release 2014.07.23

Conflicts:
	youtube_dl/extractor/mlb.py

.travis.yml

@@ -3,6 +3,7 @@ python:
   - "2.6"
   - "2.7"
   - "3.3"
+  - "3.4"
 script: nosetests test --verbose
 notifications:
   email:

CHANGELOG

@@ -1,14 +0,0 @@
-2013.01.02  Codename: GIULIA
-
-    * Add support for ComedyCentral clips <nto>
-    * Corrected Vimeo description fetching <Nick Daniels>
-    * Added the --no-post-overwrites argument <Barbu Paul - Gheorghe>
-    * --verbose offers more environment info
-    * New info_dict field: uploader_id
-    * New updates system, with signature checking
-    * New IEs: NBA, JustinTV, FunnyOrDie, TweetReel, Steam, Ustream
-    * Fixed IEs: BlipTv
-    * Fixed for Python 3 IEs: Xvideo, Youku, XNXX, Dailymotion, Vimeo, InfoQ
-    * Simplified IEs and test code
-    * Various (Python 3 and other) fixes
-    * Revamped and expanded tests

Makefile

@@ -1,7 +1,7 @@
 all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
 
 clean:
-	rm -rf youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz
+	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
 
 cleanall: clean
 	rm -f youtube-dl youtube-dl.exe
@@ -55,7 +55,9 @@ README.txt: README.md
 	pandoc -f markdown -t plain README.md -o README.txt
 
 youtube-dl.1: README.md
-	pandoc -s -f markdown -t man README.md -o youtube-dl.1
+	python devscripts/prepare_manpage.py >youtube-dl.1.temp.md
+	pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1
+	rm -f youtube-dl.1.temp.md
 
 youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-completion.in
 	python devscripts/bash-completion.py
@@ -75,6 +77,6 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
 		--exclude 'docs/_build' \
 		-- \
 		bin devscripts test youtube_dl docs \
-		CHANGELOG LICENSE README.md README.txt \
+		LICENSE README.md README.txt \
 		Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion setup.py \
 		youtube-dl

README.md

@@ -1,11 +1,24 @@
-% YOUTUBE-DL(1)
-
-# NAME
 youtube-dl - download videos from youtube.com or other video platforms
 
 # SYNOPSIS
 **youtube-dl** [OPTIONS] URL [URL...]
 
+# INSTALLATION
+
+To install it right away for all UNIX users (Linux, OS X, etc.), type:
+
+    sudo curl https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl
+    sudo chmod a+x /usr/local/bin/youtube-dl
+
+If you do not have curl, you can alternatively use a recent wget:
+
+    sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl
+    sudo chmod a+x /usr/local/bin/youtube-dl
+
+Windows users can [download a .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in their home directory or any other location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29).
+
+Alternatively, refer to the developer instructions below for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html .
+
 # DESCRIPTION
 **youtube-dl** is a small command-line program to download videos from
 YouTube.com and a few more sites. It requires the Python interpreter, version
@@ -57,8 +70,9 @@ which means you can modify it, redistribute it or use it however you like.
     --default-search PREFIX          Use this prefix for unqualified URLs. For
                                      example "gvsearch2:" downloads two videos
                                      from google videos for  youtube-dl "large
-                                     apple". By default (with value "auto")
-                                     youtube-dl guesses.
+                                     apple". Use the value "auto" to let
+                                     youtube-dl guess. The default value "error"
+                                     just throws an error.
     --ignore-config                  Do not read configuration files. When given
                                      in the global configuration file /etc
                                      /youtube-dl.conf: do not read the user
@@ -241,7 +255,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      128K (default 5)
     --recode-video FORMAT            Encode the video to another format if
                                      necessary (currently supported:
-                                     mp4|flv|ogg|webm)
+                                     mp4|flv|ogg|webm|mkv)
     -k, --keep-video                 keeps the video file on disk after the
                                      post-processing; the video is erased by
                                      default
@@ -458,7 +472,7 @@ If your report is shorter than two lines, it is almost certainly missing some of
 
 For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
 
-Site support requests must contain an example URL. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
+Site support requests **must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
 
 ###  Are you using the latest version?
 

devscripts/make_readme.py

@@ -15,7 +15,7 @@ header = oldreadme[:oldreadme.index('# OPTIONS')]
 footer = oldreadme[oldreadme.index('# CONFIGURATION'):]
 
 options = helptext[helptext.index('  General Options:') + 19:]
-options = re.sub(r'^  (\w.+)$', r'## \1', options, flags=re.M)
+options = re.sub(r'(?m)^  (\w.+)$', r'## \1', options)
 options = '# OPTIONS\n' + options + '\n'
 
 with io.open(README_FILE, 'w', encoding='utf-8') as f:

devscripts/prepare_manpage.py

@@ -0,0 +1,20 @@
+
+import io
+import os.path
+import sys
+import re
+
+ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+README_FILE = os.path.join(ROOT_DIR, 'README.md')
+
+with io.open(README_FILE, encoding='utf-8') as f:
+    readme = f.read()
+
+PREFIX = '%YOUTUBE-DL(1)\n\n# NAME\n'
+readme = re.sub(r'(?s)# INSTALLATION.*?(?=# DESCRIPTION)', '', readme)
+readme = PREFIX + readme
+
+if sys.version_info < (3, 0):
+    print(readme.encode('utf-8'))
+else:
+    print(readme)

devscripts/release.sh

@@ -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 CHANGELOG README.md and youtube_dl/version.py..."
+/bin/echo -e "\n### Committing README.md and youtube_dl/version.py..."
 make README.md
-git add CHANGELOG README.md youtube_dl/version.py
+git add README.md youtube_dl/version.py
 git commit -m "release $version"
 
 /bin/echo -e "\n### Now tagging, signing and pushing..."

test/helper.py

@@ -74,13 +74,19 @@ class FakeYDL(YoutubeDL):
             old_report_warning(message)
         self.report_warning = types.MethodType(report_warning, self)
 
-def gettestcases():
+
+def gettestcases(include_onlymatching=False):
     for ie in youtube_dl.extractor.gen_extractors():
         t = getattr(ie, '_TEST', None)
         if t:
-            t['name'] = type(ie).__name__[:-len('IE')]
-            yield t
-        for t in getattr(ie, '_TESTS', []):
+            assert not hasattr(ie, '_TESTS'), \
+                '%s has _TEST and _TESTS' % type(ie).__name__
+            tests = [t]
+        else:
+            tests = getattr(ie, '_TESTS', [])
+        for t in tests:
+            if not include_onlymatching and t.get('only_matching', False):
+                continue
             t['name'] = type(ie).__name__[:-len('IE')]
             yield t
 
@@ -101,7 +107,7 @@ def expect_info_dict(self, expected_dict, got_dict):
         elif isinstance(expected, type):
             got = got_dict.get(info_field)
             self.assertTrue(isinstance(got, expected),
-                u'Expected type %r, but got value %r of type %r' % (expected, got, type(got)))
+                u'Expected type %r for field %s, but got value %r of type %r' % (expected, info_field, got, type(got)))
         else:
             if isinstance(expected, compat_str) and expected.startswith('md5:'):
                 got = 'md5:' + md5(got_dict.get(info_field))
@@ -128,3 +134,24 @@ def expect_info_dict(self, expected_dict, got_dict):
             missing_keys,
             'Missing keys in test definition: %s' % (
                 ', '.join(sorted(missing_keys))))
+
+
+def assertRegexpMatches(self, text, regexp, msg=None):
+    if hasattr(self, 'assertRegexpMatches'):
+        return self.assertRegexpMatches(text, regexp, msg)
+    else:
+        m = re.match(regexp, text)
+        if not m:
+            note = 'Regexp didn\'t match: %r not found in %r' % (regexp, text)
+            if msg is None:
+                msg = note
+            else:
+                msg = note + ', ' + msg
+            self.assertTrue(m, msg)
+
+
+def assertGreaterEqual(self, got, expected, msg=None):
+    if not (got >= expected):
+        if msg is None:
+            msg = '%r not greater than or equal to %r' % (got, expected)
+        self.assertTrue(got >= expected, msg)

test/swftests/.gitignore

@@ -0,0 +1 @@
+*.swf

test/swftests/ArrayAccess.as

@@ -0,0 +1,19 @@
+// input: [["a", "b", "c", "d"]]
+// output: ["c", "b", "a", "d"]
+
+package {
+public class ArrayAccess {
+    public static function main(ar:Array):Array {
+    	var aa:ArrayAccess = new ArrayAccess();
+    	return aa.f(ar, 2);
+    }
+
+    private function f(ar:Array, num:Number):Array{
+        var x:String = ar[0];
+        var y:String = ar[num % ar.length];
+        ar[0] = y;
+        ar[num] = x;
+        return ar;
+    }
+}
+}

test/swftests/ClassCall.as

@@ -0,0 +1,17 @@
+// input: []
+// output: 121
+
+package {
+public class ClassCall {
+    public static function main():int{
+    	var f:OtherClass = new OtherClass();
+        return f.func(100,20);
+    }
+}
+}
+
+class OtherClass {
+	public function func(x: int, y: int):int {
+		return x+y+1;
+	}
+}

test/swftests/ClassConstruction.as

@@ -0,0 +1,15 @@
+// input: []
+// output: 0
+
+package {
+public class ClassConstruction {
+    public static function main():int{
+    	var f:Foo = new Foo();
+        return 0;
+    }
+}
+}
+
+class Foo {
+
+}

test/swftests/LocalVars.as

@@ -0,0 +1,13 @@
+// input: [1, 2]
+// output: 3
+
+package {
+public class LocalVars {
+    public static function main(a:int, b:int):int{
+        var c:int = a + b + b;
+        var d:int = c - b;
+        var e:int = d;
+        return e;
+    }
+}
+}

test/swftests/PrivateCall.as

@@ -0,0 +1,21 @@
+// input: []
+// output: 9
+
+package {
+public class PrivateCall {
+    public static function main():int{
+    	var f:OtherClass = new OtherClass();
+        return f.func();
+    }
+}
+}
+
+class OtherClass {
+	private function pf():int {
+		return 9;
+	}
+
+	public function func():int {
+		return this.pf();
+	}
+}

test/swftests/StaticAssignment.as

@@ -0,0 +1,13 @@
+// input: [1]
+// output: 1
+
+package {
+public class StaticAssignment {
+	public static var v:int;
+
+    public static function main(a:int):int{
+        v = a;
+        return v;
+    }
+}
+}

test/swftests/StaticRetrieval.as

@@ -0,0 +1,16 @@
+// input: []
+// output: 1
+
+package {
+public class StaticRetrieval {
+	public static var v:int;
+
+    public static function main():int{
+        if (v) {
+        	return 0;
+        } else {
+        	return 1;
+        }
+    }
+}
+}

test/test_YoutubeDL.py

@@ -8,7 +8,7 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from test.helper import FakeYDL
+from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
 from youtube_dl.extractor import YoutubeIE
 
@@ -67,7 +67,7 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['ext'], 'mp4')
 
-        # No prefer_free_formats => prefer mp4 and flv for greater compatibilty
+        # No prefer_free_formats => prefer mp4 and flv for greater compatibility
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
@@ -274,6 +274,12 @@ class TestFormatSelection(unittest.TestCase):
         # Replace missing fields with 'NA'
         self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
 
+    def test_format_note(self):
+        ydl = YoutubeDL()
+        self.assertEqual(ydl._format_note({}), '')
+        assertRegexpMatches(self, ydl._format_note({
+            'vbr': 10,
+        }), '^\s*10k$')
 
 if __name__ == '__main__':
     unittest.main()

test/test_age_restriction.py

@@ -13,7 +13,7 @@ from youtube_dl import YoutubeDL
 
 
 def _download_restricted(url, filename, age):
-    """ Returns true iff the file has been downloaded """
+    """ Returns true if the file has been downloaded """
 
     params = {
         'age_limit': age,

test/test_all_urls.py

@@ -69,28 +69,25 @@ class TestAllURLsMatching(unittest.TestCase):
     def test_youtube_show_matching(self):
         self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
 
-    def test_youtube_truncated(self):
-        self.assertMatch('http://www.youtube.com/watch?', ['youtube:truncated_url'])
-
     def test_youtube_search_matching(self):
         self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
         self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
 
     def test_justin_tv_channelid_matching(self):
-        self.assertTrue(JustinTVIE.suitable(u"justin.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"twitch.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"www.justin.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"www.twitch.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv/"))
-        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/"))
+        self.assertTrue(JustinTVIE.suitable('justin.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('twitch.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('www.justin.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('www.twitch.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('http://www.justin.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('http://www.justin.tv/vanillatv/'))
+        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv/'))
 
     def test_justintv_videoid_matching(self):
-        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/b/328087483"))
+        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
 
     def test_justin_tv_chapterid_matching(self):
-        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361"))
+        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
 
     def test_youtube_extract(self):
         assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
@@ -106,7 +103,7 @@ class TestAllURLsMatching(unittest.TestCase):
 
     def test_no_duplicates(self):
         ies = gen_extractors()
-        for tc in gettestcases():
+        for tc in gettestcases(include_onlymatching=True):
             url = tc['url']
             for ie in ies:
                 if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
@@ -176,5 +173,6 @@ class TestAllURLsMatching(unittest.TestCase):
             'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
             ['Yahoo'])
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_playlists.py

@@ -10,6 +10,8 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
+    assertRegexpMatches,
+    assertGreaterEqual,
     expect_info_dict,
     FakeYDL,
 )
@@ -22,10 +24,14 @@ from youtube_dl.extractor import (
     VimeoUserIE,
     VimeoAlbumIE,
     VimeoGroupsIE,
+    VineUserIE,
     UstreamChannelIE,
     SoundcloudSetIE,
     SoundcloudUserIE,
+    SoundcloudPlaylistIE,
+    TeacherTubeUserIE,
     LivestreamIE,
+    LivestreamOriginalIE,
     NHLVideocenterIE,
     BambuserChannelIE,
     BandcampAlbumIE,
@@ -36,6 +42,7 @@ from youtube_dl.extractor import (
     KhanAcademyIE,
     EveryonesMixtapeIE,
     RutubeChannelIE,
+    RutubePersonIE,
     GoogleSearchIE,
     GenericIE,
     TEDIE,
@@ -65,8 +72,8 @@ class TestPlaylists(unittest.TestCase):
         ie = DailymotionUserIE(dl)
         result = ie.extract('https://www.dailymotion.com/user/nqtv')
         self.assertIsPlaylist(result)
+        assertGreaterEqual(self, len(result['entries']), 100)
         self.assertEqual(result['title'], 'Rémi Gaillard')
-        self.assertTrue(len(result['entries']) >= 100)
 
     def test_vimeo_channel(self):
         dl = FakeYDL()
@@ -100,13 +107,20 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['title'], 'Rolex Awards for Enterprise')
         self.assertTrue(len(result['entries']) > 72)
 
+    def test_vine_user(self):
+        dl = FakeYDL()
+        ie = VineUserIE(dl)
+        result = ie.extract('https://vine.co/Visa')
+        self.assertIsPlaylist(result)
+        assertGreaterEqual(self, len(result['entries']), 47)
+
     def test_ustream_channel(self):
         dl = FakeYDL()
         ie = UstreamChannelIE(dl)
-        result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty')
+        result = ie.extract('http://www.ustream.tv/channel/channeljapan')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '5124905')
-        self.assertTrue(len(result['entries']) >= 6)
+        self.assertEqual(result['id'], '10874166')
+        assertGreaterEqual(self, len(result['entries']), 54)
 
     def test_soundcloud_set(self):
         dl = FakeYDL()
@@ -114,7 +128,7 @@ class TestPlaylists(unittest.TestCase):
         result = ie.extract('https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep')
         self.assertIsPlaylist(result)
         self.assertEqual(result['title'], 'The Royal Concept EP')
-        self.assertTrue(len(result['entries']) >= 6)
+        assertGreaterEqual(self, len(result['entries']), 6)
 
     def test_soundcloud_user(self):
         dl = FakeYDL()
@@ -122,7 +136,26 @@ class TestPlaylists(unittest.TestCase):
         result = ie.extract('https://soundcloud.com/the-concept-band')
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], '9615865')
-        self.assertTrue(len(result['entries']) >= 12)
+        assertGreaterEqual(self, len(result['entries']), 12)
+
+    def test_soundcloud_likes(self):
+        dl = FakeYDL()
+        ie = SoundcloudUserIE(dl)
+        result = ie.extract('https://soundcloud.com/the-concept-band/likes')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '9615865')
+        assertGreaterEqual(self, len(result['entries']), 1)
+
+    def test_soundcloud_playlist(self):
+        dl = FakeYDL()
+        ie = SoundcloudPlaylistIE(dl)
+        result = ie.extract('http://api.soundcloud.com/playlists/4110309')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '4110309')
+        self.assertEqual(result['title'], 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]')
+        assertRegexpMatches(
+            self, result['description'], r'TILT Brass - Bowery Poetry Club')
+        self.assertEqual(len(result['entries']), 6)
 
     def test_livestream_event(self):
         dl = FakeYDL()
@@ -130,7 +163,15 @@ class TestPlaylists(unittest.TestCase):
         result = ie.extract('http://new.livestream.com/tedx/cityenglish')
         self.assertIsPlaylist(result)
         self.assertEqual(result['title'], 'TEDCity2.0 (English)')
-        self.assertTrue(len(result['entries']) >= 4)
+        assertGreaterEqual(self, len(result['entries']), 4)
+
+    def test_livestreamoriginal_folder(self):
+        dl = FakeYDL()
+        ie = LivestreamOriginalIE(dl)
+        result = ie.extract('https://www.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'a07bf706-d0e4-4e75-a747-b021d84f2fd3')
+        assertGreaterEqual(self, len(result['entries']), 28)
 
     def test_nhl_videocenter(self):
         dl = FakeYDL()
@@ -147,7 +188,7 @@ class TestPlaylists(unittest.TestCase):
         result = ie.extract('http://bambuser.com/channel/pixelversity')
         self.assertIsPlaylist(result)
         self.assertEqual(result['title'], 'pixelversity')
-        self.assertTrue(len(result['entries']) >= 60)
+        assertGreaterEqual(self, len(result['entries']), 60)
 
     def test_bandcamp_album(self):
         dl = FakeYDL()
@@ -155,7 +196,7 @@ class TestPlaylists(unittest.TestCase):
         result = ie.extract('http://mpallante.bandcamp.com/album/nightmare-night-ep')
         self.assertIsPlaylist(result)
         self.assertEqual(result['title'], 'Nightmare Night EP')
-        self.assertTrue(len(result['entries']) >= 4)
+        assertGreaterEqual(self, len(result['entries']), 4)
         
     def test_smotri_community(self):
         dl = FakeYDL()
@@ -164,7 +205,7 @@ class TestPlaylists(unittest.TestCase):
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], 'kommuna')
         self.assertEqual(result['title'], 'КПРФ')
-        self.assertTrue(len(result['entries']) >= 4)
+        assertGreaterEqual(self, len(result['entries']), 4)
         
     def test_smotri_user(self):
         dl = FakeYDL()
@@ -173,7 +214,7 @@ class TestPlaylists(unittest.TestCase):
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], 'inspector')
         self.assertEqual(result['title'], 'Inspector')
-        self.assertTrue(len(result['entries']) >= 9)
+        assertGreaterEqual(self, len(result['entries']), 9)
 
     def test_AcademicEarthCourse(self):
         dl = FakeYDL()
@@ -188,20 +229,20 @@ class TestPlaylists(unittest.TestCase):
     def test_ivi_compilation(self):
         dl = FakeYDL()
         ie = IviCompilationIE(dl)
-        result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel')
+        result = ie.extract('http://www.ivi.ru/watch/dvoe_iz_lartsa')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'dezhurnyi_angel')
-        self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012)')
-        self.assertTrue(len(result['entries']) >= 36)
+        self.assertEqual(result['id'], 'dvoe_iz_lartsa')
+        self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008)')
+        assertGreaterEqual(self, len(result['entries']), 24)
 
     def test_ivi_compilation_season(self):
         dl = FakeYDL()
         ie = IviCompilationIE(dl)
-        result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel/season2')
+        result = ie.extract('http://www.ivi.ru/watch/dvoe_iz_lartsa/season1')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'dezhurnyi_angel/season2')
-        self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012) 2 сезон')
-        self.assertTrue(len(result['entries']) >= 20)
+        self.assertEqual(result['id'], 'dvoe_iz_lartsa/season1')
+        self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008) 1 сезон')
+        assertGreaterEqual(self, len(result['entries']), 12)
         
     def test_imdb_list(self):
         dl = FakeYDL()
@@ -220,7 +261,7 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['id'], 'cryptography')
         self.assertEqual(result['title'], 'Journey into cryptography')
         self.assertEqual(result['description'], 'How have humans protected their secret messages through history? What has changed today?')
-        self.assertTrue(len(result['entries']) >= 3)
+        assertGreaterEqual(self, len(result['entries']), 3)
 
     def test_EveryonesMixtape(self):
         dl = FakeYDL()
@@ -234,10 +275,18 @@ class TestPlaylists(unittest.TestCase):
     def test_rutube_channel(self):
         dl = FakeYDL()
         ie = RutubeChannelIE(dl)
-        result = ie.extract('http://rutube.ru/tags/video/1409')
+        result = ie.extract('http://rutube.ru/tags/video/1800/')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '1409')
-        self.assertTrue(len(result['entries']) >= 34)
+        self.assertEqual(result['id'], '1800')
+        assertGreaterEqual(self, len(result['entries']), 68)
+
+    def test_rutube_person(self):
+        dl = FakeYDL()
+        ie = RutubePersonIE(dl)
+        result = ie.extract('http://rutube.ru/video/person/313878/')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '313878')
+        assertGreaterEqual(self, len(result['entries']), 37)
 
     def test_multiple_brightcove_videos(self):
         # https://github.com/rg3/youtube-dl/issues/2283
@@ -274,7 +323,7 @@ class TestPlaylists(unittest.TestCase):
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], '10')
         self.assertEqual(result['title'], 'Who are the hackers?')
-        self.assertTrue(len(result['entries']) >= 6)
+        assertGreaterEqual(self, len(result['entries']), 6)
 
     def test_toypics_user(self):
         dl = FakeYDL()
@@ -282,7 +331,7 @@ class TestPlaylists(unittest.TestCase):
         result = ie.extract('http://videos.toypics.net/Mikey')
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], 'Mikey')
-        self.assertTrue(len(result['entries']) >= 17)
+        assertGreaterEqual(self, len(result['entries']), 17)
 
     def test_xtube_user(self):
         dl = FakeYDL()
@@ -290,7 +339,7 @@ class TestPlaylists(unittest.TestCase):
         result = ie.extract('http://www.xtube.com/community/profile.php?user=greenshowers')
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], 'greenshowers')
-        self.assertTrue(len(result['entries']) >= 155)
+        assertGreaterEqual(self, len(result['entries']), 155)
 
     def test_InstagramUser(self):
         dl = FakeYDL()
@@ -298,7 +347,7 @@ class TestPlaylists(unittest.TestCase):
         result = ie.extract('http://instagram.com/porsche')
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], 'porsche')
-        self.assertTrue(len(result['entries']) >= 2)
+        assertGreaterEqual(self, len(result['entries']), 2)
         test_video = next(
             e for e in result['entries']
             if e['id'] == '614605558512799803_462752227')
@@ -337,7 +386,15 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['id'], '152147')
         self.assertEqual(
             result['title'], 'Brace Yourself - Today\'s Weirdest News')
-        self.assertTrue(len(result['entries']) >= 10)
+        assertGreaterEqual(self, len(result['entries']), 10)
+
+    def test_TeacherTubeUser(self):
+        dl = FakeYDL()
+        ie = TeacherTubeUserIE(dl)
+        result = ie.extract('http://www.teachertube.com/user/profile/rbhagwati2')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'rbhagwati2')
+        assertGreaterEqual(self, len(result['entries']), 179)
 
 if __name__ == '__main__':
     unittest.main()

test/test_subtitles.py

@@ -87,7 +87,7 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
 
     def test_youtube_nosubtitles(self):
         self.DL.expect_warning(u'video doesn\'t have subtitles')
-        self.url = 'sAjKT8FhjI8'
+        self.url = 'n5BB19UTcdA'
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
@@ -181,7 +181,7 @@ class TestTedSubtitles(BaseTestSubtitles):
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(len(subtitles.keys()), 28)
+        self.assertTrue(len(subtitles.keys()) >= 28)
 
     def test_list_subtitles(self):
         self.DL.expect_warning(u'Automatic Captions not supported by this server')

test/test_swfinterp.py

@@ -0,0 +1,77 @@
+#!/usr/bin/env python
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+import errno
+import io
+import json
+import re
+import subprocess
+
+from youtube_dl.swfinterp import SWFInterpreter
+
+
+TEST_DIR = os.path.join(
+    os.path.dirname(os.path.abspath(__file__)), 'swftests')
+
+
+class TestSWFInterpreter(unittest.TestCase):
+    pass
+
+
+def _make_testfunc(testfile):
+    m = re.match(r'^(.*)\.(as)$', testfile)
+    if not m:
+        return
+    test_id = m.group(1)
+
+    def test_func(self):
+        as_file = os.path.join(TEST_DIR, testfile)
+        swf_file = os.path.join(TEST_DIR, test_id + '.swf')
+        if ((not os.path.exists(swf_file))
+                or os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
+            # Recompile
+            try:
+                subprocess.check_call(['mxmlc', '-output', swf_file, as_file])
+            except OSError as ose:
+                if ose.errno == errno.ENOENT:
+                    print('mxmlc not found! Skipping test.')
+                    return
+                raise
+
+        with open(swf_file, 'rb') as swf_f:
+            swf_content = swf_f.read()
+        swfi = SWFInterpreter(swf_content)
+
+        with io.open(as_file, 'r', encoding='utf-8') as as_f:
+            as_content = as_f.read()
+
+        def _find_spec(key):
+            m = re.search(
+                r'(?m)^//\s*%s:\s*(.*?)\n' % re.escape(key), as_content)
+            if not m:
+                raise ValueError('Cannot find %s in %s' % (key, testfile))
+            return json.loads(m.group(1))
+
+        input_args = _find_spec('input')
+        output = _find_spec('output')
+
+        swf_class = swfi.extract_class(test_id)
+        func = swfi.extract_function(swf_class, 'main')
+        res = func(input_args)
+        self.assertEqual(res, output)
+
+    test_func.__name__ = str('test_swf_' + test_id)
+    setattr(TestSWFInterpreter, test_func.__name__, test_func)
+
+
+for testfile in os.listdir(TEST_DIR):
+    _make_testfunc(testfile)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_youtube_lists.py

@@ -112,11 +112,11 @@ class TestYoutubeLists(unittest.TestCase):
     def test_youtube_mix(self):
         dl = FakeYDL()
         ie = YoutubePlaylistIE(dl)
-        result = ie.extract('http://www.youtube.com/watch?v=lLJf9qJHR3E&list=RDrjFaenf1T-Y')
+        result = ie.extract('https://www.youtube.com/watch?v=W01L70IGBgE&index=2&list=RDOQpdSVF_k_w')
         entries = result['entries']
         self.assertTrue(len(entries) >= 20)
         original_video = entries[0]
-        self.assertEqual(original_video['id'], 'rjFaenf1T-Y')
+        self.assertEqual(original_video['id'], 'OQpdSVF_k_w')
 
     def test_youtube_toptracks(self):
         print('Skipping: The playlist page gives error 500')

test/test_youtube_signature.py

@@ -33,6 +33,30 @@ _TESTS = [
         90,
         u']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876',
     ),
+    (
+        u'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl0Cbn9e.js',
+        u'js',
+        84,
+        u'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVW@YZ!"#$%&\'()*+,-./:;<=',
+    ),
+    (
+        u'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js',
+        u'js',
+        u'2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA',
+        u'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2',
+    ),
+    (
+        u'http://s.ytimg.com/yts/swfbin/player-vfl5vIhK2/watch_as3.swf',
+        u'swf',
+        86,
+        u'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVWXY\\!"#$%&\'()*+,-./:;<=>?'
+    ),
+    (
+        u'http://s.ytimg.com/yts/swfbin/player-vflmDyk47/watch_as3.swf',
+        u'swf',
+        u'F375F75BF2AFDAAF2666E43868D46816F83F13E81C46.3725A8218E446A0DECD33F79DC282994D6AA92C92C9',
+        u'9C29AA6D499282CD97F33DCED0A644E8128A5273.64C18E31F38361864D86834E6662FAADFA2FB57F'
+    ),
 ]
 
 
@@ -44,13 +68,13 @@ class TestSignature(unittest.TestCase):
             os.mkdir(self.TESTDATA_DIR)
 
 
-def make_tfunc(url, stype, sig_length, expected_sig):
-    basename = url.rpartition('/')[2]
-    m = re.match(r'.*-([a-zA-Z0-9_-]+)\.[a-z]+$', basename)
-    assert m, '%r should follow URL format' % basename
+def make_tfunc(url, stype, sig_input, expected_sig):
+    m = re.match(r'.*-([a-zA-Z0-9_-]+)(?:/watch_as3)?\.[a-z]+$', url)
+    assert m, '%r should follow URL format' % url
     test_id = m.group(1)
 
     def test_func(self):
+        basename = 'player-%s.%s' % (test_id, stype)
         fn = os.path.join(self.TESTDATA_DIR, basename)
 
         if not os.path.exists(fn):
@@ -66,7 +90,9 @@ def make_tfunc(url, stype, sig_length, expected_sig):
             with open(fn, 'rb') as testf:
                 swfcode = testf.read()
             func = ie._parse_sig_swf(swfcode)
-        src_sig = compat_str(string.printable[:sig_length])
+        src_sig = (
+            compat_str(string.printable[:sig_input])
+            if isinstance(sig_input, int) else sig_input)
         got_sig = func(src_sig)
         self.assertEqual(got_sig, expected_sig)
 

youtube_dl/YoutubeDL.py

@@ -31,6 +31,7 @@ from .utils import (
     ContentTooShortError,
     date_from_str,
     DateRange,
+    DEFAULT_OUTTMPL,
     determine_ext,
     DownloadError,
     encodeFilename,
@@ -440,7 +441,8 @@ class YoutubeDL(object):
                                  if v is not None)
             template_dict = collections.defaultdict(lambda: 'NA', template_dict)
 
-            tmpl = os.path.expanduser(self.params['outtmpl'])
+            outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
+            tmpl = os.path.expanduser(outtmpl)
             filename = tmpl % template_dict
             return filename
         except ValueError as err:
@@ -715,6 +717,17 @@ class YoutubeDL(object):
             info_dict['playlist'] = None
             info_dict['playlist_index'] = None
 
+        thumbnails = info_dict.get('thumbnails')
+        if thumbnails:
+            thumbnails.sort(key=lambda t: (
+                t.get('width'), t.get('height'), t.get('url')))
+            for t in thumbnails:
+                if 'width' in t and 'height' in t:
+                    t['resolution'] = '%dx%d' % (t['width'], t['height'])
+
+        if thumbnails and 'thumbnail' not in info_dict:
+            info_dict['thumbnail'] = thumbnails[-1]['url']
+
         if 'display_id' not in info_dict and 'id' in info_dict:
             info_dict['display_id'] = info_dict['id']
 
@@ -980,6 +993,8 @@ class YoutubeDL(object):
                         fd = get_suitable_downloader(info)(self, self.params)
                         for ph in self._progress_hooks:
                             fd.add_progress_hook(ph)
+                        if self.params.get('verbose'):
+                            self.to_stdout('[debug] Invoking downloader on %r' % info.get('url'))
                         return fd.download(name, info)
                     if info_dict.get('requested_formats') is not None:
                         downloaded = []
@@ -1025,10 +1040,11 @@ class YoutubeDL(object):
 
     def download(self, url_list):
         """Download a given list of URLs."""
+        outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
         if (len(url_list) > 1 and
-                '%' not in self.params['outtmpl']
+                '%' not in outtmpl
                 and self.params.get('max_downloads') != 1):
-            raise SameFileError(self.params['outtmpl'])
+            raise SameFileError(outtmpl)
 
         for url in url_list:
             try:
@@ -1139,57 +1155,61 @@ class YoutubeDL(object):
             res = default
         return res
 
-    def list_formats(self, info_dict):
-        def format_note(fdict):
-            res = ''
-            if fdict.get('ext') in ['f4f', 'f4m']:
-                res += '(unsupported) '
-            if fdict.get('format_note') is not None:
-                res += fdict['format_note'] + ' '
-            if fdict.get('tbr') is not None:
-                res += '%4dk ' % fdict['tbr']
-            if fdict.get('container') is not None:
-                if res:
-                    res += ', '
-                res += '%s container' % fdict['container']
-            if (fdict.get('vcodec') is not None and
-                    fdict.get('vcodec') != 'none'):
-                if res:
-                    res += ', '
-                res += fdict['vcodec']
-                if fdict.get('vbr') is not None:
-                    res += '@'
-            elif fdict.get('vbr') is not None and fdict.get('abr') is not None:
-                res += 'video@'
+    def _format_note(self, fdict):
+        res = ''
+        if fdict.get('ext') in ['f4f', 'f4m']:
+            res += '(unsupported) '
+        if fdict.get('format_note') is not None:
+            res += fdict['format_note'] + ' '
+        if fdict.get('tbr') is not None:
+            res += '%4dk ' % fdict['tbr']
+        if fdict.get('container') is not None:
+            if res:
+                res += ', '
+            res += '%s container' % fdict['container']
+        if (fdict.get('vcodec') is not None and
+                fdict.get('vcodec') != 'none'):
+            if res:
+                res += ', '
+            res += fdict['vcodec']
             if fdict.get('vbr') is not None:
-                res += '%4dk' % fdict['vbr']
-            if fdict.get('acodec') is not None:
-                if res:
-                    res += ', '
-                if fdict['acodec'] == 'none':
-                    res += 'video only'
-                else:
-                    res += '%-5s' % fdict['acodec']
-            elif fdict.get('abr') is not None:
-                if res:
-                    res += ', '
-                res += 'audio'
-            if fdict.get('abr') is not None:
-                res += '@%3dk' % fdict['abr']
-            if fdict.get('asr') is not None:
-                res += ' (%5dHz)' % fdict['asr']
-            if fdict.get('filesize') is not None:
-                if res:
-                    res += ', '
-                res += format_bytes(fdict['filesize'])
-            return res
+                res += '@'
+        elif fdict.get('vbr') is not None and fdict.get('abr') is not None:
+            res += 'video@'
+        if fdict.get('vbr') is not None:
+            res += '%4dk' % fdict['vbr']
+        if fdict.get('acodec') is not None:
+            if res:
+                res += ', '
+            if fdict['acodec'] == 'none':
+                res += 'video only'
+            else:
+                res += '%-5s' % fdict['acodec']
+        elif fdict.get('abr') is not None:
+            if res:
+                res += ', '
+            res += 'audio'
+        if fdict.get('abr') is not None:
+            res += '@%3dk' % fdict['abr']
+        if fdict.get('asr') is not None:
+            res += ' (%5dHz)' % fdict['asr']
+        if fdict.get('filesize') is not None:
+            if res:
+                res += ', '
+            res += format_bytes(fdict['filesize'])
+        elif fdict.get('filesize_approx') is not None:
+            if res:
+                res += ', '
+            res += '~' + format_bytes(fdict['filesize_approx'])
+        return res
 
+    def list_formats(self, info_dict):
         def line(format, idlen=20):
             return (('%-' + compat_str(idlen + 1) + 's%-10s%-12s%s') % (
                 format['format_id'],
                 format['ext'],
                 self.format_resolution(format),
-                format_note(format),
+                self._format_note(format),
             ))
 
         formats = info_dict.get('formats', [info_dict])
@@ -1197,8 +1217,8 @@ class YoutubeDL(object):
                     max(len(f['format_id']) for f in formats))
         formats_s = [line(f, idlen) for f in formats]
         if len(formats) > 1:
-            formats_s[0] += (' ' if format_note(formats[0]) else '') + '(worst)'
-            formats_s[-1] += (' ' if format_note(formats[-1]) else '') + '(best)'
+            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({
             'format_id': 'format code', 'ext': 'extension',

youtube_dl/__init__.py

@@ -53,17 +53,28 @@ __authors__  = (
     'Mattias Harrysson',
     'phaer',
     'Sainyam Kapoor',
+    'Nicolas Évrard',
+    'Jason Normore',
+    'Hoje Lee',
+    'Adam Thalhammer',
+    'Georg Jähnig',
+    'Ralf Haring',
+    'Koki Takahashi',
+    'Ariset Llerena',
+    'Adam Malcontenti-Wilson',
+    'Tobias Bell',
+    'Naglis Jonaitis',
+    'Charles Chen',
+    'Hassaan Ali',
 )
 
 __license__ = 'Public Domain'
 
 import codecs
 import io
-import locale
 import optparse
 import os
 import random
-import re
 import shlex
 import sys
 
@@ -72,6 +83,7 @@ from .utils import (
     compat_getpass,
     compat_print,
     DateRange,
+    DEFAULT_OUTTMPL,
     decodeOption,
     get_term_width,
     DownloadError,
@@ -262,7 +274,7 @@ def parseOpts(overrideArguments=None):
     general.add_option(
         '--default-search',
         dest='default_search', metavar='PREFIX',
-        help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for  youtube-dl "large apple". By default (with value "auto") youtube-dl guesses.')
+        help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for  youtube-dl "large apple". Use the value "auto" to let youtube-dl guess. The default value "error" just throws an error.')
     general.add_option(
         '--ignore-config',
         action='store_true',
@@ -498,7 +510,7 @@ def parseOpts(overrideArguments=None):
     postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='5',
             help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5)')
     postproc.add_option('--recode-video', metavar='FORMAT', dest='recodevideo', default=None,
-            help='Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm)')
+            help='Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)')
     postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
             help='keeps the video file on disk after the post-processing; the video is erased by default')
     postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False,
@@ -621,7 +633,7 @@ def _real_main(argv=None):
             if desc is False:
                 continue
             if hasattr(ie, 'SEARCH_KEY'):
-                _SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise')
+                _SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise', u'sleeping bunny')
                 _COUNTS = (u'', u'5', u'10', u'all')
                 desc += u' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
             compat_print(desc)
@@ -676,7 +688,7 @@ def _real_main(argv=None):
         if not opts.audioquality.isdigit():
             parser.error(u'invalid audio quality specified')
     if opts.recodevideo is not None:
-        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg']:
+        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
             parser.error(u'invalid video recode format specified')
     if opts.date is not None:
         date = DateRange.day(opts.date)
@@ -705,7 +717,7 @@ def _real_main(argv=None):
             or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s')
             or (opts.useid and u'%(id)s.%(ext)s')
             or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
-            or u'%(title)s-%(id)s.%(ext)s')
+            or DEFAULT_OUTTMPL)
     if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
         parser.error(u'Cannot download a video and extract audio into the same'
                      u' file! Use "{0}.%(ext)s" instead of "{0}" as the output'

youtube_dl/downloader/hls.py

@@ -25,7 +25,7 @@ class HlsFD(FileDownloader):
             except (OSError, IOError):
                 pass
         else:
-            self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found')
+            self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
         cmd = [program] + args
 
         retval = subprocess.call(cmd)

youtube_dl/downloader/http.py

@@ -14,6 +14,8 @@ from ..utils import (
 
 
 class HttpFD(FileDownloader):
+    _TEST_FILE_SIZE = 10241
+
     def real_download(self, filename, info_dict):
         url = info_dict['url']
         tmpfilename = self.temp_name(filename)
@@ -28,8 +30,10 @@ class HttpFD(FileDownloader):
         basic_request = compat_urllib_request.Request(url, None, headers)
         request = compat_urllib_request.Request(url, None, headers)
 
-        if self.params.get('test', False):
-            request.add_header('Range', 'bytes=0-10240')
+        is_test = self.params.get('test', False)
+
+        if is_test:
+            request.add_header('Range', 'bytes=0-%s' % str(self._TEST_FILE_SIZE - 1))
 
         # Establish possible resume length
         if os.path.isfile(encodeFilename(tmpfilename)):
@@ -100,6 +104,15 @@ class HttpFD(FileDownloader):
             return False
 
         data_len = data.info().get('Content-length', None)
+
+        # Range HTTP header may be ignored/unsupported by a webserver
+        # (e.g. extractor/scivee.py, extractor/bambuser.py).
+        # However, for a test we still would like to download just a piece of a file.
+        # To achieve this we limit data_len to _TEST_FILE_SIZE and manually control
+        # block size when downloading a file.
+        if is_test and (data_len is None or int(data_len) > self._TEST_FILE_SIZE):
+            data_len = self._TEST_FILE_SIZE
+
         if data_len is not None:
             data_len = int(data_len) + resume_len
             min_data_len = self.params.get("min_filesize", None)
@@ -118,7 +131,7 @@ class HttpFD(FileDownloader):
         while True:
             # Download and write
             before = time.time()
-            data_block = data.read(block_size)
+            data_block = data.read(block_size if not is_test else min(block_size, data_len - byte_counter))
             after = time.time()
             if len(data_block) == 0:
                 break
@@ -162,6 +175,9 @@ class HttpFD(FileDownloader):
                 'speed': speed,
             })
 
+            if is_test and byte_counter == data_len:
+                break
+
             # Apply rate limit
             self.slow_down(start, byte_counter - resume_len)
 

youtube_dl/downloader/rtmp.py

@@ -10,6 +10,7 @@ from .common import FileDownloader
 from ..utils import (
     encodeFilename,
     format_bytes,
+    compat_str,
 )
 
 
@@ -95,6 +96,7 @@ class RtmpFD(FileDownloader):
         flash_version = info_dict.get('flash_version', None)
         live = info_dict.get('rtmp_live', False)
         conn = info_dict.get('rtmp_conn', None)
+        protocol = info_dict.get('rtmp_protocol', None)
 
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
@@ -104,7 +106,7 @@ class RtmpFD(FileDownloader):
         try:
             subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
         except (OSError, IOError):
-            self.report_error('RTMP download detected but "rtmpdump" could not be run')
+            self.report_error('RTMP download detected but "rtmpdump" could not be run. Please install it.')
             return False
 
         # Download using rtmpdump. rtmpdump returns exit code 2 when
@@ -127,8 +129,13 @@ class RtmpFD(FileDownloader):
             basic_args += ['--flashVer', flash_version]
         if live:
             basic_args += ['--live']
-        if conn:
+        if isinstance(conn, list):
+            for entry in conn:
+                basic_args += ['--conn', entry]
+        elif isinstance(conn, compat_str):
             basic_args += ['--conn', conn]
+        if protocol is not None:
+            basic_args += ['--protocol', protocol]
         args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
 
         if sys.platform == 'win32' and sys.version_info < (3, 0):

youtube_dl/extractor/__init__.py

@@ -1,8 +1,10 @@
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
+from .adultswim import AdultSwimIE
 from .aftonbladet import AftonbladetIE
 from .anitube import AnitubeIE
 from .aol import AolIE
+from .allocine import AllocineIE
 from .aparat import AparatIE
 from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
@@ -20,6 +22,7 @@ from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
+from .bilibili import BiliBiliIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
@@ -40,6 +43,7 @@ from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
+from .clubic import ClubicIE
 from .cmt import CMTIE
 from .cnet import CNETIE
 from .cnn import (
@@ -49,6 +53,7 @@ from .cnn import (
 from .collegehumor import CollegeHumorIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .condenast import CondeNastIE
+from .cracked import CrackedIE
 from .criterion import CriterionIE
 from .crunchyroll import CrunchyrollIE
 from .cspan import CSpanIE
@@ -59,8 +64,10 @@ from .dailymotion import (
     DailymotionUserIE,
 )
 from .daum import DaumIE
+from .dfb import DFBIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
+from .drtv import DRTVIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .divxstage import DivxStageIE
@@ -70,6 +77,7 @@ from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .eitb import EitbIE
 from .elpais import ElPaisIE
+from .empflix import EmpflixIE
 from .engadget import EngadgetIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
@@ -77,6 +85,8 @@ from .exfm import ExfmIE
 from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
+from .fc2 import FC2IE
+from .firedrive import FiredriveIE
 from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
@@ -99,18 +109,23 @@ from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
 from .funnyordie import FunnyOrDieIE
 from .gamekings import GamekingsIE
+from .gameone import GameOneIE
 from .gamespot import GameSpotIE
 from .gametrailers import GametrailersIE
 from .gdcvault import GDCVaultIE
 from .generic import GenericIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
+from .gorillavid import GorillaVidIE
+from .goshgay import GoshgayIE
 from .hark import HarkIE
 from .helsinki import HelsinkiIE
+from .hentaistigma import HentaiStigmaIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
 from .huffpost import HuffPostIE
 from .hypem import HypemIE
+from .iconosquare import IconosquareIE
 from .ign import IGNIE, OneUPIE
 from .imdb import (
     ImdbIE,
@@ -136,10 +151,15 @@ from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
 from .kontrtube import KontrTubeIE
+from .ku6 import Ku6IE
 from .la7 import LA7IE
 from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
-from .livestream import LivestreamIE, LivestreamOriginalIE
+from .livestream import (
+    LivestreamIE,
+    LivestreamOriginalIE,
+    LivestreamShortenerIE,
+)
 from .lynda import (
     LyndaIE,
     LyndaCourseIE
@@ -153,14 +173,18 @@ from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mixcloud import MixcloudIE
+from .mlb import MLBIE
 from .mpora import MporaIE
 from .mofosex import MofosexIE
 from .mooshare import MooshareIE
 from .morningstar import MorningstarIE
+from .motherless import MotherlessIE
 from .motorsport import MotorsportIE
+from .moviezine import MoviezineIE
 from .movshare import MovShareIE
 from .mtv import (
     MTVIE,
+    MTVServicesEmbeddedIE,
     MTVIggyIE,
 )
 from .musicplayon import MusicPlayOnIE
@@ -177,15 +201,24 @@ from .nbc import (
 from .ndr import NDRIE
 from .ndtv import NDTVIE
 from .newgrounds import NewgroundsIE
+from .newstube import NewstubeIE
 from .nfb import NFBIE
 from .nhl import NHLIE, NHLVideocenterIE
 from .niconico import NiconicoIE
 from .ninegag import NineGagIE
+from .noco import NocoIE
 from .normalboots import NormalbootsIE
 from .novamov import NovaMovIE
 from .nowness import NownessIE
 from .nowvideo import NowVideoIE
+from .npo import NPOIE
+from .nrk import (
+    NRKIE,
+    NRKTVIE,
+)
 from .ntv import NTVIE
+from .nytimes import NYTimesIE
+from .nuvid import NuvidIE
 from .oe1 import OE1IE
 from .ooyala import OoyalaIE
 from .orf import ORFIE
@@ -200,15 +233,19 @@ from .pornotube import PornotubeIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
 from .radiofrance import RadioFranceIE
+from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
 from .redtube import RedTubeIE
+from .reverbnation import ReverbNationIE
 from .ringtv import RingTVIE
 from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
+from .rtbf import RTBFIE
 from .rtlnow import RTLnowIE
 from .rts import RTSIE
 from .rtve import RTVEALaCartaIE
+from .ruhd import RUHDIE
 from .rutube import (
     RutubeIE,
     RutubeChannelIE,
@@ -216,41 +253,62 @@ from .rutube import (
     RutubePersonIE,
 )
 from .rutv import RUTVIE
+from .sapo import SapoIE
 from .savefrom import SaveFromIE
+from .scivee import SciVeeIE
+from .screencast import ScreencastIE
 from .servingsys import ServingSysIE
 from .sina import SinaIE
 from .slideshare import SlideshareIE
+from .slutload import SlutloadIE
 from .smotri import (
     SmotriIE,
     SmotriCommunityIE,
     SmotriUserIE,
     SmotriBroadcastIE,
 )
+from .snotr import SnotrIE
+from .sockshare import SockshareIE
 from .sohu import SohuIE
-from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE
-from .southparkstudios import (
-    SouthParkStudiosIE,
+from .soundcloud import (
+    SoundcloudIE,
+    SoundcloudSetIE,
+    SoundcloudUserIE,
+    SoundcloudPlaylistIE
+)
+from .soundgasm import SoundgasmIE
+from .southpark import (
+    SouthParkIE,
     SouthparkDeIE,
 )
 from .space import SpaceIE
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE
+from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
 from .stanfordoc import StanfordOpenClassroomIE
-from .statigram import StatigramIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
+from .swrmediathek import SWRMediathekIE
 from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
+from .tagesschau import TagesschauIE
+from .teachertube import (
+    TeacherTubeIE,
+    TeacherTubeUserIE,
+)
+from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
+from .tenplay import TenPlayIE
 from .testurl import TestURLIE
 from .tf1 import TF1IE
 from .theplatform import ThePlatformIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
+from .tlc import TlcIE, TlcDeIE
 from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
@@ -274,12 +332,14 @@ from .veehd import VeeHDIE
 from .veoh import VeohIE
 from .vesti import VestiIE
 from .vevo import VevoIE
+from .vh1 import VH1IE
 from .viddler import ViddlerIE
 from .videobam import VideoBamIE
 from .videodetective import VideoDetectiveIE
 from .videolecturesnet import VideoLecturesNetIE
 from .videofyme import VideofyMeIE
 from .videopremium import VideoPremiumIE
+from .videott import VideoTtIE
 from .videoweed import VideoWeedIE
 from .vimeo import (
     VimeoIE,
@@ -288,21 +348,31 @@ from .vimeo import (
     VimeoAlbumIE,
     VimeoGroupsIE,
     VimeoReviewIE,
+    VimeoWatchLaterIE,
+)
+from .vimple import VimpleIE
+from .vine import (
+    VineIE,
+    VineUserIE,
 )
-from .vine import VineIE
 from .viki import VikiIE
 from .vk import VKIE
+from .vodlocker import VodlockerIE
 from .vube import VubeIE
+from .vuclip import VuClipIE
+from .vulture import VultureIE
 from .washingtonpost import WashingtonPostIE
 from .wat import WatIE
 from .wdr import (
     WDRIE,
+    WDRMobileIE,
     WDRMausIE,
 )
 from .weibo import WeiboIE
 from .wimp import WimpIE
 from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
+from .wrzuta import WrzutaIE
 from .xbef import XBefIE
 from .xhamster import XHamsterIE
 from .xnxx import XNXXIE
@@ -333,6 +403,7 @@ from .youtube import (
     YoutubeUserIE,
     YoutubeWatchLaterIE,
 )
+
 from .zdf import ZDFIE
 
 

youtube_dl/extractor/adultswim.py

@@ -0,0 +1,139 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+class AdultSwimIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$'
+    _TEST = {
+        'url': 'http://video.adultswim.com/rick-and-morty/close-rick-counters-of-the-rick-kind.html?x=y#title',
+        'playlist': [
+            {
+                'md5': '4da359ec73b58df4575cd01a610ba5dc',
+                'info_dict': {
+                    'id': '8a250ba1450996e901453d7f02ca02f5',
+                    'ext': 'flv',
+                    'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 1',
+                    'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
+                    'uploader': 'Rick and Morty',
+                    'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
+                }
+            },
+            {
+                'md5': 'ffbdf55af9331c509d95350bd0cc1819',
+                'info_dict': {
+                    'id': '8a250ba1450996e901453d7f4bd102f6',
+                    'ext': 'flv',
+                    'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 2',
+                    'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
+                    'uploader': 'Rick and Morty',
+                    'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
+                }
+            },
+            {
+                'md5': 'b92409635540304280b4b6c36bd14a0a',
+                'info_dict': {
+                    'id': '8a250ba1450996e901453d7fa73c02f7',
+                    'ext': 'flv',
+                    'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 3',
+                    'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
+                    'uploader': 'Rick and Morty',
+                    'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
+                }
+            },
+            {
+                'md5': 'e8818891d60e47b29cd89d7b0278156d',
+                'info_dict': {
+                    'id': '8a250ba1450996e901453d7fc8ba02f8',
+                    'ext': 'flv',
+                    'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 4',
+                    'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
+                    'uploader': 'Rick and Morty',
+                    'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
+                }
+            }
+        ]
+    }
+
+    _video_extensions = {
+        '3500': 'flv',
+        '640': 'mp4',
+        '150': 'mp4',
+        'ipad': 'm3u8',
+        'iphone': 'm3u8'
+    }
+    _video_dimensions = {
+        '3500': (1280, 720),
+        '640': (480, 270),
+        '150': (320, 180)
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_path = mobj.group('path')
+
+        webpage = self._download_webpage(url, video_path)
+        episode_id = self._html_search_regex(r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>', webpage, 'episode_id')
+        title = self._og_search_title(webpage)
+
+        index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id
+        idoc = self._download_xml(index_url, title, 'Downloading episode index', 'Unable to download episode index')
+
+        episode_el = idoc.find('.//episode')
+        show_title = episode_el.attrib.get('collectionTitle')
+        episode_title = episode_el.attrib.get('title')
+        thumbnail = episode_el.attrib.get('thumbnailUrl')
+        description = episode_el.find('./description').text.strip()
+
+        entries = []
+        segment_els = episode_el.findall('./segments/segment')
+
+        for part_num, segment_el in enumerate(segment_els):
+            segment_id = segment_el.attrib.get('id')
+            segment_title = '%s %s part %d' % (show_title, episode_title, part_num + 1)
+            thumbnail = segment_el.attrib.get('thumbnailUrl')
+            duration = segment_el.attrib.get('duration')
+
+            segment_url = 'http://asfix.adultswim.com/asfix-svc/episodeservices/getCvpPlaylist?networkName=AS&id=%s' % segment_id
+            idoc = self._download_xml(segment_url, segment_title, 'Downloading segment information', 'Unable to download segment information')
+
+            formats = []
+            file_els = idoc.findall('.//files/file')
+
+            for file_el in file_els:
+                bitrate = file_el.attrib.get('bitrate')
+                type = file_el.attrib.get('type')
+                width, height = self._video_dimensions.get(bitrate, (None, None))
+                formats.append({
+                    'format_id': '%s-%s' % (bitrate, type),
+                    'url': file_el.text,
+                    'ext': self._video_extensions.get(bitrate, 'mp4'),
+                    # The bitrate may not be a number (for example: 'iphone')
+                    'tbr': int(bitrate) if bitrate.isdigit() else None,
+                    'height': height,
+                    'width': width
+                })
+
+            self._sort_formats(formats)
+
+            entries.append({
+                'id': segment_id,
+                'title': segment_title,
+                'formats': formats,
+                'uploader': show_title,
+                'thumbnail': thumbnail,
+                'duration': duration,
+                'description': description
+            })
+
+        return {
+            '_type': 'playlist',
+            'id': episode_id,
+            'display_id': video_path,
+            'entries': entries,
+            'title': '%s %s' % (show_title, episode_title),
+            'description': description,
+            'thumbnail': thumbnail
+        }

youtube_dl/extractor/aftonbladet.py

@@ -1,7 +1,6 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import datetime
 import re
 
 from .common import InfoExtractor
@@ -16,6 +15,7 @@ class AftonbladetIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
             'description': 'Jupiters måne mest aktiv av alla himlakroppar',
+            'timestamp': 1394142732,
             'upload_date': '20140306',
         },
     }
@@ -27,17 +27,17 @@ class AftonbladetIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         # find internal video meta data
-        META_URL = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
+        meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
         internal_meta_id = self._html_search_regex(
             r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id')
-        internal_meta_url = META_URL % internal_meta_id
+        internal_meta_url = meta_url % internal_meta_id
         internal_meta_json = self._download_json(
             internal_meta_url, video_id, 'Downloading video meta data')
 
         # find internal video formats
-        FORMATS_URL = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
+        format_url = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
         internal_video_id = internal_meta_json['videoId']
-        internal_formats_url = FORMATS_URL % internal_video_id
+        internal_formats_url = format_url % internal_video_id
         internal_formats_json = self._download_json(
             internal_formats_url, video_id, 'Downloading video formats')
 
@@ -54,16 +54,13 @@ class AftonbladetIE(InfoExtractor):
             })
         self._sort_formats(formats)
 
-        timestamp = datetime.datetime.fromtimestamp(internal_meta_json['timePublished'])
-        upload_date = timestamp.strftime('%Y%m%d')
-
         return {
             'id': video_id,
             'title': internal_meta_json['title'],
             'formats': formats,
             'thumbnail': internal_meta_json['imageUrl'],
             'description': internal_meta_json['shortPreamble'],
-            'upload_date': upload_date,
+            'timestamp': internal_meta_json['timePublished'],
             'duration': internal_meta_json['duration'],
             'view_count': internal_meta_json['views'],
         }

youtube_dl/extractor/allocine.py

@@ -0,0 +1,89 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_str,
+    qualities,
+    determine_ext,
+)
+
+
+class AllocineIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=)(?P<id>[0-9]+)(?:\.html)?'
+
+    _TESTS = [{
+        'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
+        'md5': '0c9fcf59a841f65635fa300ac43d8269',
+        'info_dict': {
+            'id': '19546517',
+            'ext': 'mp4',
+            'title': 'Astérix - Le Domaine des Dieux Teaser VF',
+            'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }, {
+        'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
+        'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0',
+        'info_dict': {
+            'id': '19540403',
+            'ext': 'mp4',
+            'title': 'Planes 2 Bande-annonce VF',
+            'description': 'md5:eeaffe7c2d634525e21159b93acf3b1e',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }, {
+        'url': 'http://www.allocine.fr/film/fichefilm_gen_cfilm=181290.html',
+        'md5': '101250fb127ef9ca3d73186ff22a47ce',
+        'info_dict': {
+            'id': '19544709',
+            'ext': 'mp4',
+            'title': 'Dragons 2 - Bande annonce finale VF',
+            'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        typ = mobj.group('typ')
+        display_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        if typ == 'film':
+            video_id = self._search_regex(r'href="/video/player_gen_cmedia=([0-9]+).+"', webpage, 'video id')
+        else:
+            player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player')
+
+            player_data = json.loads(player)
+            video_id = compat_str(player_data['refMedia'])
+
+        xml = self._download_xml('http://www.allocine.fr/ws/AcVisiondataV4.ashx?media=%s' % video_id, display_id)
+
+        video = xml.find('.//AcVisionVideo').attrib
+        quality = qualities(['ld', 'md', 'hd'])
+
+        formats = []
+        for k, v in video.items():
+            if re.match(r'.+_path', k):
+                format_id = k.split('_')[0]
+                formats.append({
+                    'format_id': format_id,
+                    'quality': quality(format_id),
+                    'url': v,
+                    'ext': determine_ext(v),
+                })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video['videoTitle'],
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+        }

youtube_dl/extractor/anitube.py

@@ -1,22 +1,24 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class AnitubeIE(InfoExtractor):
-    IE_NAME = u'anitube.se'
+    IE_NAME = 'anitube.se'
     _VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://www.anitube.se/video/36621',
-        u'md5': u'59d0eeae28ea0bc8c05e7af429998d43',
-        u'file': u'36621.mp4',
-        u'info_dict': {
-            u'id': u'36621',
-            u'ext': u'mp4',
-            u'title': u'Recorder to Randoseru 01',
+        'url': 'http://www.anitube.se/video/36621',
+        'md5': '59d0eeae28ea0bc8c05e7af429998d43',
+        'info_dict': {
+            'id': '36621',
+            'ext': 'mp4',
+            'title': 'Recorder to Randoseru 01',
+            'duration': 180.19,
         },
-        u'skip': u'Blocked in the US',
+        'skip': 'Blocked in the US',
     }
 
     def _real_extract(self, url):
@@ -24,13 +26,15 @@ class AnitubeIE(InfoExtractor):
         video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
-        key = self._html_search_regex(r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)',
-                                      webpage, u'key')
+        key = self._html_search_regex(
+            r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)', webpage, 'key')
 
-        config_xml = self._download_xml('http://www.anitube.se/nuevo/econfig.php?key=%s' % key,
-                                                key)
+        config_xml = self._download_xml(
+            'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key)
 
         video_title = config_xml.find('title').text
+        thumbnail = config_xml.find('image').text
+        duration = float(config_xml.find('duration').text)
 
         formats = []
         video_url = config_xml.find('file')
@@ -49,5 +53,7 @@ class AnitubeIE(InfoExtractor):
         return {
             'id': video_id,
             'title': video_title,
+            'thumbnail': thumbnail,
+            'duration': duration,
             'formats': formats
         }

youtube_dl/extractor/ard.py

@@ -7,23 +7,32 @@ from .common import InfoExtractor
 from ..utils import (
     determine_ext,
     ExtractorError,
+    qualities,
 )
 
 
 class ARDIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
+    _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
 
-    _TEST = {
-        'url': 'http://www.ardmediathek.de/das-erste/guenther-jauch/edward-snowden-im-interview-held-oder-verraeter?documentId=19288786',
-        'file': '19288786.mp4',
-        'md5': '515bf47ce209fb3f5a61b7aad364634c',
+    _TESTS = [{
+        'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
+        'file': '22429276.mp4',
+        'md5': '469751912f1de0816a9fc9df8336476c',
         'info_dict': {
-            'title': 'Edward Snowden im Interview - Held oder Verräter?',
-            'description': 'Edward Snowden hat alles aufs Spiel gesetzt, um die weltweite \xdcberwachung durch die Geheimdienste zu enttarnen. Nun stellt sich der ehemalige NSA-Mitarbeiter erstmals weltweit in einem TV-Interview den Fragen eines NDR-Journalisten. Die Sendung vom Sonntagabend.',
-            'thumbnail': 'http://www.ardmediathek.de/ard/servlet/contentblob/19/28/87/90/19288790/bild/2250037',
+            'title': 'Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?',
+            'description': 'Das Erste Mediathek [ARD]: Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?, Anne Will, Über die Spionage-Affäre diskutieren Clemens Binninger, Katrin Göring-Eckardt, Georg Mascolo, Andrew B. Denison und Constanze Kurz.. Das Video zur Sendung Anne Will am Mittwoch, 16.07.2014',
         },
         'skip': 'Blocked outside of Germany',
-    }
+    }, {
+        'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916',
+        'info_dict': {
+            'id': '22490580',
+            'ext': 'mp4',
+            'title': 'Das Wunder von Wolbeck (Video tgl. ab 20 Uhr)',
+            'description': 'Auf einem restaurierten Hof bei Wolbeck wird der Heilpraktiker Raffael Lembeck eines morgens von seiner Frau Stella tot aufgefunden. Das Opfer war offensichtlich in seiner Praxis zu Fall gekommen und ist dann verblutet, erklärt Prof. Boerne am Tatort.',
+        },
+        'skip': 'Blocked outside of Germany',
+    }]
 
     def _real_extract(self, url):
         # determine video id from url
@@ -38,39 +47,69 @@ class ARDIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         title = self._html_search_regex(
-            r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', webpage, 'title')
+            [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
+             r'<meta name="dcterms.title" content="(.*?)"/>',
+             r'<h4 class="headline">(.*?)</h4>'],
+            webpage, 'title')
         description = self._html_search_meta(
-            'dcterms.abstract', webpage, 'description')
-        thumbnail = self._og_search_thumbnail(webpage)
+            'dcterms.abstract', webpage, 'description', default=None)
+        if description is None:
+            description = self._html_search_meta(
+                'description', webpage, 'meta description')
 
-        streams = [
-            mo.groupdict()
-            for mo in re.finditer(
-                r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)', webpage)]
-        if not streams:
-            if '"fsk"' in webpage:
-                raise ExtractorError('This video is only available after 20:00')
+        # Thumbnail is sometimes not present.
+        # It is in the mobile version, but that seems to use a different URL
+        # structure altogether.
+        thumbnail = self._og_search_thumbnail(webpage, default=None)
 
-        formats = []
-        for s in streams:
-            format = {
-                'quality': int(s['quality']),
-            }
-            if s.get('rtmp_url'):
-                format['protocol'] = 'rtmp'
-                format['url'] = s['rtmp_url']
-                format['playpath'] = s['video_url']
-            else:
-                format['url'] = s['video_url']
+        media_streams = re.findall(r'''(?x)
+            mediaCollection\.addMediaStream\([0-9]+,\s*[0-9]+,\s*"[^"]*",\s*
+            "([^"]+)"''', webpage)
 
-            quality_name = self._search_regex(
-                r'[,.]([a-zA-Z0-9_-]+),?\.mp4', format['url'],
-                'quality name', default='NA')
-            format['format_id'] = '%s-%s-%s-%s' % (
-                determine_ext(format['url']), quality_name, s['media_type'],
-                s['quality'])
+        if media_streams:
+            QUALITIES = qualities(['lo', 'hi', 'hq'])
+            formats = []
+            for furl in set(media_streams):
+                if furl.endswith('.f4m'):
+                    fid = 'f4m'
+                else:
+                    fid_m = re.match(r'.*\.([^.]+)\.[^.]+$', furl)
+                    fid = fid_m.group(1) if fid_m else None
+                formats.append({
+                    'quality': QUALITIES(fid),
+                    'format_id': fid,
+                    'url': furl,
+                })
+        else:  # request JSON file
+            media_info = self._download_json(
+                'http://www.ardmediathek.de/play/media/%s' % video_id, video_id)
+            # The second element of the _mediaArray contains the standard http urls
+            streams = media_info['_mediaArray'][1]['_mediaStreamArray']
+            if not streams:
+                if '"fsk"' in webpage:
+                    raise ExtractorError('This video is only available after 20:00')
 
-            formats.append(format)
+            formats = []
+            for s in streams:
+                if type(s['_stream']) == list:
+                    for index, url in enumerate(s['_stream'][::-1]):
+                        quality = s['_quality'] + index
+                        formats.append({
+                            'quality': quality,
+                            'url': url,
+                            'format_id': '%s-%s' % (determine_ext(url), quality)
+                        })
+                    continue
+
+                format = {
+                    'quality': s['_quality'],
+                    'url': s['_stream'],
+                }
+
+                format['format_id'] = '%s-%s' % (
+                    determine_ext(format['url']), format['quality'])
+
+                formats.append(format)
 
         self._sort_formats(formats)
 

youtube_dl/extractor/arte.py

@@ -39,7 +39,10 @@ class ArteTvIE(InfoExtractor):
 
         formats = [{
             'forma_id': q.attrib['quality'],
-            'url': q.text,
+            # The playpath starts at 'mp4:', if we don't manually
+            # split the url, rtmpdump will incorrectly parse them
+            'url': q.text.split('mp4:', 1)[0],
+            'play_path': 'mp4:' + q.text.split('mp4:', 1)[1],
             'ext': 'flv',
             'quality': 2 if q.attrib['quality'] == 'hd' else 1,
         } for q in config.findall('./urls/url')]
@@ -74,7 +77,8 @@ class ArteTVPlus7IE(InfoExtractor):
         return self._extract_from_webpage(webpage, video_id, lang)
 
     def _extract_from_webpage(self, webpage, video_id, lang):
-        json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
+        json_url = self._html_search_regex(
+            r'arte_vp_url="(.*?)"', webpage, 'json vp url')
         return self._extract_from_json_url(json_url, video_id, lang)
 
     def _extract_from_json_url(self, json_url, video_id, lang):
@@ -110,7 +114,7 @@ class ArteTVPlus7IE(InfoExtractor):
         if not formats:
             # Some videos are only available in the 'Originalversion'
             # they aren't tagged as being in French or German
-            if all(f['versionCode'] == 'VO' for f in all_formats):
+            if all(f['versionCode'] == 'VO' or f['versionCode'] == 'VA' for f in all_formats):
                 formats = all_formats
             else:
                 raise ExtractorError(u'The formats list is empty')
@@ -120,14 +124,17 @@ class ArteTVPlus7IE(InfoExtractor):
                 return ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality'])
         else:
             def sort_key(f):
+                versionCode = f.get('versionCode')
+                if versionCode is None:
+                    versionCode = ''
                 return (
                     # Sort first by quality
-                    int(f.get('height',-1)),
-                    int(f.get('bitrate',-1)),
+                    int(f.get('height', -1)),
+                    int(f.get('bitrate', -1)),
                     # The original version with subtitles has lower relevance
-                    re.match(r'VO-ST(F|A)', f.get('versionCode', '')) is None,
+                    re.match(r'VO-ST(F|A)', versionCode) is None,
                     # The version with sourds/mal subtitles has also lower relevance
-                    re.match(r'VO?(F|A)-STM\1', f.get('versionCode', '')) is None,
+                    re.match(r'VO?(F|A)-STM\1', versionCode) is None,
                     # Prefer http downloads over m3u8
                     0 if f['url'].endswith('m3u8') else 1,
                 )
@@ -185,9 +192,10 @@ class ArteTVFutureIE(ArteTVPlus7IE):
     _TEST = {
         'url': 'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081',
         'info_dict': {
-            'id': '050940-003',
+            'id': '5201',
             'ext': 'mp4',
             'title': 'Les champignons au secours de la planète',
+            'upload_date': '20131101',
         },
     }
 

youtube_dl/extractor/bandcamp.py

@@ -12,14 +12,14 @@ from ..utils import (
 
 
 class BandcampIE(InfoExtractor):
-    _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
+    _VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>.*)'
     _TESTS = [{
         'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
         'file': '1812978515.mp3',
         'md5': 'c557841d5e50261777a6585648adf439',
         'info_dict': {
             "title": "youtube-dl  \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
-            "duration": 10,
+            "duration": 9.8485,
         },
         '_skip': 'There is a limit of 200 free downloads / month for the test song'
     }]
@@ -28,36 +28,32 @@ class BandcampIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         title = mobj.group('title')
         webpage = self._download_webpage(url, title)
-        # We get the link to the free download page
         m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
-        if m_download is None:
+        if not m_download:
             m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
             if m_trackinfo:
                 json_code = m_trackinfo.group(1)
-                data = json.loads(json_code)
-                d = data[0]
+                data = json.loads(json_code)[0]
 
-                duration = int(round(d['duration']))
                 formats = []
-                for format_id, format_url in d['file'].items():
-                    ext, _, abr_str = format_id.partition('-')
-
+                for format_id, format_url in data['file'].items():
+                    ext, abr_str = format_id.split('-', 1)
                     formats.append({
                         'format_id': format_id,
                         'url': format_url,
-                        'ext': format_id.partition('-')[0],
+                        'ext': ext,
                         'vcodec': 'none',
-                        'acodec': format_id.partition('-')[0],
-                        'abr': int(format_id.partition('-')[2]),
+                        'acodec': ext,
+                        'abr': int(abr_str),
                     })
 
                 self._sort_formats(formats)
 
                 return {
-                    'id': compat_str(d['id']),
-                    'title': d['title'],
+                    'id': compat_str(data['id']),
+                    'title': data['title'],
                     'formats': formats,
-                    'duration': duration,
+                    'duration': float(data['duration']),
                 }
             else:
                 raise ExtractorError('No free songs found')
@@ -67,11 +63,9 @@ class BandcampIE(InfoExtractor):
             r'var TralbumData = {(.*?)id: (?P<id>\d*?)$',
             webpage, re.MULTILINE | re.DOTALL).group('id')
 
-        download_webpage = self._download_webpage(download_link, video_id,
-                                                  'Downloading free downloads page')
-        # We get the dictionary of the track from some javascrip code
-        info = re.search(r'items: (.*?),$',
-                         download_webpage, re.MULTILINE).group(1)
+        download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
+        # We get the dictionary of the track from some javascript code
+        info = re.search(r'items: (.*?),$', download_webpage, re.MULTILINE).group(1)
         info = json.loads(info)[0]
         # We pick mp3-320 for now, until format selection can be easily implemented.
         mp3_info = info['downloads']['mp3-320']
@@ -100,7 +94,7 @@ class BandcampIE(InfoExtractor):
 
 class BandcampAlbumIE(InfoExtractor):
     IE_NAME = 'Bandcamp:album'
-    _VALID_URL = r'http://.*?\.bandcamp\.com/album/(?P<title>.*)'
+    _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))'
 
     _TEST = {
         'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
@@ -123,13 +117,15 @@ class BandcampAlbumIE(InfoExtractor):
         'params': {
             'playlistend': 2
         },
-        'skip': 'Bancamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
+        'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('subdomain')
         title = mobj.group('title')
-        webpage = self._download_webpage(url, title)
+        display_id = title or playlist_id
+        webpage = self._download_webpage(url, display_id)
         tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
         if not tracks_paths:
             raise ExtractorError('The page doesn\'t contain any tracks')
@@ -139,6 +135,8 @@ class BandcampAlbumIE(InfoExtractor):
         title = self._search_regex(r'album_title : "(.*?)"', webpage, 'title')
         return {
             '_type': 'playlist',
+            'id': playlist_id,
+            'display_id': display_id,
             'title': title,
             'entries': entries,
         }

youtube_dl/extractor/bilibili.py

@@ -0,0 +1,106 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_parse_qs,
+    ExtractorError,
+    int_or_none,
+    unified_strdate,
+)
+
+
+class BiliBiliIE(InfoExtractor):
+    _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'
+
+    _TEST = {
+        'url': 'http://www.bilibili.tv/video/av1074402/',
+        'md5': '2c301e4dab317596e837c3e7633e7d86',
+        'info_dict': {
+            'id': '1074402',
+            'ext': 'flv',
+            'title': '【金坷垃】金泡沫',
+            'duration': 308,
+            'upload_date': '20140420',
+            'thumbnail': 're:^https?://.+\.jpg',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        video_code = self._search_regex(
+            r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
+
+        title = self._html_search_meta(
+            'media:title', video_code, 'title', fatal=True)
+        duration_str = self._html_search_meta(
+            'duration', video_code, 'duration')
+        if duration_str is None:
+            duration = None
+        else:
+            duration_mobj = re.match(
+                r'^T(?:(?P<hours>[0-9]+)H)?(?P<minutes>[0-9]+)M(?P<seconds>[0-9]+)S$',
+                duration_str)
+            duration = (
+                int_or_none(duration_mobj.group('hours'), default=0) * 3600 +
+                int(duration_mobj.group('minutes')) * 60 +
+                int(duration_mobj.group('seconds')))
+        upload_date = unified_strdate(self._html_search_meta(
+            'uploadDate', video_code, fatal=False))
+        thumbnail = self._html_search_meta(
+            'thumbnailUrl', video_code, 'thumbnail', fatal=False)
+
+        player_params = compat_parse_qs(self._html_search_regex(
+            r'<iframe .*?class="player" src="https://secure\.bilibili\.(?:tv|com)/secure,([^"]+)"',
+            webpage, 'player params'))
+
+        if 'cid' in player_params:
+            cid = player_params['cid'][0]
+
+            lq_doc = self._download_xml(
+                'http://interface.bilibili.cn/v_cdn_play?cid=%s' % cid,
+                video_id,
+                note='Downloading LQ video info'
+            )
+            lq_durl = lq_doc.find('.//durl')
+            formats = [{
+                'format_id': 'lq',
+                'quality': 1,
+                'url': lq_durl.find('./url').text,
+                'filesize': int_or_none(
+                    lq_durl.find('./size'), get_attr='text'),
+            }]
+
+            hq_doc = self._download_xml(
+                'http://interface.bilibili.cn/playurl?cid=%s' % cid,
+                video_id,
+                note='Downloading HQ video info',
+                fatal=False,
+            )
+            if hq_doc is not False:
+                hq_durl = hq_doc.find('.//durl')
+                formats.append({
+                    'format_id': 'hq',
+                    'quality': 2,
+                    'ext': 'flv',
+                    'url': hq_durl.find('./url').text,
+                    'filesize': int_or_none(
+                        hq_durl.find('./size'), get_attr='text'),
+                })
+        else:
+            raise ExtractorError('Unsupported player parameters: %r' % (player_params,))
+
+        self._sort_formats(formats)
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'duration': duration,
+            'upload_date': upload_date,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/blinkx.py

@@ -1,13 +1,10 @@
 from __future__ import unicode_literals
 
-import datetime
 import json
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    remove_start,
-)
+from ..utils import remove_start
 
 
 class BlinkxIE(InfoExtractor):
@@ -16,18 +13,21 @@ class BlinkxIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB',
-        'file': '8aQUy7GV.mp4',
         'md5': '2e9a07364af40163a908edbf10bb2492',
         'info_dict': {
-            "title": "Police Car Rolls Away",
-            "uploader": "stupidvideos.com",
-            "upload_date": "20131215",
-            "description": "A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!",
-            "duration": 14.886,
-            "thumbnails": [{
-                "width": 100,
-                "height": 76,
-                "url": "http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg",
+            'id': '8aQUy7GV',
+            'ext': 'mp4',
+            'title': 'Police Car Rolls Away',
+            'uploader': 'stupidvideos.com',
+            'upload_date': '20131215',
+            'timestamp': 1387068000,
+            'description': 'A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!',
+            'duration': 14.886,
+            'thumbnails': [{
+                'width': 100,
+                'height': 76,
+                'resolution': '100x76',
+                'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg',
             }],
         },
     }
@@ -37,13 +37,10 @@ class BlinkxIE(InfoExtractor):
         video_id = m.group('id')
         display_id = video_id[:8]
 
-        api_url = (u'https://apib4.blinkx.com/api.php?action=play_video&' +
+        api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' +
                    'video=%s' % video_id)
         data_json = self._download_webpage(api_url, display_id)
         data = json.loads(data_json)['api']['results'][0]
-        dt = datetime.datetime.fromtimestamp(data['pubdate_epoch'])
-        pload_date = dt.strftime('%Y%m%d')
-
         duration = None
         thumbnails = []
         formats = []
@@ -58,16 +55,13 @@ class BlinkxIE(InfoExtractor):
                 duration = m['d']
             elif m['type'] == 'youtube':
                 yt_id = m['link']
-                self.to_screen(u'Youtube video detected: %s' % yt_id)
+                self.to_screen('Youtube video detected: %s' % yt_id)
                 return self.url_result(yt_id, 'Youtube', video_id=yt_id)
             elif m['type'] in ('flv', 'mp4'):
                 vcodec = remove_start(m['vcodec'], 'ff')
                 acodec = remove_start(m['acodec'], 'ff')
                 tbr = (int(m['vbr']) + int(m['abr'])) // 1000
-                format_id = (u'%s-%sk-%s' %
-                             (vcodec,
-                              tbr,
-                              m['w']))
+                format_id = '%s-%sk-%s' % (vcodec, tbr, m['w'])
                 formats.append({
                     'format_id': format_id,
                     'url': m['link'],
@@ -88,7 +82,7 @@ class BlinkxIE(InfoExtractor):
             'title': data['title'],
             'formats': formats,
             'uploader': data['channel_name'],
-            'upload_date': pload_date,
+            'timestamp': data['pubdate_epoch'],
             'description': data.get('description'),
             'thumbnails': thumbnails,
             'duration': duration,

youtube_dl/extractor/bliptv.py

@@ -1,102 +1,124 @@
 from __future__ import unicode_literals
 
-import datetime
 import re
 
 from .common import InfoExtractor
 from .subtitles import SubtitlesInfoExtractor
 from ..utils import (
-    compat_str,
     compat_urllib_request,
-
     unescapeHTML,
+    parse_iso8601,
+    compat_urlparse,
+    clean_html,
+    compat_str,
 )
 
 
 class BlipTVIE(SubtitlesInfoExtractor):
-    """Information extractor for blip.tv"""
+    _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+]+)))'
 
-    _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(?P<presumptive_id>.+)$'
-
-    _TESTS = [{
-        'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
-        'md5': 'c6934ad0b6acf2bd920720ec888eb812',
-        'info_dict': {
-            'id': '5779306',
-            'ext': 'mov',
-            'upload_date': '20111205',
-            'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
-            'uploader': 'Comic Book Resources - CBR TV',
-            'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
+    _TESTS = [
+        {
+            'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
+            'md5': 'c6934ad0b6acf2bd920720ec888eb812',
+            'info_dict': {
+                'id': '5779306',
+                'ext': 'mov',
+                'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
+                'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
+                'timestamp': 1323138843,
+                'upload_date': '20111206',
+                'uploader': 'cbr',
+                'uploader_id': '679425',
+                'duration': 81,
+            }
+        },
+        {
+            # https://github.com/rg3/youtube-dl/pull/2274
+            'note': 'Video with subtitles',
+            'url': 'http://blip.tv/play/h6Uag5OEVgI.html',
+            'md5': '309f9d25b820b086ca163ffac8031806',
+            'info_dict': {
+                'id': '6586561',
+                'ext': 'mp4',
+                'title': 'Red vs. Blue Season 11 Episode 1',
+                'description': 'One-Zero-One',
+                'timestamp': 1371261608,
+                'upload_date': '20130615',
+                'uploader': 'redvsblue',
+                'uploader_id': '792887',
+                'duration': 279,
+            }
         }
-    }, {
-        # https://github.com/rg3/youtube-dl/pull/2274
-        'note': 'Video with subtitles',
-        'url': 'http://blip.tv/play/h6Uag5OEVgI.html',
-        'md5': '309f9d25b820b086ca163ffac8031806',
-        'info_dict': {
-            'id': '6586561',
-            'ext': 'mp4',
-            'uploader': 'Red vs. Blue',
-            'description': 'One-Zero-One',
-            'upload_date': '20130614',
-            'title': 'Red vs. Blue Season 11 Episode 1',
-        }
-    }]
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        presumptive_id = mobj.group('presumptive_id')
+        lookup_id = mobj.group('lookup_id')
 
         # See https://github.com/rg3/youtube-dl/issues/857
-        embed_mobj = re.match(r'https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', url)
-        if embed_mobj:
-            info_url = 'http://blip.tv/play/%s.x?p=1' % embed_mobj.group(1)
-            info_page = self._download_webpage(info_url, embed_mobj.group(1))
-            video_id = self._search_regex(
-                r'data-episode-id="([0-9]+)', info_page, 'video_id')
-            return self.url_result('http://blip.tv/a/a-' + video_id, 'BlipTV')
-        
-        cchar = '&' if '?' in url else '?'
-        json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
-        request = compat_urllib_request.Request(json_url)
-        request.add_header('User-Agent', 'iTunes/10.6.1')
-
-        json_data = self._download_json(request, video_id=presumptive_id)
-
-        if 'Post' in json_data:
-            data = json_data['Post']
+        if lookup_id:
+            info_page = self._download_webpage(
+                'http://blip.tv/play/%s.x?p=1' % lookup_id, lookup_id, 'Resolving lookup id')
+            video_id = self._search_regex(r'data-episode-id="([0-9]+)', info_page, 'video_id')
         else:
-            data = json_data
+            video_id = mobj.group('id')
+
+        rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS')
+
+        def blip(s):
+            return '{http://blip.tv/dtd/blip/1.0}%s' % s
+
+        def media(s):
+            return '{http://search.yahoo.com/mrss/}%s' % s
+
+        def itunes(s):
+            return '{http://www.itunes.com/dtds/podcast-1.0.dtd}%s' % s
+
+        item = rss.find('channel/item')
+
+        video_id = item.find(blip('item_id')).text
+        title = item.find('./title').text
+        description = clean_html(compat_str(item.find(blip('puredescription')).text))
+        timestamp = parse_iso8601(item.find(blip('datestamp')).text)
+        uploader = item.find(blip('user')).text
+        uploader_id = item.find(blip('userid')).text
+        duration = int(item.find(blip('runtime')).text)
+        media_thumbnail = item.find(media('thumbnail'))
+        thumbnail = media_thumbnail.get('url') if media_thumbnail is not None else item.find(itunes('image')).text
+        categories = [category.text for category in item.findall('category')]
 
-        video_id = compat_str(data['item_id'])
-        upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
-        subtitles = {}
         formats = []
-        if 'additionalMedia' in data:
-            for f in data['additionalMedia']:
-                if f.get('file_type_srt') == 1:
-                    LANGS = {
-                        'english': 'en',
-                    }
-                    lang = f['role'].rpartition('-')[-1].strip().lower()
-                    langcode = LANGS.get(lang, lang)
-                    subtitles[langcode] = f['url']
-                    continue
-                if not int(f['media_width']):  # filter m3u8
-                    continue
+        subtitles = {}
+
+        media_group = item.find(media('group'))
+        for media_content in media_group.findall(media('content')):
+            url = media_content.get('url')
+            role = media_content.get(blip('role'))
+            msg = self._download_webpage(
+                url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url',
+                video_id, 'Resolving URL for %s' % role)
+            real_url = compat_urlparse.parse_qs(msg)['message'][0]
+
+            media_type = media_content.get('type')
+            if media_type == 'text/srt' or url.endswith('.srt'):
+                LANGS = {
+                    'english': 'en',
+                }
+                lang = role.rpartition('-')[-1].strip().lower()
+                langcode = LANGS.get(lang, lang)
+                subtitles[langcode] = url
+            elif media_type.startswith('video/'):
                 formats.append({
-                    'url': f['url'],
-                    'format_id': f['role'],
-                    'width': int(f['media_width']),
-                    'height': int(f['media_height']),
+                    'url': real_url,
+                    'format_id': role,
+                    'format_note': media_type,
+                    'vcodec': media_content.get(blip('vcodec')),
+                    'acodec': media_content.get(blip('acodec')),
+                    'filesize': media_content.get('filesize'),
+                    'width': int(media_content.get('width')),
+                    'height': int(media_content.get('height')),
                 })
-        else:
-            formats.append({
-                'url': data['media']['url'],
-                'width': int(data['media']['width']),
-                'height': int(data['media']['height']),
-            })
         self._sort_formats(formats)
 
         # subtitles
@@ -107,12 +129,14 @@ class BlipTVIE(SubtitlesInfoExtractor):
 
         return {
             'id': video_id,
-            'uploader': data['display_name'],
-            'upload_date': upload_date,
-            'title': data['title'],
-            'thumbnail': data['thumbnailUrl'],
-            'description': data['description'],
-            'user_agent': 'iTunes/10.6.1',
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'duration': duration,
+            'thumbnail': thumbnail,
+            'categories': categories,
             'formats': formats,
             'subtitles': video_subtitles,
         }

youtube_dl/extractor/br.py

@@ -12,20 +12,18 @@ from ..utils import (
 
 class BRIE(InfoExtractor):
     IE_DESC = 'Bayerischer Rundfunk Mediathek'
-    _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[a-z0-9\-]+/)+(?P<id>[a-z0-9\-]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html'
     _BASE_URL = 'http://www.br.de'
 
     _TESTS = [
         {
-            'url': 'http://www.br.de/mediathek/video/anselm-gruen-114.html',
-            'md5': 'c4f83cf0f023ba5875aba0bf46860df2',
+            'url': 'http://www.br.de/mediathek/video/sendungen/heimatsound/heimatsound-festival-2014-trailer-100.html',
+            'md5': '93556dd2bcb2948d9259f8670c516d59',
             'info_dict': {
-                'id': '2c8d81c5-6fb7-4a74-88d4-e768e5856532',
+                'id': '25e279aa-1ffd-40fd-9955-5325bd48a53a',
                 'ext': 'mp4',
-                'title': 'Feiern und Verzichten',
-                'description': 'Anselm Grün: Feiern und Verzichten',
-                'uploader': 'BR/Birgit Baier',
-                'upload_date': '20140301',
+                'title': 'Am 1. und 2. August in Oberammergau',
+                'description': 'md5:dfd224e5aa6819bc1fcbb7826a932021',
             }
         },
         {

youtube_dl/extractor/brightcove.py

@@ -15,6 +15,7 @@ from ..utils import (
     compat_urllib_request,
     compat_parse_qs,
 
+    determine_ext,
     ExtractorError,
     unsmuggle_url,
     unescapeHTML,
@@ -29,10 +30,11 @@ class BrightcoveIE(InfoExtractor):
         {
             # From http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/
             'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001',
-            'file': '2371591881001.mp4',
             'md5': '5423e113865d26e40624dce2e4b45d95',
             'note': 'Test Brightcove downloads and detection in GenericIE',
             'info_dict': {
+                'id': '2371591881001',
+                'ext': 'mp4',
                 'title': 'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”',
                 'uploader': '8TV',
                 'description': 'md5:a950cc4285c43e44d763d036710cd9cd',
@@ -41,8 +43,9 @@ class BrightcoveIE(InfoExtractor):
         {
             # From http://medianetwork.oracle.com/video/player/1785452137001
             'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1217746023001&flashID=myPlayer&%40videoPlayer=1785452137001',
-            'file': '1785452137001.flv',
             'info_dict': {
+                'id': '1785452137001',
+                'ext': 'flv',
                 'title': 'JVMLS 2012: Arrays 2.0 - Opportunities and Challenges',
                 'description': 'John Rose speaks at the JVM Language Summit, August 1, 2012.',
                 'uploader': 'Oracle',
@@ -70,7 +73,20 @@ class BrightcoveIE(InfoExtractor):
                 'description': 'md5:363109c02998fee92ec02211bd8000df',
                 'uploader': 'National Ballet of Canada',
             },
-        }
+        },
+        {
+            # test flv videos served by akamaihd.net
+            # From http://www.redbull.com/en/bike/stories/1331655643987/replay-uci-dh-world-cup-2014-from-fort-william
+            'url': 'http://c.brightcove.com/services/viewer/htmlFederated?%40videoPlayer=ref%3ABC2996102916001&linkBaseURL=http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fvideos%2F1331655630249%2Freplay-uci-fort-william-2014-dh&playerKey=AQ%7E%7E%2CAAAApYJ7UqE%7E%2Cxqr_zXk0I-zzNndy8NlHogrCb5QdyZRf&playerID=1398061561001#__youtubedl_smuggle=%7B%22Referer%22%3A+%22http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fstories%2F1331655643987%2Freplay-uci-dh-world-cup-2014-from-fort-william%22%7D',
+            # The md5 checksum changes on each download
+            'info_dict': {
+                'id': '2996102916001',
+                'ext': 'flv',
+                'title': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
+                'uploader': 'Red Bull TV',
+                'description': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
+            },
+        },
     ]
 
     @classmethod
@@ -187,7 +203,7 @@ class BrightcoveIE(InfoExtractor):
         webpage = self._download_webpage(req, video_id)
 
         self.report_extraction(video_id)
-        info = self._search_regex(r'var experienceJSON = ({.*?});', webpage, 'json')
+        info = self._search_regex(r'var experienceJSON = ({.*});', webpage, 'json')
         info = json.loads(info)['data']
         video_info = info['programmedContent']['videoPlayer']['mediaDTO']
         video_info['_youtubedl_adServerURL'] = info.get('adServerURL')
@@ -219,12 +235,26 @@ class BrightcoveIE(InfoExtractor):
 
         renditions = video_info.get('renditions')
         if renditions:
-            renditions = sorted(renditions, key=lambda r: r['size'])
-            info['formats'] = [{
-                'url': rend['defaultURL'],
-                'height': rend.get('frameHeight'),
-                'width': rend.get('frameWidth'),
-            } for rend in renditions]
+            formats = []
+            for rend in renditions:
+                url = rend['defaultURL']
+                if rend['remote']:
+                    # This type of renditions are served through akamaihd.net,
+                    # but they don't use f4m manifests
+                    url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB'
+                    ext = 'flv'
+                else:
+                    ext = determine_ext(url)
+                size = rend.get('size')
+                formats.append({
+                    'url': url,
+                    'ext': ext,
+                    'height': rend.get('frameHeight'),
+                    'width': rend.get('frameWidth'),
+                    'filesize': size if size != 0 else None,
+                })
+            self._sort_formats(formats)
+            info['formats'] = formats
         elif video_info.get('FLVFullLengthURL') is not None:
             info.update({
                 'url': video_info['FLVFullLengthURL'],

youtube_dl/extractor/canalplus.py

@@ -1,53 +1,72 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
+from ..utils import (
+    unified_strdate,
+    url_basename,
+)
 
 
 class CanalplusIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>\d+))'
+    _VALID_URL = r'https?://(?:www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
-    IE_NAME = u'canalplus.fr'
+    IE_NAME = 'canalplus.fr'
 
     _TEST = {
-        u'url': u'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
-        u'file': u'922470.flv',
-        u'info_dict': {
-            u'title': u'Zapping - 26/08/13',
-            u'description': u'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
-            u'upload_date': u'20130826',
-        },
-        u'params': {
-            u'skip_download': True,
+        'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
+        'md5': '3db39fb48b9685438ecf33a1078023e4',
+        'info_dict': {
+            'id': '922470',
+            'ext': 'flv',
+            'title': 'Zapping - 26/08/13',
+            'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
+            'upload_date': '20130826',
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.groupdict().get('id')
+
+        # Beware, some subclasses do not define an id group
+        display_id = url_basename(mobj.group('path'))
+
         if video_id is None:
-            webpage = self._download_webpage(url, mobj.group('path'))
-            video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, u'video id')
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, 'video id')
+
         info_url = self._VIDEO_INFO_TEMPLATE % video_id
-        doc = self._download_xml(info_url,video_id, 
-                                           u'Downloading video info')
+        doc = self._download_xml(info_url, video_id, 'Downloading video XML')
 
-        self.report_extraction(video_id)
         video_info = [video for video in doc if video.find('ID').text == video_id][0]
-        infos = video_info.find('INFOS')
         media = video_info.find('MEDIA')
-        formats = [media.find('VIDEOS/%s' % format)
-            for format in ['BAS_DEBIT', 'HAUT_DEBIT', 'HD']]
-        video_url = [format.text for format in formats if format is not None][-1]
+        infos = video_info.find('INFOS')
 
-        return {'id': video_id,
-                'title': u'%s - %s' % (infos.find('TITRAGE/TITRE').text,
-                                       infos.find('TITRAGE/SOUS_TITRE').text),
-                'url': video_url,
-                'ext': 'flv',
-                'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
-                'thumbnail': media.find('IMAGES/GRAND').text,
-                'description': infos.find('DESCRIPTION').text,
-                'view_count': int(infos.find('NB_VUES').text),
-                }
+        preferences = ['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS']
+
+        formats = [
+            {
+                'url': fmt.text + '?hdcore=2.11.3' if fmt.tag == 'HDS' else fmt.text,
+                'format_id': fmt.tag,
+                'ext': 'mp4' if fmt.tag == 'HLS' else 'flv',
+                'preference': preferences.index(fmt.tag) if fmt.tag in preferences else -1,
+            } for fmt in media.find('VIDEOS') if fmt.text
+        ]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
+                                  infos.find('TITRAGE/SOUS_TITRE').text),
+            'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
+            'thumbnail': media.find('IMAGES/GRAND').text,
+            'description': infos.find('DESCRIPTION').text,
+            'view_count': int(infos.find('NB_VUES').text),
+            'like_count': int(infos.find('NB_LIKES').text),
+            'comment_count': int(infos.find('NB_COMMENTS').text),
+            'formats': formats,
+        }

youtube_dl/extractor/cbs.py

@@ -1,24 +1,42 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class CBSIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/video/(?P<id>[^/]+)/.*'
+    _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/(?:video|artist)/(?P<id>[^/]+)/.*'
 
-    _TEST = {
-        u'url': u'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
-        u'file': u'4JUVEwq3wUT7.flv',
-        u'info_dict': {
-            u'title': u'Connect Chat feat. Garth Brooks',
-            u'description': u'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
-            u'duration': 1495,
+    _TESTS = [{
+        'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
+        'info_dict': {
+            'id': '4JUVEwq3wUT7',
+            'ext': 'flv',
+            'title': 'Connect Chat feat. Garth Brooks',
+            'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
+            'duration': 1495,
         },
-        u'params': {
+        'params': {
             # rtmp download
-            u'skip_download': True,
+            'skip_download': True,
         },
-    }
+        '_skip': 'Blocked outside the US',
+    }, {
+        'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
+        'info_dict': {
+            'id': 'P9gjWjelt6iP',
+            'ext': 'flv',
+            'title': 'Live on Letterman - St. Vincent',
+            'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',
+            'duration': 3221,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+        '_skip': 'Blocked outside the US',
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -26,5 +44,5 @@ class CBSIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         real_id = self._search_regex(
             r"video\.settings\.pid\s*=\s*'([^']+)';",
-            webpage, u'real video ID')
+            webpage, 'real video ID')
         return self.url_result(u'theplatform:%s' % real_id)

youtube_dl/extractor/chilloutzone.py

@@ -42,7 +42,7 @@ class ChilloutzoneIE(InfoExtractor):
             'id': '85523671',
             'ext': 'mp4',
             'title': 'The Sunday Times - Icons',
-            'description': 'md5:3e1c0dc6047498d6728dcdaad0891762',
+            'description': 'md5:a5f7ff82e2f7a9ed77473fe666954e84',
             'uploader': 'Us',
             'uploader_id': 'usfilms',
             'upload_date': '20140131'

youtube_dl/extractor/cinemassacre.py

@@ -1,10 +1,12 @@
 # encoding: utf-8
 from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    int_or_none,
 )
 
 
@@ -13,9 +15,10 @@ class CinemassacreIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
-            'file': '19911.mp4',
-            'md5': '782f8504ca95a0eba8fc9177c373eec7',
+            'md5': 'fde81fbafaee331785f58cd6c0d46190',
             'info_dict': {
+                'id': '19911',
+                'ext': 'mp4',
                 'upload_date': '20121110',
                 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
                 'description': 'md5:fb87405fcb42a331742a0dce2708560b',
@@ -23,9 +26,10 @@ class CinemassacreIE(InfoExtractor):
         },
         {
             'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
-            'file': '521be8ef82b16.mp4',
-            'md5': 'dec39ee5118f8d9cc067f45f9cbe3a35',
+            'md5': 'd72f10cd39eac4215048f62ab477a511',
             'info_dict': {
+                'id': '521be8ef82b16',
+                'ext': 'mp4',
                 'upload_date': '20131002',
                 'title': 'The Mummy’s Hand (1940)',
             },
@@ -50,29 +54,40 @@ class CinemassacreIE(InfoExtractor):
             r'<div class="entry-content">(?P<description>.+?)</div>',
             webpage, 'description', flags=re.DOTALL, fatal=False)
 
-        playerdata = self._download_webpage(playerdata_url, video_id)
+        playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage')
+        video_thumbnail = self._search_regex(
+            r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
+        sd_url = self._search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file')
+        videolist_url = self._search_regex(r'file: \'([^\']+\.smil)\'}', playerdata, 'videolist_url')
 
-        sd_url = self._html_search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file')
-        hd_url = self._html_search_regex(
-            r'file: \'([^\']+)\', label: \'HD\'', playerdata, 'hd_file',
-            default=None)
-        video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
+        videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
 
-        formats = [{
-            'url': sd_url,
-            'ext': 'mp4',
-            'format': 'sd',
-            'format_id': 'sd',
-            'quality': 1,
-        }]
-        if hd_url:
-            formats.append({
-                'url': hd_url,
-                'ext': 'mp4',
-                'format': 'hd',
-                'format_id': 'hd',
-                'quality': 2,
-            })
+        formats = []
+        baseurl = sd_url[:sd_url.rfind('/')+1]
+        for video in videolist.findall('.//video'):
+            src = video.get('src')
+            if not src:
+                continue
+            file_ = src.partition(':')[-1]
+            width = int_or_none(video.get('width'))
+            height = int_or_none(video.get('height'))
+            bitrate = int_or_none(video.get('system-bitrate'))
+            format = {
+                'url': baseurl + file_,
+                'format_id': src.rpartition('.')[0].rpartition('_')[-1],
+            }
+            if width or height:
+                format.update({
+                    'tbr': bitrate // 1000 if bitrate else None,
+                    'width': width,
+                    'height': height,
+                })
+            else:
+                format.update({
+                    'abr': bitrate // 1000 if bitrate else None,
+                    'vcodec': 'none',
+                })
+            formats.append(format)
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/clubic.py

@@ -0,0 +1,58 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    qualities,
+)
+
+
+class ClubicIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?clubic\.com/video/[^/]+/video.*-(?P<id>[0-9]+)\.html'
+
+    _TEST = {
+        'url': 'http://www.clubic.com/video/clubic-week/video-clubic-week-2-0-le-fbi-se-lance-dans-la-photo-d-identite-448474.html',
+        'md5': '1592b694ba586036efac1776b0b43cd3',
+        'info_dict': {
+            'id': '448474',
+            'ext': 'mp4',
+            'title': 'Clubic Week 2.0 : le FBI se lance dans la photo d\u0092identité',
+            'description': 're:Gueule de bois chez Nokia. Le constructeur a indiqué cette.*',
+            'thumbnail': 're:^http://img\.clubic\.com/.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        player_url = 'http://player.m6web.fr/v1/player/clubic/%s.html' % video_id
+        player_page = self._download_webpage(player_url, video_id)
+
+        config_json = self._search_regex(
+            r'(?m)M6\.Player\.config\s*=\s*(\{.+?\});$', player_page,
+            'configuration')
+        config = json.loads(config_json)
+
+        video_info = config['videoInfo']
+        sources = config['sources']
+        quality_order = qualities(['sd', 'hq'])
+
+        formats = [{
+            'format_id': src['streamQuality'],
+            'url': src['src'],
+            'quality': quality_order(src['streamQuality']),
+        } for src in sources]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_info['title'],
+            'formats': formats,
+            'description': clean_html(video_info.get('description')),
+            'thumbnail': config.get('poster'),
+        }

youtube_dl/extractor/cmt.py

@@ -1,19 +1,19 @@
+from __future__ import unicode_literals
 from .mtv import MTVIE
 
+
 class CMTIE(MTVIE):
-    IE_NAME = u'cmt.com'
+    IE_NAME = 'cmt.com'
     _VALID_URL = r'https?://www\.cmt\.com/videos/.+?/(?P<videoid>[^/]+)\.jhtml'
     _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
 
-    _TESTS = [
-        {
-            u'url': u'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061',
-            u'md5': u'e6b7ef3c4c45bbfae88061799bbba6c2',
-            u'info_dict': {
-                u'id': u'989124',
-                u'ext': u'mp4',
-                u'title': u'Garth Brooks - "The Call (featuring Trisha Yearwood)"',
-                u'description': u'Blame It All On My Roots',
-            },
+    _TESTS = [{
+        'url': 'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061',
+        'md5': 'e6b7ef3c4c45bbfae88061799bbba6c2',
+        'info_dict': {
+            'id': '989124',
+            'ext': 'mp4',
+            'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"',
+            'description': 'Blame It All On My Roots',
         },
-    ]
+    }]

youtube_dl/extractor/cnet.py

@@ -33,7 +33,7 @@ class CNETIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
         data_json = self._html_search_regex(
-            r"<div class=\"cnetVideoPlayer\" data-cnet-video-options='([^']+)'",
+            r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'",
             webpage, 'data json')
         data = json.loads(data_json)
         vdata = data['video']
@@ -43,7 +43,11 @@ class CNETIE(InfoExtractor):
             raise ExtractorError('Cannot find video data')
 
         video_id = vdata['id']
-        title = vdata['headline']
+        title = vdata.get('headline')
+        if title is None:
+            title = vdata.get('title')
+        if title is None:
+            raise ExtractorError('Cannot find title!')
         description = vdata.get('dek')
         thumbnail = vdata.get('image', {}).get('path')
         author = vdata.get('author')

youtube_dl/extractor/cnn.py

@@ -79,8 +79,11 @@ class CNNIE(InfoExtractor):
 
         self._sort_formats(formats)
 
-        thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')])
-        thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails]
+        thumbnails = [{
+            'height': int(t.attrib['height']),
+            'width': int(t.attrib['width']),
+            'url': t.text,
+        } for t in info.findall('images/image')]
 
         metas_el = info.find('metas')
         upload_date = (
@@ -93,8 +96,7 @@ class CNNIE(InfoExtractor):
             'id': info.attrib['id'],
             'title': info.find('headline').text,
             'formats': formats,
-            'thumbnail': thumbnails[-1][1],
-            'thumbnails': thumbs_dict,
+            'thumbnails': thumbnails,
             'description': info.find('description').text,
             'duration': duration,
             'upload_date': upload_date,

youtube_dl/extractor/comedycentral.py

@@ -14,13 +14,13 @@ from ..utils import (
 
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:www\.)?(comedycentral|cc)\.com/
-        (video-clips|episodes|cc-studios|video-collections)
+    _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
+        (video-clips|episodes|cc-studios|video-collections|full-episodes)
         /(?P<title>.*)'''
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 
     _TEST = {
-        'url': 'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
+        'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
         'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
         'info_dict': {
             'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
@@ -130,7 +130,7 @@ class ComedyCentralShowsIE(InfoExtractor):
                 raise ExtractorError('Invalid redirected URL: ' + url)
             if mobj.group('episode') == '':
                 raise ExtractorError('Redirected URL is still not specific: ' + url)
-            epTitle = mobj.group('episode').rpartition('/')[-1]
+            epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1]
 
         mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
         if len(mMovieParams) == 0:
@@ -188,7 +188,7 @@ class ComedyCentralShowsIE(InfoExtractor):
                 })
                 formats.append({
                     'format_id': 'rtmp-%s' % format,
-                    'url': rtmp_video_url,
+                    'url': rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm'),
                     'ext': self._video_extensions.get(format, 'mp4'),
                     'height': h,
                     'width': w,

youtube_dl/extractor/common.py

@@ -1,11 +1,12 @@
 import base64
 import hashlib
 import json
+import netrc
 import os
 import re
 import socket
 import sys
-import netrc
+import time
 import xml.etree.ElementTree
 
 from ..utils import (
@@ -68,6 +69,7 @@ class InfoExtractor(object):
                     * vcodec     Name of the video codec in use
                     * container  Name of the container format
                     * filesize   The number of bytes, if known in advance
+                    * filesize_approx  An estimate for the number of bytes
                     * player_url SWF Player URL (used for rtmpdump).
                     * protocol   The protocol that will be used for the actual
                                  download, lower-case.
@@ -92,8 +94,12 @@ class InfoExtractor(object):
                     unique, but available before title. Typically, id is
                     something like "4234987", title "Dancing naked mole rats",
                     and display_id "dancing-naked-mole-rats"
-    thumbnails:     A list of dictionaries (with the entries "resolution" and
-                    "url") for the varying thumbnails
+    thumbnails:     A list of dictionaries, with the following entries:
+                        * "url"
+                        * "width" (optional, int)
+                        * "height" (optional, int)
+                        * "resolution" (optional, string "{width}x{height"},
+                                        deprecated)
     thumbnail:      Full URL to a video thumbnail image.
     description:    One-line video description.
     uploader:       Full name of the video uploader.
@@ -113,6 +119,8 @@ class InfoExtractor(object):
     webpage_url:    The url to the video webpage, if given to youtube-dl it
                     should allow to get the same result again. (It will be set
                     by YoutubeDL if it's missing)
+    categories:     A list of categories that the video falls in, for example
+                    ["Sports", "Berlin"]
 
     Unless mentioned otherwise, the fields should be Unicode strings.
 
@@ -242,10 +250,11 @@ class InfoExtractor(object):
                 url = url_or_request.get_full_url()
             except AttributeError:
                 url = url_or_request
-            if len(url) > 200:
-                h = u'___' + hashlib.md5(url.encode('utf-8')).hexdigest()
-                url = url[:200 - len(h)] + h
-            raw_filename = ('%s_%s.dump' % (video_id, url))
+            basen = '%s_%s' % (video_id, url)
+            if len(basen) > 240:
+                h = u'___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
+                basen = basen[:240 - len(h)] + h
+            raw_filename = basen + '.dump'
             filename = sanitize_filename(raw_filename, restricted=True)
             self.to_screen(u'Saving request to ' + filename)
             with open(filename, 'wb') as outf:
@@ -279,9 +288,12 @@ class InfoExtractor(object):
 
     def _download_xml(self, url_or_request, video_id,
                       note=u'Downloading XML', errnote=u'Unable to download XML',
-                      transform_source=None):
+                      transform_source=None, fatal=True):
         """Return the xml as an xml.etree.ElementTree.Element"""
-        xml_string = self._download_webpage(url_or_request, video_id, note, errnote)
+        xml_string = self._download_webpage(
+            url_or_request, video_id, note, errnote, fatal=fatal)
+        if xml_string is False:
+            return xml_string
         if transform_source:
             xml_string = transform_source(xml_string)
         return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
@@ -449,14 +461,17 @@ class InfoExtractor(object):
         if secure: regexes = self._og_regexes('video:secure_url') + regexes
         return self._html_search_regex(regexes, html, name, **kargs)
 
-    def _html_search_meta(self, name, html, display_name=None, fatal=False):
+    def _og_search_url(self, html, **kargs):
+        return self._og_search_property('url', html, **kargs)
+
+    def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs):
         if display_name is None:
             display_name = name
         return self._html_search_regex(
             r'''(?ix)<meta
-                    (?=[^>]+(?:itemprop|name|property)=["\']%s["\'])
+                    (?=[^>]+(?:itemprop|name|property)=["\']?%s["\']?)
                     [^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
-            html, display_name, fatal=fatal)
+            html, display_name, fatal=fatal, **kwargs)
 
     def _dc_search_uploader(self, html):
         return self._html_search_meta('dc.creator', html, 'uploader')
@@ -541,10 +556,35 @@ class InfoExtractor(object):
                 f.get('abr') if f.get('abr') is not None else -1,
                 audio_ext_preference,
                 f.get('filesize') if f.get('filesize') is not None else -1,
+                f.get('filesize_approx') if f.get('filesize_approx') is not None else -1,
                 f.get('format_id'),
             )
         formats.sort(key=_formats_key)
 
+    def http_scheme(self):
+        """ Either "https:" or "https:", depending on the user's preferences """
+        return (
+            'http:'
+            if self._downloader.params.get('prefer_insecure', False)
+            else 'https:')
+
+    def _proto_relative_url(self, url, scheme=None):
+        if url is None:
+            return url
+        if url.startswith('//'):
+            if scheme is None:
+                scheme = self.http_scheme()
+            return scheme + url
+        else:
+            return url
+
+    def _sleep(self, timeout, video_id, msg_template=None):
+        if msg_template is None:
+            msg_template = u'%(video_id)s: Waiting for %(timeout)s seconds'
+        msg = msg_template % {'video_id': video_id, 'timeout': timeout}
+        self.to_screen(msg)
+        time.sleep(timeout)
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/condenast.py

@@ -28,16 +28,18 @@ class CondeNastIE(InfoExtractor):
         'glamour': 'Glamour',
         'wmagazine': 'W Magazine',
         'vanityfair': 'Vanity Fair',
+        'cnevids': 'Condé Nast',
     }
 
-    _VALID_URL = r'http://(video|www)\.(?P<site>%s)\.com/(?P<type>watch|series|video)/(?P<id>.+)' % '|'.join(_SITES.keys())
+    _VALID_URL = r'http://(video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys())
     IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
 
     _TEST = {
         'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',
-        'file': '5171b343c2b4c00dd0c1ccb3.mp4',
         'md5': '1921f713ed48aabd715691f774c451f7',
         'info_dict': {
+            'id': '5171b343c2b4c00dd0c1ccb3',
+            'ext': 'mp4',
             'title': '3D Printed Speakers Lit With LED',
             'description': 'Check out these beautiful 3D printed LED speakers.  You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
         }
@@ -55,12 +57,16 @@ class CondeNastIE(InfoExtractor):
         entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
         return self.playlist_result(entries, playlist_title=title)
 
-    def _extract_video(self, webpage):
-        description = self._html_search_regex([r'<div class="cne-video-description">(.+?)</div>',
-                                               r'<div class="video-post-content">(.+?)</div>',
-                                               ],
-                                              webpage, 'description',
-                                              fatal=False, flags=re.DOTALL)
+    def _extract_video(self, webpage, url_type):
+        if url_type != 'embed':
+            description = self._html_search_regex(
+                [
+                    r'<div class="cne-video-description">(.+?)</div>',
+                    r'<div class="video-post-content">(.+?)</div>',
+                ],
+                webpage, 'description', fatal=False, flags=re.DOTALL)
+        else:
+            description = None
         params = self._search_regex(r'var params = {(.+?)}[;,]', webpage,
                                     'player params', flags=re.DOTALL)
         video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id')
@@ -99,12 +105,12 @@ class CondeNastIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         site = mobj.group('site')
         url_type = mobj.group('type')
-        id = mobj.group('id')
+        item_id = mobj.group('id')
 
-        self.to_screen(u'Extracting from %s with the Condé Nast extractor' % self._SITES[site])
-        webpage = self._download_webpage(url, id)
+        self.to_screen('Extracting from %s with the Condé Nast extractor' % self._SITES[site])
+        webpage = self._download_webpage(url, item_id)
 
         if url_type == 'series':
             return self._extract_series(url, webpage)
         else:
-            return self._extract_video(webpage)
+            return self._extract_video(webpage, url_type)

youtube_dl/extractor/cracked.py

@@ -0,0 +1,65 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_iso8601,
+    str_to_int,
+)
+
+
+class CrackedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cracked\.com/video_(?P<id>\d+)_[\da-z-]+\.html'
+    _TEST = {
+        'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
+        'md5': '4b29a5eeec292cd5eca6388c7558db9e',
+        'info_dict': {
+            'id': '19006',
+            'ext': 'mp4',
+            'title': '4 Plot Holes You Didn\'t Notice in Your Favorite Movies',
+            'description': 'md5:3b909e752661db86007d10e5ec2df769',
+            'timestamp': 1405659600,
+            'upload_date': '20140718',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._html_search_regex(
+            [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'], webpage, 'video URL')
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+
+        timestamp = self._html_search_regex(r'<time datetime="([^"]+)"', webpage, 'upload date', fatal=False)
+        if timestamp:
+            timestamp = parse_iso8601(timestamp[:-6])
+
+        view_count = str_to_int(self._html_search_regex(
+            r'<span class="views" id="viewCounts">([\d,\.]+) Views</span>', webpage, 'view count', fatal=False))
+        comment_count = str_to_int(self._html_search_regex(
+            r'<span id="commentCounts">([\d,\.]+)</span>', webpage, 'comment count', fatal=False))
+
+        m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url)
+        if m:
+            width = int(m.group('width'))
+            height = int(m.group('height'))
+        else:
+            width = height = None
+
+        return {
+            'id': video_id,
+            'url':video_url,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'height': height,
+            'width': width,
+        }

youtube_dl/extractor/criterion.py

@@ -1,40 +1,43 @@
 # -*- coding: utf-8 -*-
+from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
-from ..utils import determine_ext
+
 
 class CriterionIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.criterion\.com/films/(\d*)-.+'
+    _VALID_URL = r'https?://www\.criterion\.com/films/(?P<id>[0-9]+)-.+'
     _TEST = {
-        u'url': u'http://www.criterion.com/films/184-le-samourai',
-        u'file': u'184.mp4',
-        u'md5': u'bc51beba55685509883a9a7830919ec3',
-        u'info_dict': {
-            u"title": u"Le Samouraï",
-            u"description" : u'md5:a2b4b116326558149bef81f76dcbb93f',
+        'url': 'http://www.criterion.com/films/184-le-samourai',
+        'md5': 'bc51beba55685509883a9a7830919ec3',
+        'info_dict': {
+            'id': '184',
+            'ext': 'mp4',
+            'title': 'Le Samouraï',
+            'description': 'md5:a2b4b116326558149bef81f76dcbb93f',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
 
-        final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;',
-                                webpage, 'video url')
-        title = self._html_search_regex(r'<meta content="(.+?)" property="og:title" />',
-                                webpage, 'video title')
-        description = self._html_search_regex(r'<meta name="description" content="(.+?)" />',
-                                webpage, 'video description')
-        thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
-                                webpage, 'thumbnail url')
+        final_url = self._search_regex(
+            r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
+        title = self._og_search_title(webpage)
+        description = self._html_search_regex(
+            r'<meta name="description" content="(.+?)" />',
+            webpage, 'video description')
+        thumbnail = self._search_regex(
+            r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
+            webpage, 'thumbnail url')
 
-        return {'id': video_id,
-                'url' : final_url,
-                'title': title,
-                'ext': determine_ext(final_url),
-                'description': description,
-                'thumbnail': thumbnail,
-                }
+        return {
+            'id': video_id,
+            'url': final_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/dailymotion.py

@@ -8,12 +8,11 @@ from .subtitles import SubtitlesInfoExtractor
 from ..utils import (
     compat_urllib_request,
     compat_str,
-    get_element_by_id,
     orderedSet,
     str_to_int,
     int_or_none,
-
     ExtractorError,
+    unescapeHTML,
 )
 
 class DailymotionBaseInfoExtractor(InfoExtractor):
@@ -151,7 +150,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
         return {
             'id':       video_id,
             'formats': formats,
-            'uploader': info['owner_screenname'],
+            'uploader': info['owner.screenname'],
             'upload_date':  video_upload_date,
             'title':    self._og_search_title(webpage),
             'subtitles':    video_subtitles,
@@ -189,7 +188,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
             webpage = self._download_webpage(request,
                                              id, u'Downloading page %s' % pagenum)
 
-            video_ids.extend(re.findall(r'data-id="(.+?)"', webpage))
+            video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage))
 
             if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
                 break
@@ -218,9 +217,9 @@ class DailymotionUserIE(DailymotionPlaylistIE):
         mobj = re.match(self._VALID_URL, url)
         user = mobj.group('user')
         webpage = self._download_webpage(url, user)
-        full_user = self._html_search_regex(
-            r'<a class="label" href="/%s".*?>(.*?)</' % re.escape(user),
-            webpage, u'user', flags=re.DOTALL)
+        full_user = unescapeHTML(self._html_search_regex(
+            r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
+            webpage, u'user', flags=re.DOTALL))
 
         return {
             '_type': 'playlist',

youtube_dl/extractor/dfb.py

@@ -0,0 +1,44 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class DFBIE(InfoExtractor):
+    IE_NAME = 'tv.dfb.de'
+    _VALID_URL = r'https?://tv\.dfb\.de/video/[^/]+/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://tv.dfb.de/video/highlights-des-empfangs-in-berlin/9070/',
+        # The md5 is different each time
+        'info_dict': {
+            'id': '9070',
+            'ext': 'flv',
+            'title': 'Highlights des Empfangs in Berlin',
+            'upload_date': '20140716',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        player_info = self._download_xml(
+            'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id,
+            video_id)
+        video_info = player_info.find('video')
+
+        f4m_info = self._download_xml(video_info.find('url').text, video_id)
+        token_el = f4m_info.find('token')
+        manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0'
+
+        return {
+            'id': video_id,
+            'title': video_info.find('title').text,
+            'url': manifest_url,
+            'ext': 'flv',
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'upload_date': ''.join(video_info.find('time_date').text.split('.')[::-1]),
+        }

youtube_dl/extractor/discovery.py

@@ -7,9 +7,9 @@ from .common import InfoExtractor
 
 
 class DiscoveryIE(InfoExtractor):
-    _VALID_URL = r'http://dsc\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
+    _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
     _TEST = {
-        'url': 'http://dsc.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
+        'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
         'md5': 'e12614f9ee303a6ccef415cb0793eba2',
         'info_dict': {
             'id': '614784',

youtube_dl/extractor/dreisat.py

@@ -1,39 +1,37 @@
-# coding: utf-8
+from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    unified_strdate,
-)
+from ..utils import unified_strdate
 
 
 class DreiSatIE(InfoExtractor):
     IE_NAME = '3sat'
     _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
     _TEST = {
-        u"url": u"http://www.3sat.de/mediathek/index.php?obj=36983",
-        u'file': u'36983.mp4',
-        u'md5': u'9dcfe344732808dbfcc901537973c922',
-        u'info_dict': {
-            u"title": u"Kaffeeland Schweiz",
-            u"description": u"Über 80 Kaffeeröstereien liefern in der Schweiz das Getränk, in das das Land so vernarrt ist: Mehr als 1000 Tassen trinkt ein Schweizer pro Jahr. SCHWEIZWEIT nimmt die Kaffeekultur unter die...", 
-            u"uploader": u"3sat",
-            u"upload_date": u"20130622"
+        'url': 'http://www.3sat.de/mediathek/index.php?obj=36983',
+        'md5': '9dcfe344732808dbfcc901537973c922',
+        'info_dict': {
+            'id': '36983',
+            'ext': 'mp4',
+            'title': 'Kaffeeland Schweiz',
+            'description': 'md5:cc4424b18b75ae9948b13929a0814033',
+            'uploader': '3sat',
+            'upload_date': '20130622'
         }
     }
 
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
-        details_doc = self._download_xml(details_url, video_id, note=u'Downloading video details')
+        details_doc = self._download_xml(details_url, video_id, 'Downloading video details')
 
         thumbnail_els = details_doc.findall('.//teaserimage')
         thumbnails = [{
-            'width': te.attrib['key'].partition('x')[0],
-            'height': te.attrib['key'].partition('x')[2],
+            'width': int(te.attrib['key'].partition('x')[0]),
+            'height': int(te.attrib['key'].partition('x')[2]),
             'url': te.text,
         } for te in thumbnail_els]
 

youtube_dl/extractor/dropbox.py

@@ -5,24 +5,26 @@ import os.path
 import re
 
 from .common import InfoExtractor
+from ..utils import compat_urllib_parse_unquote
 
 
 class DropboxIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P<id>[a-zA-Z0-9]{15})/(?P<title>[^?#]*)'
     _TEST = {
-        'url': 'https://www.dropbox.com/s/0qr9sai2veej4f8/THE_DOCTOR_GAMES.mp4',
-        'md5': '8ae17c51172fb7f93bdd6a214cc8c896',
+        'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4',
+        'md5': '8a3d905427a6951ccb9eb292f154530b',
         'info_dict': {
-            'id': '0qr9sai2veej4f8',
+            'id': 'nelirfsxnmcfbfh',
             'ext': 'mp4',
-            'title': 'THE_DOCTOR_GAMES'
+            'title': 'youtube-dl test video \'ä"BaW_jenozKc'
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        title = os.path.splitext(mobj.group('title'))[0]
+        fn = compat_urllib_parse_unquote(mobj.group('title'))
+        title = os.path.splitext(fn)[0]
         video_url = url + '?dl=1'
 
         return {

youtube_dl/extractor/drtv.py

@@ -0,0 +1,91 @@
+from __future__ import unicode_literals
+
+import re
+
+from .subtitles import SubtitlesInfoExtractor
+from .common import ExtractorError
+from ..utils import parse_iso8601
+
+
+class DRTVIE(SubtitlesInfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?dr\.dk/tv/se/[^/]+/(?P<id>[\da-z-]+)'
+
+    _TEST = {
+        'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8',
+        'md5': '4a7e1dd65cdb2643500a3f753c942f25',
+        'info_dict': {
+            'id': 'partiets-mand-7-8',
+            'ext': 'mp4',
+            'title': 'Partiets mand (7:8)',
+            'description': 'md5:a684b90a8f9336cd4aab94b7647d7862',
+            'timestamp': 1403047940,
+            'upload_date': '20140617',
+            'duration': 1299.040,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        programcard = self._download_json(
+            'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, video_id, 'Downloading video JSON')
+
+        data = programcard['Data'][0]
+
+        title = data['Title']
+        description = data['Description']
+        timestamp = parse_iso8601(data['CreatedTime'][:-5])
+
+        thumbnail = None
+        duration = None
+
+        restricted_to_denmark = False
+
+        formats = []
+        subtitles = {}
+
+        for asset in data['Assets']:
+            if asset['Kind'] == 'Image':
+                thumbnail = asset['Uri']
+            elif asset['Kind'] == 'VideoResource':
+                duration = asset['DurationInMilliseconds'] / 1000.0
+                restricted_to_denmark = asset['RestrictedToDenmark']
+                for link in asset['Links']:
+                    target = link['Target']
+                    uri = link['Uri']
+                    formats.append({
+                        'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri,
+                        'format_id': target,
+                        'ext': link['FileFormat'],
+                        'preference': -1 if target == 'HDS' else -2,
+                    })
+                subtitles_list = asset.get('SubtitlesList')
+                if isinstance(subtitles_list, list):
+                    LANGS = {
+                        'Danish': 'dk',
+                    }
+                    for subs in subtitles_list:
+                        lang = subs['Language']
+                        subtitles[LANGS.get(lang, lang)] = subs['Uri']
+
+        if not formats and restricted_to_denmark:
+            raise ExtractorError(
+                'Unfortunately, DR is not allowed to show this program outside Denmark.', expected=True)
+
+        self._sort_formats(formats)
+
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': self.extract_subtitles(video_id, subtitles),
+        }

youtube_dl/extractor/empflix.py

@@ -0,0 +1,54 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class EmpflixIE(InfoExtractor):
+    _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html'
+    _TEST = {
+        'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
+        'md5': 'b1bc15b6412d33902d6e5952035fcabc',
+        'info_dict': {
+            'id': '33051',
+            'ext': 'mp4',
+            'title': 'Amateur Finger Fuck',
+            'description': 'Amateur solo finger fucking.',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        age_limit = self._rta_search(webpage)
+
+        video_title = self._html_search_regex(
+            r'name="title" value="(?P<title>[^"]*)"', webpage, 'title')
+        video_description = self._html_search_regex(
+            r'name="description" value="([^"]*)"', webpage, 'description', fatal=False)
+
+        cfg_url = self._html_search_regex(
+            r'flashvars\.config = escape\("([^"]+)"',
+            webpage, 'flashvars.config')
+
+        cfg_xml = self._download_xml(
+            cfg_url, video_id, note='Downloading metadata')
+
+        formats = [
+            {
+                'url': item.find('videoLink').text,
+                'format_id': item.find('res').text,
+            } for item in cfg_xml.findall('./quality/item')
+        ]
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'description': video_description,
+            'formats': formats,
+            'age_limit': age_limit,
+        }

youtube_dl/extractor/extremetube.py

@@ -1,4 +1,5 @@
-import os
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -8,18 +9,23 @@ from ..utils import (
     compat_urllib_parse,
 )
 
+
 class ExtremeTubeIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
-    _TEST = {
-        u'url': u'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-        u'file': u'652431.mp4',
-        u'md5': u'1fb9228f5e3332ec8c057d6ac36f33e0',
-        u'info_dict': {
-            u"title": u"Music Video 14 british euro brit european cumshots swallow",
-            u"uploader": u"unknown",
-            u"age_limit": 18,
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
+    _TESTS = [{
+        'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
+        'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
+        'info_dict': {
+            'id': '652431',
+            'ext': 'mp4',
+            'title': 'Music Video 14 british euro brit european cumshots swallow',
+            'uploader': 'unknown',
+            'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'http://www.extremetube.com/gay/video/abcde-1234',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -30,11 +36,14 @@ class ExtremeTubeIE(InfoExtractor):
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
-        video_title = self._html_search_regex(r'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, u'title')
-        uploader = self._html_search_regex(r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, u'uploader', fatal=False)
-        video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, u'video_url'))
+        video_title = self._html_search_regex(
+            r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
+        uploader = self._html_search_regex(
+            r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader',
+            fatal=False)
+        video_url = compat_urllib_parse.unquote(self._html_search_regex(
+            r'video_url=(.+?)&amp;', webpage, 'video_url'))
         path = compat_urllib_parse_urlparse(video_url).path
-        extension = os.path.splitext(path)[1][1:]
         format = path.split('/')[5].split('_')[:2]
         format = "-".join(format)
 
@@ -43,7 +52,6 @@ class ExtremeTubeIE(InfoExtractor):
             'title': video_title,
             'uploader': uploader,
             'url': video_url,
-            'ext': extension,
             'format': format,
             'format_id': format,
             'age_limit': 18,

youtube_dl/extractor/facebook.py

@@ -76,9 +76,8 @@ class FacebookIE(InfoExtractor):
 
             check_form = {
                 'fb_dtsg': self._search_regex(r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg'),
-                'nh': self._search_regex(r'name="nh" value="(\w*?)"', login_results, 'nh'),
+                'h': self._search_regex(r'name="h" value="(\w*?)"', login_results, 'h'),
                 'name_action_selected': 'dont_save',
-                'submit[Continue]': self._search_regex(r'<button[^>]+value="(.*?)"[^>]+name="submit\[Continue\]"', login_results, 'continue'),
             }
             check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
             check_req.add_header('Content-Type', 'application/x-www-form-urlencoded')

youtube_dl/extractor/fc2.py

@@ -0,0 +1,63 @@
+#! -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+import hashlib
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_request,
+    compat_urlparse,
+)
+
+
+class FC2IE(InfoExtractor):
+    _VALID_URL = r'^http://video\.fc2\.com/((?P<lang>[^/]+)/)?content/(?P<id>[^/]+)'
+    IE_NAME = 'fc2'
+    _TEST = {
+        'url': 'http://video.fc2.com/en/content/20121103kUan1KHs',
+        'md5': 'a6ebe8ebe0396518689d963774a54eb7',
+        'info_dict': {
+            'id': '20121103kUan1KHs',
+            'ext': 'flv',
+            'title': 'Boxing again with Puff',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        self._downloader.cookiejar.clear_session_cookies()  # must clear
+
+        title = self._og_search_title(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+        refer = url.replace('/content/', '/a/content/')
+
+        mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
+
+        info_url = (
+            "http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&".
+            format(video_id, mimi, compat_urllib_request.quote(refer, safe='').replace('.','%2E')))
+
+        info_webpage = self._download_webpage(
+            info_url, video_id, note='Downloading info page')
+        info = compat_urlparse.parse_qs(info_webpage)
+
+        if 'err_code' in info:
+            raise ExtractorError('Error code: %s' % info['err_code'][0])
+
+        video_url = info['filepath'][0] + '?mid=' + info['mid'][0]
+        title_info = info.get('title')
+        if title_info:
+            title = title_info[0]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'ext': 'flv',
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/firedrive.py

@@ -0,0 +1,82 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+
+
+class FiredriveIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?firedrive\.com/' + \
+                 '(?:file|embed)/(?P<id>[0-9a-zA-Z]+)'
+    _FILE_DELETED_REGEX = r'<div class="removed_file_image">'
+
+    _TESTS = [{
+        'url': 'https://www.firedrive.com/file/FEB892FA160EBD01',
+        'md5': 'd5d4252f80ebeab4dc2d5ceaed1b7970',
+        'info_dict': {
+            'id': 'FEB892FA160EBD01',
+            'ext': 'flv',
+            'title': 'bbb_theora_486kbit.flv',
+            'thumbnail': 're:^http://.*\.jpg$',
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        url = 'http://firedrive.com/file/%s' % video_id
+
+        webpage = self._download_webpage(url, video_id)
+
+        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id,
+                                 expected=True)
+
+        fields = dict(re.findall(r'''(?x)<input\s+
+            type="hidden"\s+
+            name="([^"]+)"\s+
+            (?:id="[^"]+"\s+)?
+            value="([^"]*)"
+            ''', webpage))
+
+        post = compat_urllib_parse.urlencode(fields)
+        req = compat_urllib_request.Request(url, post)
+        req.add_header('Content-type', 'application/x-www-form-urlencoded')
+
+        # Apparently, this header is required for confirmation to work.
+        req.add_header('Host', 'www.firedrive.com')
+
+        webpage = self._download_webpage(req, video_id,
+                                         'Downloading video page')
+
+        title = self._search_regex(r'class="external_title_left">(.+)</div>',
+                                   webpage, 'title')
+        thumbnail = self._search_regex(r'image:\s?"(//[^\"]+)', webpage,
+                                       'thumbnail', fatal=False)
+        if thumbnail is not None:
+            thumbnail = 'http:' + thumbnail
+
+        ext = self._search_regex(r'type:\s?\'([^\']+)\',',
+                                 webpage, 'extension', fatal=False)
+        video_url = self._search_regex(
+            r'file:\s?\'(http[^\']+)\',', webpage, 'file url')
+
+        formats = [{
+            'format_id': 'sd',
+            'url': video_url,
+            'ext': ext,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/firstpost.py

@@ -15,6 +15,7 @@ class FirstpostIE(InfoExtractor):
             'id': '1025403',
             'ext': 'mp4',
             'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
+            'description': 'md5:feef3041cb09724e0bdc02843348f5f4',
         }
     }
 
@@ -22,13 +23,16 @@ class FirstpostIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
+        page = self._download_webpage(url, video_id)
+        title = self._html_search_meta('twitter:title', page, 'title')
+        description = self._html_search_meta('twitter:description', page, 'title')
+
         data = self._download_xml(
             'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id,
             'Downloading video XML')
 
         item = data.find('./playlist/item')
         thumbnail = item.find('./image').text
-        title = item.find('./title').text
 
         formats = [
             {
@@ -42,6 +46,7 @@ class FirstpostIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
+            'description': description,
             'thumbnail': thumbnail,
             'formats': formats,
         }

youtube_dl/extractor/fivemin.py

@@ -5,6 +5,8 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     compat_str,
+    compat_urllib_parse,
+    ExtractorError,
 )
 
 
@@ -16,16 +18,28 @@ class FiveMinIE(InfoExtractor):
         (?P<id>\d+)
         '''
 
-    _TEST = {
-        # From http://www.engadget.com/2013/11/15/ipad-mini-retina-display-review/
-        'url': 'http://pshared.5min.com/Scripts/PlayerSeed.js?sid=281&width=560&height=345&playList=518013791',
-        'md5': '4f7b0b79bf1a470e5004f7112385941d',
-        'info_dict': {
-            'id': '518013791',
-            'ext': 'mp4',
-            'title': 'iPad Mini with Retina Display Review',
+    _TESTS = [
+        {
+            # From http://www.engadget.com/2013/11/15/ipad-mini-retina-display-review/
+            'url': 'http://pshared.5min.com/Scripts/PlayerSeed.js?sid=281&width=560&height=345&playList=518013791',
+            'md5': '4f7b0b79bf1a470e5004f7112385941d',
+            'info_dict': {
+                'id': '518013791',
+                'ext': 'mp4',
+                'title': 'iPad Mini with Retina Display Review',
+            },
         },
-    }
+        {
+            # From http://on.aol.com/video/how-to-make-a-next-level-fruit-salad-518086247
+            'url': '5min:518086247',
+            'md5': 'e539a9dd682c288ef5a498898009f69e',
+            'info_dict': {
+                'id': '518086247',
+                'ext': 'mp4',
+                'title': 'How to Make a Next-Level Fruit Salad',
+            },
+        },
+    ]
 
     @classmethod
     def _build_result(cls, video_id):
@@ -34,10 +48,28 @@ class FiveMinIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        info = self._download_json(
-            'https://syn.5min.com/handlers/SenseHandler.ashx?func=GetResults&'
-            'playlist=%s&url=https' % video_id,
-            video_id)['binding'][0]
+        embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id
+        embed_page = self._download_webpage(embed_url, video_id,
+            'Downloading embed page')
+        sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid')
+        query = compat_urllib_parse.urlencode({
+            'func': 'GetResults',
+            'playlist': video_id,
+            'sid': sid,
+            'isPlayerSeed': 'true',
+            'url': embed_url,
+        })
+        response = self._download_json(
+            'https://syn.5min.com/handlers/SenseHandler.ashx?' + query,
+            video_id)
+        if not response['success']:
+            err_msg = response['errorMessage']
+            if err_msg == 'ErrorVideoUserNotGeo':
+                msg = 'Video not available from your location'
+            else:
+                msg = 'Aol said: %s' % err_msg
+            raise ExtractorError(msg, expected=True, video_id=video_id)
+        info = response['binding'][0]
 
         second_id = compat_str(int(video_id[:-2]) + 1)
         formats = []

youtube_dl/extractor/francetv.py

@@ -48,24 +48,36 @@ class PluzzIE(FranceTVBaseInfoExtractor):
 
 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
     IE_NAME = 'francetvinfo.fr'
-    _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+)\.html'
+    _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
-        'file': '84981923.mp4',
         'info_dict': {
+            'id': '84981923',
+            'ext': 'mp4',
             'title': 'Soir 3',
         },
         'params': {
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
+        'info_dict': {
+            'id': 'EV_20019',
+            'ext': 'mp4',
+            'title': 'Débat des candidats à la Commission européenne',
+            'description': 'Débat des candidats à la Commission européenne',
+        },
+        'params': {
+            'skip_download': 'HLS (reqires ffmpeg)'
+        }
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
-        video_id = self._search_regex(r'id-video=(\d+?)[@"]', webpage, 'video id')
+        video_id = self._search_regex(r'id-video=((?:[^0-9]*?_)?[0-9]+)[@"]', webpage, 'video id')
         return self._extract_video(video_id)
 
 
@@ -199,7 +211,7 @@ class GenerationQuoiIE(InfoExtractor):
 
 class CultureboxIE(FranceTVBaseInfoExtractor):
     IE_NAME = 'culturebox.francetvinfo.fr'
-    _VALID_URL = r'https?://culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
+    _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 
     _TEST = {
         'url': 'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813',

youtube_dl/extractor/funnyordie.py

@@ -4,22 +4,32 @@ import json
 import re
 
 from .common import InfoExtractor
+from ..utils import ExtractorError
 
 
 class FunnyOrDieIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
-        'file': '0732f586d7.mp4',
-        'md5': 'f647e9e90064b53b6e046e75d0241fbd',
+        'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9',
         'info_dict': {
-            'description': ('Lyrics changed to match the video. Spoken cameo '
-                'by Obscurus Lupa (from ThatGuyWithTheGlasses.com). Based on a '
-                'concept by Dustin McLean (DustFilms.com). Performed, edited, '
-                'and written by David A. Scott.'),
+            'id': '0732f586d7',
+            'ext': 'mp4',
             'title': 'Heart-Shaped Box: Literal Video Version',
+            'description': 'md5:ea09a01bc9a1c46d9ab696c01747c338',
+            'thumbnail': 're:^http:.*\.jpg$',
         },
-    }
+    }, {
+        'url': 'http://www.funnyordie.com/embed/e402820827',
+        'md5': 'ff4d83318f89776ed0250634cfaa8d36',
+        'info_dict': {
+            'id': 'e402820827',
+            'ext': 'mp4',
+            'title': 'Please Use This Song (Jon Lajoie)',
+            'description': 'Please use this to sell something.  www.jonlajoie.com',
+            'thumbnail': 're:^http:.*\.jpg$',
+        },
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -27,27 +37,34 @@ class FunnyOrDieIE(InfoExtractor):
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
 
-        video_url = self._search_regex(
-            [r'type="video/mp4" src="(.*?)"', r'src="([^>]*?)" type=\'video/mp4\''],
-            webpage, 'video URL', flags=re.DOTALL)
+        links = re.findall(r'<source src="([^"]+/v)\d+\.([^"]+)" type=\'video', webpage)
+        if not links:
+            raise ExtractorError('No media links available for %s' % video_id)
 
-        if mobj.group('type') == 'embed':
-            post_json = self._search_regex(
-                r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details')
-            post = json.loads(post_json)
-            title = post['name']
-            description = post.get('description')
-            thumbnail = post.get('picture')
-        else:
-            title = self._og_search_title(webpage)
-            description = self._og_search_description(webpage)
-            thumbnail = None
+        links.sort(key=lambda link: 1 if link[1] == 'mp4' else 0)
+
+        bitrates = self._html_search_regex(r'<source src="[^"]+/v,((?:\d+,)+)\.mp4\.csmil', webpage, 'video bitrates')
+        bitrates = [int(b) for b in bitrates.rstrip(',').split(',')]
+        bitrates.sort()
+
+        formats = []
+
+        for bitrate in bitrates:
+            for link in links:
+                formats.append({
+                    'url': '%s%d.%s' % (link[0], bitrate, link[1]),
+                    'format_id': '%s-%d' % (link[1], bitrate),
+                    'vbr': bitrate,
+                })
+
+        post_json = self._search_regex(
+            r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details')
+        post = json.loads(post_json)
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
+            'title': post['name'],
+            'description': post.get('description'),
+            'thumbnail': post.get('picture'),
+            'formats': formats,
         }

youtube_dl/extractor/gamekings.py

@@ -15,7 +15,7 @@ class GamekingsIE(InfoExtractor):
             'id': '20130811',
             'ext': 'mp4',
             'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review',
-            'description': 'md5:632e61a9f97d700e83f43d77ddafb6a4',
+            'description': 'md5:36fd701e57e8c15ac8682a2374c99731',
         }
     }
 

youtube_dl/extractor/gameone.py

@@ -0,0 +1,90 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    xpath_with_ns,
+    parse_iso8601
+)
+
+NAMESPACE_MAP = {
+    'media': 'http://search.yahoo.com/mrss/',
+}
+
+# URL prefix to download the mp4 files directly instead of streaming via rtmp
+# Credits go to XBox-Maniac
+# http://board.jdownloader.org/showpost.php?p=185835&postcount=31
+RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/'
+
+
+class GameOneIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.gameone.de/tv/288',
+        'md5': '136656b7fb4c9cb4a8e2d500651c499b',
+        'info_dict': {
+            'id': '288',
+            'ext': 'mp4',
+            'title': 'Game One - Folge 288',
+            'duration': 1238,
+            'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg',
+            'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1',
+            'age_limit': 16,
+            'upload_date': '20140513',
+            'timestamp': 1399980122,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        og_video = self._og_search_video_url(webpage, secure=False)
+        description = self._html_search_meta('description', webpage)
+        age_limit = int(
+            self._search_regex(
+                r'age=(\d+)',
+                self._html_search_meta(
+                    'age-de-meta-label',
+                    webpage),
+                'age_limit',
+                '0'))
+        mrss_url = self._search_regex(r'mrss=([^&]+)', og_video, 'mrss')
+
+        mrss = self._download_xml(mrss_url, video_id, 'Downloading mrss')
+        title = mrss.find('.//item/title').text
+        thumbnail = mrss.find('.//item/image').get('url')
+        timestamp = parse_iso8601(mrss.find('.//pubDate').text, delimiter=' ')
+        content = mrss.find(xpath_with_ns('.//media:content', NAMESPACE_MAP))
+        content_url = content.get('url')
+
+        content = self._download_xml(
+            content_url,
+            video_id,
+            'Downloading media:content')
+        rendition_items = content.findall('.//rendition')
+        duration = int(rendition_items[0].get('duration'))
+        formats = [
+            {
+                'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text),
+                'width': int(r.get('width')),
+                'height': int(r.get('height')),
+                'tbr': int(r.get('bitrate')),
+            }
+            for r in rendition_items
+        ]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+            'description': description,
+            'age_limit': age_limit,
+            'timestamp': timestamp,
+        }

youtube_dl/extractor/gamespot.py

@@ -15,11 +15,12 @@ from ..utils import (
 class GameSpotIE(InfoExtractor):
     _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<page_id>\d+)/?'
     _TEST = {
-        "url": "http://www.gamespot.com/arma-iii/videos/arma-iii-community-guide-sitrep-i-6410818/",
-        "file": "gs-2300-6410818.mp4",
-        "md5": "b2a30deaa8654fcccd43713a6b6a4825",
-        "info_dict": {
-            "title": "Arma 3 - Community Guide: SITREP I",
+        'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
+        'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
+        'info_dict': {
+            'id': 'gs-2300-6410818',
+            'ext': 'mp4',
+            'title': 'Arma 3 - Community Guide: SITREP I',
             'description': 'Check out this video where some of the basics of Arma 3 is explained.',
         }
     }

youtube_dl/extractor/generic.py

@@ -35,9 +35,10 @@ class GenericIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
-            'file': '13601338388002.mp4',
-            'md5': '6e15c93721d7ec9e9ca3fdbf07982cfd',
+            'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
             'info_dict': {
+                'id': '13601338388002',
+                'ext': 'mp4',
                 'uploader': 'www.hodiho.fr',
                 'title': 'R\u00e9gis plante sa Jeep',
             }
@@ -46,8 +47,9 @@ class GenericIE(InfoExtractor):
         {
             'add_ie': ['Bandcamp'],
             'url': 'http://bronyrock.com/track/the-pony-mash',
-            'file': '3235767654.mp3',
             'info_dict': {
+                'id': '3235767654',
+                'ext': 'mp3',
                 'title': 'The Pony Mash',
                 'uploader': 'M_Pallante',
             },
@@ -73,9 +75,10 @@ class GenericIE(InfoExtractor):
         {
             # https://github.com/rg3/youtube-dl/issues/2253
             'url': 'http://bcove.me/i6nfkrc3',
-            'file': '3101154703001.mp4',
             'md5': '0ba9446db037002366bab3b3eb30c88c',
             'info_dict': {
+                'id': '3101154703001',
+                'ext': 'mp4',
                 'title': 'Still no power',
                 'uploader': 'thestar.com',
                 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
@@ -236,6 +239,56 @@ class GenericIE(InfoExtractor):
                 'uploader_id': 'rbctv_2012_4',
             },
         },
+        # Condé Nast embed
+        {
+            'url': 'http://www.wired.com/2014/04/honda-asimo/',
+            'md5': 'ba0dfe966fa007657bd1443ee672db0f',
+            'info_dict': {
+                'id': '53501be369702d3275860000',
+                'ext': 'mp4',
+                'title': 'Honda’s  New Asimo Robot Is More Human Than Ever',
+            }
+        },
+        # Dailymotion embed
+        {
+            'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
+            'md5': '441aeeb82eb72c422c7f14ec533999cd',
+            'info_dict': {
+                'id': 'k2mm4bCdJ6CQ2i7c8o2',
+                'ext': 'mp4',
+                'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
+                'uploader': 'Spi0n',
+            },
+            'add_ie': ['Dailymotion'],
+        },
+        # YouTube embed
+        {
+            'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
+            'info_dict': {
+                'id': 'FXRb4ykk4S0',
+                'ext': 'mp4',
+                'title': 'The NBL Auction 2014',
+                'uploader': 'BADMINTON England',
+                'uploader_id': 'BADMINTONEvents',
+                'upload_date': '20140603',
+                'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
+            },
+            'add_ie': ['Youtube'],
+            'params': {
+                'skip_download': True,
+            }
+        },
+        # MTVSercices embed
+        {
+            'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
+            'md5': '35727f82f58c76d996fc188f9755b0d5',
+            'info_dict': {
+                'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
+                'ext': 'mp4',
+                'title': 'Review',
+                'description': 'Mario\'s life in the fast lane has never looked so good.',
+            },
+        },
     ]
 
     def report_download_webpage(self, video_id):
@@ -320,11 +373,17 @@ class GenericIE(InfoExtractor):
         }
 
     def _real_extract(self, url):
+        if url.startswith('//'):
+            return {
+                '_type': 'url',
+                'url': self.http_scheme() + url,
+            }
+
         parsed_url = compat_urlparse.urlparse(url)
         if not parsed_url.scheme:
             default_search = self._downloader.params.get('default_search')
             if default_search is None:
-                default_search = 'auto_warning'
+                default_search = 'error'
 
             if default_search in ('auto', 'auto_warning'):
                 if '/' in url:
@@ -332,9 +391,19 @@ class GenericIE(InfoExtractor):
                     return self.url_result('http://' + url)
                 else:
                     if default_search == 'auto_warning':
-                        self._downloader.report_warning(
-                            'Falling back to youtube search for  %s . Set --default-search to "auto" to suppress this warning.' % url)
+                        if re.match(r'^(?:url|URL)$', url):
+                            raise ExtractorError(
+                                'Invalid URL:  %r . Call youtube-dl like this:  youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc"  ' % url,
+                                expected=True)
+                        else:
+                            self._downloader.report_warning(
+                                'Falling back to youtube search for  %s . Set --default-search "auto" to suppress this warning.' % url)
                     return self.url_result('ytsearch:' + url)
+            elif default_search == 'error':
+                raise ExtractorError(
+                    ('%r is not a valid URL. '
+                     'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
+                    ) % (url, url), expected=True)
             else:
                 assert ':' in default_search
                 return self.url_result(default_search + url)
@@ -442,8 +511,13 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded YouTube player
         matches = re.findall(r'''(?x)
-            (?:<iframe[^>]+?src=|embedSWF\(\s*)
-            (["\'])(?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
+            (?:
+                <iframe[^>]+?src=|
+                <embed[^>]+?src=|
+                embedSWF\(?:\s*
+            )
+            (["\'])
+                (?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
                 (?:embed|v)/.+?)
             \1''', webpage)
         if matches:
@@ -456,7 +530,7 @@ class GenericIE(InfoExtractor):
         matches = re.findall(
             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
         if matches:
-            urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Dailymotion')
+            urlrs = [self.url_result(unescapeHTML(tuppl[1]))
                      for tuppl in matches]
             return self.playlist_result(
                 urlrs, playlist_id=video_id, playlist_title=video_title)
@@ -482,6 +556,22 @@ class GenericIE(InfoExtractor):
         if mobj:
             return self.url_result(mobj.group(1), 'BlipTV')
 
+        # Look for embedded condenast player
+        matches = re.findall(
+            r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
+            webpage)
+        if matches:
+            return {
+                '_type': 'playlist',
+                'entries': [{
+                    '_type': 'url',
+                    'ie_key': 'CondeNast',
+                    'url': ma,
+                } for ma in matches],
+                'title': video_title,
+                'id': video_id,
+            }
+
         # Look for Bandcamp pages with custom domain
         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
         if mobj is not None:
@@ -502,7 +592,7 @@ class GenericIE(InfoExtractor):
             return OoyalaIE._build_url_result(mobj.group('ec'))
 
         # Look for Aparat videos
-        mobj = re.search(r'<iframe src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
+        mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
         if mobj is not None:
             return self.url_result(mobj.group(1), 'Aparat')
 
@@ -513,7 +603,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded NovaMov-based player
         mobj = re.search(
-            r'''(?x)<iframe[^>]+?src=(["\'])
+            r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
                     (?P<url>http://(?:(?:embed|www)\.)?
                         (?:novamov\.com|
                            nowvideo\.(?:ch|sx|eu|at|ag|co)|
@@ -535,6 +625,11 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'VK')
 
+        # Look for embedded ivi player
+        mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Ivi')
+
         # Look for embedded Huffington Post player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
@@ -586,65 +681,102 @@ class GenericIE(InfoExtractor):
         if smotri_url:
             return self.url_result(smotri_url, 'Smotri')
 
-        # Start with something easy: JW Player in SWFObject
-        mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
-        if mobj is None:
-            # Look for gorilla-vid style embedding
-            mobj = re.search(r'(?s)(?:jw_plugins|JWPlayerOptions).*?file\s*:\s*["\'](.*?)["\']', webpage)
-        if mobj is None:
-            # Broaden the search a little bit
-            mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
-        if mobj is None:
-            # Broaden the search a little bit: JWPlayer JS loader
-            mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
+        # Look for embeded soundcloud player
+        mobj = re.search(
+            r'<iframe src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
+            webpage)
+        if mobj is not None:
+            url = unescapeHTML(mobj.group('url'))
+            return self.url_result(url)
 
-        if mobj is None:
+        # Look for embedded vulture.com player
+        mobj = re.search(
+            r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
+            webpage)
+        if mobj is not None:
+            url = unescapeHTML(mobj.group('url'))
+            return self.url_result(url, ie='Vulture')
+
+        # Look for embedded mtvservices player
+        mobj = re.search(
+            r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
+            webpage)
+        if mobj is not None:
+            url = unescapeHTML(mobj.group('url'))
+            return self.url_result(url, ie='MTVServicesEmbedded')
+
+        # Start with something easy: JW Player in SWFObject
+        found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+        if not found:
+            # Look for gorilla-vid style embedding
+            found = re.findall(r'''(?sx)
+                (?:
+                    jw_plugins|
+                    JWPlayerOptions|
+                    jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
+                )
+                .*?file\s*:\s*["\'](.*?)["\']''', webpage)
+        if not found:
+            # Broaden the search a little bit
+            found = re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+        if not found:
+            # Broaden the findall a little bit: JWPlayer JS loader
+            found = re.findall(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
+        if not found:
             # Try to find twitter cards info
-            mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
-        if mobj is None:
+            found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
+        if not found:
             # We look for Open Graph info:
             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
-            m_video_type = re.search(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
+            m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
             if m_video_type is not None:
-                mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
-        if mobj is None:
+                found = re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
+        if not found:
             # HTML5 video
-            mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
-        if mobj is None:
-            mobj = re.search(
+            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage)
+        if not found:
+            found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
                 r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'([^\']+)\'"',
                 webpage)
-            if mobj:
-                new_url = mobj.group(1)
+            if found:
+                new_url = found.group(1)
                 self.report_following_redirect(new_url)
                 return {
                     '_type': 'url',
                     'url': new_url,
                 }
-        if mobj is None:
+        if not found:
             raise ExtractorError('Unsupported URL: %s' % url)
 
-        # It's possible that one of the regexes
-        # matched, but returned an empty group:
-        if mobj.group(1) is None:
-            raise ExtractorError('Did not find a valid video URL at %s' % url)
+        entries = []
+        for video_url in found:
+            video_url = compat_urlparse.urljoin(url, video_url)
+            video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
 
-        video_url = mobj.group(1)
-        video_url = compat_urlparse.urljoin(url, video_url)
-        video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
+            # Sometimes, jwplayer extraction will result in a YouTube URL
+            if YoutubeIE.suitable(video_url):
+                entries.append(self.url_result(video_url, 'Youtube'))
+                continue
 
-        # Sometimes, jwplayer extraction will result in a YouTube URL
-        if YoutubeIE.suitable(video_url):
-            return self.url_result(video_url, 'Youtube')
+            # here's a fun little line of code for you:
+            video_id = os.path.splitext(video_id)[0]
 
-        # here's a fun little line of code for you:
-        video_id = os.path.splitext(video_id)[0]
+            entries.append({
+                'id': video_id,
+                'url': video_url,
+                'uploader': video_uploader,
+                'title': video_title,
+            })
+
+        if len(entries) == 1:
+            return entries[0]
+        else:
+            for num, e in enumerate(entries, start=1):
+                e['title'] = '%s (%d)' % (e['title'], num)
+            return {
+                '_type': 'playlist',
+                'entries': entries,
+            }
 
-        return {
-            'id': video_id,
-            'url': video_url,
-            'uploader': video_uploader,
-            'title': video_title,
-        }

youtube_dl/extractor/googleplus.py

@@ -52,8 +52,7 @@ class GooglePlusIE(InfoExtractor):
 
         # Extract title
         # Get the first line for title
-        video_title = self._html_search_regex(r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]',
-            webpage, 'title', default='NA')
+        video_title = self._og_search_description(webpage).splitlines()[0]
 
         # Step 2, Simulate clicking the image box to launch video
         DOMAIN = 'https://plus.google.com/'

youtube_dl/extractor/gorillavid.py

@@ -0,0 +1,88 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+
+
+class GorillaVidIE(InfoExtractor):
+    IE_DESC = 'GorillaVid.in and daclips.in'
+    _VALID_URL = r'''(?x)
+        https?://(?P<host>(?:www\.)?
+            (?:daclips\.in|gorillavid\.in))/
+        (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
+    '''
+
+    _TESTS = [{
+        'url': 'http://gorillavid.in/06y9juieqpmi',
+        'md5': '5ae4a3580620380619678ee4875893ba',
+        'info_dict': {
+            'id': '06y9juieqpmi',
+            'ext': 'flv',
+            'title': 'Rebecca Black My Moment Official Music Video Reaction',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }, {
+        'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
+        'md5': 'c9e293ca74d46cad638e199c3f3fe604',
+        'info_dict': {
+            'id': 'z08zf8le23c6',
+            'ext': 'mp4',
+            'title': 'Say something nice',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }, {
+        'url': 'http://daclips.in/3rso4kdn6f9m',
+        'md5': '1ad8fd39bb976eeb66004d3a4895f106',
+        'info_dict': {
+            'id': '3rso4kdn6f9m',
+            'ext': 'mp4',
+            'title': 'Micro Pig piglets ready on 16th July 2009',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage('http://%s/%s' % (mobj.group('host'), video_id), video_id)
+
+        fields = dict(re.findall(r'''(?x)<input\s+
+            type="hidden"\s+
+            name="([^"]+)"\s+
+            (?:id="[^"]+"\s+)?
+            value="([^"]*)"
+            ''', webpage))
+        
+        if fields['op'] == 'download1':
+            post = compat_urllib_parse.urlencode(fields)
+
+            req = compat_urllib_request.Request(url, post)
+            req.add_header('Content-type', 'application/x-www-form-urlencoded')
+
+            webpage = self._download_webpage(req, video_id, 'Downloading video page')
+
+        title = self._search_regex(r'style="z-index: [0-9]+;">([0-9a-zA-Z ]+)(?:-.+)?</span>', webpage, 'title')
+        thumbnail = self._search_regex(r'image:\'(http[^\']+)\',', webpage, 'thumbnail')
+        url = self._search_regex(r'file: \'(http[^\']+)\',', webpage, 'file url')
+
+        formats = [{
+            'format_id': 'sd',
+            'url': url,
+            'ext': determine_ext(url),
+            'quality': 1,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/goshgay.py

@@ -0,0 +1,73 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urlparse,
+    str_to_int,
+    ExtractorError,
+)
+import json
+
+
+class GoshgayIE(InfoExtractor):
+    _VALID_URL = r'^(?:https?://)www.goshgay.com/video(?P<id>\d+?)($|/)'
+    _TEST = {
+        'url': 'http://www.goshgay.com/video4116282',
+        'md5': '268b9f3c3229105c57859e166dd72b03',
+        'info_dict': {
+            'id': '4116282',
+            'ext': 'flv',
+            'title': 'md5:089833a4790b5e103285a07337f245bf',
+            'thumbnail': 're:http://.*\.jpg',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._search_regex(r'class="video-title"><h1>(.+?)<', webpage, 'title')
+
+        player_config = self._search_regex(
+            r'(?s)jwplayer\("player"\)\.setup\(({.+?})\)', webpage, 'config settings')
+        player_vars = json.loads(player_config.replace("'", '"'))
+        width = str_to_int(player_vars.get('width'))
+        height = str_to_int(player_vars.get('height'))
+        config_uri = player_vars.get('config')
+
+        if config_uri is None:
+            raise ExtractorError('Missing config URI')
+        node = self._download_xml(config_uri, video_id, 'Downloading player config XML',
+                                  errnote='Unable to download XML')
+        if node is None:
+            raise ExtractorError('Missing config XML')
+        if node.tag != 'config':
+            raise ExtractorError('Missing config attribute')
+        fns = node.findall('file')
+        imgs = node.findall('image')
+        if len(fns) != 1:
+            raise ExtractorError('Missing media URI')
+        video_url = fns[0].text
+        if len(imgs) < 1:
+            thumbnail = None
+        else:
+            thumbnail = imgs[0].text
+
+        url_comp = compat_urlparse.urlparse(url)
+        ref = "%s://%s%s" % (url_comp[0], url_comp[1], url_comp[2])
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'width': width,
+            'height': height,
+            'thumbnail': thumbnail,
+            'http_referer': ref,
+            'age_limit': 18,
+        }

youtube_dl/extractor/hentaistigma.py

@@ -0,0 +1,42 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class HentaiStigmaIE(InfoExtractor):
+    _VALID_URL = r'^https?://hentai\.animestigma\.com/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://hentai.animestigma.com/inyouchuu-etsu-bonus/',
+        'md5': '4e3d07422a68a4cc363d8f57c8bf0d23',
+        'info_dict': {
+            'id': 'inyouchuu-etsu-bonus',
+            'ext': 'mp4',
+            "title": "Inyouchuu Etsu Bonus",
+            "age_limit": 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+            r'<h2 class="posttitle"><a[^>]*>([^<]+)</a>',
+            webpage, 'title')
+        wrap_url = self._html_search_regex(
+            r'<iframe src="([^"]+mp4)"', webpage, 'wrapper url')
+        wrap_webpage = self._download_webpage(wrap_url, video_id)
+
+        video_url = self._html_search_regex(
+            r'clip:\s*{\s*url: "([^"]*)"', wrap_webpage, 'video url')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'age_limit': 18,
+        }

youtube_dl/extractor/hypem.py

@@ -1,10 +1,11 @@
+from __future__ import unicode_literals
+
 import json
 import re
 import time
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_str,
     compat_urllib_parse,
     compat_urllib_request,
 
@@ -13,59 +14,55 @@ from ..utils import (
 
 
 class HypemIE(InfoExtractor):
-    """Information Extractor for hypem"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
     _TEST = {
-        u'url': u'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
-        u'file': u'1v6ga.mp3',
-        u'md5': u'b9cc91b5af8995e9f0c1cee04c575828',
-        u'info_dict': {
-            u"title": u"Tame"
+        'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
+        'md5': 'b9cc91b5af8995e9f0c1cee04c575828',
+        'info_dict': {
+            'id': '1v6ga',
+            'ext': 'mp3',
+            'title': 'Tame',
+            'uploader': 'BODYWORK',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
         track_id = mobj.group(1)
 
         data = {'ax': 1, 'ts': time.time()}
         data_encoded = compat_urllib_parse.urlencode(data)
         complete_url = url + "?" + data_encoded
         request = compat_urllib_request.Request(complete_url)
-        response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url')
+        response, urlh = self._download_webpage_handle(
+            request, track_id, 'Downloading webpage with the url')
         cookie = urlh.headers.get('Set-Cookie', '')
 
-        self.report_extraction(track_id)
-
-        html_tracks = self._html_search_regex(r'<script type="application/json" id="displayList-data">(.*?)</script>',
-            response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip()
+        html_tracks = self._html_search_regex(
+            r'(?ms)<script type="application/json" id="displayList-data">\s*(.*?)\s*</script>',
+            response, 'tracks')
         try:
             track_list = json.loads(html_tracks)
-            track = track_list[u'tracks'][0]
+            track = track_list['tracks'][0]
         except ValueError:
-            raise ExtractorError(u'Hypemachine contained invalid JSON.')
+            raise ExtractorError('Hypemachine contained invalid JSON.')
 
-        key = track[u"key"]
-        track_id = track[u"id"]
-        artist = track[u"artist"]
-        title = track[u"song"]
+        key = track['key']
+        track_id = track['id']
+        artist = track['artist']
+        title = track['song']
 
-        serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key))
-        request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'})
+        serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key)
+        request = compat_urllib_request.Request(
+            serve_url, '', {'Content-Type': 'application/json'})
         request.add_header('cookie', cookie)
-        song_data_json = self._download_webpage(request, track_id, u'Downloading metadata')
-        try:
-            song_data = json.loads(song_data_json)
-        except ValueError:
-            raise ExtractorError(u'Hypemachine contained invalid JSON.')
-        final_url = song_data[u"url"]
+        song_data = self._download_json(request, track_id, 'Downloading metadata')
+        final_url = song_data["url"]
 
-        return [{
-            'id':       track_id,
-            'url':      final_url,
-            'ext':      "mp3",
-            'title':    title,
-            'artist':   artist,
-        }]
+        return {
+            'id': track_id,
+            'url': final_url,
+            'ext': 'mp3',
+            'title': title,
+            'uploader': artist,
+        }

youtube_dl/extractor/iconosquare.py

@@ -5,8 +5,8 @@ import re
 from .common import InfoExtractor
 
 
-class StatigramIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.)?statigr\.am/p/(?P<id>[^/]+)'
+class IconosquareIE(InfoExtractor):
+    _VALID_URL = r'https?://(www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P<id>[^/]+)'
     _TEST = {
         'url': 'http://statigr.am/p/522207370455279102_24101272',
         'md5': '6eb93b882a3ded7c378ee1d6884b1814',
@@ -15,6 +15,7 @@ class StatigramIE(InfoExtractor):
             'ext': 'mp4',
             'uploader_id': 'aguynamedpatrick',
             'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
+            'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d',
         },
     }
 
@@ -25,7 +26,7 @@ class StatigramIE(InfoExtractor):
         html_title = self._html_search_regex(
             r'<title>(.+?)</title>',
             webpage, 'title')
-        title = re.sub(r'(?: *\(Videos?\))? \| Statigram$', '', html_title)
+        title = re.sub(r'(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)$', '', html_title)
         uploader_id = self._html_search_regex(
             r'@([^ ]+)', title, 'uploader name', fatal=False)
 
@@ -33,6 +34,7 @@ class StatigramIE(InfoExtractor):
             'id': video_id,
             'url': self._og_search_video_url(webpage),
             'title': title,
+            'description': self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
             'uploader_id': uploader_id
         }

youtube_dl/extractor/ign.py

@@ -106,7 +106,7 @@ class OneUPIE(IGNIE):
 
     _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://gamevideos.1up.com/video/id/34976',
         'md5': '68a54ce4ebc772e4b71e3123d413163d',
         'info_dict': {
@@ -115,10 +115,7 @@ class OneUPIE(IGNIE):
             'title': 'Sniper Elite V2 - Trailer',
             'description': 'md5:5d289b722f5a6d940ca3136e9dae89cf',
         }
-    }
-
-    # Override IGN tests
-    _TESTS = []
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/infoq.py

@@ -11,16 +11,15 @@ from ..utils import (
 
 class InfoQIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
+
     _TEST = {
-        "name": "InfoQ",
-        "url": "http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
-        "file": "12-jan-pythonthings.mp4",
-        "info_dict": {
-            "description": "Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.",
-            "title": "A Few of My Favorite [Python] Things",
-        },
-        "params": {
-            "skip_download": True,
+        'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
+        'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
+        'info_dict': {
+            'id': '12-jan-pythonthings',
+            'ext': 'mp4',
+            'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.',
+            'title': 'A Few of My Favorite [Python] Things',
         },
     }
 
@@ -30,26 +29,39 @@ class InfoQIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
+        video_description = self._html_search_meta('description', webpage, 'description')
+
+        # The server URL is hardcoded
+        video_url = 'rtmpe://video.infoq.com/cfx/st/'
+
         # Extract video URL
-        encoded_id = self._search_regex(r"jsclassref ?= ?'([^']*)'", webpage, 'encoded id')
+        encoded_id = self._search_regex(
+            r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id')
         real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
-        video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
+        playpath = 'mp4:' + real_id
 
-        # Extract title
-        video_title = self._search_regex(r'contentTitle = "(.*?)";',
-            webpage, 'title')
-
-        # Extract description
-        video_description = self._html_search_regex(r'<meta name="description" content="(.*)"(?:\s*/)?>',
-            webpage, 'description', fatal=False)
-
-        video_filename = video_url.split('/')[-1]
+        video_filename = playpath.split('/')[-1]
         video_id, extension = video_filename.split('.')
 
+        http_base = self._search_regex(
+            r'EXPRESSINSTALL_SWF\s*=\s*"(https?://[^/"]+/)', webpage,
+            'HTTP base URL')
+
+        formats = [{
+            'format_id': 'rtmp',
+            'url': video_url,
+            'ext': extension,
+            'play_path': playpath,
+        }, {
+            'format_id': 'http',
+            'url': http_base + real_id,
+        }]
+        self._sort_formats(formats)
+
         return {
             'id': video_id,
-            'url': video_url,
             'title': video_title,
-            'ext': extension,  # Extension is always(?) mp4, but seems to be flv
             'description': video_description,
+            'formats': formats,
         }

youtube_dl/extractor/ivi.py

@@ -14,7 +14,7 @@ from ..utils import (
 class IviIE(InfoExtractor):
     IE_DESC = 'ivi.ru'
     IE_NAME = 'ivi'
-    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch(?:/(?P<compilationid>[^/]+))?/(?P<videoid>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<videoid>\d+)'
 
     _TESTS = [
         # Single movie
@@ -33,14 +33,14 @@ class IviIE(InfoExtractor):
         },
         # Serial's serie
         {
-            'url': 'http://www.ivi.ru/watch/dezhurnyi_angel/74791',
-            'md5': '3e6cc9a848c1d2ebcc6476444967baa9',
+            'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549',
+            'md5': '221f56b35e3ed815fde2df71032f4b3e',
             'info_dict': {
-                'id': '74791',
+                'id': '9549',
                 'ext': 'mp4',
-                'title': 'Дежурный ангел - 1 серия',
-                'duration': 2490,
-                'thumbnail': 'http://thumbs.ivi.ru/f7.vcp.digitalaccess.ru/contents/8/e/bc2f6c2b6e5d291152fdd32c059141.jpg',
+                'title': 'Двое из ларца - Серия 1',
+                'duration': 2655,
+                'thumbnail': 'http://thumbs.ivi.ru/f15.vcp.digitalaccess.ru/contents/8/4/0068dc0677041f3336b7c2baad8fc0.jpg',
             },
             'skip': 'Only works from Russia',
          }

youtube_dl/extractor/jukebox.py

@@ -14,7 +14,7 @@ class JukeboxIE(InfoExtractor):
     _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+)\.html'
     _TEST = {
         'url': 'http://www.jukebox.es/kosheen/videoclip,pride,r303r.html',
-        'md5': '5dc6477e74b1e37042ac5acedd8413e5',
+        'md5': '1574e9b4d6438446d5b7dbcdf2786276',
         'info_dict': {
             'id': 'r303r',
             'ext': 'flv',

youtube_dl/extractor/kickstarter.py

@@ -8,7 +8,7 @@ from .common import InfoExtractor
 
 class KickStarterIE(InfoExtractor):
     _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>[^/]*)/.*'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location',
         'md5': 'c81addca81327ffa66c642b5d8b08cab',
         'info_dict': {
@@ -18,22 +18,45 @@ class KickStarterIE(InfoExtractor):
             'description': 'A unique motocross documentary that examines the '
                 'life and mind of one of sports most elite athletes: Josh Grant.',
         },
-    }
+    }, {
+        'note': 'Embedded video (not using the native kickstarter video service)',
+        'url': 'https://www.kickstarter.com/projects/597507018/pebble-e-paper-watch-for-iphone-and-android/posts/659178',
+        'playlist': [
+            {
+                'info_dict': {
+                    'id': '78704821',
+                    'ext': 'mp4',
+                    'uploader_id': 'pebble',
+                    'uploader': 'Pebble Technology',
+                    'title': 'Pebble iOS Notifications',
+                }
+            }
+        ],
+    }]
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
         video_id = m.group('id')
         webpage = self._download_webpage(url, video_id)
 
-        video_url = self._search_regex(r'data-video-url="(.*?)"',
-            webpage, 'video URL')
-        video_title = self._html_search_regex(r'<title>(.*?)</title>',
-            webpage, 'title').rpartition('— Kickstarter')[0].strip()
+        title = self._html_search_regex(
+            r'<title>\s*(.*?)(?:\s*&mdash; Kickstarter)?\s*</title>',
+            webpage, 'title')
+        video_url = self._search_regex(
+            r'data-video-url="(.*?)"',
+            webpage, 'video URL', default=None)
+        if video_url is None:  # No native kickstarter, look for embedded videos
+            return {
+                '_type': 'url_transparent',
+                'ie_key': 'Generic',
+                'url': url,
+                'title': title,
+            }
 
         return {
             'id': video_id,
             'url': video_url,
-            'title': video_title,
+            'title': title,
             'description': self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
         }

youtube_dl/extractor/ku6.py

@@ -0,0 +1,35 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class Ku6IE(InfoExtractor):
+    _VALID_URL = r'http://v\.ku6\.com/show/(?P<id>[a-zA-Z0-9\-\_]+)(?:\.)*html'
+    _TEST = {
+        'url': 'http://v.ku6.com/show/JG-8yS14xzBr4bCn1pu0xw...html',
+        'md5': '01203549b9efbb45f4b87d55bdea1ed1',
+        'info_dict': {
+            'id': 'JG-8yS14xzBr4bCn1pu0xw',
+            'ext': 'f4v',
+            'title': 'techniques test',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._search_regex(r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
+        dataUrl = 'http://v.ku6.com/fetchVideo4Player/%s.html' % video_id
+        jsonData = self._download_json(dataUrl, video_id)
+        downloadUrl = jsonData['data']['f']
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': downloadUrl
+        }
+

youtube_dl/extractor/lifenews.py

@@ -24,7 +24,7 @@ class LifeNewsIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом',
             'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.',
-            'thumbnail': 'http://lifenews.ru/static/posts/2014/1/126342/.video.jpg',
+            'thumbnail': 're:http://.*\.jpg',
             'upload_date': '20140130',
         }
     }

youtube_dl/extractor/livestream.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
@@ -6,31 +8,37 @@ from ..utils import (
     compat_urllib_parse_urlparse,
     compat_urlparse,
     xpath_with_ns,
+    compat_str,
+    orderedSet,
 )
 
 
 class LivestreamIE(InfoExtractor):
-    IE_NAME = u'livestream'
+    IE_NAME = 'livestream'
     _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
     _TEST = {
-        u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
-        u'file': u'4719370.mp4',
-        u'md5': u'0d2186e3187d185a04b3cdd02b828836',
-        u'info_dict': {
-            u'title': u'Live from Webster Hall NYC',
-            u'upload_date': u'20121012',
+        'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
+        'md5': '53274c76ba7754fb0e8d072716f2292b',
+        'info_dict': {
+            'id': '4719370',
+            'ext': 'mp4',
+            'title': 'Live from Webster Hall NYC',
+            'upload_date': '20121012',
         }
     }
 
     def _extract_video_info(self, video_data):
-        video_url = video_data.get('progressive_url_hd') or video_data.get('progressive_url')
-        return {'id': video_data['id'],
-                'url': video_url,
-                'ext': 'mp4',
-                'title': video_data['caption'],
-                'thumbnail': video_data['thumbnail_url'],
-                'upload_date': video_data['updated_at'].replace('-','')[:8],
-                }
+        video_url = (
+            video_data.get('progressive_url_hd') or
+            video_data.get('progressive_url')
+        )
+        return {
+            'id': compat_str(video_data['id']),
+            'url': video_url,
+            'title': video_data['caption'],
+            'thumbnail': video_data['thumbnail_url'],
+            'upload_date': video_data['updated_at'].replace('-', '')[:8],
+        }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -40,43 +48,44 @@ class LivestreamIE(InfoExtractor):
 
         if video_id is None:
             # This is an event page:
-            config_json = self._search_regex(r'window.config = ({.*?});',
-                webpage, u'window config')
+            config_json = self._search_regex(
+                r'window.config = ({.*?});', webpage, 'window config')
             info = json.loads(config_json)['event']
             videos = [self._extract_video_info(video_data['data'])
-                for video_data in info['feed']['data'] if video_data['type'] == u'video']
+                for video_data in info['feed']['data']
+                if video_data['type'] == 'video']
             return self.playlist_result(videos, info['id'], info['full_name'])
         else:
-            og_video = self._og_search_video_url(webpage, name=u'player url')
+            og_video = self._og_search_video_url(webpage, 'player url')
             query_str = compat_urllib_parse_urlparse(og_video).query
             query = compat_urlparse.parse_qs(query_str)
             api_url = query['play_url'][0].replace('.smil', '')
-            info = json.loads(self._download_webpage(api_url, video_id,
-                                                     u'Downloading video info'))
+            info = json.loads(self._download_webpage(
+                api_url, video_id, 'Downloading video info'))
             return self._extract_video_info(info)
 
 
 # The original version of Livestream uses a different system
 class LivestreamOriginalIE(InfoExtractor):
-    IE_NAME = u'livestream:original'
-    _VALID_URL = r'https?://www\.livestream\.com/(?P<user>[^/]+)/video\?.*?clipId=(?P<id>.*?)(&|$)'
+    IE_NAME = 'livestream:original'
+    _VALID_URL = r'''(?x)https?://www\.livestream\.com/
+        (?P<user>[^/]+)/(?P<type>video|folder)
+        (?:\?.*?Id=|/)(?P<id>.*?)(&|$)
+        '''
     _TEST = {
-        u'url': u'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
-        u'info_dict': {
-            u'id': u'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
-            u'ext': u'flv',
-            u'title': u'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
+        'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
+        'info_dict': {
+            'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
+            'ext': 'flv',
+            'title': 'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
         },
-        u'params': {
+        'params': {
             # rtmp
-            u'skip_download': True,
+            'skip_download': True,
         },
     }
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        user = mobj.group('user')
+    def _extract_video(self, user, video_id):
         api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id)
 
         info = self._download_xml(api_url, video_id)
@@ -84,7 +93,7 @@ class LivestreamOriginalIE(InfoExtractor):
         ns = {'media': 'http://search.yahoo.com/mrss'}
         thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url']
         # Remove the extension and number from the path (like 1.jpg)
-        path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, u'path')
+        path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, 'path')
 
         return {
             'id': video_id,
@@ -94,3 +103,44 @@ class LivestreamOriginalIE(InfoExtractor):
             'ext': 'flv',
             'thumbnail': thumbnail_url,
         }
+
+    def _extract_folder(self, url, folder_id):
+        webpage = self._download_webpage(url, folder_id)
+        urls = orderedSet(re.findall(r'<a href="(https?://livestre\.am/.*?)"', webpage))
+
+        return {
+            '_type': 'playlist',
+            'id': folder_id,
+            'entries': [{
+                '_type': 'url',
+                'url': video_url,
+            } for video_url in urls],
+        }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        id = mobj.group('id')
+        user = mobj.group('user')
+        url_type = mobj.group('type')
+        if url_type == 'folder':
+            return self._extract_folder(url, id)
+        else:
+            return self._extract_video(user, id)
+
+
+# The server doesn't support HEAD request, the generic extractor can't detect
+# the redirection
+class LivestreamShortenerIE(InfoExtractor):
+    IE_NAME = 'livestream:shortener'
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'https?://livestre\.am/(?P<id>.+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        id = mobj.group('id')
+        webpage = self._download_webpage(url, id)
+
+        return {
+            '_type': 'url',
+            'url': self._og_search_url(webpage),
+        }

youtube_dl/extractor/mailru.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 import re
-import datetime
 
 from .common import InfoExtractor
 
@@ -10,28 +9,48 @@ from .common import InfoExtractor
 class MailRuIE(InfoExtractor):
     IE_NAME = 'mailru'
     IE_DESC = 'Видео@Mail.Ru'
-    _VALID_URL = r'http://(?:www\.)?my\.mail\.ru/video/.*#video=/?(?P<id>[^/]+/[^/]+/[^/]+/\d+)'
+    _VALID_URL = r'http://(?:www\.)?my\.mail\.ru/(?:video/.*#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html)'
 
-    _TEST = {
-        'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76',
-        'md5': 'dea205f03120046894db4ebb6159879a',
-        'info_dict': {
-            'id': '46301138',
-            'ext': 'mp4',
-            'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
-            'upload_date': '20140224',
-            'uploader': 'sonypicturesrus',
-            'uploader_id': 'sonypicturesrus@mail.ru',
-            'duration': 184,
-        }
-    }
+    _TESTS = [
+        {
+            'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76',
+            'md5': 'dea205f03120046894db4ebb6159879a',
+            'info_dict': {
+                'id': '46301138',
+                'ext': 'mp4',
+                'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
+                'timestamp': 1393232740,
+                'upload_date': '20140224',
+                'uploader': 'sonypicturesrus',
+                'uploader_id': 'sonypicturesrus@mail.ru',
+                'duration': 184,
+            },
+        },
+        {
+            'url': 'http://my.mail.ru/corp/hitech/video/news_hi-tech_mail_ru/1263.html',
+            'md5': '00a91a58c3402204dcced523777b475f',
+            'info_dict': {
+                'id': '46843144',
+                'ext': 'mp4',
+                'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion',
+                'timestamp': 1397217632,
+                'upload_date': '20140411',
+                'uploader': 'hitech',
+                'uploader_id': 'hitech@corp.mail.ru',
+                'duration': 245,
+            },
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = mobj.group('idv1')
+
+        if not video_id:
+            video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix')
 
         video_data = self._download_json(
-            'http://videoapi.my.mail.ru/videos/%s.json?new=1' % video_id, video_id, 'Downloading video JSON')
+            'http://api.video.mail.ru/videos/%s.json?new=1' % video_id, video_id, 'Downloading video JSON')
 
         author = video_data['author']
         uploader = author['name']
@@ -40,10 +59,11 @@ class MailRuIE(InfoExtractor):
         movie = video_data['movie']
         content_id = str(movie['contentId'])
         title = movie['title']
+        if title.endswith('.mp4'):
+            title = title[:-4]
         thumbnail = movie['poster']
         duration = movie['duration']
 
-        upload_date = datetime.datetime.fromtimestamp(video_data['timestamp']).strftime('%Y%m%d')
         view_count = video_data['views_count']
 
         formats = [
@@ -57,7 +77,7 @@ class MailRuIE(InfoExtractor):
             'id': content_id,
             'title': title,
             'thumbnail': thumbnail,
-            'upload_date': upload_date,
+            'timestamp': video_data['timestamp'],
             'uploader': uploader,
             'uploader_id': uploader_id,
             'duration': duration,

youtube_dl/extractor/mdr.py

@@ -1,15 +1,18 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
 
 
 class MDRIE(InfoExtractor):
-    _VALID_URL = r'^(?P<domain>(?:https?://)?(?:www\.)?mdr\.de)/mediathek/(?:.*)/(?P<type>video|audio)(?P<video_id>[^/_]+)_.*'
+    _VALID_URL = r'^(?P<domain>https?://(?:www\.)?mdr\.de)/(?:.*)/(?P<type>video|audio)(?P<video_id>[^/_]+)(?:_|\.html)'
     
     # No tests, MDR regularily deletes its videos
+    _TEST = {
+        'url': 'http://www.mdr.de/fakt/video189002.html',
+        'only_matching': True,
+    }
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
@@ -19,9 +22,9 @@ class MDRIE(InfoExtractor):
         # determine title and media streams from webpage
         html = self._download_webpage(url, video_id)
 
-        title = self._html_search_regex(r'<h2>(.*?)</h2>', html, u'title')
+        title = self._html_search_regex(r'<h[12]>(.*?)</h[12]>', html, 'title')
         xmlurl = self._search_regex(
-            r'(/mediathek/(?:.+)/(?:video|audio)[0-9]+-avCustom.xml)', html, u'XML URL')
+            r'dataURL:\'(/(?:.+)/(?:video|audio)[0-9]+-avCustom.xml)', html, 'XML URL')
 
         doc = self._download_xml(domain + xmlurl, video_id)
         formats = []
@@ -41,7 +44,7 @@ class MDRIE(InfoExtractor):
             if vbr_el is None:
                 format.update({
                     'vcodec': 'none',
-                    'format_id': u'%s-%d' % (media_type, abr),
+                    'format_id': '%s-%d' % (media_type, abr),
                 })
             else:
                 vbr = int(vbr_el.text) // 1000
@@ -49,12 +52,9 @@ class MDRIE(InfoExtractor):
                     'vbr': vbr,
                     'width': int(a.find('frameWidth').text),
                     'height': int(a.find('frameHeight').text),
-                    'format_id': u'%s-%d' % (media_type, vbr),
+                    'format_id': '%s-%d' % (media_type, vbr),
                 })
             formats.append(format)
-        if not formats:
-            raise ExtractorError(u'Could not find any valid formats')
-
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/mixcloud.py

@@ -4,9 +4,10 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    unified_strdate,
     compat_urllib_parse,
     ExtractorError,
+    int_or_none,
+    parse_iso8601,
 )
 
 
@@ -24,6 +25,10 @@ class MixcloudIE(InfoExtractor):
             'uploader': 'Daniel Holbach',
             'uploader_id': 'dholbach',
             'upload_date': '20111115',
+            'timestamp': 1321359578,
+            'thumbnail': 're:https?://.*\.jpg',
+            'view_count': int,
+            'like_count': int,
         },
     }
 
@@ -51,10 +56,6 @@ class MixcloudIE(InfoExtractor):
 
         webpage = self._download_webpage(url, track_id)
 
-        api_url = 'http://api.mixcloud.com/%s/%s/' % (uploader, cloudcast_name)
-        info = self._download_json(
-            api_url, track_id, 'Downloading cloudcast info')
-
         preview_url = self._search_regex(
             r'\s(?:data-preview-url|m-preview)="(.+?)"', webpage, 'preview url')
         song_url = preview_url.replace('/previews/', '/c/originals/')
@@ -65,16 +66,41 @@ class MixcloudIE(InfoExtractor):
             template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
             final_song_url = self._get_url(template_url)
         if final_song_url is None:
-            raise ExtractorError(u'Unable to extract track url')
+            raise ExtractorError('Unable to extract track url')
+
+        PREFIX = (
+            r'<div class="cloudcast-play-button-container"'
+            r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
+        title = self._html_search_regex(
+            PREFIX + r'm-title="([^"]+)"', webpage, 'title')
+        thumbnail = self._proto_relative_url(self._html_search_regex(
+            PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail',
+            fatal=False))
+        uploader = self._html_search_regex(
+            PREFIX + r'm-owner-name="([^"]+)"',
+            webpage, 'uploader', fatal=False)
+        uploader_id = self._search_regex(
+            r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
+        description = self._og_search_description(webpage)
+        like_count = int_or_none(self._search_regex(
+            r'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"',
+            webpage, 'like count', fatal=False))
+        view_count = int_or_none(self._search_regex(
+            r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
+            webpage, 'play count', fatal=False))
+        timestamp = parse_iso8601(self._search_regex(
+            r'<time itemprop="dateCreated" datetime="([^"]+)">',
+            webpage, 'upload date'))
 
         return {
             'id': track_id,
-            'title': info['name'],
+            'title': title,
             'url': final_song_url,
-            'description': info.get('description'),
-            'thumbnail': info['pictures'].get('extra_large'),
-            'uploader': info['user']['name'],
-            'uploader_id': info['user']['username'],
-            'upload_date': unified_strdate(info['created_time']),
-            'view_count': info['play_count'],
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'timestamp': timestamp,
+            'view_count': view_count,
+            'like_count': like_count,
         }

youtube_dl/extractor/mlb.py

@@ -0,0 +1,116 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    parse_iso8601,
+    find_xpath_attr,
+)
+
+
+class MLBIE(InfoExtractor):
+    _VALID_URL = r'https?://m\.mlb\.com/(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v(?P<id>n?\d+)'
+    _TESTS = [
+        {
+            'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea',
+            'md5': 'ff56a598c2cf411a9a38a69709e97079',
+            'info_dict': {
+                'id': '34698933',
+                'ext': 'mp4',
+                'title': "Ackley's spectacular catch",
+                'description': 'md5:7f5a981eb4f3cbc8daf2aeffa2215bf0',
+                'duration': 66,
+                'timestamp': 1405980600,
+                'upload_date': '20140721',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
+        {
+            'url': 'http://m.mlb.com/video/topic/81536970/v34496663/mianym-stanton-practices-for-the-home-run-derby',
+            'md5': 'd9c022c10d21f849f49c05ae12a8a7e9',
+            'info_dict': {
+                'id': '34496663',
+                'ext': 'mp4',
+                'title': 'Stanton prepares for Derby',
+                'description': 'md5:d00ce1e5fd9c9069e9c13ab4faedfa57',
+                'duration': 46,
+                'timestamp': 1405105800,
+                'upload_date': '20140711',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
+        {
+            'url': 'http://m.mlb.com/video/topic/vtp_hrd_sponsor/v34578115/hrd-cespedes-wins-2014-gillette-home-run-derby',
+            'md5': '0e6e73d509321e142409b695eadd541f',
+            'info_dict': {
+                'id': '34578115',
+                'ext': 'mp4',
+                'title': 'Cespedes repeats as Derby champ',
+                'description': 'md5:08df253ce265d4cf6fb09f581fafad07',
+                'duration': 488,
+                'timestamp': 1405399936,
+                'upload_date': '20140715',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
+        {
+            'url': 'http://m.mlb.com/video/v34577915/bautista-on-derby-captaining-duties-his-performance',
+            'md5': 'b8fd237347b844365d74ea61d4245967',
+            'info_dict': {
+                'id': '34577915',
+                'ext': 'mp4',
+                'title': 'Bautista on Home Run Derby',
+                'description': 'md5:b80b34031143d0986dddc64a8839f0fb',
+                'duration': 52,
+                'timestamp': 1405390722,
+                'upload_date': '20140715',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        detail = self._download_xml(
+            'http://m.mlb.com/gen/multimedia/detail/%s/%s/%s/%s.xml'
+            % (video_id[-3], video_id[-2], video_id[-1], video_id), video_id)
+
+        title = detail.find('./headline').text
+        description = detail.find('./big-blurb').text
+        duration = parse_duration(detail.find('./duration').text)
+        timestamp = parse_iso8601(detail.attrib['date'][:-5])
+
+        thumbnail = find_xpath_attr(
+            detail, './thumbnailScenarios/thumbnailScenario', 'type', '45').text
+
+        formats = []
+        for media_url in detail.findall('./url'):
+            playback_scenario = media_url.attrib['playback_scenario']
+            fmt = {
+                'url': media_url.text,
+                'format_id': playback_scenario,
+            }
+            m = re.search(r'(?P<vbr>\d+)K_(?P<width>\d+)X(?P<height>\d+)', playback_scenario)
+            if m:
+                fmt.update({
+                    'vbr': int(m.group('vbr')) * 1000,
+                    'width': int(m.group('width')),
+                    'height': int(m.group('height')),
+                })
+            formats.append(fmt)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/motherless.py

@@ -0,0 +1,87 @@
+from __future__ import unicode_literals
+
+import datetime
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_strdate,
+)
+
+
+class MotherlessIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?motherless\.com/(?P<id>[A-Z0-9]+)'
+    _TESTS = [
+        {
+            'url': 'http://motherless.com/AC3FFE1',
+            'md5': '5527fef81d2e529215dad3c2d744a7d9',
+            'info_dict': {
+                'id': 'AC3FFE1',
+                'ext': 'flv',
+                'title': 'Fucked in the ass while playing PS3',
+                'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
+                'upload_date': '20100913',
+                'uploader_id': 'famouslyfuckedup',
+                'thumbnail': 're:http://.*\.jpg',
+                'age_limit': 18,
+            }
+        },
+        {
+            'url': 'http://motherless.com/532291B',
+            'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
+            'info_dict': {
+                'id': '532291B',
+                'ext': 'mp4',
+                'title': 'Amazing girl playing the omegle game, PERFECT!',
+                'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', 'game', 'hairy'],
+                'upload_date': '20140622',
+                'uploader_id': 'Sulivana7x',
+                'thumbnail': 're:http://.*\.jpg',
+                'age_limit': 18,
+            }
+        }
+    ]
+
+    def _real_extract(self,url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
+        
+        video_url = self._html_search_regex(r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video_url')
+        age_limit = self._rta_search(webpage)
+
+        view_count = self._html_search_regex(r'<strong>Views</strong>\s+([^<]+)<', webpage, 'view_count')
+ 
+        upload_date = self._html_search_regex(r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload_date')
+        if 'Ago' in upload_date:
+            days = int(re.search(r'([0-9]+)', upload_date).group(1))
+            upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d')
+        else:
+            upload_date = unified_strdate(upload_date)
+
+        like_count = self._html_search_regex(r'<strong>Favorited</strong>\s+([^<]+)<', webpage, 'like_count')
+
+        comment_count = webpage.count('class="media-comment-contents"')
+        uploader_id = self._html_search_regex(r'"thumb-member-username">\s+<a href="/m/([^"]+)"', webpage, 'uploader_id')
+
+        categories = self._html_search_meta('keywords', webpage)
+        if categories:
+            categories = [cat.strip() for cat in categories.split(',')]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'upload_date': upload_date,
+            'uploader_id': uploader_id,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'categories': categories,
+            'view_count': int_or_none(view_count.replace(',', '')),
+            'like_count': int_or_none(like_count.replace(',', '')),
+            'comment_count': comment_count,
+            'age_limit': age_limit,
+            'url': video_url,
+        }

youtube_dl/extractor/moviezine.py

@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class MoviezineIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.moviezine\.se/video/(?P<id>[^?#]+)'
+
+    _TEST = {
+        'url': 'http://www.moviezine.se/video/205866',
+        'info_dict': {
+            'id': '205866',
+            'ext': 'mp4',
+            'title': 'Oculus - Trailer 1',
+            'description': 'md5:40cc6790fc81d931850ca9249b40e8a4',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        jsplayer = self._download_webpage('http://www.moviezine.se/api/player.js?video=%s' % video_id, video_id, 'Downloading js api player')
+
+        formats =[{
+            'format_id': 'sd',
+            'url': self._html_search_regex(r'file: "(.+?)",', jsplayer, 'file'),
+            'quality': 0,
+            'ext': 'mp4',
+        }]
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._search_regex(r'title: "(.+?)",', jsplayer, 'title'),
+            'thumbnail': self._search_regex(r'image: "(.+?)",', jsplayer, 'image'),
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+        }

youtube_dl/extractor/mpora.py

@@ -28,7 +28,7 @@ class MporaIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
         data_json = self._search_regex(
-            r"new FM\.Player\('[^']+',\s*(\{.*?)\);\n", webpage, 'json')
+            r"new FM\.Player\('[^']+',\s*(\{.*?)\).player;", webpage, 'json')
 
         data = json.loads(data_json)
 

youtube_dl/extractor/mtv.py

@@ -22,6 +22,7 @@ def _media_xml_tag(tag):
 
 class MTVServicesInfoExtractor(InfoExtractor):
     _MOBILE_TEMPLATE = None
+
     @staticmethod
     def _id_from_uri(uri):
         return uri.split(':')[-1]
@@ -35,6 +36,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
         base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
         return base + m.group('finalid')
 
+    def _get_feed_url(self, uri):
+        return self._FEED_URL
+
     def _get_thumbnail_url(self, uri, itemdoc):
         search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
         thumb_node = itemdoc.find(search_path)
@@ -80,6 +84,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
                                 })
             except (KeyError, TypeError):
                 raise ExtractorError('Invalid rendition field.')
+        self._sort_formats(formats)
         return formats
 
     def _get_video_info(self, itemdoc):
@@ -135,10 +140,10 @@ class MTVServicesInfoExtractor(InfoExtractor):
 
     def _get_videos_info(self, uri):
         video_id = self._id_from_uri(uri)
+        feed_url = self._get_feed_url(uri)
         data = compat_urllib_parse.urlencode({'uri': uri})
-
         idoc = self._download_xml(
-            self._FEED_URL + '?' + data, video_id,
+            feed_url + '?' + data, video_id,
             'Downloading info', transform_source=fix_xml_ampersands)
         return [self._get_video_info(item) for item in idoc.findall('.//item')]
 
@@ -153,12 +158,46 @@ class MTVServicesInfoExtractor(InfoExtractor):
             if mgid.endswith('.swf'):
                 mgid = mgid[:-4]
         except RegexNotFoundError:
+            mgid = None
+
+        if mgid is None or ':' not in mgid:
             mgid = self._search_regex(
                 [r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'],
                 webpage, u'mgid')
         return self._get_videos_info(mgid)
 
 
+class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
+    IE_NAME = 'mtvservices:embedded'
+    _VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)'
+
+    _TEST = {
+        # From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/
+        'url': 'http://media.mtvnservices.com/embed/mgid:uma:video:mtv.com:1043906/cp~vid%3D1043906%26uri%3Dmgid%3Auma%3Avideo%3Amtv.com%3A1043906',
+        'md5': 'cb349b21a7897164cede95bd7bf3fbb9',
+        'info_dict': {
+            'id': '1043906',
+            'ext': 'mp4',
+            'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds',
+            'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.',
+        },
+    }
+
+    def _get_feed_url(self, uri):
+        video_id = self._id_from_uri(uri)
+        site_id = uri.replace(video_id, '')
+        config_url = 'http://media.mtvnservices.com/pmt/e1/players/{0}/config.xml'.format(site_id)
+        config_doc = self._download_xml(config_url, video_id)
+        feed_node = config_doc.find('.//feed')
+        feed_url = feed_node.text.strip().split('?')[0]
+        return feed_url
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        mgid = mobj.group('mgid')
+        return self._get_videos_info(mgid)
+
+
 class MTVIE(MTVServicesInfoExtractor):
     _VALID_URL = r'''(?x)^https?://
         (?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$|

youtube_dl/extractor/naver.py

@@ -1,4 +1,6 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -12,12 +14,13 @@ class NaverIE(InfoExtractor):
     _VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://tvcast.naver.com/v/81652',
-        u'file': u'81652.mp4',
-        u'info_dict': {
-            u'title': u'[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번',
-            u'description': u'합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.',
-            u'upload_date': u'20130903',
+        'url': 'http://tvcast.naver.com/v/81652',
+        'info_dict': {
+            'id': '81652',
+            'ext': 'mp4',
+            'title': '[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번',
+            'description': '합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.',
+            'upload_date': '20130903',
         },
     }
 
@@ -28,7 +31,7 @@ class NaverIE(InfoExtractor):
         m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
             webpage)
         if m_id is None:
-            raise ExtractorError(u'couldn\'t extract vid and key')
+            raise ExtractorError('couldn\'t extract vid and key')
         vid = m_id.group(1)
         key = m_id.group(2)
         query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key,})
@@ -39,22 +42,27 @@ class NaverIE(InfoExtractor):
         })
         info = self._download_xml(
             'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query,
-            video_id, u'Downloading video info')
+            video_id, 'Downloading video info')
         urls = self._download_xml(
             'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls,
-            video_id, u'Downloading video formats info')
+            video_id, 'Downloading video formats info')
 
         formats = []
         for format_el in urls.findall('EncodingOptions/EncodingOption'):
             domain = format_el.find('Domain').text
-            if domain.startswith('rtmp'):
-                continue
-            formats.append({
+            f = {
                 'url': domain + format_el.find('uri').text,
                 'ext': 'mp4',
                 'width': int(format_el.find('width').text),
                 'height': int(format_el.find('height').text),
-            })
+            }
+            if domain.startswith('rtmp'):
+                f.update({
+                    'ext': 'flv',
+                    'rtmp_protocol': '1', # rtmpt
+                })
+            formats.append(f)
+        self._sort_formats(formats)
 
         return {
             'id': video_id,

youtube_dl/extractor/nbc.py

@@ -1,6 +1,7 @@
 from __future__ import unicode_literals
 
 import re
+import json
 
 from .common import InfoExtractor
 from ..utils import find_xpath_attr, compat_str
@@ -31,30 +32,82 @@ class NBCIE(InfoExtractor):
 
 
 class NBCNewsIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
+    _VALID_URL = r'''(?x)https?://www\.nbcnews\.com/
+        ((video/.+?/(?P<id>\d+))|
+        (feature/[^/]+/(?P<title>.+)))
+        '''
 
-    _TEST = {
-        'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
-        'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
-        'info_dict': {
-            'id': '52753292',
-            'ext': 'flv',
-            'title': 'Crew emerges after four-month Mars food study',
-            'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
+    _TESTS = [
+        {
+            'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
+            'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
+            'info_dict': {
+                'id': '52753292',
+                'ext': 'flv',
+                'title': 'Crew emerges after four-month Mars food study',
+                'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
+            },
         },
-    }
+        {
+            'url': 'http://www.nbcnews.com/feature/edward-snowden-interview/how-twitter-reacted-snowden-interview-n117236',
+            'md5': 'b2421750c9f260783721d898f4c42063',
+            'info_dict': {
+                'id': 'I1wpAI_zmhsQ',
+                'ext': 'flv',
+                'title': 'How Twitter Reacted To The Snowden Interview',
+                'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
+            },
+            'add_ie': ['ThePlatform'],
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
-        info = all_info.find('video')
+        if video_id is not None:
+            all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
+            info = all_info.find('video')
 
-        return {
-            'id': video_id,
-            'title': info.find('headline').text,
-            'ext': 'flv',
-            'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
-            'description': compat_str(info.find('caption').text),
-            'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
-        }
+            return {
+                'id': video_id,
+                'title': info.find('headline').text,
+                'ext': 'flv',
+                'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
+                'description': compat_str(info.find('caption').text),
+                'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
+            }
+        else:
+            # "feature" pages use theplatform.com
+            title = mobj.group('title')
+            webpage = self._download_webpage(url, title)
+            bootstrap_json = self._search_regex(
+                r'var bootstrapJson = ({.+})\s*$', webpage, 'bootstrap json',
+                flags=re.MULTILINE)
+            bootstrap = json.loads(bootstrap_json)
+            info = bootstrap['results'][0]['video']
+            mpxid = info['mpxId']
+
+            base_urls = [
+                info['fallbackPlaylistUrl'],
+                info['associatedPlaylistUrl'],
+            ]
+
+            for base_url in base_urls:
+                playlist_url = base_url + '?form=MPXNBCNewsAPI'
+                all_videos = self._download_json(playlist_url, title)['videos']
+
+                try:
+                    info = next(v for v in all_videos if v['mpxId'] == mpxid)
+                    break
+                except StopIteration:
+                    continue
+
+            if info is None:
+                raise ExtractorError('Could not find video in playlists')
+
+            return {
+                '_type': 'url',
+                # We get the best quality video
+                'url': info['videoAssets'][-1]['publicUrl'],
+                'ie_key': 'ThePlatform',
+            }

youtube_dl/extractor/ndr.py

@@ -4,7 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    qualities,
+)
 
 
 class NDRIE(InfoExtractor):
@@ -14,15 +18,15 @@ class NDRIE(InfoExtractor):
 
     _TESTS = [
         {
-            'url': 'http://www.ndr.de/fernsehen/sendungen/markt/markt7959.html',
-            'md5': 'e7a6079ca39d3568f4996cb858dd6708',
+            'url': 'http://www.ndr.de/fernsehen/media/dienordreportage325.html',
+            'md5': '4a4eeafd17c3058b65f0c8f091355855',
             'note': 'Video file',
             'info_dict': {
-                'id': '7959',
+                'id': '325',
                 'ext': 'mp4',
-                'title': 'Markt - die ganze Sendung',
-                'description': 'md5:af9179cf07f67c5c12dc6d9997e05725',
-                'duration': 2655,
+                'title': 'Blaue Bohnen aus Blocken',
+                'description': 'md5:190d71ba2ccddc805ed01547718963bc',
+                'duration': 1715,
             },
         },
         {
@@ -45,17 +49,16 @@ class NDRIE(InfoExtractor):
 
         page = self._download_webpage(url, video_id, 'Downloading page')
 
-        title = self._og_search_title(page)
+        title = self._og_search_title(page).strip()
         description = self._og_search_description(page)
+        if description:
+            description = description.strip()
 
-        mobj = re.search(
-            r'<div class="duration"><span class="min">(?P<minutes>\d+)</span>:<span class="sec">(?P<seconds>\d+)</span></div>',
-            page)
-        duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+        duration = int_or_none(self._html_search_regex(r'duration: (\d+),\n', page, 'duration', fatal=False))
 
         formats = []
 
-        mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
+        mp3_url = re.search(r'''\{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
         if mp3_url:
             formats.append({
                 'url': mp3_url.group('audio'),
@@ -64,13 +67,15 @@ class NDRIE(InfoExtractor):
 
         thumbnail = None
 
-        video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
+        video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
         if video_url:
-            thumbnail = self._html_search_regex(r'(?m)title: "NDR PLAYER",\s*poster: "([^"]+)",',
-                page, 'thumbnail', fatal=False)
-            if thumbnail:
-                thumbnail = 'http://www.ndr.de' + thumbnail
-            for format_id in ['lo', 'hi', 'hq']:
+            thumbnails = re.findall(r'''\d+: \{src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
+            if thumbnails:
+                quality_key = qualities(['xs', 's', 'm', 'l', 'xl'])
+                largest = max(thumbnails, key=lambda thumb: quality_key(thumb[1]))
+                thumbnail = 'http://www.ndr.de' + largest[0]
+
+            for format_id in 'lo', 'hi', 'hq':
                 formats.append({
                     'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
                     'format_id': format_id,

youtube_dl/extractor/ndtv.py

@@ -1,22 +1,28 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import month_by_name
+from ..utils import (
+    month_by_name,
+    int_or_none,
+)
 
 
 class NDTVIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?ndtv\.com/video/player/[^/]*/[^/]*/(?P<id>[a-z0-9]+)'
 
     _TEST = {
-        u"url": u"http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710",
-        u"file": u"300710.mp4",
-        u"md5": u"39f992dbe5fb531c395d8bbedb1e5e88",
-        u"info_dict": {
-            u"title": u"NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal",
-            u"description": u"In an exclusive interview to NDTV, Aam Aadmi Party's Arvind Kejriwal says it makes no difference to him that Rahul Gandhi said the Congress needs to learn from his party.",
-            u"upload_date": u"20131208",
-            u"duration": 1327,
-            u"thumbnail": u"http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg",
+        'url': 'http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710',
+        'md5': '39f992dbe5fb531c395d8bbedb1e5e88',
+        'info_dict': {
+            'id': '300710',
+            'ext': 'mp4',
+            'title': "NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal",
+            'description': 'md5:ab2d4b4a6056c5cb4caa6d729deabf02',
+            'upload_date': '20131208',
+            'duration': 1327,
+            'thumbnail': 'http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg',
         },
     }
 
@@ -27,13 +33,12 @@ class NDTVIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         filename = self._search_regex(
-            r"__filename='([^']+)'", webpage, u'video filename')
-        video_url = (u'http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' %
+            r"__filename='([^']+)'", webpage, 'video filename')
+        video_url = ('http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' %
                      filename)
 
-        duration_str = filename = self._search_regex(
-            r"__duration='([^']+)'", webpage, u'duration', fatal=False)
-        duration = None if duration_str is None else int(duration_str)
+        duration = int_or_none(self._search_regex(
+            r"__duration='([^']+)'", webpage, 'duration', fatal=False))
 
         date_m = re.search(r'''(?x)
             <p\s+class="vod_dateline">\s*
@@ -41,7 +46,7 @@ class NDTVIE(InfoExtractor):
                 (?P<monthname>[A-Za-z]+)\s+(?P<day>[0-9]+),\s*(?P<year>[0-9]+)
             ''', webpage)
         upload_date = None
-        assert date_m
+
         if date_m is not None:
             month = month_by_name(date_m.group('monthname'))
             if month is not None:
@@ -49,14 +54,19 @@ class NDTVIE(InfoExtractor):
                     date_m.group('year'), month, int(date_m.group('day')))
 
         description = self._og_search_description(webpage)
-        READ_MORE = u' (Read more)'
+        READ_MORE = ' (Read more)'
         if description.endswith(READ_MORE):
             description = description[:-len(READ_MORE)]
 
+        title = self._og_search_title(webpage)
+        TITLE_SUFFIX = ' - NDTV'
+        if title.endswith(TITLE_SUFFIX):
+            title = title[:-len(TITLE_SUFFIX)]
+
         return {
             'id': video_id,
             'url': video_url,
-            'title': self._og_search_title(webpage),
+            'title': title,
             'description': description,
             'thumbnail': self._og_search_thumbnail(webpage),
             'duration': duration,