release 2014.07.23.2

Fixes #3326
Apparently, on some platforms, even outputting this fails already.

README.md

@@ -12,7 +12,7 @@ To install it right away for all UNIX users (Linux, OS X, etc.), type:
 
 If you do not have curl, you can alternatively use a recent wget:
 
-    sudo wget https://yt-dl.org/downloads/2014.05.13/youtube-dl -O /usr/local/bin/youtube-dl
+    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).
@@ -70,8 +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
@@ -254,7 +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

test/helper.py

@@ -137,8 +137,8 @@ def expect_info_dict(self, expected_dict, got_dict):
 
 
 def assertRegexpMatches(self, text, regexp, msg=None):
-    if hasattr(self, 'assertRegexpMatches'):
-        return self.assertRegexpMatches(text, regexp, msg)
+    if hasattr(self, 'assertRegexp'):
+        return self.assertRegexp(text, regexp, msg)
     else:
         m = re.match(regexp, text)
         if not m:
@@ -148,3 +148,10 @@ def assertRegexpMatches(self, text, regexp, msg=None):
             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_all_urls.py

@@ -69,9 +69,6 @@ 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'])

test/test_playlists.py

@@ -11,6 +11,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
     assertRegexpMatches,
+    assertGreaterEqual,
     expect_info_dict,
     FakeYDL,
 )
@@ -28,7 +29,9 @@ from youtube_dl.extractor import (
     SoundcloudSetIE,
     SoundcloudUserIE,
     SoundcloudPlaylistIE,
+    TeacherTubeUserIE,
     LivestreamIE,
+    LivestreamOriginalIE,
     NHLVideocenterIE,
     BambuserChannelIE,
     BandcampAlbumIE,
@@ -39,6 +42,7 @@ from youtube_dl.extractor import (
     KhanAcademyIE,
     EveryonesMixtapeIE,
     RutubeChannelIE,
+    RutubePersonIE,
     GoogleSearchIE,
     GenericIE,
     TEDIE,
@@ -68,8 +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()
@@ -108,15 +112,15 @@ class TestPlaylists(unittest.TestCase):
         ie = VineUserIE(dl)
         result = ie.extract('https://vine.co/Visa')
         self.assertIsPlaylist(result)
-        self.assertTrue(len(result['entries']) >= 50)
+        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()
@@ -124,7 +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()
@@ -132,7 +136,15 @@ 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()
@@ -142,7 +154,7 @@ class TestPlaylists(unittest.TestCase):
         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, result['description'], r'.*?TILT Brass - Bowery Poetry Club')
         self.assertEqual(len(result['entries']), 6)
 
     def test_livestream_event(self):
@@ -151,7 +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()
@@ -168,7 +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()
@@ -176,7 +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()
@@ -185,7 +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()
@@ -194,7 +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()
@@ -213,7 +233,7 @@ class TestPlaylists(unittest.TestCase):
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], 'dvoe_iz_lartsa')
         self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008)')
-        self.assertTrue(len(result['entries']) >= 24)
+        assertGreaterEqual(self, len(result['entries']), 24)
 
     def test_ivi_compilation_season(self):
         dl = FakeYDL()
@@ -222,7 +242,7 @@ class TestPlaylists(unittest.TestCase):
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], 'dvoe_iz_lartsa/season1')
         self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008) 1 сезон')
-        self.assertTrue(len(result['entries']) >= 12)
+        assertGreaterEqual(self, len(result['entries']), 12)
         
     def test_imdb_list(self):
         dl = FakeYDL()
@@ -241,7 +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()
@@ -255,10 +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
@@ -295,7 +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()
@@ -303,7 +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()
@@ -311,7 +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()
@@ -319,7 +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')
@@ -358,7 +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()

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 +33,36 @@ _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\\!"#$%&\'()*+,-./:;<=>?'
+    ),
+    (
+        u'http://s.ytimg.com/yts/swfbin/player-vflmDyk47/watch_as3.swf',
+        u'swf',
+        u'F375F75BF2AFDAAF2666E43868D46816F83F13E81C46.3725A8218E446A0DECD33F79DC282994D6AA92C92C9',
+        u'9C29AA6D499282CD97F33DCED0A644E8128A5273.64C18E31F38361864D86834E6662FAADFA2FB57F'
+    ),
+    (
+        u'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js',
+        u'js',
+        84,
+        u'123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>'
+    )
 ]
 
 
@@ -44,13 +74,13 @@ 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 +96,9 @@ 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

@@ -717,6 +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']
 
@@ -982,6 +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 = []
@@ -1184,6 +1197,10 @@ class YoutubeDL(object):
             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):
@@ -1217,14 +1234,21 @@ class YoutubeDL(object):
         if not self.params.get('verbose'):
             return
 
-        write_string(
+        encoding_str = (
             '[debug] Encodings: locale %s, fs %s, out %s, pref %s\n' % (
                 locale.getpreferredencoding(),
                 sys.getfilesystemencoding(),
                 sys.stdout.encoding,
-                self.get_encoding()),
-            encoding=None
-        )
+                self.get_encoding()))
+        try:
+            write_string(encoding_str, encoding=None)
+        except:
+            errmsg = 'Failed to write encoding string %r' % encoding_str
+            try:
+                sys.stdout.write(errmsg)
+            except:
+                pass
+            raise IOError(errmsg)
 
         self._write_string('[debug] youtube-dl version ' + __version__ + '\n')
         try:

youtube_dl/__init__.py

@@ -57,17 +57,24 @@ __authors__  = (
     '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
 
@@ -267,7 +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',
@@ -503,7 +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,
@@ -626,7 +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)

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/rtmp.py

@@ -96,6 +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)
@@ -105,7 +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
@@ -133,6 +134,8 @@ class RtmpFD(FileDownloader):
                 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
@@ -51,6 +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
@@ -61,8 +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
@@ -81,6 +86,7 @@ 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
@@ -103,12 +109,15 @@ 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
@@ -142,10 +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
@@ -159,15 +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
@@ -194,6 +211,7 @@ 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,
@@ -215,8 +233,10 @@ 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
@@ -225,6 +245,7 @@ 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,
@@ -232,8 +253,10 @@ 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
@@ -244,6 +267,8 @@ from .smotri import (
     SmotriUserIE,
     SmotriBroadcastIE,
 )
+from .snotr import SnotrIE
+from .sockshare import SockshareIE
 from .sohu import SohuIE
 from .soundcloud import (
     SoundcloudIE,
@@ -251,13 +276,15 @@ from .soundcloud import (
     SoundcloudUserIE,
     SoundcloudPlaylistIE
 )
-from .southparkstudios import (
-    SouthParkStudiosIE,
+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 .steam import SteamIE
@@ -266,9 +293,16 @@ 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
@@ -298,6 +332,7 @@ 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
@@ -315,14 +350,17 @@ from .vimeo import (
     VimeoReviewIE,
     VimeoWatchLaterIE,
 )
+from .vimple import VimpleIE
 from .vine import (
     VineIE,
     VineUserIE,
 )
 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 (
@@ -334,6 +372,7 @@ 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
@@ -364,6 +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/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
@@ -43,29 +52,64 @@ class ARDIE(InfoExtractor):
              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')
 
+        # 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)
 
-        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')
+        media_streams = re.findall(r'''(?x)
+            mediaCollection\.addMediaStream\([0-9]+,\s*[0-9]+,\s*"[^"]*",\s*
+            "([^"]+)"''', webpage)
 
-        formats = []
-        for s in streams:
-            format = {
-                'quality': s['_quality'],
-                'url': s['_stream'],
-            }
+        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')
 
-            format['format_id'] = '%s-%s' % (
-                determine_ext(format['url']), format['quality'])
+            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
 
-            formats.append(format)
+                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')]
@@ -111,7 +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')
@@ -189,9 +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/bilibili.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class BiliBiliIE(InfoExtractor):
-    _VALID_URL = r'http://www\.bilibili\.tv/video/av(?P<id>[0-9]+)/'
+    _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'
 
     _TEST = {
         'url': 'http://www.bilibili.tv/video/av1074402/',
@@ -56,7 +56,7 @@ class BiliBiliIE(InfoExtractor):
             'thumbnailUrl', video_code, 'thumbnail', fatal=False)
 
         player_params = compat_parse_qs(self._html_search_regex(
-            r'<iframe .*?class="player" src="https://secure.bilibili.tv/secure,([^"]+)"',
+            r'<iframe .*?class="player" src="https://secure\.bilibili\.(?:tv|com)/secure,([^"]+)"',
             webpage, 'player params'))
 
         if 'cid' in player_params:

youtube_dl/extractor/blinkx.py

@@ -4,9 +4,7 @@ import json
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    remove_start,
-)
+from ..utils import remove_start
 
 
 class BlinkxIE(InfoExtractor):
@@ -15,9 +13,10 @@ class BlinkxIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB',
-        'file': '8aQUy7GV.mp4',
         'md5': '2e9a07364af40163a908edbf10bb2492',
         'info_dict': {
+            'id': '8aQUy7GV',
+            'ext': 'mp4',
             'title': 'Police Car Rolls Away',
             'uploader': 'stupidvideos.com',
             'upload_date': '20131215',
@@ -27,6 +26,7 @@ class BlinkxIE(InfoExtractor):
             'thumbnails': [{
                 'width': 100,
                 'height': 76,
+                'resolution': '100x76',
                 'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg',
             }],
         },
@@ -37,7 +37,7 @@ 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]
@@ -55,13 +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'],

youtube_dl/extractor/bliptv.py

@@ -15,7 +15,7 @@ from ..utils import (
 
 
 class BlipTVIE(SubtitlesInfoExtractor):
-    _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/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+]+)))'
 
     _TESTS = [
         {

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/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/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

@@ -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:

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.
@@ -295,8 +301,12 @@ class InfoExtractor(object):
     def _download_json(self, url_or_request, video_id,
                        note=u'Downloading JSON metadata',
                        errnote=u'Unable to download JSON metadata',
-                       transform_source=None):
-        json_string = self._download_webpage(url_or_request, video_id, note, errnote)
+                       transform_source=None,
+                       fatal=True):
+        json_string = self._download_webpage(
+            url_or_request, video_id, note, errnote, fatal=fatal)
+        if (not fatal) and json_string is False:
+            return None
         if transform_source:
             json_string = transform_source(json_string)
         try:
@@ -455,14 +465,17 @@ 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')
@@ -547,6 +560,7 @@ 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)
@@ -568,6 +582,13 @@ class InfoExtractor(object):
         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):
     """
@@ -611,4 +632,3 @@ class SearchInfoExtractor(InfoExtractor):
     @property
     def SEARCH_KEY(self):
         return self._SEARCH_KEY
-

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

@@ -150,7 +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,

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/fc2.py

@@ -50,10 +50,13 @@ class FC2IE(InfoExtractor):
             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': info['title'][0],
+            '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/francetv.py

@@ -48,7 +48,7 @@ class PluzzIE(FranceTVBaseInfoExtractor):
 
 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
     IE_NAME = 'francetvinfo.fr'
-    _VALID_URL = r'https?://www\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
+    _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
 
     _TESTS = [{
         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
@@ -211,7 +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

@@ -26,7 +26,7 @@ class FunnyOrDieIE(InfoExtractor):
             'id': 'e402820827',
             'ext': 'mp4',
             'title': 'Please Use This Song (Jon Lajoie)',
-            'description': 'md5:2ed27d364f5a805a6dba199faaf6681d',
+            'description': 'Please use this to sell something.  www.jonlajoie.com',
             'thumbnail': 're:^http:.*\.jpg$',
         },
     }]

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/generic.py

@@ -260,7 +260,35 @@ class GenericIE(InfoExtractor):
                 '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):
@@ -355,7 +383,7 @@ class GenericIE(InfoExtractor):
         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:
@@ -369,8 +397,13 @@ class GenericIE(InfoExtractor):
                                 expected=True)
                         else:
                             self._downloader.report_warning(
-                                'Falling back to youtube search for  %s . Set --default-search to "auto" to suppress this warning.' % url)
+                                '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)
@@ -478,8 +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:
@@ -587,6 +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)
@@ -646,6 +689,22 @@ class GenericIE(InfoExtractor):
             url = unescapeHTML(mobj.group('url'))
             return self.url_result(url)
 
+        # 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:

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/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/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

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/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/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

@@ -4,7 +4,11 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import find_xpath_attr, compat_str
+from ..utils import (
+    compat_str,
+    ExtractorError,
+    find_xpath_attr,
+)
 
 
 class NBCIE(InfoExtractor):
@@ -85,11 +89,25 @@ class NBCNewsIE(InfoExtractor):
                 flags=re.MULTILINE)
             bootstrap = json.loads(bootstrap_json)
             info = bootstrap['results'][0]['video']
-            playlist_url = info['fallbackPlaylistUrl'] + '?form=MPXNBCNewsAPI'
             mpxid = info['mpxId']
-            all_videos = self._download_json(playlist_url, title)['videos']
-            # The response contains additional videos
-            info = next(v for v in all_videos if v['mpxId'] == 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',

youtube_dl/extractor/ndr.py

@@ -18,15 +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,
             },
         },
         {

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,

youtube_dl/extractor/newstube.py

@@ -4,18 +4,19 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import ExtractorError
 
 
 class NewstubeIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?newstube\.ru/media/(?P<id>.+)'
     _TEST = {
-        'url': 'http://newstube.ru/media/na-korable-progress-prodolzhaetsya-testirovanie-sistemy-kurs',
+        'url': 'http://www.newstube.ru/media/telekanal-cnn-peremestil-gorod-slavyansk-v-krym',
         'info_dict': {
-            'id': 'd156a237-a6e9-4111-a682-039995f721f1',
+            'id': '728e0ef2-e187-4012-bac0-5a081fdcb1f6',
             'ext': 'flv',
-            'title': 'На корабле «Прогресс» продолжается тестирование системы «Курс»',
-            'description': 'md5:d0cbe7b4a6f600552617e48548d5dc77',
-            'duration': 20.04,
+            'title': 'Телеканал CNN переместил город Славянск в Крым',
+            'description': 'md5:419a8c9f03442bc0b0a794d689360335',
+            'duration': 31.05,
         },
         'params': {
             # rtmp download
@@ -40,6 +41,10 @@ class NewstubeIE(InfoExtractor):
         def ns(s):
             return s.replace('/', '/%(ns)s') % {'ns': '{http://app1.newstube.ru/N2SiteWS/player.asmx}'}
 
+        error_message = player.find(ns('./ErrorMessage'))
+        if error_message is not None:
+            raise ExtractorError('%s returned error: %s' % (self.IE_NAME, error_message.text), expected=True)
+
         session_id = player.find(ns('./SessionId')).text
         media_info = player.find(ns('./Medias/MediaInfo'))
         title = media_info.find(ns('./Name')).text

youtube_dl/extractor/niconico.py

@@ -8,10 +8,9 @@ from ..utils import (
     compat_urllib_parse,
     compat_urllib_request,
     compat_urlparse,
-    compat_str,
-
-    ExtractorError,
     unified_strdate,
+    parse_duration,
+    int_or_none,
 )
 
 
@@ -30,6 +29,7 @@ class NiconicoIE(InfoExtractor):
             'uploader_id': '2698420',
             'upload_date': '20131123',
             'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
+            'duration': 33,
         },
         'params': {
             'username': 'ydl.niconico@gmail.com',
@@ -37,17 +37,20 @@ class NiconicoIE(InfoExtractor):
         },
     }
 
-    _VALID_URL = r'^https?://(?:www\.|secure\.)?nicovideo\.jp/watch/([a-z][a-z][0-9]+)(?:.*)$'
+    _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/((?:[a-z]{2})?[0-9]+)'
     _NETRC_MACHINE = 'niconico'
+    # Determine whether the downloader uses authentication to download video
+    _AUTHENTICATE = False
 
     def _real_initialize(self):
-        self._login()
+        if self._downloader.params.get('username', None) is not None:
+            self._AUTHENTICATE = True
+
+        if self._AUTHENTICATE:
+            self._login()
 
     def _login(self):
         (username, password) = self._get_login_info()
-        if username is None:
-            # Login is required
-            raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
 
         # Log in
         login_form_strs = {
@@ -79,44 +82,66 @@ class NiconicoIE(InfoExtractor):
             'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
             note='Downloading video info page')
 
-        # Get flv info
-        flv_info_webpage = self._download_webpage(
-            'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
-            video_id, 'Downloading flv info')
+        if self._AUTHENTICATE:
+            # Get flv info
+            flv_info_webpage = self._download_webpage(
+                'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
+                video_id, 'Downloading flv info')
+        else:
+            # Get external player info
+            ext_player_info = self._download_webpage(
+                'http://ext.nicovideo.jp/thumb_watch/' + video_id, video_id)
+            thumb_play_key = self._search_regex(
+                r'\'thumbPlayKey\'\s*:\s*\'(.*?)\'', ext_player_info, 'thumbPlayKey')
+
+            # Get flv info
+            flv_info_data = compat_urllib_parse.urlencode({
+                'k': thumb_play_key,
+                'v': video_id
+            })
+            flv_info_request = compat_urllib_request.Request(
+                'http://ext.nicovideo.jp/thumb_watch', flv_info_data,
+                {'Content-Type': 'application/x-www-form-urlencoded'})
+            flv_info_webpage = self._download_webpage(
+                flv_info_request, video_id,
+                note='Downloading flv info', errnote='Unable to download flv info')
+
         video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
 
         # Start extracting information
-        video_title = video_info.find('.//title').text
-        video_extension = video_info.find('.//movie_type').text
-        video_format = video_extension.upper()
-        video_thumbnail = video_info.find('.//thumbnail_url').text
-        video_description = video_info.find('.//description').text
-        video_uploader_id = video_info.find('.//user_id').text
-        video_upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0])
-        video_view_count = video_info.find('.//view_counter').text
-        video_webpage_url = video_info.find('.//watch_url').text
+        title = video_info.find('.//title').text
+        extension = video_info.find('.//movie_type').text
+        video_format = extension.upper()
+        thumbnail = video_info.find('.//thumbnail_url').text
+        description = video_info.find('.//description').text
+        upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0])
+        view_count = int_or_none(video_info.find('.//view_counter').text)
+        comment_count = int_or_none(video_info.find('.//comment_num').text)
+        duration = parse_duration(video_info.find('.//length').text)
+        webpage_url = video_info.find('.//watch_url').text
 
-        # uploader
-        video_uploader = video_uploader_id
-        url = 'http://seiga.nicovideo.jp/api/user/info?id=' + video_uploader_id
-        try:
-            user_info = self._download_xml(
-                url, video_id, note='Downloading user information')
-            video_uploader = user_info.find('.//nickname').text
-        except ExtractorError as err:
-            self._downloader.report_warning('Unable to download user info webpage: %s' % compat_str(err))
+        if video_info.find('.//ch_id') is not None:
+            uploader_id = video_info.find('.//ch_id').text
+            uploader = video_info.find('.//ch_name').text
+        elif video_info.find('.//user_id') is not None:
+            uploader_id = video_info.find('.//user_id').text
+            uploader = video_info.find('.//user_nickname').text
+        else:
+            uploader_id = uploader = None
 
         return {
             'id': video_id,
             'url': video_real_url,
-            'title': video_title,
-            'ext': video_extension,
+            'title': title,
+            'ext': extension,
             'format': video_format,
-            'thumbnail': video_thumbnail,
-            'description': video_description,
-            'uploader': video_uploader,
-            'upload_date': video_upload_date,
-            'uploader_id': video_uploader_id,
-            'view_count': video_view_count,
-            'webpage_url': video_webpage_url,
+            'thumbnail': thumbnail,
+            'description': description,
+            'uploader': uploader,
+            'upload_date': upload_date,
+            'uploader_id': uploader_id,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'duration': duration,
+            'webpage_url': webpage_url,
         }

youtube_dl/extractor/ninegag.py

@@ -47,7 +47,7 @@ class NineGagIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         post_view = json.loads(self._html_search_regex(
-            r'var postView = new app\.PostView\({\s*post:\s*({.+?}),', webpage, 'post view'))
+            r'var postView = new app\.PostView\({\s*post:\s*({.+?}),\s*posts:\s*prefetchedCurrentPost', webpage, 'post view'))
 
         youtube_id = post_view['videoExternalId']
         title = post_view['title']

youtube_dl/extractor/noco.py

@@ -35,7 +35,7 @@ class NocoIE(InfoExtractor):
         video_id = mobj.group('id')
 
         medias = self._download_json(
-            'http://api.noco.tv/1.0/video/medias/%s' % video_id, video_id, 'Downloading video JSON')
+            'https://api.noco.tv/1.0/video/medias/%s' % video_id, video_id, 'Downloading video JSON')
 
         formats = []
 
@@ -43,7 +43,7 @@ class NocoIE(InfoExtractor):
             format_id = fmt['quality_key']
 
             file = self._download_json(
-                'http://api.noco.tv/1.0/video/file/%s/fr/%s' % (format_id.lower(), video_id),
+                'https://api.noco.tv/1.0/video/file/%s/fr/%s' % (format_id.lower(), video_id),
                 video_id, 'Downloading %s video JSON' % format_id)
 
             file_url = file['file']
@@ -71,7 +71,7 @@ class NocoIE(InfoExtractor):
         self._sort_formats(formats)
 
         show = self._download_json(
-            'http://api.noco.tv/1.0/shows/show/%s' % video_id, video_id, 'Downloading show JSON')[0]
+            'https://api.noco.tv/1.0/shows/show/%s' % video_id, video_id, 'Downloading show JSON')[0]
 
         upload_date = unified_strdate(show['indexed'])
         uploader = show['partner_name']

youtube_dl/extractor/npo.py

@@ -0,0 +1,62 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    unified_strdate,
+)
+
+
+class NPOIE(InfoExtractor):
+    IE_NAME = 'npo.nl'
+    _VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?P<id>[^/?]+)'
+
+    _TEST = {
+        'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
+        'md5': '4b3f9c429157ec4775f2c9cb7b911016',
+        'info_dict': {
+            'id': 'VPWON_1220719',
+            'ext': 'mp4',
+            'title': 'Nieuwsuur',
+            'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
+            'upload_date': '20140622',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        metadata = self._download_json(
+            'http://e.omroep.nl/metadata/aflevering/%s' % video_id,
+            video_id,
+            # We have to remove the javascript callback
+            transform_source=lambda j: re.sub(r'parseMetadata\((.*?)\);\n//.*$', r'\1', j)
+        )
+        token_page = self._download_webpage(
+            'http://ida.omroep.nl/npoplayer/i.js',
+            video_id,
+            note='Downloading token'
+        )
+        token = self._search_regex(r'npoplayer.token = "(.+?)"', token_page, 'token')
+        streams_info = self._download_json(
+            'http://ida.omroep.nl/odi/?prid=%s&puboptions=h264_std&adaptive=yes&token=%s' % (video_id, token),
+            video_id
+        )
+
+        stream_info = self._download_json(
+            streams_info['streams'][0] + '&type=json',
+            video_id,
+            'Downloading stream info'
+        )
+
+        return {
+            'id': video_id,
+            'title': metadata['titel'],
+            'ext': 'mp4',
+            'url': stream_info['url'],
+            'description': metadata['info'],
+            'thumbnail': metadata['images'][-1]['url'],
+            'upload_date': unified_strdate(metadata['gidsdatum']),
+        }

youtube_dl/extractor/nrk.py

@@ -6,7 +6,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
-    int_or_none,
+    float_or_none,
     unified_strdate,
 )
 
@@ -72,14 +72,14 @@ class NRKIE(InfoExtractor):
 
 
 class NRKTVIE(InfoExtractor):
-    _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-z]{4}\d{8})'
+    _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})'
 
     _TESTS = [
         {
-            'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/muhh48000314/23-05-2014',
+            'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
             'md5': '7b96112fbae1faf09a6f9ae1aff6cb84',
             'info_dict': {
-                'id': 'muhh48000314',
+                'id': 'MUHH48000314',
                 'ext': 'flv',
                 'title': '20 spørsmål',
                 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
@@ -89,7 +89,7 @@ class NRKTVIE(InfoExtractor):
         },
         {
             'url': 'http://tv.nrk.no/program/mdfp15000514',
-            'md5': '383650ece2b25ecec996ad7b5bb2a384',
+            'md5': 'af01795a31f1cf7265c8657534d8077b',
             'info_dict': {
                 'id': 'mdfp15000514',
                 'ext': 'flv',
@@ -111,9 +111,8 @@ class NRKTVIE(InfoExtractor):
         description = self._html_search_meta('description', page, 'description')
         thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False)
         upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False))
-        duration = self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False)
-        if duration:
-            duration = float(duration)
+        duration = float_or_none(
+            self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False))
 
         formats = []
 
@@ -142,4 +141,4 @@ class NRKTVIE(InfoExtractor):
             'upload_date': upload_date,
             'duration': duration,
             'formats': formats,
-        }
+        }

youtube_dl/extractor/ntv.py

@@ -5,7 +5,6 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
     unescapeHTML
 )
 

youtube_dl/extractor/nuvid.py

@@ -3,6 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    unified_strdate,
+    compat_urllib_request,
+)
 
 
 class NuvidIE(InfoExtractor):
@@ -13,8 +18,10 @@ class NuvidIE(InfoExtractor):
         'info_dict': {
             'id': '1310741',
             'ext': 'mp4',
-            "title": "Horny babes show their awesome bodeis and",
-            "age_limit": 18,
+            'title': 'Horny babes show their awesome bodeis and',
+            'duration': 129,
+            'upload_date': '20140508',
+            'age_limit': 18,
         }
     }
 
@@ -22,27 +29,41 @@ class NuvidIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
-        murl = url.replace('://www.', '://m.')
-        webpage = self._download_webpage(murl, video_id)
+        formats = []
 
+        for dwnld_speed, format_id in [(0, '3gp'), (5, 'mp4')]:
+            request = compat_urllib_request.Request(
+                'http://m.nuvid.com/play/%s' % video_id)
+            request.add_header('Cookie', 'skip_download_page=1; dwnld_speed=%d; adv_show=1' % dwnld_speed)
+            webpage = self._download_webpage(
+                request, video_id, 'Downloading %s page' % format_id)
+            video_url = self._html_search_regex(
+                r'<a href="([^"]+)"\s*>Continue to watch video', webpage, '%s video URL' % format_id, fatal=False)
+            if not video_url:
+                continue
+            formats.append({
+                'url': video_url,
+                'format_id': format_id,
+            })
+
+        webpage = self._download_webpage(
+            'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page')
         title = self._html_search_regex(
-            r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>',
-            webpage, 'title').strip()
-
-        url_end = self._html_search_regex(
-            r'href="(/[^"]+)"[^>]*data-link_type="mp4"',
-            webpage, 'video_url')
-        video_url = 'http://m.nuvid.com' + url_end
-
+            r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>', webpage, 'title').strip()
         thumbnail = self._html_search_regex(
             r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"',
             webpage, 'thumbnail URL', fatal=False)
+        duration = parse_duration(self._html_search_regex(
+            r'Length:\s*<span>(\d{2}:\d{2})</span>',webpage, 'duration', fatal=False))
+        upload_date = unified_strdate(self._html_search_regex(
+            r'Added:\s*<span>(\d{4}-\d{2}-\d{2})</span>', webpage, 'upload date', fatal=False))
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
             'title': title,
-            'thumbnail': thumbnail,
+            'thumbnail': 'http://m.nuvid.com%s' % thumbnail,
+            'duration': duration,
+            'upload_date': upload_date,
             'age_limit': 18,
-        }
+            'formats': formats,
+        }

youtube_dl/extractor/prosiebensat1.py

@@ -158,19 +158,19 @@ class ProSiebenSat1IE(InfoExtractor):
     _CLIPID_REGEXES = [
         r'"clip_id"\s*:\s+"(\d+)"',
         r'clipid: "(\d+)"',
-        r'clipId=(\d+)',
+        r'clip[iI]d=(\d+)',
     ]
     _TITLE_REGEXES = [
         r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>',
         r'<header class="clearfix">\s*<h3>(.+?)</h3>',
         r'<!-- start video -->\s*<h1>(.+?)</h1>',
-        r'<div class="ep-femvideos-pi4-video-txt">\s*<h2>(.+?)</h2>',
+        r'<h1 class="att-name">\s*(.+?)</h1>',
     ]
     _DESCRIPTION_REGEXES = [
         r'<p itemprop="description">\s*(.+?)</p>',
         r'<div class="videoDecription">\s*<p><strong>Beschreibung</strong>: (.+?)</p>',
         r'<div class="g-plusone" data-size="medium"></div>\s*</div>\s*</header>\s*(.+?)\s*<footer>',
-        r'<p>(.+?)</p>\s*<div class="ep-femvideos-pi4-video-footer">',
+        r'<p class="att-description">\s*(.+?)\s*</p>',
     ]
     _UPLOAD_DATE_REGEXES = [
         r'<meta property="og:published_time" content="(.+?)">',

youtube_dl/extractor/pyvideo.py

@@ -46,7 +46,7 @@ class PyvideoIE(InfoExtractor):
             return self.url_result(m_youtube.group(1), 'Youtube')
 
         title = self._html_search_regex(
-            r'<div class="section">.*?<h3(?:\s+class="[^"]*")?>([^>]+?)</h3>',
+            r'<div class="section">\s*<h3(?:\s+class="[^"]*"[^>]*)?>([^>]+?)</h3>',
             webpage, 'title', flags=re.DOTALL)
         video_url = self._search_regex(
             [r'<source src="(.*?)"', r'<dt>Download</dt>.*?<a href="(.+?)"'],

youtube_dl/extractor/rai.py

@@ -0,0 +1,122 @@
+from __future__ import unicode_literals
+
+import re
+
+from .subtitles import SubtitlesInfoExtractor
+from ..utils import (
+    parse_duration,
+    unified_strdate,
+    compat_urllib_parse,
+)
+
+
+class RaiIE(SubtitlesInfoExtractor):
+    _VALID_URL = r'(?P<url>http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html)'
+    _TESTS = [
+        {
+            'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
+            'md5': 'c064c0b2d09c278fb293116ef5d0a32d',
+            'info_dict': {
+                'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
+                'ext': 'mp4',
+                'title': 'Report del 07/04/2014',
+                'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
+                'upload_date': '20140407',
+                'duration': 6160,
+            }
+        },
+        {
+            'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
+            'md5': '8bb9c151924ce241b74dd52ef29ceafa',
+            'info_dict': {
+                'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
+                'ext': 'mp4',
+                'title': 'TG PRIMO TEMPO',
+                'description': '',
+                'upload_date': '20140612',
+                'duration': 1758,
+            },
+            'skip': 'Error 404',
+        },
+        {
+            'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
+            'md5': '35cf7c229f22eeef43e48b5cf923bef0',
+            'info_dict': {
+                'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13',
+                'ext': 'mp4',
+                'title': 'State of the Net, Antonella La Carpia: regole virali',
+                'description': 'md5:b0ba04a324126903e3da7763272ae63c',
+                'upload_date': '20140613',
+            },
+            'skip': 'Error 404',
+        },
+        {
+            'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
+            'md5': '35694f062977fe6619943f08ed935730',
+            'info_dict': {
+                'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
+                'ext': 'mp4',
+                'title': 'Alluvione in Sardegna e dissesto idrogeologico',
+                'description': 'Edizione delle ore 20:30 ',
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        media = self._download_json('%s?json' % mobj.group('url'), video_id, 'Downloading video JSON')
+
+        title = media.get('name')
+        description = media.get('desc')
+        thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
+        duration = parse_duration(media.get('length'))
+        uploader = media.get('author')
+        upload_date = unified_strdate(media.get('date'))
+
+        formats = []
+
+        for format_id in ['wmv', 'm3u8', 'mediaUri', 'h264']:
+            media_url = media.get(format_id)
+            if not media_url:
+                continue
+            formats.append({
+                'url': media_url,
+                'format_id': format_id,
+                'ext': 'mp4',
+            })
+
+        if self._downloader.params.get('listsubtitles', False):
+            page = self._download_webpage(url, video_id)
+            self._list_available_subtitles(video_id, page)
+            return
+
+        subtitles = {}
+        if self._have_to_download_any_subtitles:
+            page = self._download_webpage(url, video_id)
+            subtitles = self.extract_subtitles(video_id, page)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'upload_date': upload_date,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+    def _get_available_subtitles(self, video_id, webpage):
+        subtitles = {}
+        m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
+        if m:
+            captions = m.group('captions')
+            STL_EXT = '.stl'
+            SRT_EXT = '.srt'
+            if captions.endswith(STL_EXT):
+                captions = captions[:-len(STL_EXT)] + SRT_EXT
+            subtitles['it'] = 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions)
+        return subtitles

youtube_dl/extractor/redtube.py

@@ -35,9 +35,7 @@ class RedTubeIE(InfoExtractor):
             r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
             webpage, u'title')
 
-        video_thumbnail = self._html_search_regex(
-            r'playerInnerHTML.+?<img\s+src="(.+?)"',
-            webpage, u'thumbnail', fatal=False)
+        video_thumbnail = self._og_search_thumbnail(webpage)
 
         # No self-labeling, but they describe themselves as
         # "Home of Videos Porno"

youtube_dl/extractor/reverbnation.py

@@ -0,0 +1,45 @@
+from __future__ import unicode_literals
+
+import re
+import time
+
+from .common import InfoExtractor
+from ..utils import strip_jsonp
+
+
+class ReverbNationIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$'
+    _TESTS = [{
+        'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa',
+        'file': '16965047.mp3',
+        'md5': '3da12ebca28c67c111a7f8b262d3f7a7',
+        'info_dict': {
+            "title": "MONA LISA",
+            "uploader": "ALKILADOS",
+            "uploader_id": 216429,
+            "thumbnail": "//gp1.wac.edgecastcdn.net/802892/production_public/Photo/13761700/image/1366002176_AVATAR_MONA_LISA.jpg"
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        song_id = mobj.group('id')
+
+        api_res = self._download_json(
+            'https://api.reverbnation.com/song/%s?callback=api_response_5&_=%d'
+                % (song_id, int(time.time() * 1000)),
+            song_id,
+            transform_source=strip_jsonp,
+            note='Downloading information of song %s' % song_id
+        )
+
+        return {
+            'id': song_id,
+            'title': api_res.get('name'),
+            'url': api_res.get('url'),
+            'uploader': api_res.get('artist', {}).get('name'),
+            'uploader_id': api_res.get('artist', {}).get('id'),
+            'thumbnail': api_res.get('image', api_res.get('thumbnail')),
+            'ext': 'mp3',
+            'vcodec': 'none',
+        }

youtube_dl/extractor/rtbf.py

@@ -30,7 +30,7 @@ class RTBFIE(InfoExtractor):
         page = self._download_webpage('https://www.rtbf.be/video/embed?id=%s' % video_id, video_id)
 
         data = json.loads(self._html_search_regex(
-            r'<div class="js-player-embed" data-video="([^"]+)"', page, 'data video'))['data']
+            r'<div class="js-player-embed(?: player-embed)?" data-video="([^"]+)"', page, 'data video'))['data']
 
         video_url = data.get('downloadUrl') or data.get('url')
 

youtube_dl/extractor/rtlnow.py

@@ -92,16 +92,7 @@ class RTLnowIE(InfoExtractor):
         },
         {
             'url': 'http://www.n-tvnow.de/deluxe-alles-was-spass-macht/thema-ua-luxushotel-fuer-vierbeiner.php?container_id=153819&player=1&season=0',
-            'info_dict': {
-                'id': '153819',
-                'ext': 'flv',
-                'title': 'Deluxe - Alles was Spaß macht - Thema u.a.: Luxushotel für Vierbeiner',
-                'description': 'md5:c3705e1bb32e1a5b2bcd634fc065c631',
-                'thumbnail': 'http://autoimg.static-fra.de/ntvnow/383157/1500x1500/image2.jpg',
-                'upload_date': '20140221',
-                'duration': 2429,
-            },
-            'skip': 'Only works from Germany',
+            'only_matching': True,
         },
     ]
 

youtube_dl/extractor/rtve.py

@@ -17,7 +17,7 @@ class RTVEALaCartaIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
-        'md5': '18fcd45965bdd076efdb12cd7f6d7b9e',
+        'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
         'info_dict': {
             'id': '2491869',
             'ext': 'mp4',

youtube_dl/extractor/ruhd.py

@@ -0,0 +1,46 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class RUHDIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.ruhd.ru/play.php?vid=207',
+        'md5': 'd1a9ec4edf8598e3fbd92bb16072ba83',
+        'info_dict': {
+            'id': '207',
+            'ext': 'divx',
+            'title': 'КОТ бааааам',
+            'description': 'классный кот)',
+            '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)
+
+        video_url = self._html_search_regex(
+            r'<param name="src" value="([^"]+)"', webpage, 'video url')
+        title = self._html_search_regex(
+            r'<title>([^<]+)&nbsp;&nbsp; RUHD.ru - Видео Высокого качества №1 в России!</title>', webpage, 'title')
+        description = self._html_search_regex(
+            r'(?s)<div id="longdesc">(.+?)<span id="showlink">', webpage, 'description', fatal=False)
+        thumbnail = self._html_search_regex(
+            r'<param name="previewImage" value="([^"]+)"', webpage, 'thumbnail', fatal=False)
+        if thumbnail:
+            thumbnail = 'http://www.ruhd.ru' + thumbnail
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/sapo.py

@@ -0,0 +1,119 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    unified_strdate,
+)
+
+
+class SapoIE(InfoExtractor):
+    IE_DESC = 'SAPO Vídeos'
+    _VALID_URL = r'https?://(?:(?:v2|www)\.)?videos\.sapo\.(?:pt|cv|ao|mz|tl)/(?P<id>[\da-zA-Z]{20})'
+
+    _TESTS = [
+        {
+            'url': 'http://videos.sapo.pt/UBz95kOtiWYUMTA5Ghfi',
+            'md5': '79ee523f6ecb9233ac25075dee0eda83',
+            'note': 'SD video',
+            'info_dict': {
+                'id': 'UBz95kOtiWYUMTA5Ghfi',
+                'ext': 'mp4',
+                'title': 'Benfica - Marcas na Hitória',
+                'description': 'md5:c9082000a128c3fd57bf0299e1367f22',
+                'duration': 264,
+                'uploader': 'tiago_1988',
+                'upload_date': '20080229',
+                'categories': ['benfica', 'cabral', 'desporto', 'futebol', 'geovanni', 'hooijdonk', 'joao', 'karel', 'lisboa', 'miccoli'],
+            },
+        },
+        {
+            'url': 'http://videos.sapo.pt/IyusNAZ791ZdoCY5H5IF',
+            'md5': '90a2f283cfb49193fe06e861613a72aa',
+            'note': 'HD video',
+            'info_dict': {
+                'id': 'IyusNAZ791ZdoCY5H5IF',
+                'ext': 'mp4',
+                'title': 'Codebits VII - Report',
+                'description': 'md5:6448d6fd81ce86feac05321f354dbdc8',
+                'duration': 144,
+                'uploader': 'codebits',
+                'upload_date': '20140427',
+                'categories': ['codebits', 'codebits2014'],
+            },
+        },
+        {
+            'url': 'http://v2.videos.sapo.pt/yLqjzPtbTimsn2wWBKHz',
+            'md5': 'e5aa7cc0bdc6db9b33df1a48e49a15ac',
+            'note': 'v2 video',
+            'info_dict': {
+                'id': 'yLqjzPtbTimsn2wWBKHz',
+                'ext': 'mp4',
+                'title': 'Hipnose Condicionativa 4',
+                'description': 'md5:ef0481abf8fb4ae6f525088a6dadbc40',
+                'duration': 692,
+                'uploader': 'sapozen',
+                'upload_date': '20090609',
+                'categories': ['condicionativa', 'heloisa', 'hipnose', 'miranda', 'sapo', 'zen'],
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        item = self._download_xml(
+            'http://rd3.videos.sapo.pt/%s/rss2' % video_id, video_id).find('./channel/item')
+
+        title = item.find('./title').text
+        description = item.find('./{http://videos.sapo.pt/mrss/}synopse').text
+        thumbnail = item.find('./{http://search.yahoo.com/mrss/}content').get('url')
+        duration = parse_duration(item.find('./{http://videos.sapo.pt/mrss/}time').text)
+        uploader = item.find('./{http://videos.sapo.pt/mrss/}author').text
+        upload_date = unified_strdate(item.find('./pubDate').text)
+        view_count = int(item.find('./{http://videos.sapo.pt/mrss/}views').text)
+        comment_count = int(item.find('./{http://videos.sapo.pt/mrss/}comment_count').text)
+        tags = item.find('./{http://videos.sapo.pt/mrss/}tags').text
+        categories = tags.split() if tags else []
+        age_limit = 18 if item.find('./{http://videos.sapo.pt/mrss/}m18').text == 'true' else 0
+
+        video_url = item.find('./{http://videos.sapo.pt/mrss/}videoFile').text
+        video_size = item.find('./{http://videos.sapo.pt/mrss/}videoSize').text.split('x')
+
+        formats = [{
+            'url': video_url,
+            'ext': 'mp4',
+            'format_id': 'sd',
+            'width': int(video_size[0]),
+            'height': int(video_size[1]),
+        }]
+
+        if item.find('./{http://videos.sapo.pt/mrss/}HD').text == 'true':
+            formats.append({
+                'url': re.sub(r'/mov/1$', '/mov/39', video_url),
+                'ext': 'mp4',
+                'format_id': 'hd',
+                'width': 1280,
+                'height': 720,
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'uploader': uploader,
+            'upload_date': upload_date,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'categories': categories,
+            'age_limit': age_limit,
+            'formats': formats,
+        }

youtube_dl/extractor/savefrom.py

@@ -20,7 +20,7 @@ class SaveFromIE(InfoExtractor):
             'upload_date': '20120816',
             'uploader': 'Howcast',
             'uploader_id': 'Howcast',
-            'description': 'md5:4f0aac94361a12e1ce57d74f85265175',
+            'description': 're:(?s).* Hi, my name is Rene Dreifuss\. And I\'m here to show you some MMA.*',
         },
         'params': {
             'skip_download': True

youtube_dl/extractor/screencast.py

@@ -0,0 +1,112 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_parse_qs,
+    compat_urllib_request,
+)
+
+
+class ScreencastIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.screencast\.com/t/(?P<id>[a-zA-Z0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.screencast.com/t/3ZEjQXlT',
+        'md5': '917df1c13798a3e96211dd1561fded83',
+        'info_dict': {
+            'id': '3ZEjQXlT',
+            'ext': 'm4v',
+            'title': 'Color Measurement with Ocean Optics Spectrometers',
+            'description': 'md5:240369cde69d8bed61349a199c5fb153',
+            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
+        }
+    }, {
+        'url': 'http://www.screencast.com/t/V2uXehPJa1ZI',
+        'md5': 'e8e4b375a7660a9e7e35c33973410d34',
+        'info_dict': {
+            'id': 'V2uXehPJa1ZI',
+            'ext': 'mov',
+            'title': 'The Amadeus Spectrometer',
+            'description': 're:^In this video, our friends at.*To learn more about Amadeus, visit',
+            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
+        }
+    }, {
+        'url': 'http://www.screencast.com/t/aAB3iowa',
+        'md5': 'dedb2734ed00c9755761ccaee88527cd',
+        'info_dict': {
+            'id': 'aAB3iowa',
+            'ext': 'mp4',
+            'title': 'Google Earth Export',
+            'description': 'Provides a demo of a CommunityViz export to Google Earth, one of the 3D viewing options.',
+            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
+        }
+    }, {
+        'url': 'http://www.screencast.com/t/X3ddTrYh',
+        'md5': '669ee55ff9c51988b4ebc0877cc8b159',
+        'info_dict': {
+            'id': 'X3ddTrYh',
+            'ext': 'wmv',
+            'title': 'Toolkit 6 User Group Webinar (2014-03-04) - Default Judgment and First Impression',
+            'description': 'md5:7b9f393bc92af02326a5c5889639eab0',
+            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
+        }
+    },
+    ]
+
+    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_url = self._html_search_regex(
+            r'<embed name="Video".*?src="([^"]+)"', webpage,
+            'QuickTime embed', default=None)
+
+        if video_url is None:
+            flash_vars_s = self._html_search_regex(
+                r'<param name="flashVars" value="([^"]+)"', webpage, 'flash vars',
+                default=None)
+            if not flash_vars_s:
+                flash_vars_s = self._html_search_regex(
+                    r'<param name="initParams" value="([^"]+)"', webpage, 'flash vars',
+                    default=None)
+                if flash_vars_s:
+                    flash_vars_s = flash_vars_s.replace(',', '&')
+            if flash_vars_s:
+                flash_vars = compat_parse_qs(flash_vars_s)
+                video_url_raw = compat_urllib_request.quote(
+                    flash_vars['content'][0])
+                video_url = video_url_raw.replace('http%3A', 'http:')
+
+        if video_url is None:
+            video_meta = self._html_search_meta(
+                'og:video', webpage, default=None)
+            if video_meta:
+                video_url = self._search_regex(
+                    r'src=(.*?)(?:$|&)', video_meta,
+                    'meta tag video URL', default=None)
+
+        if video_url is None:
+            raise ExtractorError('Cannot find video')
+
+        title = self._og_search_title(webpage, default=None)
+        if title is None:
+            title = self._html_search_regex(
+                [r'<b>Title:</b> ([^<]*)</div>',
+                r'class="tabSeperator">></span><span class="tabText">(.*?)<'],
+                webpage, 'title')
+        thumbnail = self._og_search_thumbnail(webpage)
+        description = self._og_search_description(webpage, default=None)
+        if description is None:
+            description = self._html_search_meta('description', webpage)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/slutload.py

@@ -3,9 +3,6 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
 
 
 class SlutloadIE(InfoExtractor):

youtube_dl/extractor/snotr.py

@@ -0,0 +1,68 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    str_to_int,
+    parse_duration,
+)
+
+
+class SnotrIE(InfoExtractor):
+    _VALID_URL = r'http?://(?:www\.)?snotr\.com/video/(?P<id>\d+)/([\w]+)'
+    _TESTS = [{
+        'url': 'http://www.snotr.com/video/13708/Drone_flying_through_fireworks',
+        'info_dict': {
+            'id': '13708',
+            'ext': 'flv',
+            'title': 'Drone flying through fireworks!',
+            'duration': 247,
+            'filesize_approx': 98566144,
+            'description': 'A drone flying through Fourth of July Fireworks',
+        }
+    }, {
+        'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10',
+        'info_dict': {
+            'id': '530',
+            'ext': 'flv',
+            'title': 'David Letteman - George W. Bush Top 10',
+            'duration': 126,
+            'filesize_approx': 8912896,
+            'description': 'The top 10 George W. Bush moments, brought to you by David Letterman!',
+        }
+    }]
+
+    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._og_search_title(webpage)
+
+        description = self._og_search_description(webpage)
+        video_url = "http://cdn.videos.snotr.com/%s.flv" % video_id
+
+        view_count = str_to_int(self._html_search_regex(
+            r'<p>\n<strong>Views:</strong>\n([\d,\.]+)</p>',
+            webpage, 'view count', fatal=False))
+
+        duration = parse_duration(self._html_search_regex(
+            r'<p>\n<strong>Length:</strong>\n\s*([0-9:]+).*?</p>',
+            webpage, 'duration', fatal=False))
+
+        filesize_approx = float_or_none(self._html_search_regex(
+            r'<p>\n<strong>Filesize:</strong>\n\s*([0-9.]+)\s*megabyte</p>',
+            webpage, 'filesize', fatal=False), invscale=1024 * 1024)
+
+        return {
+            'id': video_id,
+            'description': description,
+            'title': title,
+            'url': video_url,
+            'view_count': view_count,
+            'duration': duration,
+            'filesize_approx': filesize_approx,
+        }

youtube_dl/extractor/sockshare.py

@@ -0,0 +1,80 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from ..utils import (
+    ExtractorError,
+    compat_urllib_parse,
+    compat_urllib_request,
+    determine_ext,
+)
+import re
+
+from .common import InfoExtractor
+
+
+class SockshareIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?sockshare\.com/file/(?P<id>[0-9A-Za-z]+)'
+    _FILE_DELETED_REGEX = r'This file doesn\'t exist, or has been removed\.</div>'
+    _TEST = {
+        'url': 'http://www.sockshare.com/file/437BE28B89D799D7',
+        'md5': '9d0bf1cfb6dbeaa8d562f6c97506c5bd',
+        'info_dict': {
+            'id': '437BE28B89D799D7',
+            'title': 'big_buck_bunny_720p_surround.avi',
+            'ext': 'avi',
+            'thumbnail': 're:^http://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        url = 'http://sockshare.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)
+
+        confirm_hash = self._html_search_regex(r'''(?x)<input\s+
+            type="hidden"\s+
+            value="([^"]*)"\s+
+            name="hash"
+            ''', webpage, 'hash')
+
+        fields = {
+            "hash": confirm_hash,
+            "confirm": "Continue as Free User"
+        }
+
+        post = compat_urllib_parse.urlencode(fields)
+        req = compat_urllib_request.Request(url, post)
+        # Apparently, this header is required for confirmation to work.
+        req.add_header('Host', 'www.sockshare.com')
+        req.add_header('Content-type', 'application/x-www-form-urlencoded')
+
+        webpage = self._download_webpage(
+            req, video_id, 'Downloading video page')
+
+        video_url = self._html_search_regex(
+            r'<a href="([^"]*)".+class="download_file_link"',
+            webpage, 'file url')
+        video_url = "http://www.sockshare.com" + video_url
+        title = self._html_search_regex(r'<h1>(.+)<strong>', webpage, 'title')
+        thumbnail = self._html_search_regex(
+            r'<img\s+src="([^"]*)".+?name="bg"',
+            webpage, 'thumbnail')
+
+        formats = [{
+            'format_id': 'sd',
+            'url': video_url,
+            'ext': determine_ext(title),
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/soundcloud.py

@@ -1,7 +1,6 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import json
 import re
 import itertools
 
@@ -12,6 +11,7 @@ from ..utils import (
     compat_urllib_parse,
 
     ExtractorError,
+    int_or_none,
     unified_strdate,
 )
 
@@ -44,7 +44,8 @@ class SoundcloudIE(InfoExtractor):
                 "upload_date": "20121011",
                 "description": "No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd",
                 "uploader": "E.T. ExTerrestrial Music",
-                "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
+                "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1",
+                "duration": 143,
             }
         },
         # not streamable song
@@ -57,6 +58,7 @@ class SoundcloudIE(InfoExtractor):
                 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com',
                 'uploader': 'The Royal Concept',
                 'upload_date': '20120521',
+                'duration': 227,
             },
             'params': {
                 # rtmp
@@ -74,19 +76,21 @@ class SoundcloudIE(InfoExtractor):
                 'uploader': 'jaimeMF',
                 'description': 'test chars:  \"\'/\\ä↭',
                 'upload_date': '20131209',
+                'duration': 9,
             },
         },
         # downloadable song
         {
-            'url': 'https://soundcloud.com/simgretina/just-your-problem-baby-1',
-            'md5': '56a8b69568acaa967b4c49f9d1d52d19',
+            'url': 'https://soundcloud.com/oddsamples/bus-brakes',
+            'md5': '7624f2351f8a3b2e7cd51522496e7631',
             'info_dict': {
-                'id': '105614606',
-                'ext': 'wav',
-                'title': 'Just Your Problem Baby (Acapella)',
-                'description': 'Vocals',
-                'uploader': 'Sim Gretina',
-                'upload_date': '20130815',
+                'id': '128590877',
+                'ext': 'mp3',
+                'title': 'Bus Brakes',
+                'description': 'md5:0170be75dd395c96025d210d261c784e',
+                'uploader': 'oddsamples',
+                'upload_date': '20140109',
+                'duration': 17,
             },
         },
     ]
@@ -119,6 +123,7 @@ class SoundcloudIE(InfoExtractor):
             'title': info['title'],
             'description': info['description'],
             'thumbnail': thumbnail,
+            'duration': int_or_none(info.get('duration'), 1000),
         }
         formats = []
         if info.get('downloadable', False):
@@ -250,7 +255,7 @@ class SoundcloudSetIE(SoundcloudIE):
 
 
 class SoundcloudUserIE(SoundcloudIE):
-    _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$'
+    _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)/?((?P<rsrc>tracks|likes)/?)?(\?.*)?$'
     IE_NAME = 'soundcloud:user'
 
     # it's in tests/test_playlists.py
@@ -259,24 +264,31 @@ class SoundcloudUserIE(SoundcloudIE):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         uploader = mobj.group('user')
+        resource = mobj.group('rsrc')
+        if resource is None:
+            resource = 'tracks'
+        elif resource == 'likes':
+            resource = 'favorites'
 
         url = 'http://soundcloud.com/%s/' % uploader
         resolv_url = self._resolv_url(url)
         user = self._download_json(
             resolv_url, uploader, 'Downloading user info')
-        base_url = 'http://api.soundcloud.com/users/%s/tracks.json?' % uploader
+        base_url = 'http://api.soundcloud.com/users/%s/%s.json?' % (uploader, resource)
 
         entries = []
         for i in itertools.count():
             data = compat_urllib_parse.urlencode({
                 'offset': i * 50,
+                'limit': 50,
                 'client_id': self._CLIENT_ID,
             })
             new_entries = self._download_json(
                 base_url + data, uploader, 'Downloading track page %s' % (i + 1))
-            entries.extend(self._extract_info_dict(e, quiet=True) for e in new_entries)
-            if len(new_entries) < 50:
+            if len(new_entries) == 0:
+                self.to_screen('%s: End page received' % uploader)
                 break
+            entries.extend(self._extract_info_dict(e, quiet=True) for e in new_entries)
 
         return {
             '_type': 'playlist',

youtube_dl/extractor/soundgasm.py

@@ -0,0 +1,40 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class SoundgasmIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<user>[0-9a-zA-Z_\-]+)/(?P<title>[0-9a-zA-Z_\-]+)'
+    _TEST = {
+        'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
+        'md5': '010082a2c802c5275bb00030743e75ad',
+        'info_dict': {
+            'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9',
+            'ext': 'm4a',
+            'title': 'ytdl_Piano-sample',
+            'description': 'Royalty Free Sample Music'
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('title')
+        audio_title = mobj.group('user') + '_' + mobj.group('title')
+        webpage = self._download_webpage(url, display_id)
+        audio_url = self._html_search_regex(
+            r'(?s)m4a\:\s"([^"]+)"', webpage, 'audio URL')
+        audio_id = re.split('\/|\.', audio_url)[-2]
+        description = self._html_search_regex(
+            r'(?s)<li>Description:\s(.*?)<\/li>', webpage, 'description',
+            fatal=False)
+
+        return {
+            'id': audio_id,
+            'display_id': display_id,
+            'url': audio_url,
+            'title': audio_title,
+            'description': description
+        }

youtube_dl/extractor/southpark.py

@@ -3,24 +3,24 @@ from __future__ import unicode_literals
 from .mtv import MTVServicesInfoExtractor
 
 
-class SouthParkStudiosIE(MTVServicesInfoExtractor):
-    IE_NAME = 'southparkstudios.com'
-    _VALID_URL = r'https?://(www\.)?(?P<url>southparkstudios\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
+class SouthParkIE(MTVServicesInfoExtractor):
+    IE_NAME = 'southpark.cc.com'
+    _VALID_URL = r'https?://(www\.)?(?P<url>southpark\.cc\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
 
     _FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
 
     _TESTS = [{
-        'url': 'http://www.southparkstudios.com/clips/104437/bat-daded#tab=featured',
+        'url': 'http://southpark.cc.com/clips/104437/bat-daded#tab=featured',
         'info_dict': {
             'id': 'a7bff6c2-ed00-11e0-aca6-0026b9414f30',
             'ext': 'mp4',
-            'title': 'Bat Daded',
+            'title': 'South Park|Bat Daded',
             'description': 'Randy disqualifies South Park by getting into a fight with Bat Dad.',
         },
     }]
 
 
-class SouthparkDeIE(SouthParkStudiosIE):
+class SouthparkDeIE(SouthParkIE):
     IE_NAME = 'southpark.de'
     _VALID_URL = r'https?://(www\.)?(?P<url>southpark\.de/(clips|alle-episoden)/(?P<id>.+?)(\?|#|$))'
     _FEED_URL = 'http://www.southpark.de/feeds/video-player/mrss/'

youtube_dl/extractor/spiegel.py

@@ -1,3 +1,4 @@
+# encoding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -9,18 +10,33 @@ class SpiegelIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
     _TESTS = [{
         'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
-        'file': '1259285.mp4',
         'md5': '2c2754212136f35fb4b19767d242f66e',
         'info_dict': {
+            'id': '1259285',
+            'ext': 'mp4',
             'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv',
+            'description': 'md5:8029d8310232196eb235d27575a8b9f4',
+            'duration': 49,
         },
-    },
-    {
+    }, {
         'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
-        'file': '1309159.mp4',
         'md5': 'f2cdf638d7aa47654e251e1aee360af1',
         'info_dict': {
+            'id': '1309159',
+            'ext': 'mp4',
             'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
+            'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
+            'duration': 983,
+        },
+    }, {
+        'url': 'http://www.spiegel.de/video/johann-westhauser-videobotschaft-des-hoehlenforschers-video-1502367.html',
+        'md5': '54f58ba0e752e3c07bc2a26222dd0acf',
+        'info_dict': {
+            'id': '1502367',
+            'ext': 'mp4',
+            'title': 'Videobotschaft: Höhlenforscher Westhauser dankt seinen Rettern',
+            'description': 'md5:c6f1ec11413ebd1088b6813943e5fc91',
+            'duration': 42,
         },
     }]
 
@@ -30,18 +46,20 @@ class SpiegelIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        video_title = self._html_search_regex(
+        title = self._html_search_regex(
             r'<div class="module-title">(.*?)</div>', webpage, 'title')
+        description = self._html_search_meta('description', webpage, 'description')
 
-        xml_url = 'http://video2.spiegel.de/flash/' + video_id + '.xml'
-        idoc = self._download_xml(
-            xml_url, video_id,
-            note='Downloading XML', errnote='Failed to download XML')
+        base_url = self._search_regex(
+            r'var\s+server\s*=\s*"([^"]+)\"', webpage, 'server URL')
+
+        xml_url = base_url + video_id + '.xml'
+        idoc = self._download_xml(xml_url, video_id)
 
         formats = [
             {
                 'format_id': n.tag.rpartition('type')[2],
-                'url': 'http://video2.spiegel.de/flash/' + n.find('./filename').text,
+                'url': base_url + n.find('./filename').text,
                 'width': int(n.find('./width').text),
                 'height': int(n.find('./height').text),
                 'abr': int(n.find('./audiobitrate').text),
@@ -59,7 +77,8 @@ class SpiegelIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': video_title,
+            'title': title,
+            'description': description,
             'duration': duration,
             'formats': formats,
         }

youtube_dl/extractor/spiegeltv.py

@@ -0,0 +1,81 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+from .common import InfoExtractor
+
+
+class SpiegeltvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/filme/(?P<id>[\-a-z0-9]+)'
+    _TEST = {
+        'url': 'http://www.spiegel.tv/filme/flug-mh370/',
+        'info_dict': {
+            'id': 'flug-mh370',
+            'ext': 'm4v',
+            'title': 'Flug MH370',
+            'description': 'Das Rätsel um die Boeing 777 der Malaysia-Airlines',
+            'thumbnail': 're:http://.*\.jpg$',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }
+
+    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'<h1.*?>(.*?)</h1>', webpage, 'title')
+
+        apihost = 'http://spiegeltv-ivms2-restapi.s3.amazonaws.com'
+        version_json = self._download_json(
+            '%s/version.json' % apihost, video_id,
+            note='Downloading version information')
+        version_name = version_json['version_name']
+
+        slug_json = self._download_json(
+            '%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id),
+            video_id,
+            note='Downloading object information')
+        oid = slug_json['object_id']
+
+        media_json = self._download_json(
+            '%s/%s/restapi/media/%s.json' % (apihost, version_name, oid),
+            video_id, note='Downloading media information')
+        uuid = media_json['uuid']
+        is_wide = media_json['is_wide']
+
+        server_json = self._download_json(
+            'http://www.spiegel.tv/streaming_servers/', video_id,
+            note='Downloading server information')
+        server = server_json[0]['endpoint']
+
+        thumbnails = []
+        for image in media_json['images']:
+            thumbnails.append({
+                'url': image['url'],
+                'width': image['width'],
+                'height': image['height'],
+            })
+
+        description = media_json['subtitle']
+        duration = media_json['duration_in_ms'] / 1000.
+
+        if is_wide:
+            format = '16x9'
+        else:
+            format = '4x3'
+
+        url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v'
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': url,
+            'ext': 'm4v',
+            'description': description,
+            'duration': duration,
+            'thumbnails': thumbnails
+        }

youtube_dl/extractor/steam.py

@@ -53,7 +53,7 @@ class SteamIE(InfoExtractor):
             'ext': 'mp4',
             'upload_date': '20140329',
             'title': 'FRONTIERS - Final Greenlight Trailer',
-            'description': "The final trailer for the Steam Greenlight launch. Hooray, progress! Here's the official Greenlight page: http://steamcommunity.com/sharedfiles/filedetails/?id=242472205",
+            'description': 'md5:dc96a773669d0ca1b36c13c1f30250d9',
             'uploader': 'AAD Productions',
             'uploader_id': 'AtomicAgeDogGames',
         }

youtube_dl/extractor/tagesschau.py

@@ -0,0 +1,69 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class TagesschauIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/video/video(?P<id>-?[0-9]+)\.html'
+
+    _TESTS = [{
+        'url': 'http://www.tagesschau.de/multimedia/video/video1399128.html',
+        'md5': 'bcdeac2194fb296d599ce7929dfa4009',
+        'info_dict': {
+            'id': '1399128',
+            'ext': 'mp4',
+            'title': 'Harald Range, Generalbundesanwalt, zu den Ermittlungen',
+            'description': 'md5:69da3c61275b426426d711bde96463ab',
+            'thumbnail': 're:^http:.*\.jpg$',
+        },
+    }]
+
+    _FORMATS = {
+        's': {'width': 256, 'height': 144, 'quality': 1},
+        'm': {'width': 512, 'height': 288, 'quality': 2},
+        'l': {'width': 960, 'height': 544, 'quality': 3},
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        if video_id.startswith('-'):
+            display_id = video_id.strip('-')
+        else:
+            display_id = video_id
+
+        webpage = self._download_webpage(url, display_id)
+
+        playerpage = self._download_webpage(
+            'http://www.tagesschau.de/multimedia/video/video%s~player_autoplay-true.html' % video_id,
+            display_id, 'Downloading player page')
+
+        medias = re.findall(
+            r'"(http://media.+?)", type:"video/(.+?)", quality:"(.+?)"',
+            playerpage)
+
+        formats = []
+        for url, ext, res in medias:
+            f = {
+                'format_id': res + '_' + ext,
+                'url': url,
+                'ext': ext,
+            }
+            f.update(self._FORMATS.get(res, {}))
+            formats.append(f)
+
+        self._sort_formats(formats)
+
+        thumbnail = re.findall(r'"(/multimedia/.+?\.jpg)"', playerpage)[-1]
+
+        return {
+            'id': display_id,
+            'title': self._og_search_title(webpage).strip(),
+            'thumbnail': 'http://www.tagesschau.de' + thumbnail,
+            'formats': formats,
+            'description': self._og_search_description(webpage).strip(),
+        }