release 2014.08.02.1

Duh.

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).
@@ -38,12 +38,6 @@ which means you can modify it, redistribute it or use it however you like.
                                      playlist or the command line) if an error
                                      occurs
     --dump-user-agent                display the current browser identification
-    --user-agent UA                  specify a custom user agent
-    --referer REF                    specify a custom referer, use if the video
-                                     access is restricted to one domain
-    --add-header FIELD:VALUE         specify a custom HTTP header and its value,
-                                     separated by a colon ':'. You can use this
-                                     option multiple times
     --list-extractors                List all supported extractors and the URLs
                                      they would handle
     --extractor-descriptions         Output descriptions of all supported
@@ -51,34 +45,22 @@ which means you can modify it, redistribute it or use it however you like.
     --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in
                                      an empty string (--proxy "") for direct
                                      connection
-    --no-check-certificate           Suppress HTTPS certificate validation.
-    --prefer-insecure                Use an unencrypted connection to retrieve
-                                     information about the video. (Currently
-                                     supported only for YouTube)
-    --cache-dir DIR                  Location in the filesystem where youtube-dl
-                                     can store some downloaded information
-                                     permanently. By default $XDG_CACHE_HOME
-                                     /youtube-dl or ~/.cache/youtube-dl . At the
-                                     moment, only YouTube player files (for
-                                     videos with obfuscated signatures) are
-                                     cached, but that may change.
-    --no-cache-dir                   Disable filesystem caching
     --socket-timeout None            Time to wait before giving up, in seconds
-    --bidi-workaround                Work around terminals that lack
-                                     bidirectional text support. Requires bidiv
-                                     or fribidi executable in PATH
     --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 ("auto_warning" to emit a
+                                     warning when guessing). "error" just throws
+                                     an error. The default value "fixup_error"
+                                     repairs broken URLs, but emits an error if
+                                     this is not possible instead of searching.
     --ignore-config                  Do not read configuration files. When given
                                      in the global configuration file /etc
                                      /youtube-dl.conf: do not read the user
                                      configuration in ~/.config/youtube-dl.conf
                                      (%APPDATA%/youtube-dl/config.txt on
                                      Windows)
-    --encoding ENCODING              Force the specified encoding (experimental)
 
 ## Video Selection:
     --playlist-start NUMBER          playlist video to start at (default is 1)
@@ -124,9 +106,9 @@ which means you can modify it, redistribute it or use it however you like.
                                      of SIZE.
 
 ## Filesystem Options:
-    -t, --title                      use title in file name (default)
+    -a, --batch-file FILE            file containing URLs to download ('-' for
+                                     stdin)
     --id                             use only video ID in file name
-    -l, --literal                    [deprecated] alias of --title
     -A, --auto-number                number downloaded files starting from 00000
     -o, --output TEMPLATE            output filename template. Use %(title)s to
                                      get the title, %(uploader)s for the
@@ -159,18 +141,15 @@ which means you can modify it, redistribute it or use it however you like.
     --restrict-filenames             Restrict filenames to only ASCII
                                      characters, and avoid "&" and spaces in
                                      filenames
-    -a, --batch-file FILE            file containing URLs to download ('-' for
-                                     stdin)
-    --load-info FILE                 json file containing the video information
-                                     (created with the "--write-json" option)
+    -t, --title                      [deprecated] use title in file name
+                                     (default)
+    -l, --literal                    [deprecated] alias of --title
     -w, --no-overwrites              do not overwrite files
     -c, --continue                   force resume of partially downloaded files.
                                      By default, youtube-dl will resume
                                      downloads if possible.
     --no-continue                    do not resume partially downloaded files
                                      (restart from beginning)
-    --cookies FILE                   file to read cookies from and dump cookie
-                                     jar in
     --no-part                        do not use .part files
     --no-mtime                       do not use the Last-modified header to set
                                      the file modification time
@@ -180,6 +159,19 @@ which means you can modify it, redistribute it or use it however you like.
     --write-annotations              write video annotations to a .annotation
                                      file
     --write-thumbnail                write thumbnail image to disk
+    --load-info FILE                 json file containing the video information
+                                     (created with the "--write-json" option)
+    --cookies FILE                   file to read cookies from and dump cookie
+                                     jar in
+    --cache-dir DIR                  Location in the filesystem where youtube-dl
+                                     can store some downloaded information
+                                     permanently. By default $XDG_CACHE_HOME
+                                     /youtube-dl or ~/.cache/youtube-dl . At the
+                                     moment, only YouTube player files (for
+                                     videos with obfuscated signatures) are
+                                     cached, but that may change.
+    --no-cache-dir                   Disable filesystem caching
+    --rm-cache-dir                   Delete all filesystem cache files
 
 ## Verbosity / Simulation Options:
     -q, --quiet                      activates quiet mode
@@ -209,6 +201,22 @@ which means you can modify it, redistribute it or use it however you like.
                                      problems
     --print-traffic                  Display sent and read HTTP traffic
 
+## Workarounds:
+    --encoding ENCODING              Force the specified encoding (experimental)
+    --no-check-certificate           Suppress HTTPS certificate validation.
+    --prefer-insecure                Use an unencrypted connection to retrieve
+                                     information about the video. (Currently
+                                     supported only for YouTube)
+    --user-agent UA                  specify a custom user agent
+    --referer REF                    specify a custom referer, use if the video
+                                     access is restricted to one domain
+    --add-header FIELD:VALUE         specify a custom HTTP header and its value,
+                                     separated by a colon ':'. You can use this
+                                     option multiple times
+    --bidi-workaround                Work around terminals that lack
+                                     bidirectional text support. Requires bidiv
+                                     or fribidi executable in PATH
+
 ## Video Format Options:
     -f, --format FORMAT              video format code, specify the order of
                                      preference using slashes: "-f 22/17/18".
@@ -254,7 +262,7 @@ 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

@@ -15,7 +15,6 @@ from youtube_dl.extractor import (
     FacebookIE,
     gen_extractors,
     JustinTVIE,
-    PBSIE,
     YoutubeIE,
 )
 
@@ -69,9 +68,6 @@ 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_download.py

@@ -10,7 +10,6 @@ from test.helper import (
     get_params,
     gettestcases,
     expect_info_dict,
-    md5,
     try_rm,
     report_warning,
 )
@@ -24,7 +23,6 @@ import socket
 import youtube_dl.YoutubeDL
 from youtube_dl.utils import (
     compat_http_client,
-    compat_str,
     compat_urllib_error,
     compat_HTTPError,
     DownloadError,

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,
 )
@@ -28,8 +29,9 @@ from youtube_dl.extractor import (
     SoundcloudSetIE,
     SoundcloudUserIE,
     SoundcloudPlaylistIE,
-    TeacherTubeClassroomIE,
+    TeacherTubeUserIE,
     LivestreamIE,
+    LivestreamOriginalIE,
     NHLVideocenterIE,
     BambuserChannelIE,
     BandcampAlbumIE,
@@ -40,6 +42,7 @@ from youtube_dl.extractor import (
     KhanAcademyIE,
     EveryonesMixtapeIE,
     RutubeChannelIE,
+    RutubePersonIE,
     GoogleSearchIE,
     GenericIE,
     TEDIE,
@@ -69,8 +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()
@@ -109,15 +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()
@@ -125,7 +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()
@@ -133,7 +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()
@@ -143,7 +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):
@@ -152,7 +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()
@@ -169,15 +188,15 @@ 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()
         ie = BandcampAlbumIE(dl)
-        result = ie.extract('http://mpallante.bandcamp.com/album/nightmare-night-ep')
+        result = ie.extract('http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Nightmare Night EP')
-        self.assertTrue(len(result['entries']) >= 4)
+        self.assertEqual(result['title'], 'Hierophany of the Open Grave')
+        assertGreaterEqual(self, len(result['entries']), 9)
         
     def test_smotri_community(self):
         dl = FakeYDL()
@@ -186,7 +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()
@@ -195,7 +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()
@@ -214,7 +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()
@@ -223,7 +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()
@@ -242,7 +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()
@@ -256,10 +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
@@ -296,7 +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()
@@ -304,7 +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()
@@ -312,7 +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()
@@ -320,7 +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')
@@ -359,15 +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_TeacherTubeClassroom(self):
+    def test_TeacherTubeUser(self):
         dl = FakeYDL()
-        ie = TeacherTubeClassroomIE(dl)
-        result = ie.extract('http://www.teachertube.com/view_classroom.php?user=rbhagwati2')
+        ie = TeacherTubeUserIE(dl)
+        result = ie.extract('http://www.teachertube.com/user/profile/rbhagwati2')
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], 'rbhagwati2')
-        self.assertTrue(len(result['entries']) >= 20)
+        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_signature.py

@@ -1,5 +1,7 @@
 #!/usr/bin/env python
 
+from __future__ import unicode_literals
+
 # Allow direct execution
 import os
 import sys
@@ -16,23 +18,65 @@ from youtube_dl.utils import compat_str, compat_urlretrieve
 
 _TESTS = [
     (
-        u'https://s.ytimg.com/yts/jsbin/html5player-vflHOr_nV.js',
-        u'js',
+        'https://s.ytimg.com/yts/jsbin/html5player-vflHOr_nV.js',
+        'js',
         86,
-        u'>=<;:/.-[+*)(\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBA\\yxwvutsrqponmlkjihgfedcba987654321',
+        '>=<;:/.-[+*)(\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBA\\yxwvutsrqponmlkjihgfedcba987654321',
     ),
     (
-        u'https://s.ytimg.com/yts/jsbin/html5player-vfldJ8xgI.js',
-        u'js',
+        'https://s.ytimg.com/yts/jsbin/html5player-vfldJ8xgI.js',
+        'js',
         85,
-        u'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
+        '3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
     ),
     (
-        u'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js',
-        u'js',
+        'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js',
+        'js',
         90,
-        u']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876',
+        ']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876',
     ),
+    (
+        'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl0Cbn9e.js',
+        'js',
+        84,
+        'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVW@YZ!"#$%&\'()*+,-./:;<=',
+    ),
+    (
+        'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js',
+        'js',
+        '2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA',
+        'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2',
+    ),
+    (
+        'http://s.ytimg.com/yts/swfbin/player-vfl5vIhK2/watch_as3.swf',
+        'swf',
+        86,
+        'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVWXY\\!"#$%&\'()*+,-./:;<=>?'
+    ),
+    (
+        'http://s.ytimg.com/yts/swfbin/player-vflmDyk47/watch_as3.swf',
+        'swf',
+        'F375F75BF2AFDAAF2666E43868D46816F83F13E81C46.3725A8218E446A0DECD33F79DC282994D6AA92C92C9',
+        '9C29AA6D499282CD97F33DCED0A644E8128A5273.64C18E31F38361864D86834E6662FAADFA2FB57F'
+    ),
+    (
+        'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js',
+        'js',
+        84,
+        '123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>'
+    ),
+    (
+        'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl9FYC6l.js',
+        'js',
+        83,
+        '123456789abcdefghijklmnopqr0tuvwxyzABCDETGHIJKLMNOPQRS>UVWXYZ!"#$%&\'()*+,-./:;<=F'
+    ),
+    (
+        'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflCGk6yw/html5player.js',
+        'js',
+        '4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288',
+        '82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B'
+    )
 ]
 
 
@@ -44,13 +88,13 @@ 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]+$', basename)
-    assert m, '%r should follow URL format' % basename
+def make_tfunc(url, stype, sig_input, expected_sig):
+    m = re.match(r'.*-([a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.[a-z]+$', 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 +110,9 @@ 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/FileDownloader.py

@@ -1,12 +0,0 @@
-# Legacy file for backwards compatibility, use youtube_dl.downloader instead!
-from .downloader import FileDownloader as RealFileDownloader
-from .downloader import get_suitable_downloader
-
-
-# This class reproduces the old behaviour of FileDownloader
-class FileDownloader(RealFileDownloader):
-    def _do_download(self, filename, info_dict):
-        real_fd = get_suitable_downloader(info_dict)(self.ydl, self.params)
-        for ph in self._progress_hooks:
-            real_fd.add_progress_hook(ph)
-        return real_fd.download(filename, info_dict)

youtube_dl/YoutubeDL.py

@@ -275,7 +275,7 @@ class YoutubeDL(object):
             return message
 
         assert hasattr(self, '_output_process')
-        assert type(message) == type('')
+        assert isinstance(message, compat_str)
         line_count = message.count('\n') + 1
         self._output_process.stdin.write((message + '\n').encode('utf-8'))
         self._output_process.stdin.flush()
@@ -303,7 +303,7 @@ class YoutubeDL(object):
 
     def to_stderr(self, message):
         """Print message to stderr."""
-        assert type(message) == type('')
+        assert isinstance(message, compat_str)
         if self.params.get('logger'):
             self.params['logger'].error(message)
         else:
@@ -849,7 +849,7 @@ class YoutubeDL(object):
         # Keep for backwards compatibility
         info_dict['stitle'] = info_dict['title']
 
-        if not 'format' in info_dict:
+        if 'format' not in info_dict:
             info_dict['format'] = info_dict['ext']
 
         reason = self._match_entry(info_dict)
@@ -993,11 +993,13 @@ 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 = []
                         success = True
-                        merger = FFmpegMergerPP(self)
+                        merger = FFmpegMergerPP(self, not self.params.get('keepvideo'))
                         if not merger._get_executable():
                             postprocessors = []
                             self.report_warning('You have requested multiple '
@@ -1195,6 +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):
@@ -1228,14 +1234,18 @@ class YoutubeDL(object):
         if not self.params.get('verbose'):
             return
 
-        write_string(
+        if type('') is not compat_str:
+            # Python 2.6 on SLES11 SP1 (https://github.com/rg3/youtube-dl/issues/3326)
+            self.report_warning(
+                'Your Python is broken! Update to a newer and supported version')
+
+        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()))
+        write_string(encoding_str, encoding=None)
 
         self._write_string('[debug] youtube-dl version ' + __version__ + '\n')
         try:

youtube_dl/__init__.py

@@ -59,18 +59,24 @@ __authors__  = (
     '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 shutil
 import sys
 
 
@@ -92,7 +98,7 @@ from .utils import (
     write_string,
 )
 from .update import update_self
-from .FileDownloader import (
+from .downloader import (
     FileDownloader,
 )
 from .extractor import gen_extractors
@@ -217,6 +223,7 @@ def parseOpts(overrideArguments=None):
     downloader     = optparse.OptionGroup(parser, 'Download Options')
     postproc       = optparse.OptionGroup(parser, 'Post-processing Options')
     filesystem     = optparse.OptionGroup(parser, 'Filesystem Options')
+    workarounds    = optparse.OptionGroup(parser, 'Workarounds')
     verbosity      = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
 
     general.add_option('-h', '--help',
@@ -233,14 +240,6 @@ def parseOpts(overrideArguments=None):
     general.add_option('--dump-user-agent',
             action='store_true', dest='dump_user_agent',
             help='display the current browser identification', default=False)
-    general.add_option('--user-agent',
-            dest='user_agent', help='specify a custom user agent', metavar='UA')
-    general.add_option('--referer',
-            dest='referer', help='specify a custom referer, use if the video access is restricted to one domain',
-            metavar='REF', default=None)
-    general.add_option('--add-header',
-            dest='headers', help='specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times', action="append",
-            metavar='FIELD:VALUE')
     general.add_option('--list-extractors',
             action='store_true', dest='list_extractors',
             help='List all supported extractors and the URLs they would handle', default=False)
@@ -250,33 +249,17 @@ def parseOpts(overrideArguments=None):
     general.add_option(
         '--proxy', dest='proxy', default=None, metavar='URL',
         help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection')
-    general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
-    general.add_option(
-        '--prefer-insecure', '--prefer-unsecure', action='store_true', dest='prefer_insecure',
-        help='Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)')
-    general.add_option(
-        '--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR',
-        help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.')
-    general.add_option(
-        '--no-cache-dir', action='store_const', const=None, dest='cachedir',
-        help='Disable filesystem caching')
     general.add_option(
         '--socket-timeout', dest='socket_timeout',
         type=float, default=None, help=u'Time to wait before giving up, in seconds')
-    general.add_option(
-        '--bidi-workaround', dest='bidi_workaround', action='store_true',
-        help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH')
     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 ("auto_warning" to emit a warning when guessing). "error" just throws an error. The default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.')
     general.add_option(
         '--ignore-config',
         action='store_true',
         help='Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows)')
-    general.add_option(
-        '--encoding', dest='encoding', metavar='ENCODING',
-        help='Force the specified encoding (experimental)')
 
     selection.add_option(
         '--playlist-start',
@@ -377,6 +360,33 @@ def parseOpts(overrideArguments=None):
             help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.', default=False)
     downloader.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP)
 
+    workarounds.add_option(
+        '--encoding', dest='encoding', metavar='ENCODING',
+        help='Force the specified encoding (experimental)')
+    workarounds.add_option(
+        '--no-check-certificate', action='store_true',
+        dest='no_check_certificate', default=False,
+        help='Suppress HTTPS certificate validation.')
+    workarounds.add_option(
+        '--prefer-insecure', '--prefer-unsecure', action='store_true', dest='prefer_insecure',
+        help='Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)')
+    workarounds.add_option(
+        '--user-agent', metavar='UA',
+        dest='user_agent', help='specify a custom user agent')
+    workarounds.add_option(
+        '--referer', metavar='REF',
+        dest='referer', default=None,
+        help='specify a custom referer, use if the video access is restricted to one domain',
+    )
+    workarounds.add_option(
+        '--add-header', metavar='FIELD:VALUE',
+        dest='headers', action='append',
+        help='specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times',
+    )
+    workarounds.add_option(
+        '--bidi-workaround', dest='bidi_workaround', action='store_true',
+        help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH')
+
     verbosity.add_option('-q', '--quiet',
             action='store_true', dest='quiet', help='activates quiet mode', default=False)
     verbosity.add_option(
@@ -434,12 +444,10 @@ def parseOpts(overrideArguments=None):
             help='Display sent and read HTTP traffic')
 
 
-    filesystem.add_option('-t', '--title',
-            action='store_true', dest='usetitle', help='use title in file name (default)', default=False)
+    filesystem.add_option('-a', '--batch-file',
+            dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
     filesystem.add_option('--id',
             action='store_true', dest='useid', help='use only video ID in file name', default=False)
-    filesystem.add_option('-l', '--literal',
-            action='store_true', dest='usetitle', help='[deprecated] alias of --title', default=False)
     filesystem.add_option('-A', '--auto-number',
             action='store_true', dest='autonumber',
             help='number downloaded files starting from 00000', default=False)
@@ -465,11 +473,10 @@ def parseOpts(overrideArguments=None):
     filesystem.add_option('--restrict-filenames',
             action='store_true', dest='restrictfilenames',
             help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
-    filesystem.add_option('-a', '--batch-file',
-            dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
-    filesystem.add_option('--load-info',
-            dest='load_info_filename', metavar='FILE',
-            help='json file containing the video information (created with the "--write-json" option)')
+    filesystem.add_option('-t', '--title',
+            action='store_true', dest='usetitle', help='[deprecated] use title in file name (default)', default=False)
+    filesystem.add_option('-l', '--literal',
+            action='store_true', dest='usetitle', help='[deprecated] alias of --title', default=False)
     filesystem.add_option('-w', '--no-overwrites',
             action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
     filesystem.add_option('-c', '--continue',
@@ -477,8 +484,6 @@ def parseOpts(overrideArguments=None):
     filesystem.add_option('--no-continue',
             action='store_false', dest='continue_dl',
             help='do not resume partially downloaded files (restart from beginning)')
-    filesystem.add_option('--cookies',
-            dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
     filesystem.add_option('--no-part',
             action='store_true', dest='nopart', help='do not use .part files', default=False)
     filesystem.add_option('--no-mtime',
@@ -496,6 +501,20 @@ def parseOpts(overrideArguments=None):
     filesystem.add_option('--write-thumbnail',
             action='store_true', dest='writethumbnail',
             help='write thumbnail image to disk', default=False)
+    filesystem.add_option('--load-info',
+            dest='load_info_filename', metavar='FILE',
+            help='json file containing the video information (created with the "--write-json" option)')
+    filesystem.add_option('--cookies',
+            dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
+    filesystem.add_option(
+        '--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR',
+        help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.')
+    filesystem.add_option(
+        '--no-cache-dir', action='store_const', const=None, dest='cachedir',
+        help='Disable filesystem caching')
+    filesystem.add_option(
+        '--rm-cache-dir', action='store_true', dest='rm_cachedir',
+        help='Delete all filesystem cache files')
 
 
     postproc.add_option('-x', '--extract-audio', action='store_true', dest='extractaudio', default=False,
@@ -505,7 +524,7 @@ 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,
@@ -529,6 +548,7 @@ def parseOpts(overrideArguments=None):
     parser.add_option_group(downloader)
     parser.add_option_group(filesystem)
     parser.add_option_group(verbosity)
+    parser.add_option_group(workarounds)
     parser.add_option_group(video_format)
     parser.add_option_group(subtitles)
     parser.add_option_group(authentication)
@@ -628,7 +648,7 @@ 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)
@@ -689,7 +709,7 @@ def _real_main(argv=None):
         date = DateRange.day(opts.date)
     else:
         date = DateRange(opts.dateafter, opts.datebefore)
-    if opts.default_search not in ('auto', 'auto_warning', None) and ':' not in opts.default_search:
+    if opts.default_search not in ('auto', 'auto_warning', 'error', 'fixup_error', None) and ':' not in opts.default_search:
         parser.error(u'--default-search invalid; did you forget a colon (:) at the end?')
 
     # Do not download videos when there are audio-only formats
@@ -828,9 +848,26 @@ def _real_main(argv=None):
         if opts.update_self:
             update_self(ydl.to_screen, opts.verbose)
 
+        # Remove cache dir
+        if opts.rm_cachedir:
+            if opts.cachedir is None:
+                ydl.to_screen(u'No cache dir specified (Did you combine --no-cache-dir and --rm-cache-dir?)')
+            else:
+                if ('.cache' not in opts.cachedir) or ('youtube-dl' not in opts.cachedir):
+                    ydl.to_screen(u'Not removing directory %s - this does not look like a cache dir')
+                    retcode = 141
+                else:
+                    ydl.to_screen(
+                        u'Removing cache dir %s .' % opts.cachedir,
+                        skip_eol=True)
+                    if os.path.exists(opts.cachedir):
+                        ydl.to_screen(u'.', skip_eol=True)
+                        shutil.rmtree(opts.cachedir)
+                    ydl.to_screen(u'.')
+
         # Maybe do nothing
         if (len(all_urls) < 1) and (opts.load_info_filename is None):
-            if not opts.update_self:
+            if not (opts.update_self or opts.rm_cachedir):
                 parser.error(u'you must provide at least one URL')
             else:
                 sys.exit()

youtube_dl/downloader/f4m.py

@@ -220,6 +220,7 @@ class F4mFD(FileDownloader):
 
     def real_download(self, filename, info_dict):
         man_url = info_dict['url']
+        requested_bitrate = info_dict.get('tbr')
         self.to_screen('[download] Downloading f4m manifest')
         manifest = self.ydl.urlopen(man_url).read()
         self.report_destination(filename)
@@ -233,8 +234,14 @@ class F4mFD(FileDownloader):
 
         doc = etree.fromstring(manifest)
         formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))]
-        formats = sorted(formats, key=lambda f: f[0])
-        rate, media = formats[-1]
+        if requested_bitrate is None:
+            # get the best format
+            formats = sorted(formats, key=lambda f: f[0])
+            rate, media = formats[-1]
+        else:
+            rate, media = list(filter(
+                lambda f: int(f[0]) == requested_bitrate, formats))[0]
+
         base_url = compat_urlparse.urljoin(man_url, media.attrib['url'])
         bootstrap = base64.b64decode(doc.find(_add_ns('bootstrapInfo')).text)
         metadata = base64.b64decode(media.find(_add_ns('metadata')).text)

youtube_dl/extractor/__init__.py

@@ -1,8 +1,11 @@
+from .abc import ABCIE
 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 +54,7 @@ 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 +65,10 @@ 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 +87,7 @@ 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 +110,17 @@ 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 .gamestar import GameStarIE
 from .gametrailers import GametrailersIE
 from .gdcvault import GDCVaultIE
 from .generic import GenericIE
+from .godtube import GodTubeIE
 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
@@ -131,6 +143,7 @@ from .ivi import (
     IviIE,
     IviCompilationIE
 )
+from .izlesene import IzleseneIE
 from .jadorecettepub import JadoreCettePubIE
 from .jeuxvideo import JeuxVideoIE
 from .jukebox import JukeboxIE
@@ -142,11 +155,16 @@ from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
 from .kontrtube import KontrTubeIE
+from .krasview import KrasViewIE
 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
@@ -160,15 +178,18 @@ 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
@@ -195,6 +216,7 @@ 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,
@@ -216,8 +238,10 @@ 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
@@ -226,6 +250,7 @@ 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,
@@ -233,9 +258,12 @@ 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 .shared import SharedIE
 from .sina import SinaIE
 from .slideshare import SlideshareIE
 from .slutload import SlutloadIE
@@ -245,6 +273,8 @@ from .smotri import (
     SmotriUserIE,
     SmotriBroadcastIE,
 )
+from .snotr import SnotrIE
+from .sockshare import SockshareIE
 from .sohu import SohuIE
 from .soundcloud import (
     SoundcloudIE,
@@ -252,8 +282,9 @@ from .soundcloud import (
     SoundcloudUserIE,
     SoundcloudPlaylistIE
 )
-from .southparkstudios import (
-    SouthParkStudiosIE,
+from .soundgasm import SoundgasmIE
+from .southpark import (
+    SouthParkIE,
     SouthparkDeIE,
 )
 from .space import SpaceIE
@@ -271,12 +302,13 @@ from .sztvhu import SztvHuIE
 from .tagesschau import TagesschauIE
 from .teachertube import (
     TeacherTubeIE,
-    TeacherTubeClassroomIE,
+    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
@@ -294,6 +326,8 @@ from .tumblr import TumblrIE
 from .tutv import TutvIE
 from .tvigle import TvigleIE
 from .tvp import TvpIE
+from .tvplay import TVPlayIE
+from.ubu import UbuIE
 from .udemy import (
     UdemyIE,
     UdemyCourseIE
@@ -315,6 +349,7 @@ from .videofyme import VideofyMeIE
 from .videopremium import VideoPremiumIE
 from .videott import VideoTtIE
 from .videoweed import VideoWeedIE
+from .vidme import VidmeIE
 from .vimeo import (
     VimeoIE,
     VimeoChannelIE,
@@ -324,12 +359,14 @@ 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
@@ -344,6 +381,7 @@ 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
@@ -374,6 +412,7 @@ from .youtube import (
     YoutubeUserIE,
     YoutubeWatchLaterIE,
 )
+
 from .zdf import ZDFIE
 
 

youtube_dl/extractor/abc.py

@@ -0,0 +1,48 @@
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class ABCIE(InfoExtractor):
+    IE_NAME = 'abc.net.au'
+    _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.abc.net.au/news/2014-07-25/bringing-asylum-seekers-to-australia-would-give/5624716',
+        'md5': 'dad6f8ad011a70d9ddf887ce6d5d0742',
+        'info_dict': {
+            'id': '5624716',
+            'ext': 'mp4',
+            'title': 'Bringing asylum seekers to Australia would give them right to asylum claims: professor',
+            'description': 'md5:ba36fa5e27e5c9251fd929d339aea4af',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+
+        urls_info_json = self._search_regex(
+            r'inlineVideoData\.push\((.*?)\);', webpage, 'video urls',
+            flags=re.DOTALL)
+        urls_info = json.loads(urls_info_json.replace('\'', '"'))
+        formats = [{
+            'url': url_info['url'],
+            'width': int(url_info['width']),
+            'height': int(url_info['height']),
+            'tbr': int(url_info['bitrate']),
+            'filesize': int(url_info['filesize']),
+        } for url_info in urls_info]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

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 +7,34 @@ from .common import InfoExtractor
 from ..utils import (
     determine_ext,
     ExtractorError,
+    qualities,
+    compat_urllib_parse_urlparse,
+    compat_urllib_parse,
 )
 
 
 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
@@ -35,6 +46,9 @@ class ARDIE(InfoExtractor):
         else:
             video_id = m.group('video_id')
 
+        urlp = compat_urllib_parse_urlparse(url)
+        url = urlp._replace(path=compat_urllib_parse.quote(urlp.path.encode('utf-8'))).geturl()
+
         webpage = self._download_webpage(url, video_id)
 
         title = self._html_search_regex(
@@ -43,29 +57,64 @@ 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]
@@ -52,16 +52,16 @@ class BlinkxIE(InfoExtractor):
                     'height': int(m['h']),
                 })
             elif m['type'] == 'original':
-                duration = m['d']
+                duration = float(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/bloomberg.py

@@ -10,7 +10,7 @@ class BloombergIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
-        'md5': '7bf08858ff7c203c870e8a6190e221e5',
+        # The md5 checksum changes
         'info_dict': {
             'id': 'qurhIVlJSB6hzkVi229d8g',
             'ext': 'flv',
@@ -31,8 +31,7 @@ class BloombergIE(InfoExtractor):
         return {
             'id': name.split('-')[-1],
             'title': title,
-            'url': f4m_url,
-            'ext': 'flv',
+            'formats': self._extract_f4m_formats(f4m_url, name),
             'description': self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
         }

youtube_dl/extractor/br.py

@@ -7,25 +7,25 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
+    parse_duration,
 )
 
 
 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': 'Wenn das Traditions-Theater wackelt',
+                'description': 'Heimatsound-Festival 2014: Wenn das Traditions-Theater wackelt',
+                'duration': 34,
             }
         },
         {
@@ -36,6 +36,7 @@ class BRIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Über den Pass',
                 'description': 'Die Eroberung der Alpen: Über den Pass',
+                'duration': 2588,
             }
         },
         {
@@ -46,6 +47,7 @@ class BRIE(InfoExtractor):
                 'ext': 'aac',
                 'title': '"Keine neuen Schulden im nächsten Jahr"',
                 'description': 'Haushaltsentwurf: "Keine neuen Schulden im nächsten Jahr"',
+                'duration': 64,
             }
         },
         {
@@ -56,6 +58,7 @@ class BRIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Umweltbewusster Häuslebauer',
                 'description': 'Uwe Erdelt: Umweltbewusster Häuslebauer',
+                'duration': 116,
             }
         },
         {
@@ -66,6 +69,7 @@ class BRIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Folge 1 - Metaphysik',
                 'description': 'Kant für Anfänger: Folge 1 - Metaphysik',
+                'duration': 893,
                 'uploader': 'Eva Maria Steimle',
                 'upload_date': '20140117',
             }
@@ -86,6 +90,7 @@ class BRIE(InfoExtractor):
             media = {
                 'id': xml_media.get('externalId'),
                 'title': xml_media.find('title').text,
+                'duration': parse_duration(xml_media.find('duration').text),
                 'formats': self._extract_formats(xml_media.find('assets')),
                 'thumbnails': self._extract_thumbnails(xml_media.find('teaserImage/variants')),
                 'description': ' '.join(xml_media.find('shareTitle').text.splitlines()),

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/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/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 (
@@ -17,6 +18,7 @@ from ..utils import (
     clean_html,
     compiled_regex_type,
     ExtractorError,
+    int_or_none,
     RegexNotFoundError,
     sanitize_filename,
     unescapeHTML,
@@ -68,6 +70,7 @@ 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.
@@ -299,8 +302,12 @@ 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:
@@ -367,7 +374,8 @@ class InfoExtractor(object):
         else:
             for p in pattern:
                 mobj = re.search(p, string, flags)
-                if mobj: break
+                if mobj:
+                    break
 
         if os.name != 'nt' and sys.stderr.isatty():
             _name = u'\033[0;34m%s\033[0m' % name
@@ -459,14 +467,17 @@ 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')
@@ -551,6 +562,7 @@ 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)
@@ -572,6 +584,31 @@ 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)
+
+    def _extract_f4m_formats(self, manifest_url, video_id):
+        manifest = self._download_xml(
+            manifest_url, video_id, 'Downloading f4m manifest',
+            'Unable to download f4m manifest')
+
+        formats = []
+        for media_el in manifest.findall('{http://ns.adobe.com/f4m/1.0}media'):
+            formats.append({
+                'url': manifest_url,
+                'ext': 'flv',
+                'tbr': int_or_none(media_el.attrib.get('bitrate')),
+                'width': int_or_none(media_el.attrib.get('width')),
+                'height': int_or_none(media_el.attrib.get('height')),
+            })
+        self._sort_formats(formats)
+
+        return formats
+
 
 class SearchInfoExtractor(InfoExtractor):
     """
@@ -615,4 +652,3 @@ 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/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/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

@@ -19,17 +19,35 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
             + video_id, video_id, 'Downloading XML config')
 
         manifest_url = info.find('videos/video/url').text
-        video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8')
-        video_url = video_url.replace('/z/', '/i/')
+        manifest_url = manifest_url.replace('/z/', '/i/')
+        
+        if manifest_url.startswith('rtmp'):
+            formats = [{'url': manifest_url, 'ext': 'flv'}]
+        else:
+            formats = []
+            available_formats = self._search_regex(r'/[^,]*,(.*?),k\.mp4', manifest_url, 'available formats')
+            for index, format_descr in enumerate(available_formats.split(',')):
+                format_info = {
+                    'url': manifest_url.replace('manifest.f4m', 'index_%d_av.m3u8' % index),
+                    'ext': 'mp4',
+                }
+                m_resolution = re.search(r'(?P<width>\d+)x(?P<height>\d+)', format_descr)
+                if m_resolution is not None:
+                    format_info.update({
+                        'width': int(m_resolution.group('width')),
+                        'height': int(m_resolution.group('height')),
+                    })
+                formats.append(format_info)
+
         thumbnail_path = info.find('image').text
 
-        return {'id': video_id,
-                'ext': 'flv' if video_url.startswith('rtmp') else 'mp4',
-                'url': video_url,
-                'title': info.find('titre').text,
-                'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
-                'description': info.find('synopsis').text,
-                }
+        return {
+            'id': video_id,
+            'title': info.find('titre').text,
+            'formats': formats,
+            'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
+            'description': info.find('synopsis').text,
+        }
 
 
 class PluzzIE(FranceTVBaseInfoExtractor):
@@ -48,7 +66,7 @@ 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 +229,7 @@ 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/gamestar.py

@@ -0,0 +1,74 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    str_to_int,
+    unified_strdate,
+)
+
+
+class GameStarIE(InfoExtractor):
+    _VALID_URL = r'http://www\.gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
+    _TEST = {
+        'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
+        'md5': '96974ecbb7fd8d0d20fca5a00810cea7',
+        'info_dict': {
+            'id': '76110',
+            'ext': 'mp4',
+            'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil',
+            'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den vollständigen Trailer an.',
+            'thumbnail': 'http://images.gamestar.de/images/idgwpgsgp/bdb/2494525/600x.jpg',
+            'upload_date': '20140728',
+            'duration': 17
+        }
+    }
+
+    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_title = self._og_search_title(webpage)
+        title = og_title.replace(' - Video bei GameStar.de', '').strip()
+
+        url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id
+
+        description = self._og_search_description(webpage).strip()
+
+        thumbnail = self._proto_relative_url(
+            self._og_search_thumbnail(webpage), scheme='http:')
+
+        upload_date = unified_strdate(self._html_search_regex(
+            r'<span style="float:left;font-size:11px;">Datum: ([0-9]+\.[0-9]+\.[0-9]+)&nbsp;&nbsp;',
+            webpage, 'upload_date', fatal=False))
+
+        duration = parse_duration(self._html_search_regex(
+            r'&nbsp;&nbsp;Länge: ([0-9]+:[0-9]+)</span>', webpage, 'duration',
+            fatal=False))
+
+        view_count = str_to_int(self._html_search_regex(
+            r'&nbsp;&nbsp;Zuschauer: ([0-9\.]+)&nbsp;&nbsp;', webpage,
+            'view_count', fatal=False))
+
+        comment_count = int_or_none(self._html_search_regex(
+            r'>Kommentieren \(([0-9]+)\)</a>', webpage, 'comment_count',
+            fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': url,
+            'ext': 'mp4',
+            'thumbnail': thumbnail,
+            'description': description,
+            'upload_date': upload_date,
+            'duration': duration,
+            'view_count': view_count,
+            'comment_count': comment_count
+        }

youtube_dl/extractor/gdcvault.py

@@ -8,6 +8,7 @@ from ..utils import (
     compat_urllib_request,
 )
 
+
 class GDCVaultIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)'
     _TESTS = [
@@ -31,6 +32,15 @@ class GDCVaultIE(InfoExtractor):
                 'skip_download': True,  # Requires rtmpdump
             }
         },
+        {
+            'url': 'http://www.gdcvault.com/play/1015301/Thexder-Meets-Windows-95-or',
+            'md5': 'a5eb77996ef82118afbbe8e48731b98e',
+            'info_dict': {
+                'id': '1015301',
+                'ext': 'flv',
+                'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
+            }
+        }
     ]
 
     def _parse_mp4(self, xml_description):
@@ -103,18 +113,40 @@ class GDCVaultIE(InfoExtractor):
         webpage_url = 'http://www.gdcvault.com/play/' + video_id
         start_page = self._download_webpage(webpage_url, video_id)
 
-        xml_root = self._html_search_regex(r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', start_page, 'xml root', None, False)
+        direct_url = self._search_regex(
+            r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);',
+            start_page, 'url', default=None)
+        if direct_url:
+            video_url = 'http://www.gdcvault.com/' + direct_url
+            title = self._html_search_regex(
+                r'<td><strong>Session Name</strong></td>\s*<td>(.*?)</td>',
+                start_page, 'title')
 
+            return {
+                'id': video_id,
+                'url': video_url,
+                'ext': 'flv',
+                'title': title,
+            }
+
+        xml_root = self._html_search_regex(
+            r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>',
+            start_page, 'xml root', default=None)
         if xml_root is None:
             # Probably need to authenticate
-            start_page = self._login(webpage_url, video_id)
-            if start_page is None:
+            login_res = self._login(webpage_url, video_id)
+            if login_res is None:
                 self.report_warning('Could not login.')
             else:
+                start_page = login_res
                 # Grab the url from the authenticated page
-                xml_root = self._html_search_regex(r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', start_page, 'xml root')
+                xml_root = self._html_search_regex(
+                    r'<iframe src="(.*?)player.html.*?".*?</iframe>',
+                    start_page, 'xml root')
 
-        xml_name = self._html_search_regex(r'<iframe src=".*?\?xml=(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename', None, False)
+        xml_name = self._html_search_regex(
+            r'<iframe src=".*?\?xml=(.+?\.xml).*?".*?</iframe>',
+            start_page, 'xml filename', default=None)
         if xml_name is None:
             # Fallback to the older format
             xml_name = self._html_search_regex(r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename')

youtube_dl/extractor/generic.py

@@ -278,6 +278,17 @@ class GenericIE(InfoExtractor):
                 '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):
@@ -372,13 +383,13 @@ 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 = 'fixup_error'
 
-            if default_search in ('auto', 'auto_warning'):
+            if default_search in ('auto', 'auto_warning', 'fixup_error'):
                 if '/' in url:
                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
                     return self.url_result('http://' + url)
-                else:
+                elif default_search != 'fixup_error':
                     if default_search == 'auto_warning':
                         if re.match(r'^(?:url|URL)$', url):
                             raise ExtractorError(
@@ -386,8 +397,14 @@ 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)
+
+            if default_search in ('error', 'fixup_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)
@@ -609,6 +626,11 @@ 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)
@@ -676,6 +698,14 @@ class GenericIE(InfoExtractor):
             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/godtube.py

@@ -0,0 +1,58 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    parse_iso8601,
+)
+
+
+class GodTubeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?godtube\.com/watch/\?v=(?P<id>[\da-zA-Z]+)'
+    _TESTS = [
+        {
+            'url': 'https://www.godtube.com/watch/?v=0C0CNNNU',
+            'md5': '77108c1e4ab58f48031101a1a2119789',
+            'info_dict': {
+                'id': '0C0CNNNU',
+                'ext': 'mp4',
+                'title': 'Woman at the well.',
+                'duration': 159,
+                'timestamp': 1205712000,
+                'uploader': 'beverlybmusic',
+                'upload_date': '20080317',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        config = self._download_xml(
+            'http://www.godtube.com/resource/mediaplayer/%s.xml' % video_id.lower(),
+            video_id, 'Downloading player config XML')
+
+        video_url = config.find('.//file').text
+        uploader = config.find('.//author').text
+        timestamp = parse_iso8601(config.find('.//date').text)
+        duration = parse_duration(config.find('.//duration').text)
+        thumbnail = config.find('.//image').text
+
+        media = self._download_xml(
+            'http://www.godtube.com/media/xml/?v=%s' % video_id, video_id, 'Downloading media XML')
+
+        title = media.find('.//title').text
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'duration': duration,
+        }

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/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/izlesene.py

@@ -0,0 +1,97 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    get_element_by_id,
+    parse_iso8601,
+    determine_ext,
+    int_or_none,
+    str_to_int,
+)
+
+
+class IzleseneIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)'
+    _STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}'
+    _TEST = {
+        'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
+        'md5': '4384f9f0ea65086734b881085ee05ac2',
+        'info_dict': {
+            'id': '7599694',
+            'ext': 'mp4',
+            'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
+            'description': 'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor',
+            'thumbnail': 're:^http://.*\.jpg',
+            'uploader_id': 'pelikzzle',
+            'timestamp': 1404298698,
+            'upload_date': '20140702',
+            'duration': 95.395,
+            'age_limit': 0,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        url = 'http://www.izlesene.com/video/%s' % video_id
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        uploader = self._html_search_regex(
+            r"adduserUsername\s*=\s*'([^']+)';", webpage, 'uploader', fatal=False, default='')
+        timestamp = parse_iso8601(self._html_search_meta(
+            'uploadDate', webpage, 'upload date', fatal=False))
+
+        duration = int_or_none(self._html_search_regex(
+            r'"videoduration"\s*:\s*"([^"]+)"', webpage, 'duration', fatal=False))
+        if duration:
+            duration /= 1000.0
+
+        view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
+        comment_count = self._html_search_regex(
+            r'comment_count\s*=\s*\'([^\']+)\';', webpage, 'uploader', fatal=False)
+
+        family_friendly = self._html_search_meta(
+            'isFamilyFriendly', webpage, 'age limit', fatal=False)
+
+        content_url = self._html_search_meta(
+            'contentURL', webpage, 'content URL', fatal=False)
+        ext = determine_ext(content_url, 'mp4')
+
+        # Might be empty for some videos.
+        qualities = self._html_search_regex(
+            r'"quality"\s*:\s*"([^"]+)"', webpage, 'qualities', fatal=False, default='')
+
+        formats = []
+        for quality in qualities.split('|'):
+            json = self._download_json(
+                self._STREAM_URL.format(id=video_id, format=quality), video_id,
+                note='Getting video URL for "%s" quality' % quality,
+                errnote='Failed to get video URL for "%s" quality' % quality
+            )
+            formats.append({
+                'url': json.get('streamurl'),
+                'ext': ext,
+                'format_id': '%sp' % quality if quality else 'sd',
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader_id': uploader,
+            'timestamp': timestamp,
+            'duration': duration,
+            'view_count': int_or_none(view_count),
+            'comment_count': int_or_none(comment_count),
+            'age_limit': 18 if family_friendly == 'False' else 0,
+            'formats': formats,
+        }

youtube_dl/extractor/justintv.py

@@ -1,5 +1,6 @@
 from __future__ import unicode_literals
 
+import itertools
 import json
 import os
 import re
@@ -43,10 +44,11 @@ class JustinTVIE(InfoExtractor):
     }
 
     # Return count of items, list of *valid* items
-    def _parse_page(self, url, video_id):
-        info_json = self._download_webpage(url, video_id,
-                                           'Downloading video info JSON',
-                                           'unable to download video info JSON')
+    def _parse_page(self, url, video_id, counter):
+        info_json = self._download_webpage(
+            url, video_id,
+            'Downloading video info JSON on page %d' % counter,
+            'Unable to download video info JSON %d' % counter)
 
         response = json.loads(info_json)
         if type(response) != list:
@@ -138,11 +140,10 @@ class JustinTVIE(InfoExtractor):
         entries = []
         offset = 0
         limit = self._JUSTIN_PAGE_LIMIT
-        while True:
-            if paged:
-                self.report_download_page(video_id, offset)
+        for counter in itertools.count(1):
             page_url = api + ('?offset=%d&limit=%d' % (offset, limit))
-            page_count, page_info = self._parse_page(page_url, video_id)
+            page_count, page_info = self._parse_page(
+                page_url, video_id, counter)
             entries.extend(page_info)
             if not paged or page_count != limit:
                 break

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/krasview.py

@@ -0,0 +1,59 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unescapeHTML,
+)
+
+
+class KrasViewIE(InfoExtractor):
+    IE_DESC = 'Красвью'
+    _VALID_URL = r'https?://krasview\.ru/video/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://krasview.ru/video/512228',
+        'md5': '3b91003cf85fc5db277870c8ebd98eae',
+        'info_dict': {
+            'id': '512228',
+            'ext': 'mp4',
+            'title': 'Снег, лёд, заносы',
+            'description': 'Снято в городе Нягань, в Ханты-Мансийском автономном округе.',
+            'duration': 27,
+            'thumbnail': 're:^https?://.*\.jpg',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        flashvars = json.loads(self._search_regex(
+            r'flashvars\s*:\s*({.+?})\s*}\);', webpage, 'flashvars'))
+
+        video_url = flashvars['url']
+        title = unescapeHTML(flashvars['title'])
+        description = unescapeHTML(flashvars.get('subtitle') or self._og_search_description(webpage, default=None))
+        thumbnail = flashvars['image']
+        duration = int(flashvars['duration'])
+        filesize = int(flashvars['size'])
+        width = int_or_none(self._og_search_property('video:width', webpage, 'video width'))
+        height = int_or_none(self._og_search_property('video:height', webpage, 'video height'))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'filesize': filesize,
+            'width': width,
+            'height': height,
+        }

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

@@ -1,36 +1,109 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
 from .common import InfoExtractor
 from ..utils import (
+    compat_str,
     compat_urllib_parse_urlparse,
     compat_urlparse,
+    ExtractorError,
+    find_xpath_attr,
+    int_or_none,
+    orderedSet,
     xpath_with_ns,
 )
 
 
 class LivestreamIE(InfoExtractor):
-    IE_NAME = u'livestream'
+    IE_NAME = 'livestream'
     _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
     _TEST = {
-        u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
-        u'file': u'4719370.mp4',
-        u'md5': u'0d2186e3187d185a04b3cdd02b828836',
-        u'info_dict': {
-            u'title': u'Live from Webster Hall NYC',
-            u'upload_date': u'20121012',
+        'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
+        'md5': '53274c76ba7754fb0e8d072716f2292b',
+        'info_dict': {
+            'id': '4719370',
+            'ext': 'mp4',
+            'title': 'Live from Webster Hall NYC',
+            'upload_date': '20121012',
+            'like_count': int,
+            'view_count': int,
+            'thumbnail': 're:^http://.*\.jpg$'
         }
     }
 
+    def _parse_smil(self, video_id, smil_url):
+        formats = []
+        _SWITCH_XPATH = (
+            './/{http://www.w3.org/2001/SMIL20/Language}body/'
+            '{http://www.w3.org/2001/SMIL20/Language}switch')
+        smil_doc = self._download_xml(
+            smil_url, video_id,
+            note='Downloading SMIL information',
+            errnote='Unable to download SMIL information',
+            fatal=False)
+        if smil_doc is False:  # Download failed
+            return formats
+        title_node = find_xpath_attr(
+            smil_doc, './/{http://www.w3.org/2001/SMIL20/Language}meta',
+            'name', 'title')
+        if title_node is None:
+            self.report_warning('Cannot find SMIL id')
+            switch_node = smil_doc.find(_SWITCH_XPATH)
+        else:
+            title_id = title_node.attrib['content']
+            switch_node = find_xpath_attr(
+                smil_doc, _SWITCH_XPATH, 'id', title_id)
+        if switch_node is None:
+            raise ExtractorError('Cannot find switch node')
+        video_nodes = switch_node.findall(
+            '{http://www.w3.org/2001/SMIL20/Language}video')
+
+        for vn in video_nodes:
+            tbr = int_or_none(vn.attrib.get('system-bitrate'))
+            furl = (
+                'http://livestream-f.akamaihd.net/%s?v=3.0.3&fp=WIN%%2014,0,0,145' %
+                (vn.attrib['src']))
+            if 'clipBegin' in vn.attrib:
+                furl += '&ssek=' + vn.attrib['clipBegin']
+            formats.append({
+                'url': furl,
+                'format_id': 'smil_%d' % tbr,
+                'ext': 'flv',
+                'tbr': tbr,
+                'preference': -1000,
+            })
+        return formats
+
     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_id = compat_str(video_data['id'])
+
+        FORMAT_KEYS = (
+            ('sd', 'progressive_url'),
+            ('hd', 'progressive_url_hd'),
+        )
+        formats = [{
+            'format_id': format_id,
+            'url': video_data[key],
+            'quality': i + 1,
+        } for i, (format_id, key) in enumerate(FORMAT_KEYS)
+            if video_data.get(key)]
+
+        smil_url = video_data.get('smil_url')
+        if smil_url:
+            formats.extend(self._parse_smil(video_id, smil_url))
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': video_data['caption'],
+            'thumbnail': video_data.get('thumbnail_url'),
+            'upload_date': video_data['updated_at'].replace('-', '')[:8],
+            'like_count': video_data.get('likes', {}).get('total'),
+            'view_count': video_data.get('views'),
+        }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -40,43 +113,44 @@ 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 +158,7 @@ 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 +168,44 @@ 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)
@@ -136,10 +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')]
 
@@ -154,12 +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/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

@@ -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',
@@ -141,4 +141,4 @@ class NRKTVIE(InfoExtractor):
             'upload_date': upload_date,
             'duration': duration,
             'formats': formats,
-        }
+        }

youtube_dl/extractor/pbs.py

@@ -32,13 +32,21 @@ class PBSIE(InfoExtractor):
         },
     }
 
-    def _real_extract(self, url):
+    def _extract_ids(self, url):
         mobj = re.match(self._VALID_URL, url)
 
         presumptive_id = mobj.group('presumptive_id')
         display_id = presumptive_id
         if presumptive_id:
             webpage = self._download_webpage(url, display_id)
+
+            # frontline video embed
+            media_id = self._search_regex(
+                r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",
+                webpage, 'frontline video ID', fatal=False, default=None)
+            if media_id:
+                return media_id, presumptive_id
+
             url = self._search_regex(
                 r'<iframe\s+id=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
                 webpage, 'player URL')
@@ -57,6 +65,11 @@ class PBSIE(InfoExtractor):
             video_id = mobj.group('id')
             display_id = video_id
 
+        return video_id, display_id
+
+    def _real_extract(self, url):
+        video_id, display_id = self._extract_ids(url)
+
         info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
         info = self._download_json(info_url, display_id)
 

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/shared.py

@@ -0,0 +1,57 @@
+from __future__ import unicode_literals
+
+import re
+import base64
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_request,
+    compat_urllib_parse,
+    int_or_none,
+)
+
+
+class SharedIE(InfoExtractor):
+    _VALID_URL = r'http://shared\.sx/(?P<id>[\da-z]{10})'
+
+    _TEST = {
+        'url': 'http://shared.sx/0060718775',
+        'md5': '53e1c58fc3e777ae1dfe9e57ba2f9c72',
+        'info_dict': {
+            'id': '0060718775',
+            'ext': 'mp4',
+            'title': 'Big Buck Bunny Trailer',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id)
+
+        if re.search(r'>File does not exist<', page) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+        download_form = dict(re.findall(r'<input type="hidden" name="([^"]+)" value="([^"]*)"', page))
+
+        request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(download_form))
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+
+        video_page = self._download_webpage(request, video_id, 'Downloading video page')
+
+        video_url = self._html_search_regex(r'data-url="([^"]+)"', video_page, 'video URL')
+        title = base64.b64decode(self._html_search_meta('full:title', page, 'title')).decode('utf-8')
+        filesize = int_or_none(self._html_search_meta('full:size', page, 'file size', fatal=False))
+        thumbnail = self._html_search_regex(
+            r'data-poster="([^"]+)"', video_page, 'thumbnail', fatal=False, default=None)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'filesize': filesize,
+            'title': title,
+            'thumbnail': thumbnail,
+        }

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

@@ -81,16 +81,16 @@ class SoundcloudIE(InfoExtractor):
         },
         # 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',
-                #'duration': 42,
+                'id': '128590877',
+                'ext': 'mp3',
+                'title': 'Bus Brakes',
+                'description': 'md5:0170be75dd395c96025d210d261c784e',
+                'uploader': 'oddsamples',
+                'upload_date': '20140109',
+                'duration': 17,
             },
         },
     ]
@@ -255,7 +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
@@ -264,24 +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/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/streamcloud.py

@@ -1,4 +1,6 @@
 # coding: utf-8
+from __future__ import unicode_literals
+
 import re
 import time
 
@@ -10,18 +12,18 @@ from ..utils import (
 
 
 class StreamcloudIE(InfoExtractor):
-    IE_NAME = u'streamcloud.eu'
+    IE_NAME = 'streamcloud.eu'
     _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)/(?P<fname>[^#?]*)\.html'
 
     _TEST = {
-        u'url': u'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html',
-        u'file': u'skp9j99s4bpz.mp4',
-        u'md5': u'6bea4c7fa5daaacc2a946b7146286686',
-        u'info_dict': {
-            u'title': u'youtube-dl test video  \'/\\ ä ↭',
-            u'duration': 9,
+        'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html',
+        'md5': '6bea4c7fa5daaacc2a946b7146286686',
+        'info_dict': {
+            'id': 'skp9j99s4bpz',
+            'ext': 'mp4',
+            'title': 'youtube-dl test video  \'/\\ ä ↭',
         },
-        u'skip': u'Only available from the EU'
+        'skip': 'Only available from the EU'
     }
 
     def _real_extract(self, url):
@@ -46,21 +48,17 @@ class StreamcloudIE(InfoExtractor):
         req = compat_urllib_request.Request(url, post, headers)
 
         webpage = self._download_webpage(
-            req, video_id, note=u'Downloading video page ...')
+            req, video_id, note='Downloading video page ...')
         title = self._html_search_regex(
-            r'<h1[^>]*>([^<]+)<', webpage, u'title')
+            r'<h1[^>]*>([^<]+)<', webpage, 'title')
         video_url = self._search_regex(
-            r'file:\s*"([^"]+)"', webpage, u'video URL')
-        duration_str = self._search_regex(
-            r'duration:\s*"?([0-9]+)"?', webpage, u'duration', fatal=False)
-        duration = None if duration_str is None else int(duration_str)
+            r'file:\s*"([^"]+)"', webpage, 'video URL')
         thumbnail = self._search_regex(
-            r'image:\s*"([^"]+)"', webpage, u'thumbnail URL', fatal=False)
+            r'image:\s*"([^"]+)"', webpage, 'thumbnail URL', fatal=False)
 
         return {
             'id': video_id,
             'title': title,
             'url': video_url,
-            'duration': duration,
             'thumbnail': thumbnail,
         }

youtube_dl/extractor/swrmediathek.py

@@ -8,7 +8,7 @@ from ..utils import parse_duration
 
 
 class SWRMediathekIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?swrmediathek\.de/player\.htm\?show=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
+    _VALID_URL = r'https?://(?:www\.)?swrmediathek\.de/(?:content/)?player\.htm\?show=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
 
     _TESTS = [{
         'url': 'http://swrmediathek.de/player.htm?show=849790d0-dab8-11e3-a953-0026b975f2e6',
@@ -52,6 +52,20 @@ class SWRMediathekIE(InfoExtractor):
             'uploader': 'SWR 2',
             'uploader_id': '284670',
         }
+    }, {
+        'url': 'http://swrmediathek.de/content/player.htm?show=52dc7e00-15c5-11e4-84bc-0026b975f2e6',
+        'md5': '881531487d0633080a8cc88d31ef896f',
+        'info_dict': {
+            'id': '52dc7e00-15c5-11e4-84bc-0026b975f2e6',
+            'ext': 'mp4',
+            'title': 'Familienspaß am Bodensee',
+            'description': 'md5:0b591225a32cfde7be1629ed49fe4315',
+            'thumbnail': 're:http://.*\.jpg',
+            'duration': 1784,
+            'upload_date': '20140727',
+            'uploader': 'SWR Fernsehen BW',
+            'uploader_id': '281130',
+        }
     }]
 
     def _real_extract(self, url):