ie_key': 'Soundcloud'}
-
-        webpage = self._download_webpage(url, video_id)
-        artist = self._html_search_regex(
-            r'<span class="artist">(.*?)</span>', webpage, "artist")
-        songtitle = self._html_search_regex(
-            r'<h1 class="profile-title song-title"><span class="artist">.*?</span>(.*?)</h1>',
-            webpage, "title")
-        title = artist + " - " + songtitle
+        # if so, pass the work off to the soundcloud extractor
+        if SoundcloudIE.suitable(api_response['url']):
+            return {'_type': 'url', 'url': api_response['url'], 'ie_key': 'Soundcloud'}
 
         return {
-            'id': video_id,
-            'title': title,
-            'url': realurl,
+            'id': api_response.get('id', album_url_tag),
+            'uploader': api_response.get('artist'),
+            'title': api_response.get('title'),
+            'url': api_response['url'],
         }
+
+
+class AudiomackAlbumIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?audiomack\.com/album/(?P<id>[\w/-]+)'
+    IE_NAME = 'audiomack:album'
+    _TESTS = [
+        # Standard album playlist
+        {
+            'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape',
+            'playlist_count': 15,
+            'info_dict':
+            {
+                'id': '812251',
+                'title': 'Tha Tour: Part 2 (Official Mixtape)'
+            }
+        },
+        # Album playlist ripped from fakeshoredrive with no metadata
+        {
+            'url': 'http://www.audiomack.com/album/fakeshoredrive/ppp-pistol-p-project',
+            'playlist': [{
+                'info_dict': {
+                    'title': '9.-heaven-or-hell-chimaca-ft-zuse-prod-by-dj-fu',
+                    'id': '9.-heaven-or-hell-chimaca-ft-zuse-prod-by-dj-fu',
+                    'ext': 'mp3',
+                }
+            }],
+            'params': {
+                'playliststart': 8,
+                'playlistend': 8,
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        # URLs end with [uploader name]/[uploader title]
+        # this title is whatever the user types in, and is rarely
+        # the proper song title.  Real metadata is in the api response
+        album_url_tag = self._match_id(url)
+        result = {'_type': 'playlist', 'entries': []}
+        # There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata
+        # Therefore we don't know how many songs the album has and must infi-loop until failure
+        for track_no in itertools.count():
+            # Get song's metadata
+            api_response = self._download_json(
+                'http://www.audiomack.com/api/music/url/album/%s/%d?extended=1&_=%d'
+                % (album_url_tag, track_no, time.time()), album_url_tag,
+                note='Querying song information (%d)' % (track_no + 1))
+
+            # Total failure, only occurs when url is totally wrong
+            # Won't happen in middle of valid playlist (next case)
+            if 'url' not in api_response or 'error' in api_response:
+                raise ExtractorError('Invalid url for track %d of album url %s' % (track_no, url))
+            # URL is good but song id doesn't exist - usually means end of playlist
+            elif not api_response['url']:
+                break
+            else:
+                # Pull out the album metadata and add to result (if it exists)
+                for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]:
+                    if apikey in api_response and resultkey not in result:
+                        result[resultkey] = api_response[apikey]
+                song_id = url_basename(api_response['url']).rpartition('.')[0]
+                result['entries'].append({
+                    'id': api_response.get('id', song_id),
+                    'uploader': api_response.get('artist'),
+                    'title': api_response.get('title', song_id),
+                    'url': api_response['url'],
+                })
+        return result

youtube_dl/extractor/auengine.py

@@ -7,6 +7,7 @@ from ..compat import compat_urllib_parse
 from ..utils import (
     determine_ext,
     ExtractorError,
+    remove_end,
 )
 
 
@@ -27,23 +28,18 @@ class AUEngineIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title')
-        title = title.strip()
-        links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
-        links = map(compat_urllib_parse.unquote, links)
+        title = self._html_search_regex(
+            r'<title>\s*(?P<title>.+?)\s*</title>', webpage, 'title')
+        video_urls = re.findall(r'http://\w+.auengine.com/vod/.*[^\W]', webpage)
+        video_url = compat_urllib_parse.unquote(video_urls[0])
+        thumbnails = re.findall(r'http://\w+.auengine.com/thumb/.*[^\W]', webpage)
+        thumbnail = compat_urllib_parse.unquote(thumbnails[0])
 
-        thumbnail = None
-        video_url = None
-        for link in links:
-            if link.endswith('.png'):
-                thumbnail = link
-            elif '/videos/' in link:
-                video_url = link
         if not video_url:
             raise ExtractorError('Could not find video URL')
+
         ext = '.' + determine_ext(video_url)
-        if ext == title[-len(ext):]:
-            title = title[:-len(ext)]
+        title = remove_end(title, ext)
 
         return {
             'id': video_id,

youtube_dl/extractor/bandcamp.py

@@ -161,7 +161,8 @@ class BandcampAlbumIE(InfoExtractor):
         entries = [
             self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
             for t_path in tracks_paths]
-        title = self._search_regex(r'album_title : "(.*?)"', webpage, 'title')
+        title = self._search_regex(
+            r'album_title\s*:\s*"(.*?)"', webpage, 'title', fatal=False)
         return {
             '_type': 'playlist',
             'id': playlist_id,

youtube_dl/extractor/bbccouk.py

@@ -10,7 +10,7 @@ from ..compat import compat_HTTPError
 class BBCCoUkIE(SubtitlesInfoExtractor):
     IE_NAME = 'bbc.co.uk'
     IE_DESC = 'BBC iPlayer'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:programmes|iplayer/episode)/(?P<id>[\da-z]{8})'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
 
     _TESTS = [
         {
@@ -18,8 +18,8 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
             'info_dict': {
                 'id': 'b039d07m',
                 'ext': 'flv',
-                'title': 'Kaleidoscope: Leonard Cohen',
-                'description': 'md5:db4755d7a665ae72343779f7dacb402c',
+                'title': 'Kaleidoscope, Leonard Cohen',
+                'description': 'The Canadian poet and songwriter reflects on his musical career.',
                 'duration': 1740,
             },
             'params': {
@@ -71,7 +71,54 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
                 'skip_download': True,
             },
             'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
-        },
+        }, {
+            'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
+            'info_dict': {
+                'id': 'b04v209v',
+                'ext': 'flv',
+                'title': 'Pete Tong, The Essential New Tune Special',
+                'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
+                'duration': 10800,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }, {
+            'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
+            'note': 'Audio',
+            'info_dict': {
+                'id': 'p02frcch',
+                'ext': 'flv',
+                'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix',
+                'description': 'French house superstar Madeon takes us out of the club and onto the after party.',
+                'duration': 3507,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }, {
+            'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
+            'note': 'Video',
+            'info_dict': {
+                'id': 'p025c103',
+                'ext': 'flv',
+                'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
+                'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
+                'duration': 226,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
+            'only_matching': True,
+        }, {
+            'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
+            'only_matching': True,
+        }
     ]
 
     def _extract_asx_playlist(self, connection, programme_id):
@@ -203,6 +250,59 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
 
         return formats, subtitles
 
+    def _download_playlist(self, playlist_id):
+        try:
+            playlist = self._download_json(
+                'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
+                playlist_id, 'Downloading playlist JSON')
+
+            version = playlist.get('defaultAvailableVersion')
+            if version:
+                smp_config = version['smpConfig']
+                title = smp_config['title']
+                description = smp_config['summary']
+                for item in smp_config['items']:
+                    kind = item['kind']
+                    if kind != 'programme' and kind != 'radioProgramme':
+                        continue
+                    programme_id = item.get('vpid')
+                    duration = int(item.get('duration'))
+                    formats, subtitles = self._download_media_selector(programme_id)
+                return programme_id, title, description, duration, formats, subtitles
+        except ExtractorError as ee:
+            if not isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
+                raise
+
+        # fallback to legacy playlist
+        playlist = self._download_xml(
+            'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id,
+            playlist_id, 'Downloading legacy playlist XML')
+
+        no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
+        if no_items is not None:
+            reason = no_items.get('reason')
+            if reason == 'preAvailability':
+                msg = 'Episode %s is not yet available' % playlist_id
+            elif reason == 'postAvailability':
+                msg = 'Episode %s is no longer available' % playlist_id
+            elif reason == 'noMedia':
+                msg = 'Episode %s is not currently available' % playlist_id
+            else:
+                msg = 'Episode %s is not available: %s' % (playlist_id, reason)
+            raise ExtractorError(msg, expected=True)
+
+        for item in self._extract_items(playlist):
+            kind = item.get('kind')
+            if kind != 'programme' and kind != 'radioProgramme':
+                continue
+            title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
+            description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
+            programme_id = item.get('identifier')
+            duration = int(item.get('duration'))
+            formats, subtitles = self._download_media_selector(programme_id)
+
+        return programme_id, title, description, duration, formats, subtitles
+
     def _real_extract(self, url):
         group_id = self._match_id(url)
 
@@ -219,32 +319,7 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
             duration = player['duration']
             formats, subtitles = self._download_media_selector(programme_id)
         else:
-            playlist = self._download_xml(
-                'http://www.bbc.co.uk/iplayer/playlist/%s' % group_id,
-                group_id, 'Downloading playlist XML')
-
-            no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
-            if no_items is not None:
-                reason = no_items.get('reason')
-                if reason == 'preAvailability':
-                    msg = 'Episode %s is not yet available' % group_id
-                elif reason == 'postAvailability':
-                    msg = 'Episode %s is no longer available' % group_id
-                elif reason == 'noMedia':
-                    msg = 'Episode %s is not currently available' % group_id
-                else:
-                    msg = 'Episode %s is not available: %s' % (group_id, reason)
-                raise ExtractorError(msg, expected=True)
-
-            for item in self._extract_items(playlist):
-                kind = item.get('kind')
-                if kind != 'programme' and kind != 'radioProgramme':
-                    continue
-                title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
-                description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
-                programme_id = item.get('identifier')
-                duration = int(item.get('duration'))
-                formats, subtitles = self._download_media_selector(programme_id)
+            programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
 
         if self._downloader.params.get('listsubtitles', False):
             self._list_available_subtitles(programme_id, subtitles)

youtube_dl/extractor/bet.py

@@ -16,7 +16,7 @@ class BetIE(InfoExtractor):
         {
             'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
             'info_dict': {
-                'id': '417cd61c-c793-4e8e-b006-e445ecc45add',
+                'id': '740ab250-bb94-4a8a-8787-fe0de7c74471',
                 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
                 'ext': 'flv',
                 'title': 'BET News Presents: A Conversation With President Obama',
@@ -35,7 +35,7 @@ class BetIE(InfoExtractor):
         {
             'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
             'info_dict': {
-                'id': '4160e53b-ad41-43b1-980f-8d85f63121f4',
+                'id': 'bcd1b1df-673a-42cf-8d01-b282db608f2d',
                 'display_id': 'justice-for-ferguson-a-community-reacts',
                 'ext': 'flv',
                 'title': 'Justice for Ferguson: A Community Reacts',
@@ -55,7 +55,6 @@ class BetIE(InfoExtractor):
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-
         webpage = self._download_webpage(url, display_id)
 
         media_url = compat_urllib_parse.unquote(self._search_regex(

youtube_dl/extractor/bilibili.py

@@ -4,9 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_parse_qs
 from ..utils import (
-    ExtractorError,
     int_or_none,
     unified_strdate,
 )
@@ -54,45 +52,38 @@ class BiliBiliIE(InfoExtractor):
         thumbnail = self._html_search_meta(
             'thumbnailUrl', video_code, 'thumbnail', fatal=False)
 
-        player_params = compat_parse_qs(self._html_search_regex(
-            r'<iframe .*?class="player" src="https://secure\.bilibili\.(?:tv|com)/secure,([^"]+)"',
-            webpage, 'player params'))
+        cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
 
-        if 'cid' in player_params:
-            cid = player_params['cid'][0]
+        lq_doc = self._download_xml(
+            'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
+            video_id,
+            note='Downloading LQ video info'
+        )
+        lq_durl = lq_doc.find('./durl')
+        formats = [{
+            'format_id': 'lq',
+            'quality': 1,
+            'url': lq_durl.find('./url').text,
+            'filesize': int_or_none(
+                lq_durl.find('./size'), get_attr='text'),
+        }]
 
-            lq_doc = self._download_xml(
-                'http://interface.bilibili.cn/v_cdn_play?cid=%s' % cid,
-                video_id,
-                note='Downloading LQ video info'
-            )
-            lq_durl = lq_doc.find('.//durl')
-            formats = [{
-                'format_id': 'lq',
-                'quality': 1,
-                'url': lq_durl.find('./url').text,
+        hq_doc = self._download_xml(
+            'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
+            video_id,
+            note='Downloading HQ video info',
+            fatal=False,
+        )
+        if hq_doc is not False:
+            hq_durl = hq_doc.find('./durl')
+            formats.append({
+                'format_id': 'hq',
+                'quality': 2,
+                'ext': 'flv',
+                'url': hq_durl.find('./url').text,
                 'filesize': int_or_none(
-                    lq_durl.find('./size'), get_attr='text'),
-            }]
-
-            hq_doc = self._download_xml(
-                'http://interface.bilibili.cn/playurl?cid=%s' % cid,
-                video_id,
-                note='Downloading HQ video info',
-                fatal=False,
-            )
-            if hq_doc is not False:
-                hq_durl = hq_doc.find('.//durl')
-                formats.append({
-                    'format_id': 'hq',
-                    'quality': 2,
-                    'ext': 'flv',
-                    'url': hq_durl.find('./url').text,
-                    'filesize': int_or_none(
-                        hq_durl.find('./size'), get_attr='text'),
-                })
-        else:
-            raise ExtractorError('Unsupported player parameters: %r' % (player_params,))
+                    hq_durl.find('./size'), get_attr='text'),
+            })
 
         self._sort_formats(formats)
         return {

youtube_dl/extractor/brightcove.py

@@ -25,7 +25,7 @@ from ..utils import (
 
 
 class BrightcoveIE(InfoExtractor):
-    _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*?\?(?P<query>.*)'
+    _VALID_URL = r'(?:https?://.*brightcove\.com/(services|viewer).*?\?|brightcove:)(?P<query>.*)'
     _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
 
     _TESTS = [

youtube_dl/extractor/buzzfeed.py

@@ -33,7 +33,7 @@ class BuzzFeedIE(InfoExtractor):
             'skip_download': True,  # Got enough YouTube download tests
         },
         'info_dict': {
-            'description': 'Munchkin the Teddy Bear is back !',
+            'description': 're:Munchkin the Teddy Bear is back ?!',
             'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill',
         },
         'playlist': [{
@@ -42,9 +42,9 @@ class BuzzFeedIE(InfoExtractor):
                 'ext': 'mp4',
                 'upload_date': '20141124',
                 'uploader_id': 'CindysMunchkin',
-                'description': '© 2014 Munchkin the Shih Tzu\nAll rights reserved\nFacebook: http://facebook.com/MunchkintheShihTzu',
+                'description': 're:© 2014 Munchkin the Shih Tzu',
                 'uploader': 'Munchkin the Shih Tzu',
-                'title': 'Munchkin the Teddy Bear gets her exercise',
+                'title': 're:Munchkin the Teddy Bear gets her exercise',
             },
         }]
     }]

youtube_dl/extractor/canalplus.py

@@ -5,6 +5,8 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
+    HEADRequest,
     unified_strdate,
     url_basename,
     qualities,
@@ -76,6 +78,16 @@ class CanalplusIE(InfoExtractor):
 
         preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
 
+        fmt_url = next(iter(media.find('VIDEOS'))).text
+        if '/geo' in fmt_url.lower():
+            response = self._request_webpage(
+                HEADRequest(fmt_url), video_id,
+                'Checking if the video is georestricted')
+            if '/blocage' in response.geturl():
+                raise ExtractorError(
+                    'The video is not available in your country',
+                    expected=True)
+
         formats = []
         for fmt in media.find('VIDEOS'):
             format_url = fmt.text

youtube_dl/extractor/ceskatelevize.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
 from ..compat import (
     compat_urllib_request,
     compat_urllib_parse,
@@ -11,49 +11,42 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    float_or_none,
 )
 
 
-class CeskaTelevizeIE(InfoExtractor):
+class CeskaTelevizeIE(SubtitlesInfoExtractor):
     _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
 
     _TESTS = [
         {
-            'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka',
+            'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
             'info_dict': {
-                'id': '213512120230004',
-                'ext': 'flv',
-                'title': 'První republika: Španělská chřipka',
-                'duration': 3107.4,
+                'id': '214411058091220',
+                'ext': 'mp4',
+                'title': 'Hyde Park Civilizace',
+                'description': 'Věda a současná civilizace. Interaktivní pořad - prostor pro vaše otázky a komentáře',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'duration': 3350,
             },
             'params': {
-                'skip_download': True,  # requires rtmpdump
+                # m3u8 download
+                'skip_download': True,
             },
-            'skip': 'Works only from Czech Republic.',
-        },
-        {
-            'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt',
-            'info_dict': {
-                'id': '20138143440',
-                'ext': 'flv',
-                'title': 'Tsatsiki, maminka a policajt',
-                'duration': 6754.1,
-            },
-            'params': {
-                'skip_download': True,  # requires rtmpdump
-            },
-            'skip': 'Works only from Czech Republic.',
         },
         {
             'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
             'info_dict': {
                 'id': '14716',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'První republika: Zpěvačka z Dupárny Bobina',
-                'duration': 90,
+                'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'duration': 88.4,
             },
             'params': {
-                'skip_download': True,  # requires rtmpdump
+                # m3u8 download
+                'skip_download': True,
             },
         },
     ]
@@ -80,8 +73,9 @@ class CeskaTelevizeIE(InfoExtractor):
             'requestSource': 'iVysilani',
         }
 
-        req = compat_urllib_request.Request('http://www.ceskatelevize.cz/ivysilani/ajax/get-playlist-url',
-                                            data=compat_urllib_parse.urlencode(data))
+        req = compat_urllib_request.Request(
+            'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
+            data=compat_urllib_parse.urlencode(data))
 
         req.add_header('Content-type', 'application/x-www-form-urlencoded')
         req.add_header('x-addr', '127.0.0.1')
@@ -90,39 +84,72 @@ class CeskaTelevizeIE(InfoExtractor):
 
         playlistpage = self._download_json(req, video_id)
 
-        req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlistpage['url']))
+        playlist_url = playlistpage['url']
+        if playlist_url == 'error_region':
+            raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
+
+        req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlist_url))
         req.add_header('Referer', url)
 
-        playlist = self._download_xml(req, video_id)
+        playlist = self._download_json(req, video_id)
 
+        item = playlist['playlist'][0]
         formats = []
-        for i in playlist.find('smilRoot/body'):
-            if 'AD' not in i.attrib['id']:
-                base_url = i.attrib['base']
-                parsedurl = compat_urllib_parse_urlparse(base_url)
-                duration = i.attrib['duration']
-
-                for video in i.findall('video'):
-                    if video.attrib['label'] != 'AD':
-                        format_id = video.attrib['label']
-                        play_path = video.attrib['src']
-                        vbr = int(video.attrib['system-bitrate'])
-
-                        formats.append({
-                            'format_id': format_id,
-                            'url': base_url,
-                            'vbr': vbr,
-                            'play_path': play_path,
-                            'app': parsedurl.path[1:] + '?' + parsedurl.query,
-                            'rtmp_live': True,
-                            'ext': 'flv',
-                        })
-
+        for format_id, stream_url in item['streamUrls'].items():
+            formats.extend(self._extract_m3u8_formats(stream_url, video_id, 'mp4'))
         self._sort_formats(formats)
 
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        duration = float_or_none(item.get('duration'))
+        thumbnail = item.get('previewImageUrl')
+
+        subtitles = {}
+        subs = item.get('subtitles')
+        if subs:
+            subtitles['cs'] = subs[0]['url']
+
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
+
+        subtitles = self._fix_subtitles(self.extract_subtitles(video_id, subtitles))
+
         return {
             'id': episode_id,
-            'title': self._html_search_regex(r'<title>(.+?) — iVysílání — Česká televize</title>', webpage, 'title'),
-            'duration': float(duration),
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
             'formats': formats,
+            'subtitles': subtitles,
         }
+
+    @staticmethod
+    def _fix_subtitles(subtitles):
+        """ Convert millisecond-based subtitles to SRT """
+        if subtitles is None:
+            return subtitles  # subtitles not requested
+
+        def _msectotimecode(msec):
+            """ Helper utility to convert milliseconds to timecode """
+            components = []
+            for divider in [1000, 60, 60, 100]:
+                components.append(msec % divider)
+                msec //= divider
+            return "{3:02}:{2:02}:{1:02},{0:03}".format(*components)
+
+        def _fix_subtitle(subtitle):
+            for line in subtitle.splitlines():
+                m = re.match(r"^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$", line)
+                if m:
+                    yield m.group(1)
+                    start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:])
+                    yield "{0} --> {1}".format(start, stop)
+                else:
+                    yield line
+
+        fixed_subtitles = {}
+        for k, v in subtitles.items():
+            fixed_subtitles[k] = "\r\n".join(_fix_subtitle(v))
+        return fixed_subtitles

youtube_dl/extractor/cnn.py

@@ -11,14 +11,14 @@ from ..utils import (
 
 
 class CNNIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/
-        (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn(-ap)?|(?=&)))'''
+    _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/
+        (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:cnn|hln)(?:-ap)?|(?=&)))'''
 
     _TESTS = [{
         'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
         'md5': '3e6121ea48df7e2259fe73a0628605c4',
         'info_dict': {
-            'id': 'sports_2013_06_09_nadal-1-on-1.cnn',
+            'id': 'sports/2013/06/09/nadal-1-on-1.cnn',
             'ext': 'mp4',
             'title': 'Nadal wins 8th French Open title',
             'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
@@ -35,13 +35,23 @@ class CNNIE(InfoExtractor):
             "description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
             "upload_date": "20130821",
         }
+    }, {
+        'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html',
+        'md5': 'f14d02ebd264df951feb2400e2c25a1b',
+        'info_dict': {
+            'id': 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln',
+            'ext': 'mp4',
+            'title': 'Nashville Ep. 1: Hand crafted skateboards',
+            'description': 'md5:e7223a503315c9f150acac52e76de086',
+            'upload_date': '20141222',
+        }
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         path = mobj.group('path')
         page_title = mobj.group('title')
-        info_url = 'http://cnn.com/video/data/3.0/%s/index.xml' % path
+        info_url = 'http://edition.cnn.com/video/data/3.0/%s/index.xml' % path
         info = self._download_xml(info_url, page_title)
 
         formats = []
@@ -127,3 +137,28 @@ class CNNBlogsIE(InfoExtractor):
             'url': cnn_url,
             'ie_key': CNNIE.ie_key(),
         }
+
+
+class CNNArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!video/)'
+    _TEST = {
+        'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
+        'md5': '689034c2a3d9c6dc4aa72d65a81efd01',
+        'info_dict': {
+            'id': 'bestoftv/2014/12/21/ip-north-korea-obama.cnn',
+            'ext': 'mp4',
+            'title': 'Obama: Cyberattack not an act of war',
+            'description': 'md5:51ce6750450603795cad0cdfbd7d05c5',
+            'upload_date': '20141221',
+        },
+        'add_ie': ['CNN'],
+    }
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, url_basename(url))
+        cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url')
+        return {
+            '_type': 'url',
+            'url': 'http://cnn.com/video/?/video/' + cnn_url,
+            'ie_key': CNNIE.ie_key(),
+        }

youtube_dl/extractor/collegerama.py

@@ -0,0 +1,92 @@
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_request
+from ..utils import (
+    float_or_none,
+    int_or_none,
+)
+
+
+class CollegeRamaIE(InfoExtractor):
+    _VALID_URL = r'https?://collegerama\.tudelft\.nl/Mediasite/Play/(?P<id>[\da-f]+)'
+    _TESTS = [
+        {
+            'url': 'https://collegerama.tudelft.nl/Mediasite/Play/585a43626e544bdd97aeb71a0ec907a01d',
+            'md5': '481fda1c11f67588c0d9d8fbdced4e39',
+            'info_dict': {
+                'id': '585a43626e544bdd97aeb71a0ec907a01d',
+                'ext': 'mp4',
+                'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.',
+                'description': '',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 7713.088,
+                'timestamp': 1413309600,
+                'upload_date': '20141014',
+            },
+        },
+        {
+            'url': 'https://collegerama.tudelft.nl/Mediasite/Play/86a9ea9f53e149079fbdb4202b521ed21d?catalog=fd32fd35-6c99-466c-89d4-cd3c431bc8a4',
+            'md5': 'ef1fdded95bdf19b12c5999949419c92',
+            'info_dict': {
+                'id': '86a9ea9f53e149079fbdb4202b521ed21d',
+                'ext': 'wmv',
+                'title': '64ste Vakantiecursus: Afvalwater',
+                'description': 'md5:7fd774865cc69d972f542b157c328305',
+                'duration': 10853,
+                'timestamp': 1326446400,
+                'upload_date': '20120113',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        player_options_request = {
+            "getPlayerOptionsRequest": {
+                "ResourceId": video_id,
+                "QueryString": "",
+            }
+        }
+
+        request = compat_urllib_request.Request(
+            'http://collegerama.tudelft.nl/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions',
+            json.dumps(player_options_request))
+        request.add_header('Content-Type', 'application/json')
+
+        player_options = self._download_json(request, video_id)
+
+        presentation = player_options['d']['Presentation']
+        title = presentation['Title']
+        description = presentation.get('Description')
+        thumbnail = None
+        duration = float_or_none(presentation.get('Duration'), 1000)
+        timestamp = int_or_none(presentation.get('UnixTime'), 1000)
+
+        formats = []
+        for stream in presentation['Streams']:
+            for video in stream['VideoUrls']:
+                thumbnail_url = stream.get('ThumbnailUrl')
+                if thumbnail_url:
+                    thumbnail = 'http://collegerama.tudelft.nl' + thumbnail_url
+                format_id = video['MediaType']
+                if format_id == 'SS':
+                    continue
+                formats.append({
+                    'url': video['Location'],
+                    'format_id': format_id,
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+        }

youtube_dl/extractor/comedycentral.py

@@ -34,12 +34,12 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
 
 class ComedyCentralShowsIE(MTVServicesInfoExtractor):
     IE_DESC = 'The Daily Show / The Colbert Report'
-    # urls can be abbreviations like :thedailyshow or :colbert
+    # urls can be abbreviations like :thedailyshow
     # urls for episodes like:
     # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
     #                     or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
     #                     or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
-    _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
+    _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow)
                       |https?://(:www\.)?
                           (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
                          ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
@@ -50,7 +50,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
                           )|
                           (?P<interview>
                               extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
-                     (?:[?#].*|$)'''
+                     '''
     _TESTS = [{
         'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
         'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
@@ -83,6 +83,9 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
     }, {
         'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
         'only_matching': True,
+    }, {
+        'url': 'http://thedailyshow.cc.com/video-playlists/t6d9sg/the-daily-show-20038-highlights/be3cwo',
+        'only_matching': True,
     }, {
         'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
         'only_matching': True,

youtube_dl/extractor/common.py

@@ -21,6 +21,7 @@ from ..compat import (
     compat_str,
 )
 from ..utils import (
+    age_restricted,
     clean_html,
     compiled_regex_type,
     ExtractorError,
@@ -40,7 +41,7 @@ class InfoExtractor(object):
     information about the video (or videos) the URL refers to. This
     information includes the real video URL, the video title, author and
     others. The information is stored in a dictionary which is then
-    passed to the FileDownloader. The FileDownloader processes this
+    passed to the YoutubeDL. The YoutubeDL processes this
     information possibly downloading the video to the file system, among
     other possible outcomes.
 
@@ -92,6 +93,8 @@ class InfoExtractor(object):
                                  by this field, regardless of all other values.
                                  -1 for default (order by other properties),
                                  -2 or smaller for less than default.
+                                 < -1000 to hide the format (if there is
+                                    another one which is strictly better)
                     * language_preference  Is this in the correct requested
                                  language?
                                  10 if it's what the URL is about,
@@ -111,6 +114,9 @@ class InfoExtractor(object):
                                  to add to the request.
                     * http_post_data  Additional data to send with a POST
                                  request.
+                    * stretched_ratio  If given and not 1, indicates that the
+                                       video's pixels are not square.
+                                       width : height ratio as float.
     url:            Final video URL.
     ext:            Video filename extension.
     format:         The video format, defaults to ext (used for --get-format)
@@ -144,6 +150,17 @@ class InfoExtractor(object):
     like_count:     Number of positive ratings of the video
     dislike_count:  Number of negative ratings of the video
     comment_count:  Number of comments on the video
+    comments:       A list of comments, each with one or more of the following
+                    properties (all but one of text or html optional):
+                        * "author" - human-readable name of the comment author
+                        * "author_id" - user ID of the comment author
+                        * "id" - Comment ID
+                        * "html" - Comment as HTML
+                        * "text" - Plain text of the comment
+                        * "timestamp" - UNIX timestamp of comment
+                        * "parent" - ID of the comment this one is replying to.
+                                     Set to "root" to indicate that this is a
+                                     comment to the original video.
     age_limit:      Age restriction for the video, as an integer (years)
     webpage_url:    The url to the video webpage, if given to youtube-dl it
                     should allow to get the same result again. (It will be set
@@ -362,9 +379,19 @@ class InfoExtractor(object):
 
         return content
 
-    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
+    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5):
         """ Returns the data of the page as a string """
-        res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
+        success = False
+        try_count = 0
+        while success is False:
+            try:
+                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
+                success = True
+            except compat_http_client.IncompleteRead as e:
+                try_count += 1
+                if try_count >= tries:
+                    raise e
+                self._sleep(timeout, video_id)
         if res is False:
             return res
         else:
@@ -589,9 +616,9 @@ class InfoExtractor(object):
         if display_name is None:
             display_name = name
         return self._html_search_regex(
-            r'''(?ix)<meta
+            r'''(?isx)<meta
                     (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
-                    [^>]+content=(["\'])(?P<content>.*?)\1''' % re.escape(name),
+                    [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name),
             html, display_name, fatal=fatal, group='content', **kwargs)
 
     def _dc_search_uploader(self, html):
@@ -715,8 +742,14 @@ class InfoExtractor(object):
             'Unable to download f4m manifest')
 
         formats = []
+        manifest_version = '1.0'
         media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
+        if not media_nodes:
+            manifest_version = '2.0'
+            media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
         for i, media_el in enumerate(media_nodes):
+            if manifest_version == '2.0':
+                manifest_url = '/'.join(manifest_url.split('/')[:-1]) + '/' + media_el.attrib.get('href')
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             format_id = 'f4m-%d' % (i if tbr is None else tbr)
             formats.append({
@@ -875,6 +908,35 @@ class InfoExtractor(object):
             None, '/', True, False, expire_time, '', None, None, None)
         self._downloader.cookiejar.set_cookie(cookie)
 
+    def get_testcases(self, include_onlymatching=False):
+        t = getattr(self, '_TEST', None)
+        if t:
+            assert not hasattr(self, '_TESTS'), \
+                '%s has _TEST and _TESTS' % type(self).__name__
+            tests = [t]
+        else:
+            tests = getattr(self, '_TESTS', [])
+        for t in tests:
+            if not include_onlymatching and t.get('only_matching', False):
+                continue
+            t['name'] = type(self).__name__[:-len('IE')]
+            yield t
+
+    def is_suitable(self, age_limit):
+        """ Test whether the extractor is generally suitable for the given
+        age limit (i.e. pornographic sites are not, all others usually are) """
+
+        any_restricted = False
+        for tc in self.get_testcases(include_onlymatching=False):
+            if 'playlist' in tc:
+                tc = tc['playlist'][0]
+            is_restricted = age_restricted(
+                tc.get('info_dict', {}).get('age_limit'), age_limit)
+            if not is_restricted:
+                return True
+            any_restricted = any_restricted or is_restricted
+        return not any_restricted
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/commonmistakes.py

@@ -0,0 +1,29 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class CommonMistakesIE(InfoExtractor):
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'''(?x)
+        (?:url|URL)
+    '''
+
+    _TESTS = [{
+        'url': 'url',
+        'only_matching': True,
+    }, {
+        'url': 'URL',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        msg = (
+            'You\'ve asked youtube-dl to download the URL "%s". '
+            'That doesn\'t make any sense. '
+            'Simply remove the parameter in your command or configuration.'
+        ) % url
+        if self._downloader.params.get('verbose'):
+            msg += ' Add -v to the command line to see what arguments and configuration youtube-dl got.'
+        raise ExtractorError(msg, expected=True)

youtube_dl/extractor/crunchyroll.py

@@ -29,10 +29,9 @@ from .common import InfoExtractor
 
 
 class CrunchyrollIE(SubtitlesInfoExtractor):
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _TESTS = [{
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
-        #'md5': 'b1639fd6ddfaa43788c85f6d1dddd412',
         'info_dict': {
             'id': '645513',
             'ext': 'flv',
@@ -47,7 +46,10 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
             # rtmp
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
+        'only_matching': True,
+    }]
 
     _FORMAT_IDS = {
         '360': ('60', '106'),
@@ -226,7 +228,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
 
         formats = []
-        for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage):
+        for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
             stream_quality, stream_format = self._FORMAT_IDS[fmt]
             video_format = fmt + 'p'
             streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')

youtube_dl/extractor/cspan.py

@@ -27,7 +27,6 @@ class CSpanIE(InfoExtractor):
         'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
         # For whatever reason, the served video alternates between
         # two different ones
-        #'md5': 'dbb0f047376d457f2ab8b3929cbb2d0c',
         'info_dict': {
             'id': '340723',
             'ext': 'mp4',

youtube_dl/extractor/daum.py

@@ -38,7 +38,7 @@ class DaumIE(InfoExtractor):
         canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
         webpage = self._download_webpage(canonical_url, video_id)
         full_id = self._search_regex(
-            r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
+            r'src=["\']http://videofarm\.daum\.net/controller/video/viewer/Video\.html\?.*?vid=(.+?)[&"\']',
             webpage, 'full id')
         query = compat_urllib_parse.urlencode({'vid': full_id})
         info = self._download_xml(

youtube_dl/extractor/dbtv.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     float_or_none,
     int_or_none,
@@ -61,7 +62,7 @@ class DBTVIE(InfoExtractor):
         self._sort_formats(formats)
 
         return {
-            'id': video['id'],
+            'id': compat_str(video['id']),
             'display_id': display_id,
             'title': video['title'],
             'description': clean_html(video['desc']),

youtube_dl/extractor/discovery.py

@@ -1,47 +1,45 @@
 from __future__ import unicode_literals
 
-import re
-import json
-
 from .common import InfoExtractor
+from ..utils import (
+    parse_iso8601,
+    int_or_none,
+)
 
 
 class DiscoveryIE(InfoExtractor):
-    _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
+    _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?'
     _TEST = {
         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
-        'md5': 'e12614f9ee303a6ccef415cb0793eba2',
+        'md5': '3c69d77d9b0d82bfd5e5932a60f26504',
         'info_dict': {
-            'id': '614784',
-            'ext': 'mp4',
-            'title': 'MythBusters: Mission Impossible Outtakes',
+            'id': 'mission-impossible-outtakes',
+            'ext': 'flv',
+            'title': 'Mission Impossible Outtakes',
             'description': ('Watch Jamie Hyneman and Adam Savage practice being'
                             ' each other -- to the point of confusing Jamie\'s dog -- and '
                             'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
                             ' back.'),
             'duration': 156,
+            'timestamp': 1303099200,
+            'upload_date': '20110418',
         },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        video_list_json = self._search_regex(r'var videoListJSON = ({.*?});',
-                                             webpage, 'video list', flags=re.DOTALL)
-        video_list = json.loads(video_list_json)
-        info = video_list['clips'][0]
-        formats = []
-        for f in info['mp4']:
-            formats.append(
-                {'url': f['src'], 'ext': 'mp4', 'tbr': int(f['bitrate'][:-1])})
+        info = self._parse_json(self._search_regex(
+            r'(?s)<script type="application/ld\+json">(.*?)</script>',
+            webpage, 'video info'), video_id)
 
         return {
-            'id': info['contentId'],
-            'title': video_list['name'],
-            'formats': formats,
-            'description': info['videoCaption'],
-            'thumbnail': info.get('videoStillURL') or info.get('thumbnailURL'),
-            'duration': info['duration'],
+            'id': video_id,
+            'title': info['name'],
+            'url': info['contentURL'],
+            'description': info.get('description'),
+            'thumbnail': info.get('thumbnailUrl'),
+            'timestamp': parse_iso8601(info.get('uploadDate')),
+            'duration': int_or_none(info.get('duration')),
         }

youtube_dl/extractor/drbonanza.py

@@ -0,0 +1,131 @@
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class DRBonanzaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/(?:[^/]+/)+(?:[^/])+?(?:assetId=(?P<id>\d+))?(?:[#&]|$)'
+
+    _TESTS = [{
+        'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517',
+        'md5': 'fe330252ddea607635cf2eb2c99a0af3',
+        'info_dict': {
+            'id': '65517',
+            'ext': 'mp4',
+            'title': 'Talkshowet - Leonard Cohen',
+            'description': 'md5:8f34194fb30cd8c8a30ad8b27b70c0ca',
+            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
+            'timestamp': 1295537932,
+            'upload_date': '20110120',
+            'duration': 3664,
+        },
+    }, {
+        'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410',
+        'md5': '6dfe039417e76795fb783c52da3de11d',
+        'info_dict': {
+            'id': '59410',
+            'ext': 'mp3',
+            'title': 'EM fodbold 1992 Danmark - Tyskland finale Transmission',
+            'description': 'md5:501e5a195749480552e214fbbed16c4e',
+            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
+            'timestamp': 1223274900,
+            'upload_date': '20081006',
+            'duration': 7369,
+        },
+    }]
+
+    def _real_extract(self, url):
+        url_id = self._match_id(url)
+        webpage = self._download_webpage(url, url_id)
+
+        if url_id:
+            info = json.loads(self._html_search_regex(r'({.*?%s.*})' % url_id, webpage, 'json'))
+        else:
+            # Just fetch the first video on that page
+            info = json.loads(self._html_search_regex(r'bonanzaFunctions.newPlaylist\(({.*})\)', webpage, 'json'))
+
+        asset_id = str(info['AssetId'])
+        title = info['Title'].rstrip(' \'\"-,.:;!?')
+        duration = int_or_none(info.get('Duration'), scale=1000)
+        # First published online. "FirstPublished" contains the date for original airing.
+        timestamp = parse_iso8601(
+            re.sub(r'\.\d+$', '', info['Created']))
+
+        def parse_filename_info(url):
+            match = re.search(r'/\d+_(?P<width>\d+)x(?P<height>\d+)x(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
+            if match:
+                return {
+                    'width': int(match.group('width')),
+                    'height': int(match.group('height')),
+                    'vbr': int(match.group('bitrate')),
+                    'ext': match.group('ext')
+                }
+            match = re.search(r'/\d+_(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
+            if match:
+                return {
+                    'vbr': int(match.group('bitrate')),
+                    'ext': match.group(2)
+                }
+            return {}
+
+        video_types = ['VideoHigh', 'VideoMid', 'VideoLow']
+        preferencemap = {
+            'VideoHigh': -1,
+            'VideoMid': -2,
+            'VideoLow': -3,
+            'Audio': -4,
+        }
+
+        formats = []
+        for file in info['Files']:
+            if info['Type'] == "Video":
+                if file['Type'] in video_types:
+                    format = parse_filename_info(file['Location'])
+                    format.update({
+                        'url': file['Location'],
+                        'format_id': file['Type'].replace('Video', ''),
+                        'preference': preferencemap.get(file['Type'], -10),
+                    })
+                    formats.append(format)
+                elif file['Type'] == "Thumb":
+                    thumbnail = file['Location']
+            elif info['Type'] == "Audio":
+                if file['Type'] == "Audio":
+                    format = parse_filename_info(file['Location'])
+                    format.update({
+                        'url': file['Location'],
+                        'format_id': file['Type'],
+                        'vcodec': 'none',
+                    })
+                    formats.append(format)
+                elif file['Type'] == "Thumb":
+                    thumbnail = file['Location']
+
+        description = '%s\n%s\n%s\n' % (
+            info['Description'], info['Actors'], info['Colophon'])
+
+        for f in formats:
+            f['url'] = f['url'].replace('rtmp://vod-bonanza.gss.dr.dk/bonanza/', 'http://vodfiles.dr.dk/')
+            f['url'] = f['url'].replace('mp4:bonanza', 'bonanza')
+        self._sort_formats(formats)
+
+        display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id
+        display_id = re.sub(r'-+', '-', display_id)
+
+        return {
+            'id': asset_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+        }

youtube_dl/extractor/drtv.py

@@ -6,7 +6,7 @@ from ..utils import parse_iso8601
 
 
 class DRTVIE(SubtitlesInfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)+(?P<id>[\da-z-]+)(?:[/#?]|$)'
+    _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)+(?P<id>[\da-z-]+)(?:[/#?]|$)'
 
     _TEST = {
         'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8',

youtube_dl/extractor/dvtv.py

@@ -0,0 +1,125 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    unescapeHTML,
+    ExtractorError,
+)
+
+
+class DVTVIE(InfoExtractor):
+    IE_NAME = 'dvtv'
+    IE_DESC = 'http://video.aktualne.cz/'
+
+    _VALID_URL = r'http://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})'
+
+    _TESTS = [{
+        'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/',
+        'md5': '67cb83e4a955d36e1b5d31993134a0c2',
+        'info_dict': {
+            'id': 'dc0768de855511e49e4b0025900fea04',
+            'ext': 'mp4',
+            'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně',
+        }
+    }, {
+        'url': 'http://video.aktualne.cz/dvtv/stropnicky-policie-vrbetice-preventivne-nekontrolovala/r~82ed4322849211e4a10c0025900fea04/',
+        'md5': '6388f1941b48537dbd28791f712af8bf',
+        'info_dict': {
+            'id': '72c02230849211e49f60002590604f2e',
+            'ext': 'mp4',
+            'title': 'Stropnický: Policie Vrbětice preventivně nekontrolovala',
+        }
+    }, {
+        'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/',
+        'info_dict': {
+            'title': 'DVTV 16. 12. 2014: útok Talibanu, boj o kliniku, uprchlíci',
+            'id': '973eb3bc854e11e498be002590604f2e',
+        },
+        'playlist': [{
+            'md5': 'da7ca6be4935532241fa9520b3ad91e4',
+            'info_dict': {
+                'id': 'b0b40906854d11e4bdad0025900fea04',
+                'ext': 'mp4',
+                'title': 'Drtinová Veselovský TV 16. 12. 2014: Témata dne'
+            }
+        }, {
+            'md5': '5f7652a08b05009c1292317b449ffea2',
+            'info_dict': {
+                'id': '420ad9ec854a11e4bdad0025900fea04',
+                'ext': 'mp4',
+                'title': 'Školní masakr možná změní boj s Talibanem, říká novinářka'
+            }
+        }, {
+            'md5': '498eb9dfa97169f409126c617e2a3d64',
+            'info_dict': {
+                'id': '95d35580846a11e4b6d20025900fea04',
+                'ext': 'mp4',
+                'title': 'Boj o kliniku: Veřejný zájem, nebo právo na majetek?'
+            }
+        }, {
+            'md5': 'b8dc6b744844032dab6ba3781a7274b9',
+            'info_dict': {
+                'id': '6fe14d66853511e4833a0025900fea04',
+                'ext': 'mp4',
+                'title': 'Pánek: Odmítání syrských uprchlíků je ostudou české vlády'
+            }
+        }],
+    }, {
+        'url': 'http://video.aktualne.cz/v-cechach-poprve-zazni-zelenkova-zrestaurovana-mse/r~45b4b00483ec11e4883b002590604f2e/',
+        'only_matching': True,
+    }]
+
+    def _parse_video_metadata(self, js, video_id):
+        metadata = self._parse_json(js, video_id, transform_source=js_to_json)
+
+        formats = []
+        for video in metadata['sources']:
+            ext = video['type'][6:]
+            formats.append({
+                'url': video['file'],
+                'ext': ext,
+                'format_id': '%s-%s' % (ext, video['label']),
+                'height': int(video['label'].rstrip('p')),
+                'fps': 25,
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': metadata['mediaid'],
+            'title': unescapeHTML(metadata['title']),
+            'thumbnail': self._proto_relative_url(metadata['image'], 'http:'),
+            'formats': formats
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        # single video
+        item = self._search_regex(
+            r"(?s)embedData[0-9a-f]{32}\['asset'\]\s*=\s*(\{.+?\});",
+            webpage, 'video', default=None, fatal=False)
+
+        if item:
+            return self._parse_video_metadata(item, video_id)
+
+        # playlist
+        items = re.findall(
+            r"(?s)BBX\.context\.assets\['[0-9a-f]{32}'\]\.push\(({.+?})\);",
+            webpage)
+
+        if items:
+            return {
+                '_type': 'playlist',
+                'id': video_id,
+                'title': self._og_search_title(webpage),
+                'entries': [self._parse_video_metadata(i, video_id) for i in items]
+            }
+
+        raise ExtractorError('Could not find neither video nor playlist')

youtube_dl/extractor/echomsk.py

@@ -0,0 +1,46 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class EchoMskIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?echo\.msk\.ru/sounds/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.echo.msk.ru/sounds/1464134.html',
+        'md5': '2e44b3b78daff5b458e4dbc37f191f7c',
+        'info_dict': {
+            'id': '1464134',
+            'ext': 'mp3',
+            'title': 'Особое мнение - 29 декабря 2014, 19:08',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        audio_url = self._search_regex(
+            r'<a rel="mp3" href="([^"]+)">', webpage, 'audio URL')
+
+        title = self._html_search_regex(
+            r'<a href="/programs/[^"]+" target="_blank">([^<]+)</a>',
+            webpage, 'title')
+
+        air_date = self._html_search_regex(
+            r'(?s)<div class="date">(.+?)</div>',
+            webpage, 'date', fatal=False, default=None)
+
+        if air_date:
+            air_date = re.sub(r'(\s)\1+', r'\1', air_date)
+            if air_date:
+                title = '%s - %s' % (title, air_date)
+
+        return {
+            'id': video_id,
+            'url': audio_url,
+            'title': title,
+        }

youtube_dl/extractor/eighttracks.py

@@ -9,6 +9,9 @@ from .common import InfoExtractor
 from ..compat import (
     compat_str,
 )
+from ..utils import (
+    ExtractorError,
+)
 
 
 class EightTracksIE(InfoExtractor):
@@ -112,14 +115,29 @@ class EightTracksIE(InfoExtractor):
         session = str(random.randint(0, 1000000000))
         mix_id = data['id']
         track_count = data['tracks_count']
+        duration = data['duration']
+        avg_song_duration = float(duration) / track_count
         first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
         next_url = first_url
         entries = []
+
         for i in range(track_count):
-            api_json = self._download_webpage(
-                next_url, playlist_id,
-                note='Downloading song information %d/%d' % (i + 1, track_count),
-                errnote='Failed to download song information')
+            api_json = None
+            download_tries = 0
+
+            while api_json is None:
+                try:
+                    api_json = self._download_webpage(
+                        next_url, playlist_id,
+                        note='Downloading song information %d/%d' % (i + 1, track_count),
+                        errnote='Failed to download song information')
+                except ExtractorError:
+                    if download_tries > 3:
+                        raise
+                    else:
+                        download_tries += 1
+                        self._sleep(avg_song_duration, playlist_id)
+
             api_data = json.loads(api_json)
             track_data = api_data['set']['track']
             info = {
@@ -131,6 +149,7 @@ class EightTracksIE(InfoExtractor):
                 'ext': 'm4a',
             }
             entries.append(info)
+
             next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (
                 session, mix_id, track_data['id'])
         return {

youtube_dl/extractor/ellentv.py

@@ -1,7 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
 import json
 
 from .common import InfoExtractor
@@ -12,32 +11,49 @@ from ..utils import (
 
 
 class EllenTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
+    _TESTS = [{
         'url': 'http://www.ellentv.com/videos/0-7jqrsr18/',
         'md5': 'e4af06f3bf0d5f471921a18db5764642',
         'info_dict': {
             'id': '0-7jqrsr18',
             'ext': 'mp4',
             'title': 'What\'s Wrong with These Photos? A Whole Lot',
+            'description': 'md5:35f152dc66b587cf13e6d2cf4fa467f6',
             'timestamp': 1406876400,
             'upload_date': '20140801',
         }
-    }
+    }, {
+        'url': 'http://ellentube.com/videos/0-dvzmabd5/',
+        'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb',
+        'info_dict': {
+            'id': '0-dvzmabd5',
+            'ext': 'mp4',
+            'title': '1 year old twin sister makes her brother laugh',
+            'description': '1 year old twin sister makes her brother laugh',
+            'timestamp': 1419542075,
+            'upload_date': '20141225',
+        }
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
+        video_url = self._html_search_meta('VideoURL', webpage, 'url')
+        title = self._og_search_title(webpage, default=None) or self._search_regex(
+            r'pageName\s*=\s*"([^"]+)"', webpage, 'title')
+        description = self._html_search_meta(
+            'description', webpage, 'description') or self._og_search_description(webpage)
         timestamp = parse_iso8601(self._search_regex(
             r'<span class="publish-date"><time datetime="([^"]+)">',
             webpage, 'timestamp'))
 
         return {
             'id': video_id,
-            'title': self._og_search_title(webpage),
-            'url': self._html_search_meta('VideoURL', webpage, 'url'),
+            'url': video_url,
+            'title': title,
+            'description': description,
             'timestamp': timestamp,
         }
 
@@ -55,8 +71,7 @@ class EllenTVClipsIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        playlist_id = mobj.group('id')
+        playlist_id = self._match_id(url)
 
         webpage = self._download_webpage(url, playlist_id)
         playlist = self._extract_playlist(webpage)

youtube_dl/extractor/elpais.py

@@ -1,8 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import unified_strdate
 
@@ -24,9 +22,7 @@ class ElPaisIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         prefix = self._html_search_regex(

youtube_dl/extractor/eroprofile.py

@@ -0,0 +1,45 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class EroProfileIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
+        'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
+        'info_dict': {
+            'id': '3733775',
+            'display_id': 'sexy-babe-softcore',
+            'ext': 'm4v',
+            'title': 'sexy babe softcore',
+            'thumbnail': 're:https?://.*\.jpg',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
+            webpage, 'video id', default=None)
+
+        video_url = self._search_regex(
+            r'<source src="([^"]+)', webpage, 'video url')
+        title = self._html_search_regex(
+            r'Title:</th><td>([^<]+)</td>', webpage, 'title')
+        thumbnail = self._search_regex(
+            r'onclick="showVideoPlayer\(\)"><img src="([^"]+)',
+            webpage, 'thumbnail', fatal=False)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'age_limit': 18,
+        }

youtube_dl/extractor/fktv.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 class FKTVIE(InfoExtractor):
     IE_NAME = 'fernsehkritik.tv'
-    _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
+    _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
 
     _TEST = {
         'url': 'http://fernsehkritik.tv/folge-1',
@@ -26,29 +26,32 @@ class FKTVIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        episode = int(mobj.group('ep'))
+        episode = int(self._match_id(url))
 
-        server = random.randint(2, 4)
-        video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%d.jpg' % episode
-        start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%d/Start' % episode,
+        video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%s.jpg' % episode
+        start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/Start' % episode,
                                                episode)
         playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage,
                                       'playlist', flags=re.DOTALL)
         files = json.loads(re.sub('{[^{}]*?}', '{}', playlist))
-        # TODO: return a single multipart video
+
         videos = []
         for i, _ in enumerate(files, 1):
             video_id = '%04d%d' % (episode, i)
-            video_url = 'http://dl%d.fernsehkritik.tv/fernsehkritik%d%s.flv' % (server, episode, '' if i == 1 else '-%d' % i)
+            video_url = 'http://fernsehkritik.tv/js/directme.php?file=%s%s.flv' % (episode, '' if i == 1 else '-%d' % i)
             videos.append({
+                'ext': 'flv',
                 'id': video_id,
                 'url': video_url,
                 'title': clean_html(get_element_by_id('eptitle', start_webpage)),
                 'description': clean_html(get_element_by_id('contentlist', start_webpage)),
                 'thumbnail': video_thumbnail
             })
-        return videos
+        return {
+            '_type': 'multi_video',
+            'entries': videos,
+            'id': 'folge-%s' % episode,
+        }
 
 
 class FKTVPosteckeIE(InfoExtractor):

youtube_dl/extractor/fourtube.py

@@ -7,10 +7,9 @@ from ..compat import (
     compat_urllib_request,
 )
 from ..utils import (
-    clean_html,
     parse_duration,
+    parse_iso8601,
     str_to_int,
-    unified_strdate,
 )
 
 
@@ -28,68 +27,81 @@ class FourTubeIE(InfoExtractor):
             'uploader': 'WCP Club',
             'uploader_id': 'wcp-club',
             'upload_date': '20131031',
+            'timestamp': 1383263892,
             'duration': 583,
+            'view_count': int,
+            'like_count': int,
+            'categories': list,
         }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage_url = 'http://www.4tube.com/videos/' + video_id
-        webpage = self._download_webpage(webpage_url, video_id)
+        webpage = self._download_webpage(url, video_id)
 
-        self.report_extraction(video_id)
+        title = self._html_search_meta('name', webpage)
+        timestamp = parse_iso8601(self._html_search_meta(
+            'uploadDate', webpage))
+        thumbnail = self._html_search_meta('thumbnailUrl', webpage)
+        uploader_id = self._html_search_regex(
+            r'<a class="img-avatar" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',
+            webpage, 'uploader id')
+        uploader = self._html_search_regex(
+            r'<a class="img-avatar" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',
+            webpage, 'uploader')
 
-        playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, 'Playlist')
-        media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, 'Media Id')
-        sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, 'Sources').split(',')
-        title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, 'Title')
-        thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, 'Thumbnail', fatal=False)
+        categories_html = self._search_regex(
+            r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="list">(.*?)</ul>',
+            webpage, 'categories', fatal=False)
+        categories = None
+        if categories_html:
+            categories = [
+                c.strip() for c in re.findall(
+                    r'(?s)<li><a.*?>(.*?)</a>', categories_html)]
 
-        uploader_str = self._search_regex(r'<span>Uploaded by</span>(.*?)<span>', webpage, 'uploader', fatal=False)
-        mobj = re.search(r'<a href="/sites/(?P<id>[^"]+)"><strong>(?P<name>[^<]+)</strong></a>', uploader_str)
-        (uploader, uploader_id) = (mobj.group('name'), mobj.group('id')) if mobj else (clean_html(uploader_str), None)
+        view_count = str_to_int(self._search_regex(
+            r'<meta itemprop="interactionCount" content="UserPlays:([0-9,]+)">',
+            webpage, 'view count', fatal=False))
+        like_count = str_to_int(self._search_regex(
+            r'<meta itemprop="interactionCount" content="UserLikes:([0-9,]+)">',
+            webpage, 'like count', fatal=False))
+        duration = parse_duration(self._html_search_meta('duration', webpage))
 
-        upload_date = None
-        view_count = None
-        duration = None
-        description = self._html_search_meta('description', webpage, 'description')
-        if description:
-            upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date',
-                                             fatal=False)
-            if upload_date:
-                upload_date = unified_strdate(upload_date)
-            view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False)
-            if view_count:
-                view_count = str_to_int(view_count)
-            duration = parse_duration(self._search_regex(r'Length: (\d+m\d+s)', description, 'duration', fatal=False))
+        params_js = self._search_regex(
+            r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)',
+            webpage, 'initialization parameters'
+        )
+        params = self._parse_json('[%s]' % params_js, video_id)
+        media_id = params[0]
+        sources = ['%s' % p for p in params[2]]
 
-        token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources))
+        token_url = 'http://tkn.4tube.com/{0}/desktop/{1}'.format(
+            media_id, '+'.join(sources))
         headers = {
             b'Content-Type': b'application/x-www-form-urlencoded',
             b'Origin': b'http://www.4tube.com',
         }
         token_req = compat_urllib_request.Request(token_url, b'{}', headers)
         tokens = self._download_json(token_req, video_id)
-
         formats = [{
             'url': tokens[format]['token'],
             'format_id': format + 'p',
             'resolution': format + 'p',
             'quality': int(format),
         } for format in sources]
-
         self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': title,
             'formats': formats,
-            'thumbnail': thumbnail_url,
+            'categories': categories,
+            'thumbnail': thumbnail,
             'uploader': uploader,
             'uploader_id': uploader_id,
-            'upload_date': upload_date,
+            'timestamp': timestamp,
+            'like_count': like_count,
             'view_count': view_count,
             'duration': duration,
             'age_limit': 18,
-            'webpage_url': webpage_url,
         }

youtube_dl/extractor/gameone.py

@@ -6,7 +6,9 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     xpath_with_ns,
-    parse_iso8601
+    parse_iso8601,
+    float_or_none,
+    int_or_none,
 )
 
 NAMESPACE_MAP = {
@@ -21,25 +23,41 @@ RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/'
 
 class GameOneIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P<id>\d+)'
-    _TEST = {
-        'url': 'http://www.gameone.de/tv/288',
-        'md5': '136656b7fb4c9cb4a8e2d500651c499b',
-        'info_dict': {
-            'id': '288',
-            'ext': 'mp4',
-            'title': 'Game One - Folge 288',
-            'duration': 1238,
-            'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg',
-            'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1',
-            'age_limit': 16,
-            'upload_date': '20140513',
-            'timestamp': 1399980122,
+    _TESTS = [
+        {
+            'url': 'http://www.gameone.de/tv/288',
+            'md5': '136656b7fb4c9cb4a8e2d500651c499b',
+            'info_dict': {
+                'id': '288',
+                'ext': 'mp4',
+                'title': 'Game One - Folge 288',
+                'duration': 1238,
+                'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg',
+                'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1',
+                'age_limit': 16,
+                'upload_date': '20140513',
+                'timestamp': 1399980122,
+            }
+        },
+        {
+            'url': 'http://gameone.de/tv/220',
+            'md5': '5227ca74c4ae6b5f74c0510a7c48839e',
+            'info_dict': {
+                'id': '220',
+                'ext': 'mp4',
+                'upload_date': '20120918',
+                'description': 'Jet Set Radio HD, Tekken Tag Tournament 2, Source Filmmaker',
+                'timestamp': 1347971451,
+                'title': 'Game One - Folge 220',
+                'duration': 896.62,
+                'age_limit': 16,
+            }
         }
-    }
+
+    ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
         og_video = self._og_search_video_url(webpage, secure=False)
@@ -66,13 +84,13 @@ class GameOneIE(InfoExtractor):
             video_id,
             'Downloading media:content')
         rendition_items = content.findall('.//rendition')
-        duration = int(rendition_items[0].get('duration'))
+        duration = float_or_none(rendition_items[0].get('duration'))
         formats = [
             {
                 'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text),
-                'width': int(r.get('width')),
-                'height': int(r.get('height')),
-                'tbr': int(r.get('bitrate')),
+                'width': int_or_none(r.get('width')),
+                'height': int_or_none(r.get('height')),
+                'tbr': int_or_none(r.get('bitrate')),
             }
             for r in rendition_items
         ]
@@ -105,7 +123,8 @@ class GameOnePlaylistIE(InfoExtractor):
         webpage = self._download_webpage('http://www.gameone.de/tv', 'TV')
         max_id = max(map(int, re.findall(r'<a href="/tv/(\d+)"', webpage)))
         entries = [
-            self.url_result('http://www.gameone.de/tv/%d' % video_id, 'GameOne')
+            self.url_result('http://www.gameone.de/tv/%d' %
+                            video_id, 'GameOne')
             for video_id in range(max_id, 0, -1)]
 
         return {

youtube_dl/extractor/gamestar.py

@@ -1,8 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
@@ -29,9 +27,7 @@ class GameStarIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         og_title = self._og_search_title(webpage)

youtube_dl/extractor/gdcvault.py

@@ -39,7 +39,8 @@ class GDCVaultIE(InfoExtractor):
                 'id': '1015301',
                 'ext': 'flv',
                 'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
-            }
+            },
+            'skip': 'Requires login',
         }
     ]
 

youtube_dl/extractor/generic.py

@@ -17,12 +17,14 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     HEADRequest,
+    is_html,
     orderedSet,
     parse_xml,
     smuggle_url,
     unescapeHTML,
     unified_strdate,
     unsmuggle_url,
+    UnsupportedError,
     url_basename,
 )
 from .brightcove import BrightcoveIE
@@ -130,12 +132,13 @@ class GenericIE(InfoExtractor):
         # ooyala video
         {
             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
-            'md5': '5644c6ca5d5782c1d0d350dad9bd840c',
+            'md5': '166dd577b433b4d4ebfee10b0824d8ff',
             'info_dict': {
                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
                 'ext': 'mp4',
                 'title': '2cc213299525360.mov',  # that's what we get
             },
+            'add_ie': ['Ooyala'],
         },
         # google redirect
         {
@@ -145,7 +148,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'upload_date': '20130224',
                 'uploader_id': 'TheVerge',
-                'description': 'Chris Ziegler takes a look at the Alcatel OneTouch Fire and the ZTE Open; two of the first Firefox OS handsets to be officially announced.',
+                'description': 're:^Chris Ziegler takes a look at the\.*',
                 'uploader': 'The Verge',
                 'title': 'First Firefox OS phones side-by-side',
             },
@@ -180,6 +183,14 @@ class GenericIE(InfoExtractor):
                 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
             },
         },
+        # BBC iPlayer embeds
+        {
+            'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
+            'info_dict': {
+                'title': 'BBC - Blogs -  Adam Curtis - BUGGER',
+            },
+            'playlist_mincount': 18,
+        },
         # RUTV embed
         {
             'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
@@ -478,6 +489,16 @@ class GenericIE(InfoExtractor):
                 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
             }
         },
+        # Cinerama player
+        {
+            'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
+            'info_dict': {
+                'id': '730m_DandD_1901_512k',
+                'ext': 'mp4',
+                'uploader': 'www.abc.net.au',
+                'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
+            }
+        }
     ]
 
     def report_following_redirect(self, new_url):
@@ -637,7 +658,7 @@ class GenericIE(InfoExtractor):
         # Maybe it's a direct link to a video?
         # Be careful not to download the whole thing!
         first_bytes = full_response.read(512)
-        if not re.match(r'^\s*<', first_bytes.decode('utf-8', 'replace')):
+        if not is_html(first_bytes):
             self._downloader.report_warning(
                 'URL could be a direct video link, returning it as such.')
             upload_date = unified_strdate(
@@ -698,9 +719,9 @@ class GenericIE(InfoExtractor):
             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
 
         # Helper method
-        def _playlist_from_matches(matches, getter, ie=None):
+        def _playlist_from_matches(matches, getter=None, ie=None):
             urlrs = orderedSet(
-                self.url_result(self._proto_relative_url(getter(m)), ie)
+                self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
                 for m in matches)
             return self.playlist_result(
                 urlrs, playlist_id=video_id, playlist_title=video_title)
@@ -904,6 +925,11 @@ class GenericIE(InfoExtractor):
             return _playlist_from_matches(
                 matches, getter=unescapeHTML, ie='FunnyOrDie')
 
+        # Look for BBC iPlayer embed
+        matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
+        if matches:
+            return _playlist_from_matches(matches, ie='BBCCoUk')
+
         # Look for embedded RUTV player
         rutv_url = RUTVIE._extract_url(webpage)
         if rutv_url:
@@ -911,7 +937,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded TED player
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>http://embed\.ted\.com/.+?)\1', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'TED')
 
@@ -1030,6 +1056,10 @@ class GenericIE(InfoExtractor):
                     \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s*
                         ["']?url["']?\s*:\s*["']([^"']+)["']
             ''', webpage))
+        if not found:
+            # Cinerama player
+            found = re.findall(
+                r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
         if not found:
             # Try to find twitter cards info
             found = filter_video(re.findall(
@@ -1057,7 +1087,7 @@ class GenericIE(InfoExtractor):
                     'url': new_url,
                 }
         if not found:
-            raise ExtractorError('Unsupported URL: %s' % url)
+            raise UnsupportedError(url)
 
         entries = []
         for video_url in found:

youtube_dl/extractor/giga.py

@@ -0,0 +1,101 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import itertools
+
+from .common import InfoExtractor
+from ..utils import (
+    qualities,
+    compat_str,
+    parse_duration,
+    parse_iso8601,
+    str_to_int,
+)
+
+
+class GigaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?giga\.de/(?:[^/]+/)*(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'http://www.giga.de/filme/anime-awesome/trailer/anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss/',
+        'md5': '6bc5535e945e724640664632055a584f',
+        'info_dict': {
+            'id': '2622086',
+            'display_id': 'anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss',
+            'ext': 'mp4',
+            'title': 'Anime Awesome: Chihiros Reise ins Zauberland – Das Beste kommt zum Schluss',
+            'description': 'md5:afdf5862241aded4718a30dff6a57baf',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 578,
+            'timestamp': 1414749706,
+            'upload_date': '20141031',
+            'uploader': 'Robin Schweiger',
+            'view_count': int,
+        },
+    }, {
+        'url': 'http://www.giga.de/games/channel/giga-top-montag/giga-topmontag-die-besten-serien-2014/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.giga.de/extra/netzkultur/videos/giga-games-tom-mats-robin-werden-eigene-wege-gehen-eine-ankuendigung/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.giga.de/tv/jonas-liest-spieletitel-eingedeutscht-episode-2/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            [r'data-video-id="(\d+)"', r'/api/video/jwplayer/#v=(\d+)'],
+            webpage, 'video id')
+
+        playlist = self._download_json(
+            'http://www.giga.de/api/syndication/video/video_id/%s/playlist.json?content=syndication/key/368b5f151da4ae05ced7fa296bdff65a/'
+            % video_id, video_id)[0]
+
+        quality = qualities(['normal', 'hd720'])
+
+        formats = []
+        for format_id in itertools.count(0):
+            fmt = playlist.get(compat_str(format_id))
+            if not fmt:
+                break
+            formats.append({
+                'url': fmt['src'],
+                'format_id': '%s-%s' % (fmt['quality'], fmt['type'].split('/')[-1]),
+                'quality': quality(fmt['quality']),
+            })
+        self._sort_formats(formats)
+
+        title = self._html_search_meta(
+            'title', webpage, 'title', fatal=True)
+        description = self._html_search_meta(
+            'description', webpage, 'description')
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        duration = parse_duration(self._search_regex(
+            r'(?s)(?:data-video-id="{0}"|data-video="[^"]*/api/video/jwplayer/#v={0}[^"]*")[^>]*>.+?<span class="duration">([^<]+)</span>'.format(video_id),
+            webpage, 'duration', fatal=False))
+
+        timestamp = parse_iso8601(self._search_regex(
+            r'datetime="([^"]+)"', webpage, 'upload date', fatal=False))
+        uploader = self._search_regex(
+            r'class="author">([^<]+)</a>', webpage, 'uploader', fatal=False)
+
+        view_count = str_to_int(self._search_regex(
+            r'<span class="views"><strong>([\d.]+)</strong>', webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'view_count': view_count,
+            'formats': formats,
+        }

youtube_dl/extractor/hearthisat.py

@@ -0,0 +1,117 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_request,
+    compat_urlparse,
+)
+from ..utils import (
+    HEADRequest,
+    str_to_int,
+    urlencode_postdata,
+    urlhandle_detect_ext,
+)
+
+
+class HearThisAtIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hearthis\.at/(?P<artist>[^/]+)/(?P<title>[A-Za-z0-9\-]+)/?$'
+    _PLAYLIST_URL = 'https://hearthis.at/playlist.php'
+    _TEST = {
+        'url': 'https://hearthis.at/moofi/dr-kreep',
+        'md5': 'ab6ec33c8fed6556029337c7885eb4e0',
+        'info_dict': {
+            'id': '150939',
+            'ext': 'wav',
+            'title': 'Moofi - Dr. Kreep',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1421564134,
+            'description': 'Creepy Patch. Mutable Instruments Braids Vowel + Formant Mode.',
+            'upload_date': '20150118',
+            'comment_count': int,
+            'view_count': int,
+            'like_count': int,
+            'duration': 71,
+            'categories': ['Experimental'],
+        }
+    }
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        display_id = '{artist:s} - {title:s}'.format(**m.groupdict())
+
+        webpage = self._download_webpage(url, display_id)
+        track_id = self._search_regex(
+            r'intTrackId\s*=\s*(\d+)', webpage, 'track ID')
+
+        payload = urlencode_postdata({'tracks[]': track_id})
+        req = compat_urllib_request.Request(self._PLAYLIST_URL, payload)
+        req.add_header('Content-type', 'application/x-www-form-urlencoded')
+
+        track = self._download_json(req, track_id, 'Downloading playlist')[0]
+        title = '{artist:s} - {title:s}'.format(**track)
+
+        categories = None
+        if track.get('category'):
+            categories = [track['category']]
+
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        meta_span = r'<span[^>]+class="%s".*?</i>([^<]+)</span>'
+        view_count = str_to_int(self._search_regex(
+            meta_span % 'plays_count', webpage, 'view count', fatal=False))
+        like_count = str_to_int(self._search_regex(
+            meta_span % 'likes_count', webpage, 'like count', fatal=False))
+        comment_count = str_to_int(self._search_regex(
+            meta_span % 'comment_count', webpage, 'comment count', fatal=False))
+        duration = str_to_int(self._search_regex(
+            r'data-length="(\d+)', webpage, 'duration', fatal=False))
+        timestamp = str_to_int(self._search_regex(
+            r'<span[^>]+class="calctime"[^>]+data-time="(\d+)', webpage, 'timestamp', fatal=False))
+
+        formats = []
+        mp3_url = self._search_regex(
+            r'(?s)<a class="player-link"\s+(?:[a-zA-Z0-9_:-]+="[^"]+"\s+)*?data-mp3="([^"]+)"',
+            webpage, 'mp3 URL', fatal=False)
+        if mp3_url:
+            formats.append({
+                'format_id': 'mp3',
+                'vcodec': 'none',
+                'acodec': 'mp3',
+                'url': mp3_url,
+            })
+        download_path = self._search_regex(
+            r'<a class="[^"]*download_fct[^"]*"\s+href="([^"]+)"',
+            webpage, 'download URL', default=None)
+        if download_path:
+            download_url = compat_urlparse.urljoin(url, download_path)
+            ext_req = HEADRequest(download_url)
+            ext_handle = self._request_webpage(
+                ext_req, display_id, note='Determining extension')
+            ext = urlhandle_detect_ext(ext_handle)
+            formats.append({
+                'format_id': 'download',
+                'vcodec': 'none',
+                'ext': ext,
+                'url': download_url,
+                'preference': 2,  # Usually better quality
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': track_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'description': description,
+            'duration': duration,
+            'timestamp': timestamp,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'like_count': like_count,
+            'categories': categories,
+        }

youtube_dl/extractor/hellporno.py

@@ -0,0 +1,71 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    remove_end,
+)
+
+
+class HellPornoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
+        'md5': '1fee339c610d2049699ef2aa699439f1',
+        'info_dict': {
+            'id': '149116',
+            'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
+            'ext': 'mp4',
+            'title': 'Dixie is posing with naked ass very erotic',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = remove_end(self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno')
+
+        flashvars = self._parse_json(self._search_regex(
+            r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
+            display_id, transform_source=js_to_json)
+
+        video_id = flashvars.get('video_id')
+        thumbnail = flashvars.get('preview_url')
+        ext = flashvars.get('postfix', '.mp4')[1:]
+
+        formats = []
+        for video_url_key in ['video_url', 'video_alt_url']:
+            video_url = flashvars.get(video_url_key)
+            if not video_url:
+                continue
+            video_text = flashvars.get('%s_text' % video_url_key)
+            fmt = {
+                'url': video_url,
+                'ext': ext,
+                'format_id': video_text,
+            }
+            m = re.search(r'^(?P<height>\d+)[pP]', video_text)
+            if m:
+                fmt['height'] = int(m.group('height'))
+            formats.append(fmt)
+        self._sort_formats(formats)
+
+        categories = self._html_search_meta(
+            'keywords', webpage, 'categories', default='').split(',')
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'age_limit': 18,
+            'formats': formats,
+        }

youtube_dl/extractor/hitbox.py

@@ -0,0 +1,166 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    parse_iso8601,
+    float_or_none,
+    int_or_none,
+    compat_str,
+)
+
+
+class HitboxIE(InfoExtractor):
+    IE_NAME = 'hitbox'
+    _VALID_URL = r'https?://(?:www\.)?hitbox\.tv/video/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.hitbox.tv/video/203213',
+        'info_dict': {
+            'id': '203213',
+            'title': 'hitbox @ gamescom, Sub Button Hype extended, Giveaway - hitbox News Update with Oxy',
+            'alt_title': 'hitboxlive - Aug 9th #6',
+            'description': '',
+            'ext': 'mp4',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 215.1666,
+            'resolution': 'HD 720p',
+            'uploader': 'hitboxlive',
+            'view_count': int,
+            'timestamp': 1407576133,
+            'upload_date': '20140809',
+            'categories': ['Live Show'],
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _extract_metadata(self, url, video_id):
+        thumb_base = 'https://edge.sf.hitbox.tv'
+        metadata = self._download_json(
+            '%s/%s' % (url, video_id), video_id)
+
+        date = 'media_live_since'
+        media_type = 'livestream'
+        if metadata.get('media_type') == 'video':
+            media_type = 'video'
+            date = 'media_date_added'
+
+        video_meta = metadata.get(media_type, [])[0]
+        title = video_meta.get('media_status')
+        alt_title = video_meta.get('media_title')
+        description = clean_html(
+            video_meta.get('media_description') or
+            video_meta.get('media_description_md'))
+        duration = float_or_none(video_meta.get('media_duration'))
+        uploader = video_meta.get('media_user_name')
+        views = int_or_none(video_meta.get('media_views'))
+        timestamp = parse_iso8601(video_meta.get(date), ' ')
+        categories = [video_meta.get('category_name')]
+        thumbs = [
+            {'url': thumb_base + video_meta.get('media_thumbnail'),
+             'width': 320,
+             'height': 180},
+            {'url': thumb_base + video_meta.get('media_thumbnail_large'),
+             'width': 768,
+             'height': 432},
+        ]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'alt_title': alt_title,
+            'description': description,
+            'ext': 'mp4',
+            'thumbnails': thumbs,
+            'duration': duration,
+            'uploader': uploader,
+            'view_count': views,
+            'timestamp': timestamp,
+            'categories': categories,
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        metadata = self._extract_metadata(
+            'https://www.hitbox.tv/api/media/video',
+            video_id)
+
+        player_config = self._download_json(
+            'https://www.hitbox.tv/api/player/config/video/%s' % video_id,
+            video_id)
+
+        clip = player_config.get('clip')
+        video_url = clip.get('url')
+        res = clip.get('bitrates', [])[0].get('label')
+
+        metadata['resolution'] = res
+        metadata['url'] = video_url
+        metadata['protocol'] = 'm3u8'
+
+        return metadata
+
+
+class HitboxLiveIE(HitboxIE):
+    IE_NAME = 'hitbox:live'
+    _VALID_URL = r'https?://(?:www\.)?hitbox\.tv/(?!video)(?P<id>.+)'
+    _TEST = {
+        'url': 'http://www.hitbox.tv/dimak',
+        'info_dict': {
+            'id': 'dimak',
+            'ext': 'mp4',
+            'description': 'md5:c9f80fa4410bc588d7faa40003fc7d0e',
+            'timestamp': int,
+            'upload_date': compat_str,
+            'title': compat_str,
+            'uploader': 'Dimak',
+        },
+        'params': {
+            # live
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        metadata = self._extract_metadata(
+            'https://www.hitbox.tv/api/media/live',
+            video_id)
+
+        player_config = self._download_json(
+            'https://www.hitbox.tv/api/player/config/live/%s' % video_id,
+            video_id)
+
+        formats = []
+        cdns = player_config.get('cdns')
+        servers = []
+        for cdn in cdns:
+            base_url = cdn.get('netConnectionUrl')
+            host = re.search('.+\.([^\.]+\.[^\./]+)/.+', base_url).group(1)
+            if base_url not in servers:
+                servers.append(base_url)
+                for stream in cdn.get('bitrates'):
+                    label = stream.get('label')
+                    if label != 'Auto':
+                        formats.append({
+                            'url': '%s/%s' % (base_url, stream.get('url')),
+                            'ext': 'mp4',
+                            'vbr': stream.get('bitrate'),
+                            'resolution': label,
+                            'rtmp_live': True,
+                            'format_note': host,
+                            'page_url': url,
+                            'player_url': 'http://www.hitbox.tv/static/player/flowplayer/flowplayer.commercial-3.2.16.swf',
+                        })
+
+        self._sort_formats(formats)
+        metadata['formats'] = formats
+        metadata['is_live'] = True
+        metadata['title'] = self._live_title(metadata.get('title'))
+        return metadata

youtube_dl/extractor/huffpost.py

@@ -39,8 +39,9 @@ class HuffPostIE(InfoExtractor):
         data = self._download_json(api_url, video_id)['data']
 
         video_title = data['title']
-        duration = parse_duration(data['running_time'])
-        upload_date = unified_strdate(data['schedule']['starts_at'])
+        duration = parse_duration(data.get('running_time'))
+        upload_date = unified_strdate(
+            data.get('schedule', {}).get('starts_at') or data.get('segment_start_date_time'))
         description = data.get('description')
 
         thumbnails = []
@@ -59,16 +60,11 @@ class HuffPostIE(InfoExtractor):
             'ext': 'mp4',
             'url': url,
             'vcodec': 'none' if key.startswith('audio/') else None,
-        } for key, url in data['sources']['live'].items()]
-        if data.get('fivemin_id'):
-            fid = data['fivemin_id']
-            fcat = str(int(fid) // 100 + 1)
-            furl = 'http://avideos.5min.com/2/' + fcat[-3:] + '/' + fcat + '/' + fid + '.mp4'
-            formats.append({
-                'format': 'fivemin',
-                'url': furl,
-                'preference': 1,
-            })
+        } for key, url in data.get('sources', {}).get('live', {}).items()]
+
+        if not formats and data.get('fivemin_id'):
+            return self.url_result('5min:%s' % data['fivemin_id'])
+
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/imdb.py

@@ -16,7 +16,6 @@ class ImdbIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.imdb.com/video/imdb/vi2524815897',
-        'md5': '9f34fa777ade3a6e57a054fdbcb3a068',
         'info_dict': {
             'id': '2524815897',
             'ext': 'mp4',

youtube_dl/extractor/internetvideoarchive.py

@@ -22,7 +22,7 @@ class InternetVideoArchiveIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'SKYFALL',
             'description': 'In SKYFALL, Bond\'s loyalty to M is tested as her past comes back to haunt her. As MI6 comes under attack, 007 must track down and destroy the threat, no matter how personal the cost.',
-            'duration': 149,
+            'duration': 152,
         },
     }
 

youtube_dl/extractor/karaoketv.py

@@ -0,0 +1,40 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse
+from ..utils import (
+    js_to_json,
+)
+
+
+class KaraoketvIE(InfoExtractor):
+    _VALID_URL = r'http://karaoketv\.co\.il/\?container=songs&id=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://karaoketv.co.il/?container=songs&id=171568',
+        'info_dict': {
+            'id': '171568',
+            'ext': 'mp4',
+            'title': 'אל העולם שלך - רותם כהן - שרים קריוקי',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        page_video_url = self._og_search_video_url(webpage, video_id)
+        config_json = compat_urllib_parse.unquote_plus(self._search_regex(
+            r'config=(.*)', page_video_url, 'configuration'))
+
+        urls_info_json = self._download_json(
+            config_json, video_id, 'Downloading configuration',
+            transform_source=js_to_json)
+
+        url = urls_info_json['playlist'][0]['url']
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'url': url,
+        }

youtube_dl/extractor/khanacademy.py

@@ -22,8 +22,10 @@ class KhanAcademyIE(InfoExtractor):
             'description': 'The perfect cipher',
             'duration': 176,
             'uploader': 'Brit Cruise',
+            'uploader_id': 'khanacademy',
             'upload_date': '20120411',
-        }
+        },
+        'add_ie': ['Youtube'],
     }, {
         'url': 'https://www.khanacademy.org/math/applied-math/cryptography',
         'info_dict': {

youtube_dl/extractor/kontrtube.py

@@ -10,13 +10,14 @@ from ..utils import int_or_none
 class KontrTubeIE(InfoExtractor):
     IE_NAME = 'kontrtube'
     IE_DESC = 'KontrTube.ru - Труба зовёт'
-    _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/.+'
+    _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/'
 
     _TEST = {
         'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
         'md5': '975a991a4926c9a85f383a736a2e6b80',
         'info_dict': {
             'id': '2678',
+            'display_id': 'nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag',
             'ext': 'mp4',
             'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
             'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',
@@ -28,21 +29,28 @@ class KontrTubeIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
 
-        webpage = self._download_webpage(url, video_id, 'Downloading page')
+        webpage = self._download_webpage(
+            url, display_id, 'Downloading page')
 
-        video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL')
-        thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False)
+        video_url = self._html_search_regex(
+            r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL')
+        thumbnail = self._html_search_regex(
+            r"preview_url\s*:\s*'(.+?)/?',", webpage, 'video thumbnail', fatal=False)
         title = self._html_search_regex(
             r'<title>(.+?)</title>', webpage, 'video title')
-        description = self._html_search_meta('description', webpage, 'video description')
+        description = self._html_search_meta(
+            'description', webpage, 'video description')
 
         mobj = re.search(
-            r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', webpage)
+            r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>',
+            webpage)
         duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
 
         view_count = self._html_search_regex(
-            r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage, 'view count', fatal=False)
+            r'<div class="col_2">Просмотров: <span>(\d+)</span></div>',
+            webpage, 'view count', fatal=False)
 
         comment_count = None
         comment_str = self._html_search_regex(
@@ -56,6 +64,7 @@ class KontrTubeIE(InfoExtractor):
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'url': video_url,
             'thumbnail': thumbnail,
             'title': title,

youtube_dl/extractor/liveleak.py

@@ -8,20 +8,20 @@ from ..utils import int_or_none
 
 
 class LiveLeakIE(InfoExtractor):
-    _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
+    _VALID_URL = r'https?://(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)'
     _TESTS = [{
         'url': 'http://www.liveleak.com/view?i=757_1364311680',
-        'md5': '0813c2430bea7a46bf13acf3406992f4',
+        'md5': '50f79e05ba149149c1b4ea961223d5b3',
         'info_dict': {
             'id': '757_1364311680',
-            'ext': 'mp4',
+            'ext': 'flv',
             'description': 'extremely bad day for this guy..!',
             'uploader': 'ljfriel2',
             'title': 'Most unlucky car accident'
         }
     }, {
         'url': 'http://www.liveleak.com/view?i=f93_1390833151',
-        'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
+        'md5': 'b13a29626183c9d33944e6a04f41aafc',
         'info_dict': {
             'id': 'f93_1390833151',
             'ext': 'mp4',
@@ -43,8 +43,7 @@ class LiveLeakIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('video_id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
@@ -81,9 +80,19 @@ class LiveLeakIE(InfoExtractor):
         sources = json.loads(sources_json)
 
         formats = [{
+            'format_id': '%s' % i,
             'format_note': s.get('label'),
             'url': s['file'],
-        } for s in sources]
+        } for i, s in enumerate(sources)]
+        for i, s in enumerate(sources):
+            orig_url = s['file'].replace('.h264_base.mp4', '')
+            if s['file'] != orig_url:
+                formats.append({
+                    'format_id': 'original-%s' % i,
+                    'format_note': s.get('label'),
+                    'url': orig_url,
+                    'preference': 1,
+                })
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/lnkgo.py

@@ -0,0 +1,124 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    js_to_json,
+    unified_strdate,
+)
+
+
+class LnkGoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?lnkgo\.alfa\.lt/visi\-video/(?P<show>[^/]+)/ziurek\-(?P<display_id>[A-Za-z0-9\-]+)'
+    _TESTS = [{
+        'url': 'http://lnkgo.alfa.lt/visi-video/yra-kaip-yra/ziurek-yra-kaip-yra-162',
+        'info_dict': {
+            'id': '46712',
+            'ext': 'mp4',
+            'title': 'Yra kaip yra',
+            'upload_date': '20150107',
+            'description': 'md5:d82a5e36b775b7048617f263a0e3475e',
+            'age_limit': 7,
+            'duration': 3019,
+            'thumbnail': 're:^https?://.*\.jpg$'
+        },
+        'params': {
+            'skip_download': True,  # HLS download
+        },
+    }, {
+        'url': 'http://lnkgo.alfa.lt/visi-video/aktualai-pratesimas/ziurek-nerdas-taiso-kompiuteri-2',
+        'info_dict': {
+            'id': '47289',
+            'ext': 'mp4',
+            'title': 'Nėrdas: Kompiuterio Valymas',
+            'upload_date': '20150113',
+            'description': 'md5:7352d113a242a808676ff17e69db6a69',
+            'age_limit': 18,
+            'duration': 346,
+            'thumbnail': 're:^https?://.*\.jpg$'
+        },
+        'params': {
+            'skip_download': True,  # HLS download
+        },
+    }]
+    _AGE_LIMITS = {
+        'N-7': 7,
+        'N-14': 14,
+        'S': 18,
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(
+            url, display_id, 'Downloading player webpage')
+
+        video_id = self._search_regex(
+            r'data-ep="([^"]+)"', webpage, 'video ID')
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+
+        thumbnail_w = int_or_none(
+            self._og_search_property('image:width', webpage, 'thumbnail width', fatal=False))
+        thumbnail_h = int_or_none(
+            self._og_search_property('image:height', webpage, 'thumbnail height', fatal=False))
+        thumbnail = {
+            'url': self._og_search_thumbnail(webpage),
+        }
+        if thumbnail_w and thumbnail_h:
+            thumbnail.update({
+                'width': thumbnail_w,
+                'height': thumbnail_h,
+            })
+
+        upload_date = unified_strdate(self._search_regex(
+            r'class="meta-item\sair-time">.*?<strong>([^<]+)</strong>', webpage, 'upload date', fatal=False))
+        duration = int_or_none(self._search_regex(
+            r'VideoDuration = "([^"]+)"', webpage, 'duration', fatal=False))
+
+        pg_rating = self._search_regex(
+            r'pgrating="([^"]+)"', webpage, 'PG rating', fatal=False, default='')
+        age_limit = self._AGE_LIMITS.get(pg_rating.upper(), 0)
+
+        sources_js = self._search_regex(
+            r'(?s)sources:\s(\[.*?\]),', webpage, 'sources')
+        sources = self._parse_json(
+            sources_js, video_id, transform_source=js_to_json)
+
+        formats = []
+        for source in sources:
+            if source.get('provider') == 'rtmp':
+                m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<play_path>.+)$', source['file'])
+                if not m:
+                    continue
+                formats.append({
+                    'format_id': 'rtmp',
+                    'ext': 'flv',
+                    'url': m.group('url'),
+                    'play_path': m.group('play_path'),
+                    'page_url': url,
+                })
+            elif source.get('file').endswith('.m3u8'):
+                formats.append({
+                    'format_id': 'hls',
+                    'ext': source.get('type', 'mp4'),
+                    'url': source['file'],
+                })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'thumbnails': [thumbnail],
+            'duration': duration,
+            'description': description,
+            'age_limit': age_limit,
+            'upload_date': upload_date,
+        }

youtube_dl/extractor/lrt.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
 from ..utils import (
@@ -28,7 +27,6 @@ class LRTIE(InfoExtractor):
         'params': {
             'skip_download': True,  # HLS download
         },
-
     }
 
     def _real_extract(self, url):
@@ -44,7 +42,9 @@ class LRTIE(InfoExtractor):
 
         formats = []
         for js in re.findall(r'(?s)config:\s*(\{.*?\})', webpage):
-            data = json.loads(js_to_json(js))
+            data = self._parse_json(js, video_id, transform_source=js_to_json)
+            if 'provider' not in data:
+                continue
             if data['provider'] == 'rtmp':
                 formats.append({
                     'format_id': 'rtmp',

youtube_dl/extractor/mit.py

@@ -17,7 +17,7 @@ from ..utils import (
 
 class TechTVMITIE(InfoExtractor):
     IE_NAME = 'techtv.mit.edu'
-    _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
+    _VALID_URL = r'https?://techtv\.mit\.edu/(?:videos|embeds)/(?P<id>\d+)'
 
     _TEST = {
         'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
@@ -31,8 +31,7 @@ class TechTVMITIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         raw_page = self._download_webpage(
             'http://techtv.mit.edu/videos/%s' % video_id, video_id)
         clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page)
@@ -106,7 +105,10 @@ class OCWMITIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence',
                 'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
-                #'subtitles': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/MIT6_041F11_lec07_300k.mp4.srt'
+                'upload_date': '20121109',
+                'uploader_id': 'MIT',
+                'uploader': 'MIT OpenCourseWare',
+                # 'subtitles': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/MIT6_041F11_lec07_300k.mp4.srt'
             }
         },
         {
@@ -115,8 +117,11 @@ class OCWMITIE(InfoExtractor):
                 'id': '7K1sB05pE0A',
                 'ext': 'mp4',
                 'title': 'Session 1: Introduction to Derivatives',
+                'upload_date': '20090818',
+                'uploader_id': 'MIT',
+                'uploader': 'MIT OpenCourseWare',
                 'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.',
-                #'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT'
+                # 'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT'
             }
         }
     ]

youtube_dl/extractor/moevideo.py

@@ -52,7 +52,8 @@ class MoeVideoIE(InfoExtractor):
                 'height': 296,
                 'duration': 6027,
                 'filesize': 588257923,
-            }
+            },
+            'skip': 'Video has been removed',
         },
     ]
 

youtube_dl/extractor/mooshare.py

@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 import re
-import time
 
 from .common import InfoExtractor
 from ..compat import (
@@ -64,8 +63,7 @@ class MooshareIE(InfoExtractor):
             'http://mooshare.biz/%s' % video_id, compat_urllib_parse.urlencode(download_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 
-        self.to_screen('%s: Waiting for timeout' % video_id)
-        time.sleep(5)
+        self._sleep(5, video_id)
 
         video_page = self._download_webpage(request, video_id, 'Downloading video page')
 

youtube_dl/extractor/motorsport.py

@@ -1,63 +1,49 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import hashlib
-import json
-import time
-
 from .common import InfoExtractor
 from ..compat import (
-    compat_parse_qs,
-    compat_str,
-)
-from ..utils import (
-    int_or_none,
+    compat_urlparse,
 )
 
 
 class MotorsportIE(InfoExtractor):
     IE_DESC = 'motorsport.com'
-    _VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/(?:$|[?#])'
+    _VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
     _TEST = {
         'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/',
-        'md5': '5592cb7c5005d9b2c163df5ac3dc04e4',
         'info_dict': {
-            'id': '7063',
+            'id': '2-T3WuR-KMM',
             'ext': 'mp4',
             'title': 'Red Bull Racing: 2014 Rules Explained',
-            'duration': 207,
+            'duration': 208,
             'description': 'A new clip from Red Bull sees Daniel Ricciardo and Sebastian Vettel explain the 2014 Formula One regulations – which are arguably the most complex the sport has ever seen.',
-            'uploader': 'rainiere',
-            'thumbnail': r're:^http://.*motorsport\.com/.+\.jpg$'
-        }
+            'uploader': 'mcomstaff',
+            'uploader_id': 'UC334JIYKkVnyFoNCclfZtHQ',
+            'upload_date': '20140903',
+            'thumbnail': r're:^https?://.+\.jpg$'
+        },
+        'add_ie': ['Youtube'],
+        'params': {
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
 
-        flashvars_code = self._html_search_regex(
-            r'<embed id="player".*?flashvars="([^"]+)"', webpage, 'flashvars')
-        flashvars = compat_parse_qs(flashvars_code)
-        params = json.loads(flashvars['parameters'][0])
-
-        e = compat_str(int(time.time()) + 24 * 60 * 60)
-        base_video_url = params['location'] + '?e=' + e
-        s = 'h3hg713fh32'
-        h = hashlib.md5((s + base_video_url).encode('utf-8')).hexdigest()
-        video_url = base_video_url + '&h=' + h
-
-        uploader = self._html_search_regex(
-            r'(?s)<span class="label">Video by: </span>(.*?)</a>', webpage,
-            'uploader', fatal=False)
+        iframe_path = self._html_search_regex(
+            r'<iframe id="player_iframe"[^>]+src="([^"]+)"', webpage,
+            'iframe path')
+        iframe = self._download_webpage(
+            compat_urlparse.urljoin(url, iframe_path), display_id,
+            'Downloading iframe')
+        youtube_id = self._search_regex(
+            r'www.youtube.com/embed/(.{11})', iframe, 'youtube id')
 
         return {
-            'id': params['video_id'],
+            '_type': 'url_transparent',
             'display_id': display_id,
-            'title': params['title'],
-            'url': video_url,
-            'description': params.get('description'),
-            'thumbnail': params.get('main_thumb'),
-            'duration': int_or_none(params.get('duration')),
-            'uploader': uploader,
+            'url': 'https://youtube.com/watch?v=%s' % youtube_id,
         }

youtube_dl/extractor/nbc.py

@@ -6,6 +6,7 @@ import json
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
+    compat_HTTPError,
 )
 from ..utils import (
     ExtractorError,
@@ -78,6 +79,16 @@ class NBCNewsIE(InfoExtractor):
             },
             'add_ie': ['ThePlatform'],
         },
+        {
+            'url': 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156',
+            'md5': 'fdbf39ab73a72df5896b6234ff98518a',
+            'info_dict': {
+                'id': 'Wjf9EDR3A_60',
+                'ext': 'mp4',
+                'title': 'FULL EPISODE: Family Business',
+                'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
+            },
+        },
     ]
 
     def _real_extract(self, url):
@@ -115,10 +126,19 @@ class NBCNewsIE(InfoExtractor):
                 if not base_url:
                     continue
                 playlist_url = base_url + '?form=MPXNBCNewsAPI'
-                all_videos = self._download_json(playlist_url, title)['videos']
 
                 try:
-                    info = next(v for v in all_videos if v['mpxId'] == mpxid)
+                    all_videos = self._download_json(playlist_url, title)
+                except ExtractorError as ee:
+                    if isinstance(ee.cause, compat_HTTPError):
+                        continue
+                    raise
+
+                if not all_videos or 'videos' not in all_videos:
+                    continue
+
+                try:
+                    info = next(v for v in all_videos['videos'] if v['mpxId'] == mpxid)
                     break
                 except StopIteration:
                     continue

youtube_dl/extractor/ndtv.py

@@ -27,9 +27,7 @@ class NDTVIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         filename = self._search_regex(

youtube_dl/extractor/nerdcubed.py

@@ -0,0 +1,35 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import datetime
+
+from .common import InfoExtractor
+
+
+class NerdCubedFeedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nerdcubed\.co\.uk/feed\.json'
+    _TEST = {
+        'url': 'http://www.nerdcubed.co.uk/feed.json',
+        'info_dict': {
+            'title': 'nerdcubed.co.uk feed',
+        },
+        'playlist_mincount': 1300,
+    }
+
+    def _real_extract(self, url):
+        feed = self._download_json(url, url, "Downloading NerdCubed JSON feed")
+
+        entries = [{
+            '_type': 'url',
+            'title': feed_entry['title'],
+            'uploader': feed_entry['source']['name'] if feed_entry['source'] else None,
+            'upload_date': datetime.datetime.strptime(feed_entry['date'], '%Y-%m-%d').strftime('%Y%m%d'),
+            'url': "http://www.youtube.com/watch?v=" + feed_entry['youtube_id'],
+        } for feed_entry in feed]
+
+        return {
+            '_type': 'playlist',
+            'title': 'nerdcubed.co.uk feed',
+            'id': 'nerdcubed-feed',
+            'entries': entries,
+        }

youtube_dl/extractor/netzkino.py

@@ -0,0 +1,86 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    int_or_none,
+    js_to_json,
+    parse_iso8601,
+)
+
+
+class NetzkinoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?netzkino\.de/\#!/(?P<category>[^/]+)/(?P<id>[^/]+)'
+
+    _TEST = {
+        'url': 'http://www.netzkino.de/#!/scifikino/rakete-zum-mond',
+        'md5': '92a3f8b76f8d7220acce5377ea5d4873',
+        'info_dict': {
+            'id': 'rakete-zum-mond',
+            'ext': 'mp4',
+            'title': 'Rakete zum Mond (Endstation Mond, Destination Moon)',
+            'comments': 'mincount:3',
+            'description': 'md5:1eddeacc7e62d5a25a2d1a7290c64a28',
+            'upload_date': '20120813',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'timestamp': 1344858571,
+            'age_limit': 12,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        category_id = mobj.group('category')
+        video_id = mobj.group('id')
+
+        api_url = 'http://api.netzkino.de.simplecache.net/capi-2.0a/categories/%s.json?d=www' % category_id
+        api_info = self._download_json(api_url, video_id)
+        info = next(
+            p for p in api_info['posts'] if p['slug'] == video_id)
+        custom_fields = info['custom_fields']
+
+        production_js = self._download_webpage(
+            'http://www.netzkino.de/beta/dist/production.min.js', video_id,
+            note='Downloading player code')
+        avo_js = self._search_regex(
+            r'window\.avoCore\s*=.*?urlTemplate:\s*(\{.*?"\})',
+            production_js, 'URL templates')
+        templates = self._parse_json(
+            avo_js, video_id, transform_source=js_to_json)
+
+        suffix = {
+            'hds': '.mp4/manifest.f4m',
+            'hls': '.mp4/master.m3u8',
+            'pmd': '.mp4',
+        }
+        film_fn = custom_fields['Streaming'][0]
+        formats = [{
+            'format_id': key,
+            'ext': 'mp4',
+            'url': tpl.replace('{}', film_fn) + suffix[key],
+        } for key, tpl in templates.items()]
+        self._sort_formats(formats)
+
+        comments = [{
+            'timestamp': parse_iso8601(c.get('date'), delimiter=' '),
+            'id': c['id'],
+            'author': c['name'],
+            'html': c['content'],
+            'parent': 'root' if c.get('parent', 0) == 0 else c['parent'],
+        } for c in info.get('comments', [])]
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'comments': comments,
+            'title': info['title'],
+            'age_limit': int_or_none(custom_fields.get('FSK')[0]),
+            'timestamp': parse_iso8601(info.get('date'), delimiter=' '),
+            'description': clean_html(info.get('content')),
+            'thumbnail': info.get('thumbnail'),
+            'playlist_title': api_info.get('title'),
+            'playlist_id': category_id,
+        }

youtube_dl/extractor/nhl.py

@@ -54,7 +54,7 @@ class NHLBaseInfoExtractor(InfoExtractor):
 
 class NHLIE(NHLBaseInfoExtractor):
     IE_NAME = 'nhl.com'
-    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P<id>[0-9a-z-]+)'
+    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)'
 
     _TESTS = [{
         'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',

youtube_dl/extractor/normalboots.py

@@ -22,7 +22,11 @@ class NormalbootsIE(InfoExtractor):
             'description': 'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for ‘Tense Battle Theme’:\xa0http://www.youtube.com/Kiamet/',
             'uploader': 'JonTron',
             'upload_date': '20140125',
-        }
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/npo.py

@@ -1,18 +1,26 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
-    unified_strdate,
+    fix_xml_ampersands,
     parse_duration,
     qualities,
     strip_jsonp,
+    unified_strdate,
     url_basename,
 )
 
 
-class NPOIE(InfoExtractor):
+class NPOBaseIE(InfoExtractor):
+    def _get_token(self, video_id):
+        token_page = self._download_webpage(
+            'http://ida.omroep.nl/npoplayer/i.js',
+            video_id, note='Downloading token')
+        return self._search_regex(
+            r'npoplayer\.token = "(.+?)"', token_page, 'token')
+
+
+class NPOIE(NPOBaseIE):
     IE_NAME = 'npo.nl'
     _VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?P<id>[^/?]+)'
 
@@ -51,12 +59,35 @@ class NPOIE(InfoExtractor):
                 'upload_date': '20130225',
                 'duration': 3000,
             },
-        }
+        },
+        {
+            'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
+            'info_dict': {
+                'id': 'WO_VPRO_043706',
+                'ext': 'wmv',
+                'title': 'De nieuwe mens - Deel 1',
+                'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
+                'duration': 4680,
+            },
+            'params': {
+                # mplayer mms download
+                'skip_download': True,
+            }
+        },
+        # non asf in streams
+        {
+            'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
+            'md5': 'b3da13de374cbe2d5332a7e910bef97f',
+            'info_dict': {
+                'id': 'WO_NOS_762771',
+                'ext': 'mp4',
+                'title': 'Hoe gaat Europa verder na Parijs?',
+            },
+        },
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         return self._get_info(video_id)
 
     def _get_info(self, video_id):
@@ -66,39 +97,68 @@ class NPOIE(InfoExtractor):
             # We have to remove the javascript callback
             transform_source=strip_jsonp,
         )
-        token_page = self._download_webpage(
-            'http://ida.omroep.nl/npoplayer/i.js',
-            video_id,
-            note='Downloading token'
-        )
-        token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token')
+
+        token = self._get_token(video_id)
 
         formats = []
-        quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
-        for format_id in metadata['pubopties']:
-            format_info = self._download_json(
-                'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s' % (video_id, format_id, token),
-                video_id, 'Downloading %s JSON' % format_id)
-            if format_info.get('error_code', 0) or format_info.get('errorcode', 0):
-                continue
-            streams = format_info.get('streams')
-            if streams:
-                video_info = self._download_json(
-                    streams[0] + '&type=json',
-                    video_id, 'Downloading %s stream JSON' % format_id)
-            else:
-                video_info = format_info
-            video_url = video_info.get('url')
-            if not video_url:
-                continue
-            if format_id == 'adaptive':
-                formats.extend(self._extract_m3u8_formats(video_url, video_id))
-            else:
+
+        pubopties = metadata.get('pubopties')
+        if pubopties:
+            quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
+            for format_id in pubopties:
+                format_info = self._download_json(
+                    'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s'
+                    % (video_id, format_id, token),
+                    video_id, 'Downloading %s JSON' % format_id)
+                if format_info.get('error_code', 0) or format_info.get('errorcode', 0):
+                    continue
+                streams = format_info.get('streams')
+                if streams:
+                    video_info = self._download_json(
+                        streams[0] + '&type=json',
+                        video_id, 'Downloading %s stream JSON' % format_id)
+                else:
+                    video_info = format_info
+                video_url = video_info.get('url')
+                if not video_url:
+                    continue
+                if format_id == 'adaptive':
+                    formats.extend(self._extract_m3u8_formats(video_url, video_id))
+                else:
+                    formats.append({
+                        'url': video_url,
+                        'format_id': format_id,
+                        'quality': quality(format_id),
+                    })
+
+        streams = metadata.get('streams')
+        if streams:
+            for i, stream in enumerate(streams):
+                stream_url = stream.get('url')
+                if not stream_url:
+                    continue
+                if '.asf' not in stream_url:
+                    formats.append({
+                        'url': stream_url,
+                        'quality': stream.get('kwaliteit'),
+                    })
+                    continue
+                asx = self._download_xml(
+                    stream_url, video_id,
+                    'Downloading stream %d ASX playlist' % i,
+                    transform_source=fix_xml_ampersands)
+                ref = asx.find('./ENTRY/Ref')
+                if ref is None:
+                    continue
+                video_url = ref.get('href')
+                if not video_url:
+                    continue
                 formats.append({
                     'url': video_url,
-                    'format_id': format_id,
-                    'quality': quality(format_id),
+                    'ext': stream.get('formaat', 'asf'),
+                    'quality': stream.get('kwaliteit'),
                 })
+
         self._sort_formats(formats)
 
         return {
@@ -112,6 +172,83 @@ class NPOIE(InfoExtractor):
         }
 
 
+class NPOLiveIE(NPOBaseIE):
+    IE_NAME = 'npo.nl:live'
+    _VALID_URL = r'https?://www\.npo\.nl/live/(?P<id>.+)'
+
+    _TEST = {
+        'url': 'http://www.npo.nl/live/npo-1',
+        'info_dict': {
+            'id': 'LI_NEDERLAND1_136692',
+            'display_id': 'npo-1',
+            'ext': 'mp4',
+            'title': 're:^Nederland 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'description': 'Livestream',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        live_id = self._search_regex(
+            r'data-prid="([^"]+)"', webpage, 'live id')
+
+        metadata = self._download_json(
+            'http://e.omroep.nl/metadata/%s' % live_id,
+            display_id, transform_source=strip_jsonp)
+
+        token = self._get_token(display_id)
+
+        formats = []
+
+        streams = metadata.get('streams')
+        if streams:
+            for stream in streams:
+                stream_type = stream.get('type').lower()
+                if stream_type == 'ss':
+                    continue
+                stream_info = self._download_json(
+                    'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp'
+                    % (stream.get('url'), token),
+                    display_id, 'Downloading %s JSON' % stream_type)
+                if stream_info.get('error_code', 0) or stream_info.get('errorcode', 0):
+                    continue
+                stream_url = self._download_json(
+                    stream_info['stream'], display_id,
+                    'Downloading %s URL' % stream_type,
+                    transform_source=strip_jsonp)
+                if stream_type == 'hds':
+                    f4m_formats = self._extract_f4m_formats(stream_url, display_id)
+                    # f4m downloader downloads only piece of live stream
+                    for f4m_format in f4m_formats:
+                        f4m_format['preference'] = -1
+                    formats.extend(f4m_formats)
+                elif stream_type == 'hls':
+                    formats.extend(self._extract_m3u8_formats(stream_url, display_id, 'mp4'))
+                else:
+                    formats.append({
+                        'url': stream_url,
+                    })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': live_id,
+            'display_id': display_id,
+            'title': self._live_title(metadata['titel']),
+            'description': metadata['info'],
+            'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
+            'formats': formats,
+            'is_live': True,
+        }
+
+
 class TegenlichtVproIE(NPOIE):
     IE_NAME = 'tegenlicht.vpro.nl'
     _VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?'

youtube_dl/extractor/nrk.py

@@ -7,8 +7,10 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     float_or_none,
+    parse_duration,
     unified_strdate,
 )
+from .subtitles import SubtitlesInfoExtractor
 
 
 class NRKIE(InfoExtractor):
@@ -71,13 +73,13 @@ class NRKIE(InfoExtractor):
         }
 
 
-class NRKTVIE(InfoExtractor):
-    _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})'
+class NRKTVIE(SubtitlesInfoExtractor):
+    _VALID_URL = r'(?P<baseurl>http://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
 
     _TESTS = [
         {
             'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
-            'md5': '7b96112fbae1faf09a6f9ae1aff6cb84',
+            'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
             'info_dict': {
                 'id': 'MUHH48000314',
                 'ext': 'flv',
@@ -85,11 +87,11 @@ class NRKTVIE(InfoExtractor):
                 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
                 'upload_date': '20140523',
                 'duration': 1741.52,
-            }
+            },
         },
         {
             'url': 'http://tv.nrk.no/program/mdfp15000514',
-            'md5': 'af01795a31f1cf7265c8657534d8077b',
+            'md5': '383650ece2b25ecec996ad7b5bb2a384',
             'info_dict': {
                 'id': 'mdfp15000514',
                 'ext': 'flv',
@@ -97,42 +99,155 @@ class NRKTVIE(InfoExtractor):
                 'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
                 'upload_date': '20140524',
                 'duration': 4605.0,
-            }
+            },
         },
+        {
+            # single playlist video
+            'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
+            'md5': 'adbd1dbd813edaf532b0a253780719c2',
+            'info_dict': {
+                'id': 'MSPO40010515-part2',
+                'ext': 'flv',
+                'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
+                'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+                'upload_date': '20150106',
+            },
+            'skip': 'Only works from Norway',
+        },
+        {
+            'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
+            'playlist': [
+                {
+                    'md5': '9480285eff92d64f06e02a5367970a7a',
+                    'info_dict': {
+                        'id': 'MSPO40010515-part1',
+                        'ext': 'flv',
+                        'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
+                        'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+                        'upload_date': '20150106',
+                    },
+                },
+                {
+                    'md5': 'adbd1dbd813edaf532b0a253780719c2',
+                    'info_dict': {
+                        'id': 'MSPO40010515-part2',
+                        'ext': 'flv',
+                        'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
+                        'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+                        'upload_date': '20150106',
+                    },
+                },
+            ],
+            'info_dict': {
+                'id': 'MSPO40010515',
+                'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
+                'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+                'upload_date': '20150106',
+                'duration': 6947.5199999999995,
+            },
+            'skip': 'Only works from Norway',
+        }
     ]
 
+    def _seconds2str(self, s):
+        return '%02d:%02d:%02d.%03d' % (s / 3600, (s % 3600) / 60, s % 60, (s % 1) * 1000)
+
+    def _debug_print(self, txt):
+        if self._downloader.params.get('verbose', False):
+            self.to_screen('[debug] %s' % txt)
+
+    def _extract_captions(self, subtitlesurl, video_id, baseurl):
+        url = "%s%s" % (baseurl, subtitlesurl)
+        self._debug_print('%s: Subtitle url: %s' % (video_id, url))
+        captions = self._download_xml(url, video_id, 'Downloading subtitles')
+        lang = captions.get('lang', 'no')
+        ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/ns/ttml}'))
+        srt = ''
+        for pos, p in enumerate(ps):
+            begin = parse_duration(p.get('begin'))
+            duration = parse_duration(p.get('dur'))
+            starttime = self._seconds2str(begin)
+            endtime = self._seconds2str(begin + duration)
+            text = '\n'.join(p.itertext())
+            srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), starttime, endtime, text)
+        return {lang: srt}
+
+    def _extract_f4m(self, manifest_url, video_id):
+        return self._extract_f4m_formats(manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id)
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        part_id = mobj.group('part_id')
+        baseurl = mobj.group('baseurl')
 
-        page = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, video_id)
 
-        title = self._html_search_meta('title', page, 'title')
-        description = self._html_search_meta('description', page, 'description')
-        thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False)
-        upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False))
-        duration = float_or_none(
-            self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False))
+        title = self._html_search_meta(
+            'title', webpage, 'title')
+        description = self._html_search_meta(
+            'description', webpage, 'description')
+
+        thumbnail = self._html_search_regex(
+            r'data-posterimage="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+        upload_date = unified_strdate(self._html_search_meta(
+            'rightsfrom', webpage, 'upload date', fatal=False))
+        duration = float_or_none(self._html_search_regex(
+            r'data-duration="([^"]+)"',
+            webpage, 'duration', fatal=False))
+
+        # playlist
+        parts = re.findall(
+            r'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage)
+        if parts:
+            entries = []
+            for current_part_id, stream_url, part_title in parts:
+                if part_id and current_part_id != part_id:
+                    continue
+                video_part_id = '%s-part%s' % (video_id, current_part_id)
+                formats = self._extract_f4m(stream_url, video_part_id)
+                entries.append({
+                    'id': video_part_id,
+                    'title': part_title,
+                    'description': description,
+                    'thumbnail': thumbnail,
+                    'upload_date': upload_date,
+                    'formats': formats,
+                })
+            if part_id:
+                if entries:
+                    return entries[0]
+            else:
+                playlist = self.playlist_result(entries, video_id, title, description)
+                playlist.update({
+                    'thumbnail': thumbnail,
+                    'upload_date': upload_date,
+                    'duration': duration,
+                })
+                return playlist
 
         formats = []
 
-        f4m_url = re.search(r'data-media="([^"]+)"', page)
+        f4m_url = re.search(r'data-media="([^"]+)"', webpage)
         if f4m_url:
-            formats.append({
-                'url': f4m_url.group(1) + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
-                'format_id': 'f4m',
-                'ext': 'flv',
-            })
+            formats.extend(self._extract_f4m(f4m_url.group(1), video_id))
 
-        m3u8_url = re.search(r'data-hls-media="([^"]+)"', page)
+        m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
         if m3u8_url:
-            formats.append({
-                'url': m3u8_url.group(1),
-                'format_id': 'm3u8',
-            })
-
+            formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4'))
         self._sort_formats(formats)
 
+        subtitles_url = self._html_search_regex(
+            r'data-subtitlesurl[ ]*=[ ]*"([^"]+)"',
+            webpage, 'subtitle URL', default=None)
+        subtitles = None
+        if subtitles_url:
+            subtitles = self._extract_captions(subtitles_url, video_id, baseurl)
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
+
         return {
             'id': video_id,
             'title': title,
@@ -141,4 +256,5 @@ class NRKTVIE(InfoExtractor):
             'upload_date': upload_date,
             'duration': duration,
             'formats': formats,
+            'subtitles': subtitles,
         }

youtube_dl/extractor/openfilm.py

@@ -0,0 +1,70 @@
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_iso8601,
+    compat_urllib_parse,
+    parse_age_limit,
+    int_or_none,
+)
+
+
+class OpenFilmIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)openfilm\.com/videos/(?P<id>.+)'
+    _TEST = {
+        'url': 'http://www.openfilm.com/videos/human-resources-remastered',
+        'md5': '42bcd88c2f3ec13b65edf0f8ad1cac37',
+        'info_dict': {
+            'id': '32736',
+            'display_id': 'human-resources-remastered',
+            'ext': 'mp4',
+            'title': 'Human Resources (Remastered)',
+            'description': 'Social Engineering in the 20th Century.',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 7164,
+            'timestamp': 1334756988,
+            'upload_date': '20120418',
+            'uploader_id': '41117',
+            'view_count': int,
+            'age_limit': 0,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        player = compat_urllib_parse.unquote_plus(
+            self._og_search_video_url(webpage))
+
+        video = json.loads(self._search_regex(
+            r'\bp=({.+?})(?:&|$)', player, 'video JSON'))
+
+        video_url = '%s1.mp4' % video['location']
+        video_id = video.get('video_id')
+        display_id = video.get('alias') or display_id
+        title = video.get('title')
+        description = video.get('description')
+        thumbnail = video.get('main_thumb')
+        duration = int_or_none(video.get('duration'))
+        timestamp = parse_iso8601(video.get('dt_published'), ' ')
+        uploader_id = video.get('user_id')
+        view_count = int_or_none(video.get('views_count'))
+        age_limit = parse_age_limit(video.get('age_limit'))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'uploader_id': uploader_id,
+            'view_count': view_count,
+            'age_limit': age_limit,
+        }

youtube_dl/extractor/orf.py

@@ -17,9 +17,9 @@ from ..utils import (
 class ORFTVthekIE(InfoExtractor):
     IE_NAME = 'orf:tvthek'
     IE_DESC = 'ORF TVthek'
-    _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics/.+?|program/[^/]+)/(?P<id>\d+)'
+    _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics?/.+?|program/[^/]+)/(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
         'playlist': [{
             'md5': '2942210346ed779588f428a92db88712',
@@ -32,8 +32,21 @@ class ORFTVthekIE(InfoExtractor):
                 'upload_date': '20141208',
             },
         }],
-        'skip': 'Blocked outside of Austria',
-    }
+        'skip': 'Blocked outside of Austria / Germany',
+    }, {
+        'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256',
+        'playlist': [{
+            'md5': '68f543909aea49d621dfc7703a11cfaf',
+            'info_dict': {
+                'id': '7982259',
+                'ext': 'mp4',
+                'title': 'Best of Ingrid Thurnher',
+                'upload_date': '20140527',
+                'description': 'Viele Jahre war Ingrid Thurnher das "Gesicht" der ZIB 2. Vor ihrem Wechsel zur ZIB 2 im jahr 1995 moderierte sie unter anderem "Land und Leute", "Österreich-Bild" und "Niederösterreich heute".',
+            }
+        }],
+        '_skip': 'Blocked outside of Austria / Germany',
+    }]
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
@@ -45,7 +58,9 @@ class ORFTVthekIE(InfoExtractor):
 
         def get_segments(all_data):
             for data in all_data:
-                if data['name'] == 'Tracker::EPISODE_DETAIL_PAGE_OVER_PROGRAM':
+                if data['name'] in (
+                        'Tracker::EPISODE_DETAIL_PAGE_OVER_PROGRAM',
+                        'Tracker::EPISODE_DETAIL_PAGE_OVER_TOPIC'):
                     return data['values']['segments']
 
         sdata = get_segments(all_data)
@@ -113,13 +128,16 @@ class ORFTVthekIE(InfoExtractor):
         }
 
 
-# Audios on ORF radio are only available for 7 days, so we can't add tests.
-
-
 class ORFOE1IE(InfoExtractor):
     IE_NAME = 'orf:oe1'
     IE_DESC = 'Radio Österreich 1'
-    _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)'
+    _VALID_URL = r'http://oe1\.orf\.at/(?:programm/|konsole.*?#\?track_id=)(?P<id>[0-9]+)'
+
+    # Audios on ORF radio are only available for 7 days, so we can't add tests.
+    _TEST = {
+        'url': 'http://oe1.orf.at/konsole?show=on_demand#?track_id=394211',
+        'only_matching': True,
+    }
 
     def _real_extract(self, url):
         show_id = self._match_id(url)
@@ -145,7 +163,7 @@ class ORFOE1IE(InfoExtractor):
 
 
 class ORFFM4IE(InfoExtractor):
-    IE_DESC = 'orf:fm4'
+    IE_NAME = 'orf:fm4'
     IE_DESC = 'radio FM4'
     _VALID_URL = r'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)'