release 2015.02.10.2

This functionality is intended to eventually encompass the current format filtering.

AUTHORS

@@ -108,3 +108,5 @@ Enam Mijbah Noor
 David Luhmer
 Shaya Goldberg
 Paul Hartmann
+Frans de Jonge
+Robin de Rooij

CONTRIBUTING.md

@@ -1,4 +1,6 @@
-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):
 
@@ -122,7 +124,7 @@ If you want to add support for a new site, you can follow this quick list (assum
 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
 7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
-8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501).
+8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
 9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
 
         $ git add youtube_dl/extractor/__init__.py

Makefile

@@ -1,10 +1,7 @@
 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
-
-cleanall: clean
-	rm -f youtube-dl youtube-dl.exe
+	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json *.mp4 *.flv *.mp3 CONTRIBUTING.md.tmp youtube-dl youtube-dl.exe
 
 PREFIX ?= /usr/local
 BINDIR ?= $(PREFIX)/bin

README.md

@@ -119,6 +119,23 @@ which means you can modify it, redistribute it or use it however you like.
                                      COUNT views
     --max-views COUNT                Do not download any videos with more than
                                      COUNT views
+    --match-filter FILTER            (Experimental) Generic video filter.
+                                     Specify any key (see help for -o for a list
+                                     of available keys) to match if the key is
+                                     present, !key to check if the key is not
+                                     present,key > NUMBER (like "comment_count >
+                                     12", also works with >=, <, <=, !=, =) to
+                                     compare against a number, and & to require
+                                     multiple matches. Values which are not
+                                     known are excluded unless you put a
+                                     question mark (?) after the operator.For
+                                     example, to only match videos that have
+                                     been liked more than 100 times and disliked
+                                     less than 50 times (or the dislike
+                                     functionality is not available at the given
+                                     service), but who also have a description,
+                                     use  --match-filter "like_count > 100 &
+                                     dislike_count <? 50 & description" .
     --no-playlist                    If the URL refers to a video and a
                                      playlist, download only the video.
     --age-limit YEARS                download only videos suitable for the given
@@ -292,18 +309,20 @@ which means you can modify it, redistribute it or use it however you like.
                                      video results by putting a condition in
                                      brackets, as in -f "best[height=720]" (or
                                      -f "[filesize>10M]").  This works for
-                                     filesize, height, width, tbr, abr, vbr, and
-                                     fps 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
+                                     filesize, height, width, tbr, abr, vbr,
+                                     asr, and fps and the comparisons <, <=, >,
+                                     >=, =, != and for ext, acodec, vcodec,
+                                     container, and protocol and the comparisons
+                                     =, != . Formats for which the value is not
+                                     known are excluded unless you put a
+                                     question mark (?) after the operator. You
+                                     can combine format filters, so  -f "[height
+                                     <=? 720][tbr>500]" selects up to 720p
+                                     videos (or videos where the height is not
+                                     known) with a bitrate of at least 500
+                                     KBit/s. By default, youtube-dl will pick
+                                     the best quality. Use commas to download
+                                     multiple audio formats, such as -f
                                      136/137/mp4/bestvideo,140/m4a/bestaudio.
                                      You can merge the video and audio of two
                                      formats into a single file using -f <video-
@@ -532,6 +551,14 @@ Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the opt
     youtube-dl -- -wNyEUrxzFU
     youtube-dl "http://www.youtube.com/watch?v=-wNyEUrxzFU"
 
+### Can you add support for this anime video site, or site which shows current movies for free?
+
+As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.
+
+A note on the service that they don't host the infringing content, but just link to those who do, is evidence that the service should **not** be included into youtube-dl. The same goes for any DMCA note when the whole front page of the service is filled with videos they are not allowed to distribute. A "fair use" note is equally unconvincing if the service shows copyright-protected videos in full without authorization.
+
+Support requests for services that **do** purchase the rights to distribute their content are perfectly fine though. If in doubt, you can simply include a source that mentions the legitimate purchase of content.
+
 ### How can I detect whether a given URL is supported by youtube-dl?
 
 For one, have a look at the [list of supported sites](docs/supportedsites.md). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/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.
@@ -728,7 +755,7 @@ 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?
 

devscripts/release.sh

@@ -35,7 +35,7 @@ if [ ! -z "$useless_files" ]; then echo "ERROR: Non-.py files in youtube_dl: $us
 if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi
 
 /bin/echo -e "\n### First of all, testing..."
-make cleanall
+make clean
 if $skip_tests ; then
     echo 'SKIPPING TESTS'
 else
@@ -45,9 +45,9 @@ fi
 /bin/echo -e "\n### Changing version in version.py..."
 sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
 
-/bin/echo -e "\n### Committing README.md and youtube_dl/version.py..."
-make README.md
-git add README.md youtube_dl/version.py
+/bin/echo -e "\n### Committing documentation and youtube_dl/version.py..."
+make README.md CONTRIBUTING.md supportedsites
+git add README.md CONTRIBUTING.md docs/supportedsites.md youtube_dl/version.py
 git commit -m "release $version"
 
 /bin/echo -e "\n### Now tagging, signing and pushing..."

docs/supportedsites.md

@@ -9,16 +9,21 @@
  - **8tracks**
  - **9gag**
  - **abc.net.au**
+ - **Abc7News**
  - **AcademicEarth:Course**
  - **AddAnime**
  - **AdobeTV**
  - **AdultSwim**
+ - **Aftenposten**
  - **Aftonbladet**
  - **AlJazeera**
  - **Allocine**
+ - **AlphaPorno**
  - **anitube.se**
  - **AnySex**
  - **Aparat**
+ - **AppleDailyAnimationNews**
+ - **AppleDailyRealtimeNews**
  - **AppleTrailers**
  - **archive.org**: archive.org videos
  - **ARD**
@@ -30,8 +35,10 @@
  - **arte.tv:ddc**
  - **arte.tv:embed**
  - **arte.tv:future**
+ - **AtresPlayer**
+ - **ATTTechChannel**
  - **audiomack**
- - **AUEngine**
+ - **audiomack:album**
  - **Azubu**
  - **bambuser**
  - **bambuser:channel**
@@ -71,8 +78,10 @@
  - **cmt.com**
  - **CNET**
  - **CNN**
+ - **CNNArticle**
  - **CNNBlogs**
  - **CollegeHumor**
+ - **CollegeRama**
  - **ComCarCoff**
  - **ComedyCentral**
  - **ComedyCentralShows**: The Daily Show / The Colbert Report
@@ -82,23 +91,27 @@
  - **Crunchyroll**
  - **crunchyroll:playlist**
  - **CSpan**: C-SPAN
+ - **CtsNews**
  - **culturebox.francetvinfo.fr**
  - **dailymotion**
  - **dailymotion:playlist**
  - **dailymotion:user**
  - **daum.net**
  - **DBTV**
+ - **DctpTv**
  - **DeezerPlaylist**
  - **defense.gouv.fr**
  - **Discovery**
  - **divxstage**: DivxStage
  - **Dotsub**
+ - **DRBonanza**
  - **Dropbox**
  - **DrTuber**
  - **DRTV**
  - **Dump**
  - **dvtv**: http://video.aktualne.cz/
  - **EbaumsWorld**
+ - **EchoMsk**
  - **eHow**
  - **Einthusan**
  - **eitb.tv**
@@ -108,6 +121,7 @@
  - **EMPFlix**
  - **Engadget**
  - **Eporner**
+ - **EroProfile**
  - **Escapist**
  - **EveryonesMixtape**
  - **exfm**: ex.fm
@@ -143,6 +157,7 @@
  - **GDCVault**
  - **generic**: Generic downloader that works on some sites
  - **GiantBomb**
+ - **Giga**
  - **Glide**: Glide mobile video messages (glide.me)
  - **Globo**
  - **GodTube**
@@ -153,9 +168,14 @@
  - **Grooveshark**
  - **Groupon**
  - **Hark**
+ - **HearThisAt**
  - **Heise**
+ - **HellPorno**
  - **Helsinki**: helsinki.fi
  - **HentaiStigma**
+ - **HistoricFilms**
+ - **hitbox**
+ - **hitbox:live**
  - **HornBunny**
  - **HostingBulk**
  - **HotNewHipHop**
@@ -182,6 +202,7 @@
  - **jpopsuki.tv**
  - **Jukebox**
  - **Kankan**
+ - **Karaoketv**
  - **keek**
  - **KeezMovies**
  - **KhanAcademy**
@@ -195,6 +216,7 @@
  - **LiveLeak**
  - **livestream**
  - **livestream:original**
+ - **LnkGo**
  - **lrt.lt**
  - **lynda**: lynda.com videos
  - **lynda:course**: lynda.com online courses
@@ -235,6 +257,7 @@
  - **MySpass**
  - **myvideo**
  - **MyVidster**
+ - **n-tv.de**
  - **Naver**
  - **NBA**
  - **NBC**
@@ -242,11 +265,16 @@
  - **ndr**: NDR.de - Mediathek
  - **NDTV**
  - **NerdCubedFeed**
+ - **Nerdist**
+ - **Netzkino**
  - **Newgrounds**
  - **Newstube**
+ - **NextMedia**
+ - **NextMediaActionNews**
  - **nfb**: National Film Board of Canada
  - **nfl.com**
  - **nhl.com**
+ - **nhl.com:news**: NHL news
  - **nhl.com:videocenter**: NHL videocenter category
  - **niconico**: ニコニコ動画
  - **NiconicoPlaylist**
@@ -257,18 +285,20 @@
  - **Nowness**
  - **nowvideo**: NowVideo
  - **npo.nl**
+ - **npo.nl:live**
  - **NRK**
  - **NRKTV**
- - **NTV**
+ - **ntv.ru**
  - **Nuvid**
  - **NYTimes**
  - **ocw.mit.edu**
  - **OktoberfestTV**
  - **on.aol.com**
  - **Ooyala**
+ - **OpenFilm**
+ - **orf:fm4**: radio FM4
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
- - **ORFFM4**: radio FM4
  - **parliamentlive.tv**: UK parliament videos
  - **Patreon**
  - **PBS**
@@ -290,6 +320,7 @@
  - **Pyvideo**
  - **QuickVid**
  - **radio.de**
+ - **radiobremen**
  - **radiofrance**
  - **Rai**
  - **RBMARadio**
@@ -300,6 +331,8 @@
  - **RottenTomatoes**
  - **Roxwel**
  - **RTBF**
+ - **Rte**
+ - **RTL2**
  - **RTLnow**
  - **rtlxl.nl**
  - **RTP**
@@ -309,6 +342,7 @@
  - **RUHD**
  - **rutube**: Rutube videos
  - **rutube:channel**: Rutube channels
+ - **rutube:embed**: Rutube embedded videos
  - **rutube:movie**: Rutube movies
  - **rutube:person**: Rutube person videos
  - **RUTV**: RUTV.RU
@@ -351,12 +385,14 @@
  - **Sport5**
  - **SportBox**
  - **SportDeutschland**
- - **SRMediathek**: Süddeutscher Rundfunk
+ - **SRMediathek**: Saarländischer Rundfunk
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
  - **streamcloud.eu**
  - **StreamCZ**
+ - **StreetVoice**
  - **SunPorno**
+ - **SVTPlay**
  - **SWRMediathek**
  - **Syfy**
  - **SztvHu**
@@ -375,7 +411,9 @@
  - **TeleBruxelles**
  - **telecinco.es**
  - **TeleMB**
+ - **TeleTask**
  - **TenPlay**
+ - **TestTube**
  - **TF1**
  - **TheOnion**
  - **ThePlatform**
@@ -403,8 +441,16 @@
  - **tv.dfb.de**
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvp.pl**
+ - **tvp.pl:Series**
  - **TVPlay**: TV3Play and related services
- - **Twitch**
+ - **Tweakers**
+ - **twitch:bookmarks**
+ - **twitch:chapter**
+ - **twitch:past_broadcasts**
+ - **twitch:profile**
+ - **twitch:stream**
+ - **twitch:video**
+ - **twitch:vod**
  - **Ubu**
  - **udemy**
  - **udemy:course**
@@ -433,6 +479,8 @@
  - **videoweed**: VideoWeed
  - **Vidme**
  - **Vidzi**
+ - **vier**
+ - **vier:videos**
  - **viki**
  - **vimeo**
  - **vimeo:album**
@@ -460,11 +508,13 @@
  - **WDR**
  - **wdr:mobile**
  - **WDRMaus**: Sendung mit der Maus
+ - **WebOfStories**
  - **Weibo**
  - **Wimp**
  - **Wistia**
  - **WorldStarHipHop**
  - **wrzuta.pl**
+ - **WSJ**: Wall Street Journal
  - **XBef**
  - **XboxClips**
  - **XHamster**
@@ -472,7 +522,9 @@
  - **XNXX**
  - **XTube**
  - **XTubeUser**: XTube user profile
+ - **Xuite**
  - **XVideos**
+ - **XXXYMovies**
  - **Yahoo**: Yahoo screen and movies
  - **YesJapan**
  - **Ynet**
@@ -491,7 +543,6 @@
  - **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**

test/helper.py

@@ -103,6 +103,16 @@ def expect_info_dict(self, got_dict, expected_dict):
             self.assertTrue(
                 match_rex.match(got),
                 'field %s (value: %r) should match %r' % (info_field, got, match_str))
+        elif isinstance(expected, compat_str) and expected.startswith('startswith:'):
+            got = got_dict.get(info_field)
+            start_str = expected[len('startswith:'):]
+            self.assertTrue(
+                isinstance(got, compat_str),
+                'Expected a %s object, but got %s for field %s' % (
+                    compat_str.__name__, type(got).__name__, info_field))
+            self.assertTrue(
+                got.startswith(start_str),
+                'field %s (value: %r) should start with %r' % (info_field, got, start_str))
         elif isinstance(expected, type):
             got = got_dict.get(info_field)
             self.assertTrue(isinstance(got, expected),

test/test_YoutubeDL.py

@@ -13,6 +13,7 @@ import copy
 from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
 from youtube_dl.extractor import YoutubeIE
+from youtube_dl.postprocessor.common import PostProcessor
 
 
 class YDL(FakeYDL):
@@ -370,5 +371,35 @@ class TestFormatSelection(unittest.TestCase):
             'vbr': 10,
         }), '^\s*10k$')
 
+    def test_postprocessors(self):
+        filename = 'post-processor-testfile.mp4'
+        audiofile = filename + '.mp3'
+
+        class SimplePP(PostProcessor):
+            def run(self, info):
+                with open(audiofile, 'wt') as f:
+                    f.write('EXAMPLE')
+                info['filepath']
+                return False, info
+
+        def run_pp(params):
+            with open(filename, 'wt') as f:
+                f.write('EXAMPLE')
+            ydl = YoutubeDL(params)
+            ydl.add_post_processor(SimplePP())
+            ydl.post_process(filename, {'filepath': filename})
+
+        run_pp({'keepvideo': True})
+        self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
+        self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
+        os.unlink(filename)
+        os.unlink(audiofile)
+
+        run_pp({'keepvideo': False})
+        self.assertFalse(os.path.exists(filename), '%s exists' % filename)
+        self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
+        os.unlink(audiofile)
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -53,6 +53,7 @@ from youtube_dl.utils import (
     version_tuple,
     xpath_with_ns,
     render_table,
+    match_str,
 )
 
 
@@ -156,6 +157,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(
             unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
             '20141126')
+        self.assertEqual(
+            unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
+            '20150202')
 
     def test_find_xpath_attr(self):
         testxml = '''<root>
@@ -456,6 +460,37 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
             '123  4\n'
             '9999 51')
 
+    def test_match_str(self):
+        self.assertRaises(ValueError, match_str, 'xy>foobar', {})
+        self.assertFalse(match_str('xy', {'x': 1200}))
+        self.assertTrue(match_str('!xy', {'x': 1200}))
+        self.assertTrue(match_str('x', {'x': 1200}))
+        self.assertFalse(match_str('!x', {'x': 1200}))
+        self.assertTrue(match_str('x', {'x': 0}))
+        self.assertFalse(match_str('x>0', {'x': 0}))
+        self.assertFalse(match_str('x>0', {}))
+        self.assertTrue(match_str('x>?0', {}))
+        self.assertTrue(match_str('x>1K', {'x': 1200}))
+        self.assertFalse(match_str('x>2K', {'x': 1200}))
+        self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
+        self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
+        self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
+        self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
+        self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
+        self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
+        self.assertFalse(match_str(
+            'like_count > 100 & dislike_count <? 50 & description',
+            {'like_count': 90, 'description': 'foo'}))
+        self.assertTrue(match_str(
+            'like_count > 100 & dislike_count <? 50 & description',
+            {'like_count': 190, 'description': 'foo'}))
+        self.assertFalse(match_str(
+            'like_count > 100 & dislike_count <? 50 & description',
+            {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
+        self.assertFalse(match_str(
+            'like_count > 100 & dislike_count <? 50 & description',
+            {'like_count': 190, 'dislike_count': 10}))
+
 
 if __name__ == '__main__':
     unittest.main()

youtube_dl/YoutubeDL.py

@@ -228,6 +228,11 @@ class YoutubeDL(object):
     external_downloader:  Executable of the external downloader to call.
     listformats:       Print an overview of available video formats and exit.
     list_thumbnails:   Print a table of all thumbnails and exit.
+    match_filter:      A function that gets called with the info_dict of
+                       every video.
+                       If it returns a message, the video is ignored.
+                       If it returns None, the video is downloaded.
+                       match_filter_func in utils.py is one example for this.
 
 
     The following parameters are not used by YoutubeDL itself, they are used by
@@ -583,9 +588,16 @@ class YoutubeDL(object):
             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)
         if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')):
-            return 'Skipping "%s" because it is age restricted' % title
+            return 'Skipping "%s" because it is age restricted' % video_title
         if self.in_download_archive(info_dict):
             return '%s has already been recorded in archive' % video_title
+
+        match_filter = self.params.get('match_filter')
+        if match_filter is not None:
+            ret = match_filter(info_dict)
+            if ret is not None:
+                return ret
+
         return None
 
     @staticmethod
@@ -826,27 +838,44 @@ class YoutubeDL(object):
             '!=': operator.ne,
         }
         operator_rex = re.compile(r'''(?x)\s*\[
-            (?P<key>width|height|tbr|abr|vbr|filesize|fps)
+            (?P<key>width|height|tbr|abr|vbr|asr|filesize|fps)
             \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
             (?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)
             \]$
             ''' % '|'.join(map(re.escape, OPERATORS.keys())))
         m = operator_rex.search(format_spec)
+        if m:
+            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')]
+
+        if not m:
+            STR_OPERATORS = {
+                '=': operator.eq,
+                '!=': operator.ne,
+            }
+            str_operator_rex = re.compile(r'''(?x)\s*\[
+                \s*(?P<key>ext|acodec|vcodec|container|protocol)
+                \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
+                \s*(?P<value>[a-zA-Z0-9_-]+)
+                \s*\]$
+                ''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
+            m = str_operator_rex.search(format_spec)
+            if m:
+                comparison_value = m.group('value')
+                op = STR_OPERATORS[m.group('op')]
+
         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:
@@ -938,6 +967,9 @@ class YoutubeDL(object):
             def has_header(self, h):
                 return h in self.headers
 
+            def get_header(self, h, default=None):
+                return self.headers.get(h, default)
+
         pr = _PseudoRequest(info_dict['url'])
         self.cookiejar.add_cookie_header(pr)
         return pr.headers.get('Cookie')
@@ -964,9 +996,11 @@ class YoutubeDL(object):
             thumbnails.sort(key=lambda t: (
                 t.get('preference'), t.get('width'), t.get('height'),
                 t.get('id'), t.get('url')))
-            for t in thumbnails:
+            for i, t in enumerate(thumbnails):
                 if 'width' in t and 'height' in t:
                     t['resolution'] = '%dx%d' % (t['width'], t['height'])
+                if t.get('id') is None:
+                    t['id'] = '%d' % i
 
         if thumbnails and 'thumbnail' not in info_dict:
             info_dict['thumbnail'] = thumbnails[-1]['url']
@@ -1074,7 +1108,8 @@ class YoutubeDL(object):
                                 else self.params['merge_output_format'])
                             selected_format = {
                                 'requested_formats': formats_info,
-                                'format': rf,
+                                'format': '%s+%s' % (formats_info[0].get('format'),
+                                                     formats_info[1].get('format')),
                                 'format_id': '%s+%s' % (formats_info[0].get('format_id'),
                                                         formats_info[1].get('format_id')),
                                 'width': formats_info[0].get('width'),
@@ -1523,7 +1558,6 @@ class YoutubeDL(object):
             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)'
 
         header_line = line({

youtube_dl/__init__.py

@@ -23,9 +23,10 @@ from .compat import (
 )
 from .utils import (
     DateRange,
-    DEFAULT_OUTTMPL,
     decodeOption,
+    DEFAULT_OUTTMPL,
     DownloadError,
+    match_filter_func,
     MaxDownloadsReached,
     preferredencoding,
     read_batch_urls,
@@ -247,6 +248,9 @@ def _real_main(argv=None):
             xattr  # Confuse flake8
         except ImportError:
             parser.error('setting filesize xattr requested but python-xattr is not available')
+    match_filter = (
+        None if opts.match_filter is None
+        else match_filter_func(opts.match_filter))
 
     ydl_opts = {
         'usenetrc': opts.usenetrc,
@@ -344,6 +348,7 @@ def _real_main(argv=None):
         'list_thumbnails': opts.list_thumbnails,
         'playlist_items': opts.playlist_items,
         'xattr_set_filesize': opts.xattr_set_filesize,
+        'match_filter': match_filter,
     }
 
     with YoutubeDL(ydl_opts) as ydl:

youtube_dl/extractor/__init__.py

@@ -6,6 +6,7 @@ from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
 from .adobetv import AdobeTVIE
 from .adultswim import AdultSwimIE
+from .aftenposten import AftenpostenIE
 from .aftonbladet import AftonbladetIE
 from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
@@ -73,7 +74,7 @@ from .collegehumor import CollegeHumorIE
 from .collegerama import CollegeRamaIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .comcarcoff import ComCarCoffIE
-from .commonmistakes import CommonMistakesIE
+from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
 from .condenast import CondeNastIE
 from .cracked import CrackedIE
 from .criterion import CriterionIE
@@ -285,6 +286,7 @@ from .ndr import NDRIE
 from .ndtv import NDTVIE
 from .netzkino import NetzkinoIE
 from .nerdcubed import NerdCubedFeedIE
+from .nerdist import NerdistIE
 from .newgrounds import NewgroundsIE
 from .newstube import NewstubeIE
 from .nextmedia import (
@@ -426,6 +428,7 @@ from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
 from .streetvoice import StreetVoiceIE
 from .sunporno import SunPornoIE
+from .svtplay import SVTPlayIE
 from .swrmediathek import SWRMediathekIE
 from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
@@ -474,6 +477,7 @@ from .tutv import TutvIE
 from .tvigle import TvigleIE
 from .tvp import TvpIE, TvpSeriesIE
 from .tvplay import TVPlayIE
+from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
 from .twitch import (
     TwitchVideoIE,
@@ -553,6 +557,7 @@ from .wimp import WimpIE
 from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
 from .wrzuta import WrzutaIE
+from .wsj import WSJIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
 from .xhamster import XHamsterIE

youtube_dl/extractor/aftenposten.py

@@ -0,0 +1,103 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+    xpath_with_ns,
+    xpath_text,
+    find_xpath_attr,
+)
+
+
+class AftenpostenIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/([^/]+/)*(?P<id>[^/]+)-\d+\.html'
+
+    _TEST = {
+        'url': 'http://www.aftenposten.no/webtv/serier-og-programmer/sweatshopenglish/TRAILER-SWEATSHOP---I-cant-take-any-more-7800835.html?paging=&section=webtv_serierogprogrammer_sweatshop_sweatshopenglish',
+        'md5': 'fd828cd29774a729bf4d4425fe192972',
+        'info_dict': {
+            'id': '21039',
+            'ext': 'mov',
+            'title': 'TRAILER: "Sweatshop" - I can´t take any more',
+            'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238',
+            'timestamp': 1416927969,
+            'upload_date': '20141125',
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._html_search_regex(
+            r'data-xs-id="(\d+)"', webpage, 'video id')
+
+        data = self._download_xml(
+            'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=%s' % video_id, video_id)
+
+        NS_MAP = {
+            'atom': 'http://www.w3.org/2005/Atom',
+            'xt': 'http://xstream.dk/',
+            'media': 'http://search.yahoo.com/mrss/',
+        }
+
+        entry = data.find(xpath_with_ns('./atom:entry', NS_MAP))
+
+        title = xpath_text(
+            entry, xpath_with_ns('./atom:title', NS_MAP), 'title')
+        description = xpath_text(
+            entry, xpath_with_ns('./atom:summary', NS_MAP), 'description')
+        timestamp = parse_iso8601(xpath_text(
+            entry, xpath_with_ns('./atom:published', NS_MAP), 'upload date'))
+
+        formats = []
+        media_group = entry.find(xpath_with_ns('./media:group', NS_MAP))
+        for media_content in media_group.findall(xpath_with_ns('./media:content', NS_MAP)):
+            media_url = media_content.get('url')
+            if not media_url:
+                continue
+            tbr = int_or_none(media_content.get('bitrate'))
+            mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', media_url)
+            if mobj:
+                formats.append({
+                    'url': mobj.group('url'),
+                    'play_path': 'mp4:%s' % mobj.group('playpath'),
+                    'app': mobj.group('app'),
+                    'ext': 'flv',
+                    'tbr': tbr,
+                    'format_id': 'rtmp-%d' % tbr,
+                })
+            else:
+                formats.append({
+                    'url': media_url,
+                    'tbr': tbr,
+                })
+        self._sort_formats(formats)
+
+        link = find_xpath_attr(
+            entry, xpath_with_ns('./atom:link', NS_MAP), 'rel', 'original')
+        if link is not None:
+            formats.append({
+                'url': link.get('href'),
+                'format_id': link.get('rel'),
+            })
+
+        thumbnails = [{
+            'url': splash.get('url'),
+            'width': int_or_none(splash.get('width')),
+            'height': int_or_none(splash.get('height')),
+        } for splash in media_group.findall(xpath_with_ns('./xt:splash', NS_MAP))]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
+            'formats': formats,
+            'thumbnails': thumbnails,
+        }

youtube_dl/extractor/aftonbladet.py

@@ -1,8 +1,6 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -21,9 +19,7 @@ class AftonbladetIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.search(self._VALID_URL, url)
-
-        video_id = mobj.group('video_id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         # find internal video meta data

youtube_dl/extractor/aparat.py

@@ -20,6 +20,7 @@ class AparatIE(InfoExtractor):
             'id': 'wP8On',
             'ext': 'mp4',
             'title': 'تیم گلکسی 11 - زومیت',
+            'age_limit': 0,
         },
         # 'skip': 'Extremely unreliable',
     }
@@ -34,7 +35,8 @@ class AparatIE(InfoExtractor):
                      video_id + '/vt/frame')
         webpage = self._download_webpage(embed_url, video_id)
 
-        video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage)
+        video_urls = [video_url.replace('\\/', '/') for video_url in re.findall(
+            r'(?:fileList\[[0-9]+\]\s*=|"file"\s*:)\s*"([^"]+)"', webpage)]
         for i, video_url in enumerate(video_urls):
             req = HEADRequest(video_url)
             res = self._request_webpage(
@@ -46,7 +48,7 @@ class AparatIE(InfoExtractor):
 
         title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title')
         thumbnail = self._search_regex(
-            r'\s+image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
+            r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
 
         return {
             'id': video_id,
@@ -54,4 +56,5 @@ class AparatIE(InfoExtractor):
             'url': video_url,
             'ext': 'mp4',
             'thumbnail': thumbnail,
+            'age_limit': self._family_friendly_search(webpage),
         }

youtube_dl/extractor/bandcamp.py

@@ -72,26 +72,29 @@ class BandcampIE(InfoExtractor):
 
         download_link = m_download.group(1)
         video_id = self._search_regex(
-            r'var TralbumData = {.*?id: (?P<id>\d+),?$',
-            webpage, 'video id', flags=re.MULTILINE | re.DOTALL)
+            r'(?ms)var TralbumData = {.*?id: (?P<id>\d+),?$',
+            webpage, 'video id')
 
         download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
         # We get the dictionary of the track from some javascript code
-        info = re.search(r'items: (.*?),$', download_webpage, re.MULTILINE).group(1)
-        info = json.loads(info)[0]
+        all_info = self._parse_json(self._search_regex(
+            r'(?sm)items: (.*?),$', download_webpage, 'items'), video_id)
+        info = all_info[0]
         # We pick mp3-320 for now, until format selection can be easily implemented.
         mp3_info = info['downloads']['mp3-320']
         # If we try to use this url it says the link has expired
         initial_url = mp3_info['url']
-        re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
-        m_url = re.match(re_url, initial_url)
+        m_url = re.match(
+            r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$',
+            initial_url)
         # We build the url we will use to get the final track url
         # This url is build in Bandcamp in the script download_bunde_*.js
         request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
         final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
         # If we could correctly generate the .rand field the url would be
         # in the "download_url" key
-        final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
+        final_url = self._search_regex(
+            r'"retry_url":"(.*?)"', final_url_webpage, 'final video URL')
 
         return {
             'id': video_id,

youtube_dl/extractor/brightcove.py

@@ -108,7 +108,7 @@ class BrightcoveIE(InfoExtractor):
         """
 
         # Fix up some stupid HTML, see https://github.com/rg3/youtube-dl/issues/1553
-        object_str = re.sub(r'(<param name="[^"]+" value="[^"]+")>',
+        object_str = re.sub(r'(<param(?:\s+[a-zA-Z0-9_]+="[^"]*")*)>',
                             lambda m: m.group(1) + '/>', object_str)
         # Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608
         object_str = object_str.replace('<--', '<!--')

youtube_dl/extractor/common.py

@@ -145,6 +145,7 @@ class InfoExtractor(object):
     thumbnail:      Full URL to a video thumbnail image.
     description:    Full video description.
     uploader:       Full name of the video uploader.
+    creator:        The main artist who created the video.
     timestamp:      UNIX timestamp of the moment the video became available.
     upload_date:    Video upload date (YYYYMMDD).
                     If not explicitly set, calculated from timestamp.
@@ -263,8 +264,15 @@ class InfoExtractor(object):
 
     def extract(self, url):
         """Extracts URL information and returns it in list of dicts."""
-        self.initialize()
-        return self._real_extract(url)
+        try:
+            self.initialize()
+            return self._real_extract(url)
+        except ExtractorError:
+            raise
+        except compat_http_client.IncompleteRead as e:
+            raise ExtractorError('A network error has occured.', cause=e, expected=True)
+        except (KeyError,) as e:
+            raise ExtractorError('An extractor error has occured.', cause=e)
 
     def set_downloader(self, downloader):
         """Sets the downloader for this IE."""
@@ -655,6 +663,21 @@ class InfoExtractor(object):
         }
         return RATING_TABLE.get(rating.lower(), None)
 
+    def _family_friendly_search(self, html):
+        # See http://schema.org/VideoObj
+        family_friendly = self._html_search_meta('isFamilyFriendly', html)
+
+        if not family_friendly:
+            return None
+
+        RATING_TABLE = {
+            '1': 0,
+            'true': 0,
+            '0': 18,
+            'false': 18,
+        }
+        return RATING_TABLE.get(family_friendly.lower(), None)
+
     def _twitter_search_player(self, html):
         return self._html_search_meta('twitter:player', html,
                                       'twitter card player')
@@ -704,11 +727,11 @@ class InfoExtractor(object):
                 preference,
                 f.get('language_preference') if f.get('language_preference') is not None else -1,
                 f.get('quality') if f.get('quality') is not None else -1,
+                f.get('tbr') if f.get('tbr') is not None else -1,
+                f.get('vbr') if f.get('vbr') is not None else -1,
                 f.get('height') if f.get('height') is not None else -1,
                 f.get('width') if f.get('width') is not None else -1,
                 ext_preference,
-                f.get('tbr') if f.get('tbr') is not None else -1,
-                f.get('vbr') if f.get('vbr') is not None else -1,
                 f.get('abr') if f.get('abr') is not None else -1,
                 audio_ext_preference,
                 f.get('fps') if f.get('fps') is not None else -1,
@@ -764,7 +787,7 @@ class InfoExtractor(object):
         self.to_screen(msg)
         time.sleep(timeout)
 
-    def _extract_f4m_formats(self, manifest_url, video_id):
+    def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None):
         manifest = self._download_xml(
             manifest_url, video_id, 'Downloading f4m manifest',
             'Unable to download f4m manifest')
@@ -777,26 +800,28 @@ class InfoExtractor(object):
             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')
+                manifest_url = ('/'.join(manifest_url.split('/')[:-1]) + '/'
+                                + (media_el.attrib.get('href') or media_el.attrib.get('url')))
             tbr = int_or_none(media_el.attrib.get('bitrate'))
-            format_id = 'f4m-%d' % (i if tbr is None else tbr)
             formats.append({
-                'format_id': format_id,
+                'format_id': '-'.join(filter(None, [f4m_id, 'f4m-%d' % (i if tbr is None else tbr)])),
                 'url': manifest_url,
                 'ext': 'flv',
                 'tbr': tbr,
                 'width': int_or_none(media_el.attrib.get('width')),
                 'height': int_or_none(media_el.attrib.get('height')),
+                'preference': preference,
             })
         self._sort_formats(formats)
 
         return formats
 
     def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
-                              entry_protocol='m3u8', preference=None):
+                              entry_protocol='m3u8', preference=None,
+                              m3u8_id=None):
 
         formats = [{
-            'format_id': 'm3u8-meta',
+            'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-meta'])),
             'url': m3u8_url,
             'ext': ext,
             'protocol': 'm3u8',
@@ -832,9 +857,8 @@ class InfoExtractor(object):
                     formats.append({'url': format_url(line)})
                     continue
                 tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
-
                 f = {
-                    'format_id': 'm3u8-%d' % (tbr if tbr else len(formats)),
+                    'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-%d' % (tbr if tbr else len(formats))])),
                     'url': format_url(line.strip()),
                     'tbr': tbr,
                     'ext': ext,
@@ -860,10 +884,13 @@ class InfoExtractor(object):
         return formats
 
     # TODO: improve extraction
-    def _extract_smil_formats(self, smil_url, video_id):
+    def _extract_smil_formats(self, smil_url, video_id, fatal=True):
         smil = self._download_xml(
             smil_url, video_id, 'Downloading SMIL file',
-            'Unable to download SMIL file')
+            'Unable to download SMIL file', fatal=fatal)
+        if smil is False:
+            assert not fatal
+            return []
 
         base = smil.find('./head/meta').get('base')
 

youtube_dl/extractor/commonmistakes.py

@@ -24,6 +24,23 @@ class CommonMistakesIE(InfoExtractor):
             'That doesn\'t make any sense. '
             'Simply remove the parameter in your command or configuration.'
         ) % url
-        if self._downloader.params.get('verbose'):
+        if not 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)
+
+
+class UnicodeBOMIE(InfoExtractor):
+        IE_DESC = False
+        _VALID_URL = r'(?P<bom>\ufeff)(?P<id>.*)$'
+
+        _TESTS = [{
+            'url': '\ufeffhttp://www.youtube.com/watch?v=BaW_jenozKc',
+            'only_matching': True,
+        }]
+
+        def _real_extract(self, url):
+            real_url = self._match_id(url)
+            self.report_warning(
+                'Your URL starts with a Byte Order Mark (BOM). '
+                'Removing the BOM and looking for "%s" ...' % real_url)
+            return self.url_result(real_url)

youtube_dl/extractor/franceculture.py

@@ -1,77 +1,69 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
-import re
-
 from .common import InfoExtractor
 from ..compat import (
-    compat_parse_qs,
     compat_urlparse,
 )
+from ..utils import (
+    determine_ext,
+    int_or_none,
+)
 
 
 class FranceCultureIE(InfoExtractor):
-    _VALID_URL = r'(?P<baseurl>http://(?:www\.)?franceculture\.fr/)player/reecouter\?play=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.franceculture.fr/player/reecouter?play=4795174',
         'info_dict': {
             'id': '4795174',
             'ext': 'mp3',
             'title': 'Rendez-vous au pays des geeks',
+            'alt_title': 'Carnet nomade | 13-14',
             'vcodec': 'none',
-            'uploader': 'Colette Fellous',
             'upload_date': '20140301',
-            'duration': 3601,
             'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
-            'description': 'Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats-Unis dans la S ...',
+            'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats',
+            'timestamp': 1393700400,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        baseurl = mobj.group('baseurl')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        params_code = self._search_regex(
-            r"<param name='movie' value='/sites/all/modules/rf/rf_player/swf/loader.swf\?([^']+)' />",
-            webpage, 'parameter code')
-        params = compat_parse_qs(params_code)
-        video_url = compat_urlparse.urljoin(baseurl, params['urlAOD'][0])
+
+        video_path = self._search_regex(
+            r'<a id="player".*?href="([^"]+)"', webpage, 'video path')
+        video_url = compat_urlparse.urljoin(url, video_path)
+        timestamp = int_or_none(self._search_regex(
+            r'<a id="player".*?data-date="([0-9]+)"',
+            webpage, 'upload date', fatal=False))
+        thumbnail = self._search_regex(
+            r'<a id="player".*?>\s+<img src="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
 
         title = self._html_search_regex(
-            r'<h1 class="title[^"]+">(.+?)</h1>', webpage, 'title')
+            r'<span class="title-diffusion">(.*?)</span>', webpage, 'title')
+        alt_title = self._html_search_regex(
+            r'<span class="title">(.*?)</span>',
+            webpage, 'alt_title', fatal=False)
+        description = self._html_search_regex(
+            r'<span class="description">(.*?)</span>',
+            webpage, 'description', fatal=False)
+
         uploader = self._html_search_regex(
             r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
-            webpage, 'uploader', fatal=False)
-        thumbnail_part = self._html_search_regex(
-            r'(?s)<div id="emission".*?<img src="([^"]+)"', webpage,
-            'thumbnail', fatal=False)
-        if thumbnail_part is None:
-            thumbnail = None
-        else:
-            thumbnail = compat_urlparse.urljoin(baseurl, thumbnail_part)
-        description = self._html_search_regex(
-            r'(?s)<p class="desc">(.*?)</p>', webpage, 'description')
-
-        info = json.loads(params['infoData'][0])[0]
-        duration = info.get('media_length')
-        upload_date_candidate = info.get('media_section5')
-        upload_date = (
-            upload_date_candidate
-            if (upload_date_candidate is not None and
-                re.match(r'[0-9]{8}$', upload_date_candidate))
-            else None)
+            webpage, 'uploader', default=None)
+        vcodec = 'none' if determine_ext(video_url.lower()) == 'mp3' else None
 
         return {
             'id': video_id,
             'url': video_url,
-            'vcodec': 'none' if video_url.lower().endswith('.mp3') else None,
-            'duration': duration,
+            'vcodec': vcodec,
             'uploader': uploader,
-            'upload_date': upload_date,
+            'timestamp': timestamp,
             'title': title,
+            'alt_title': alt_title,
             'thumbnail': thumbnail,
             'description': description,
         }

youtube_dl/extractor/gamekings.py

@@ -1,41 +1,67 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..utils import (
+    xpath_text,
+    xpath_with_ns,
+)
 
 
 class GamekingsIE(InfoExtractor):
-    _VALID_URL = r'http://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)'
-    _TEST = {
+    _VALID_URL = r'http://www\.gamekings\.tv/(?:videos|nieuws)/(?P<id>[^/]+)'
+    _TESTS = [{
         'url': 'http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/',
         # MD5 is flaky, seems to change regularly
         # 'md5': '2f32b1f7b80fdc5cb616efb4f387f8a3',
         'info_dict': {
-            'id': '20130811',
+            'id': 'phoenix-wright-ace-attorney-dual-destinies-review',
             'ext': 'mp4',
             'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review',
             'description': 'md5:36fd701e57e8c15ac8682a2374c99731',
-        }
-    }
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }, {
+        # vimeo video
+        'url': 'http://www.gamekings.tv/videos/the-legend-of-zelda-majoras-mask/',
+        'md5': '12bf04dfd238e70058046937657ea68d',
+        'info_dict': {
+            'id': 'the-legend-of-zelda-majoras-mask',
+            'ext': 'mp4',
+            'title': 'The Legend of Zelda: Majora’s Mask',
+            'description': 'md5:9917825fe0e9f4057601fe1e38860de3',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.gamekings.tv/nieuws/gamekings-extra-shelly-en-david-bereiden-zich-voor-op-de-livestream/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
+        video_id = self._match_id(url)
 
-        mobj = re.match(self._VALID_URL, url)
-        name = mobj.group('name')
-        webpage = self._download_webpage(url, name)
-        video_url = self._og_search_video_url(webpage)
+        webpage = self._download_webpage(url, video_id)
 
-        video = re.search(r'[0-9]+', video_url)
-        video_id = video.group(0)
+        playlist_id = self._search_regex(
+            r'gogoVideo\(\s*\d+\s*,\s*"([^"]+)', webpage, 'playlist id')
 
-        # Todo: add medium format
-        video_url = video_url.replace(video_id, 'large/' + video_id)
+        playlist = self._download_xml(
+            'http://www.gamekings.tv/wp-content/themes/gk2010/rss_playlist.php?id=%s' % playlist_id,
+            video_id)
+
+        NS_MAP = {
+            'jwplayer': 'http://rss.jwpcdn.com/'
+        }
+
+        item = playlist.find('./channel/item')
+
+        thumbnail = xpath_text(item, xpath_with_ns('./jwplayer:image', NS_MAP), 'thumbnail')
+        video_url = item.find(xpath_with_ns('./jwplayer:source', NS_MAP)).get('file')
 
         return {
             'id': video_id,
-            'ext': 'mp4',
             'url': video_url,
             'title': self._og_search_title(webpage),
             'description': self._og_search_description(webpage),
+            'thumbnail': thumbnail,
         }

youtube_dl/extractor/generic.py

@@ -140,6 +140,19 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Ooyala'],
         },
+        # multiple ooyala embeds on SBN network websites
+        {
+            'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
+            'info_dict': {
+                'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
+                'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
+            },
+            'playlist_mincount': 3,
+            'params': {
+                'skip_download': True,
+            },
+            'add_ie': ['Ooyala'],
+        },
         # google redirect
         {
             'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
@@ -511,6 +524,19 @@ class GenericIE(InfoExtractor):
                 'upload_date': '20150126',
             },
             'add_ie': ['Viddler'],
+        },
+        # jwplayer YouTube
+        {
+            'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
+            'info_dict': {
+                'id': 'Mrj4DVp2zeA',
+                'ext': 'mp4',
+                'upload_date': '20150204',
+                'uploader': 'The National Archives UK',
+                'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
+                'uploader_id': 'NationalArchives08',
+                'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
+            },
         }
     ]
 
@@ -882,10 +908,19 @@ class GenericIE(InfoExtractor):
 
         # Look for Ooyala videos
         mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
-                re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage))
+                re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
+                re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage))
         if mobj is not None:
             return OoyalaIE._build_url_result(mobj.group('ec'))
 
+        # Look for multiple Ooyala embeds on SBN network websites
+        mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
+        if mobj is not None:
+            embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
+            if embeds:
+                return _playlist_from_matches(
+                    embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
+
         # Look for Aparat videos
         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
         if mobj is not None:
@@ -1012,7 +1047,12 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded sbs.com.au player
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)sbs\.com\.au/ondemand/video/single/.+?)\1',
+            r'''(?x)
+            (?:
+                <meta\s+property="og:video"\s+content=|
+                <iframe[^>]+?src=
+            )
+            (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
             webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'SBS')
@@ -1043,6 +1083,8 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'), 'Livestream')
 
         def check_video(vurl):
+            if YoutubeIE.suitable(vurl):
+                return True
             vpath = compat_urlparse.urlparse(vurl).path
             vext = determine_ext(vpath)
             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
@@ -1060,7 +1102,8 @@ class GenericIE(InfoExtractor):
                     JWPlayerOptions|
                     jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
                 )
-                .*?file\s*:\s*["\'](.*?)["\']''', webpage))
+                .*?
+                ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
         if not found:
             # Broaden the search a little bit
             found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))

youtube_dl/extractor/goshgay.py

@@ -34,8 +34,6 @@ class GoshgayIE(InfoExtractor):
         duration = parse_duration(self._html_search_regex(
             r'<span class="duration">\s*-?\s*(.*?)</span>',
             webpage, 'duration', fatal=False))
-        family_friendly = self._html_search_meta(
-            'isFamilyFriendly', webpage, default='false')
 
         flashvars = compat_parse_qs(self._html_search_regex(
             r'<embed.+?id="flash-player-embed".+?flashvars="([^"]+)"',
@@ -49,5 +47,5 @@ class GoshgayIE(InfoExtractor):
             'title': title,
             'thumbnail': thumbnail,
             'duration': duration,
-            'age_limit': 0 if family_friendly == 'true' else 18,
+            'age_limit': self._family_friendly_search(webpage),
         }

youtube_dl/extractor/izlesene.py

@@ -80,9 +80,6 @@ class IzleseneIE(InfoExtractor):
             r'comment_count\s*=\s*\'([^\']+)\';',
             webpage, 'comment_count', fatal=False)
 
-        family_friendly = self._html_search_meta(
-            'isFamilyFriendly', webpage, 'age limit', fatal=False)
-
         content_url = self._html_search_meta(
             'contentURL', webpage, 'content URL', fatal=False)
         ext = determine_ext(content_url, 'mp4')
@@ -120,6 +117,6 @@ class IzleseneIE(InfoExtractor):
             'duration': duration,
             'view_count': int_or_none(view_count),
             'comment_count': int_or_none(comment_count),
-            'age_limit': 18 if family_friendly == 'False' else 0,
+            'age_limit': self._family_friendly_search(webpage),
             'formats': formats,
         }

youtube_dl/extractor/mixcloud.py

@@ -18,7 +18,7 @@ class MixcloudIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
     IE_NAME = 'mixcloud'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
         'info_dict': {
             'id': 'dholbach-cryptkeeper',
@@ -33,7 +33,20 @@ class MixcloudIE(InfoExtractor):
             'view_count': int,
             'like_count': int,
         },
-    }
+    }, {
+        'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
+        'info_dict': {
+            'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
+            'ext': 'm4a',
+            'title': 'Electric Relaxation vol. 3',
+            'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
+            'uploader': 'Daniel Drumz',
+            'uploader_id': 'gillespeterson',
+            'thumbnail': 're:https?://.*\.jpg',
+            'view_count': int,
+            'like_count': int,
+        },
+    }]
 
     def _get_url(self, track_id, template_url):
         server_count = 30
@@ -60,7 +73,7 @@ class MixcloudIE(InfoExtractor):
         webpage = self._download_webpage(url, track_id)
 
         preview_url = self._search_regex(
-            r'\s(?:data-preview-url|m-preview)="(.+?)"', webpage, 'preview url')
+            r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')
         song_url = preview_url.replace('/previews/', '/c/originals/')
         template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
         final_song_url = self._get_url(track_id, template_url)

youtube_dl/extractor/nerdist.py

@@ -0,0 +1,80 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+from ..utils import (
+    determine_ext,
+    parse_iso8601,
+    xpath_text,
+)
+
+
+class NerdistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nerdist\.com/vepisode/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'http://www.nerdist.com/vepisode/exclusive-which-dc-characters-w',
+        'md5': '3698ed582931b90d9e81e02e26e89f23',
+        'info_dict': {
+            'display_id': 'exclusive-which-dc-characters-w',
+            'id': 'RPHpvJyr',
+            'ext': 'mp4',
+            'title': 'Your TEEN TITANS Revealed! Who\'s on the show?',
+            'thumbnail': 're:^https?://.*/thumbs/.*\.jpg$',
+            'description': 'Exclusive: Find out which DC Comics superheroes will star in TEEN TITANS Live-Action TV Show on Nerdist News with Jessica Chobot!',
+            'uploader': 'Eric Diaz',
+            'upload_date': '20150202',
+            'timestamp': 1422892808,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            r'''(?x)<script\s+(?:type="text/javascript"\s+)?
+                src="https?://content\.nerdist\.com/players/([a-zA-Z0-9_]+)-''',
+            webpage, 'video ID')
+        timestamp = parse_iso8601(self._html_search_meta(
+            'shareaholic:article_published_time', webpage, 'upload date'))
+        uploader = self._html_search_meta(
+            'shareaholic:article_author_name', webpage, 'article author')
+
+        doc = self._download_xml(
+            'http://content.nerdist.com/jw6/%s.xml' % video_id, video_id)
+        video_info = doc.find('.//item')
+        title = xpath_text(video_info, './title', fatal=True)
+        description = xpath_text(video_info, './description')
+        thumbnail = xpath_text(
+            video_info, './{http://rss.jwpcdn.com/}image', 'thumbnail')
+
+        formats = []
+        for source in video_info.findall('./{http://rss.jwpcdn.com/}source'):
+            vurl = source.attrib['file']
+            ext = determine_ext(vurl)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    vurl, video_id, entry_protocol='m3u8_native', ext='mp4',
+                    preference=0))
+            elif ext == 'smil':
+                formats.extend(self._extract_smil_formats(
+                    vurl, video_id, fatal=False
+                ))
+            else:
+                formats.append({
+                    'format_id': ext,
+                    'url': vurl,
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'formats': formats,
+            'uploader': uploader,
+        }

youtube_dl/extractor/nfl.py

@@ -46,7 +46,18 @@ class NFLIE(InfoExtractor):
                 'timestamp': 1388354455,
                 'thumbnail': 're:^https?://.*\.jpg$',
             }
-        }
+        },
+        {
+            'url': 'http://www.nfl.com/news/story/0ap3000000467586/article/patriots-seahawks-involved-in-lategame-skirmish',
+            'info_dict': {
+                'id': '0ap3000000467607',
+                'ext': 'mp4',
+                'title': 'Frustrations flare on the field',
+                'description': 'Emotions ran high at the end of the Super Bowl on both sides of the ball after a dramatic finish.',
+                'timestamp': 1422850320,
+                'upload_date': '20150202',
+            },
+        },
     ]
 
     @staticmethod
@@ -80,7 +91,11 @@ class NFLIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         config_url = NFLIE.prepend_host(host, self._search_regex(
-            r'(?:config|configURL)\s*:\s*"([^"]+)"', webpage, 'config URL'))
+            r'(?:config|configURL)\s*:\s*"([^"]+)"', webpage, 'config URL',
+            default='static/content/static/config/video/config.json'))
+        # For articles, the id in the url is not the video id
+        video_id = self._search_regex(
+            r'contentId\s*:\s*"([^"]+)"', webpage, 'video id', default=video_id)
         config = self._download_json(config_url, video_id,
                                      note='Downloading player config')
         url_template = NFLIE.prepend_host(

youtube_dl/extractor/normalboots.py

@@ -1,8 +1,6 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 from ..utils import (
@@ -11,7 +9,7 @@ from ..utils import (
 
 
 class NormalbootsIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$'
+    _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<id>[0-9a-z-]*)/?$'
     _TEST = {
         'url': 'http://normalboots.com/video/home-alone-games-jontron/',
         'md5': '8bf6de238915dd501105b44ef5f1e0f6',
@@ -30,19 +28,22 @@ class NormalbootsIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
-                                                 webpage, 'uploader')
-        raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
-                                                  webpage, 'date')
-        video_upload_date = unified_strdate(raw_upload_date)
 
-        player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url')
+        video_uploader = self._html_search_regex(
+            r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
+            webpage, 'uploader', fatal=False)
+        video_upload_date = unified_strdate(self._html_search_regex(
+            r'<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
+            webpage, 'date', fatal=False))
+
+        player_url = self._html_search_regex(
+            r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"',
+            webpage, 'player url')
         player_page = self._download_webpage(player_url, video_id)
-        video_url = self._html_search_regex(r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file')
+        video_url = self._html_search_regex(
+            r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file')
 
         return {
             'id': video_id,

youtube_dl/extractor/npo.py

@@ -1,6 +1,6 @@
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
 from ..utils import (
     fix_xml_ampersands,
     parse_duration,
@@ -11,7 +11,7 @@ from ..utils import (
 )
 
 
-class NPOBaseIE(InfoExtractor):
+class NPOBaseIE(SubtitlesInfoExtractor):
     def _get_token(self, video_id):
         token_page = self._download_webpage(
             'http://ida.omroep.nl/npoplayer/i.js',
@@ -161,6 +161,16 @@ class NPOIE(NPOBaseIE):
 
         self._sort_formats(formats)
 
+        subtitles = {}
+        if metadata.get('tt888') == 'ja':
+            subtitles['nl'] = 'http://e.omroep.nl/tt888/%s' % video_id
+
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
+
+        subtitles = self.extract_subtitles(video_id, subtitles)
+
         return {
             'id': video_id,
             'title': metadata['titel'],
@@ -169,6 +179,7 @@ class NPOIE(NPOBaseIE):
             'upload_date': unified_strdate(metadata.get('gidsdatum')),
             'duration': parse_duration(metadata.get('tijdsduur')),
             'formats': formats,
+            'subtitles': subtitles,
         }
 
 

youtube_dl/extractor/rtlnow.py

@@ -91,6 +91,15 @@ class RTLnowIE(InfoExtractor):
             },
         },
         {
+            'url': 'http://rtl-now.rtl.de/der-bachelor/folge-4.php?film_id=188729&player=1&season=5',
+            'info_dict': {
+                'id': '188729',
+                'ext': 'flv',
+                'upload_date': '20150204',
+                'description': 'md5:5e1ce23095e61a79c166d134b683cecc',
+                'title': 'Der Bachelor - Folge 4',
+            }
+        }, {
             'url': 'http://www.n-tvnow.de/deluxe-alles-was-spass-macht/thema-ua-luxushotel-fuer-vierbeiner.php?container_id=153819&player=1&season=0',
             'only_matching': True,
         },
@@ -134,9 +143,18 @@ class RTLnowIE(InfoExtractor):
                     'player_url': video_page_url + 'includes/vodplayer.swf',
                 }
             else:
-                fmt = {
-                    'url': filename.text,
-                }
+                mobj = re.search(r'.*/(?P<hoster>[^/]+)/videos/(?P<play_path>.+)\.f4m', filename.text)
+                if mobj:
+                    fmt = {
+                        'url': 'rtmpe://fmspay-fra2.rtl.de/' + mobj.group('hoster'),
+                        'play_path': 'mp4:' + mobj.group('play_path'),
+                        'page_url': url,
+                        'player_url': video_page_url + 'includes/vodplayer.swf',
+                    }
+                else:
+                    fmt = {
+                        'url': filename.text,
+                    }
             fmt.update({
                 'width': int_or_none(filename.get('width')),
                 'height': int_or_none(filename.get('height')),

youtube_dl/extractor/rtp.py

@@ -1,16 +1,16 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
+import re
 
 from .common import InfoExtractor
-from ..utils import js_to_json
 
 
 class RTPIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P<program_id>[0-9]+)/(?P<id>[^/?#]+)/?'
     _TESTS = [{
         'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas',
+        'md5': 'e736ce0c665e459ddb818546220b4ef8',
         'info_dict': {
             'id': 'e174042',
             'ext': 'mp3',
@@ -18,9 +18,6 @@ class RTPIE(InfoExtractor):
             'description': 'As paixões musicais de António Cartaxo e António Macedo',
             'thumbnail': 're:^https?://.*\.jpg',
         },
-        'params': {
-            'skip_download': True,  # RTMP download
-        },
     }, {
         'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas',
         'only_matching': True,
@@ -37,20 +34,48 @@ class RTPIE(InfoExtractor):
 
         player_config = self._search_regex(
             r'(?s)RTPPLAY\.player\.newPlayer\(\s*(\{.*?\})\s*\)', webpage, 'player config')
-        config = json.loads(js_to_json(player_config))
+        config = self._parse_json(player_config, video_id)
 
         path, ext = config.get('file').rsplit('.', 1)
         formats = [{
+            'format_id': 'rtmp',
+            'ext': ext,
+            'vcodec': config.get('type') == 'audio' and 'none' or None,
+            'preference': -2,
+            'url': 'rtmp://{streamer:s}/{application:s}'.format(**config),
             'app': config.get('application'),
             'play_path': '{ext:s}:{path:s}'.format(ext=ext, path=path),
             'page_url': url,
-            'url': 'rtmp://{streamer:s}/{application:s}'.format(**config),
             'rtmp_live': config.get('live', False),
-            'ext': ext,
-            'vcodec': config.get('type') == 'audio' and 'none' or None,
             'player_url': 'http://programas.rtp.pt/play/player.swf?v3',
+            'rtmp_real_time': True,
         }]
 
+        # Construct regular HTTP download URLs
+        replacements = {
+            'audio': {
+                'format_id': 'mp3',
+                'pattern': r'^nas2\.share/wavrss/',
+                'repl': 'http://rsspod.rtp.pt/podcasts/',
+                'vcodec': 'none',
+            },
+            'video': {
+                'format_id': 'mp4_h264',
+                'pattern': r'^nas2\.share/h264/',
+                'repl': 'http://rsspod.rtp.pt/videocasts/',
+                'vcodec': 'h264',
+            },
+        }
+        r = replacements[config['type']]
+        if re.match(r['pattern'], config['file']) is not None:
+            formats.append({
+                'format_id': r['format_id'],
+                'url': re.sub(r['pattern'], r['repl'], config['file']),
+                'vcodec': r['vcodec'],
+            })
+
+        self._sort_formats(formats)
+
         return {
             'id': video_id,
             'title': title,

youtube_dl/extractor/rts.py

@@ -6,12 +6,14 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
+    compat_urllib_parse_urlparse,
 )
 from ..utils import (
     int_or_none,
     parse_duration,
     parse_iso8601,
     unescapeHTML,
+    xpath_text,
 )
 
 
@@ -159,11 +161,27 @@ class RTSIE(InfoExtractor):
             return int_or_none(self._search_regex(
                 r'-([0-9]+)k\.', url, 'bitrate', default=None))
 
-        formats = [{
-            'format_id': fid,
-            'url': furl,
-            'tbr': extract_bitrate(furl),
-        } for fid, furl in info['streams'].items()]
+        formats = []
+        for format_id, format_url in info['streams'].items():
+            if format_url.endswith('.f4m'):
+                token = self._download_xml(
+                    'http://tp.srgssr.ch/token/akahd.xml?stream=%s/*' % compat_urllib_parse_urlparse(format_url).path,
+                    video_id, 'Downloading %s token' % format_id)
+                auth_params = xpath_text(token, './/authparams', 'auth params')
+                if not auth_params:
+                    continue
+                formats.extend(self._extract_f4m_formats(
+                    '%s?%s&hdcore=3.4.0&plugin=aasp-3.4.0.132.66' % (format_url, auth_params),
+                    video_id, f4m_id=format_id))
+            elif format_url.endswith('.m3u8'):
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', m3u8_id=format_id))
+            else:
+                formats.append({
+                    'format_id': format_id,
+                    'url': format_url,
+                    'tbr': extract_bitrate(format_url),
+                })
 
         if 'media' in info:
             formats.extend([{

youtube_dl/extractor/soulanime.py

@@ -1,80 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    HEADRequest,
-    urlhandle_detect_ext,
-)
-
-
-class SoulAnimeWatchingIE(InfoExtractor):
-    IE_NAME = "soulanime:watching"
-    IE_DESC = "SoulAnime video"
-    _TEST = {
-        'url': 'http://www.soul-anime.net/watching/seirei-tsukai-no-blade-dance-episode-9/',
-        'md5': '05fae04abf72298098b528e98abf4298',
-        'info_dict': {
-            'id': 'seirei-tsukai-no-blade-dance-episode-9',
-            'ext': 'mp4',
-            'title': 'seirei-tsukai-no-blade-dance-episode-9',
-            'description': 'seirei-tsukai-no-blade-dance-episode-9'
-        }
-    }
-    _VALID_URL = r'http://[w.]*soul-anime\.(?P<domain>[^/]+)/watch[^/]*/(?P<id>[^/]+)'
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        domain = mobj.group('domain')
-
-        page = self._download_webpage(url, video_id)
-
-        video_url_encoded = self._html_search_regex(
-            r'<div id="download">[^<]*<a href="(?P<url>[^"]+)"', page, 'url')
-        video_url = "http://www.soul-anime." + domain + video_url_encoded
-
-        ext_req = HEADRequest(video_url)
-        ext_handle = self._request_webpage(
-            ext_req, video_id, note='Determining extension')
-        ext = urlhandle_detect_ext(ext_handle)
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'ext': ext,
-            'title': video_id,
-            'description': video_id
-        }
-
-
-class SoulAnimeSeriesIE(InfoExtractor):
-    IE_NAME = "soulanime:series"
-    IE_DESC = "SoulAnime Series"
-
-    _VALID_URL = r'http://[w.]*soul-anime\.(?P<domain>[^/]+)/anime./(?P<id>[^/]+)'
-
-    _EPISODE_REGEX = r'<option value="(/watch[^/]*/[^"]+)">[^<]*</option>'
-
-    _TEST = {
-        'url': 'http://www.soul-anime.net/anime1/black-rock-shooter-tv/',
-        'info_dict': {
-            'id': 'black-rock-shooter-tv'
-        },
-        'playlist_count': 8
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        series_id = mobj.group('id')
-        domain = mobj.group('domain')
-
-        pattern = re.compile(self._EPISODE_REGEX)
-
-        page = self._download_webpage(url, series_id, "Downloading series page")
-        mobj = pattern.findall(page)
-
-        entries = [self.url_result("http://www.soul-anime." + domain + obj) for obj in mobj]
-
-        return self.playlist_result(entries, series_id)

youtube_dl/extractor/svtplay.py

@@ -0,0 +1,56 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+)
+
+
+class SVTPlayIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?svtplay\.se/video/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.svtplay.se/video/2609989/sm-veckan/sm-veckan-rally-final-sasong-1-sm-veckan-rally-final',
+        'md5': 'f4a184968bc9c802a9b41316657aaa80',
+        'info_dict': {
+            'id': '2609989',
+            'ext': 'mp4',
+            'title': 'SM veckan vinter, Örebro - Rally, final',
+            'duration': 4500,
+            'thumbnail': 're:^https?://.*[\.-]jpg$',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        info = self._download_json(
+            'http://www.svtplay.se/video/%s?output=json' % video_id, video_id)
+
+        title = info['context']['title']
+        thumbnail = info['context'].get('thumbnailImage')
+
+        video_info = info['video']
+        formats = []
+        for vr in video_info['videoReferences']:
+            vurl = vr['url']
+            if determine_ext(vurl) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    vurl, video_id,
+                    ext='mp4', entry_protocol='m3u8_native',
+                    m3u8_id=vr.get('playerType')))
+            else:
+                formats.append({
+                    'format_id': vr.get('playerType'),
+                    'url': vurl,
+                })
+        self._sort_formats(formats)
+
+        duration = video_info.get('materialLength')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'duration': duration,
+        }

youtube_dl/extractor/teamcoco.py

@@ -15,7 +15,8 @@ class TeamcocoIE(InfoExtractor):
                 'id': '80187',
                 'ext': 'mp4',
                 'title': 'Conan Becomes A Mary Kay Beauty Consultant',
-                'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.'
+                'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.',
+                'age_limit': 0,
             }
         }, {
             'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
@@ -24,7 +25,8 @@ class TeamcocoIE(InfoExtractor):
                 'id': '19705',
                 'ext': 'mp4',
                 "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.",
-                "title": "Louis C.K. Interview Pt. 1 11/3/11"
+                "title": "Louis C.K. Interview Pt. 1 11/3/11",
+                'age_limit': 0,
             }
         }
     ]
@@ -83,4 +85,5 @@ class TeamcocoIE(InfoExtractor):
             'title': self._og_search_title(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
             'description': self._og_search_description(webpage),
+            'age_limit': self._family_friendly_search(webpage),
         }

youtube_dl/extractor/trilulilu.py

@@ -1,40 +1,55 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
-import json
+import re
 
 from .common import InfoExtractor
+from ..utils import ExtractorError
 
 
 class TriluliluIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?trilulilu\.ro/video-[^/]+/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?trilulilu\.ro/(?:video-[^/]+/)?(?P<id>[^/#\?]+)'
     _TEST = {
         'url': 'http://www.trilulilu.ro/video-animatie/big-buck-bunny-1',
+        'md5': 'c1450a00da251e2769b74b9005601cac',
         'info_dict': {
-            'id': 'big-buck-bunny-1',
+            'id': 'ae2899e124140b',
             'ext': 'mp4',
             'title': 'Big Buck Bunny',
             'description': ':) pentru copilul din noi',
         },
-        # Server ignores Range headers (--test)
-        'params': {
-            'skip_download': True
-        }
     }
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
 
+        if re.search(r'Fişierul nu este disponibil pentru vizionare în ţara dumneavoastră', webpage):
+            raise ExtractorError(
+                'This video is not available in your country.', expected=True)
+        elif re.search('Fişierul poate fi accesat doar de către prietenii lui', webpage):
+            raise ExtractorError('This video is private.', expected=True)
+
+        flashvars_str = self._search_regex(
+            r'block_flash_vars\s*=\s*(\{[^\}]+\})', webpage, 'flashvars', fatal=False, default=None)
+
+        if flashvars_str:
+            flashvars = self._parse_json(flashvars_str, display_id)
+        else:
+            raise ExtractorError(
+                'This page does not contain videos', expected=True)
+
+        if flashvars['isMP3'] == 'true':
+            raise ExtractorError(
+                'Audio downloads are currently not supported', expected=True)
+
+        video_id = flashvars['hash']
         title = self._og_search_title(webpage)
         thumbnail = self._og_search_thumbnail(webpage)
-        description = self._og_search_description(webpage)
-
-        log_str = self._search_regex(
-            r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, 'log info')
-        log = json.loads(log_str)
+        description = self._og_search_description(webpage, default=None)
 
         format_url = ('http://fs%(server)s.trilulilu.ro/%(hash)s/'
-                      'video-formats2' % log)
+                      'video-formats2' % flashvars)
         format_doc = self._download_xml(
             format_url, video_id,
             note='Downloading formats',
@@ -44,10 +59,10 @@ class TriluliluIE(InfoExtractor):
             'http://fs%(server)s.trilulilu.ro/stream.php?type=video'
             '&source=site&hash=%(hash)s&username=%(userid)s&'
             'key=ministhebest&format=%%s&sig=&exp=' %
-            log)
+            flashvars)
         formats = [
             {
-                'format': fnode.text,
+                'format_id': fnode.text.partition('-')[2],
                 'url': video_url_template % fnode.text,
                 'ext': fnode.text.partition('-')[0]
             }
@@ -56,8 +71,8 @@ class TriluliluIE(InfoExtractor):
         ]
 
         return {
-            '_type': 'video',
             'id': video_id,
+            'display_id': display_id,
             'formats': formats,
             'title': title,
             'description': description,

youtube_dl/extractor/tvigle.py

@@ -1,6 +1,8 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     float_or_none,
@@ -11,7 +13,7 @@ from ..utils import (
 class TvigleIE(InfoExtractor):
     IE_NAME = 'tvigle'
     IE_DESC = 'Интернет-телевидение Tvigle.ru'
-    _VALID_URL = r'http://(?:www\.)?tvigle\.ru/(?:[^/]+/)+(?P<id>[^/]+)/$'
+    _VALID_URL = r'https?://(?:www\.)?(?:tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$|cloud\.tvigle\.ru/video/(?P<id>\d+))'
 
     _TESTS = [
         {
@@ -38,16 +40,22 @@ class TvigleIE(InfoExtractor):
                 'duration': 186.080,
                 'age_limit': 0,
             },
-        },
+        }, {
+            'url': 'https://cloud.tvigle.ru/video/5267604/',
+            'only_matching': True,
+        }
     ]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
 
-        webpage = self._download_webpage(url, display_id)
-
-        video_id = self._html_search_regex(
-            r'<li class="video-preview current_playing" id="(\d+)">', webpage, 'video id')
+        if not video_id:
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._html_search_regex(
+                r'<li class="video-preview current_playing" id="(\d+)">',
+                webpage, 'video id')
 
         video_data = self._download_json(
             'http://cloud.tvigle.ru/api/play/video/%s/' % video_id, display_id)

youtube_dl/extractor/tweakers.py

@@ -0,0 +1,65 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    xpath_text,
+    xpath_with_ns,
+    int_or_none,
+    float_or_none,
+)
+
+
+class TweakersIE(InfoExtractor):
+    _VALID_URL = r'https?://tweakers\.net/video/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://tweakers.net/video/9926/new-nintendo-3ds-xl-op-alle-fronten-beter.html',
+        'md5': '1b5afa817403bb5baa08359dca31e6df',
+        'info_dict': {
+            'id': '9926',
+            'ext': 'mp4',
+            'title': 'New Nintendo 3DS XL - Op alle fronten beter',
+            'description': 'md5:f97324cc71e86e11c853f0763820e3ba',
+            'thumbnail': 're:^https?://.*\.jpe?g$',
+            'duration': 386,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        playlist = self._download_xml(
+            'https://tweakers.net/video/s1playlist/%s/playlist.xspf' % video_id,
+            video_id)
+
+        NS_MAP = {
+            'xspf': 'http://xspf.org/ns/0/',
+            's1': 'http://static.streamone.nl/player/ns/0',
+        }
+
+        track = playlist.find(xpath_with_ns('./xspf:trackList/xspf:track', NS_MAP))
+
+        title = xpath_text(
+            track, xpath_with_ns('./xspf:title', NS_MAP), 'title')
+        description = xpath_text(
+            track, xpath_with_ns('./xspf:annotation', NS_MAP), 'description')
+        thumbnail = xpath_text(
+            track, xpath_with_ns('./xspf:image', NS_MAP), 'thumbnail')
+        duration = float_or_none(
+            xpath_text(track, xpath_with_ns('./xspf:duration', NS_MAP), 'duration'),
+            1000)
+
+        formats = [{
+            'url': location.text,
+            'format_id': location.get(xpath_with_ns('s1:label', NS_MAP)),
+            'width': int_or_none(location.get(xpath_with_ns('s1:width', NS_MAP))),
+            'height': int_or_none(location.get(xpath_with_ns('s1:height', NS_MAP))),
+        } for location in track.findall(xpath_with_ns('./xspf:location', NS_MAP))]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/vevo.py

@@ -9,6 +9,7 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    int_or_none,
 )
 
 
@@ -192,9 +193,29 @@ class VevoIE(InfoExtractor):
         # Download via HLS API
         formats.extend(self._download_api_formats(video_id))
 
+        # Download SMIL
+        smil_blocks = sorted((
+            f for f in video_info['videoVersions']
+            if f['sourceType'] == 13),
+            key=lambda f: f['version'])
+        smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (
+            self._SMIL_BASE_URL, video_id, video_id.lower())
+        if smil_blocks:
+            smil_url_m = self._search_regex(
+                r'url="([^"]+)"', smil_blocks[-1]['data'], 'SMIL URL',
+                default=None)
+            if smil_url_m is not None:
+                smil_url = smil_url_m
+        if smil_url:
+            smil_xml = self._download_webpage(
+                smil_url, video_id, 'Downloading SMIL info', fatal=False)
+            if smil_xml:
+                formats.extend(self._formats_from_smil(smil_xml))
+
         self._sort_formats(formats)
-        timestamp_ms = int(self._search_regex(
-            r'/Date\((\d+)\)/', video_info['launchDate'], 'launch date'))
+        timestamp_ms = int_or_none(self._search_regex(
+            r'/Date\((\d+)\)/',
+            video_info['launchDate'], 'launch date', fatal=False))
 
         return {
             'id': video_id,

youtube_dl/extractor/wsj.py

@@ -0,0 +1,89 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_strdate,
+)
+
+
+class WSJIE(InfoExtractor):
+    _VALID_URL = r'https?://video-api\.wsj\.com/api-video/player/iframe\.html\?guid=(?P<id>[a-zA-Z0-9-]+)'
+    IE_DESC = 'Wall Street Journal'
+    _TEST = {
+        'url': 'http://video-api.wsj.com/api-video/player/iframe.html?guid=1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
+        'md5': '9747d7a6ebc2f4df64b981e1dde9efa9',
+        'info_dict': {
+            'id': '1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
+            'ext': 'mp4',
+            'upload_date': '20150202',
+            'uploader_id': 'bbright',
+            'creator': 'bbright',
+            'categories': list,  # a long list
+            'duration': 90,
+            'title': 'Bills Coach Rex Ryan Updates His Old Jets Tattoo',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        bitrates = [128, 174, 264, 320, 464, 664, 1264]
+        api_url = (
+            'http://video-api.wsj.com/api-video/find_all_videos.asp?'
+            'type=guid&count=1&query=%s&'
+            'fields=hls,adZone,thumbnailList,guid,state,secondsUntilStartTime,'
+            'author,description,name,linkURL,videoStillURL,duration,videoURL,'
+            'adCategory,catastrophic,linkShortURL,doctypeID,youtubeID,'
+            'titletag,rssURL,wsj-section,wsj-subsection,allthingsd-section,'
+            'allthingsd-subsection,sm-section,sm-subsection,provider,'
+            'formattedCreationDate,keywords,keywordsOmniture,column,editor,'
+            'emailURL,emailPartnerID,showName,omnitureProgramName,'
+            'omnitureVideoFormat,linkRelativeURL,touchCastID,'
+            'omniturePublishDate,%s') % (
+                video_id, ','.join('video%dkMP4Url' % br for br in bitrates))
+        info = self._download_json(api_url, video_id)['items'][0]
+
+        # Thumbnails are conveniently in the correct format already
+        thumbnails = info.get('thumbnailList')
+        creator = info.get('author')
+        uploader_id = info.get('editor')
+        categories = info.get('keywords')
+        duration = int_or_none(info.get('duration'))
+        upload_date = unified_strdate(
+            info.get('formattedCreationDate'), day_first=False)
+        title = info.get('name', info.get('titletag'))
+
+        formats = [{
+            'format_id': 'f4m',
+            'format_note': 'f4m (meta URL)',
+            'url': info['videoURL'],
+        }]
+        if info.get('hls'):
+            formats.extend(self._extract_m3u8_formats(
+                info['hls'], video_id, ext='mp4',
+                preference=0, entry_protocol='m3u8_native'))
+        for br in bitrates:
+            field = 'video%dkMP4Url' % br
+            if info.get(field):
+                formats.append({
+                    'format_id': 'mp4-%d' % br,
+                    'container': 'mp4',
+                    'tbr': br,
+                    'url': info[field],
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'creator': creator,
+            'uploader_id': uploader_id,
+            'duration': duration,
+            'upload_date': upload_date,
+            'title': title,
+            'formats': formats,
+            'categories': categories,
+        }

youtube_dl/extractor/youtube.py

@@ -780,8 +780,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                     fo for fo in formats
                     if fo['format_id'] == format_id)
             except StopIteration:
-                f.update(self._formats.get(format_id, {}).items())
-                formats.append(f)
+                full_info = self._formats.get(format_id, {}).copy()
+                full_info.update(f)
+                formats.append(full_info)
             else:
                 existing_format.update(f)
         return formats

youtube_dl/options.py

@@ -244,6 +244,25 @@ def parseOpts(overrideArguments=None):
         '--max-views',
         metavar='COUNT', dest='max_views', default=None, type=int,
         help='Do not download any videos with more than COUNT views')
+    selection.add_option(
+        '--match-filter',
+        metavar='FILTER', dest='match_filter', default=None,
+        help=(
+            '(Experimental) Generic video filter. '
+            'Specify any key (see help for -o for a list of available keys) to'
+            ' match if the key is present, '
+            '!key to check if the key is not present,'
+            'key > NUMBER (like "comment_count > 12", also works with '
+            '>=, <, <=, !=, =) to compare against a number, and '
+            '& to require multiple matches. '
+            'Values which are not known are excluded unless you'
+            ' put a question mark (?) after the operator.'
+            'For example, to only match videos that have been liked more than '
+            '100 times and disliked less than 50 times (or the dislike '
+            'functionality is not available at the given service), but who '
+            'also have a description, use  --match-filter '
+            '"like_count > 100 & dislike_count <? 50 & description" .'
+        ))
     selection.add_option(
         '--no-playlist',
         action='store_true', dest='noplaylist', default=False,
@@ -297,8 +316,10 @@ def parseOpts(overrideArguments=None):
             ' 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, vbr, and fps'
-            ' and the comparisons <, <=, >, >=, =, != .'
+            ' This works for filesize, height, width, tbr, abr, vbr, asr, and fps'
+            ' and the comparisons <, <=, >, >=, =, !='
+            ' and for ext, acodec, vcodec, container, and protocol'
+            ' and the comparisons =, != .'
             ' Formats for which the value is not known are excluded unless you'
             ' put a question mark (?) after the operator.'
             ' You can combine format filters, so  '
@@ -732,22 +753,22 @@ def parseOpts(overrideArguments=None):
         if opts.verbose:
             write_string('[debug] Override config: ' + repr(overrideArguments) + '\n')
     else:
-        commandLineConf = sys.argv[1:]
-        if '--ignore-config' in commandLineConf:
-            systemConf = []
-            userConf = []
+        command_line_conf = sys.argv[1:]
+        if '--ignore-config' in command_line_conf:
+            system_conf = []
+            user_conf = []
         else:
-            systemConf = _readOptions('/etc/youtube-dl.conf')
-            if '--ignore-config' in systemConf:
-                userConf = []
+            system_conf = _readOptions('/etc/youtube-dl.conf')
+            if '--ignore-config' in system_conf:
+                user_conf = []
             else:
-                userConf = _readUserConf()
-        argv = systemConf + userConf + commandLineConf
+                user_conf = _readUserConf()
+        argv = system_conf + user_conf + command_line_conf
 
         opts, args = parser.parse_args(argv)
         if opts.verbose:
-            write_string('[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
-            write_string('[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n')
-            write_string('[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n')
+            write_string('[debug] System config: ' + repr(_hide_login_info(system_conf)) + '\n')
+            write_string('[debug] User config: ' + repr(_hide_login_info(user_conf)) + '\n')
+            write_string('[debug] Command-line args: ' + repr(_hide_login_info(command_line_conf)) + '\n')
 
     return parser, opts, args

youtube_dl/postprocessor/ffmpeg.py

@@ -166,14 +166,13 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
         if filecodec is None:
             raise PostProcessingError('WARNING: unable to obtain file audio codec with ffprobe')
 
-        uses_avconv = self._uses_avconv()
         more_opts = []
         if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'):
             if filecodec == 'aac' and self._preferredcodec in ['m4a', 'best']:
                 # Lossless, but in another container
                 acodec = 'copy'
                 extension = 'm4a'
-                more_opts = ['-bsf:a' if uses_avconv else '-absf', 'aac_adtstoasc']
+                more_opts = ['-bsf:a', 'aac_adtstoasc']
             elif filecodec in ['aac', 'mp3', 'vorbis', 'opus']:
                 # Lossless if possible
                 acodec = 'copy'
@@ -189,9 +188,9 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
                 more_opts = []
                 if self._preferredquality is not None:
                     if int(self._preferredquality) < 10:
-                        more_opts += ['-q:a' if uses_avconv else '-aq', self._preferredquality]
+                        more_opts += ['-q:a', self._preferredquality]
                     else:
-                        more_opts += ['-b:a' if uses_avconv else '-ab', self._preferredquality + 'k']
+                        more_opts += ['-b:a', self._preferredquality + 'k']
         else:
             # We convert the audio (lossy)
             acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'opus': 'opus', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
@@ -200,13 +199,13 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
             if self._preferredquality is not None:
                 # The opus codec doesn't support the -aq option
                 if int(self._preferredquality) < 10 and extension != 'opus':
-                    more_opts += ['-q:a' if uses_avconv else '-aq', self._preferredquality]
+                    more_opts += ['-q:a', self._preferredquality]
                 else:
-                    more_opts += ['-b:a' if uses_avconv else '-ab', self._preferredquality + 'k']
+                    more_opts += ['-b:a', self._preferredquality + 'k']
             if self._preferredcodec == 'aac':
                 more_opts += ['-f', 'adts']
             if self._preferredcodec == 'm4a':
-                more_opts += ['-bsf:a' if uses_avconv else '-absf', 'aac_adtstoasc']
+                more_opts += ['-bsf:a', 'aac_adtstoasc']
             if self._preferredcodec == 'vorbis':
                 extension = 'ogg'
             if self._preferredcodec == 'wav':
@@ -511,8 +510,9 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
             metadata['artist'] = info['uploader_id']
         if info.get('description') is not None:
             metadata['description'] = info['description']
+            metadata['comment'] = info['description']
         if info.get('webpage_url') is not None:
-            metadata['comment'] = info['webpage_url']
+            metadata['purl'] = info['webpage_url']
 
         if not metadata:
             self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add')

youtube_dl/utils.py

@@ -17,6 +17,7 @@ import io
 import json
 import locale
 import math
+import operator
 import os
 import pipes
 import platform
@@ -701,7 +702,7 @@ def unified_strdate(date_str, day_first=True):
     # %z (UTC offset) is only supported in python>=3.2
     date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str)
     # Remove AM/PM + timezone
-    date_str = re.sub(r'(?i)\s*(?:AM|PM)\s+[A-Z]+', '', date_str)
+    date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
 
     format_expressions = [
         '%d %B %Y',
@@ -1678,3 +1679,79 @@ def render_table(header_row, data):
     max_lens = [max(len(compat_str(v)) for v in col) for col in zip(*table)]
     format_str = ' '.join('%-' + compat_str(ml + 1) + 's' for ml in max_lens[:-1]) + '%s'
     return '\n'.join(format_str % tuple(row) for row in table)
+
+
+def _match_one(filter_part, dct):
+    COMPARISON_OPERATORS = {
+        '<': operator.lt,
+        '<=': operator.le,
+        '>': operator.gt,
+        '>=': operator.ge,
+        '=': operator.eq,
+        '!=': operator.ne,
+    }
+    operator_rex = re.compile(r'''(?x)\s*
+        (?P<key>[a-z_]+)
+        \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
+        (?:
+            (?P<intval>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)|
+            (?P<strval>(?![0-9.])[a-z0-9A-Z]*)
+        )
+        \s*$
+        ''' % '|'.join(map(re.escape, COMPARISON_OPERATORS.keys())))
+    m = operator_rex.search(filter_part)
+    if m:
+        op = COMPARISON_OPERATORS[m.group('op')]
+        if m.group('strval') is not None:
+            if m.group('op') not in ('=', '!='):
+                raise ValueError(
+                    'Operator %s does not support string values!' % m.group('op'))
+            comparison_value = m.group('strval')
+        else:
+            try:
+                comparison_value = int(m.group('intval'))
+            except ValueError:
+                comparison_value = parse_filesize(m.group('intval'))
+                if comparison_value is None:
+                    comparison_value = parse_filesize(m.group('intval') + 'B')
+                if comparison_value is None:
+                    raise ValueError(
+                        'Invalid integer value %r in filter part %r' % (
+                            m.group('intval'), filter_part))
+        actual_value = dct.get(m.group('key'))
+        if actual_value is None:
+            return m.group('none_inclusive')
+        return op(actual_value, comparison_value)
+
+    UNARY_OPERATORS = {
+        '': lambda v: v is not None,
+        '!': lambda v: v is None,
+    }
+    operator_rex = re.compile(r'''(?x)\s*
+        (?P<op>%s)\s*(?P<key>[a-z_]+)
+        \s*$
+        ''' % '|'.join(map(re.escape, UNARY_OPERATORS.keys())))
+    m = operator_rex.search(filter_part)
+    if m:
+        op = UNARY_OPERATORS[m.group('op')]
+        actual_value = dct.get(m.group('key'))
+        return op(actual_value)
+
+    raise ValueError('Invalid filter part %r' % filter_part)
+
+
+def match_str(filter_str, dct):
+    """ Filter a dictionary with a simple string syntax. Returns True (=passes filter) or false """
+
+    return all(
+        _match_one(filter_part, dct) for filter_part in filter_str.split('&'))
+
+
+def match_filter_func(filter_str):
+    def _match_func(info_dict):
+        if match_str(filter_str, info_dict):
+            return None
+        else:
+            video_title = info_dict.get('title', info_dict.get('id', 'video'))
+            return '%s does not pass filter %s, skipping ..' % (video_title, filter_str)
+    return _match_func

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2015.02.02.2'
+__version__ = '2015.02.10.2'