release 2014.09.12

On 2.x, we now try TLS first, and fall back to the compat 23 (basically anything) afterwards.
On 3.4+, we now use the proper function so that we get all the latest security configurations.
We allow SSLv3 though for the time being, since a lot of older pages use that.
On 3.3, we default to SSLv23 (basically "anything, including TLS") because that has the widest compatibility.

.gitignore

@@ -26,5 +26,6 @@ updates_key.pem
 *.m4a
 *.m4v
 *.part
+*.swp
 test/testdata
 .tox

README.md

@@ -255,6 +255,7 @@ which means you can modify it, redistribute it or use it however you like.
 ## Authentication Options:
     -u, --username USERNAME          account username
     -p, --password PASSWORD          account password
+    -2, --twofactor TWOFACTOR        two-factor auth code
     -n, --netrc                      use .netrc authentication data
     --video-password PASSWORD        video password (vimeo, smotri)
 
@@ -287,6 +288,10 @@ which means you can modify it, redistribute it or use it however you like.
                                      postprocessors (default)
     --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
                                      postprocessors
+    --exec CMD                       Execute a command on the file after
+                                     downloading, similar to find's -exec
+                                     syntax. Example: --exec 'adb push {}
+                                     /sdcard/Music/ && rm {}'
 
 # CONFIGURATION
 

test/helper.py

@@ -102,7 +102,11 @@ def expect_info_dict(self, expected_dict, got_dict):
             match_rex = re.compile(match_str)
 
             self.assertTrue(
-                isinstance(got, compat_str) and match_rex.match(got),
+                isinstance(got, compat_str),
+                u'Expected a %s object, but got %s for field %s' % (
+                    compat_str.__name__, type(got).__name__, info_field))
+            self.assertTrue(
+                match_rex.match(got),
                 u'field %s (value: %r) should match %r' % (info_field, got, match_str))
         elif isinstance(expected, type):
             got = got_dict.get(info_field)

test/parameters.json

@@ -27,7 +27,6 @@
     "rejecttitle": null, 
     "retries": 10, 
     "simulate": false, 
-    "skip_download": false, 
     "subtitleslang": null, 
     "subtitlesformat": "srt",
     "test": true, 

test/test_all_urls.py

@@ -109,7 +109,9 @@ class TestAllURLsMatching(unittest.TestCase):
                 if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
                     self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
                 else:
-                    self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url))
+                    self.assertFalse(
+                        ie.suitable(url),
+                        '%s should not match URL %r . That URL belongs to %s.' % (type(ie).__name__, url, tc['name']))
 
     def test_keywords(self):
         self.assertMatch(':ytsubs', ['youtube:subscriptions'])
@@ -141,32 +143,6 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
         self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])
 
-    def test_ComedyCentralShows(self):
-        self.assertMatch(
-            'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
-            ['ComedyCentralShows'])
-
     def test_yahoo_https(self):
         # https://github.com/rg3/youtube-dl/issues/2701
         self.assertMatch(

test/test_cache.py

@@ -0,0 +1,59 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+import shutil
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+from test.helper import FakeYDL
+from youtube_dl.cache import Cache
+
+
+def _is_empty(d):
+    return not bool(os.listdir(d))
+
+
+def _mkdir(d):
+    if not os.path.exists(d):
+        os.mkdir(d)
+
+
+class TestCache(unittest.TestCase):
+    def setUp(self):
+        TEST_DIR = os.path.dirname(os.path.abspath(__file__))
+        TESTDATA_DIR = os.path.join(TEST_DIR, 'testdata')
+        _mkdir(TESTDATA_DIR)
+        self.test_dir = os.path.join(TESTDATA_DIR, 'cache_test')
+        self.tearDown()
+
+    def tearDown(self):
+        if os.path.exists(self.test_dir):
+            shutil.rmtree(self.test_dir)
+
+    def test_cache(self):
+        ydl = FakeYDL({
+            'cachedir': self.test_dir,
+        })
+        c = Cache(ydl)
+        obj = {'x': 1, 'y': ['ä', '\\a', True]}
+        self.assertEqual(c.load('test_cache', 'k.'), None)
+        c.store('test_cache', 'k.', obj)
+        self.assertEqual(c.load('test_cache', 'k2'), None)
+        self.assertFalse(_is_empty(self.test_dir))
+        self.assertEqual(c.load('test_cache', 'k.'), obj)
+        self.assertEqual(c.load('test_cache', 'y'), None)
+        self.assertEqual(c.load('test_cache2', 'k.'), None)
+        c.remove()
+        self.assertFalse(os.path.exists(self.test_dir))
+        self.assertEqual(c.load('test_cache', 'k.'), None)
+
+
+if __name__ == '__main__':
+    unittest.main()

test/test_download.py

@@ -7,6 +7,7 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
+    assertGreaterEqual,
     get_params,
     gettestcases,
     expect_info_dict,
@@ -27,6 +28,7 @@ from youtube_dl.utils import (
     compat_HTTPError,
     DownloadError,
     ExtractorError,
+    format_bytes,
     UnavailableVideoError,
 )
 from youtube_dl.extractor import get_info_extractor
@@ -102,8 +104,11 @@ def generator(test_case):
         def get_tc_filename(tc):
             return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
 
-        def try_rm_tcs_files():
-            for tc in test_cases:
+        res_dict = None
+        def try_rm_tcs_files(tcs=None):
+            if tcs is None:
+                tcs = test_cases
+            for tc in tcs:
                 tc_filename = get_tc_filename(tc)
                 try_rm(tc_filename)
                 try_rm(tc_filename + '.part')
@@ -136,29 +141,58 @@ def generator(test_case):
                 self.assertEqual(res_dict['_type'], 'playlist')
                 expect_info_dict(self, test_case.get('info_dict', {}), res_dict)
             if 'playlist_mincount' in test_case:
-                self.assertGreaterEqual(
+                assertGreaterEqual(
+                    self,
                     len(res_dict['entries']),
                     test_case['playlist_mincount'],
                     'Expected at least %d in playlist %s, but got only %d' % (
                         test_case['playlist_mincount'], test_case['url'],
                         len(res_dict['entries'])))
+            if 'playlist_count' in test_case:
+                self.assertEqual(
+                    len(res_dict['entries']),
+                    test_case['playlist_count'],
+                    'Expected %d entries in playlist %s, but got %d.' % (
+                        test_case['playlist_count'],
+                        test_case['url'],
+                        len(res_dict['entries']),
+                    ))
+            if 'playlist_duration_sum' in test_case:
+                got_duration = sum(e['duration'] for e in res_dict['entries'])
+                self.assertEqual(
+                    test_case['playlist_duration_sum'], got_duration)
 
             for tc in test_cases:
                 tc_filename = get_tc_filename(tc)
                 if not test_case.get('params', {}).get('skip_download', False):
                     self.assertTrue(os.path.exists(tc_filename), msg='Missing file ' + tc_filename)
                     self.assertTrue(tc_filename in finished_hook_called)
+                    expected_minsize = tc.get('file_minsize', 10000)
+                    if expected_minsize is not None:
+                        if params.get('test'):
+                            expected_minsize = max(expected_minsize, 10000)
+                        got_fsize = os.path.getsize(tc_filename)
+                        assertGreaterEqual(
+                            self, got_fsize, expected_minsize,
+                            'Expected %s to be at least %s, but it\'s only %s ' %
+                            (tc_filename, format_bytes(expected_minsize),
+                                format_bytes(got_fsize)))
+                    if 'md5' in tc:
+                        md5_for_file = _file_md5(tc_filename)
+                        self.assertEqual(md5_for_file, tc['md5'])
                 info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
                 self.assertTrue(os.path.exists(info_json_fn))
-                if 'md5' in tc:
-                    md5_for_file = _file_md5(tc_filename)
-                    self.assertEqual(md5_for_file, tc['md5'])
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
 
                 expect_info_dict(self, tc.get('info_dict', {}), info_dict)
         finally:
             try_rm_tcs_files()
+            if is_playlist and res_dict is not None:
+                # Remove all other files that may have been extracted if the
+                # extractor returns full results even with extract_flat
+                res_tcs = [{'info_dict': e} for e in res_dict['entries']]
+                try_rm_tcs_files(res_tcs)
 
     return test_template
 

test/test_playlists.py

@@ -1,411 +0,0 @@
-#!/usr/bin/env python
-# encoding: utf-8
-
-## DEPRECATED FILE!
-# Add new tests to the extractors themselves, like this:
-# _TEST = {
-#    'url': 'http://example.com/playlist/42',
-#    'playlist_mincount': 99,
-#    'info_dict': {
-#        'id': '42',
-#        'title': 'Playlist number forty-two',
-#    }
-# }
-
-from __future__ import unicode_literals
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from test.helper import (
-    assertRegexpMatches,
-    assertGreaterEqual,
-    expect_info_dict,
-    FakeYDL,
-)
-
-from youtube_dl.extractor import (
-    AcademicEarthCourseIE,
-    DailymotionPlaylistIE,
-    DailymotionUserIE,
-    VimeoChannelIE,
-    VimeoUserIE,
-    VimeoAlbumIE,
-    VimeoGroupsIE,
-    VineUserIE,
-    UstreamChannelIE,
-    SoundcloudSetIE,
-    SoundcloudUserIE,
-    SoundcloudPlaylistIE,
-    TeacherTubeUserIE,
-    LivestreamIE,
-    LivestreamOriginalIE,
-    NHLVideocenterIE,
-    BambuserChannelIE,
-    BandcampAlbumIE,
-    SmotriCommunityIE,
-    SmotriUserIE,
-    IviCompilationIE,
-    ImdbListIE,
-    KhanAcademyIE,
-    EveryonesMixtapeIE,
-    RutubeChannelIE,
-    RutubePersonIE,
-    GoogleSearchIE,
-    GenericIE,
-    TEDIE,
-    ToypicsUserIE,
-    XTubeUserIE,
-    InstagramUserIE,
-    CSpanIE,
-    AolIE,
-)
-
-
-class TestPlaylists(unittest.TestCase):
-    def assertIsPlaylist(self, info):
-        """Make sure the info has '_type' set to 'playlist'"""
-        self.assertEqual(info['_type'], 'playlist')
-
-    def test_dailymotion_playlist(self):
-        dl = FakeYDL()
-        ie = DailymotionPlaylistIE(dl)
-        result = ie.extract('http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'SPORT')
-        self.assertTrue(len(result['entries']) > 20)
-
-    def test_dailymotion_user(self):
-        dl = FakeYDL()
-        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')
-
-    def test_vimeo_channel(self):
-        dl = FakeYDL()
-        ie = VimeoChannelIE(dl)
-        result = ie.extract('http://vimeo.com/channels/tributes')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Vimeo Tributes')
-        self.assertTrue(len(result['entries']) > 24)
-
-    def test_vimeo_user(self):
-        dl = FakeYDL()
-        ie = VimeoUserIE(dl)
-        result = ie.extract('http://vimeo.com/nkistudio/videos')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Nki')
-        self.assertTrue(len(result['entries']) > 65)
-
-    def test_vimeo_album(self):
-        dl = FakeYDL()
-        ie = VimeoAlbumIE(dl)
-        result = ie.extract('http://vimeo.com/album/2632481')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Staff Favorites: November 2013')
-        self.assertTrue(len(result['entries']) > 12)
-
-    def test_vimeo_groups(self):
-        dl = FakeYDL()
-        ie = VimeoGroupsIE(dl)
-        result = ie.extract('http://vimeo.com/groups/rolexawards')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Rolex Awards for Enterprise')
-        self.assertTrue(len(result['entries']) > 72)
-
-    def test_vine_user(self):
-        dl = FakeYDL()
-        ie = VineUserIE(dl)
-        result = ie.extract('https://vine.co/Visa')
-        self.assertIsPlaylist(result)
-        assertGreaterEqual(self, len(result['entries']), 47)
-
-    def test_ustream_channel(self):
-        dl = FakeYDL()
-        ie = UstreamChannelIE(dl)
-        result = ie.extract('http://www.ustream.tv/channel/channeljapan')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '10874166')
-        assertGreaterEqual(self, len(result['entries']), 54)
-
-    def test_soundcloud_set(self):
-        dl = FakeYDL()
-        ie = SoundcloudSetIE(dl)
-        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')
-        assertGreaterEqual(self, len(result['entries']), 6)
-
-    def test_soundcloud_user(self):
-        dl = FakeYDL()
-        ie = SoundcloudUserIE(dl)
-        result = ie.extract('https://soundcloud.com/the-concept-band')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '9615865')
-        assertGreaterEqual(self, len(result['entries']), 12)
-
-    def test_soundcloud_likes(self):
-        dl = FakeYDL()
-        ie = SoundcloudUserIE(dl)
-        result = ie.extract('https://soundcloud.com/the-concept-band/likes')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '9615865')
-        assertGreaterEqual(self, len(result['entries']), 1)
-
-    def test_soundcloud_playlist(self):
-        dl = FakeYDL()
-        ie = SoundcloudPlaylistIE(dl)
-        result = ie.extract('http://api.soundcloud.com/playlists/4110309')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '4110309')
-        self.assertEqual(result['title'], 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]')
-        assertRegexpMatches(
-            self, result['description'], r'.*?TILT Brass - Bowery Poetry Club')
-        self.assertEqual(len(result['entries']), 6)
-
-    def test_livestream_event(self):
-        dl = FakeYDL()
-        ie = LivestreamIE(dl)
-        result = ie.extract('http://new.livestream.com/tedx/cityenglish')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'TEDCity2.0 (English)')
-        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()
-        ie = NHLVideocenterIE(dl)
-        result = ie.extract('http://video.canucks.nhl.com/videocenter/console?catid=999')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '999')
-        self.assertEqual(result['title'], 'Highlights')
-        self.assertEqual(len(result['entries']), 12)
-
-    def test_bambuser_channel(self):
-        dl = FakeYDL()
-        ie = BambuserChannelIE(dl)
-        result = ie.extract('http://bambuser.com/channel/pixelversity')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'pixelversity')
-        assertGreaterEqual(self, len(result['entries']), 60)
-
-    def test_bandcamp_album(self):
-        dl = FakeYDL()
-        ie = BandcampAlbumIE(dl)
-        result = ie.extract('http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Hierophany of the Open Grave')
-        assertGreaterEqual(self, len(result['entries']), 9)
-        
-    def test_smotri_community(self):
-        dl = FakeYDL()
-        ie = SmotriCommunityIE(dl)
-        result = ie.extract('http://smotri.com/community/video/kommuna')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'kommuna')
-        self.assertEqual(result['title'], 'КПРФ')
-        assertGreaterEqual(self, len(result['entries']), 4)
-        
-    def test_smotri_user(self):
-        dl = FakeYDL()
-        ie = SmotriUserIE(dl)
-        result = ie.extract('http://smotri.com/user/inspector')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'inspector')
-        self.assertEqual(result['title'], 'Inspector')
-        assertGreaterEqual(self, len(result['entries']), 9)
-
-    def test_AcademicEarthCourse(self):
-        dl = FakeYDL()
-        ie = AcademicEarthCourseIE(dl)
-        result = ie.extract('http://academicearth.org/playlists/laws-of-nature/')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'laws-of-nature')
-        self.assertEqual(result['title'], 'Laws of Nature')
-        self.assertEqual(result['description'],u'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.')# u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
-        self.assertEqual(len(result['entries']), 4)
-        
-    def test_ivi_compilation(self):
-        dl = FakeYDL()
-        ie = IviCompilationIE(dl)
-        result = ie.extract('http://www.ivi.ru/watch/dvoe_iz_lartsa')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'dvoe_iz_lartsa')
-        self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008)')
-        assertGreaterEqual(self, len(result['entries']), 24)
-
-    def test_ivi_compilation_season(self):
-        dl = FakeYDL()
-        ie = IviCompilationIE(dl)
-        result = ie.extract('http://www.ivi.ru/watch/dvoe_iz_lartsa/season1')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'dvoe_iz_lartsa/season1')
-        self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008) 1 сезон')
-        assertGreaterEqual(self, len(result['entries']), 12)
-        
-    def test_imdb_list(self):
-        dl = FakeYDL()
-        ie = ImdbListIE(dl)
-        result = ie.extract('http://www.imdb.com/list/JFs9NWw6XI0')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'JFs9NWw6XI0')
-        self.assertEqual(result['title'], 'March 23, 2012 Releases')
-        self.assertEqual(len(result['entries']), 7)
-
-    def test_khanacademy_topic(self):
-        dl = FakeYDL()
-        ie = KhanAcademyIE(dl)
-        result = ie.extract('https://www.khanacademy.org/math/applied-math/cryptography')
-        self.assertIsPlaylist(result)
-        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?')
-        assertGreaterEqual(self, len(result['entries']), 3)
-
-    def test_EveryonesMixtape(self):
-        dl = FakeYDL()
-        ie = EveryonesMixtapeIE(dl)
-        result = ie.extract('http://everyonesmixtape.com/#/mix/m7m0jJAbMQi')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'm7m0jJAbMQi')
-        self.assertEqual(result['title'], 'Driving')
-        self.assertEqual(len(result['entries']), 24)
-        
-    def test_rutube_channel(self):
-        dl = FakeYDL()
-        ie = RutubeChannelIE(dl)
-        result = ie.extract('http://rutube.ru/tags/video/1800/')
-        self.assertIsPlaylist(result)
-        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
-        dl = FakeYDL()
-        ie = GenericIE(dl)
-        result = ie.extract('http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'always-never-nuclear-command-and-control')
-        self.assertEqual(result['title'], 'Always/Never: A Little-Seen Movie About Nuclear Command and Control : The New Yorker')
-        self.assertEqual(len(result['entries']), 3)
-
-    def test_GoogleSearch(self):
-        dl = FakeYDL()
-        ie = GoogleSearchIE(dl)
-        result = ie.extract('gvsearch15:python language')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'python language')
-        self.assertEqual(result['title'], 'python language')
-        self.assertEqual(len(result['entries']), 15)
-
-    def test_generic_rss_feed(self):
-        dl = FakeYDL()
-        ie = GenericIE(dl)
-        result = ie.extract('http://phihag.de/2014/youtube-dl/rss.xml')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'http://phihag.de/2014/youtube-dl/rss.xml')
-        self.assertEqual(result['title'], 'Zero Punctuation')
-        self.assertTrue(len(result['entries']) > 10)
-
-    def test_ted_playlist(self):
-        dl = FakeYDL()
-        ie = TEDIE(dl)
-        result = ie.extract('http://www.ted.com/playlists/who_are_the_hackers')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '10')
-        self.assertEqual(result['title'], 'Who are the hackers?')
-        assertGreaterEqual(self, len(result['entries']), 6)
-
-    def test_toypics_user(self):
-        dl = FakeYDL()
-        ie = ToypicsUserIE(dl)
-        result = ie.extract('http://videos.toypics.net/Mikey')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'Mikey')
-        assertGreaterEqual(self, len(result['entries']), 17)
-
-    def test_xtube_user(self):
-        dl = FakeYDL()
-        ie = XTubeUserIE(dl)
-        result = ie.extract('http://www.xtube.com/community/profile.php?user=greenshowers')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'greenshowers')
-        assertGreaterEqual(self, len(result['entries']), 155)
-
-    def test_InstagramUser(self):
-        dl = FakeYDL()
-        ie = InstagramUserIE(dl)
-        result = ie.extract('http://instagram.com/porsche')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'porsche')
-        assertGreaterEqual(self, len(result['entries']), 2)
-        test_video = next(
-            e for e in result['entries']
-            if e['id'] == '614605558512799803_462752227')
-        dl.add_default_extra_info(test_video, ie, '(irrelevant URL)')
-        dl.process_video_result(test_video, download=False)
-        EXPECTED = {
-            'id': '614605558512799803_462752227',
-            'ext': 'mp4',
-            'title': '#Porsche Intelligent Performance.',
-            'thumbnail': 're:^https?://.*\.jpg',
-            'uploader': 'Porsche',
-            'uploader_id': 'porsche',
-            'timestamp': 1387486713,
-            'upload_date': '20131219',
-        }
-        expect_info_dict(self, EXPECTED, test_video)
-
-    def test_CSpan_playlist(self):
-        dl = FakeYDL()
-        ie = CSpanIE(dl)
-        result = ie.extract(
-            'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '342759')
-        self.assertEqual(
-            result['title'], 'General Motors Ignition Switch Recall')
-        whole_duration = sum(e['duration'] for e in result['entries'])
-        self.assertEqual(whole_duration, 14855)
-
-    def test_aol_playlist(self):
-        dl = FakeYDL()
-        ie = AolIE(dl)
-        result = ie.extract(
-            'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '152147')
-        self.assertEqual(
-            result['title'], 'Brace Yourself - Today\'s Weirdest News')
-        assertGreaterEqual(self, len(result['entries']), 10)
-
-    def test_TeacherTubeUser(self):
-        dl = FakeYDL()
-        ie = TeacherTubeUserIE(dl)
-        result = ie.extract('http://www.teachertube.com/user/profile/rbhagwati2')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'rbhagwati2')
-        assertGreaterEqual(self, len(result['entries']), 179)
-
-if __name__ == '__main__':
-    unittest.main()

test/test_utils.py

@@ -1,6 +1,8 @@
 #!/usr/bin/env python
 # coding: utf-8
 
+from __future__ import unicode_literals
+
 # Allow direct execution
 import os
 import sys
@@ -13,7 +15,6 @@ import io
 import json
 import xml.etree.ElementTree
 
-#from youtube_dl.utils import htmlentity_transform
 from youtube_dl.utils import (
     DateRange,
     encodeFilename,
@@ -41,11 +42,6 @@ from youtube_dl.utils import (
     uppercase_escape,
 )
 
-if sys.version_info < (3, 0):
-    _compat_str = lambda b: b.decode('unicode-escape')
-else:
-    _compat_str = lambda s: s
-
 
 class TestUtil(unittest.TestCase):
     def test_timeconvert(self):
@@ -67,9 +63,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual('this - that', sanitize_filename('this: that'))
 
         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
-        aumlaut = _compat_str('\xe4')
+        aumlaut = 'ä'
         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
-        tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
+        tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
         self.assertEqual(sanitize_filename(tests), tests)
 
         forbidden = '"\0\\/'
@@ -91,9 +87,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
 
-        tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
+        tests = 'a\xe4b\u4e2d\u56fd\u7684c'
         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
-        self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '')  # No empty filename
+        self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
 
         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
         for fc in forbidden:
@@ -101,8 +97,8 @@ class TestUtil(unittest.TestCase):
                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
 
         # Handle a common case more neatly
-        self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
-        self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
+        self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
+        self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
         # .. but make sure the file name is never empty
         self.assertTrue(sanitize_filename('-', restricted=True) != '')
         self.assertTrue(sanitize_filename(':', restricted=True) != '')
@@ -120,7 +116,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 
     def test_unescape_html(self):
-        self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
+        self.assertEqual(unescapeHTML('%20;'), '%20;')
+        self.assertEqual(
+            unescapeHTML('&eacute;'), 'é')
         
     def test_daterange(self):
         _20century = DateRange("19000101","20000101")
@@ -138,7 +136,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 
     def test_find_xpath_attr(self):
-        testxml = u'''<root>
+        testxml = '''<root>
             <node/>
             <node x="a"/>
             <node x="a" y="c" />
@@ -151,18 +149,18 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 
     def test_meta_parser(self):
-        testhtml = u'''
+        testhtml = '''
         <head>
             <meta name="description" content="foo &amp; bar">
             <meta content='Plato' name='author'/>
         </head>
         '''
         get_meta = lambda name: get_meta_content(name, testhtml)
-        self.assertEqual(get_meta('description'), u'foo & bar')
+        self.assertEqual(get_meta('description'), 'foo & bar')
         self.assertEqual(get_meta('author'), 'Plato')
 
     def test_xpath_with_ns(self):
-        testxml = u'''<root xmlns:media="http://example.com/">
+        testxml = '''<root xmlns:media="http://example.com/">
             <media:song>
                 <media:author>The Author</media:author>
                 <url>http://server.com/download.mp3</url>
@@ -171,8 +169,8 @@ class TestUtil(unittest.TestCase):
         doc = xml.etree.ElementTree.fromstring(testxml)
         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
         self.assertTrue(find('media:song') is not None)
-        self.assertEqual(find('media:song/media:author').text, u'The Author')
-        self.assertEqual(find('media:song/url').text, u'http://server.com/download.mp3')
+        self.assertEqual(find('media:song/media:author').text, 'The Author')
+        self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 
     def test_smuggle_url(self):
         data = {u"ö": u"ö", u"abc": [3]}
@@ -187,22 +185,22 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(res_data, None)
 
     def test_shell_quote(self):
-        args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')]
-        self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""")
+        args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
+        self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 
     def test_str_to_int(self):
         self.assertEqual(str_to_int('123,456'), 123456)
         self.assertEqual(str_to_int('123.456'), 123456)
 
     def test_url_basename(self):
-        self.assertEqual(url_basename(u'http://foo.de/'), u'')
-        self.assertEqual(url_basename(u'http://foo.de/bar/baz'), u'baz')
-        self.assertEqual(url_basename(u'http://foo.de/bar/baz?x=y'), u'baz')
-        self.assertEqual(url_basename(u'http://foo.de/bar/baz#x=y'), u'baz')
-        self.assertEqual(url_basename(u'http://foo.de/bar/baz/'), u'baz')
+        self.assertEqual(url_basename('http://foo.de/'), '')
+        self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
+        self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
+        self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
+        self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
         self.assertEqual(
-            url_basename(u'http://media.w3.org/2010/05/sintel/trailer.mp4'),
-            u'trailer.mp4')
+            url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
+            'trailer.mp4')
 
     def test_parse_duration(self):
         self.assertEqual(parse_duration(None), None)
@@ -213,12 +211,16 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('00:01:01'), 61)
         self.assertEqual(parse_duration('x:y'), None)
         self.assertEqual(parse_duration('3h11m53s'), 11513)
+        self.assertEqual(parse_duration('3h 11m 53s'), 11513)
+        self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
+        self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
         self.assertEqual(parse_duration('62m45s'), 3765)
         self.assertEqual(parse_duration('6m59s'), 419)
         self.assertEqual(parse_duration('49s'), 49)
         self.assertEqual(parse_duration('0h0m0s'), 0)
         self.assertEqual(parse_duration('0m0s'), 0)
         self.assertEqual(parse_duration('0s'), 0)
+        self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -255,16 +257,16 @@ class TestUtil(unittest.TestCase):
         testPL(5, 2, (20, 99), [])
 
     def test_struct_unpack(self):
-        self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,))
+        self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
 
     def test_read_batch_urls(self):
-        f = io.StringIO(u'''\xef\xbb\xbf foo
+        f = io.StringIO('''\xef\xbb\xbf foo
             bar\r
             baz
             # More after this line\r
             ; or after this
             bam''')
-        self.assertEqual(read_batch_urls(f), [u'foo', u'bar', u'baz', u'bam'])
+        self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
 
     def test_urlencode_postdata(self):
         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
@@ -281,8 +283,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(d, [{"id": "532cb", "x": 3}])
 
     def test_uppercase_escape(self):
-        self.assertEqual(uppercase_escape(u'aä'), u'aä')
-        self.assertEqual(uppercase_escape(u'\\U0001d550'), u'𝕐')
+        self.assertEqual(uppercase_escape('aä'), 'aä')
+        self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
 
 if __name__ == '__main__':
     unittest.main()

youtube_dl/YoutubeDL.py

@@ -57,6 +57,7 @@ from .utils import (
     YoutubeDLHandler,
     prepend_extension,
 )
+from .cache import Cache
 from .extractor import get_info_extractor, gen_extractors
 from .downloader import get_suitable_downloader
 from .postprocessor import FFmpegMergerPP
@@ -133,7 +134,7 @@ class YoutubeDL(object):
     daterange:         A DateRange object, download only if the upload_date is in the range.
     skip_download:     Skip the actual download of the video file
     cachedir:          Location of the cache files in the filesystem.
-                       None to disable filesystem cache.
+                       False to disable filesystem cache.
     noplaylist:        Download single video instead of a playlist if in doubt.
     age_limit:         An integer representing the user's age in years.
                        Unsuitable videos for the given age are skipped.
@@ -172,6 +173,7 @@ class YoutubeDL(object):
     The following options are used by the post processors:
     prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
                        otherwise prefer avconv.
+    exec_cmd:          Arbitrary command to run after downloading
     """
 
     params = None
@@ -194,6 +196,7 @@ class YoutubeDL(object):
         self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
         self._err_file = sys.stderr
         self.params = params
+        self.cache = Cache(self)
 
         if params.get('bidi_workaround', False):
             try:
@@ -424,7 +427,7 @@ class YoutubeDL(object):
             autonumber_templ = '%0' + str(autonumber_size) + 'd'
             template_dict['autonumber'] = autonumber_templ % self._num_downloads
             if template_dict.get('playlist_index') is not None:
-                template_dict['playlist_index'] = '%05d' % template_dict['playlist_index']
+                template_dict['playlist_index'] = '%0*d' % (len(str(template_dict['n_entries'])), template_dict['playlist_index'])
             if template_dict.get('resolution') is None:
                 if template_dict.get('width') and template_dict.get('height'):
                     template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height'])
@@ -636,6 +639,7 @@ class YoutubeDL(object):
             for i, entry in enumerate(entries, 1):
                 self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries))
                 extra = {
+                    'n_entries': n_entries,
                     'playlist': playlist,
                     'playlist_index': i + playliststart,
                     'extractor': ie_result['extractor'],

youtube_dl/__init__.py

@@ -72,6 +72,9 @@ __authors__  = (
     'Alexander Kirk',
     'Erik Johnson',
     'Keith Beckman',
+    'Ole Ernst',
+    'Aaron McDaniel (mcd1992)',
+    'Magnus Kolstad',
 )
 
 __license__ = 'Public Domain'
@@ -82,7 +85,6 @@ import optparse
 import os
 import random
 import shlex
-import shutil
 import sys
 
 
@@ -94,7 +96,6 @@ from .utils import (
     decodeOption,
     get_term_width,
     DownloadError,
-    get_cachedir,
     MaxDownloadsReached,
     preferredencoding,
     read_batch_urls,
@@ -118,6 +119,7 @@ from .postprocessor import (
     FFmpegExtractAudioPP,
     FFmpegEmbedSubtitlePP,
     XAttrMetadataPP,
+    ExecAfterDownloadPP,
 )
 
 
@@ -317,6 +319,8 @@ def parseOpts(overrideArguments=None):
             dest='username', metavar='USERNAME', help='account username')
     authentication.add_option('-p', '--password',
             dest='password', metavar='PASSWORD', help='account password')
+    authentication.add_option('-2', '--twofactor',
+            dest='twofactor', metavar='TWOFACTOR', help='two-factor auth code')
     authentication.add_option('-n', '--netrc',
             action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
     authentication.add_option('--video-password',
@@ -513,10 +517,10 @@ def parseOpts(overrideArguments=None):
     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',
+        '--cache-dir', dest='cachedir', default=None, 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',
+        '--no-cache-dir', action='store_const', const=False, dest='cachedir',
         help='Disable filesystem caching')
     filesystem.add_option(
         '--rm-cache-dir', action='store_true', dest='rm_cachedir',
@@ -547,7 +551,9 @@ def parseOpts(overrideArguments=None):
         help='Prefer avconv over ffmpeg for running the postprocessors (default)')
     postproc.add_option('--prefer-ffmpeg', action='store_true', dest='prefer_ffmpeg',
         help='Prefer ffmpeg over avconv for running the postprocessors')
-
+    postproc.add_option(
+        '--exec', metavar='CMD', dest='exec_cmd',
+        help='Execute a command on the file after downloading, similar to find\'s -exec syntax. Example: --exec \'adb push {} /sdcard/Music/ && rm {}\'' )
 
     parser.add_option_group(general)
     parser.add_option_group(selection)
@@ -751,6 +757,7 @@ def _real_main(argv=None):
         'usenetrc': opts.usenetrc,
         'username': opts.username,
         'password': opts.password,
+        'twofactor': opts.twofactor,
         'videopassword': opts.videopassword,
         'quiet': (opts.quiet or any_printing),
         'no_warnings': opts.no_warnings,
@@ -827,6 +834,7 @@ def _real_main(argv=None):
         'default_search': opts.default_search,
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
         'encoding': opts.encoding,
+        'exec_cmd': opts.exec_cmd,
     }
 
     with YoutubeDL(ydl_opts) as ydl:
@@ -850,26 +858,20 @@ def _real_main(argv=None):
                 ydl.add_post_processor(FFmpegAudioFixPP())
             ydl.add_post_processor(AtomicParsleyPP())
 
+
+        # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
+        # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
+        if opts.exec_cmd:
+            ydl.add_post_processor(ExecAfterDownloadPP(
+                verboseOutput=opts.verbose, exec_cmd=opts.exec_cmd))
+
         # Update version
         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'.')
+            ydl.cache.remove()
 
         # Maybe do nothing
         if (len(all_urls) < 1) and (opts.load_info_filename is None):

youtube_dl/cache.py

@@ -0,0 +1,94 @@
+from __future__ import unicode_literals
+
+import errno
+import io
+import json
+import os
+import re
+import shutil
+import traceback
+
+from .utils import (
+    write_json_file,
+)
+
+
+class Cache(object):
+    def __init__(self, ydl):
+        self._ydl = ydl
+
+    def _get_root_dir(self):
+        res = self._ydl.params.get('cachedir')
+        if res is None:
+            cache_root = os.environ.get('XDG_CACHE_HOME', '~/.cache')
+            res = os.path.join(cache_root, 'youtube-dl')
+        return os.path.expanduser(res)
+
+    def _get_cache_fn(self, section, key, dtype):
+        assert re.match(r'^[a-zA-Z0-9_.-]+$', section), \
+            'invalid section %r' % section
+        assert re.match(r'^[a-zA-Z0-9_.-]+$', key), 'invalid key %r' % key
+        return os.path.join(
+            self._get_root_dir(), section, '%s.%s' % (key, dtype))
+
+    @property
+    def enabled(self):
+        return self._ydl.params.get('cachedir') is not False
+
+    def store(self, section, key, data, dtype='json'):
+        assert dtype in ('json',)
+
+        if not self.enabled:
+            return
+
+        fn = self._get_cache_fn(section, key, dtype)
+        try:
+            try:
+                os.makedirs(os.path.dirname(fn))
+            except OSError as ose:
+                if ose.errno != errno.EEXIST:
+                    raise
+            write_json_file(data, fn)
+        except Exception:
+            tb = traceback.format_exc()
+            self._ydl.report_warning(
+                'Writing cache to %r failed: %s' % (fn, tb))
+
+    def load(self, section, key, dtype='json', default=None):
+        assert dtype in ('json',)
+
+        if not self.enabled:
+            return default
+
+        cache_fn = self._get_cache_fn(section, key, dtype)
+        try:
+            try:
+                with io.open(cache_fn, 'r', encoding='utf-8') as cachef:
+                    return json.load(cachef)
+            except ValueError:
+                try:
+                    file_size = os.path.getsize(cache_fn)
+                except (OSError, IOError) as oe:
+                    file_size = str(oe)
+                self._ydl.report_warning(
+                    'Cache retrieval from %s failed (%s)' % (cache_fn, file_size))
+        except IOError:
+            pass  # No cache available
+
+        return default
+
+    def remove(self):
+        if not self.enabled:
+            self._ydl.to_screen('Cache is disabled (Did you combine --no-cache-dir and --rm-cache-dir?)')
+            return
+
+        cachedir = self._get_root_dir()
+        if not any((term in cachedir) for term in ('cache', 'tmp')):
+            raise Exception('Not removing directory %s - this does not look like a cache dir' % cachedir)
+
+        self._ydl.to_screen(
+            'Removing cache dir %s .' % cachedir, skip_eol=True)
+        if os.path.exists(cachedir):
+            self._ydl.to_screen('.', skip_eol=True)
+            shutil.rmtree(cachedir)
+        self._ydl.to_screen('.')

youtube_dl/downloader/hls.py

@@ -3,6 +3,7 @@ import subprocess
 
 from .common import FileDownloader
 from ..utils import (
+    check_executable,
     encodeFilename,
 )
 
@@ -19,13 +20,11 @@ class HlsFD(FileDownloader):
             encodeFilename(tmpfilename, for_subprocess=True)]
 
         for program in ['avconv', 'ffmpeg']:
-            try:
-                subprocess.call([program, '-version'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+            if check_executable(program, ['-version']):
                 break
-            except (OSError, IOError):
-                pass
         else:
             self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
+            return False
         cmd = [program] + args
 
         retval = subprocess.call(cmd)
@@ -42,5 +41,5 @@ class HlsFD(FileDownloader):
             return True
         else:
             self.to_stderr(u"\n")
-            self.report_error(u'ffmpeg exited with code %d' % retval)
+            self.report_error(u'%s exited with code %d' % (program, retval))
             return False

youtube_dl/downloader/http.py

@@ -193,7 +193,8 @@ class HttpFD(FileDownloader):
             self.to_stderr(u"\n")
             self.report_error(u'Did not get any data blocks')
             return False
-        stream.close()
+        if tmpfilename != u'-':
+            stream.close()
         self.report_finish(data_len_str, (time.time() - start))
         if data_len is not None and byte_counter != data_len:
             raise ContentTooShortError(byte_counter, int(data_len))

youtube_dl/downloader/rtmp.py

@@ -8,9 +8,10 @@ import time
 
 from .common import FileDownloader
 from ..utils import (
+    check_executable,
+    compat_str,
     encodeFilename,
     format_bytes,
-    compat_str,
 )
 
 
@@ -103,9 +104,7 @@ class RtmpFD(FileDownloader):
         test = self.params.get('test', False)
 
         # Check for rtmpdump first
-        try:
-            subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
-        except (OSError, IOError):
+        if not check_executable('rtmpdump', ['-h']):
             self.report_error('RTMP download detected but "rtmpdump" could not be run. Please install it.')
             return False
 

youtube_dl/extractor/__init__.py

@@ -4,12 +4,13 @@ from .addanime import AddAnimeIE
 from .adultswim import AdultSwimIE
 from .aftonbladet import AftonbladetIE
 from .anitube import AnitubeIE
+from .anysex import AnySexIE
 from .aol import AolIE
 from .allocine import AllocineIE
 from .aparat import AparatIE
 from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
-from .ard import ARDIE
+from .ard import ARDIE, ARDMediathekIE
 from .arte import (
     ArteTvIE,
     ArteTVPlus7IE,
@@ -23,6 +24,7 @@ from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
+from .beeg import BeegIE
 from .bilibili import BiliBiliIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
@@ -65,9 +67,11 @@ from .dailymotion import (
     DailymotionUserIE,
 )
 from .daum import DaumIE
+from .dbtv import DBTVIE
 from .dfb import DFBIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
+from .drtuber import DrTuberIE
 from .drtv import DRTVIE
 from .dump import DumpIE
 from .defense import DefenseGouvFrIE
@@ -83,8 +87,9 @@ from .ellentv import (
     EllenTVClipsIE,
 )
 from .elpais import ElPaisIE
-from .empflix import EmpflixIE
+from .empflix import EMPFlixIE
 from .engadget import EngadgetIE
+from .eporner import EpornerIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
@@ -116,7 +121,10 @@ from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
 from .funnyordie import FunnyOrDieIE
 from .gamekings import GamekingsIE
-from .gameone import GameOneIE
+from .gameone import (
+    GameOneIE,
+    GameOnePlaylistIE,
+)
 from .gamespot import GameSpotIE
 from .gamestar import GameStarIE
 from .gametrailers import GametrailersIE
@@ -131,6 +139,8 @@ from .grooveshark import GroovesharkIE
 from .hark import HarkIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
+from .hornbunny import HornBunnyIE
+from .hostingbulk import HostingBulkIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
 from .howstuffworks import HowStuffWorksIE
@@ -191,6 +201,7 @@ from .mitele import MiTeleIE
 from .mixcloud import MixcloudIE
 from .mlb import MLBIE
 from .mpora import MporaIE
+from .moevideo import MoeVideoIE
 from .mofosex import MofosexIE
 from .mojvideo import MojvideoIE
 from .mooshare import MooshareIE
@@ -206,6 +217,7 @@ from .mtv import (
     MTVIggyIE,
 )
 from .musicplayon import MusicPlayOnIE
+from .musicvault import MusicVaultIE
 from .muzu import MuzuTVIE
 from .myspace import MySpaceIE
 from .myspass import MySpassIE
@@ -226,6 +238,7 @@ from .niconico import NiconicoIE
 from .ninegag import NineGagIE
 from .noco import NocoIE
 from .normalboots import NormalbootsIE
+from .nosvideo import NosVideoIE
 from .novamov import NovaMovIE
 from .nowness import NownessIE
 from .nowvideo import NowVideoIE
@@ -253,6 +266,7 @@ from .podomatic import PodomaticIE
 from .pornhd import PornHdIE
 from .pornhub import PornHubIE
 from .pornotube import PornotubeIE
+from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
 from .radiofrance import RadioFranceIE
@@ -284,6 +298,7 @@ from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .servingsys import ServingSysIE
 from .shared import SharedIE
+from .sharesix import ShareSixIE
 from .sina import SinaIE
 from .slideshare import SlideshareIE
 from .slutload import SlutloadIE
@@ -312,10 +327,12 @@ from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE
 from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
+from .sportdeutschland import SportDeutschlandIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
+from .sunporno import SunPornoIE
 from .swrmediathek import SWRMediathekIE
 from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
@@ -335,6 +352,7 @@ from .theplatform import ThePlatformIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
+from .tnaflix import TNAFlixIE
 from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
@@ -360,6 +378,7 @@ from .veehd import VeeHDIE
 from .veoh import VeohIE
 from .vesti import VestiIE
 from .vevo import VevoIE
+from .vgtv import VGTVIE
 from .vh1 import VH1IE
 from .viddler import ViddlerIE
 from .videobam import VideoBamIE
@@ -387,6 +406,7 @@ from .vine import (
 from .viki import VikiIE
 from .vk import VKIE
 from .vodlocker import VodlockerIE
+from .vporn import VpornIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
 from .vulture import VultureIE

youtube_dl/extractor/academicearth.py

@@ -7,6 +7,15 @@ from .common import InfoExtractor
 class AcademicEarthCourseIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
     IE_NAME = 'AcademicEarth:Course'
+    _TEST = {
+        'url': 'http://academicearth.org/playlists/laws-of-nature/',
+        'info_dict': {
+            'id': 'laws-of-nature',
+            'title': 'Laws of Nature',
+            'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.',
+        },
+        'playlist_count': 4,
+    }
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)

youtube_dl/extractor/anysex.py

@@ -0,0 +1,61 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+)
+
+
+class AnySexIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?anysex\.com/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://anysex.com/156592/',
+        'md5': '023e9fbb7f7987f5529a394c34ad3d3d',
+        'info_dict': {
+            'id': '156592',
+            'ext': 'mp4',
+            'title': 'Busty and sexy blondie in her bikini strips for you',
+            'description': 'md5:de9e418178e2931c10b62966474e1383',
+            'categories': ['Erotic'],
+            'duration': 270,
+            '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)
+
+        video_url = self._html_search_regex(r"video_url\s*:\s*'([^']+)'", webpage, 'video URL')
+
+        title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
+        description = self._html_search_regex(
+            r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
+        thumbnail = self._html_search_regex(
+            r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False)
+
+        categories = re.findall(
+            r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage)
+
+        duration = parse_duration(self._search_regex(
+            r'<b>Duration:</b> (\d+:\d+)', webpage, 'duration', fatal=False))
+        view_count = int_or_none(self._html_search_regex(
+            r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'duration': duration,
+            'view_count': view_count,
+            'age_limit': 18,
+        }

youtube_dl/extractor/aol.py

@@ -21,7 +21,7 @@ class AolIE(InfoExtractor):
         (?:$|\?)
     '''
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
         'md5': '18ef68f48740e86ae94b98da815eec42',
         'info_dict': {
@@ -30,7 +30,14 @@ class AolIE(InfoExtractor):
             'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
         },
         'add_ie': ['FiveMin'],
-    }
+    }, {
+        'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316',
+        'info_dict': {
+            'id': '152147',
+            'title': 'Brace Yourself - Today\'s Weirdest News',
+        },
+        'playlist_mincount': 10,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/ard.py

@@ -10,10 +10,14 @@ from ..utils import (
     qualities,
     compat_urllib_parse_urlparse,
     compat_urllib_parse,
+    int_or_none,
+    parse_duration,
+    unified_strdate,
 )
 
 
-class ARDIE(InfoExtractor):
+class ARDMediathekIE(InfoExtractor):
+    IE_NAME = 'ARD:mediathek'
     _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
 
     _TESTS = [{
@@ -128,3 +132,60 @@ class ARDIE(InfoExtractor):
             'formats': formats,
             'thumbnail': thumbnail,
         }
+
+
+class ARDIE(InfoExtractor):
+    _VALID_URL = '(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
+    _TEST = {
+        'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
+        'md5': 'd216c3a86493f9322545e045ddc3eb35',
+        'info_dict': {
+            'display_id': 'die-story-im-ersten-mission-unter-falscher-flagge',
+            'id': '100',
+            'ext': 'mp4',
+            'duration': 2600,
+            'title': 'Die Story im Ersten: Mission unter falscher Flagge',
+            'upload_date': '20140804',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
+
+        player_url = mobj.group('mainurl') + '~playerXml.xml'
+        doc = self._download_xml(player_url, display_id)
+        video_node = doc.find('./video')
+        upload_date = unified_strdate(video_node.find('./broadcastDate').text)
+        thumbnail = video_node.find('.//teaserImage//variant/url').text
+
+        formats = []
+        for a in video_node.findall('.//asset'):
+            f = {
+                'format_id': a.attrib['type'],
+                'width': int_or_none(a.find('./frameWidth').text),
+                'height': int_or_none(a.find('./frameHeight').text),
+                'vbr': int_or_none(a.find('./bitrateVideo').text),
+                'abr': int_or_none(a.find('./bitrateAudio').text),
+                'vcodec': a.find('./codecVideo').text,
+                'tbr': int_or_none(a.find('./totalBitrate').text),
+            }
+            if a.find('./serverPrefix').text:
+                f['url'] = a.find('./serverPrefix').text
+                f['playpath'] = a.find('./fileName').text
+            else:
+                f['url'] = a.find('./fileName').text
+            formats.append(f)
+        self._sort_formats(formats)
+
+        return {
+            'id': mobj.group('id'),
+            'formats': formats,
+            'display_id': display_id,
+            'title': video_node.find('./title').text,
+            'duration': parse_duration(video_node.find('./duration').text),
+            'upload_date': upload_date,
+            'thumbnail': thumbnail,
+        }
+

youtube_dl/extractor/arte.py

@@ -78,7 +78,8 @@ class ArteTVPlus7IE(InfoExtractor):
 
     def _extract_from_webpage(self, webpage, video_id, lang):
         json_url = self._html_search_regex(
-            r'arte_vp_url="(.*?)"', webpage, 'json vp url')
+            [r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'],
+            webpage, 'json vp url')
         return self._extract_from_json_url(json_url, video_id, lang)
 
     def _extract_from_json_url(self, json_url, video_id, lang):

youtube_dl/extractor/bambuser.py

@@ -59,6 +59,13 @@ class BambuserChannelIE(InfoExtractor):
     _VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
     # The maximum number we can get with each request
     _STEP = 50
+    _TEST = {
+        'url': 'http://bambuser.com/channel/pixelversity',
+        'info_dict': {
+            'title': 'pixelversity',
+        },
+        'playlist_mincount': 60,
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -73,10 +80,10 @@ class BambuserChannelIE(InfoExtractor):
             req = compat_urllib_request.Request(req_url)
             # Without setting this header, we wouldn't get any result
             req.add_header('Referer', 'http://bambuser.com/channel/%s' % user)
-            info_json = self._download_webpage(req, user,
-                'Downloading page %d' % i)
-            results = json.loads(info_json)['result']
-            if len(results) == 0:
+            data = self._download_json(
+                req, user, 'Downloading page %d' % i)
+            results = data['result']
+            if not results:
                 break
             last_id = results[-1]['vid']
             urls.extend(self.url_result(v['page'], 'Bambuser') for v in results)

youtube_dl/extractor/bandcamp.py

@@ -96,7 +96,7 @@ class BandcampAlbumIE(InfoExtractor):
     IE_NAME = 'Bandcamp:album'
     _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
         'playlist': [
             {
@@ -118,7 +118,13 @@ class BandcampAlbumIE(InfoExtractor):
             'playlistend': 2
         },
         'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
-    }
+    }, {
+        'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
+        'info_dict': {
+            'title': 'Hierophany of the Open Grave',
+        },
+        'playlist_mincount': 9,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/beeg.py

@@ -0,0 +1,65 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class BeegIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://beeg.com/5416503',
+        'md5': '634526ae978711f6b748fe0dd6c11f57',
+        'info_dict': {
+            'id': '5416503',
+            'ext': 'mp4',
+            'title': 'Sultry Striptease',
+            'description': 'md5:6db3c6177972822aaba18652ff59c773',
+            'categories': list,  # NSFW
+            'thumbnail': 're:https?://.*\.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)
+
+        quality_arr = self._search_regex(
+            r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats')
+
+        formats = [{
+            'url': fmt[1],
+            'format_id': fmt[0],
+            'height': int(fmt[0][:-1]),
+        } for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)]
+
+        self._sort_formats(formats)
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title')
+        
+        description = self._html_search_regex(
+            r'<meta name="description" content="([^"]*)"',
+            webpage, 'description', fatal=False)
+        thumbnail = self._html_search_regex(
+            r'\'previewer.url\'\s*:\s*"([^"]*)"',
+            webpage, 'thumbnail', fatal=False)
+
+        categories_str = self._html_search_regex(
+            r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
+        categories = (
+            None if categories_str is None
+            else categories_str.split(','))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'formats': formats,
+            'age_limit': 18,
+        }

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+_TESTS]+)))'
+    _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/cbs.py

@@ -25,7 +25,7 @@ class CBSIE(InfoExtractor):
     }, {
         'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
         'info_dict': {
-            'id': 'P9gjWjelt6iP',
+            'id': 'WWF_5KqY3PK1',
             '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.',

youtube_dl/extractor/cliphunter.py

@@ -1,11 +1,13 @@
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
-translation_table = {
+_translation_table = {
     'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
     'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
     'y': 'l', 'z': 'i',
@@ -13,6 +15,10 @@ translation_table = {
 }
 
 
+def _decode(s):
+    return ''.join(_translation_table.get(c, c) for c in s)
+
+
 class CliphunterIE(InfoExtractor):
     IE_NAME = 'cliphunter'
 
@@ -22,10 +28,14 @@ class CliphunterIE(InfoExtractor):
     '''
     _TEST = {
         'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
-        'file': '1012420.flv',
-        'md5': '15e7740f30428abf70f4223478dc1225',
+        'md5': 'a2ba71eebf523859fe527a61018f723e',
         'info_dict': {
+            'id': '1012420',
+            'ext': 'mp4',
             'title': 'Fun Jynx Maze solo',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'age_limit': 18,
+            'duration': 1317,
         }
     }
 
@@ -35,22 +45,55 @@ class CliphunterIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        video_title = self._search_regex(
+            r'mediaTitle = "([^"]+)"', webpage, 'title')
+
         pl_fiji = self._search_regex(
             r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
         pl_c_qual = self._search_regex(
             r'pl_c_qual = "(.)"', webpage, 'video quality')
-        video_title = self._search_regex(
-            r'mediaTitle = "([^"]+)"', webpage, 'title')
-
-        video_url = ''.join(translation_table.get(c, c) for c in pl_fiji)
-
+        video_url = _decode(pl_fiji)
         formats = [{
             'url': video_url,
-            'format_id': pl_c_qual,
+            'format_id': 'default-%s' % pl_c_qual,
         }]
 
+        qualities_json = self._search_regex(
+            r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info')
+        qualities_data = json.loads(qualities_json)
+
+        for i, t in enumerate(
+                re.findall(r"pl_fiji_([a-z0-9]+)\s*=\s*'([^']+')", webpage)):
+            quality_id, crypted_url = t
+            video_url = _decode(crypted_url)
+            f = {
+                'format_id': quality_id,
+                'url': video_url,
+                'quality': i,
+            }
+            if quality_id in qualities_data:
+                qd = qualities_data[quality_id]
+                m = re.match(
+                    r'''(?x)<b>(?P<width>[0-9]+)x(?P<height>[0-9]+)<\\/b>
+                        \s*\(\s*(?P<tbr>[0-9]+)\s*kb\\/s''', qd)
+                if m:
+                    f['width'] = int(m.group('width'))
+                    f['height'] = int(m.group('height'))
+                    f['tbr'] = int(m.group('tbr'))
+            formats.append(f)
+        self._sort_formats(formats)
+
+        thumbnail = self._search_regex(
+            r"var\s+mov_thumb\s*=\s*'([^']+)';",
+            webpage, 'thumbnail', fatal=False)
+        duration = int_or_none(self._search_regex(
+            r'pl_dur\s*=\s*([0-9]+)', webpage, 'duration', fatal=False))
+
         return {
             'id': video_id,
             'title': video_title,
             'formats': formats,
+            'duration': duration,
+            'age_limit': self._rta_search(webpage),
+            'thumbnail': thumbnail,
         }

youtube_dl/extractor/comedycentral.py

@@ -43,14 +43,14 @@ class ComedyCentralShowsIE(InfoExtractor):
                           (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
                          ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
                           (?P<clip>
-                              (?:(?:guests/[^/]+|videos|video-playlists|special-editions)/[^/]+/(?P<videotitle>[^/?#]+))
+                              (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+))
                               |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
                               |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
                           )|
                           (?P<interview>
                               extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
                      (?:[?#].*|$)'''
-    _TEST = {
+    _TESTS = [{
         'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
         'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
         'info_dict': {
@@ -61,7 +61,34 @@ class ComedyCentralShowsIE(InfoExtractor):
             'uploader': 'thedailyshow',
             'title': 'thedailyshow kristen-stewart part 1',
         }
-    }
+    }, {
+        'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
+        'only_matching': True,
+    }, {
+        'url': 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
+        'only_matching': True,
+    }, {
+        'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
+        'only_matching': True,
+    }, {
+        'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
+        'only_matching': True,
+    }, {
+        'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
+        'only_matching': True,
+    }, {
+        'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
+        'only_matching': True,
+    }, {
+        'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
+        'only_matching': True,
+    }, {
+        'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
+        'only_matching': True,
+    }, {
+        'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel',
+        'only_matching': True,
+    }]
 
     _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
 
@@ -185,6 +212,9 @@ class ComedyCentralShowsIE(InfoExtractor):
                     'ext': self._video_extensions.get(format, 'mp4'),
                     'height': h,
                     'width': w,
+
+                    'format_note': 'HTTP 400 at the moment (patches welcome!)',
+                    'preference': -100,
                 })
                 formats.append({
                     'format_id': 'rtmp-%s' % format,

youtube_dl/extractor/common.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import base64
 import hashlib
 import json
@@ -114,7 +116,7 @@ class InfoExtractor(object):
     upload_date:    Video upload date (YYYYMMDD).
                     If not explicitly set, calculated from timestamp.
     uploader_id:    Nickname or id of the video uploader.
-    location:       Physical location of the video.
+    location:       Physical location where the video was filmed.
     subtitles:      The subtitle file contents as a dictionary in the format
                     {language: subtitles}.
     duration:       Length of the video in seconds, as an integer.
@@ -202,17 +204,17 @@ class InfoExtractor(object):
             self.report_download_webpage(video_id)
         elif note is not False:
             if video_id is None:
-                self.to_screen(u'%s' % (note,))
+                self.to_screen('%s' % (note,))
             else:
-                self.to_screen(u'%s: %s' % (video_id, note))
+                self.to_screen('%s: %s' % (video_id, note))
         try:
             return self._downloader.urlopen(url_or_request)
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
             if errnote is False:
                 return False
             if errnote is None:
-                errnote = u'Unable to download webpage'
-            errmsg = u'%s: %s' % (errnote, compat_str(err))
+                errnote = 'Unable to download webpage'
+            errmsg = '%s: %s' % (errnote, compat_str(err))
             if fatal:
                 raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
             else:
@@ -249,7 +251,7 @@ class InfoExtractor(object):
                 url = url_or_request.get_full_url()
             except AttributeError:
                 url = url_or_request
-            self.to_screen(u'Dumping request to ' + url)
+            self.to_screen('Dumping request to ' + url)
             dump = base64.b64encode(webpage_bytes).decode('ascii')
             self._downloader.to_screen(dump)
         if self._downloader.params.get('write_pages', False):
@@ -259,11 +261,11 @@ class InfoExtractor(object):
                 url = url_or_request
             basen = '%s_%s' % (video_id, url)
             if len(basen) > 240:
-                h = u'___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
+                h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
                 basen = basen[:240 - len(h)] + h
             raw_filename = basen + '.dump'
             filename = sanitize_filename(raw_filename, restricted=True)
-            self.to_screen(u'Saving request to ' + filename)
+            self.to_screen('Saving request to ' + filename)
             with open(filename, 'wb') as outf:
                 outf.write(webpage_bytes)
 
@@ -272,14 +274,14 @@ class InfoExtractor(object):
         except LookupError:
             content = webpage_bytes.decode('utf-8', 'replace')
 
-        if (u'<title>Access to this site is blocked</title>' in content and
-                u'Websense' in content[:512]):
-            msg = u'Access to this webpage has been blocked by Websense filtering software in your network.'
+        if ('<title>Access to this site is blocked</title>' in content and
+                'Websense' in content[:512]):
+            msg = 'Access to this webpage has been blocked by Websense filtering software in your network.'
             blocked_iframe = self._html_search_regex(
                 r'<iframe src="([^"]+)"', content,
-                u'Websense information URL', default=None)
+                'Websense information URL', default=None)
             if blocked_iframe:
-                msg += u' Visit %s for more details' % blocked_iframe
+                msg += ' Visit %s for more details' % blocked_iframe
             raise ExtractorError(msg, expected=True)
 
         return (content, urlh)
@@ -294,7 +296,7 @@ class InfoExtractor(object):
             return content
 
     def _download_xml(self, url_or_request, video_id,
-                      note=u'Downloading XML', errnote=u'Unable to download XML',
+                      note='Downloading XML', errnote='Unable to download XML',
                       transform_source=None, fatal=True):
         """Return the xml as an xml.etree.ElementTree.Element"""
         xml_string = self._download_webpage(
@@ -306,8 +308,8 @@ class InfoExtractor(object):
         return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
 
     def _download_json(self, url_or_request, video_id,
-                       note=u'Downloading JSON metadata',
-                       errnote=u'Unable to download JSON metadata',
+                       note='Downloading JSON metadata',
+                       errnote='Unable to download JSON metadata',
                        transform_source=None,
                        fatal=True):
         json_string = self._download_webpage(
@@ -322,29 +324,29 @@ class InfoExtractor(object):
             raise ExtractorError('Failed to download JSON', cause=ve)
 
     def report_warning(self, msg, video_id=None):
-        idstr = u'' if video_id is None else u'%s: ' % video_id
+        idstr = '' if video_id is None else '%s: ' % video_id
         self._downloader.report_warning(
-            u'[%s] %s%s' % (self.IE_NAME, idstr, msg))
+            '[%s] %s%s' % (self.IE_NAME, idstr, msg))
 
     def to_screen(self, msg):
         """Print msg to screen, prefixing it with '[ie_name]'"""
-        self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg))
+        self._downloader.to_screen('[%s] %s' % (self.IE_NAME, msg))
 
     def report_extraction(self, id_or_name):
         """Report information extraction."""
-        self.to_screen(u'%s: Extracting information' % id_or_name)
+        self.to_screen('%s: Extracting information' % id_or_name)
 
     def report_download_webpage(self, video_id):
         """Report webpage download."""
-        self.to_screen(u'%s: Downloading webpage' % video_id)
+        self.to_screen('%s: Downloading webpage' % video_id)
 
     def report_age_confirmation(self):
         """Report attempt to confirm age."""
-        self.to_screen(u'Confirming age')
+        self.to_screen('Confirming age')
 
     def report_login(self):
         """Report attempt to log in."""
-        self.to_screen(u'Logging in')
+        self.to_screen('Logging in')
 
     #Methods for following #608
     @staticmethod
@@ -384,7 +386,7 @@ class InfoExtractor(object):
                     break
 
         if os.name != 'nt' and sys.stderr.isatty():
-            _name = u'\033[0;34m%s\033[0m' % name
+            _name = '\033[0;34m%s\033[0m' % name
         else:
             _name = name
 
@@ -394,10 +396,10 @@ class InfoExtractor(object):
         elif default is not _NO_DEFAULT:
             return default
         elif fatal:
-            raise RegexNotFoundError(u'Unable to extract %s' % _name)
+            raise RegexNotFoundError('Unable to extract %s' % _name)
         else:
-            self._downloader.report_warning(u'unable to extract %s; '
-                u'please report this issue on http://yt-dl.org/bug' % _name)
+            self._downloader.report_warning('unable to extract %s; '
+                'please report this issue on http://yt-dl.org/bug' % _name)
             return None
 
     def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
@@ -436,10 +438,26 @@ class InfoExtractor(object):
                 else:
                     raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
             except (IOError, netrc.NetrcParseError) as err:
-                self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
+                self._downloader.report_warning('parsing .netrc: %s' % compat_str(err))
         
         return (username, password)
 
+    def _get_tfa_info(self):
+        """
+        Get the two-factor authentication info
+        TODO - asking the user will be required for sms/phone verify
+        currently just uses the command line option
+        If there's no info available, return None
+        """
+        if self._downloader is None:
+            return None
+        downloader_params = self._downloader.params
+
+        if downloader_params.get('twofactor', None) is not None:
+            return downloader_params['twofactor']
+
+        return None
+
     # Helper functions for extracting OpenGraph info
     @staticmethod
     def _og_regexes(prop):
@@ -460,7 +478,7 @@ class InfoExtractor(object):
         return unescapeHTML(escaped)
 
     def _og_search_thumbnail(self, html, **kargs):
-        return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs)
+        return self._og_search_property('image', html, 'thumbnail url', fatal=False, **kargs)
 
     def _og_search_description(self, html, **kargs):
         return self._og_search_property('description', html, fatal=False, **kargs)
@@ -519,7 +537,7 @@ class InfoExtractor(object):
 
     def _sort_formats(self, formats):
         if not formats:
-            raise ExtractorError(u'No video formats found')
+            raise ExtractorError('No video formats found')
 
         def _formats_key(f):
             # TODO remove the following workaround
@@ -539,9 +557,9 @@ class InfoExtractor(object):
 
             if f.get('vcodec') == 'none':  # audio only
                 if self._downloader.params.get('prefer_free_formats'):
-                    ORDER = [u'aac', u'mp3', u'm4a', u'webm', u'ogg', u'opus']
+                    ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus']
                 else:
-                    ORDER = [u'webm', u'opus', u'ogg', u'mp3', u'aac', u'm4a']
+                    ORDER = ['webm', 'opus', 'ogg', 'mp3', 'aac', 'm4a']
                 ext_preference = 0
                 try:
                     audio_ext_preference = ORDER.index(f['ext'])
@@ -549,9 +567,9 @@ class InfoExtractor(object):
                     audio_ext_preference = -1
             else:
                 if self._downloader.params.get('prefer_free_formats'):
-                    ORDER = [u'flv', u'mp4', u'webm']
+                    ORDER = ['flv', 'mp4', 'webm']
                 else:
-                    ORDER = [u'webm', u'flv', u'mp4']
+                    ORDER = ['webm', 'flv', 'mp4']
                 try:
                     ext_preference = ORDER.index(f['ext'])
                 except ValueError:
@@ -593,7 +611,7 @@ class InfoExtractor(object):
 
     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_template = '%(video_id)s: Waiting for %(timeout)s seconds'
         msg = msg_template % {'video_id': video_id, 'timeout': timeout}
         self.to_screen(msg)
         time.sleep(timeout)
@@ -604,11 +622,15 @@ class InfoExtractor(object):
             'Unable to download f4m manifest')
 
         formats = []
-        for media_el in manifest.findall('{http://ns.adobe.com/f4m/1.0}media'):
+        media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
+        for i, media_el in enumerate(media_nodes):
+            tbr = int_or_none(media_el.attrib.get('bitrate'))
+            format_id = 'f4m-%d' % (i if tbr is None else tbr)
             formats.append({
+                'format_id': format_id,
                 'url': manifest_url,
                 'ext': 'flv',
-                'tbr': int_or_none(media_el.attrib.get('bitrate')),
+                'tbr': tbr,
                 'width': int_or_none(media_el.attrib.get('width')),
                 'height': int_or_none(media_el.attrib.get('height')),
             })
@@ -616,6 +638,61 @@ class InfoExtractor(object):
 
         return formats
 
+    def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None):
+        formats = [{
+            'format_id': 'm3u8-meta',
+            'url': m3u8_url,
+            'ext': ext,
+            'protocol': 'm3u8',
+            'preference': -1,
+            'resolution': 'multiple',
+            'format_note': 'Quality selection URL',
+        }]
+
+        m3u8_doc = self._download_webpage(m3u8_url, video_id)
+        last_info = None
+        kv_rex = re.compile(
+            r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)')
+        for line in m3u8_doc.splitlines():
+            if line.startswith('#EXT-X-STREAM-INF:'):
+                last_info = {}
+                for m in kv_rex.finditer(line):
+                    v = m.group('val')
+                    if v.startswith('"'):
+                        v = v[1:-1]
+                    last_info[m.group('key')] = v
+            elif line.startswith('#') or not line.strip():
+                continue
+            else:
+                if last_info is None:
+                    formats.append({'url': line})
+                    continue
+                tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
+
+                f = {
+                    'format_id': 'm3u8-%d' % (tbr if tbr else len(formats)),
+                    'url': line.strip(),
+                    'tbr': tbr,
+                    'ext': ext,
+                }
+                codecs = last_info.get('CODECS')
+                if codecs:
+                    # TODO: looks like video codec is not always necessarily goes first
+                    va_codecs = codecs.split(',')
+                    if va_codecs[0]:
+                        f['vcodec'] = va_codecs[0].partition('.')[0]
+                    if len(va_codecs) > 1 and va_codecs[1]:
+                        f['acodec'] = va_codecs[1].partition('.')[0]
+                resolution = last_info.get('RESOLUTION')
+                if resolution:
+                    width_str, height_str = resolution.split('x')
+                    f['width'] = int(width_str)
+                    f['height'] = int(height_str)
+                formats.append(f)
+                last_info = {}
+        self._sort_formats(formats)
+        return formats
+
 
 class SearchInfoExtractor(InfoExtractor):
     """
@@ -635,7 +712,7 @@ class SearchInfoExtractor(InfoExtractor):
     def _real_extract(self, query):
         mobj = re.match(self._make_valid_url(), query)
         if mobj is None:
-            raise ExtractorError(u'Invalid search query "%s"' % query)
+            raise ExtractorError('Invalid search query "%s"' % query)
 
         prefix = mobj.group('prefix')
         query = mobj.group('query')
@@ -646,9 +723,9 @@ class SearchInfoExtractor(InfoExtractor):
         else:
             n = int(prefix)
             if n <= 0:
-                raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query))
+                raise ExtractorError('invalid download number %s for query "%s"' % (n, query))
             elif n > self._MAX_RESULTS:
-                self._downloader.report_warning(u'%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
+                self._downloader.report_warning('%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
                 n = self._MAX_RESULTS
             return self._get_n_results(query, n)
 

youtube_dl/extractor/crunchyroll.py

@@ -5,6 +5,7 @@ import re
 import json
 import base64
 import zlib
+import xml.etree.ElementTree
 
 from hashlib import sha1
 from math import pow, sqrt, floor
@@ -17,6 +18,7 @@ from ..utils import (
     intlist_to_bytes,
     unified_strdate,
     clean_html,
+    urlencode_postdata,
 )
 from ..aes import (
     aes_cbc_decrypt,
@@ -51,6 +53,26 @@ class CrunchyrollIE(InfoExtractor):
         '1080': ('80', '108'),
     }
 
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+        self.report_login()
+        login_url = 'https://www.crunchyroll.com/?a=formhandler'
+        data = urlencode_postdata({
+            'formname': 'RpcApiUser_Login',
+            'name': username,
+            'password': password,
+        })
+        login_request = compat_urllib_request.Request(login_url, data)
+        login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        self._download_webpage(login_request, None, False, 'Wrong login info')
+
+
+    def _real_initialize(self):
+        self._login()
+
+
     def _decrypt_subtitles(self, data, iv, id):
         data = bytes_to_intlist(data)
         iv = bytes_to_intlist(iv)
@@ -97,6 +119,75 @@ class CrunchyrollIE(InfoExtractor):
             output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
         return output
 
+    def _convert_subtitles_to_ass(self, subtitles):
+        output = ''
+
+        def ass_bool(strvalue):
+            assvalue = '0'
+            if strvalue == '1':
+                assvalue = '-1'
+            return assvalue
+
+        sub_root = xml.etree.ElementTree.fromstring(subtitles)
+        if not sub_root:
+            return output
+
+        output = '[Script Info]\n'
+        output += 'Title: %s\n' % sub_root.attrib["title"]
+        output += 'ScriptType: v4.00+\n'
+        output += 'WrapStyle: %s\n' % sub_root.attrib["wrap_style"]
+        output += 'PlayResX: %s\n' % sub_root.attrib["play_res_x"]
+        output += 'PlayResY: %s\n' % sub_root.attrib["play_res_y"]
+        output += """ScaledBorderAndShadow: yes
+
+[V4+ Styles]
+Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
+"""
+        for style in sub_root.findall('./styles/style'):
+            output += 'Style: ' + style.attrib["name"]
+            output += ',' + style.attrib["font_name"]
+            output += ',' + style.attrib["font_size"]
+            output += ',' + style.attrib["primary_colour"]
+            output += ',' + style.attrib["secondary_colour"]
+            output += ',' + style.attrib["outline_colour"]
+            output += ',' + style.attrib["back_colour"]
+            output += ',' + ass_bool(style.attrib["bold"])
+            output += ',' + ass_bool(style.attrib["italic"])
+            output += ',' + ass_bool(style.attrib["underline"])
+            output += ',' + ass_bool(style.attrib["strikeout"])
+            output += ',' + style.attrib["scale_x"]
+            output += ',' + style.attrib["scale_y"]
+            output += ',' + style.attrib["spacing"]
+            output += ',' + style.attrib["angle"]
+            output += ',' + style.attrib["border_style"]
+            output += ',' + style.attrib["outline"]
+            output += ',' + style.attrib["shadow"]
+            output += ',' + style.attrib["alignment"]
+            output += ',' + style.attrib["margin_l"]
+            output += ',' + style.attrib["margin_r"]
+            output += ',' + style.attrib["margin_v"]
+            output += ',' + style.attrib["encoding"]
+            output += '\n'
+
+        output += """
+[Events]
+Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
+"""
+        for event in sub_root.findall('./events/event'):
+            output += 'Dialogue: 0'
+            output += ',' + event.attrib["start"]
+            output += ',' + event.attrib["end"]
+            output += ',' + event.attrib["style"]
+            output += ',' + event.attrib["name"]
+            output += ',' + event.attrib["margin_l"]
+            output += ',' + event.attrib["margin_r"]
+            output += ',' + event.attrib["margin_v"]
+            output += ',' + event.attrib["effect"]
+            output += ',' + event.attrib["text"]
+            output += '\n'
+
+        return output
+
     def _real_extract(self,url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('video_id')
@@ -158,6 +249,7 @@ class CrunchyrollIE(InfoExtractor):
             })
 
         subtitles = {}
+        sub_format = self._downloader.params.get('subtitlesformat', 'srt')
         for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
             sub_page = self._download_webpage('http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\
                                               video_id, note='Downloading subtitles for '+sub_name)
@@ -174,7 +266,10 @@ class CrunchyrollIE(InfoExtractor):
             lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
             if not lang_code:
                 continue
-            subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
+            if sub_format == 'ass':
+                subtitles[lang_code] = self._convert_subtitles_to_ass(subtitle)
+            else:
+                subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
 
         return {
             'id':          video_id,

youtube_dl/extractor/cspan.py

@@ -34,6 +34,13 @@ class CSpanIE(InfoExtractor):
             'title': 'International Health Care Models',
             'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
         }
+    }, {
+        'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
+        'info_dict': {
+            'id': '342759',
+            'title': 'General Motors Ignition Switch Recall',
+        },
+        'playlist_duration_sum': 14855,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/dailymotion.py

@@ -1,3 +1,6 @@
+#coding: utf-8
+from __future__ import unicode_literals
+
 import re
 import json
 import itertools
@@ -28,51 +31,53 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
     """Information Extractor for Dailymotion"""
 
     _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'
-    IE_NAME = u'dailymotion'
+    IE_NAME = 'dailymotion'
 
     _FORMATS = [
-        (u'stream_h264_ld_url', u'ld'),
-        (u'stream_h264_url', u'standard'),
-        (u'stream_h264_hq_url', u'hq'),
-        (u'stream_h264_hd_url', u'hd'),
-        (u'stream_h264_hd1080_url', u'hd180'),
+        ('stream_h264_ld_url', 'ld'),
+        ('stream_h264_url', 'standard'),
+        ('stream_h264_hq_url', 'hq'),
+        ('stream_h264_hd_url', 'hd'),
+        ('stream_h264_hd1080_url', 'hd180'),
     ]
 
     _TESTS = [
         {
-            u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
-            u'file': u'x33vw9.mp4',
-            u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
-            u'info_dict': {
-                u"uploader": u"Amphora Alex and Van .", 
-                u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
+            'url': 'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
+            'md5': '392c4b85a60a90dc4792da41ce3144eb',
+            'info_dict': {
+                'id': 'x33vw9',
+                'ext': 'mp4',
+                'uploader': 'Amphora Alex and Van .',
+                'title': 'Tutoriel de Youtubeur"DL DES VIDEO DE YOUTUBE"',
             }
         },
         # Vevo video
         {
-            u'url': u'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
-            u'file': u'USUV71301934.mp4',
-            u'info_dict': {
-                u'title': u'Roar (Official)',
-                u'uploader': u'Katy Perry',
-                u'upload_date': u'20130905',
+            'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
+            'info_dict': {
+                'title': 'Roar (Official)',
+                'id': 'USUV71301934',
+                'ext': 'mp4',
+                'uploader': 'Katy Perry',
+                'upload_date': '20130905',
             },
-            u'params': {
-                u'skip_download': True,
+            'params': {
+                'skip_download': True,
             },
-            u'skip': u'VEVO is only available in some countries',
+            'skip': 'VEVO is only available in some countries',
         },
         # age-restricted video
         {
-            u'url': u'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
-            u'file': u'xyh2zz.mp4',
-            u'md5': u'0d667a7b9cebecc3c89ee93099c4159d',
-            u'info_dict': {
-                u'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
-                u'uploader': 'HotWaves1012',
-                u'age_limit': 18,
+            'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
+            'md5': '0d667a7b9cebecc3c89ee93099c4159d',
+            'info_dict': {
+                'id': 'xyh2zz',
+                'ext': 'mp4',
+                'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
+                'uploader': 'HotWaves1012',
+                'age_limit': 18,
             }
-
         }
     ]
 
@@ -97,8 +102,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             webpage)
         if m_vevo is not None:
             vevo_id = m_vevo.group('id')
-            self.to_screen(u'Vevo video detected: %s' % vevo_id)
-            return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo')
+            self.to_screen('Vevo video detected: %s' % vevo_id)
+            return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
 
         age_limit = self._rta_search(webpage)
 
@@ -109,7 +114,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
 
         embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
         embed_page = self._download_webpage(embed_url, video_id,
-                                            u'Downloading embed page')
+                                            'Downloading embed page')
         info = self._search_regex(r'var info = ({.*?}),$', embed_page,
             'video info', flags=re.MULTILINE)
         info = json.loads(info)
@@ -134,7 +139,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
                     'height': height,
                 })
         if not formats:
-            raise ExtractorError(u'Unable to extract video URL')
+            raise ExtractorError('Unable to extract video URL')
 
         # subtitles
         video_subtitles = self.extract_subtitles(video_id, webpage)
@@ -143,7 +148,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             return
 
         view_count = self._search_regex(
-            r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, u'view count', fatal=False)
+            r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, 'view count', fatal=False)
         if view_count is not None:
             view_count = str_to_int(view_count)
 
@@ -165,28 +170,35 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
                 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
                 video_id, note=False)
         except ExtractorError as err:
-            self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
+            self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err))
             return {}
         info = json.loads(sub_list)
         if (info['total'] > 0):
             sub_lang_list = dict((l['language'], l['url']) for l in info['list'])
             return sub_lang_list
-        self._downloader.report_warning(u'video doesn\'t have subtitles')
+        self._downloader.report_warning('video doesn\'t have subtitles')
         return {}
 
 
 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
-    IE_NAME = u'dailymotion:playlist'
+    IE_NAME = 'dailymotion:playlist'
     _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
     _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
     _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
+    _TESTS = [{
+        'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
+        'info_dict': {
+            'title': 'SPORT',
+        },
+        'playlist_mincount': 20,
+    }]
 
     def _extract_entries(self, id):
         video_ids = []
         for pagenum in itertools.count(1):
             request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
             webpage = self._download_webpage(request,
-                                             id, u'Downloading page %s' % pagenum)
+                                             id, 'Downloading page %s' % pagenum)
 
             video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage))
 
@@ -209,9 +221,17 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 
 
 class DailymotionUserIE(DailymotionPlaylistIE):
-    IE_NAME = u'dailymotion:user'
+    IE_NAME = 'dailymotion:user'
     _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
+    _TESTS = [{
+        'url': 'https://www.dailymotion.com/user/nqtv',
+        'info_dict': {
+            'id': 'nqtv',
+            'title': 'Rémi Gaillard',
+        },
+        'playlist_mincount': 100,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -219,7 +239,7 @@ class DailymotionUserIE(DailymotionPlaylistIE):
         webpage = self._download_webpage(url, user)
         full_user = unescapeHTML(self._html_search_regex(
             r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
-            webpage, u'user', flags=re.DOTALL))
+            webpage, 'user'))
 
         return {
             '_type': 'playlist',

youtube_dl/extractor/dbtv.py

@@ -0,0 +1,74 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    clean_html,
+)
+
+
+class DBTVIE(InfoExtractor):
+    _VALID_URL = r'http://dbtv\.no/(?P<id>[0-9]+)#(?P<display_id>.+)'
+    _TEST = {
+        'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
+        'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc',
+        'info_dict': {
+            'id': '33100',
+            'display_id': 'Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
+            'ext': 'mp4',
+            'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen',
+            'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'timestamp': 1404039863.438,
+            'upload_date': '20140629',
+            'duration': 69.544,
+            'view_count': int,
+            'categories': list,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        data = self._download_json(
+            'http://api.dbtv.no/discovery/%s' % video_id, display_id)
+
+        video = data['playlist'][0]
+
+        formats = [{
+            'url': f['URL'],
+            'vcodec': f.get('container'),
+            'width': int_or_none(f.get('width')),
+            'height': int_or_none(f.get('height')),
+            'vbr': float_or_none(f.get('rate'), 1000),
+            'filesize': int_or_none(f.get('size')),
+        } for f in video['renditions'] if 'URL' in f]
+
+        if not formats:
+            for url_key, format_id in [('URL', 'mp4'), ('HLSURL', 'hls')]:
+                if url_key in video:
+                    formats.append({
+                        'url': video[url_key],
+                        'format_id': format_id,
+                    })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video['id'],
+            'display_id': display_id,
+            'title': video['title'],
+            'description': clean_html(video['desc']),
+            'thumbnail': video.get('splash') or video.get('thumb'),
+            'timestamp': float_or_none(video.get('publishedAt'), 1000),
+            'duration': float_or_none(video.get('length'), 1000),
+            'view_count': int_or_none(video.get('views')),
+            'categories': video.get('tags'),
+            'formats': formats,
+        }

youtube_dl/extractor/dropbox.py

@@ -11,8 +11,7 @@ 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/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4',
-        'md5': '8a3d905427a6951ccb9eb292f154530b',
+        'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0',
         'info_dict': {
             'id': 'nelirfsxnmcfbfh',
             'ext': 'mp4',
@@ -25,7 +24,9 @@ class DropboxIE(InfoExtractor):
         video_id = mobj.group('id')
         fn = compat_urllib_parse_unquote(mobj.group('title'))
         title = os.path.splitext(fn)[0]
-        video_url = url + '?dl=1'
+        video_url = (
+            re.sub(r'[?&]dl=0', '', url) +
+            ('?' if '?' in url else '&') + 'dl=1')
 
         return {
             'id': video_id,

youtube_dl/extractor/drtuber.py

@@ -0,0 +1,70 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import str_to_int
+
+
+class DrTuberIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
+    _TEST = {
+        'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
+        'md5': '93e680cf2536ad0dfb7e74d94a89facd',
+        'info_dict': {
+            'id': '1740434',
+            'display_id': 'hot-perky-blonde-naked-golf',
+            'ext': 'mp4',
+            'title': 'Hot Perky Blonde Naked Golf',
+            'like_count': int,
+            'dislike_count': int,
+            'comment_count': int,
+            'categories': list,  # NSFW
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_url = self._html_search_regex(
+            r'<source src="([^"]+)"', webpage, 'video URL')
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)\s*-\s*Free', webpage, 'title')
+
+        thumbnail = self._html_search_regex(
+            r'poster="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        like_count = str_to_int(self._html_search_regex(
+            r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
+            webpage, 'like count', fatal=False))
+        dislike_count = str_to_int(self._html_search_regex(
+            r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
+            webpage, 'like count', fatal=False))
+        comment_count = str_to_int(self._html_search_regex(
+            r'<span class="comments_count">([\d,\.]+)</span>',
+            webpage, 'comment count', fatal=False))
+
+        cats_str = self._html_search_regex(
+            r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
+        categories = None if cats_str is None else cats_str.split(' ')
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'comment_count': comment_count,
+            'categories': categories,
+            'age_limit': self._rta_search(webpage),
+        }

youtube_dl/extractor/eighttracks.py

@@ -1,10 +1,13 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
 import json
 import random
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
+    compat_str,
 )
 
 
@@ -12,86 +15,98 @@ class EightTracksIE(InfoExtractor):
     IE_NAME = '8tracks'
     _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
     _TEST = {
-        u"name": u"EightTracks",
-        u"url": u"http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
-        u"playlist": [
+        "name": "EightTracks",
+        "url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
+        "info_dict": {
+            'id': '1336550',
+            'display_id': 'youtube-dl-test-tracks-a',
+            "description": "test chars:  \"'/\\ä↭",
+            "title": "youtube-dl test tracks \"'/\\ä↭<>",
+        },
+        "playlist": [
             {
-                u"file": u"11885610.m4a",
-                u"md5": u"96ce57f24389fc8734ce47f4c1abcc55",
-                u"info_dict": {
-                    u"title": u"youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "96ce57f24389fc8734ce47f4c1abcc55",
+                "info_dict": {
+                    "id": "11885610",
+                    "ext": "m4a",
+                    "title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885608.m4a",
-                u"md5": u"4ab26f05c1f7291ea460a3920be8021f",
-                u"info_dict": {
-                    u"title": u"youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "4ab26f05c1f7291ea460a3920be8021f",
+                "info_dict": {
+                    "id": "11885608",
+                    "ext": "m4a",
+                    "title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885679.m4a",
-                u"md5": u"d30b5b5f74217410f4689605c35d1fd7",
-                u"info_dict": {
-                    u"title": u"youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "d30b5b5f74217410f4689605c35d1fd7",
+                "info_dict": {
+                    "id": "11885679",
+                    "ext": "m4a",
+                    "title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885680.m4a",
-                u"md5": u"4eb0a669317cd725f6bbd336a29f923a",
-                u"info_dict": {
-                    u"title": u"youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "4eb0a669317cd725f6bbd336a29f923a",
+                "info_dict": {
+                    "id": "11885680",
+                    "ext": "m4a",
+                    "title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885682.m4a",
-                u"md5": u"1893e872e263a2705558d1d319ad19e8",
-                u"info_dict": {
-                    u"title": u"PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "1893e872e263a2705558d1d319ad19e8",
+                "info_dict": {
+                    "id": "11885682",
+                    "ext": "m4a",
+                    "title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885683.m4a",
-                u"md5": u"b673c46f47a216ab1741ae8836af5899",
-                u"info_dict": {
-                    u"title": u"PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "b673c46f47a216ab1741ae8836af5899",
+                "info_dict": {
+                    "id": "11885683",
+                    "ext": "m4a",
+                    "title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885684.m4a",
-                u"md5": u"1d74534e95df54986da7f5abf7d842b7",
-                u"info_dict": {
-                    u"title": u"phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "1d74534e95df54986da7f5abf7d842b7",
+                "info_dict": {
+                    "id": "11885684",
+                    "ext": "m4a",
+                    "title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885685.m4a",
-                u"md5": u"f081f47af8f6ae782ed131d38b9cd1c0",
-                u"info_dict": {
-                    u"title": u"phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "f081f47af8f6ae782ed131d38b9cd1c0",
+                "info_dict": {
+                    "id": "11885685",
+                    "ext": "m4a",
+                    "title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             }
         ]
     }
 
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
         playlist_id = mobj.group('id')
 
         webpage = self._download_webpage(url, playlist_id)
 
-        json_like = self._search_regex(r"PAGE.mix = (.*?);\n", webpage, u'trax information', flags=re.DOTALL)
+        json_like = self._search_regex(
+            r"(?s)PAGE.mix = (.*?);\n", webpage, 'trax information')
         data = json.loads(json_like)
 
         session = str(random.randint(0, 1000000000))
@@ -99,21 +114,30 @@ class EightTracksIE(InfoExtractor):
         track_count = data['tracks_count']
         first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
         next_url = first_url
-        res = []
+        entries = []
         for i in range(track_count):
-            api_json = self._download_webpage(next_url, playlist_id,
-                note=u'Downloading song information %s/%s' % (str(i+1), track_count),
-                errnote=u'Failed to download song information')
+            api_json = self._download_webpage(
+                next_url, playlist_id,
+                note='Downloading song information %d/%d' % (i + 1, track_count),
+                errnote='Failed to download song information')
             api_data = json.loads(api_json)
-            track_data = api_data[u'set']['track']
+            track_data = api_data['set']['track']
             info = {
-                'id': track_data['id'],
+                'id': compat_str(track_data['id']),
                 'url': track_data['track_file_stream_url'],
                 'title': track_data['performer'] + u' - ' + track_data['name'],
                 'raw_title': track_data['name'],
                 'uploader_id': data['user']['login'],
                 'ext': 'm4a',
             }
-            res.append(info)
-            next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id'])
-        return res
+            entries.append(info)
+            next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (
+                session, mix_id, track_data['id'])
+        return {
+            '_type': 'playlist',
+            'entries': entries,
+            'id': compat_str(mix_id),
+            'display_id': playlist_id,
+            'title': data.get('name'),
+            'description': data.get('description'),
+        }

youtube_dl/extractor/empflix.py

@@ -1,54 +1,25 @@
 from __future__ import unicode_literals
 
-import re
-
-from .common import InfoExtractor
+from .tnaflix import TNAFlixIE
 
 
-class EmpflixIE(InfoExtractor):
-    _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html'
+class EMPFlixIE(TNAFlixIE):
+    _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<display_id>[0-9a-zA-Z-]+)-(?P<id>[0-9]+)\.html'
+
+    _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"'
+    _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"'
+    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
+
     _TEST = {
         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
         'md5': 'b1bc15b6412d33902d6e5952035fcabc',
         'info_dict': {
             'id': '33051',
+            'display_id': 'Amateur-Finger-Fuck',
             'ext': 'mp4',
             'title': 'Amateur Finger Fuck',
             'description': 'Amateur solo finger fucking.',
+            'thumbnail': 're:https?://.*\.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)
-        age_limit = self._rta_search(webpage)
-
-        video_title = self._html_search_regex(
-            r'name="title" value="(?P<title>[^"]*)"', webpage, 'title')
-        video_description = self._html_search_regex(
-            r'name="description" value="([^"]*)"', webpage, 'description', fatal=False)
-
-        cfg_url = self._html_search_regex(
-            r'flashvars\.config = escape\("([^"]+)"',
-            webpage, 'flashvars.config')
-
-        cfg_xml = self._download_xml(
-            cfg_url, video_id, note='Downloading metadata')
-
-        formats = [
-            {
-                'url': item.find('videoLink').text,
-                'format_id': item.find('res').text,
-            } for item in cfg_xml.findall('./quality/item')
-        ]
-
-        return {
-            'id': video_id,
-            'title': video_title,
-            'description': video_description,
-            'formats': formats,
-            'age_limit': age_limit,
-        }

youtube_dl/extractor/eporner.py

@@ -0,0 +1,75 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    str_to_int,
+)
+
+
+class EpornerIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<display_id>[\w-]+)'
+    _TEST = {
+        'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
+        'md5': '3b427ae4b9d60619106de3185c2987cd',
+        'info_dict': {
+            'id': '95008',
+            'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
+            'ext': 'flv',
+            'title': 'Infamous Tiffany Teen Strip Tease Video',
+            'duration': 194,
+            'view_count': int,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+        title = self._html_search_regex(
+            r'<title>(.*?) - EPORNER', webpage, 'title')
+
+        redirect_code = self._html_search_regex(
+            r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id,
+            webpage, 'redirect_code')
+        redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code)
+        player_code = self._download_webpage(
+            redirect_url, display_id, note='Downloading player config')
+
+        sources = self._search_regex(
+            r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources')
+
+        formats = []
+        for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources):
+            fmt = {
+                'url': video_url,
+                'format_id': format_id,
+            }
+            m = re.search(r'^(\d+)', format_id)
+            if m:
+                fmt['height'] = int(m.group(1))
+            formats.append(fmt)
+        self._sort_formats(formats)
+
+        duration = parse_duration(self._search_regex(
+            r'class="mbtim">([0-9:]+)</div>', webpage, 'duration',
+            fatal=False))
+        view_count = str_to_int(self._search_regex(
+            r'id="cinemaviews">\s*([0-9,]+)\s*<small>views',
+            webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+            'age_limit': self._rta_search(webpage),
+        }

youtube_dl/extractor/everyonesmixtape.py

@@ -12,10 +12,11 @@ from ..utils import (
 class EveryonesMixtapeIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?everyonesmixtape\.com/#/mix/(?P<id>[0-9a-zA-Z]+)(?:/(?P<songnr>[0-9]))?$'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi/5',
-        'file': '5bfseWNmlds.mp4',
         "info_dict": {
+            'id': '5bfseWNmlds',
+            'ext': 'mp4',
             "title": "Passion Pit - \"Sleepyhead\" (Official Music Video)",
             "uploader": "FKR.TV",
             "uploader_id": "frenchkissrecords",
@@ -25,7 +26,14 @@ class EveryonesMixtapeIE(InfoExtractor):
         'params': {
             'skip_download': True,  # This is simply YouTube
         }
-    }
+    }, {
+        'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi',
+        'info_dict': {
+            'id': 'm7m0jJAbMQi',
+            'title': 'Driving',
+        },
+        'playlist_count': 24
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/facebook.py

@@ -21,14 +21,14 @@ class FacebookIE(InfoExtractor):
     _VALID_URL = r'''(?x)
         https?://(?:\w+\.)?facebook\.com/
         (?:[^#]*?\#!/)?
-        (?:video/video\.php|photo\.php|video/embed)\?(?:.*?)
+        (?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?)
         (?:v|video_id)=(?P<id>[0-9]+)
         (?:.*)'''
     _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
     _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
     _NETRC_MACHINE = 'facebook'
     IE_NAME = 'facebook'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://www.facebook.com/photo.php?v=120708114770723',
         'md5': '48975a41ccc4b7a581abd68651c1a5a8',
         'info_dict': {
@@ -37,7 +37,10 @@ class FacebookIE(InfoExtractor):
             'duration': 279,
             'title': 'PEOPLE ARE AWESOME 2013',
         }
-    }
+    }, {
+        'url': 'https://www.facebook.com/video.php?v=10204634152394104',
+        'only_matching': True,
+    }]
 
     def _login(self):
         (useremail, password) = self._get_login_info()
@@ -76,7 +79,8 @@ class FacebookIE(InfoExtractor):
 
             check_form = {
                 'fb_dtsg': self._search_regex(r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg'),
-                'h': self._search_regex(r'name="h" value="(\w*?)"', login_results, 'h'),
+                'h': self._search_regex(
+                    r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'),
                 'name_action_selected': 'dont_save',
             }
             check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))

youtube_dl/extractor/gameone.py

@@ -88,3 +88,28 @@ class GameOneIE(InfoExtractor):
             'age_limit': age_limit,
             'timestamp': timestamp,
         }
+
+
+class GameOnePlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?gameone\.de(?:/tv)?/?$'
+    IE_NAME = 'gameone:playlist'
+    _TEST = {
+        'url': 'http://www.gameone.de/tv',
+        'info_dict': {
+            'title': 'GameOne',
+        },
+        'playlist_mincount': 294,
+    }
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage('http://www.gameone.de/tv', 'TV')
+        max_id = max(map(int, re.findall(r'<a href="/tv/(\d+)"', webpage)))
+        entries = [
+            self.url_result('http://www.gameone.de/tv/%d' % video_id, 'GameOne')
+            for video_id in range(max_id, 0, -1)]
+
+        return {
+            '_type': 'playlist',
+            'title': 'GameOne',
+            'entries': entries,
+        }

youtube_dl/extractor/generic.py

@@ -8,12 +8,11 @@ import re
 from .common import InfoExtractor
 from .youtube import YoutubeIE
 from ..utils import (
-    compat_urllib_error,
     compat_urllib_parse,
-    compat_urllib_request,
     compat_urlparse,
     compat_xml_parse_error,
 
+    determine_ext,
     ExtractorError,
     float_or_none,
     HEADRequest,
@@ -343,7 +342,46 @@ class GenericIE(InfoExtractor):
                 'uploader': 'www.handjobhub.com',
                 'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub',
             }
-        }
+        },
+        # RSS feed
+        {
+            'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+            'info_dict': {
+                'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+                'title': 'Zero Punctuation',
+                'description': 're:'
+            },
+            'playlist_mincount': 11,
+        },
+        # Multiple brightcove videos
+        # https://github.com/rg3/youtube-dl/issues/2283
+        {
+            'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
+            'info_dict': {
+                'id': 'always-never',
+                'title': 'Always / Never - The New Yorker',
+            },
+            'playlist_count': 3,
+            'params': {
+                'extract_flat': False,
+                'skip_download': True,
+            }
+        },
+        # MLB embed
+        {
+            'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
+            'md5': '96f09a37e44da40dd083e12d9a683327',
+            'info_dict': {
+                'id': '33322633',
+                'ext': 'mp4',
+                'title': 'Ump changes call to ball',
+                'description': 'md5:71c11215384298a172a6dcb4c2e20685',
+                'duration': 48,
+                'timestamp': 1401537900,
+                'upload_date': '20140531',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
     ]
 
     def report_download_webpage(self, video_id):
@@ -356,58 +394,6 @@ class GenericIE(InfoExtractor):
         """Report information extraction."""
         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
 
-    def _send_head(self, url):
-        """Check if it is a redirect, like url shorteners, in case return the new url."""
-
-        class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
-            """
-            Subclass the HTTPRedirectHandler to make it use our
-            HEADRequest also on the redirected URL
-            """
-            def redirect_request(self, req, fp, code, msg, headers, newurl):
-                if code in (301, 302, 303, 307):
-                    newurl = newurl.replace(' ', '%20')
-                    newheaders = dict((k,v) for k,v in req.headers.items()
-                                      if k.lower() not in ("content-length", "content-type"))
-                    try:
-                        # This function was deprecated in python 3.3 and removed in 3.4
-                        origin_req_host = req.get_origin_req_host()
-                    except AttributeError:
-                        origin_req_host = req.origin_req_host
-                    return HEADRequest(newurl,
-                                       headers=newheaders,
-                                       origin_req_host=origin_req_host,
-                                       unverifiable=True)
-                else:
-                    raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
-
-        class HTTPMethodFallback(compat_urllib_request.BaseHandler):
-            """
-            Fallback to GET if HEAD is not allowed (405 HTTP error)
-            """
-            def http_error_405(self, req, fp, code, msg, headers):
-                fp.read()
-                fp.close()
-
-                newheaders = dict((k,v) for k,v in req.headers.items()
-                                  if k.lower() not in ("content-length", "content-type"))
-                return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
-                                                 headers=newheaders,
-                                                 origin_req_host=req.get_origin_req_host(),
-                                                 unverifiable=True))
-
-        # Build our opener
-        opener = compat_urllib_request.OpenerDirector()
-        for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
-                        HTTPMethodFallback, HEADRedirectHandler,
-                        compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
-            opener.add_handler(handler())
-
-        response = opener.open(HEADRequest(url))
-        if response is None:
-            raise ExtractorError('Invalid URL protocol')
-        return response
-
     def _extract_rss(self, url, video_id, doc):
         playlist_title = doc.find('./channel/title').text
         playlist_desc_el = doc.find('./channel/description')
@@ -511,9 +497,13 @@ class GenericIE(InfoExtractor):
 
         self.to_screen('%s: Requesting header' % video_id)
 
-        try:
-            response = self._send_head(url)
+        head_req = HEADRequest(url)
+        response = self._request_webpage(
+            head_req, video_id,
+            note=False, errnote='Could not send HEAD request to %s' % url,
+            fatal=False)
 
+        if response is not False:
             # Check for redirect
             new_url = response.geturl()
             if url != new_url:
@@ -541,10 +531,6 @@ class GenericIE(InfoExtractor):
                     'upload_date': upload_date,
                 }
 
-        except compat_urllib_error.HTTPError:
-            # This may be a stupid server that doesn't like HEAD, our UA, or so
-            pass
-
         try:
             webpage = self._download_webpage(url, video_id)
         except ValueError:
@@ -642,7 +628,7 @@ class GenericIE(InfoExtractor):
                 embedSWF\(?:\s*
             )
             (["\'])
-                (?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
+                (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
                 (?:embed|v)/.+?)
             \1''', webpage)
         if matches:
@@ -838,6 +824,12 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'SBS')
 
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://m\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'MLB')
+
         # Start with something easy: JW Player in SWFObject
         found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if not found:
@@ -863,7 +855,6 @@ class GenericIE(InfoExtractor):
                     \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s*
                         ["']?url["']?\s*:\s*["']([^"']+)["']
             ''', webpage)
-            assert found
         if not found:
             # Try to find twitter cards info
             found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
@@ -875,13 +866,14 @@ class GenericIE(InfoExtractor):
             if m_video_type is not None:
                 def check_video(vurl):
                     vpath = compat_urlparse.urlparse(vurl).path
-                    return '.' in vpath and not vpath.endswith('.swf')
+                    vext = determine_ext(vpath)
+                    return '.' in vpath and vext not in ('swf', 'png', 'jpg')
                 found = list(filter(
                     check_video,
                     re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)))
         if not found:
             # HTML5 video
-            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage)
+            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]+)? src="([^"]+)"', webpage)
         if not found:
             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'

youtube_dl/extractor/googlesearch.py

@@ -14,6 +14,14 @@ class GoogleSearchIE(SearchInfoExtractor):
     _MAX_RESULTS = 1000
     IE_NAME = 'video.google:search'
     _SEARCH_KEY = 'gvsearch'
+    _TEST = {
+        'url': 'gvsearch15:python language',
+        'info_dict': {
+            'id': 'python language',
+            'title': 'python language',
+        },
+        'playlist_count': 15,
+    }
 
     def _get_n_results(self, query, n):
         """Get a specified number of results for a query"""

youtube_dl/extractor/hornbunny.py

@@ -0,0 +1,56 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_duration,
+)
+
+
+class HornBunnyIE(InfoExtractor):
+    _VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html'
+    _TEST = {
+        'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html',
+        'md5': '95e40865aedd08eff60272b704852ad7',
+        'info_dict': {
+            'id': '5227',
+            'ext': 'flv',
+            'title': 'panty slut jerk off instruction',
+            'duration': 550,
+            '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, note='Downloading initial webpage')
+        title = self._html_search_regex(
+            r'class="title">(.*?)</h2>', webpage, 'title')
+        redirect_url = self._html_search_regex(
+            r'pg&settings=(.*?)\|0"\);', webpage, 'title')
+        webpage2 = self._download_webpage(redirect_url, video_id)
+        video_url = self._html_search_regex(
+            r'flvMask:(.*?);', webpage2, 'video_url')
+        
+        duration = parse_duration(self._search_regex(
+            r'<strong>Runtime:</strong>\s*([0-9:]+)</div>',
+            webpage, 'duration', fatal=False))
+        view_count = int_or_none(self._search_regex(
+            r'<strong>Views:</strong>\s*(\d+)</div>',
+            webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'ext': 'flv',
+            'duration': duration,
+            'view_count': view_count,
+            'age_limit': 18,
+        }

youtube_dl/extractor/hostingbulk.py

@@ -0,0 +1,84 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_request,
+    int_or_none,
+    urlencode_postdata,
+)
+
+
+class HostingBulkIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?hostingbulk\.com/
+        (?:embed-)?(?P<id>[A-Za-z0-9]{12})(?:-\d+x\d+)?\.html'''
+    _FILE_DELETED_REGEX = r'<b>File Not Found</b>'
+    _TEST = {
+        'url': 'http://hostingbulk.com/n0ulw1hv20fm.html',
+        'md5': '6c8653c8ecf7ebfa83b76e24b7b2fe3f',
+        'info_dict': {
+            'id': 'n0ulw1hv20fm',
+            'ext': 'mp4',
+            'title': 'md5:5afeba33f48ec87219c269e054afd622',
+            'filesize': 6816081,
+            'thumbnail': 're:^http://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        url = 'http://hostingbulk.com/{0:}.html'.format(video_id)
+
+        # Custom request with cookie to set language to English, so our file
+        # deleted regex would work.
+        request = compat_urllib_request.Request(
+            url, headers={'Cookie': 'lang=english'})
+        webpage = self._download_webpage(request, video_id)
+
+        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id,
+                                 expected=True)
+
+        title = self._html_search_regex(r'<h3>(.*?)</h3>', webpage, 'title')
+        filesize = int_or_none(
+            self._search_regex(
+                r'<small>\((\d+)\sbytes?\)</small>',
+                webpage,
+                'filesize',
+                fatal=False
+            )
+        )
+        thumbnail = self._search_regex(
+            r'<img src="([^"]+)".+?class="pic"',
+            webpage, 'thumbnail', fatal=False)
+
+        fields = dict(re.findall(r'''(?x)<input\s+
+            type="hidden"\s+
+            name="([^"]+)"\s+
+            value="([^"]*)"
+            ''', webpage))
+
+        request = compat_urllib_request.Request(url, urlencode_postdata(fields))
+        request.add_header('Content-type', 'application/x-www-form-urlencoded')
+        response = self._request_webpage(request, video_id,
+                                         'Submiting download request')
+        video_url = response.geturl()
+
+        formats = [{
+            'format_id': 'sd',
+            'filesize': filesize,
+            'url': video_url,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/ign.py

@@ -18,6 +18,7 @@ class IGNIE(InfoExtractor):
     _DESCRIPTION_RE = [
         r'<span class="page-object-description">(.+?)</span>',
         r'id="my_show_video">.*?<p>(.*?)</p>',
+        r'<meta name="description" content="(.*?)"',
     ]
 
     _TESTS = [
@@ -55,6 +56,17 @@ class IGNIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch',
+            'md5': '4e9a0bda1e5eebd31ddcf86ec0b9b3c7',
+            'info_dict': {
+                'id': '078fdd005f6d3c02f63d795faa1b984f',
+                'ext': 'mp4',
+                'title': 'Rewind Theater - Wild Trailer Gamescom 2014',
+                'description': 'Giant skeletons, bloody hunts, and captivating'
+                    ' natural beauty take our breath away.',
+            },
+        },
     ]
 
     def _find_video_id(self, webpage):
@@ -62,6 +74,7 @@ class IGNIE(InfoExtractor):
             r'data-video-id="(.+?)"',
             r'<object id="vid_(.+?)"',
             r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
+            r'class="hero-poster[^"]*?"[^>]*id="(.+?)"',
         ]
         return self._search_regex(res_id, webpage, 'video id')
 
@@ -70,10 +83,7 @@ class IGNIE(InfoExtractor):
         name_or_id = mobj.group('name_or_id')
         page_type = mobj.group('type')
         webpage = self._download_webpage(url, name_or_id)
-        if page_type == 'articles':
-            video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, 'video url')
-            return self.url_result(video_url, ie='IGN')
-        elif page_type != 'video':
+        if page_type != 'video':
             multiple_urls = re.findall(
                 '<param name="flashvars" value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
                 webpage)

youtube_dl/extractor/imdb.py

@@ -63,6 +63,14 @@ class ImdbListIE(InfoExtractor):
     IE_NAME = 'imdb:list'
     IE_DESC = 'Internet Movie Database lists'
     _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
+    _TEST = {
+        'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
+        'info_dict': {
+            'id': 'JFs9NWw6XI0',
+            'title': 'March 23, 2012 Releases',
+        },
+        'playlist_count': 7,
+    }
     
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/instagram.py

@@ -46,6 +46,30 @@ class InstagramUserIE(InfoExtractor):
     _VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
     IE_DESC = 'Instagram user profile'
     IE_NAME = 'instagram:user'
+    _TEST = {
+        'url': 'http://instagram.com/porsche',
+        'info_dict': {
+            'id': 'porsche',
+            'title': 'porsche',
+        },
+        'playlist_mincount': 2,
+        'playlist': [{
+            'info_dict': {
+                'id': '614605558512799803_462752227',
+                'ext': 'mp4',
+                'title': '#Porsche Intelligent Performance.',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'uploader': 'Porsche',
+                'uploader_id': 'porsche',
+                'timestamp': 1387486713,
+                'upload_date': '20131219',
+            },
+        }],
+        'params': {
+            'extract_flat': True,
+            'skip_download': True,
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/ivi.py

@@ -127,6 +127,21 @@ class IviCompilationIE(InfoExtractor):
     IE_DESC = 'ivi.ru compilations'
     IE_NAME = 'ivi:compilation'
     _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
+    _TESTS = [{
+        'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa',
+        'info_dict': {
+            'id': 'dvoe_iz_lartsa',
+            'title': 'Двое из ларца (2006 - 2008)',
+        },
+        'playlist_mincount': 24,
+    }, {
+        'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1',
+        'info_dict': {
+            'id': 'dvoe_iz_lartsa/season1',
+            'title': 'Двое из ларца (2006 - 2008) 1 сезон',
+        },
+        'playlist_mincount': 12,
+    }]
 
     def _extract_entries(self, html, compilation_id):
         return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi')

youtube_dl/extractor/izlesene.py

@@ -9,29 +9,50 @@ from ..utils import (
     parse_iso8601,
     determine_ext,
     int_or_none,
+    float_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,
-        }
-    }
+    _VALID_URL = r'''(?x)
+        https?://(?:(?:www|m)\.)?izlesene\.com/
+        (?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)
+        '''
+    _TESTS = [
+        {
+            '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': 'md5:253753e2655dde93f59f74b572454f6d',
+                'thumbnail': 're:^http://.*\.jpg',
+                'uploader_id': 'pelikzzle',
+                'timestamp': 1404298698,
+                'upload_date': '20140702',
+                'duration': 95.395,
+                'age_limit': 0,
+            }
+        },
+        {
+            'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997',
+            'md5': '97f09b6872bffa284cb7fa4f6910cb72',
+            'info_dict': {
+                'id': '17997',
+                'ext': 'mp4',
+                'title': 'Tarkan Dortmund 2006 Konseri',
+                'description': 'Tarkan Dortmund 2006 Konseri',
+                'thumbnail': 're:^http://.*\.jpg',
+                'uploader_id': 'parlayankiz',
+                'timestamp': 1163318593,
+                'upload_date': '20061112',
+                'duration': 253.666,
+                'age_limit': 0,
+            }
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -45,18 +66,19 @@ class IzleseneIE(InfoExtractor):
         thumbnail = self._og_search_thumbnail(webpage)
 
         uploader = self._html_search_regex(
-            r"adduserUsername\s*=\s*'([^']+)';", webpage, 'uploader', fatal=False, default='')
+            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
+        duration = float_or_none(self._html_search_regex(
+            r'"videoduration"\s*:\s*"([^"]+)"',
+            webpage, 'duration', fatal=False), scale=1000)
 
         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)
+            r'comment_count\s*=\s*\'([^\']+)\';',
+            webpage, 'comment_count', fatal=False)
 
         family_friendly = self._html_search_meta(
             'isFamilyFriendly', webpage, 'age limit', fatal=False)
@@ -66,20 +88,26 @@ class IzleseneIE(InfoExtractor):
         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='')
+        streams = self._html_search_regex(
+            r'"qualitylevel"\s*:\s*"([^"]+)"',
+            webpage, 'streams', 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
-            )
+        if streams:
+            for stream in streams.split('|'):
+                quality, url = re.search(r'\[(\w+)\](.+)', stream).groups()
+                formats.append({
+                    'format_id': '%sp' % quality if quality else 'sd',
+                    'url': url,
+                    'ext': ext,
+                })
+        else:
+            stream_url = self._search_regex(
+                r'"streamurl"\s?:\s?"([^"]+)"', webpage, 'stream URL')
             formats.append({
-                'url': json.get('streamurl'),
+                'format_id': 'sd',
+                'url': stream_url,
                 'ext': ext,
-                'format_id': '%sp' % quality if quality else 'sd',
             })
 
         return {

youtube_dl/extractor/khanacademy.py

@@ -9,21 +9,30 @@ from ..utils import (
 
 
 class KhanAcademyIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?khanacademy\.org/(?P<key>[^/]+)/(?:[^/]+/){,2}(?P<id>[^?#/]+)(?:$|[?#])'
+    _VALID_URL = r'^https?://(?:(?:www|api)\.)?khanacademy\.org/(?P<key>[^/]+)/(?:[^/]+/){,2}(?P<id>[^?#/]+)(?:$|[?#])'
     IE_NAME = 'KhanAcademy'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.khanacademy.org/video/one-time-pad',
-        'file': 'one-time-pad.mp4',
         'md5': '7021db7f2d47d4fff89b13177cb1e8f4',
         'info_dict': {
+            'id': 'one-time-pad',
+            'ext': 'mp4',
             'title': 'The one-time pad',
             'description': 'The perfect cipher',
             'duration': 176,
             'uploader': 'Brit Cruise',
             'upload_date': '20120411',
         }
-    }
+    }, {
+        'url': 'https://www.khanacademy.org/math/applied-math/cryptography',
+        'info_dict': {
+            'id': 'cryptography',
+            'title': 'Journey into cryptography',
+            'description': 'How have humans protected their secret messages through history? What has changed today?',
+        },
+        'playlist_mincount': 3,
+    }]
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)

youtube_dl/extractor/livestream.py

@@ -19,7 +19,7 @@ from ..utils import (
 class LivestreamIE(InfoExtractor):
     IE_NAME = 'livestream'
     _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
         'md5': '53274c76ba7754fb0e8d072716f2292b',
         'info_dict': {
@@ -31,7 +31,13 @@ class LivestreamIE(InfoExtractor):
             'view_count': int,
             'thumbnail': 're:^http://.*\.jpg$'
         }
-    }
+    }, {
+        'url': 'http://new.livestream.com/tedx/cityenglish',
+        'info_dict': {
+            'title': 'TEDCity2.0 (English)',
+        },
+        'playlist_mincount': 4,
+    }]
 
     def _parse_smil(self, video_id, smil_url):
         formats = []
@@ -111,34 +117,37 @@ class LivestreamIE(InfoExtractor):
         event_name = mobj.group('event_name')
         webpage = self._download_webpage(url, video_id or event_name)
 
-        og_video = self._og_search_video_url(webpage, 'player url', fatal=False, default=None)
-        if og_video is None:
-            config_json = self._search_regex(
-                r'window.config = ({.*?});', webpage, 'window config')
-            info = json.loads(config_json)['event']
-
-            def is_relevant(vdata, vid):
-                result = vdata['type'] == 'video'
-                if video_id is not None:
-                    result = result and compat_str(vdata['data']['id']) == vid
-                return result
-
-            videos = [self._extract_video_info(video_data['data'])
-                      for video_data in info['feed']['data']
-                      if is_relevant(video_data, video_id)]
-            if video_id is None:
-                # This is an event page:
-                return self.playlist_result(videos, info['id'], info['full_name'])
-            else:
-                if videos:
-                    return videos[0]
-        else:
+        og_video = self._og_search_video_url(
+            webpage, 'player url', fatal=False, default=None)
+        if og_video is not None:
             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, 'Downloading video info'))
-            return self._extract_video_info(info)
+            if 'play_url' in query:
+                api_url = query['play_url'][0].replace('.smil', '')
+                info = json.loads(self._download_webpage(
+                    api_url, video_id, 'Downloading video info'))
+                return self._extract_video_info(info)
+
+        config_json = self._search_regex(
+            r'window.config = ({.*?});', webpage, 'window config')
+        info = json.loads(config_json)['event']
+
+        def is_relevant(vdata, vid):
+            result = vdata['type'] == 'video'
+            if video_id is not None:
+                result = result and compat_str(vdata['data']['id']) == vid
+            return result
+
+        videos = [self._extract_video_info(video_data['data'])
+                  for video_data in info['feed']['data']
+                  if is_relevant(video_data, video_id)]
+        if video_id is None:
+            # This is an event page:
+            return self.playlist_result(videos, info['id'], info['full_name'])
+        else:
+            if not videos:
+                raise ExtractorError('Cannot find video %s' % video_id)
+            return videos[0]
 
 
 # The original version of Livestream uses a different system
@@ -148,7 +157,7 @@ class LivestreamOriginalIE(InfoExtractor):
         (?P<user>[^/]+)/(?P<type>video|folder)
         (?:\?.*?Id=|/)(?P<id>.*?)(&|$)
         '''
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
         'info_dict': {
             'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
@@ -159,7 +168,13 @@ class LivestreamOriginalIE(InfoExtractor):
             # rtmp
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'https://www.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3',
+        'info_dict': {
+            'id': 'a07bf706-d0e4-4e75-a747-b021d84f2fd3',
+        },
+        'playlist_mincount': 4,
+    }]
 
     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)
@@ -182,15 +197,19 @@ class LivestreamOriginalIE(InfoExtractor):
 
     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))
+        paths = orderedSet(re.findall(
+            r'''(?x)(?:
+                <li\s+class="folder">\s*<a\s+href="|
+                <a\s+href="(?=https?://livestre\.am/)
+            )([^"]+)"''', webpage))
 
         return {
             '_type': 'playlist',
             'id': folder_id,
             'entries': [{
                 '_type': 'url',
-                'url': video_url,
-            } for video_url in urls],
+                'url': compat_urlparse.urljoin(url, p),
+            } for p in paths],
         }
 
     def _real_extract(self, url):

youtube_dl/extractor/mixcloud.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
     ExtractorError,
+    HEADRequest,
     int_or_none,
     parse_iso8601,
 )
@@ -38,7 +39,7 @@ class MixcloudIE(InfoExtractor):
             try:
                 # We only want to know if the request succeed
                 # don't download the whole file
-                self._request_webpage(url, None, False)
+                self._request_webpage(HEADRequest(url), None, False)
                 return url
             except ExtractorError:
                 url = None

youtube_dl/extractor/mlb.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class MLBIE(InfoExtractor):
-    _VALID_URL = r'https?://m\.mlb\.com/(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v(?P<id>n?\d+)'
+    _VALID_URL = r'https?://m\.mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|shared/video/embed/embed\.html\?.*?\bcontent_id=)(?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',
@@ -69,6 +69,10 @@ class MLBIE(InfoExtractor):
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
         },
+        {
+            'url': 'http://m.mlb.com/shared/video/embed/embed.html?content_id=35692085&topic_id=6479266&width=400&height=224&property=mlb',
+            'only_matching': True,
+        },
     ]
 
     def _real_extract(self, url):

youtube_dl/extractor/moevideo.py

@@ -0,0 +1,112 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_parse,
+    compat_urllib_request,
+    int_or_none,
+)
+
+
+class MoeVideoIE(InfoExtractor):
+    IE_DESC = 'LetitBit video services: moevideo.net, playreplay.net and videochart.net'
+    _VALID_URL = r'''(?x)
+        https?://(?P<host>(?:www\.)?
+        (?:(?:moevideo|playreplay|videochart)\.net))/
+        (?:video|framevideo)/(?P<id>[0-9]+\.[0-9A-Za-z]+)'''
+    _API_URL = 'http://api.letitbit.net/'
+    _API_KEY = 'tVL0gjqo5'
+    _TESTS = [
+        {
+            'url': 'http://moevideo.net/video/00297.0036103fe3d513ef27915216fd29',
+            'md5': '129f5ae1f6585d0e9bb4f38e774ffb3a',
+            'info_dict': {
+                'id': '00297.0036103fe3d513ef27915216fd29',
+                'ext': 'flv',
+                'title': 'Sink cut out machine',
+                'description': 'md5:f29ff97b663aefa760bf7ca63c8ca8a8',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'width': 540,
+                'height': 360,
+                'duration': 179,
+                'filesize': 17822500,
+            }
+        },
+        {
+            'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',
+            'md5': '74f0a014d5b661f0f0e2361300d1620e',
+            'info_dict': {
+                'id': '77107.7f325710a627383d40540d8e991a',
+                'ext': 'flv',
+                'title': 'Operacion Condor.',
+                'description': 'md5:7e68cb2fcda66833d5081c542491a9a3',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'width': 480,
+                'height': 296,
+                'duration': 6027,
+                'filesize': 588257923,
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(
+            'http://%s/video/%s' % (mobj.group('host'), video_id),
+            video_id, 'Downloading webpage')
+
+        title = self._og_search_title(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+        description = self._og_search_description(webpage)
+
+        r = [
+            self._API_KEY,
+            [
+                'preview/flv_link',
+                {
+                    'uid': video_id,
+                },
+            ],
+        ]
+        r_json = json.dumps(r)
+        post = compat_urllib_parse.urlencode({'r': r_json})
+        req = compat_urllib_request.Request(self._API_URL, post)
+        req.add_header('Content-type', 'application/x-www-form-urlencoded')
+
+        response = self._download_json(req, video_id)
+        if response['status'] != 'OK':
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, response['data']),
+                expected=True
+            )
+        item = response['data'][0]
+        video_url = item['link']
+        duration = int_or_none(item['length'])
+        width = int_or_none(item['width'])
+        height = int_or_none(item['height'])
+        filesize = int_or_none(item['convert_size'])
+
+        formats = [{
+            'format_id': 'sd',
+            'http_headers': {'Range': 'bytes=0-'},  # Required to download
+            'url': video_url,
+            'width': width,
+            'height': height,
+            'filesize': filesize,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'description': description,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/mofosex.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import os
 import re
 
@@ -8,15 +10,17 @@ from ..utils import (
     compat_urllib_parse,
 )
 
+
 class MofosexIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)'
+    _VALID_URL = r'^https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)'
     _TEST = {
-        u'url': u'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
-        u'file': u'5018.mp4',
-        u'md5': u'1b2eb47ac33cc75d4a80e3026b613c5a',
-        u'info_dict': {
-            u"title": u"Japanese Teen Music Video",
-            u"age_limit": 18,
+        'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
+        'md5': '1b2eb47ac33cc75d4a80e3026b613c5a',
+        'info_dict': {
+            'id': '5018',
+            'ext': 'mp4',
+            'title': 'Japanese Teen Music Video',
+            'age_limit': 18,
         }
     }
 
@@ -29,8 +33,8 @@ class MofosexIE(InfoExtractor):
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
-        video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, u'title')
-        video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, u'video_url'))
+        video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title')
+        video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url'))
         path = compat_urllib_parse_urlparse(video_url).path
         extension = os.path.splitext(path)[1][1:]
         format = path.split('/')[5].split('_')[:2]

youtube_dl/extractor/musicvault.py

@@ -0,0 +1,76 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    unified_strdate,
+)
+
+
+class MusicVaultIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.musicvault\.com/(?P<uploader_id>[^/?#]*)/video/(?P<display_id>[^/?#]*)_(?P<id>[0-9]+)\.html'
+    _TEST = {
+        'url': 'http://www.musicvault.com/the-allman-brothers-band/video/straight-from-the-heart_1010863.html',
+        'md5': '2cdbb3ae75f7fb3519821507d2fb3c15',
+        'info_dict': {
+            'id': '1010863',
+            'ext': 'mp4',
+            'uploader_id': 'the-allman-brothers-band',
+            'title': 'Straight from the Heart',
+            'duration': 244,
+            'uploader': 'The Allman Brothers Band',
+            'thumbnail': 're:^https?://.*/thumbnail/.*',
+            'upload_date': '19811216',
+            'location': 'Capitol Theatre (Passaic, NJ)',
+            'description': 'Listen to The Allman Brothers Band perform Straight from the Heart at Capitol Theatre (Passaic, NJ) on Dec 16, 1981',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
+        webpage = self._download_webpage(url, display_id)
+
+        thumbnail = self._search_regex(
+            r'<meta itemprop="thumbnail" content="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        data_div = self._search_regex(
+            r'(?s)<div class="data">(.*?)</div>', webpage, 'data fields')
+        uploader = self._html_search_regex(
+            r'<h1.*?>(.*?)</h1>', data_div, 'uploader', fatal=False)
+        title = self._html_search_regex(
+            r'<h2.*?>(.*?)</h2>', data_div, 'title')
+        upload_date = unified_strdate(self._html_search_regex(
+            r'<h3.*?>(.*?)</h3>', data_div, 'uploader', fatal=False))
+        location = self._html_search_regex(
+            r'<h4.*?>(.*?)</h4>', data_div, 'location', fatal=False)
+
+        duration = parse_duration(self._html_search_meta('duration', webpage))
+
+        VIDEO_URL_TEMPLATE = 'http://cdnapi.kaltura.com/p/%(uid)s/sp/%(wid)s/playManifest/entryId/%(entry_id)s/format/url/protocol/http'
+        kaltura_id = self._search_regex(
+            r'<div id="video-detail-player" data-kaltura-id="([^"]+)"',
+            webpage, 'kaltura ID')
+        video_url = VIDEO_URL_TEMPLATE % {
+            'entry_id': kaltura_id,
+            'wid': self._search_regex(r'/wid/_([0-9]+)/', webpage, 'wid'),
+            'uid': self._search_regex(r'uiconf_id/([0-9]+)/', webpage, 'uid'),
+        }
+
+        return {
+            'id': mobj.group('id'),
+            'url': video_url,
+            'ext': 'mp4',
+            'display_id': display_id,
+            'uploader_id': mobj.group('uploader_id'),
+            'thumbnail': thumbnail,
+            'description': self._html_search_meta('description', webpage),
+            'upload_date': upload_date,
+            'location': location,
+            'title': title,
+            'uploader': uploader,
+            'duration': duration,
+        }

youtube_dl/extractor/nba.py

@@ -3,18 +3,23 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import (
+    remove_end,
+    parse_duration,
+)
 
 
 class NBAIE(InfoExtractor):
     _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
     _TEST = {
         'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
-        'md5': u'c0edcfc37607344e2ff8f13c378c88a4',
+        'md5': 'c0edcfc37607344e2ff8f13c378c88a4',
         'info_dict': {
             'id': '0021200253-okc-bkn-recap.nba',
             'ext': 'mp4',
-            'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
             'title': 'Thunder vs. Nets',
+            'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
+            'duration': 181,
         },
     }
 
@@ -27,13 +32,18 @@ class NBAIE(InfoExtractor):
         video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
 
         shortened_video_id = video_id.rpartition('/')[2]
-        title = self._og_search_title(webpage, default=shortened_video_id).replace('NBA.com: ', '')
+        title = remove_end(
+            self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com')
+
+        description = self._og_search_description(webpage)
+        duration = parse_duration(
+            self._html_search_meta('duration', webpage, 'duration', fatal=False))
 
-        description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False)
 
         return {
             'id': shortened_video_id,
             'url': video_url,
             'title': title,
             'description': description,
+            'duration': duration,
         }

youtube_dl/extractor/nhl.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
@@ -25,8 +27,8 @@ class NHLBaseInfoExtractor(InfoExtractor):
             'path': initial_video_url.replace('.mp4', '_sd.mp4'),
         })
         path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
-        path_doc = self._download_xml(path_url, video_id,
-            u'Downloading final video url')
+        path_doc = self._download_xml(
+            path_url, video_id, 'Downloading final video url')
         video_url = path_doc.find('path').text
 
         join = compat_urlparse.urljoin
@@ -43,17 +45,18 @@ class NHLBaseInfoExtractor(InfoExtractor):
 
 
 class NHLIE(NHLBaseInfoExtractor):
-    IE_NAME = u'nhl.com'
-    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console\?.*?(?<=[?&])id=(?P<id>\d+)'
+    IE_NAME = 'nhl.com'
+    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console\?.*?(?:[?&])id=(?P<id>[0-9]+)'
 
     _TEST = {
-        u'url': u'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
-        u'file': u'453614.mp4',
-        u'info_dict': {
-            u'title': u'Quick clip: Weise 4-3 goal vs Flames',
-            u'description': u'Dale Weise scores his first of the season to put the Canucks up 4-3.',
-            u'duration': 18,
-            u'upload_date': u'20131006',
+        'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
+        'info_dict': {
+            'id': '453614',
+            'ext': 'mp4',
+            'title': 'Quick clip: Weise 4-3 goal vs Flames',
+            'description': 'Dale Weise scores his first of the season to put the Canucks up 4-3.',
+            'duration': 18,
+            'upload_date': '20131006',
         },
     }
 
@@ -61,23 +64,23 @@ class NHLIE(NHLBaseInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id
-        info_json = self._download_webpage(json_url, video_id,
-            u'Downloading info json')
-        info_json = self._fix_json(info_json)
-        info = json.loads(info_json)[0]
-        return self._extract_video(info)
+        data = self._download_json(
+            json_url, video_id, transform_source=self._fix_json)
+        return self._extract_video(data[0])
 
 
 class NHLVideocenterIE(NHLBaseInfoExtractor):
-    IE_NAME = u'nhl.com:videocenter'
-    IE_DESC = u'NHL videocenter category'
-    _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[^&]+))?'
-
-    @classmethod
-    def suitable(cls, url):
-        if NHLIE.suitable(url):
-            return False
-        return super(NHLVideocenterIE, cls).suitable(url)
+    IE_NAME = 'nhl.com:videocenter'
+    IE_DESC = 'NHL videocenter category'
+    _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$'
+    _TEST = {
+        'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999',
+        'info_dict': {
+            'id': '999',
+            'title': 'Highlights',
+        },
+        'playlist_count': 12,
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -86,10 +89,10 @@ class NHLVideocenterIE(NHLBaseInfoExtractor):
         cat_id = self._search_regex(
             [r'var defaultCatId = "(.+?)";',
              r'{statusIndex:0,index:0,.*?id:(.*?),'],
-            webpage, u'category id')
+            webpage, 'category id')
         playlist_title = self._html_search_regex(
             r'tab0"[^>]*?>(.*?)</td>',
-            webpage, u'playlist title', flags=re.DOTALL).lower().capitalize()
+            webpage, 'playlist title', flags=re.DOTALL).lower().capitalize()
 
         data = compat_urllib_parse.urlencode({
             'cid': cat_id,
@@ -104,7 +107,7 @@ class NHLVideocenterIE(NHLBaseInfoExtractor):
         response = self._fix_json(response)
         if not response.strip():
             self._downloader.report_warning(u'Got an empty reponse, trying '
-                                            u'adding the "newvideos" parameter')
+                                            'adding the "newvideos" parameter')
             response = self._download_webpage(request_url + '&newvideos=true',
                 playlist_title)
             response = self._fix_json(response)
@@ -114,5 +117,5 @@ class NHLVideocenterIE(NHLBaseInfoExtractor):
             '_type': 'playlist',
             'title': playlist_title,
             'id': cat_id,
-            'entries': [self._extract_video(i) for i in videos],
+            'entries': [self._extract_video(v) for v in videos],
         }

youtube_dl/extractor/noco.py

@@ -5,7 +5,10 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    compat_urllib_request,
+    compat_urllib_parse,
     ExtractorError,
+    clean_html,
     unified_strdate,
     compat_str,
 )
@@ -13,6 +16,8 @@ from ..utils import (
 
 class NocoIE(InfoExtractor):
     _VALID_URL = r'http://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
+    _LOGIN_URL = 'http://noco.tv/do.php'
+    _NETRC_MACHINE = 'noco'
 
     _TEST = {
         'url': 'http://noco.tv/emission/11538/nolife/ami-ami-idol-hello-france/',
@@ -30,6 +35,28 @@ class NocoIE(InfoExtractor):
         'skip': 'Requires noco account',
     }
 
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_form = {
+            'a': 'login',
+            'cookie': '1',
+            'username': username,
+            'password': password,
+        }
+        request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8')
+
+        login = self._download_json(request, None, 'Logging in as %s' % username)
+
+        if 'erreur' in login:
+            raise  ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True)
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')

youtube_dl/extractor/nosvideo.py

@@ -0,0 +1,70 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_request,
+    urlencode_postdata,
+    xpath_with_ns,
+)
+
+_x = lambda p: xpath_with_ns(p, {'xspf': 'http://xspf.org/ns/0/'})
+_find = lambda el, p: el.find(_x(p)).text.strip()
+
+
+class NosVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \
+                 '(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?'
+    _PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml'
+    _FILE_DELETED_REGEX = r'<b>File Not Found</b>'
+    _TEST = {
+        'url': 'http://nosvideo.com/?v=mu8fle7g7rpq',
+        'md5': '6124ed47130d8be3eacae635b071e6b6',
+        'info_dict': {
+            'id': 'mu8fle7g7rpq',
+            'ext': 'mp4',
+            'title': 'big_buck_bunny_480p_surround-fix.avi.mp4',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        fields = {
+            'id': video_id,
+            'op': 'download1',
+            'method_free': 'Continue to Video',
+        }
+        req = compat_urllib_request.Request(url, urlencode_postdata(fields))
+        req.add_header('Content-type', 'application/x-www-form-urlencoded')
+        webpage = self._download_webpage(req, video_id,
+                                         'Downloading download page')
+        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id,
+                                 expected=True)
+
+        xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID')
+        playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id)
+        playlist = self._download_xml(playlist_url, video_id)
+
+        track = playlist.find(_x('.//xspf:track'))
+        title = _find(track, './xspf:title')
+        url = _find(track, './xspf:file')
+        thumbnail = _find(track, './xspf:image')
+
+        formats = [{
+            'format_id': 'sd',
+            'url': url,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/npo.py

@@ -5,6 +5,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     unified_strdate,
+    qualities,
 )
 
 
@@ -17,7 +18,7 @@ class NPOIE(InfoExtractor):
         'md5': '4b3f9c429157ec4775f2c9cb7b911016',
         'info_dict': {
             'id': 'VPWON_1220719',
-            'ext': 'mp4',
+            'ext': 'm4v',
             'title': 'Nieuwsuur',
             'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
             'upload_date': '20140622',
@@ -39,24 +40,32 @@ class NPOIE(InfoExtractor):
             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
-        )
+        token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token')
 
-        stream_info = self._download_json(
-            streams_info['streams'][0] + '&type=json',
-            video_id,
-            'Downloading stream info'
-        )
+        formats = []
+        quality = qualities(['adaptive', 'h264_sb', 'h264_bb', 'h264_std'])
+        for format_id in metadata['pubopties']:
+            streams_info = self._download_json(
+                'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s' % (video_id, format_id, token),
+                video_id, 'Downloading %s streams info' % format_id)
+            stream_info = self._download_json(
+                streams_info['streams'][0] + '&type=json',
+                video_id, 'Downloading %s stream info' % format_id)
+            if format_id == 'adaptive':
+                formats.extend(self._extract_m3u8_formats(stream_info['url'], video_id))
+            else:
+                formats.append({
+                    'url': stream_info['url'],
+                    'format_id': format_id,
+                    'quality': quality(format_id),
+                })
+        self._sort_formats(formats)
 
         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']),
+            'formats': formats,
         }

youtube_dl/extractor/promptfile.py

@@ -0,0 +1,67 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    determine_ext,
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+
+
+class PromptFileIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)'
+    _FILE_NOT_FOUND_REGEX = r'<div.+id="not_found_msg".+>.+</div>[^-]'
+    _TEST = {
+        'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF',
+        'md5': 'd1451b6302da7215485837aaea882c4c',
+        'info_dict': {
+            'id': 'D21B4746E9-F01462F0FF',
+            'ext': 'mp4',
+            'title': 'Birds.mp4',
+            '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)
+
+        if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id,
+                                 expected=True)
+
+        fields = dict(re.findall(r'''(?x)type="hidden"\s+
+            name="(.+?)"\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')
+        webpage = self._download_webpage(
+            req, video_id, 'Downloading video page')
+
+        url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL')
+        title = self._html_search_regex(
+            r'<span.+title="([^"]+)">', webpage, 'title')
+        thumbnail = self._html_search_regex(
+            r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"',
+            webpage, 'thumbnail', fatal=False, flags=re.DOTALL)
+
+        formats = [{
+            'format_id': 'sd',
+            'url': url,
+            'ext': determine_ext(title),
+        }]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/rtlnl.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import parse_duration
 
 
 class RtlXlIE(InfoExtractor):
@@ -11,20 +12,15 @@ class RtlXlIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/6e4203a6-0a5e-3596-8424-c599a59e0677',
+        'md5': 'cc16baa36a6c169391f0764fa6b16654',
         'info_dict': {
             'id': '6e4203a6-0a5e-3596-8424-c599a59e0677',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'RTL Nieuws - Laat',
-            'description': 'Dagelijks het laatste nieuws uit binnen- en '
-                'buitenland. Voor nog meer nieuws kunt u ook gebruikmaken van '
-                'onze mobiele apps.',
+            'description': 'md5:6b61f66510c8889923b11f2778c72dc5',
             'timestamp': 1408051800,
             'upload_date': '20140814',
-        },
-        'params': {
-            # We download the first bytes of the first fragment, it can't be
-            # processed by the f4m downloader beacuse it isn't complete
-            'skip_download': True,
+            'duration': 576.880,
         },
     }
 
@@ -35,17 +31,37 @@ class RtlXlIE(InfoExtractor):
         info = self._download_json(
             'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid,
             uuid)
+
         material = info['material'][0]
         episode_info = info['episodes'][0]
 
-        f4m_url = 'http://manifest.us.rtl.nl' + material['videopath']
         progname = info['abstracts'][0]['name']
         subtitle = material['title'] or info['episodes'][0]['name']
 
+        videopath = material['videopath']
+        f4m_url = 'http://manifest.us.rtl.nl' + videopath
+
+        formats = self._extract_f4m_formats(f4m_url, uuid)
+
+        video_urlpart = videopath.split('/flash/')[1][:-4]
+        PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4'
+
+        formats.extend([
+            {
+                'url': PG_URL_TEMPLATE % ('a2m', video_urlpart),
+                'format_id': 'pg-sd',
+            },
+            {
+                'url': PG_URL_TEMPLATE % ('a3m', video_urlpart),
+                'format_id': 'pg-hd',
+            }
+        ])
+
         return {
             'id': uuid,
-            'title': '%s - %s' % (progname, subtitle), 
-            'formats': self._extract_f4m_formats(f4m_url, uuid),
+            'title': '%s - %s' % (progname, subtitle),
+            'formats': formats,
             'timestamp': material['original_date'],
             'description': episode_info['synopsis'],
+            'duration': parse_duration(material.get('duration')),
         }

youtube_dl/extractor/rutube.py

@@ -74,6 +74,13 @@ class RutubeChannelIE(InfoExtractor):
     IE_NAME = 'rutube:channel'
     IE_DESC = 'Rutube channels'
     _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://rutube.ru/tags/video/1800/',
+        'info_dict': {
+            'id': '1800',
+        },
+        'playlist_mincount': 68,
+    }]
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 
@@ -101,6 +108,7 @@ class RutubeMovieIE(RutubeChannelIE):
     IE_NAME = 'rutube:movie'
     IE_DESC = 'Rutube movies'
     _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
+    _TESTS = []
 
     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
@@ -119,5 +127,12 @@ class RutubePersonIE(RutubeChannelIE):
     IE_NAME = 'rutube:person'
     IE_DESC = 'Rutube person videos'
     _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://rutube.ru/video/person/313878/',
+        'info_dict': {
+            'id': '313878',
+        },
+        'playlist_mincount': 37,
+    }]
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'

youtube_dl/extractor/rutv.py

@@ -100,7 +100,7 @@ class RUTVIE(InfoExtractor):
             return mobj.group('url')
 
         mobj = re.search(
-            r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>http://player\.(?:rutv\.ru|vgtrk\.com)/flash2v/container\.swf\?id=.+?\2)',
+            r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/flash2v/container\.swf\?id=.+?\2)',
             webpage)
         if mobj:
             return mobj.group('url')

youtube_dl/extractor/sharesix.py

@@ -0,0 +1,91 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    compat_urllib_request,
+    parse_duration,
+)
+
+
+class ShareSixIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?sharesix\.com/(?:f/)?(?P<id>[0-9a-zA-Z]+)'
+    _TESTS = [
+        {
+            'url': 'http://sharesix.com/f/OXjQ7Y6',
+            'md5': '9e8e95d8823942815a7d7c773110cc93',
+            'info_dict': {
+                'id': 'OXjQ7Y6',
+                'ext': 'mp4',
+                'title': 'big_buck_bunny_480p_surround-fix.avi',
+                'duration': 596,
+                'width': 854,
+                'height': 480,
+            },
+        },
+        {
+            'url': 'http://sharesix.com/lfrwoxp35zdd',
+            'md5': 'dd19f1435b7cec2d7912c64beeee8185',
+            'info_dict': {
+                'id': 'lfrwoxp35zdd',
+                'ext': 'flv',
+                'title': 'WhiteBoard___a_Mac_vs_PC_Parody_Cartoon.mp4.flv',
+                'duration': 65,
+                'width': 1280,
+                'height': 720,
+            },
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        fields = {
+            'method_free': 'Free'
+        }
+        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')
+
+        video_url = self._search_regex(
+            r"var\slnk1\s=\s'([^']+)'", webpage, 'video URL')
+        title = self._html_search_regex(
+            r'(?s)<dt>Filename:</dt>.+?<dd>(.+?)</dd>', webpage, 'title')
+        duration = parse_duration(
+            self._search_regex(
+                r'(?s)<dt>Length:</dt>.+?<dd>(.+?)</dd>',
+                webpage,
+                'duration',
+                fatal=False
+            )
+        )
+
+        m = re.search(
+            r'''(?xs)<dt>Width\sx\sHeight</dt>.+?
+                     <dd>(?P<width>\d+)\sx\s(?P<height>\d+)</dd>''',
+            webpage
+        )
+        width = height = None
+        if m:
+            width, height = int(m.group('width')), int(m.group('height'))
+
+        formats = [{
+            'format_id': 'sd',
+            'url': video_url,
+            'width': width,
+            'height': height,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/smotri.py

@@ -267,6 +267,14 @@ class SmotriCommunityIE(InfoExtractor):
     IE_DESC = 'Smotri.com community videos'
     IE_NAME = 'smotri:community'
     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
+    _TEST = {
+        'url': 'http://smotri.com/community/video/kommuna',
+        'info_dict': {
+            'id': 'kommuna',
+            'title': 'КПРФ',
+        },
+        'playlist_mincount': 4,
+    }
     
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -289,6 +297,14 @@ class SmotriUserIE(InfoExtractor):
     IE_DESC = 'Smotri.com user videos'
     IE_NAME = 'smotri:user'
     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
+    _TESTS = [{
+        'url': 'http://smotri.com/user/inspector',
+        'info_dict': {
+            'id': 'inspector',
+            'title': 'Inspector',
+        },
+        'playlist_mincount': 9,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/sockshare.py

@@ -61,7 +61,10 @@ class SockshareIE(InfoExtractor):
             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')
+        title = self._html_search_regex((
+            r'<h1>(.+)<strong>',
+            r'var name = "([^"]+)";'),
+            webpage, 'title', default=None)
         thumbnail = self._html_search_regex(
             r'<img\s+src="([^"]*)".+?name="bg"',
             webpage, 'thumbnail')

youtube_dl/extractor/soundcloud.py

@@ -28,7 +28,8 @@ class SoundcloudIE(InfoExtractor):
     _VALID_URL = r'''(?x)^(?:https?://)?
                     (?:(?:(?:www\.|m\.)?soundcloud\.com/
                             (?P<uploader>[\w\d-]+)/
-                            (?!sets/)(?P<title>[\w\d-]+)/?
+                            (?!sets/|likes/?(?:$|[?#]))
+                            (?P<title>[\w\d-]+)/?
                             (?P<token>[^?]+?)?(?:[?].*)?$)
                        |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
                        |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*)
@@ -221,13 +222,16 @@ class SoundcloudIE(InfoExtractor):
 class SoundcloudSetIE(SoundcloudIE):
     _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
     IE_NAME = 'soundcloud:set'
-    # it's in tests/test_playlists.py
-    _TESTS = []
+    _TESTS = [{
+        'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep',
+        'info_dict': {
+            'title': 'The Royal Concept EP',
+        },
+        'playlist_mincount': 6,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError('Invalid URL: %s' % url)
 
         # extract uploader (which is in the url)
         uploader = mobj.group(1)
@@ -246,20 +250,32 @@ class SoundcloudSetIE(SoundcloudIE):
                 self._downloader.report_error('unable to download video webpage: %s' % compat_str(err['error_message']))
             return
 
-        self.report_extraction(full_title)
-        return {'_type': 'playlist',
-                'entries': [self._extract_info_dict(track) for track in info['tracks']],
-                'id': info['id'],
-                'title': info['title'],
-                }
+        return {
+            '_type': 'playlist',
+            'entries': [self._extract_info_dict(track) for track in info['tracks']],
+            'id': info['id'],
+            'title': info['title'],
+        }
 
 
 class SoundcloudUserIE(SoundcloudIE):
     _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)/?((?P<rsrc>tracks|likes)/?)?(\?.*)?$'
     IE_NAME = 'soundcloud:user'
-
-    # it's in tests/test_playlists.py
-    _TESTS = []
+    _TESTS = [{
+        'url': 'https://soundcloud.com/the-concept-band',
+        'info_dict': {
+            'id': '9615865',
+            'title': 'The Royal Concept',
+        },
+        'playlist_mincount': 12
+    }, {
+        'url': 'https://soundcloud.com/the-concept-band/likes',
+        'info_dict': {
+            'id': '9615865',
+            'title': 'The Royal Concept',
+        },
+        'playlist_mincount': 1,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -301,9 +317,18 @@ class SoundcloudUserIE(SoundcloudIE):
 class SoundcloudPlaylistIE(SoundcloudIE):
     _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)'
     IE_NAME = 'soundcloud:playlist'
+    _TESTS = [
 
-     # it's in tests/test_playlists.py
-    _TESTS = []
+        {
+            'url': 'http://api.soundcloud.com/playlists/4110309',
+            'info_dict': {
+                'id': '4110309',
+                'title': 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]',
+                'description': 're:.*?TILT Brass - Bowery Poetry Club',
+            },
+            'playlist_count': 6,
+        }
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/sportdeutschland.py

@@ -0,0 +1,96 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    parse_iso8601,
+)
+
+
+class SportDeutschlandIE(InfoExtractor):
+    _VALID_URL = r'https?://sportdeutschland\.tv/(?P<sport>[^/?#]+)/(?P<id>[^?#/]+)(?:$|[?#])'
+    _TESTS = [{
+        'url': 'http://sportdeutschland.tv/badminton/live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen',
+        'info_dict': {
+            'id': 'live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen',
+            'ext': 'mp4',
+            'title': 'LIVE: Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen',
+            'categories': ['Badminton'],
+            'view_count': int,
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 're:^Die Badminton-WM 2014 aus Kopenhagen LIVE',
+            'timestamp': int,
+            'upload_date': 're:^201408[23][0-9]$',
+        },
+        'params': {
+            'skip_download': 'Live stream',
+        },
+    }, {
+        'url': 'http://sportdeutschland.tv/li-ning-badminton-wm-2014/lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs',
+        'info_dict': {
+            'id': 'lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs',
+            'ext': 'mp4',
+            'upload_date': '20140825',
+            'description': 'md5:60a20536b57cee7d9a4ec005e8687504',
+            'timestamp': 1408976060,
+            'title': 'Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen: Herren Einzel, Wei Lee vs. Keun Lee',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'view_count': int,
+            'categories': ['Li-Ning Badminton WM 2014'],
+        }
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        sport_id = mobj.group('sport')
+
+        api_url = 'http://splink.tv/api/permalinks/%s/%s' % (
+            sport_id, video_id)
+        req = compat_urllib_request.Request(api_url, headers={
+            'Accept': 'application/vnd.vidibus.v2.html+json',
+            'Referer': url,
+        })
+        data = self._download_json(req, video_id)
+
+        categories = list(data.get('section', {}).get('tags', {}).values())
+        asset = data['asset']
+
+        formats = []
+        smil_url = asset['video']
+        if '.smil' in smil_url:
+            m3u8_url = smil_url.replace('.smil', '.m3u8')
+            formats.extend(
+                self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4'))
+
+            smil_doc = self._download_xml(
+                smil_url, video_id, note='Downloading SMIL metadata')
+            base_url = smil_doc.find('./head/meta').attrib['base']
+            formats.extend([{
+                'format_id': 'rmtp',
+                'url': base_url,
+                'play_path': n.attrib['src'],
+                'ext': 'flv',
+                'preference': -100,
+                'format_note': 'Seems to fail at example stream',
+            } for n in smil_doc.findall('./body/video')])
+        else:
+            formats.append({'url': smil_url})
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': asset['title'],
+            'thumbnail': asset.get('image'),
+            'description': asset.get('teaser'),
+            'categories': categories,
+            'view_count': asset.get('views'),
+            'rtmp_live': asset.get('live'),
+            'timestamp': parse_iso8601(asset.get('date')),
+        }
+

youtube_dl/extractor/sunporno.py

@@ -0,0 +1,70 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+    qualities,
+    determine_ext,
+)
+
+
+class SunPornoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.sunporno.com/videos/807778/',
+        'md5': '6457d3c165fd6de062b99ef6c2ff4c86',
+        'info_dict': {
+            'id': '807778',
+            'ext': 'flv',
+            'title': 'md5:0a400058e8105d39e35c35e7c5184164',
+            'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 302,
+            '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'<title>([^<]+)</title>', webpage, 'title')
+        description = self._html_search_meta('description', webpage, 'description')
+        thumbnail = self._html_search_regex(
+            r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
+
+        duration = parse_duration(self._search_regex(
+            r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False))
+
+        view_count = int_or_none(self._html_search_regex(
+            r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False))
+        comment_count = int_or_none(self._html_search_regex(
+            r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False))
+
+        formats = []
+        quality = qualities(['mp4', 'flv'])
+        for video_url in re.findall(r'<source src="([^"]+)"', webpage):
+            video_ext = determine_ext(video_url)
+            formats.append({
+                'url': video_url,
+                'format_id': video_ext,
+                'quality': quality(video_ext),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'formats': formats,
+            'age_limit': 18,
+        }

youtube_dl/extractor/teachertube.py

@@ -106,6 +106,13 @@ class TeacherTubeUserIE(InfoExtractor):
         \s*
         <a\s+href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)"
     '''
+    _TEST = {
+        'url': 'http://www.teachertube.com/user/profile/rbhagwati2',
+        'info_dict': {
+            'id': 'rbhagwati2'
+        },
+        'playlist_mincount': 179,
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/techtalks.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -11,24 +13,30 @@ class TechTalksIE(InfoExtractor):
     _VALID_URL = r'https?://techtalks\.tv/talks/[^/]*/(?P<id>\d+)/'
 
     _TEST = {
-        u'url': u'http://techtalks.tv/talks/learning-topic-models-going-beyond-svd/57758/',
-        u'playlist': [
+        'url': 'http://techtalks.tv/talks/learning-topic-models-going-beyond-svd/57758/',
+        'info_dict': {
+            'id': '57758',
+            'title': 'Learning Topic Models --- Going beyond SVD',
+        },
+        'playlist': [
             {
-                u'file': u'57758.flv',
-                u'info_dict': {
-                    u'title': u'Learning Topic Models --- Going beyond SVD',
+                'info_dict': {
+                    'id': '57758',
+                    'ext': 'flv',
+                    'title': 'Learning Topic Models --- Going beyond SVD',
                 },
             },
             {
-                u'file': u'57758-slides.flv',
-                u'info_dict': {
-                    u'title': u'Learning Topic Models --- Going beyond SVD',
+                'info_dict': {
+                    'id': '57758-slides',
+                    'ext': 'flv',
+                    'title': 'Learning Topic Models --- Going beyond SVD',
                 },
             },
         ],
-        u'params': {
+        'params': {
             # rtmp download
-            u'skip_download': True,
+            'skip_download': True,
         },
     }
 
@@ -36,30 +44,36 @@ class TechTalksIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         talk_id = mobj.group('id')
         webpage = self._download_webpage(url, talk_id)
-        rtmp_url = self._search_regex(r'netConnectionUrl: \'(.*?)\'', webpage,
-            u'rtmp url')
-        play_path = self._search_regex(r'href=\'(.*?)\' [^>]*id="flowplayer_presenter"',
-            webpage, u'presenter play path')
+        rtmp_url = self._search_regex(
+            r'netConnectionUrl: \'(.*?)\'', webpage, 'rtmp url')
+        play_path = self._search_regex(
+            r'href=\'(.*?)\' [^>]*id="flowplayer_presenter"',
+            webpage, 'presenter play path')
         title = clean_html(get_element_by_attribute('class', 'title', webpage))
         video_info = {
-                'id': talk_id,
-                'title': title,
-                'url': rtmp_url,
-                'play_path': play_path,
-                'ext': 'flv',
-            }
+            'id': talk_id,
+            'title': title,
+            'url': rtmp_url,
+            'play_path': play_path,
+            'ext': 'flv',
+        }
         m_slides = re.search(r'<a class="slides" href=\'(.*?)\'', webpage)
         if m_slides is None:
             return video_info
         else:
-            return [
-                video_info,
-                # The slides video
-                {
-                    'id': talk_id + '-slides',
-                    'title': title,
-                    'url': rtmp_url,
-                    'play_path': m_slides.group(1),
-                    'ext': 'flv',
-                },
-            ]
+            return {
+                '_type': 'playlist',
+                'id': talk_id,
+                'title': title,
+                'entries': [
+                    video_info,
+                    # The slides video
+                    {
+                        'id': talk_id + '-slides',
+                        'title': title,
+                        'url': rtmp_url,
+                        'play_path': m_slides.group(1),
+                        'ext': 'flv',
+                    },
+                ],
+            }

youtube_dl/extractor/ted.py

@@ -51,7 +51,6 @@ class TEDIE(SubtitlesInfoExtractor):
         }
     }, {
         'url': 'http://www.ted.com/talks/gabby_giffords_and_mark_kelly_be_passionate_be_courageous_be_your_best',
-        'md5': '49144e345a899b8cb34d315f3b9cfeeb',
         'info_dict': {
             'id': '1972',
             'ext': 'mp4',
@@ -59,6 +58,13 @@ class TEDIE(SubtitlesInfoExtractor):
             'uploader': 'Gabby Giffords and Mark Kelly',
             'description': 'md5:5174aed4d0f16021b704120360f72b92',
         },
+    }, {
+        'url': 'http://www.ted.com/playlists/who_are_the_hackers',
+        'info_dict': {
+            'id': '10',
+            'title': 'Who are the hackers?',
+        },
+        'playlist_mincount': 6,
     }]
 
     _NATIVE_FORMATS = {

youtube_dl/extractor/tnaflix.py

@@ -0,0 +1,84 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    fix_xml_ampersands,
+)
+
+
+class TNAFlixIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P<cat_id>[\w-]+)/(?P<display_id>[\w-]+)/video(?P<id>\d+)'
+
+    _TITLE_REGEX = None
+    _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
+    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
+
+    _TEST = {
+        'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
+        'md5': 'ecf3498417d09216374fc5907f9c6ec0',
+        'info_dict': {
+            'id': '553878',
+            'display_id': 'Carmella-Decesare-striptease',
+            'ext': 'mp4',
+            'title': 'Carmella Decesare - striptease',
+            'description': '',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 91,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._html_search_regex(
+            self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
+        description = self._html_search_regex(
+            self._DESCRIPTION_REGEX, webpage, 'description', fatal=False, default='')
+
+        age_limit = self._rta_search(webpage)
+
+        duration = self._html_search_meta('duration', webpage, 'duration', default=None)
+        if duration:
+            duration = parse_duration(duration[1:])
+
+        cfg_url = self._html_search_regex(
+            self._CONFIG_REGEX, webpage, 'flashvars.config')
+
+        cfg_xml = self._download_xml(
+            cfg_url, display_id, note='Downloading metadata',
+            transform_source=fix_xml_ampersands)
+
+        thumbnail = cfg_xml.find('./startThumb').text
+
+        formats = []
+        for item in cfg_xml.findall('./quality/item'):
+            video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text)
+            format_id = item.find('res').text
+            fmt = {
+                'url': video_url,
+                'format_id': format_id,
+            }
+            m = re.search(r'^(\d+)', format_id)
+            if m:
+                fmt['height'] = int(m.group(1))
+            formats.append(fmt)
+        self._sort_formats(formats)
+        
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'age_limit': age_limit,
+            'formats': formats,
+        }

youtube_dl/extractor/toypics.py

@@ -42,6 +42,13 @@ class ToypicsIE(InfoExtractor):
 class ToypicsUserIE(InfoExtractor):
     IE_DESC = 'Toypics user profile'
     _VALID_URL = r'http://videos\.toypics\.net/(?P<username>[^/?]+)(?:$|[?#])'
+    _TEST = {
+        'url': 'http://videos.toypics.net/Mikey',
+        'info_dict': {
+            'id': 'Mikey',
+        },
+        'playlist_mincount': 19,
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/tudou.py

@@ -1,5 +1,7 @@
 # coding: utf-8
 
+from __future__ import unicode_literals
+
 import re
 import json
 
@@ -9,22 +11,29 @@ from .common import InfoExtractor
 class TudouIE(InfoExtractor):
     _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs|albumplay)/(?:view|(.+?))/(?:([^/]+)|([^/]+))(?:\.html)?'
     _TESTS = [{
-        u'url': u'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
-        u'file': u'159448201.f4v',
-        u'md5': u'140a49ed444bd22f93330985d8475fcb',
-        u'info_dict': {
-            u"title": u"卡马乔国足开大脚长传冲吊集锦"
+        'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
+        'md5': '140a49ed444bd22f93330985d8475fcb',
+        'info_dict': {
+            'id': '159448201',
+            'ext': 'f4v',
+            'title': '卡马乔国足开大脚长传冲吊集锦',
+            'thumbnail': 're:^https?://.*\.jpg$',
         }
-    },
-    {
-        u'url': u'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html',
-        u'file': u'todo.mp4',
-        u'md5': u'todo.mp4',
-        u'info_dict': {
-            u'title': u'todo.mp4',
+    }, {
+        'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/',
+        'info_dict': {
+            'id': '117049447',
+            'ext': 'f4v',
+            'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }, {
+        'url': 'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html',
+        'info_dict': {
+            'title': 'todo.mp4',
         },
-        u'add_ie': [u'Youku'],
-        u'skip': u'Only works from China'
+        'add_ie': ['Youku'],
+        'skip': 'Only works from China'
     }]
 
     def _url_for_id(self, id, quality = None):
@@ -44,20 +53,22 @@ class TudouIE(InfoExtractor):
         if m and m.group(1):
             return {
                 '_type': 'url',
-                'url': u'youku:' + m.group(1),
+                'url': 'youku:' + m.group(1),
                 'ie_key': 'Youku'
             }
 
         title = self._search_regex(
-            r",kw:\s*['\"](.+?)[\"']", webpage, u'title')
+            r",kw:\s*['\"](.+?)[\"']", webpage, 'title')
         thumbnail_url = self._search_regex(
-            r",pic:\s*[\"'](.+?)[\"']", webpage, u'thumbnail URL', fatal=False)
+            r",pic:\s*[\"'](.+?)[\"']", webpage, 'thumbnail URL', fatal=False)
 
         segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments')
         segments = json.loads(segs_json)
         # It looks like the keys are the arguments that have to be passed as
         # the hd field in the request url, we pick the higher
-        quality = sorted(segments.keys())[-1]
+        # Also, filter non-number qualities (see issue #3643).
+        quality = sorted(filter(lambda k: k.isdigit(), segments.keys()),
+                         key=lambda k: int(k))[-1]
         parts = segments[quality]
         result = []
         len_parts = len(parts)
@@ -67,12 +78,13 @@ class TudouIE(InfoExtractor):
             part_id = part['k']
             final_url = self._url_for_id(part_id, quality)
             ext = (final_url.split('?')[0]).split('.')[-1]
-            part_info = {'id': part_id,
-                          'url': final_url,
-                          'ext': ext,
-                          'title': title,
-                          'thumbnail': thumbnail_url,
-                          }
+            part_info = {
+                'id': '%s' % part_id,
+                'url': final_url,
+                'ext': ext,
+                'title': title,
+                'thumbnail': thumbnail_url,
+            }
             result.append(part_info)
 
         return result

youtube_dl/extractor/tvigle.py

@@ -5,80 +5,82 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    unified_strdate,
-    clean_html,
-    int_or_none,
+    float_or_none,
+    str_to_int,
 )
 
 
 class TvigleIE(InfoExtractor):
     IE_NAME = 'tvigle'
     IE_DESC = 'Интернет-телевидение Tvigle.ru'
-    _VALID_URL = r'http://(?:www\.)?tvigle\.ru/category/.+?[\?&]v(?:ideo)?=(?P<id>\d+)'
+    _VALID_URL = r'http://(?:www\.)?tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$'
 
     _TESTS = [
         {
-            'url': 'http://www.tvigle.ru/category/cinema/1608/?video=503081',
-            'md5': '09afba4616666249f087efc6dcf83cb3',
+            'url': 'http://www.tvigle.ru/video/brat-2/',
+            'md5': '72cb7eab33e54314e1790da402d3c9c3',
             'info_dict': {
-                'id': '503081',
-                'ext': 'flv',
+                'id': '5119390',
+                'display_id': 'brat-2',
+                'ext': 'mp4',
                 'title': 'Брат 2 ',
-                'description': 'md5:f5a42970f50648cee3d7ad740f3ae769',
-                'upload_date': '20110919',
+                'description': 'md5:5751f4fe345a58e1692585c361294bd8',
+                'duration': 7356.369,
+                'age_limit': 0,
             },
         },
         {
-            'url': 'http://www.tvigle.ru/category/men/vysotskiy_vospominaniya02/?flt=196&v=676433',
-            'md5': 'e7efe5350dd5011d0de6550b53c3ba7b',
+            'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/',
+            'md5': 'd9012d7c7c598fe7a11d7fb46dc1f574',
             'info_dict': {
-                'id': '676433',
-                'ext': 'flv',
+                'id': '5142516',
+                'ext': 'mp4',
                 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком',
                 'description': 'md5:027f7dc872948f14c96d19b4178428a4',
-                'upload_date': '20121218',
+                'duration': 186.080,
+                'age_limit': 0,
             },
         },
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
 
-        video_data = self._download_xml(
-            'http://www.tvigle.ru/xml/single.php?obj=%s' % video_id, video_id, 'Downloading video XML')
+        webpage = self._download_webpage(url, display_id)
 
-        video = video_data.find('./video')
+        video_id = self._html_search_regex(
+            r'<li class="video-preview current_playing" id="(\d+)">', webpage, 'video id')
 
-        title = video.get('name')
-        description = video.get('anons')
-        if description:
-            description = clean_html(description)
-        thumbnail = video_data.get('img')
-        upload_date = unified_strdate(video.get('date'))
-        like_count = int_or_none(video.get('vtp'))
+        video_data = self._download_json(
+            'http://cloud.tvigle.ru/api/play/video/%s/' % video_id, display_id)
+
+        item = video_data['playlist']['items'][0]
+
+        title = item['title']
+        description = item['description']
+        thumbnail = item['thumbnail']
+        duration = float_or_none(item['durationMilliseconds'], 1000)
+        age_limit = str_to_int(item['ageRestrictions'])
 
         formats = []
-        for num, (format_id, format_note) in enumerate([['low_file', 'SQ'], ['file', 'HQ'], ['hd', 'HD 720']]):
-            video_url = video.get(format_id)
-            if not video_url:
-                continue
-            formats.append({
-                'url': video_url,
-                'format_id': format_id,
-                'format_note': format_note,
-                'quality': num,
-            })
-
+        for vcodec, fmts in item['videos'].items():
+            for quality, video_url in fmts.items():
+                formats.append({
+                    'url': video_url,
+                    'format_id': '%s-%s' % (vcodec, quality),
+                    'vcodec': vcodec,
+                    'height': int(quality[:-1]),
+                })
         self._sort_formats(formats)
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
-            'upload_date': upload_date,
-            'like_count': like_count,
-            'age_limit': 18,
+            'duration': duration,
+            'age_limit': age_limit,
             'formats': formats,
         }

youtube_dl/extractor/tvplay.py

@@ -6,13 +6,28 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    compat_str,
     parse_iso8601,
     qualities,
 )
 
 
 class TVPlayIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?tvplay\.lv/parraides/[^/]+/(?P<id>\d+)'
+    IE_DESC = 'TV3Play and related services'
+    _VALID_URL = r'''(?x)http://(?:www\.)?
+        (?:tvplay\.lv/parraides|
+           tv3play\.lt/programos|
+           tv3play\.ee/sisu|
+           tv3play\.se/program|
+           tv6play\.se/program|
+           tv8play\.se/program|
+           tv10play\.se/program|
+           tv3play\.no/programmer|
+           viasat4play\.no/programmer|
+           tv6play\.no/programmer|
+           tv3play\.dk/programmer|
+        )/[^/]+/(?P<id>\d+)
+        '''
     _TESTS = [
         {
             'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true',
@@ -30,6 +45,134 @@ class TVPlayIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            'url': 'http://www.tv3play.lt/programos/moterys-meluoja-geriau/409229?autostart=true',
+            'info_dict': {
+                'id': '409229',
+                'ext': 'flv',
+                'title': 'Moterys meluoja geriau',
+                'description': 'md5:9aec0fc68e2cbc992d2a140bd41fa89e',
+                'duration': 1330,
+                'timestamp': 1403769181,
+                'upload_date': '20140626',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.tv3play.ee/sisu/kodu-keset-linna/238551?autostart=true',
+            'info_dict': {
+                'id': '238551',
+                'ext': 'flv',
+                'title': 'Kodu keset linna 398537',
+                'description': 'md5:7df175e3c94db9e47c0d81ffa5d68701',
+                'duration': 1257,
+                'timestamp': 1292449761,
+                'upload_date': '20101215',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.tv3play.se/program/husraddarna/395385?autostart=true',
+            'info_dict': {
+                'id': '395385',
+                'ext': 'flv',
+                'title': 'Husräddarna S02E07',
+                'description': 'md5:f210c6c89f42d4fc39faa551be813777',
+                'duration': 2574,
+                'timestamp': 1400596321,
+                'upload_date': '20140520',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.tv6play.se/program/den-sista-dokusapan/266636?autostart=true',
+            'info_dict': {
+                'id': '266636',
+                'ext': 'flv',
+                'title': 'Den sista dokusåpan S01E08',
+                'description': 'md5:295be39c872520221b933830f660b110',
+                'duration': 1492,
+                'timestamp': 1330522854,
+                'upload_date': '20120229',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.tv8play.se/program/antikjakten/282756?autostart=true',
+            'info_dict': {
+                'id': '282756',
+                'ext': 'flv',
+                'title': 'Antikjakten S01E10',
+                'description': 'md5:1b201169beabd97e20c5ad0ad67b13b8',
+                'duration': 2646,
+                'timestamp': 1348575868,
+                'upload_date': '20120925',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.tv3play.no/programmer/anna-anka-soker-assistent/230898?autostart=true',
+            'info_dict': {
+                'id': '230898',
+                'ext': 'flv',
+                'title': 'Anna Anka søker assistent - Ep. 8',
+                'description': 'md5:f80916bf5bbe1c5f760d127f8dd71474',
+                'duration': 2656,
+                'timestamp': 1277720005,
+                'upload_date': '20100628',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.viasat4play.no/programmer/budbringerne/21873?autostart=true',
+            'info_dict': {
+                'id': '21873',
+                'ext': 'flv',
+                'title': 'Budbringerne program 10',
+                'description': 'md5:4db78dc4ec8a85bb04fd322a3ee5092d',
+                'duration': 1297,
+                'timestamp': 1254205102,
+                'upload_date': '20090929',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.tv6play.no/programmer/hotelinspektor-alex-polizzi/361883?autostart=true',
+            'info_dict': {
+                'id': '361883',
+                'ext': 'flv',
+                'title': 'Hotelinspektør Alex Polizzi - Ep. 10',
+                'description': 'md5:3ecf808db9ec96c862c8ecb3a7fdaf81',
+                'duration': 2594,
+                'timestamp': 1393236292,
+                'upload_date': '20140224',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
     ]
 
     def _real_extract(self, url):
@@ -49,7 +192,7 @@ class TVPlayIE(InfoExtractor):
         quality = qualities(['hls', 'medium', 'high'])
         formats = []
         for format_id, video_url in streams['streams'].items():
-            if not video_url:
+            if not video_url or not isinstance(video_url, compat_str):
                 continue
             fmt = {
                 'format_id': format_id,

youtube_dl/extractor/unistra.py

@@ -1,32 +1,66 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
+from ..utils import qualities
+
 
 class UnistraIE(InfoExtractor):
-    _VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(\d+)'
+    _VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(?P<id>\d+)'
 
-    _TEST = {
-        u'url': u'http://utv.unistra.fr/video.php?id_video=154',
-        u'file': u'154.mp4',
-        u'md5': u'736f605cfdc96724d55bb543ab3ced24',
-        u'info_dict': {
-            u'title': u'M!ss Yella',
-            u'description': u'md5:104892c71bd48e55d70b902736b81bbf',
+    _TESTS = [
+        {
+            'url': 'http://utv.unistra.fr/video.php?id_video=154',
+            'md5': '736f605cfdc96724d55bb543ab3ced24',
+            'info_dict': {
+                'id': '154',
+                'ext': 'mp4',
+                'title': 'M!ss Yella',
+                'description': 'md5:104892c71bd48e55d70b902736b81bbf',
+            },
         },
-    }
+        {
+            'url': 'http://utv.unistra.fr/index.php?id_video=437',
+            'md5': '1ddddd6cccaae76f622ce29b8779636d',
+            'info_dict': {
+                'id': '437',
+                'ext': 'mp4',
+                'title': 'Prix Louise Weiss 2014',
+                'description': 'md5:cc3a8735f079f4fb6b0b570fc10c135a',
+            },
+        }
+    ]
 
     def _real_extract(self, url):
-        id = re.match(self._VALID_URL, url).group(1)
-        webpage = self._download_webpage(url, id)
-        file = re.search(r'file: "(.*?)",', webpage).group(1)
-        title = self._html_search_regex(r'<title>UTV - (.*?)</', webpage, u'title')
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
 
-        video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file
+        webpage = self._download_webpage(url, video_id)
 
-        return {'id': id,
-                'title': title,
-                'ext': 'mp4',
-                'url': video_url,
-                'description': self._html_search_regex(r'<meta name="Description" content="(.*?)"', webpage, u'description', flags=re.DOTALL),
-                'thumbnail': self._search_regex(r'image: "(.*?)"', webpage, u'thumbnail'),
-                }
+        files = set(re.findall(r'file\s*:\s*"([^"]+)"', webpage))
+
+        quality = qualities(['SD', 'HD'])
+        formats = []
+        for file_path in files:
+            format_id = 'HD' if file_path.endswith('-HD.mp4') else 'SD'
+            formats.append({
+                'url': 'http://vod-flash.u-strasbg.fr:8080%s' % file_path,
+                'format_id': format_id,
+                'quality': quality(format_id)
+            })
+
+        title = self._html_search_regex(
+            r'<title>UTV - (.*?)</', webpage, 'title')
+        description = self._html_search_regex(
+            r'<meta name="Description" content="(.*?)"', webpage, 'description', flags=re.DOTALL)
+        thumbnail = self._search_regex(
+            r'image: "(.*?)"', webpage, 'thumbnail')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'formats': formats
+        }

youtube_dl/extractor/ustream.py

@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
@@ -68,21 +67,36 @@ class UstreamIE(InfoExtractor):
 class UstreamChannelIE(InfoExtractor):
     _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)'
     IE_NAME = 'ustream:channel'
+    _TEST = {
+        'url': 'http://www.ustream.tv/channel/channeljapan',
+        'info_dict': {
+            'id': '10874166',
+        },
+        'playlist_mincount': 54,
+    }
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
-        slug = m.group('slug')
-        webpage = self._download_webpage(url, slug)
+        display_id = m.group('slug')
+        webpage = self._download_webpage(url, display_id)
         channel_id = get_meta_content('ustream:channel_id', webpage)
 
         BASE = 'http://www.ustream.tv'
         next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id
         video_ids = []
         while next_url:
-            reply = json.loads(self._download_webpage(compat_urlparse.urljoin(BASE, next_url), channel_id))
+            reply = self._download_json(
+                compat_urlparse.urljoin(BASE, next_url), display_id,
+                note='Downloading video information (next: %d)' % (len(video_ids) + 1))
             video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data']))
             next_url = reply['nextUrl']
 
-        urls = ['http://www.ustream.tv/recorded/' + vid for vid in video_ids]
-        url_entries = [self.url_result(eurl, 'Ustream') for eurl in urls]
-        return self.playlist_result(url_entries, channel_id)
+        entries = [
+            self.url_result('http://www.ustream.tv/recorded/' + vid, 'Ustream')
+            for vid in video_ids]
+        return {
+            '_type': 'playlist',
+            'id': channel_id,
+            'display_id': display_id,
+            'entries': entries,
+        }

youtube_dl/extractor/veehd.py

@@ -16,8 +16,9 @@ class VeeHDIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://veehd.com/video/4686958',
-        'file': '4686958.mp4',
         'info_dict': {
+            'id': '4686958',
+            'ext': 'mp4',
             'title': 'Time Lapse View from Space ( ISS)',
             'uploader_id': 'spotted',
             'description': 'md5:f0094c4cf3a72e22bc4e4239ef767ad7',

youtube_dl/extractor/vgtv.py

@@ -0,0 +1,119 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import float_or_none
+
+
+class VGTVIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?vgtv\.no/#!/(?:.*)/(?P<id>[0-9]+)'
+    _TESTS = [
+        {
+            # streamType: vod
+            'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu',
+            'md5': 'b8be7a234cebb840c0d512c78013e02f',
+            'info_dict': {
+                'id': '84196',
+                'ext': 'mp4',
+                'title': 'Hevnen er søt episode 10: Abu',
+                'description': 'md5:e25e4badb5f544b04341e14abdc72234',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'duration': 648.000,
+                'timestamp': 1404626400,
+                'upload_date': '20140706',
+                'view_count': int,
+            },
+        },
+        {
+            # streamType: wasLive
+            'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen',
+            'info_dict': {
+                'id': '100764',
+                'ext': 'mp4',
+                'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
+                'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'duration': 9056.000,
+                'timestamp': 1410113864,
+                'upload_date': '20140907',
+                'view_count': int,
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
+        {
+            # streamType: live
+            'url': 'http://www.vgtv.no/#!/live/100015/direkte-her-kan-du-se-laksen-live-fra-suldalslaagen',
+            'info_dict': {
+                'id': '100015',
+                'ext': 'mp4',
+                'title': 'DIREKTE: Her kan du se laksen live fra Suldalslågen!',
+                'description': 'md5:9a60cc23fa349f761628924e56eeec2d',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'duration': 0,
+                'timestamp': 1407423348,
+                'upload_date': '20140807',
+                'view_count': int,
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        data = self._download_json(
+            'http://svp.vg.no/svp/api/v1/vgtv/assets/%s?appName=vgtv-website' % video_id,
+            video_id, 'Downloading media JSON')
+
+        streams = data['streamUrls']
+
+        formats = []
+
+        hls_url = streams.get('hls')
+        if hls_url:
+            formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4'))
+
+        hds_url = streams.get('hds')
+        if hds_url:
+            formats.extend(self._extract_f4m_formats(hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', video_id))
+
+        mp4_url = streams.get('mp4')
+        if mp4_url:
+            _url = hls_url or hds_url
+            MP4_URL_TEMPLATE = '%s/%%s.%s' % (mp4_url.rpartition('/')[0], mp4_url.rpartition('.')[-1])
+            for mp4_format in _url.split(','):
+                m = re.search('(?P<width>\d+)_(?P<height>\d+)_(?P<vbr>\d+)', mp4_format)
+                if not m:
+                    continue
+                width = int(m.group('width'))
+                height = int(m.group('height'))
+                vbr = int(m.group('vbr'))
+                formats.append({
+                    'url': MP4_URL_TEMPLATE % mp4_format,
+                    'format_id': 'mp4-%s' % vbr,
+                    'width': width,
+                    'height': height,
+                    'vbr': vbr,
+                    'preference': 1,
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': data['title'],
+            'description': data['description'],
+            'thumbnail': data['images']['main'] + '?t[]=900x506q80',
+            'timestamp': data['published'],
+            'duration': float_or_none(data['duration'], 1000),
+            'view_count': data['displays'],
+            'formats': formats,
+        }

youtube_dl/extractor/vimeo.py

@@ -57,6 +57,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
         (?P<proto>(?:https?:)?//)?
         (?:(?:www|(?P<player>player))\.)?
         vimeo(?P<pro>pro)?\.com/
+        (?!channels/[^/?#]+/?(?:$|[?#])|album/)
         (?:.*?/)?
         (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
         (?:videos?/)?
@@ -153,15 +154,6 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
         },
     ]
 
-    @classmethod
-    def suitable(cls, url):
-        if VimeoChannelIE.suitable(url):
-            # Otherwise channel urls like http://vimeo.com/channels/31259 would
-            # match
-            return False
-        else:
-            return super(VimeoIE, cls).suitable(url)
-
     def _verify_video_password(self, url, video_id, webpage):
         password = self._downloader.params.get('videopassword', None)
         if password is None:
@@ -205,6 +197,8 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
         if data is not None:
             headers = headers.copy()
             headers.update(data)
+        if 'Referer' not in headers:
+            headers['Referer'] = url
 
         # Extract ID from URL
         mobj = re.match(self._VALID_URL, url)
@@ -378,9 +372,16 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
 
 class VimeoChannelIE(InfoExtractor):
     IE_NAME = 'vimeo:channel'
-    _VALID_URL = r'(?:https?://)?vimeo\.com/channels/(?P<id>[^/]+)/?(\?.*)?$'
+    _VALID_URL = r'https?://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
+    _TESTS = [{
+        'url': 'http://vimeo.com/channels/tributes',
+        'info_dict': {
+            'title': 'Vimeo Tributes',
+        },
+        'playlist_mincount': 25,
+    }]
 
     def _page_url(self, base_url, pagenum):
         return '%s/videos/page:%d/' % (base_url, pagenum)
@@ -414,14 +415,15 @@ class VimeoChannelIE(InfoExtractor):
 
 class VimeoUserIE(VimeoChannelIE):
     IE_NAME = 'vimeo:user'
-    _VALID_URL = r'(?:https?://)?vimeo\.com/(?P<name>[^/]+)(?:/videos|[#?]|$)'
+    _VALID_URL = r'https?://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
-
-    @classmethod
-    def suitable(cls, url):
-        if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url) or VimeoAlbumIE.suitable(url) or VimeoGroupsIE.suitable(url):
-            return False
-        return super(VimeoUserIE, cls).suitable(url)
+    _TESTS = [{
+        'url': 'http://vimeo.com/nkistudio/videos',
+        'info_dict': {
+            'title': 'Nki',
+        },
+        'playlist_mincount': 66,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -431,8 +433,15 @@ class VimeoUserIE(VimeoChannelIE):
 
 class VimeoAlbumIE(VimeoChannelIE):
     IE_NAME = 'vimeo:album'
-    _VALID_URL = r'(?:https?://)?vimeo\.com/album/(?P<id>\d+)'
+    _VALID_URL = r'https?://vimeo\.com/album/(?P<id>\d+)'
     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
+    _TESTS = [{
+        'url': 'http://vimeo.com/album/2632481',
+        'info_dict': {
+            'title': 'Staff Favorites: November 2013',
+        },
+        'playlist_mincount': 13,
+    }]
 
     def _page_url(self, base_url, pagenum):
         return '%s/page:%d/' % (base_url, pagenum)
@@ -446,6 +455,13 @@ class VimeoAlbumIE(VimeoChannelIE):
 class VimeoGroupsIE(VimeoAlbumIE):
     IE_NAME = 'vimeo:group'
     _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)'
+    _TESTS = [{
+        'url': 'http://vimeo.com/groups/rolexawards',
+        'info_dict': {
+            'title': 'Rolex Awards for Enterprise',
+        },
+        'playlist_mincount': 73,
+    }]
 
     def _extract_list_title(self, webpage):
         return self._og_search_title(webpage)
@@ -459,8 +475,8 @@ class VimeoGroupsIE(VimeoAlbumIE):
 class VimeoReviewIE(InfoExtractor):
     IE_NAME = 'vimeo:review'
     IE_DESC = 'Review pages on vimeo'
-    _VALID_URL = r'(?:https?://)?vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
-    _TEST = {
+    _VALID_URL = r'https?://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
+    _TESTS = [{
         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
         'file': '75524534.mp4',
         'md5': 'c507a72f780cacc12b2248bb4006d253',
@@ -468,7 +484,19 @@ class VimeoReviewIE(InfoExtractor):
             'title': "DICK HARDWICK 'Comedian'",
             'uploader': 'Richard Hardwick',
         }
-    }
+    }, {
+        'note': 'video player needs Referer',
+        'url': 'http://vimeo.com/user22258446/review/91613211/13f927e053',
+        'md5': '6295fdab8f4bf6a002d058b2c6dce276',
+        'info_dict': {
+            'id': '91613211',
+            'ext': 'mp4',
+            'title': 'Death by dogma versus assembling agile - Sander Hoogendoorn',
+            'uploader': 'DevWeek Events',
+            'duration': 2773,
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -483,6 +511,10 @@ class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
     _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater'
     _LOGIN_REQUIRED = True
     _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<'
+    _TESTS = [{
+        'url': 'http://vimeo.com/home/watchlater',
+        'only_matching': True,
+    }]
 
     def _real_initialize(self):
         self._login()

youtube_dl/extractor/vine.py

@@ -65,6 +65,13 @@ class VineUserIE(InfoExtractor):
     IE_NAME = 'vine:user'
     _VALID_URL = r'(?:https?://)?vine\.co/(?P<user>[^/]+)/?(\?.*)?$'
     _VINE_BASE_URL = "https://vine.co/"
+    _TEST = {
+        'url': 'https://vine.co/Visa',
+        'info_dict': {
+            'id': 'Visa',
+        },
+        'playlist_mincount': 47,
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/vporn.py

@@ -0,0 +1,99 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    str_to_int,
+)
+
+
+class VpornIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/',
+        'md5': 'facf37c1b86546fa0208058546842c55',
+        'info_dict': {
+            'id': '497944',
+            'display_id': 'violet-on-her-th-birthday',
+            'ext': 'mp4',
+            'title': 'Violet on her 19th birthday',
+            'description': 'Violet dances in front of the camera which is sure to get you horny.',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'kileyGrope',
+            'categories': ['Masturbation', 'Teen'],
+            'duration': 393,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._html_search_regex(
+            r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip()
+        description = self._html_search_regex(
+            r'<div class="description_txt">(.*?)</div>', webpage, 'description', fatal=False)
+        thumbnail = self._html_search_regex(
+            r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None)
+        if thumbnail:
+            thumbnail = 'http://www.vporn.com' + thumbnail
+
+        uploader = self._html_search_regex(
+            r'(?s)UPLOADED BY.*?<a href="/user/[^"]+">([^<]+)</a>',
+            webpage, 'uploader', fatal=False)
+
+        categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage)
+
+        duration = parse_duration(self._search_regex(
+            r'duration (\d+ min \d+ sec)', webpage, 'duration', fatal=False))
+
+        view_count = str_to_int(self._html_search_regex(
+            r'<span>([\d,\.]+) VIEWS</span>', webpage, 'view count', fatal=False))
+        like_count = str_to_int(self._html_search_regex(
+            r'<span id="like" class="n">([\d,\.]+)</span>', webpage, 'like count', fatal=False))
+        dislike_count = str_to_int(self._html_search_regex(
+            r'<span id="dislike" class="n">([\d,\.]+)</span>', webpage, 'dislike count', fatal=False))
+        comment_count = str_to_int(self._html_search_regex(
+            r'<h4>Comments \(<b>([\d,\.]+)</b>\)</h4>', webpage, 'comment count', fatal=False))
+
+        formats = []
+
+        for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"([^"]+)"', webpage):
+            video_url = video[1]
+            fmt = {
+                'url': video_url,
+                'format_id': video[0],
+            }
+            m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)_(?P<vbr>\d+)k\.mp4$', video_url)
+            if m:
+                fmt.update({
+                    'width': int(m.group('width')),
+                    'height': int(m.group('height')),
+                    'vbr': int(m.group('vbr')),
+                })
+            formats.append(fmt)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'categories': categories,
+            'duration': duration,
+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'comment_count': comment_count,
+            'age_limit': 18,
+            'formats': formats,
+        }

youtube_dl/extractor/washingtonpost.py

@@ -13,6 +13,9 @@ class WashingtonPostIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])'
     _TEST = {
         'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/',
+        'info_dict': {
+            'title': 'Sinkhole of bureaucracy',
+        },
         'playlist': [{
             'md5': 'c3f4b4922ffa259243f68e928db2db8c',
             'info_dict': {

youtube_dl/extractor/wat.py

@@ -2,32 +2,43 @@
 from __future__ import unicode_literals
 
 import re
-import time
 import hashlib
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    unified_strdate,
-)
+from ..utils import unified_strdate
 
 
 class WatIE(InfoExtractor):
     _VALID_URL = r'http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html'
     IE_NAME = 'wat.tv'
-    _TEST = {
-        'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
-        'md5': 'ce70e9223945ed26a8056d413ca55dc9',
-        'info_dict': {
-            'id': '11713067',
-            'display_id': 'soupe-figues-l-orange-aux-epices',
-            'ext': 'mp4',
-            'title': 'Soupe de figues à l\'orange et aux épices',
-            'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.',
-            'upload_date': '20140819',
-            'duration': 120,
+    _TESTS = [
+        {
+            'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
+            'md5': 'ce70e9223945ed26a8056d413ca55dc9',
+            'info_dict': {
+                'id': '11713067',
+                'display_id': 'soupe-figues-l-orange-aux-epices',
+                'ext': 'mp4',
+                'title': 'Soupe de figues à l\'orange et aux épices',
+                'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.',
+                'upload_date': '20140819',
+                'duration': 120,
+            },
         },
-    }
+        {
+            'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
+            'md5': 'fbc84e4378165278e743956d9c1bf16b',
+            'info_dict': {
+                'id': '11713075',
+                'display_id': 'gregory-lemarchal-voix-ange',
+                'ext': 'mp4',
+                'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)',
+                'description': 'md5:b7a849cf16a2b733d9cd10c52906dee3',
+                'upload_date': '20140816',
+                'duration': 2910,
+            },
+        },
+    ]
 
     def download_video_info(self, real_id):
         # 'contentv4' is used in the website, but it also returns the related
@@ -46,8 +57,8 @@ class WatIE(InfoExtractor):
 
         video_info = self.download_video_info(real_id)
 
-        if video_info.get('geolock'):
-            raise ExtractorError('This content is not available in your area', expected=True)
+        geo_list = video_info.get('geoList')
+        country = geo_list[0] if geo_list else ''
 
         chapters = video_info['chapters']
         first_chapter = chapters[0]
@@ -82,14 +93,16 @@ class WatIE(InfoExtractor):
             fmts.append(('HD', 'webhd'))
 
         def compute_token(param):
-            timestamp = '%08x' % int(time.time())
+            timestamp = '%08x' % int(self._download_webpage(
+                'http://www.wat.tv/servertime', real_id,
+                'Downloading server time').split('|')[0])
             magic = '9b673b13fa4682ed14c3cfa5af5310274b514c4133e9b3a81e6e3aba009l2564'
             return '%s/%s' % (hashlib.md5((magic + param + timestamp).encode('ascii')).hexdigest(), timestamp)
 
         for fmt in fmts:
             webid = '/%s/%s' % (fmt[1], real_id)
             video_url = self._download_webpage(
-                'http://www.wat.tv/get%s?token=%s&getURL=1' % (webid, compute_token(webid)),
+                'http://www.wat.tv/get%s?token=%s&getURL=1&country=%s' % (webid, compute_token(webid), country),
                 real_id,
                 'Downloding %s video URL' % fmt[0],
                 'Failed to download %s video URL' % fmt[0],

youtube_dl/extractor/xtube.py

@@ -77,9 +77,17 @@ class XTubeIE(InfoExtractor):
             'age_limit': 18,
         }
 
+
 class XTubeUserIE(InfoExtractor):
     IE_DESC = 'XTube user profile'
     _VALID_URL = r'https?://(?:www\.)?xtube\.com/community/profile\.php\?(.*?)user=(?P<username>[^&#]+)(?:$|[&#])'
+    _TEST = {
+        'url': 'http://www.xtube.com/community/profile.php?user=greenshowers',
+        'info_dict': {
+            'id': 'greenshowers',
+        },
+        'playlist_mincount': 155,
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/yahoo.py

@@ -71,7 +71,8 @@ class YahooIE(InfoExtractor):
         if items_json is None:
             CONTENT_ID_REGEXES = [
                 r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"',
-                r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"'
+                r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"',
+                r'"first_videoid"\s*:\s*"([^"]+)"',
             ]
             long_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID')
             video_id = long_id

youtube_dl/extractor/youjizz.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class YouJizzIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'
+    _VALID_URL = r'^https?://(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'
     _TEST = {
         'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
         'file': '2189178.flv',

youtube_dl/extractor/youtube.py

@@ -1,7 +1,5 @@
 # coding: utf-8
 
-import errno
-import io
 import itertools
 import json
 import os.path
@@ -21,7 +19,6 @@ from ..utils import (
     compat_str,
 
     clean_html,
-    get_cachedir,
     get_element_by_id,
     get_element_by_attribute,
     ExtractorError,
@@ -30,13 +27,13 @@ from ..utils import (
     unescapeHTML,
     unified_strdate,
     orderedSet,
-    write_json_file,
     uppercase_escape,
 )
 
 class YoutubeBaseInfoExtractor(InfoExtractor):
     """Provide base functions for Youtube extractors"""
     _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
+    _TWOFACTOR_URL = 'https://accounts.google.com/SecondFactor'
     _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
     _AGE_URL = 'https://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
     _NETRC_MACHINE = 'youtube'
@@ -50,12 +47,19 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             fatal=False))
 
     def _login(self):
+        """
+        Attempt to log in to YouTube.
+        True is returned if successful or skipped.
+        False is returned if login failed.
+
+        If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
+        """
         (username, password) = self._get_login_info()
         # No authentication to be performed
         if username is None:
             if self._LOGIN_REQUIRED:
                 raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True)
-            return False
+            return True
 
         login_page = self._download_webpage(
             self._LOGIN_URL, None,
@@ -73,6 +77,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
                 u'Email': username,
                 u'GALX': galx,
                 u'Passwd': password,
+
                 u'PersistentCookie': u'yes',
                 u'_utf8': u'霱',
                 u'bgresponse': u'js_disabled',
@@ -88,6 +93,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
                 u'uilel': u'3',
                 u'hl': u'en_US',
         }
+
         # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
         # chokes on unicode
         login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
@@ -99,6 +105,68 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             note=u'Logging in', errnote=u'unable to log in', fatal=False)
         if login_results is False:
             return False
+
+        if re.search(r'id="errormsg_0_Passwd"', login_results) is not None:
+            raise ExtractorError(u'Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
+
+        # Two-Factor
+        # TODO add SMS and phone call support - these require making a request and then prompting the user
+
+        if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', login_results) is not None:
+            tfa_code = self._get_tfa_info()
+
+            if tfa_code is None:
+                self._downloader.report_warning(u'Two-factor authentication required. Provide it with --twofactor <code>')
+                self._downloader.report_warning(u'(Note that only TOTP (Google Authenticator App) codes work at this time.)')
+                return False
+
+            # Unlike the first login form, secTok and timeStmp are both required for the TFA form
+
+            match = re.search(r'id="secTok"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U)
+            if match is None:
+                self._downloader.report_warning(u'Failed to get secTok - did the page structure change?')
+            secTok = match.group(1)
+            match = re.search(r'id="timeStmp"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U)
+            if match is None:
+                self._downloader.report_warning(u'Failed to get timeStmp - did the page structure change?')
+            timeStmp = match.group(1)
+
+            tfa_form_strs = {
+                u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
+                u'smsToken': u'',
+                u'smsUserPin': tfa_code,
+                u'smsVerifyPin': u'Verify',
+
+                u'PersistentCookie': u'yes',
+                u'checkConnection': u'',
+                u'checkedDomains': u'youtube',
+                u'pstMsg': u'1',
+                u'secTok': secTok,
+                u'timeStmp': timeStmp,
+                u'service': u'youtube',
+                u'hl': u'en_US',
+            }
+            tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in tfa_form_strs.items())
+            tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii')
+
+            tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data)
+            tfa_results = self._download_webpage(
+                tfa_req, None,
+                note=u'Submitting TFA code', errnote=u'unable to submit tfa', fatal=False)
+
+            if tfa_results is False:
+                return False
+
+            if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', tfa_results) is not None:
+                self._downloader.report_warning(u'Two-factor code expired. Please try again, or use a one-use backup code instead.')
+                return False
+            if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None:
+                self._downloader.report_warning(u'unable to log in - did the page structure change?')
+                return False
+            if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
+                self._downloader.report_warning(u'Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
+                return False
+
         if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
             self._downloader.report_warning(u'unable to log in: bad username or password')
             return False
@@ -131,7 +199,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
     IE_DESC = u'YouTube.com'
     _VALID_URL = r"""(?x)^
                      (
-                         (?:https?://|//)?                                    # http(s):// or protocol-independent URL (optional)
+                         (?:https?://|//)                                    # http(s):// or protocol-independent URL
                          (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
                             (?:www\.)?deturl\.com/www\.youtube\.com/|
                             (?:www\.)?pwnyoutube\.com/|
@@ -149,7 +217,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                              )
                          ))
                          |youtu\.be/                                          # just youtu.be/xxxx
-                         |https?://(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
+                         |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
                          )
                      )?                                                       # all until now is optional -> you can pass the naked ID
                      ([0-9A-Za-z_-]{11})                                      # here is it! the YouTube video ID
@@ -244,6 +312,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 u"upload_date": u"20121002",
                 u"description": u"test chars:  \"'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .",
                 u"categories": [u'Science & Technology'],
+                'like_count': int,
+                'dislike_count': int,
             }
         },
         {
@@ -361,26 +431,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         func_id = '%s_%s_%s' % (
             player_type, player_id, self._signature_cache_id(example_sig))
         assert os.path.basename(func_id) == func_id
-        cache_dir = get_cachedir(self._downloader.params)
 
-        cache_enabled = cache_dir is not None
-        if cache_enabled:
-            cache_fn = os.path.join(os.path.expanduser(cache_dir),
-                                    u'youtube-sigfuncs',
-                                    func_id + '.json')
-            try:
-                with io.open(cache_fn, 'r', encoding='utf-8') as cachef:
-                    cache_spec = json.load(cachef)
-                return lambda s: u''.join(s[i] for i in cache_spec)
-            except IOError:
-                pass  # No cache available
-            except ValueError:
-                try:
-                    file_size = os.path.getsize(cache_fn)
-                except (OSError, IOError) as oe:
-                    file_size = str(oe)
-                self._downloader.report_warning(
-                    u'Cache %s failed (%s)' % (cache_fn, file_size))
+        cache_spec = self._downloader.cache.load(u'youtube-sigfuncs', func_id)
+        if cache_spec is not None:
+            return lambda s: u''.join(s[i] for i in cache_spec)
 
         if player_type == 'js':
             code = self._download_webpage(
@@ -398,22 +452,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         else:
             assert False, 'Invalid player type %r' % player_type
 
-        if cache_enabled:
-            try:
-                test_string = u''.join(map(compat_chr, range(len(example_sig))))
-                cache_res = res(test_string)
-                cache_spec = [ord(c) for c in cache_res]
-                try:
-                    os.makedirs(os.path.dirname(cache_fn))
-                except OSError as ose:
-                    if ose.errno != errno.EEXIST:
-                        raise
-                write_json_file(cache_spec, cache_fn)
-            except Exception:
-                tb = traceback.format_exc()
-                self._downloader.report_warning(
-                    u'Writing cache to %r failed: %s' % (cache_fn, tb))
+        if cache_spec is None:
+            test_string = u''.join(map(compat_chr, range(len(example_sig))))
+            cache_res = res(test_string)
+            cache_spec = [ord(c) for c in cache_res]
 
+        self._downloader.cache.store(u'youtube-sigfuncs', func_id, cache_spec)
         return res
 
     def _print_sig_code(self, func, example_sig):
@@ -712,7 +756,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
             upload_date = unified_strdate(upload_date)
 
-        m_cat_container = get_element_by_id("eow-category", video_webpage)
+        m_cat_container = self._search_regex(
+            r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
+            video_webpage, 'categories', fatal=False)
         if m_cat_container:
             category = self._html_search_regex(
                 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
@@ -741,15 +787,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             else:
                 video_description = u''
 
-        def _extract_count(klass):
+        def _extract_count(count_name):
             count = self._search_regex(
-                r'class="%s">([\d,]+)</span>' % re.escape(klass),
-                video_webpage, klass, default=None)
+                r'id="watch-%s"[^>]*>.*?([\d,]+)\s*</span>' % re.escape(count_name),
+                video_webpage, count_name, default=None)
             if count is not None:
                 return int(count.replace(',', ''))
             return None
-        like_count = _extract_count(u'likes-count')
-        dislike_count = _extract_count(u'dislikes-count')
+        like_count = _extract_count(u'like')
+        dislike_count = _extract_count(u'dislike')
 
         # subtitles
         video_subtitles = self.extract_subtitles(video_id, video_webpage)
@@ -979,21 +1025,26 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
         self._login()
 
     def _ids_to_results(self, ids):
-        return [self.url_result(vid_id, 'Youtube', video_id=vid_id)
-                       for vid_id in ids]
+        return [
+            self.url_result(vid_id, 'Youtube', video_id=vid_id)
+            for vid_id in ids]
 
     def _extract_mix(self, playlist_id):
         # The mixes are generated from a a single video
         # the id of the playlist is just 'RD' + video_id
         url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id)
-        webpage = self._download_webpage(url, playlist_id, u'Downloading Youtube mix')
+        webpage = self._download_webpage(
+            url, playlist_id, u'Downloading Youtube mix')
         search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
-        title_span = (search_title('playlist-title') or
-            search_title('title long-title') or search_title('title'))
+        title_span = (
+            search_title('playlist-title') or
+            search_title('title long-title') or
+            search_title('title'))
         title = clean_html(title_span)
-        video_re = r'''(?x)data-video-username=".*?".*?
-                       href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id)
-        ids = orderedSet(re.findall(video_re, webpage, flags=re.DOTALL))
+        ids = orderedSet(re.findall(
+            r'''(?xs)data-video-username=".*?".*?
+                       href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id),
+            webpage))
         url_results = self._ids_to_results(ids)
 
         return self.playlist_result(url_results, playlist_id, title)
@@ -1086,6 +1137,7 @@ class YoutubeTopListIE(YoutubePlaylistIE):
             msg = u'Downloading Youtube mix'
             if i > 0:
                 msg += ', retry #%d' % i
+
             webpage = self._download_webpage(url, title, msg)
             ids = orderedSet(re.findall(video_re, webpage))
             if ids:
@@ -1358,12 +1410,6 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
             paging = mobj.group('paging')
         return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE)
 
-class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
-    IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
-    _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
-    _FEED_NAME = 'subscriptions'
-    _PLAYLIST_TITLE = u'Youtube Subscriptions'
-
 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
     IE_DESC = u'YouTube.com recommended videos, "ytrec" keyword (requires authentication)'
     _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?'
@@ -1396,6 +1442,43 @@ class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
         return self.url_result(playlist_id, 'YoutubePlaylist')
 
 
+class YoutubeSubscriptionsIE(YoutubePlaylistIE):
+    IE_NAME = u'youtube:subscriptions'
+    IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
+    _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
+
+    def _real_extract(self, url):
+        title = u'Youtube Subscriptions'
+        page = self._download_webpage('https://www.youtube.com/feed/subscriptions', title)
+
+        # The extraction process is the same as for playlists, but the regex
+        # for the video ids doesn't contain an index
+        ids = []
+        more_widget_html = content_html = page
+
+        for page_num in itertools.count(1):
+            matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
+            new_ids = orderedSet(matches)
+            ids.extend(new_ids)
+
+            mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
+            if not mobj:
+                break
+
+            more = self._download_json(
+                'https://youtube.com/%s' % mobj.group('more'), title,
+                'Downloading page #%s' % page_num,
+                transform_source=uppercase_escape)
+            content_html = more['content_html']
+            more_widget_html = more['load_more_widget_html']
+
+        return {
+            '_type': 'playlist',
+            'title': title,
+            'entries': self._ids_to_results(ids),
+        }
+
+
 class YoutubeTruncatedURLIE(InfoExtractor):
     IE_NAME = 'youtube:truncated_url'
     IE_DESC = False  # Do not list

youtube_dl/postprocessor/__init__.py

@@ -9,6 +9,7 @@ from .ffmpeg import (
     FFmpegEmbedSubtitlePP,
 )
 from .xattrpp import XAttrMetadataPP
+from .execafterdownload import ExecAfterDownloadPP
 
 __all__ = [
     'AtomicParsleyPP',
@@ -19,4 +20,5 @@ __all__ = [
     'FFmpegExtractAudioPP',
     'FFmpegEmbedSubtitlePP',
     'XAttrMetadataPP',
+    'ExecAfterDownloadPP',
 ]

youtube_dl/postprocessor/execafterdownload.py

@@ -0,0 +1,31 @@
+from __future__ import unicode_literals
+
+import subprocess
+
+from .common import PostProcessor
+from ..utils import (
+    shlex_quote,
+    PostProcessingError,
+)
+
+
+class ExecAfterDownloadPP(PostProcessor):
+    def __init__(self, downloader=None, verboseOutput=None, exec_cmd=None):
+        self.verboseOutput = verboseOutput
+        self.exec_cmd = exec_cmd
+
+    def run(self, information):
+        cmd = self.exec_cmd
+        if not '{}' in cmd:
+            cmd += ' {}'
+
+        cmd = cmd.replace('{}', shlex_quote(information['filepath']))
+
+        self._downloader.to_screen("[exec] Executing command: %s" % cmd)
+        retCode = subprocess.call(cmd, shell=True)
+        if retCode != 0:
+            raise PostProcessingError(
+                'Command returned error code %d' % retCode)
+
+        return None, information  # by default, keep file and do nothing
+

youtube_dl/utils.py

@@ -192,6 +192,13 @@ try:
 except ImportError:  # Python 2.6
     from xml.parsers.expat import ExpatError as compat_xml_parse_error
 
+try:
+    from shlex import quote as shlex_quote
+except ImportError:  # Python < 3.3
+    def shlex_quote(s):
+        return "'" + s.replace("'", "'\"'\"'") + "'"
+
+
 def compat_ord(c):
     if type(c) is int: return c
     else: return ord(c)
@@ -291,30 +298,6 @@ def xpath_with_ns(path, ns_map):
             replaced.append('{%s}%s' % (ns_map[ns], tag))
     return '/'.join(replaced)
 
-def htmlentity_transform(matchobj):
-    """Transforms an HTML entity to a character.
-
-    This function receives a match object and is intended to be used with
-    the re.sub() function.
-    """
-    entity = matchobj.group(1)
-
-    # Known non-numeric HTML entity
-    if entity in compat_html_entities.name2codepoint:
-        return compat_chr(compat_html_entities.name2codepoint[entity])
-
-    mobj = re.match(u'(?u)#(x?\\d+)', entity)
-    if mobj is not None:
-        numstr = mobj.group(1)
-        if numstr.startswith(u'x'):
-            base = 16
-            numstr = u'0%s' % numstr
-        else:
-            base = 10
-        return compat_chr(int(numstr, base))
-
-    # Unknown entity in name, return its literal representation
-    return (u'&%s;' % entity)
 
 compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
 class BaseHTMLParser(compat_html_parser.HTMLParser):
@@ -536,13 +519,33 @@ def orderedSet(iterable):
     return res
 
 
+def _htmlentity_transform(entity):
+    """Transforms an HTML entity to a character."""
+    # Known non-numeric HTML entity
+    if entity in compat_html_entities.name2codepoint:
+        return compat_chr(compat_html_entities.name2codepoint[entity])
+
+    mobj = re.match(r'#(x?[0-9]+)', entity)
+    if mobj is not None:
+        numstr = mobj.group(1)
+        if numstr.startswith(u'x'):
+            base = 16
+            numstr = u'0%s' % numstr
+        else:
+            base = 10
+        return compat_chr(int(numstr, base))
+
+    # Unknown entity in name, return its literal representation
+    return (u'&%s;' % entity)
+
+
 def unescapeHTML(s):
     if s is None:
         return None
     assert type(s) == compat_str
 
-    result = re.sub(r'(?u)&(.+?);', htmlentity_transform, s)
-    return result
+    return re.sub(
+        r'&([^;]+);', lambda m: _htmlentity_transform(m.group(1)), s)
 
 
 def encodeFilename(s, for_subprocess=False):
@@ -614,7 +617,7 @@ def make_HTTPS_handler(opts_no_check_certificate, **kwargs):
                     self.sock = sock
                     self._tunnel()
                 try:
-                    self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv3)
+                    self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_TLSv1)
                 except ssl.SSLError:
                     self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv23)
 
@@ -622,8 +625,14 @@ def make_HTTPS_handler(opts_no_check_certificate, **kwargs):
             def https_open(self, req):
                 return self.do_open(HTTPSConnectionV3, req)
         return HTTPSHandlerV3(**kwargs)
-    else:
-        context = ssl.SSLContext(ssl.PROTOCOL_SSLv3)
+    elif hasattr(ssl, 'create_default_context'):  # Python >= 3.4
+        context = ssl.create_default_context(ssl.Purpose.CLIENT_AUTH)
+        context.options &= ~ssl.OP_NO_SSLv3  # Allow older, not-as-secure SSLv3
+        if opts_no_check_certificate:
+            context.verify_mode = ssl.CERT_NONE
+        return compat_urllib_request.HTTPSHandler(context=context, **kwargs)
+    else:  # Python < 3.4
+        context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
         context.verify_mode = (ssl.CERT_NONE
                                if opts_no_check_certificate
                                else ssl.CERT_REQUIRED)
@@ -759,10 +768,9 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
         return ret
 
     def http_request(self, req):
-        for h,v in std_headers.items():
-            if h in req.headers:
-                del req.headers[h]
-            req.add_header(h, v)
+        for h, v in std_headers.items():
+            if h not in req.headers:
+                req.add_header(h, v)
         if 'Youtubedl-no-compression' in req.headers:
             if 'Accept-encoding' in req.headers:
                 del req.headers['Accept-encoding']
@@ -1074,12 +1082,6 @@ def intlist_to_bytes(xs):
         return bytes(xs)
 
 
-def get_cachedir(params={}):
-    cache_root = os.environ.get('XDG_CACHE_HOME',
-                                os.path.expanduser('~/.cache'))
-    return params.get('cachedir', os.path.join(cache_root, 'youtube-dl'))
-
-
 # Cross-platform file locking
 if sys.platform == 'win32':
     import ctypes.wintypes
@@ -1139,10 +1141,10 @@ else:
     import fcntl
 
     def _lock_file(f, exclusive):
-        fcntl.lockf(f, fcntl.LOCK_EX if exclusive else fcntl.LOCK_SH)
+        fcntl.flock(f, fcntl.LOCK_EX if exclusive else fcntl.LOCK_SH)
 
     def _unlock_file(f):
-        fcntl.lockf(f, fcntl.LOCK_UN)
+        fcntl.flock(f, fcntl.LOCK_UN)
 
 
 class locked_file(object):
@@ -1316,9 +1318,10 @@ def str_or_none(v, default=None):
 
 
 def str_to_int(int_str):
+    """ A more relaxed version of int_or_none """
     if int_str is None:
         return None
-    int_str = re.sub(r'[,\.]', u'', int_str)
+    int_str = re.sub(r'[,\.\+]', u'', int_str)
     return int(int_str)
 
 
@@ -1330,8 +1333,10 @@ def parse_duration(s):
     if s is None:
         return None
 
+    s = s.strip()
+
     m = re.match(
-        r'(?:(?:(?P<hours>[0-9]+)[:h])?(?P<mins>[0-9]+)[:m])?(?P<secs>[0-9]+)s?(?::[0-9]+)?$', s)
+        r'(?i)(?:(?:(?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*)?(?P<mins>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?$', s)
     if not m:
         return None
     res = int(m.group('secs'))
@@ -1339,6 +1344,8 @@ def parse_duration(s):
         res += int(m.group('mins')) * 60
         if m.group('hours'):
             res += int(m.group('hours')) * 60 * 60
+    if m.group('ms'):
+        res += float(m.group('ms'))
     return res
 
 
@@ -1449,6 +1456,12 @@ def urlencode_postdata(*args, **kargs):
     return compat_urllib_parse.urlencode(*args, **kargs).encode('ascii')
 
 
+try:
+    etree_iter = xml.etree.ElementTree.Element.iter
+except AttributeError:  # Python <=2.6
+    etree_iter = lambda n: n.findall('.//*')
+
+
 def parse_xml(s):
     class TreeBuilder(xml.etree.ElementTree.TreeBuilder):
         def doctype(self, name, pubid, system):
@@ -1456,7 +1469,14 @@ def parse_xml(s):
 
     parser = xml.etree.ElementTree.XMLParser(target=TreeBuilder())
     kwargs = {'parser': parser} if sys.version_info >= (2, 7) else {}
-    return xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs)
+    tree = xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs)
+    # Fix up XML parser in Python 2.x
+    if sys.version_info < (3, 0):
+        for n in etree_iter(tree):
+            if n.text is not None:
+                if not isinstance(n.text, compat_str):
+                    n.text = n.text.decode('utf-8')
+    return tree
 
 
 if sys.version_info < (3, 0) and sys.platform == 'win32':

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.08.24.4'
+__version__ = '2014.09.12'