release 2014.09.24

It's used in some akamai videos (for example for theplatform.com).

.gitignore

@@ -11,6 +11,7 @@ MANIFEST
 README.txt
 youtube-dl.1
 youtube-dl.bash-completion
+youtube-dl.fish
 youtube-dl
 youtube-dl.exe
 youtube-dl.tar.gz

LATEST_VERSION

@@ -1 +0,0 @@
-2012.12.99

MANIFEST.in

@@ -2,5 +2,6 @@ include README.md
 include test/*.py
 include test/*.json
 include youtube-dl.bash-completion
+include youtube-dl.fish
 include youtube-dl.1
 recursive-include docs Makefile conf.py *.rst

Makefile

@@ -1,7 +1,7 @@
-all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
+all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.fish
 
 clean:
-	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz
+	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.fish
 
 cleanall: clean
 	rm -f youtube-dl youtube-dl.exe
@@ -29,6 +29,8 @@ install: youtube-dl youtube-dl.1 youtube-dl.bash-completion
 	install -m 644 youtube-dl.1 $(DESTDIR)$(MANDIR)/man1
 	install -d $(DESTDIR)$(SYSCONFDIR)/bash_completion.d
 	install -m 644 youtube-dl.bash-completion $(DESTDIR)$(SYSCONFDIR)/bash_completion.d/youtube-dl
+	install -d $(DESTDIR)$(SYSCONFDIR)/fish/completions
+	install -m 644 youtube-dl.fish $(DESTDIR)$(SYSCONFDIR)/fish/completions/youtube-dl.fish
 
 test:
 	#nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose --processes 4 test
@@ -36,9 +38,9 @@ test:
 
 tar: youtube-dl.tar.gz
 
-.PHONY: all clean install test tar bash-completion pypi-files
+.PHONY: all clean install test tar bash-completion pypi-files fish-completion
 
-pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1
+pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1 youtube-dl.fish
 
 youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
 	zip --quiet youtube-dl youtube_dl/*.py youtube_dl/*/*.py
@@ -64,7 +66,12 @@ youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-co
 
 bash-completion: youtube-dl.bash-completion
 
-youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
+youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in
+	python devscripts/fish-completion.py
+
+fish-completion: youtube-dl.fish
+
+youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.fish
 	@tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \
 		--exclude '*.DS_Store' \
 		--exclude '*.kate-swp' \
@@ -78,5 +85,6 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
 		-- \
 		bin devscripts test youtube_dl docs \
 		LICENSE README.md README.txt \
-		Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion setup.py \
+		Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion \
+		youtube-dl.fish setup.py \
 		youtube-dl

README.md

@@ -227,12 +227,15 @@ which means you can modify it, redistribute it or use it however you like.
 
 ## Video Format Options:
     -f, --format FORMAT              video format code, specify the order of
-                                     preference using slashes: "-f 22/17/18".
-                                     "-f mp4" and "-f flv" are also supported.
-                                     You can also use the special names "best",
-                                     "bestvideo", "bestaudio", "worst",
-                                     "worstvideo" and "worstaudio". By default,
-                                     youtube-dl will pick the best quality.
+                                     preference using slashes: -f 22/17/18 .  -f
+                                     mp4 , -f m4a and  -f flv  are also
+                                     supported. You can also use the special
+                                     names "best", "bestvideo", "bestaudio",
+                                     "worst", "worstvideo" and "worstaudio". By
+                                     default, youtube-dl will pick the best
+                                     quality. Use commas to download multiple
+                                     audio formats, such as  -f
+                                     136/137/mp4/bestvideo,140/m4a/bestaudio
     --all-formats                    download all available video formats
     --prefer-free-formats            prefer free video formats unless a specific
                                      one is requested
@@ -345,6 +348,25 @@ $ youtube-dl --dateafter 20000101 --datebefore 20091231
 
 # FAQ
 
+### I'm getting an error `Unable to extract OpenGraph title` on YouTube playlists
+
+YouTube changed their playlist format in March 2014 and later on, so you'll need at least youtube-dl 2014.07.25 to download all YouTube videos.
+
+If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to report bugs to the Ubuntu packaging guys - all they have to do is update the package to a somewhat recent version.
+
+Alternatively, uninstall the youtube-dl package and follow [our manual installation instructions](http://rg3.github.io/youtube-dl/download.html). In a pinch, this should do if you used `apt-get` before to install youtube-dl:
+
+```
+sudo apt-get remove -y youtube-dl
+sudo wget https://yt-dl.org/latest/youtube-dl -O /usr/local/bin/youtube-dl
+sudo chmod a+x /usr/local/bin/youtube-dl
+hash -r
+```
+
+### Do I always have to pass in `--max-quality FORMAT`, or `-citw`?
+
+By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, `--max-quality` *limits* the video quality (so if you want the best quality, do NOT pass it in), and the only option out of `-citw` that is regularly useful is `-i`.
+
 ### Can you please put the -b option back?
 
 Most people asking this question are not aware that youtube-dl now defaults to downloading the highest available quality as reported by YouTube, which will be 1080p or 720p in some cases, so you no longer need the `-b` option. For some specific videos, maybe YouTube does not report them to be available in a specific high quality format you're interested in. In that case, simply request it with the `-f` option and youtube-dl will try to download it.

devscripts/fish-completion.in

@@ -0,0 +1,5 @@
+
+{{commands}}
+
+
+complete --command youtube-dl --arguments ":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory"

devscripts/fish-completion.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env python
+from __future__ import unicode_literals
+
+import optparse
+import os
+from os.path import dirname as dirn
+import sys
+
+sys.path.append(dirn(dirn((os.path.abspath(__file__)))))
+import youtube_dl
+from youtube_dl.utils import shell_quote
+
+FISH_COMPLETION_FILE = 'youtube-dl.fish'
+FISH_COMPLETION_TEMPLATE = 'devscripts/fish-completion.in'
+
+EXTRA_ARGS = {
+    'recode-video': ['--arguments', 'mp4 flv ogg webm mkv', '--exclusive'],
+
+    # Options that need a file parameter
+    'download-archive': ['--require-parameter'],
+    'cookies': ['--require-parameter'],
+    'load-info': ['--require-parameter'],
+    'batch-file': ['--require-parameter'],
+}
+
+def build_completion(opt_parser):
+    commands = []
+
+    for group in opt_parser.option_groups:
+        for option in group.option_list:
+            long_option = option.get_opt_string().strip('-')
+            help_msg = shell_quote([option.help])
+            complete_cmd = ['complete', '--command', 'youtube-dl', '--long-option', long_option]
+            if option._short_opts:
+                complete_cmd += ['--short-option', option._short_opts[0].strip('-')]
+            if option.help != optparse.SUPPRESS_HELP:
+                complete_cmd += ['--description', option.help]
+            complete_cmd.extend(EXTRA_ARGS.get(long_option, []))
+            commands.append(shell_quote(complete_cmd))
+
+    with open(FISH_COMPLETION_TEMPLATE) as f:
+        template = f.read()
+    filled_template = template.replace('{{commands}}', '\n'.join(commands))
+    with open(FISH_COMPLETION_FILE, 'w') as f:
+        f.write(filled_template)
+
+parser = youtube_dl.parseOpts()[0]
+build_completion(parser)

devscripts/release.sh

@@ -73,7 +73,6 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
 (cd build/$version/ && sha1sum $RELEASE_FILES > SHA1SUMS)
 (cd build/$version/ && sha256sum $RELEASE_FILES > SHA2-256SUMS)
 (cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS)
-git checkout HEAD -- youtube-dl youtube-dl.exe
 
 /bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
 for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done

setup.py

@@ -48,6 +48,7 @@ if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
 else:
     files_spec = [
         ('etc/bash_completion.d', ['youtube-dl.bash-completion']),
+        ('etc/fish/completions', ['youtube-dl.fish']),
         ('share/doc/youtube_dl', ['README.txt']),
         ('share/man/man1', ['youtube-dl.1'])
     ]

test/test_all_urls.py

@@ -143,32 +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

@@ -167,21 +167,21 @@ def generator(test_case):
                 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'])
-                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)))
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
 

test/test_utils.py

@@ -40,6 +40,9 @@ from youtube_dl.utils import (
     parse_iso8601,
     strip_jsonp,
     uppercase_escape,
+    limit_length,
+    escape_rfc3986,
+    escape_url,
 )
 
 
@@ -211,6 +214,9 @@ 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)
@@ -283,5 +289,41 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(uppercase_escape('aä'), 'aä')
         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
 
+    def test_limit_length(self):
+        self.assertEqual(limit_length(None, 12), None)
+        self.assertEqual(limit_length('foo', 12), 'foo')
+        self.assertTrue(
+            limit_length('foo bar baz asd', 12).startswith('foo bar'))
+        self.assertTrue('...' in limit_length('foo bar baz asd', 12))
+
+    def test_escape_rfc3986(self):
+        reserved = "!*'();:@&=+$,/?#[]"
+        unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
+        self.assertEqual(escape_rfc3986(reserved), reserved)
+        self.assertEqual(escape_rfc3986(unreserved), unreserved)
+        self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
+        self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
+        self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
+        self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
+
+    def test_escape_url(self):
+        self.assertEqual(
+            escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
+            'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
+        )
+        self.assertEqual(
+            escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
+            'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
+        )
+        self.assertEqual(
+            escape_url('http://тест.рф/фрагмент'),
+            'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
+        )
+        self.assertEqual(
+            escape_url('http://тест.рф/абв?абв=абв#абв'),
+            'http://тест.рф/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
+        )
+        self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_lists.py

@@ -10,7 +10,6 @@ from test.helper import FakeYDL
 
 
 from youtube_dl.extractor import (
-    YoutubeUserIE,
     YoutubePlaylistIE,
     YoutubeIE,
     YoutubeChannelIE,
@@ -25,15 +24,6 @@ class TestYoutubeLists(unittest.TestCase):
         """Make sure the info has '_type' set to 'playlist'"""
         self.assertEqual(info['_type'], 'playlist')
 
-    def test_youtube_playlist(self):
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'ytdl test PL')
-        ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
-        self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE'])
-
     def test_youtube_playlist_noplaylist(self):
         dl = FakeYDL()
         dl.params['noplaylist'] = True
@@ -41,36 +31,7 @@ class TestYoutubeLists(unittest.TestCase):
         result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
         self.assertEqual(result['_type'], 'url')
         self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg')
-
-    def test_issue_673(self):
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('PLBB231211A4F62143')
-        self.assertTrue(len(result['entries']) > 25)
-
-    def test_youtube_playlist_long(self):
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
-        self.assertIsPlaylist(result)
-        self.assertTrue(len(result['entries']) >= 799)
-
-    def test_youtube_playlist_with_deleted(self):
-        #651
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
-        ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
-        self.assertFalse('pElCt5oNDuI' in ytie_results)
-        self.assertFalse('KdPEApIVdWM' in ytie_results)
-        
-    def test_youtube_playlist_empty(self):
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx')
-        self.assertIsPlaylist(result)
-        self.assertEqual(len(result['entries']), 0)
-
+    
     def test_youtube_course(self):
         dl = FakeYDL()
         ie = YoutubePlaylistIE(dl)
@@ -81,34 +42,6 @@ class TestYoutubeLists(unittest.TestCase):
         self.assertEqual(len(entries), 25)
         self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
 
-    def test_youtube_channel(self):
-        dl = FakeYDL()
-        ie = YoutubeChannelIE(dl)
-        #test paginated channel
-        result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w')
-        self.assertTrue(len(result['entries']) > 90)
-        #test autogenerated channel
-        result = ie.extract('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
-        self.assertTrue(len(result['entries']) >= 18)
-
-    def test_youtube_user(self):
-        dl = FakeYDL()
-        ie = YoutubeUserIE(dl)
-        result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')
-        self.assertTrue(len(result['entries']) >= 320)
-
-    def test_youtube_safe_search(self):
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl')
-        self.assertEqual(len(result['entries']), 2)
-
-    def test_youtube_show(self):
-        dl = FakeYDL()
-        ie = YoutubeShowIE(dl)
-        result = ie.extract('http://www.youtube.com/show/airdisasters')
-        self.assertTrue(len(result) >= 3)
-
     def test_youtube_mix(self):
         dl = FakeYDL()
         ie = YoutubePlaylistIE(dl)
@@ -127,21 +60,5 @@ class TestYoutubeLists(unittest.TestCase):
         entries = result['entries']
         self.assertEqual(len(entries), 100)
 
-    def test_youtube_toplist(self):
-        dl = FakeYDL()
-        ie = YoutubeTopListIE(dl)
-        result = ie.extract('yttoplist:music:Trending')
-        entries = result['entries']
-        self.assertTrue(len(entries) >= 5)
-
-    def test_youtube_search_url(self):
-        dl = FakeYDL()
-        ie = YoutubeSearchURLIE(dl)
-        result = ie.extract('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video')
-        entries = result['entries']
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'youtube-dl test video')
-        self.assertTrue(len(entries) >= 5)
-
 if __name__ == '__main__':
     unittest.main()

youtube-dl

@@ -1,89 +0,0 @@
-#!/usr/bin/env python
-
-import sys, os
-import json, hashlib
-
-try:
-    import urllib.request as compat_urllib_request
-except ImportError: # Python 2
-    import urllib2 as compat_urllib_request
-
-def rsa_verify(message, signature, key):
-    from struct import pack
-    from hashlib import sha256
-    from sys import version_info
-    def b(x):
-        if version_info[0] == 2: return x
-        else: return x.encode('latin1')
-    assert(type(message) == type(b('')))
-    block_size = 0
-    n = key[0]
-    while n:
-        block_size += 1
-        n >>= 8
-    signature = pow(int(signature, 16), key[1], key[0])
-    raw_bytes = []
-    while signature:
-        raw_bytes.insert(0, pack("B", signature & 0xFF))
-        signature >>= 8
-    signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
-    if signature[0:2] != b('\x00\x01'): return False
-    signature = signature[2:]
-    if not b('\x00') in signature: return False
-    signature = signature[signature.index(b('\x00'))+1:]
-    if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False
-    signature = signature[19:]
-    if signature != sha256(message).digest(): return False
-    return True
-
-sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
-sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
-sys.stderr.write(u'From now on, get the binaries from http://rg3.github.io/youtube-dl/download.html, not from the git repository.\n\n')
-
-try:
-	raw_input()
-except NameError: # Python 3
-	input()
-
-filename = sys.argv[0]
-
-UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
-VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
-JSON_URL = UPDATE_URL + 'versions.json'
-UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
-
-if not os.access(filename, os.W_OK):
-    sys.exit('ERROR: no write permissions on %s' % filename)
-
-try:
-    versions_info = compat_urllib_request.urlopen(JSON_URL).read().decode('utf-8')
-    versions_info = json.loads(versions_info)
-except:
-    sys.exit(u'ERROR: can\'t obtain versions info. Please try again later.')
-if not 'signature' in versions_info:
-    sys.exit(u'ERROR: the versions file is not signed or corrupted. Aborting.')
-signature = versions_info['signature']
-del versions_info['signature']
-if not rsa_verify(json.dumps(versions_info, sort_keys=True).encode('utf-8'), signature, UPDATES_RSA_KEY):
-    sys.exit(u'ERROR: the versions file signature is invalid. Aborting.')
-
-version = versions_info['versions'][versions_info['latest']]
-
-try:
-    urlh = compat_urllib_request.urlopen(version['bin'][0])
-    newcontent = urlh.read()
-    urlh.close()
-except (IOError, OSError) as err:
-    sys.exit('ERROR: unable to download latest version')
-
-newcontent_hash = hashlib.sha256(newcontent).hexdigest()
-if newcontent_hash != version['bin'][1]:
-    sys.exit(u'ERROR: the downloaded file hash does not match. Aborting.')
-
-try:
-    with open(filename, 'wb') as outf:
-        outf.write(newcontent)
-except (IOError, OSError) as err:
-    sys.exit('ERROR: unable to overwrite current version')
-
-sys.stderr.write(u'Done! Now you can run youtube-dl.\n')

youtube_dl/YoutubeDL.py

@@ -28,6 +28,7 @@ from .utils import (
     compat_str,
     compat_urllib_error,
     compat_urllib_request,
+    escape_url,
     ContentTooShortError,
     date_from_str,
     DateRange,
@@ -57,6 +58,7 @@ 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 +135,7 @@ 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.
@@ -195,6 +197,7 @@ 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:
@@ -705,7 +708,7 @@ class YoutubeDL(object):
             if video_formats:
                 return video_formats[0]
         else:
-            extensions = ['mp4', 'flv', 'webm', '3gp']
+            extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a']
             if format_spec in extensions:
                 filter_f = lambda f: f['ext'] == format_spec
             else:
@@ -806,28 +809,29 @@ class YoutubeDL(object):
         if req_format in ('-1', 'all'):
             formats_to_download = formats
         else:
-            # We can accept formats requested in the format: 34/5/best, we pick
-            # the first that is available, starting from left
-            req_formats = req_format.split('/')
-            for rf in req_formats:
-                if re.match(r'.+?\+.+?', rf) is not None:
-                    # Two formats have been requested like '137+139'
-                    format_1, format_2 = rf.split('+')
-                    formats_info = (self.select_format(format_1, formats),
-                        self.select_format(format_2, formats))
-                    if all(formats_info):
-                        selected_format = {
-                            'requested_formats': formats_info,
-                            'format': rf,
-                            'ext': formats_info[0]['ext'],
-                        }
+            for rfstr in req_format.split(','):
+                # We can accept formats requested in the format: 34/5/best, we pick
+                # the first that is available, starting from left
+                req_formats = rfstr.split('/')
+                for rf in req_formats:
+                    if re.match(r'.+?\+.+?', rf) is not None:
+                        # Two formats have been requested like '137+139'
+                        format_1, format_2 = rf.split('+')
+                        formats_info = (self.select_format(format_1, formats),
+                            self.select_format(format_2, formats))
+                        if all(formats_info):
+                            selected_format = {
+                                'requested_formats': formats_info,
+                                'format': rf,
+                                'ext': formats_info[0]['ext'],
+                            }
+                        else:
+                            selected_format = None
                     else:
-                        selected_format = None
-                else:
-                    selected_format = self.select_format(rf, formats)
-                if selected_format is not None:
-                    formats_to_download = [selected_format]
-                    break
+                        selected_format = self.select_format(rf, formats)
+                    if selected_format is not None:
+                        formats_to_download.append(selected_format)
+                        break
         if not formats_to_download:
             raise ExtractorError('requested format not available',
                                  expected=True)
@@ -1239,6 +1243,25 @@ class YoutubeDL(object):
 
     def urlopen(self, req):
         """ Start an HTTP download """
+
+        # According to RFC 3986, URLs can not contain non-ASCII characters, however this is not
+        # always respected by websites, some tend to give out URLs with non percent-encoded
+        # non-ASCII characters (see telemb.py, ard.py [#3412])
+        # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
+        # To work around aforementioned issue we will replace request's original URL with
+        # percent-encoded one
+        url = req if isinstance(req, compat_str) else req.get_full_url()
+        url_escaped = escape_url(url)
+
+        # Substitute URL if any change after escaping
+        if url != url_escaped:
+            if isinstance(req, compat_str):
+                req = url_escaped
+            else:
+                req = compat_urllib_request.Request(
+                    url_escaped, data=req.data, headers=req.headers,
+                    origin_req_host=req.origin_req_host, unverifiable=req.unverifiable)
+
         return self._opener.open(req, timeout=self._socket_timeout)
 
     def print_debug_header(self):

youtube_dl/__init__.py

@@ -74,29 +74,31 @@ __authors__  = (
     'Keith Beckman',
     'Ole Ernst',
     'Aaron McDaniel (mcd1992)',
+    'Magnus Kolstad',
+    'Hari Padmanaban',
+    'Carlos Ramos',
+    '5moufl',
 )
 
 __license__ = 'Public Domain'
 
 import codecs
 import io
-import optparse
 import os
 import random
-import shlex
-import shutil
 import sys
 
 
+from .options import (
+    parseOpts,
+)
 from .utils import (
     compat_getpass,
     compat_print,
     DateRange,
     DEFAULT_OUTTMPL,
     decodeOption,
-    get_term_width,
     DownloadError,
-    get_cachedir,
     MaxDownloadsReached,
     preferredencoding,
     read_batch_urls,
@@ -110,7 +112,6 @@ from .downloader import (
     FileDownloader,
 )
 from .extractor import gen_extractors
-from .version import __version__
 from .YoutubeDL import YoutubeDL
 from .postprocessor import (
     AtomicParsleyPP,
@@ -124,475 +125,6 @@ from .postprocessor import (
 )
 
 
-def parseOpts(overrideArguments=None):
-    def _readOptions(filename_bytes, default=[]):
-        try:
-            optionf = open(filename_bytes)
-        except IOError:
-            return default  # silently skip if file is not present
-        try:
-            res = []
-            for l in optionf:
-                res += shlex.split(l, comments=True)
-        finally:
-            optionf.close()
-        return res
-
-    def _readUserConf():
-        xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
-        if xdg_config_home:
-            userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config')
-            if not os.path.isfile(userConfFile):
-                userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
-        else:
-            userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config')
-            if not os.path.isfile(userConfFile):
-                userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
-        userConf = _readOptions(userConfFile, None)
-
-        if userConf is None:
-            appdata_dir = os.environ.get('appdata')
-            if appdata_dir:
-                userConf = _readOptions(
-                    os.path.join(appdata_dir, 'youtube-dl', 'config'),
-                    default=None)
-                if userConf is None:
-                    userConf = _readOptions(
-                        os.path.join(appdata_dir, 'youtube-dl', 'config.txt'),
-                        default=None)
-
-        if userConf is None:
-            userConf = _readOptions(
-                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf'),
-                default=None)
-        if userConf is None:
-            userConf = _readOptions(
-                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf.txt'),
-                default=None)
-
-        if userConf is None:
-            userConf = []
-
-        return userConf
-
-    def _format_option_string(option):
-        ''' ('-o', '--option') -> -o, --format METAVAR'''
-
-        opts = []
-
-        if option._short_opts:
-            opts.append(option._short_opts[0])
-        if option._long_opts:
-            opts.append(option._long_opts[0])
-        if len(opts) > 1:
-            opts.insert(1, ', ')
-
-        if option.takes_value(): opts.append(' %s' % option.metavar)
-
-        return "".join(opts)
-
-    def _comma_separated_values_options_callback(option, opt_str, value, parser):
-        setattr(parser.values, option.dest, value.split(','))
-
-    def _hide_login_info(opts):
-        opts = list(opts)
-        for private_opt in ['-p', '--password', '-u', '--username', '--video-password']:
-            try:
-                i = opts.index(private_opt)
-                opts[i+1] = '<PRIVATE>'
-            except ValueError:
-                pass
-        return opts
-
-    max_width = 80
-    max_help_position = 80
-
-    # No need to wrap help messages if we're on a wide console
-    columns = get_term_width()
-    if columns: max_width = columns
-
-    fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position)
-    fmt.format_option_strings = _format_option_string
-
-    kw = {
-        'version'   : __version__,
-        'formatter' : fmt,
-        'usage' : '%prog [options] url [url...]',
-        'conflict_handler' : 'resolve',
-    }
-
-    parser = optparse.OptionParser(**kw)
-
-    # option groups
-    general        = optparse.OptionGroup(parser, 'General Options')
-    selection      = optparse.OptionGroup(parser, 'Video Selection')
-    authentication = optparse.OptionGroup(parser, 'Authentication Options')
-    video_format   = optparse.OptionGroup(parser, 'Video Format Options')
-    subtitles      = optparse.OptionGroup(parser, 'Subtitle Options')
-    downloader     = optparse.OptionGroup(parser, 'Download Options')
-    postproc       = optparse.OptionGroup(parser, 'Post-processing Options')
-    filesystem     = optparse.OptionGroup(parser, 'Filesystem Options')
-    workarounds    = optparse.OptionGroup(parser, 'Workarounds')
-    verbosity      = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
-
-    general.add_option('-h', '--help',
-            action='help', help='print this help text and exit')
-    general.add_option('-v', '--version',
-            action='version', help='print program version and exit')
-    general.add_option('-U', '--update',
-            action='store_true', dest='update_self', help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
-    general.add_option('-i', '--ignore-errors',
-            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to skip unavailable videos in a playlist', default=False)
-    general.add_option('--abort-on-error',
-            action='store_false', dest='ignoreerrors',
-            help='Abort downloading of further videos (in the playlist or the command line) if an error occurs')
-    general.add_option('--dump-user-agent',
-            action='store_true', dest='dump_user_agent',
-            help='display the current browser identification', default=False)
-    general.add_option('--list-extractors',
-            action='store_true', dest='list_extractors',
-            help='List all supported extractors and the URLs they would handle', default=False)
-    general.add_option('--extractor-descriptions',
-            action='store_true', dest='list_extractor_descriptions',
-            help='Output descriptions of all supported extractors', default=False)
-    general.add_option(
-        '--proxy', dest='proxy', default=None, metavar='URL',
-        help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection')
-    general.add_option(
-        '--socket-timeout', dest='socket_timeout',
-        type=float, default=None, help=u'Time to wait before giving up, in seconds')
-    general.add_option(
-        '--default-search',
-        dest='default_search', metavar='PREFIX',
-        help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for  youtube-dl "large apple". Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.')
-    general.add_option(
-        '--ignore-config',
-        action='store_true',
-        help='Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows)')
-
-    selection.add_option(
-        '--playlist-start',
-        dest='playliststart', metavar='NUMBER', default=1, type=int,
-        help='playlist video to start at (default is %default)')
-    selection.add_option(
-        '--playlist-end',
-        dest='playlistend', metavar='NUMBER', default=None, type=int,
-        help='playlist video to end at (default is last)')
-    selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
-    selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
-    selection.add_option('--max-downloads', metavar='NUMBER',
-                         dest='max_downloads', type=int, default=None,
-                         help='Abort after downloading NUMBER files')
-    selection.add_option('--min-filesize', metavar='SIZE', dest='min_filesize', help="Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)", default=None)
-    selection.add_option('--max-filesize', metavar='SIZE', dest='max_filesize', help="Do not download any videos larger than SIZE (e.g. 50k or 44.6m)", default=None)
-    selection.add_option('--date', metavar='DATE', dest='date', help='download only videos uploaded in this date', default=None)
-    selection.add_option(
-        '--datebefore', metavar='DATE', dest='datebefore', default=None,
-        help='download only videos uploaded on or before this date (i.e. inclusive)')
-    selection.add_option(
-        '--dateafter', metavar='DATE', dest='dateafter', default=None,
-        help='download only videos uploaded on or after this date (i.e. inclusive)')
-    selection.add_option(
-        '--min-views', metavar='COUNT', dest='min_views',
-        default=None, type=int,
-        help="Do not download any videos with less than COUNT views",)
-    selection.add_option(
-        '--max-views', metavar='COUNT', dest='max_views',
-        default=None, type=int,
-        help="Do not download any videos with more than COUNT views",)
-    selection.add_option('--no-playlist', action='store_true', dest='noplaylist', help='download only the currently playing video', default=False)
-    selection.add_option('--age-limit', metavar='YEARS', dest='age_limit',
-                         help='download only videos suitable for the given age',
-                         default=None, type=int)
-    selection.add_option('--download-archive', metavar='FILE',
-                         dest='download_archive',
-                         help='Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.')
-    selection.add_option(
-        '--include-ads', dest='include_ads',
-        action='store_true',
-        help='Download advertisements as well (experimental)')
-    selection.add_option(
-        '--youtube-include-dash-manifest', action='store_true',
-        dest='youtube_include_dash_manifest', default=False,
-        help='Try to download the DASH manifest on YouTube videos (experimental)')
-
-    authentication.add_option('-u', '--username',
-            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',
-            dest='videopassword', metavar='PASSWORD', help='video password (vimeo, smotri)')
-
-
-    video_format.add_option('-f', '--format',
-            action='store', dest='format', metavar='FORMAT', default=None,
-            help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported. You can also use the special names "best", "bestvideo", "bestaudio", "worst", "worstvideo" and "worstaudio". By default, youtube-dl will pick the best quality.')
-    video_format.add_option('--all-formats',
-            action='store_const', dest='format', help='download all available video formats', const='all')
-    video_format.add_option('--prefer-free-formats',
-            action='store_true', dest='prefer_free_formats', default=False, help='prefer free video formats unless a specific one is requested')
-    video_format.add_option('--max-quality',
-            action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
-    video_format.add_option('-F', '--list-formats',
-            action='store_true', dest='listformats', help='list all available formats')
-
-    subtitles.add_option('--write-sub', '--write-srt',
-            action='store_true', dest='writesubtitles',
-            help='write subtitle file', default=False)
-    subtitles.add_option('--write-auto-sub', '--write-automatic-sub',
-            action='store_true', dest='writeautomaticsub',
-            help='write automatic subtitle file (youtube only)', default=False)
-    subtitles.add_option('--all-subs',
-            action='store_true', dest='allsubtitles',
-            help='downloads all the available subtitles of the video', default=False)
-    subtitles.add_option('--list-subs',
-            action='store_true', dest='listsubtitles',
-            help='lists all available subtitles for the video', default=False)
-    subtitles.add_option('--sub-format',
-            action='store', dest='subtitlesformat', metavar='FORMAT',
-            help='subtitle format (default=srt) ([sbv/vtt] youtube only)', default='srt')
-    subtitles.add_option('--sub-lang', '--sub-langs', '--srt-lang',
-            action='callback', dest='subtitleslangs', metavar='LANGS', type='str',
-            default=[], callback=_comma_separated_values_options_callback,
-            help='languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'')
-
-    downloader.add_option('-r', '--rate-limit',
-            dest='ratelimit', metavar='LIMIT', help='maximum download rate in bytes per second (e.g. 50K or 4.2M)')
-    downloader.add_option('-R', '--retries',
-            dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10)
-    downloader.add_option('--buffer-size',
-            dest='buffersize', metavar='SIZE', help='size of download buffer (e.g. 1024 or 16K) (default is %default)', default="1024")
-    downloader.add_option('--no-resize-buffer',
-            action='store_true', dest='noresizebuffer',
-            help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.', default=False)
-    downloader.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP)
-
-    workarounds.add_option(
-        '--encoding', dest='encoding', metavar='ENCODING',
-        help='Force the specified encoding (experimental)')
-    workarounds.add_option(
-        '--no-check-certificate', action='store_true',
-        dest='no_check_certificate', default=False,
-        help='Suppress HTTPS certificate validation.')
-    workarounds.add_option(
-        '--prefer-insecure', '--prefer-unsecure', action='store_true', dest='prefer_insecure',
-        help='Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)')
-    workarounds.add_option(
-        '--user-agent', metavar='UA',
-        dest='user_agent', help='specify a custom user agent')
-    workarounds.add_option(
-        '--referer', metavar='REF',
-        dest='referer', default=None,
-        help='specify a custom referer, use if the video access is restricted to one domain',
-    )
-    workarounds.add_option(
-        '--add-header', metavar='FIELD:VALUE',
-        dest='headers', action='append',
-        help='specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times',
-    )
-    workarounds.add_option(
-        '--bidi-workaround', dest='bidi_workaround', action='store_true',
-        help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH')
-
-    verbosity.add_option('-q', '--quiet',
-            action='store_true', dest='quiet', help='activates quiet mode', default=False)
-    verbosity.add_option(
-        '--no-warnings',
-        dest='no_warnings', action='store_true', default=False,
-        help='Ignore warnings')
-    verbosity.add_option('-s', '--simulate',
-            action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False)
-    verbosity.add_option('--skip-download',
-            action='store_true', dest='skip_download', help='do not download the video', default=False)
-    verbosity.add_option('-g', '--get-url',
-            action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
-    verbosity.add_option('-e', '--get-title',
-            action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
-    verbosity.add_option('--get-id',
-            action='store_true', dest='getid', help='simulate, quiet but print id', default=False)
-    verbosity.add_option('--get-thumbnail',
-            action='store_true', dest='getthumbnail',
-            help='simulate, quiet but print thumbnail URL', default=False)
-    verbosity.add_option('--get-description',
-            action='store_true', dest='getdescription',
-            help='simulate, quiet but print video description', default=False)
-    verbosity.add_option('--get-duration',
-            action='store_true', dest='getduration',
-            help='simulate, quiet but print video length', default=False)
-    verbosity.add_option('--get-filename',
-            action='store_true', dest='getfilename',
-            help='simulate, quiet but print output filename', default=False)
-    verbosity.add_option('--get-format',
-            action='store_true', dest='getformat',
-            help='simulate, quiet but print output format', default=False)
-    verbosity.add_option('-j', '--dump-json',
-            action='store_true', dest='dumpjson',
-            help='simulate, quiet but print JSON information. See --output for a description of available keys.', default=False)
-    verbosity.add_option('--newline',
-            action='store_true', dest='progress_with_newline', help='output progress bar as new lines', default=False)
-    verbosity.add_option('--no-progress',
-            action='store_true', dest='noprogress', help='do not print progress bar', default=False)
-    verbosity.add_option('--console-title',
-            action='store_true', dest='consoletitle',
-            help='display progress in console titlebar', default=False)
-    verbosity.add_option('-v', '--verbose',
-            action='store_true', dest='verbose', help='print various debugging information', default=False)
-    verbosity.add_option('--dump-intermediate-pages',
-            action='store_true', dest='dump_intermediate_pages', default=False,
-            help='print downloaded pages to debug problems (very verbose)')
-    verbosity.add_option('--write-pages',
-            action='store_true', dest='write_pages', default=False,
-            help='Write downloaded intermediary pages to files in the current directory to debug problems')
-    verbosity.add_option('--youtube-print-sig-code',
-            action='store_true', dest='youtube_print_sig_code', default=False,
-            help=optparse.SUPPRESS_HELP)
-    verbosity.add_option('--print-traffic',
-            dest='debug_printtraffic', action='store_true', default=False,
-            help='Display sent and read HTTP traffic')
-
-
-    filesystem.add_option('-a', '--batch-file',
-            dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
-    filesystem.add_option('--id',
-            action='store_true', dest='useid', help='use only video ID in file name', default=False)
-    filesystem.add_option('-A', '--auto-number',
-            action='store_true', dest='autonumber',
-            help='number downloaded files starting from 00000', default=False)
-    filesystem.add_option('-o', '--output',
-            dest='outtmpl', metavar='TEMPLATE',
-            help=('output filename template. Use %(title)s to get the title, '
-                  '%(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, '
-                  '%(autonumber)s to get an automatically incremented number, '
-                  '%(ext)s for the filename extension, '
-                  '%(format)s for the format description (like "22 - 1280x720" or "HD"), '
-                  '%(format_id)s for the unique id of the format (like Youtube\'s itags: "137"), '
-                  '%(upload_date)s for the upload date (YYYYMMDD), '
-                  '%(extractor)s for the provider (youtube, metacafe, etc), '
-                  '%(id)s for the video id, %(playlist)s for the playlist the video is in, '
-                  '%(playlist_index)s for the position in the playlist and %% for a literal percent. '
-                  '%(height)s and %(width)s for the width and height of the video format. '
-                  '%(resolution)s for a textual description of the resolution of the video format. '
-                  'Use - to output to stdout. Can also be used to download to a different directory, '
-                  'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .'))
-    filesystem.add_option('--autonumber-size',
-            dest='autonumber_size', metavar='NUMBER',
-            help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given')
-    filesystem.add_option('--restrict-filenames',
-            action='store_true', dest='restrictfilenames',
-            help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
-    filesystem.add_option('-t', '--title',
-            action='store_true', dest='usetitle', help='[deprecated] use title in file name (default)', default=False)
-    filesystem.add_option('-l', '--literal',
-            action='store_true', dest='usetitle', help='[deprecated] alias of --title', default=False)
-    filesystem.add_option('-w', '--no-overwrites',
-            action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
-    filesystem.add_option('-c', '--continue',
-            action='store_true', dest='continue_dl', help='force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.', default=True)
-    filesystem.add_option('--no-continue',
-            action='store_false', dest='continue_dl',
-            help='do not resume partially downloaded files (restart from beginning)')
-    filesystem.add_option('--no-part',
-            action='store_true', dest='nopart', help='do not use .part files', default=False)
-    filesystem.add_option('--no-mtime',
-            action='store_false', dest='updatetime',
-            help='do not use the Last-modified header to set the file modification time', default=True)
-    filesystem.add_option('--write-description',
-            action='store_true', dest='writedescription',
-            help='write video description to a .description file', default=False)
-    filesystem.add_option('--write-info-json',
-            action='store_true', dest='writeinfojson',
-            help='write video metadata to a .info.json file', default=False)
-    filesystem.add_option('--write-annotations',
-            action='store_true', dest='writeannotations',
-            help='write video annotations to a .annotation file', default=False)
-    filesystem.add_option('--write-thumbnail',
-            action='store_true', dest='writethumbnail',
-            help='write thumbnail image to disk', default=False)
-    filesystem.add_option('--load-info',
-            dest='load_info_filename', metavar='FILE',
-            help='json file containing the video information (created with the "--write-json" option)')
-    filesystem.add_option('--cookies',
-            dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
-    filesystem.add_option(
-        '--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR',
-        help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.')
-    filesystem.add_option(
-        '--no-cache-dir', action='store_const', const=None, dest='cachedir',
-        help='Disable filesystem caching')
-    filesystem.add_option(
-        '--rm-cache-dir', action='store_true', dest='rm_cachedir',
-        help='Delete all filesystem cache files')
-
-
-    postproc.add_option('-x', '--extract-audio', action='store_true', dest='extractaudio', default=False,
-            help='convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
-    postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
-            help='"best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; best by default')
-    postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='5',
-            help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5)')
-    postproc.add_option('--recode-video', metavar='FORMAT', dest='recodevideo', default=None,
-            help='Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)')
-    postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
-            help='keeps the video file on disk after the post-processing; the video is erased by default')
-    postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False,
-            help='do not overwrite post-processed files; the post-processed files are overwritten by default')
-    postproc.add_option('--embed-subs', action='store_true', dest='embedsubtitles', default=False,
-            help='embed subtitles in the video (only for mp4 videos)')
-    postproc.add_option('--embed-thumbnail', action='store_true', dest='embedthumbnail', default=False,
-            help='embed thumbnail in the audio as cover art')
-    postproc.add_option('--add-metadata', action='store_true', dest='addmetadata', default=False,
-            help='write metadata to the video file')
-    postproc.add_option('--xattrs', action='store_true', dest='xattrs', default=False,
-            help='write metadata to the video file\'s xattrs (using dublin core and xdg standards)')
-    postproc.add_option('--prefer-avconv', action='store_false', dest='prefer_ffmpeg',
-        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)
-    parser.add_option_group(downloader)
-    parser.add_option_group(filesystem)
-    parser.add_option_group(verbosity)
-    parser.add_option_group(workarounds)
-    parser.add_option_group(video_format)
-    parser.add_option_group(subtitles)
-    parser.add_option_group(authentication)
-    parser.add_option_group(postproc)
-
-    if overrideArguments is not None:
-        opts, args = parser.parse_args(overrideArguments)
-        if opts.verbose:
-            write_string(u'[debug] Override config: ' + repr(overrideArguments) + '\n')
-    else:
-        commandLineConf = sys.argv[1:]
-        if '--ignore-config' in commandLineConf:
-            systemConf = []
-            userConf = []
-        else:
-            systemConf = _readOptions('/etc/youtube-dl.conf')
-            if '--ignore-config' in systemConf:
-                userConf = []
-            else:
-                userConf = _readUserConf()
-        argv = systemConf + userConf + commandLineConf
-
-        opts, args = parser.parse_args(argv)
-        if opts.verbose:
-            write_string(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
-            write_string(u'[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n')
-            write_string(u'[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n')
-
-    return parser, opts, args
-
-
 def _real_main(argv=None):
     # Compatibility fixes for Windows
     if sys.platform == 'win32':
@@ -872,20 +404,7 @@ def _real_main(argv=None):
 
         # 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/f4m.py

@@ -16,6 +16,7 @@ from ..utils import (
     format_bytes,
     encodeFilename,
     sanitize_open,
+    xpath_text,
 )
 
 
@@ -251,6 +252,8 @@ class F4mFD(FileDownloader):
             # We only download the first fragment
             fragments_list = fragments_list[:1]
         total_frags = len(fragments_list)
+        # For some akamai manifests we'll need to add a query to the fragment url
+        akamai_pv = xpath_text(doc, _add_ns('pv-2.0'))
 
         tmpfilename = self.temp_name(filename)
         (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
@@ -290,6 +293,8 @@ class F4mFD(FileDownloader):
         for (seg_i, frag_i) in fragments_list:
             name = 'Seg%d-Frag%d' % (seg_i, frag_i)
             url = base_url + name
+            if akamai_pv:
+                url += '?' + akamai_pv.strip(';')
             frag_filename = '%s-%s' % (tmpfilename, name)
             success = http_dl.download(frag_filename, {'url': url})
             if not success:

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/extractor/__init__.py

@@ -4,6 +4,7 @@ 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
@@ -23,6 +24,8 @@ from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
+from .beeg import BeegIE
+from .behindkink import BehindKinkIE
 from .bilibili import BiliBiliIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
@@ -44,6 +47,7 @@ from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
+from .cloudy import CloudyIE
 from .clubic import ClubicIE
 from .cmt import CMTIE
 from .cnet import CNETIE
@@ -65,9 +69,12 @@ from .dailymotion import (
     DailymotionUserIE,
 )
 from .daum import DaumIE
+from .dbtv import DBTVIE
+from .deezer import DeezerPlaylistIE
 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
@@ -77,14 +84,16 @@ from .dropbox import DropboxIE
 from .ebaumsworld import EbaumsWorldIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
+from .einthusan import EinthusanIE
 from .eitb import EitbIE
 from .ellentv import (
     EllenTVIE,
     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
@@ -134,6 +143,8 @@ 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
@@ -188,14 +199,17 @@ from .malemotion import MalemotionIE
 from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
+from .mgoon import MgoonIE
 from .ministrygrid import MinistryGridIE
 from .mit import TechTVMITIE, MITIE, OCWMITIE
 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 .moniker import MonikerIE
 from .mooshare import MooshareIE
 from .morningstar import MorningstarIE
 from .motherless import MotherlessIE
@@ -208,6 +222,7 @@ from .mtv import (
     MTVServicesEmbeddedIE,
     MTVIggyIE,
 )
+from .muenchentv import MuenchenTVIE
 from .musicplayon import MusicPlayOnIE
 from .musicvault import MusicVaultIE
 from .muzu import MuzuTVIE
@@ -225,15 +240,20 @@ from .ndtv import NDTVIE
 from .newgrounds import NewgroundsIE
 from .newstube import NewstubeIE
 from .nfb import NFBIE
+from .nfl import NFLIE
 from .nhl import NHLIE, NHLVideocenterIE
 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
-from .npo import NPOIE
+from .npo import (
+    NPOIE,
+    TegenlichtVproIE,
+)
 from .nrk import (
     NRKIE,
     NRKTVIE,
@@ -257,6 +277,8 @@ from .podomatic import PodomaticIE
 from .pornhd import PornHdIE
 from .pornhub import PornHubIE
 from .pornotube import PornotubeIE
+from .pornoxo import PornoXOIE
+from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
 from .radiofrance import RadioFranceIE
@@ -288,6 +310,7 @@ 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
@@ -313,7 +336,7 @@ from .southpark import (
 )
 from .space import SpaceIE
 from .spankwire import SpankwireIE
-from .spiegel import SpiegelIE
+from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
 from .sportdeutschland import SportDeutschlandIE
@@ -321,6 +344,7 @@ 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
@@ -333,6 +357,7 @@ from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
+from .telemb import TeleMBIE
 from .tenplay import TenPlayIE
 from .testurl import TestURLIE
 from .tf1 import TF1IE
@@ -340,6 +365,8 @@ from .theplatform import ThePlatformIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
+from .tnaflix import TNAFlixIE
+from .thvideo import THVideoIE
 from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
@@ -348,6 +375,7 @@ from .trutube import TruTubeIE
 from .tube8 import Tube8IE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
+from .turbo import TurboIE
 from .tutv import TutvIE
 from .tvigle import TvigleIE
 from .tvp import TvpIE
@@ -365,12 +393,14 @@ 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
 from .videodetective import VideoDetectiveIE
 from .videolecturesnet import VideoLecturesNetIE
 from .videofyme import VideofyMeIE
+from .videomega import VideoMegaIE
 from .videopremium import VideoPremiumIE
 from .videott import VideoTtIE
 from .videoweed import VideoWeedIE
@@ -392,6 +422,7 @@ 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
@@ -422,6 +453,7 @@ from .yahoo import (
 from .youjizz import YouJizzIE
 from .youku import YoukuIE
 from .youporn import YouPornIE
+from .yourupload import YourUploadIE
 from .youtube import (
     YoutubeIE,
     YoutubeChannelIE,

youtube_dl/extractor/adultswim.py

@@ -75,7 +75,9 @@ class AdultSwimIE(InfoExtractor):
         video_path = mobj.group('path')
 
         webpage = self._download_webpage(url, video_path)
-        episode_id = self._html_search_regex(r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>', webpage, 'episode_id')
+        episode_id = self._html_search_regex(
+            r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>',
+            webpage, 'episode_id')
         title = self._og_search_title(webpage)
 
         index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id
@@ -97,7 +99,9 @@ class AdultSwimIE(InfoExtractor):
             duration = segment_el.attrib.get('duration')
 
             segment_url = 'http://asfix.adultswim.com/asfix-svc/episodeservices/getCvpPlaylist?networkName=AS&id=%s' % segment_id
-            idoc = self._download_xml(segment_url, segment_title, 'Downloading segment information', 'Unable to download segment information')
+            idoc = self._download_xml(
+                segment_url, segment_title,
+                'Downloading segment information', 'Unable to download segment information')
 
             formats = []
             file_els = idoc.findall('.//files/file')

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/ard.py

@@ -13,6 +13,7 @@ from ..utils import (
     int_or_none,
     parse_duration,
     unified_strdate,
+    xpath_text,
 )
 
 
@@ -50,9 +51,6 @@ class ARDMediathekIE(InfoExtractor):
         else:
             video_id = m.group('video_id')
 
-        urlp = compat_urllib_parse_urlparse(url)
-        url = urlp._replace(path=compat_urllib_parse.quote(urlp.path.encode('utf-8'))).geturl()
-
         webpage = self._download_webpage(url, video_id)
 
         if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage:
@@ -157,8 +155,9 @@ class ARDIE(InfoExtractor):
         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
+        upload_date = unified_strdate(xpath_text(
+            video_node, './broadcastDate'))
+        thumbnail = xpath_text(video_node, './/teaserImage//variant/url')
 
         formats = []
         for a in video_node.findall('.//asset'):

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/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/behindkink.py

@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import url_basename
+
+
+class BehindKinkIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
+    _TEST = {
+        'url': 'http://www.behindkink.com/2014/08/14/ab1576-performers-voice-finally-heard-the-bill-is-killed/',
+        'md5': '41ad01222b8442089a55528fec43ec01',
+        'info_dict': {
+            'id': '36370',
+            'ext': 'mp4',
+            'title': 'AB1576 - PERFORMERS VOICE FINALLY HEARD - THE BILL IS KILLED!',
+            'description': 'The adult industry voice was finally heard as Assembly Bill 1576 remained\xa0 in suspense today at the Senate Appropriations Hearing. AB1576 was, among other industry damaging issues, a condom mandate...',
+            'upload_date': '20140814',
+            'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/08/36370_AB1576_Win.jpg',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+        year = mobj.group('year')
+        month = mobj.group('month')
+        day = mobj.group('day')
+        upload_date = year + month + day
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_url = self._search_regex(
+            r"'file':\s*'([^']+)'",
+            webpage, 'URL base')
+
+        video_id = url_basename(video_url)
+        video_id = video_id.split('_')[0]
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': self._og_search_title(webpage),
+            'display_id': display_id,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(webpage),
+            'upload_date': upload_date,
+            'age_limit': 18,
+        }

youtube_dl/extractor/br.py

@@ -28,17 +28,6 @@ class BRIE(InfoExtractor):
                 'duration': 34,
             }
         },
-        {
-            'url': 'http://www.br.de/mediathek/video/sendungen/unter-unserem-himmel/unter-unserem-himmel-alpen-ueber-den-pass-100.html',
-            'md5': 'ab451b09d861dbed7d7cc9ab0be19ebe',
-            'info_dict': {
-                'id': '2c060e69-3a27-4e13-b0f0-668fac17d812',
-                'ext': 'mp4',
-                'title': 'Über den Pass',
-                'description': 'Die Eroberung der Alpen: Über den Pass',
-                'duration': 2588,
-            }
-        },
         {
             'url': 'http://www.br.de/nachrichten/schaeuble-haushaltsentwurf-bundestag-100.html',
             'md5': '3db0df1a9a9cd9fa0c70e6ea8aa8e820',

youtube_dl/extractor/chilloutzone.py

@@ -42,7 +42,7 @@ class ChilloutzoneIE(InfoExtractor):
             'id': '85523671',
             'ext': 'mp4',
             'title': 'The Sunday Times - Icons',
-            'description': 'md5:a5f7ff82e2f7a9ed77473fe666954e84',
+            'description': 're:(?s)^Watch the making of - makingoficons.com.{300,}',
             'uploader': 'Us',
             'uploader_id': 'usfilms',
             'upload_date': '20140131'

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/cloudy.py

@@ -0,0 +1,108 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_parse_qs,
+    compat_urllib_parse,
+    remove_end,
+    HEADRequest,
+    compat_HTTPError,
+)
+
+
+class CloudyIE(InfoExtractor):
+    _IE_DESC = 'cloudy.ec and videoraj.ch'
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.ch)/
+        (?:v/|embed\.php\?id=)
+        (?P<id>[A-Za-z0-9]+)
+        '''
+    _EMBED_URL = 'http://www.%s/embed.php?id=%s'
+    _API_URL = 'http://www.%s/api/player.api.php?%s'
+    _MAX_TRIES = 2
+    _TESTS = [
+        {
+            'url': 'https://www.cloudy.ec/v/af511e2527aac',
+            'md5': '5cb253ace826a42f35b4740539bedf07',
+            'info_dict': {
+                'id': 'af511e2527aac',
+                'ext': 'flv',
+                'title': 'Funny Cats and Animals Compilation june 2013',
+            }
+        },
+        {
+            'url': 'http://www.videoraj.ch/v/47f399fd8bb60',
+            'md5': '7d0f8799d91efd4eda26587421c3c3b0',
+            'info_dict': {
+                'id': '47f399fd8bb60',
+                'ext': 'flv',
+                'title': 'Burning a New iPhone 5 with Gasoline - Will it Survive?',
+            }
+        }
+    ]
+
+    def _extract_video(self, video_host, video_id, file_key, error_url=None, try_num=0):
+
+        if try_num > self._MAX_TRIES - 1:
+            raise ExtractorError('Unable to extract video URL', expected=True)
+
+        form = {
+            'file': video_id,
+            'key': file_key,
+        }
+
+        if error_url:
+            form.update({
+                'numOfErrors': try_num,
+                'errorCode': '404',
+                'errorUrl': error_url,
+            })
+
+        data_url = self._API_URL % (video_host, compat_urllib_parse.urlencode(form))
+        player_data = self._download_webpage(
+            data_url, video_id, 'Downloading player data')
+        data = compat_parse_qs(player_data)
+
+        try_num += 1
+
+        if 'error' in data:
+            raise ExtractorError(
+                '%s error: %s' % (self.IE_NAME, ' '.join(data['error_msg'])),
+                expected=True)
+
+        title = data.get('title', [None])[0]
+        if title:
+            title = remove_end(title, '&asdasdas').strip()
+
+        video_url = data.get('url', [None])[0]
+
+        if video_url:
+            try:
+                self._request_webpage(HEADRequest(video_url), video_id, 'Checking video URL')
+            except ExtractorError as e:
+                if isinstance(e.cause, compat_HTTPError) and e.cause.code in [404, 410]:
+                    self.report_warning('Invalid video URL, requesting another', video_id)
+                    return self._extract_video(video_host, video_id, file_key, video_url, try_num)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+        }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_host = mobj.group('host')
+        video_id = mobj.group('id')
+
+        url = self._EMBED_URL % (video_host, video_id)
+        webpage = self._download_webpage(url, video_id)
+
+        file_key = self._search_regex(
+            r'filekey\s*=\s*"([^"]+)"', webpage, 'file_key')
+
+        return self._extract_video(video_host, video_id, file_key)

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

@@ -130,6 +130,8 @@ class InfoExtractor(object):
                     by YoutubeDL if it's missing)
     categories:     A list of categories that the video falls in, for example
                     ["Sports", "Berlin"]
+    is_live:        True, False, or None (=unknown). Whether this video is a
+                    live stream that goes on instead of a fixed-length video.
 
     Unless mentioned otherwise, the fields should be Unicode strings.
 
@@ -677,9 +679,12 @@ class InfoExtractor(object):
                 }
                 codecs = last_info.get('CODECS')
                 if codecs:
-                    video, audio = codecs.split(',')
-                    f['vcodec'] = video.partition('.')[0]
-                    f['acodec'] = audio.partition('.')[0]
+                    # 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')

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/daum.py

@@ -11,10 +11,10 @@ from ..utils import (
 
 
 class DaumIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:v/|.*?clipid=)(?P<id>[^?#&]+)'
     IE_NAME = 'daum.net'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
         'info_dict': {
             'id': '52554690',
@@ -24,11 +24,17 @@ class DaumIE(InfoExtractor):
             'upload_date': '20130831',
             'duration': 3868,
         },
-    }
+    }, {
+        'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
+        'only_matching': True,
+    }, {
+        'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = mobj.group('id')
         canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
         webpage = self._download_webpage(canonical_url, video_id)
         full_id = self._search_regex(
@@ -42,7 +48,6 @@ class DaumIE(InfoExtractor):
             'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
             video_id, 'Downloading video formats info')
 
-        self.to_screen(u'%s: Getting video urls' % video_id)
         formats = []
         for format_el in urls.findall('result/output_list/output_list'):
             profile = format_el.attrib['profile']
@@ -52,7 +57,7 @@ class DaumIE(InfoExtractor):
             })
             url_doc = self._download_xml(
                 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
-                video_id, note=False)
+                video_id, note='Downloading video data for %s format' % profile)
             format_url = url_doc.find('result/url').text
             formats.append({
                 'url': format_url,

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/deezer.py

@@ -0,0 +1,89 @@
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    orderedSet,
+)
+
+
+class DeezerPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?deezer\.com/playlist/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.deezer.com/playlist/176747451',
+        'info_dict': {
+            'id': '176747451',
+            'title': 'Best!',
+            'uploader': 'Anonymous',
+            'thumbnail': 're:^https?://cdn-images.deezer.com/images/cover/.*\.jpg$',
+        },
+        'playlist_count': 30,
+        'skip': 'Only available in .de',
+    }
+
+    def _real_extract(self, url):
+        if 'test' not in self._downloader.params:
+            self._downloader.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
+
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, playlist_id)
+        geoblocking_msg = self._html_search_regex(
+            r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
+            default=None)
+        if geoblocking_msg is not None:
+            raise ExtractorError(
+                'Deezer said: %s' % geoblocking_msg, expected=True)
+
+        data_json = self._search_regex(
+            r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n', webpage, 'data JSON')
+        data = json.loads(data_json)
+
+        playlist_title = data.get('DATA', {}).get('TITLE')
+        playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
+        playlist_thumbnail = self._search_regex(
+            r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
+            'playlist thumbnail')
+
+        preview_pattern = self._search_regex(
+            r"var SOUND_PREVIEW_GATEWAY\s*=\s*'([^']+)';", webpage,
+            'preview URL pattern', fatal=False)
+        entries = []
+        for s in data['SONGS']['data']:
+            puid = s['MD5_ORIGIN']
+            preview_video_url = preview_pattern.\
+                replace('{0}', puid[0]).\
+                replace('{1}', puid).\
+                replace('{2}', s['MEDIA_VERSION'])
+            formats = [{
+                'format_id': 'preview',
+                'url': preview_video_url,
+                'preference': -100,  # Only the first 30 seconds
+                'ext': 'mp3',
+            }]
+            self._sort_formats(formats)
+            artists = ', '.join(
+                orderedSet(a['ART_NAME'] for a in s['ARTISTS']))
+            entries.append({
+                'id': s['SNG_ID'],
+                'duration': int_or_none(s.get('DURATION')),
+                'title': '%s - %s' % (artists, s['SNG_TITLE']),
+                'uploader': s['ART_NAME'],
+                'uploader_id': s['ART_ID'],
+                'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
+                'formats': formats,
+            })
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': playlist_title,
+            'uploader': playlist_uploader,
+            'thumbnail': playlist_thumbnail,
+            'entries': entries,
+        }

youtube_dl/extractor/divxstage.py

@@ -7,7 +7,7 @@ class DivxStageIE(NovaMovIE):
     IE_NAME = 'divxstage'
     IE_DESC = 'DivxStage'
 
-    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'divxstage\.(?:eu|net|ch|co|at|ag)'}
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'divxstage\.(?:eu|net|ch|co|at|ag|to)'}
 
     _HOST = 'www.divxstage.eu'
 
@@ -24,4 +24,4 @@ class DivxStageIE(NovaMovIE):
             'title': 'youtubedl test video',
             'description': 'This is a test video for youtubedl.',
         }
-    }
+    }

youtube_dl/extractor/dropbox.py

@@ -5,24 +5,29 @@ import os.path
 import re
 
 from .common import InfoExtractor
-from ..utils import compat_urllib_parse_unquote
+from ..utils import compat_urllib_parse_unquote, url_basename
 
 
 class DropboxIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P<id>[a-zA-Z0-9]{15})/(?P<title>[^?#]*)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/sh?/(?P<id>[a-zA-Z0-9]{15})/.*'
+    _TESTS = [{
         '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',
             'title': 'youtube-dl test video \'ä"BaW_jenozKc'
         }
-    }
+    },
+    {
+        'url': 'https://www.dropbox.com/sh/662glsejgzoj9sr/AAByil3FGH9KFNZ13e08eSa1a/Pregame%20Ceremony%20Program%20PA%2020140518.m4v',
+        'only_matching': True,
+    },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        fn = compat_urllib_parse_unquote(mobj.group('title'))
+        fn = compat_urllib_parse_unquote(url_basename(url))
         title = os.path.splitext(fn)[0]
         video_url = (
             re.sub(r'[?&]dl=0', '', url) +

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': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
+            '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._search_regex(
+            r'<span>Categories:</span><div>(.+?)</div>', webpage, 'categories', fatal=False)
+        categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
+
+        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/drtv.py

@@ -8,7 +8,7 @@ from ..utils import parse_iso8601
 
 
 class DRTVIE(SubtitlesInfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?dr\.dk/tv/se/[^/]+/(?P<id>[\da-z-]+)'
+    _VALID_URL = r'http://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)+(?P<id>[\da-z-]+)(?:[/#?]|$)'
 
     _TEST = {
         'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8',

youtube_dl/extractor/einthusan.py

@@ -0,0 +1,61 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class EinthusanIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?einthusan\.com/movies/watch.php\?([^#]*?)id=(?P<id>[0-9]+)'
+    _TESTS = [
+        {
+            'url': 'http://www.einthusan.com/movies/watch.php?id=2447',
+            'md5': 'af244f4458cd667205e513d75da5b8b1',
+            'info_dict': {
+                'id': '2447',
+                'ext': 'mp4',
+                'title': 'Ek Villain',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'description': 'md5:9d29fc91a7abadd4591fb862fa560d93',
+            }
+        },
+        {
+            'url': 'http://www.einthusan.com/movies/watch.php?id=1671',
+            'md5': 'ef63c7a803e22315880ed182c10d1c5c',
+            'info_dict': {
+                'id': '1671',
+                'ext': 'mp4',
+                'title': 'Soodhu Kavvuum',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'description': 'md5:05d8a0c0281a4240d86d76e14f2f4d51',
+            }
+        },
+    ]
+
+    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_title = self._html_search_regex(
+            r'<h1><a class="movie-title".*?>(.*?)</a></h1>', webpage, 'title')
+
+        video_url = self._html_search_regex(
+            r'''(?s)jwplayer\("mediaplayer"\)\.setup\({.*?'file': '([^']+)'.*?}\);''',
+            webpage, 'video url')
+
+        description = self._html_search_meta('description', webpage)
+        thumbnail = self._html_search_regex(
+            r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''',
+            webpage, "thumbnail url", fatal=False)
+        if thumbnail is not None:
+            thumbnail = thumbnail.replace('..', 'http://www.einthusan.com')
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'description': description,
+        }

youtube_dl/extractor/empflix.py

@@ -1,58 +1,25 @@
 from __future__ import unicode_literals
 
-import re
-
-from .common import InfoExtractor
-from ..utils import fix_xml_ampersands
+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',
-            transform_source=fix_xml_ampersands)
-
-        formats = [
-            {
-                'url': item.find('videoLink').text,
-                'format_id': item.find('res').text,
-            } for item in cfg_xml.findall('./quality/item')
-        ]
-        thumbnail = cfg_xml.find('./startThumb').text
-
-        return {
-            'id': video_id,
-            'title': video_title,
-            'description': video_description,
-            'thumbnail': thumbnail,
-            '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/facebook.py

@@ -12,8 +12,8 @@ from ..utils import (
     compat_urllib_parse,
     compat_urllib_request,
     urlencode_postdata,
-
     ExtractorError,
+    limit_length,
 )
 
 
@@ -29,13 +29,21 @@ class FacebookIE(InfoExtractor):
     _NETRC_MACHINE = 'facebook'
     IE_NAME = 'facebook'
     _TESTS = [{
-        'url': 'https://www.facebook.com/photo.php?v=120708114770723',
-        'md5': '48975a41ccc4b7a581abd68651c1a5a8',
+        'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
+        'md5': '6a40d33c0eccbb1af76cf0485a052659',
         'info_dict': {
-            'id': '120708114770723',
+            'id': '637842556329505',
             'ext': 'mp4',
-            'duration': 279,
-            'title': 'PEOPLE ARE AWESOME 2013',
+            'duration': 38,
+            'title': 'Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam fin...',
+        }
+    }, {
+        'note': 'Video without discernible title',
+        'url': 'https://www.facebook.com/video.php?v=274175099429670',
+        'info_dict': {
+            'id': '274175099429670',
+            'ext': 'mp4',
+            'title': 'Facebook video #274175099429670',
         }
     }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',
@@ -79,7 +87,8 @@ 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))
@@ -124,7 +133,15 @@ class FacebookIE(InfoExtractor):
             raise ExtractorError('Cannot find video URL')
 
         video_title = self._html_search_regex(
-            r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title')
+            r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title',
+            fatal=False)
+        if not video_title:
+            video_title = self._html_search_regex(
+                r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
+                webpage, 'alternative title', default=None)
+            video_title = limit_length(video_title, 80)
+        if not video_title:
+            video_title = 'Facebook video #%s' % video_id
 
         return {
             'id': video_id,

youtube_dl/extractor/flickr.py

@@ -10,13 +10,13 @@ from ..utils import (
 
 
 class FlickrIE(InfoExtractor):
-    """Information Extractor for Flickr videos"""
-    _VALID_URL = r'(?:https?://)?(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
+    _VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
     _TEST = {
         'url': 'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/',
-        'file': '5645318632.mp4',
         'md5': '6fdc01adbc89d72fc9c4f15b4a4ba87b',
         'info_dict': {
+            'id': '5645318632',
+            'ext': 'mp4',
             "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", 
             "uploader_id": "forestwander-nature-pictures", 
             "title": "Dark Hollow Waterfalls"
@@ -49,12 +49,12 @@ class FlickrIE(InfoExtractor):
             raise ExtractorError('Unable to extract video url')
         video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
 
-        return [{
-            'id':          video_id,
-            'url':         video_url,
-            'ext':         'mp4',
-            'title':       self._og_search_title(webpage),
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': self._og_search_title(webpage),
             'description': self._og_search_description(webpage),
-            'thumbnail':   self._og_search_thumbnail(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
             'uploader_id': video_uploader_id,
-        }]
+        }

youtube_dl/extractor/franceinter.py

@@ -4,16 +4,21 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class FranceInterIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})'
+    _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
-        'file': '793962.mp3',
         'md5': '4764932e466e6f6c79c317d2e74f6884',
         "info_dict": {
-            "title": "L’Histoire dans les jeux vidéo",
+            'id': '793962',
+            'ext': 'mp3',
+            'title': 'L’Histoire dans les jeux vidéo',
+            'description': 'md5:7e93ddb4451e7530022792240a3049c7',
+            'timestamp': 1387369800,
+            'upload_date': '20131218',
         },
     }
 
@@ -22,17 +27,26 @@ class FranceInterIE(InfoExtractor):
         video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(
-            r'<span class="roll_overflow">(.*?)</span></h1>', webpage, 'title')
+
         path = self._search_regex(
-            r'&urlAOD=(.*?)&startTime', webpage, 'video url')
+            r'<a id="player".+?href="([^"]+)"', webpage, 'video url')
         video_url = 'http://www.franceinter.fr/' + path
 
+        title = self._html_search_regex(
+            r'<span class="title">(.+?)</span>', webpage, 'title')
+        description = self._html_search_regex(
+            r'<span class="description">(.*?)</span>',
+            webpage, 'description', fatal=False)
+        timestamp = int_or_none(self._search_regex(
+            r'data-date="(\d+)"', webpage, 'upload date', fatal=False))
+
         return {
             'id': video_id,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
             'formats': [{
                 'url': video_url,
                 'vcodec': 'none',
             }],
-            'title': title,
         }

youtube_dl/extractor/francetv.py

@@ -8,45 +8,68 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
+    ExtractorError,
+    clean_html,
+    parse_duration,
+    compat_urllib_parse_urlparse,
+    int_or_none,
 )
 
 
 class FranceTVBaseInfoExtractor(InfoExtractor):
-    def _extract_video(self, video_id):
-        info = self._download_xml(
-            'http://www.francetvinfo.fr/appftv/webservices/video/'
-            'getInfosOeuvre.php?id-diffusion='
-            + video_id, video_id, 'Downloading XML config')
+    def _extract_video(self, video_id, catalogue):
+        info = self._download_json(
+            'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=%s&catalogue=%s'
+            % (video_id, catalogue),
+            video_id, 'Downloading video JSON')
 
-        manifest_url = info.find('videos/video/url').text
-        manifest_url = manifest_url.replace('/z/', '/i/')
-        
-        if manifest_url.startswith('rtmp'):
-            formats = [{'url': manifest_url, 'ext': 'flv'}]
-        else:
-            formats = []
-            available_formats = self._search_regex(r'/[^,]*,(.*?),k\.mp4', manifest_url, 'available formats')
-            for index, format_descr in enumerate(available_formats.split(',')):
-                format_info = {
-                    'url': manifest_url.replace('manifest.f4m', 'index_%d_av.m3u8' % index),
-                    'ext': 'mp4',
-                }
-                m_resolution = re.search(r'(?P<width>\d+)x(?P<height>\d+)', format_descr)
-                if m_resolution is not None:
-                    format_info.update({
-                        'width': int(m_resolution.group('width')),
-                        'height': int(m_resolution.group('height')),
-                    })
-                formats.append(format_info)
+        if info.get('status') == 'NOK':
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, info['message']), expected=True)
 
-        thumbnail_path = info.find('image').text
+        formats = []
+        for video in info['videos']:
+            if video['statut'] != 'ONLINE':
+                continue
+            video_url = video['url']
+            if not video_url:
+                continue
+            format_id = video['format']
+            if video_url.endswith('.f4m'):
+                video_url_parsed = compat_urllib_parse_urlparse(video_url)
+                f4m_url = self._download_webpage(
+                    'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path,
+                    video_id, 'Downloading f4m manifest token', fatal=False)
+                if f4m_url:
+                    f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
+                    for f4m_format in f4m_formats:
+                        f4m_format['preference'] = 1
+                    formats.extend(f4m_formats)
+            elif video_url.endswith('.m3u8'):
+                formats.extend(self._extract_m3u8_formats(video_url, video_id))
+            elif video_url.startswith('rtmp'):
+                formats.append({
+                    'url': video_url,
+                    'format_id': 'rtmp-%s' % format_id,
+                    'ext': 'flv',
+                    'preference': 1,
+                })
+            else:
+                formats.append({
+                    'url': video_url,
+                    'format_id': format_id,
+                    'preference': 2,
+                })
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': info.find('titre').text,
+            'title': info['titre'],
+            'description': clean_html(info['synopsis']),
+            'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
+            'duration': parse_duration(info['duree']),
+            'timestamp': int_or_none(info['diffusion']['timestamp']),
             'formats': formats,
-            'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
-            'description': info.find('synopsis').text,
         }
 
 
@@ -61,7 +84,7 @@ class PluzzIE(FranceTVBaseInfoExtractor):
         webpage = self._download_webpage(url, title)
         video_id = self._search_regex(
             r'data-diffusion="(\d+)"', webpage, 'ID')
-        return self._extract_video(video_id)
+        return self._extract_video(video_id, 'Pluzz')
 
 
 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
@@ -70,13 +93,13 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
+        'md5': '9cecf35f99c4079c199e9817882a9a1c',
         'info_dict': {
             'id': '84981923',
-            'ext': 'mp4',
+            'ext': 'flv',
             'title': 'Soir 3',
-        },
-        'params': {
-            'skip_download': True,
+            'upload_date': '20130826',
+            'timestamp': 1377548400,
         },
     }, {
         'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
@@ -88,15 +111,17 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
         },
         'params': {
             'skip_download': 'HLS (reqires ffmpeg)'
-        }
+        },
+        'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
-        video_id = self._search_regex(r'id-video=((?:[^0-9]*?_)?[0-9]+)[@"]', webpage, 'video id')
-        return self._extract_video(video_id)
+        video_id, catalogue = self._search_regex(
+            r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
+        return self._extract_video(video_id, catalogue)
 
 
 class FranceTVIE(FranceTVBaseInfoExtractor):
@@ -112,91 +137,77 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
         # france2
         {
             'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
-            'file': '75540104.mp4',
+            'md5': 'c03fc87cb85429ffd55df32b9fc05523',
             'info_dict': {
-                'title': '13h15, le samedi...',
-                'description': 'md5:2e5b58ba7a2d3692b35c792be081a03d',
-            },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
+                'id': '109169362',
+                'ext': 'flv',
+                'title': '13h15, le dimanche...',
+                'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7',
+                'upload_date': '20140914',
+                'timestamp': 1410693600,
             },
         },
         # france3
         {
             'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
+            'md5': '679bb8f8921f8623bd658fa2f8364da0',
             'info_dict': {
                 'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Le scandale du prix des médicaments',
                 'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
+                'upload_date': '20131113',
+                'timestamp': 1384380000,
             },
         },
         # france4
         {
             'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+            'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c',
             'info_dict': {
                 'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Hero Corp Making of - Extrait 1',
                 'description': 'md5:c87d54871b1790679aec1197e73d650a',
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
+                'upload_date': '20131106',
+                'timestamp': 1383766500,
             },
         },
         # france5
         {
             'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
+            'md5': '78f0f4064f9074438e660785bbf2c5d9',
             'info_dict': {
-                'id': '92837968',
-                'ext': 'mp4',
+                'id': '108961659',
+                'ext': 'flv',
                 'title': 'C à dire ?!',
-                'description': 'md5:fb1db1cbad784dcce7c7a7bd177c8e2f',
-            },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
+                'description': 'md5:1a4aeab476eb657bf57c4ff122129f81',
+                'upload_date': '20140915',
+                'timestamp': 1410795000,
             },
         },
         # franceo
         {
             'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013',
+            'md5': '52f0bfe202848b15915a2f39aaa8981b',
             'info_dict': {
-                'id': '92327925',
-                'ext': 'mp4',
-                'title': 'Infô-Afrique',
+                'id': '108634970',
+                'ext': 'flv',
+                'title': 'Infô Afrique',
                 'description': 'md5:ebf346da789428841bee0fd2a935ea55',
+                'upload_date': '20140915',
+                'timestamp': 1410822000,
             },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            },
-            'skip': 'The id changes frequently',
         },
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj.group('key'):
-            webpage = self._download_webpage(url, mobj.group('key'))
-            id_res = [
-                (r'''(?x)<div\s+class="video-player">\s*
-                    <a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+
-                    class="francetv-video-player">'''),
-                (r'<a id="player_direct" href="http://info\.francetelevisions'
-                 '\.fr/\?id-video=([^"/&]+)'),
-                (r'<a class="video" id="ftv_player_(.+?)"'),
-            ]
-            video_id = self._html_search_regex(id_res, webpage, 'video ID')
-        else:
-            video_id = mobj.group('id')
-        return self._extract_video(video_id)
+        webpage = self._download_webpage(url, mobj.group('key') or mobj.group('id'))
+        video_id, catalogue = self._html_search_regex(
+            r'href="http://videos\.francetv\.fr/video/([^@]+@[^"]+)"',
+            webpage, 'video ID').split('@')
+        return self._extract_video(video_id, catalogue)
 
 
 class GenerationQuoiIE(InfoExtractor):
@@ -232,16 +243,15 @@ class CultureboxIE(FranceTVBaseInfoExtractor):
     _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 
     _TEST = {
-        'url': 'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813',
+        'url': 'http://culturebox.francetvinfo.fr/festivals/dans-les-jardins-de-william-christie/dans-les-jardins-de-william-christie-le-camus-162553',
+        'md5': '5ad6dec1ffb2a3fbcb20cc4b744be8d6',
         'info_dict': {
-            'id': 'EV_6785',
-            'ext': 'mp4',
-            'title': 'Einstein on the beach au Théâtre du Châtelet',
-            'description': 'md5:9ce2888b1efefc617b5e58b3f6200eeb',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
+            'id': 'EV_22853',
+            'ext': 'flv',
+            'title': 'Dans les jardins de William Christie - Le Camus',
+            'description': 'md5:4710c82315c40f0c865ca8b9a68b5299',
+            'upload_date': '20140829',
+            'timestamp': 1409317200,
         },
     }
 
@@ -249,5 +259,7 @@ class CultureboxIE(FranceTVBaseInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
         webpage = self._download_webpage(url, name)
-        video_id = self._search_regex(r'"http://videos\.francetv\.fr/video/(.*?)"', webpage, 'video id')
-        return self._extract_video(video_id)
+        video_id, catalogue = self._search_regex(
+            r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')
+
+        return self._extract_video(video_id, catalogue)

youtube_dl/extractor/generic.py

@@ -366,7 +366,22 @@ class GenericIE(InfoExtractor):
                 '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):
@@ -569,7 +584,9 @@ class GenericIE(InfoExtractor):
 
         # Helper method
         def _playlist_from_matches(matches, getter, ie=None):
-            urlrs = orderedSet(self.url_result(getter(m), ie) for m in matches)
+            urlrs = orderedSet(
+                self.url_result(self._proto_relative_url(getter(m)), ie)
+                for m in matches)
             return self.playlist_result(
                 urlrs, playlist_id=video_id, playlist_title=video_title)
 
@@ -613,12 +630,12 @@ class GenericIE(InfoExtractor):
                 embedSWF\(?:\s*
             )
             (["\'])
-                (?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
+                (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
                 (?:embed|v)/.+?)
             \1''', webpage)
         if matches:
             return _playlist_from_matches(
-                matches, lambda m: unescapeHTML(m[1]), ie='Youtube')
+                matches, lambda m: unescapeHTML(m[1]))
 
         # Look for embedded Dailymotion player
         matches = re.findall(
@@ -809,6 +826,12 @@ 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:
@@ -856,7 +879,7 @@ class GenericIE(InfoExtractor):
         if not found:
             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
-                r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'([^\']+)\'"',
+                r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)',
                 webpage)
             if found:
                 new_url = found.group(1)

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

@@ -71,6 +71,7 @@ class IGNIE(InfoExtractor):
 
     def _find_video_id(self, webpage):
         res_id = [
+            r'"video_id"\s*:\s*"(.*?)"',
             r'data-video-id="(.+?)"',
             r'<object id="vid_(.+?)"',
             r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
@@ -85,7 +86,7 @@ class IGNIE(InfoExtractor):
         webpage = self._download_webpage(url, name_or_id)
         if page_type != 'video':
             multiple_urls = re.findall(
-                '<param name="flashvars" value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
+                '<param name="flashvars"[^>]*value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
                 webpage)
             if multiple_urls:
                 return [self.url_result(u, ie='IGN') for u in multiple_urls]
@@ -111,13 +112,13 @@ class IGNIE(InfoExtractor):
 
 
 class OneUPIE(IGNIE):
-    _VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)'
+    _VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)\.html'
     IE_NAME = '1up.com'
 
     _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'
 
     _TESTS = [{
-        'url': 'http://gamevideos.1up.com/video/id/34976',
+        'url': 'http://gamevideos.1up.com/video/id/34976.html',
         'md5': '68a54ce4ebc772e4b71e3123d413163d',
         'info_dict': {
             'id': '34976',

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

@@ -9,7 +9,7 @@ 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'
 
     _TESTS = [{

youtube_dl/extractor/mgoon.py

@@ -0,0 +1,87 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    qualities,
+    unified_strdate,
+)
+
+
+class MgoonIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://(?:www\.)?
+    (?:(:?m\.)?mgoon\.com/(?:ch/(?:.+)/v|play/view)|
+        video\.mgoon\.com)/(?P<id>[0-9]+)'''
+    _API_URL = 'http://mpos.mgoon.com/player/video?id={0:}'
+    _TESTS = [
+        {
+            'url': 'http://m.mgoon.com/ch/hi6618/v/5582148',
+            'md5': 'dd46bb66ab35cf6d51cc812fd82da79d',
+            'info_dict': {
+                'id': '5582148',
+                'uploader_id': 'hi6618',
+                'duration': 240.419,
+                'upload_date': '20131220',
+                'ext': 'mp4',
+                'title': 'md5:543aa4c27a4931d371c3f433e8cebebc',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            }
+        },
+        {
+            'url': 'http://www.mgoon.com/play/view/5582148',
+            'only_matching': True,
+        },
+        {
+            'url': 'http://video.mgoon.com/5582148',
+            'only_matching': True,
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        data = self._download_json(self._API_URL.format(video_id), video_id)
+
+        if data.get('errorInfo', {}).get('code') != 'NONE':
+            raise ExtractorError('%s encountered an error: %s' % (
+                self.IE_NAME, data['errorInfo']['message']), expected=True)
+
+        v_info = data['videoInfo']
+        title = v_info.get('v_title')
+        thumbnail = v_info.get('v_thumbnail')
+        duration = v_info.get('v_duration')
+        upload_date = unified_strdate(v_info.get('v_reg_date'))
+        uploader_id = data.get('userInfo', {}).get('u_alias')
+        if duration:
+            duration /= 1000.0
+
+        age_limit = None
+        if data.get('accessInfo', {}).get('code') == 'VIDEO_STATUS_ADULT':
+            age_limit = 18
+
+        formats = []
+        get_quality = qualities(['360p', '480p', '720p', '1080p'])
+        for fmt in data['videoFiles']:
+            formats.append({
+                'format_id': fmt['label'],
+                'quality': get_quality(fmt['label']),
+                'url': fmt['url'],
+                'ext': fmt['format'],
+
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'upload_date': upload_date,
+            'uploader_id': uploader_id,
+            'age_limit': age_limit,
+        }

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/moniker.py

@@ -0,0 +1,70 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import os.path
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+
+
+class MonikerIE(InfoExtractor):
+    IE_DESC = 'allmyvideos.net and vidspot.net'
+    _VALID_URL = r'https?://(?:www\.)?(?:allmyvideos|vidspot)\.net/(?P<id>[a-zA-Z0-9_-]+)'
+
+    _TESTS = [{
+        'url': 'http://allmyvideos.net/jih3nce3x6wn',
+        'md5': '710883dee1bfc370ecf9fa6a89307c88',
+        'info_dict': {
+            'id': 'jih3nce3x6wn',
+            'ext': 'mp4',
+            'title': 'youtube-dl test video',
+        },
+    }, {
+        'url': 'http://vidspot.net/l2ngsmhs8ci5',
+        'md5': '710883dee1bfc370ecf9fa6a89307c88',
+        'info_dict': {
+            'id': 'l2ngsmhs8ci5',
+            'ext': 'mp4',
+            'title': 'youtube-dl test video',
+        },
+    }, {
+        'url': 'https://www.vidspot.net/l2ngsmhs8ci5',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        orig_webpage = self._download_webpage(url, video_id)
+        fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
+        data = dict(fields)
+
+        post = compat_urllib_parse.urlencode(data)
+        headers = {
+            b'Content-Type': b'application/x-www-form-urlencoded',
+        }
+        req = compat_urllib_request.Request(url, post, headers)
+        webpage = self._download_webpage(
+            req, video_id, note='Downloading video page ...')
+
+        title = os.path.splitext(data['fname'])[0]
+
+        #Could be several links with different quality
+        links = re.findall(r'"file" : "?(.+?)",', webpage)
+        # Assume the links are ordered in quality
+        formats = [{
+            'url': l,
+            'quality': i,
+        } for i, l in enumerate(links)]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        }

youtube_dl/extractor/muenchentv.py

@@ -0,0 +1,77 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import datetime
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    js_to_json,
+)
+
+
+class MuenchenTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?muenchen\.tv/livestream'
+    IE_DESC = 'münchen.tv'
+    _TEST = {
+        'url': 'http://www.muenchen.tv/livestream/',
+        'info_dict': {
+            'id': '5334',
+            'display_id': 'live',
+            'ext': 'mp4',
+            'title': 're:^münchen.tv-Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = 'live'
+        webpage = self._download_webpage(url, display_id)
+
+        now = datetime.datetime.now()
+        now_str = now.strftime("%Y-%m-%d %H:%M")
+        title = self._og_search_title(webpage) + ' ' + now_str
+
+        data_js = self._search_regex(
+            r'(?s)\nplaylist:\s*(\[.*?}\]),related:',
+            webpage, 'playlist configuration')
+        data_json = js_to_json(data_js)
+        data = json.loads(data_json)[0]
+
+        video_id = data['mediaid']
+        thumbnail = data.get('image')
+
+        formats = []
+        for format_num, s in enumerate(data['sources']):
+            ext = determine_ext(s['file'], None)
+            label_str = s.get('label')
+            if label_str is None:
+                label_str = '_%d' % format_num
+
+            if ext is None:
+                format_id = label_str
+            else:
+                format_id = '%s-%s' % (ext, label_str)
+
+            formats.append({
+                'url': s['file'],
+                'tbr': int_or_none(s.get('label')),
+                'ext': 'mp4',
+                'format_id': format_id,
+                'preference': -100 if '.smil' in s['file'] else 0,
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'is_live': True,
+        }
+

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/nbc.py

@@ -16,9 +16,9 @@ class NBCIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188',
-        'md5': '54d0fbc33e0b853a65d7b4de5c06d64e',
+        # md5 checksum is not stable
         'info_dict': {
-            'id': 'u1RInQZRN7QJ',
+            'id': 'bTmnLCvIbaaH',
             'ext': 'flv',
             'title': 'I Am a Firefighter',
             'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.',

youtube_dl/extractor/nfl.py

@@ -0,0 +1,103 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    remove_end,
+)
+
+
+class NFLIE(InfoExtractor):
+    IE_NAME = 'nfl.com'
+    _VALID_URL = r'(?x)https?://(?:www\.)?nfl\.com/(?:videos/(?:.+)/|.*?\#video=)(?P<id>\d..[0-9]+)'
+    _PLAYER_CONFIG_URL = 'http://www.nfl.com/static/content/static/config/video/config.json'
+    _TEST = {
+        'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights',
+        # 'md5': '5eb8c40a727dda106d510e5d6ffa79e5',  # md5 checksum fluctuates
+        'info_dict': {
+            'id': '0ap3000000398478',
+            'ext': 'mp4',
+            'title': 'Week 3: Washington Redskins vs. Philadelphia Eagles highlights',
+            'description': 'md5:56323bfb0ac4ee5ab24bd05fdf3bf478',
+            'upload_date': '20140921',
+            'timestamp': 1411337580,
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        config = self._download_json(self._PLAYER_CONFIG_URL, video_id,
+                                     note='Downloading player config')
+        url_template = 'http://nfl.com{contentURLTemplate:s}'.format(**config)
+        video_data = self._download_json(url_template.format(id=video_id), video_id)
+
+        cdns = config.get('cdns')
+        if not cdns:
+            raise ExtractorError('Failed to get CDN data', expected=True)
+
+        formats = []
+        streams = video_data.get('cdnData', {}).get('bitrateInfo', [])
+        for name, cdn in cdns.items():
+            # LimeLight streams don't seem to work
+            if cdn.get('name') == 'LIMELIGHT':
+                continue
+
+            protocol = cdn.get('protocol')
+            host = remove_end(cdn.get('host', ''), '/')
+            if not (protocol and host):
+                continue
+
+            path_prefix = cdn.get('pathprefix', '')
+            if path_prefix and not path_prefix.endswith('/'):
+                path_prefix = '%s/' % path_prefix
+
+            get_url = lambda p: '{protocol:s}://{host:s}/{prefix:s}{path:}'.format(
+                protocol=protocol,
+                host=host,
+                prefix=path_prefix,
+                path=p,
+            )
+
+            if protocol == 'rtmp':
+                preference = -2
+            elif 'prog' in name.lower():
+                preference = -1
+            else:
+                preference = 0
+
+            for stream in streams:
+                path = stream.get('path')
+                if not path:
+                    continue
+
+                formats.append({
+                    'url': get_url(path),
+                    'vbr': int_or_none(stream.get('rate', 0), 1000),
+                    'preference': preference,
+                    'format_note': name,
+                })
+
+        self._sort_formats(formats)
+
+        thumbnail = None
+        for q in ('xl', 'l', 'm', 's', 'xs'):
+            thumbnail = video_data.get('imagePaths', {}).get(q)
+            if thumbnail:
+                break
+
+        return {
+            'id': video_id,
+            'title': video_data.get('storyHeadline'),
+            'formats': formats,
+            'description': video_data.get('caption'),
+            'duration': video_data.get('duration'),
+            'thumbnail': thumbnail,
+            'timestamp': int_or_none(video_data.get('posted'), 1000),
+        }

youtube_dl/extractor/nhl.py

@@ -46,9 +46,9 @@ class NHLBaseInfoExtractor(InfoExtractor):
 
 class NHLIE(NHLBaseInfoExtractor):
     IE_NAME = 'nhl.com'
-    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console\?.*?(?:[?&])id=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P<id>[0-9]+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
         'info_dict': {
             'id': '453614',
@@ -58,7 +58,10 @@ class NHLIE(NHLBaseInfoExtractor):
             'duration': 18,
             'upload_date': '20131006',
         },
-    }
+    }, {
+        'url': 'http://video.flames.nhl.com/videocenter/console?id=630616',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/noco.py

@@ -2,10 +2,15 @@
 from __future__ import unicode_literals
 
 import re
+import time
+import hashlib
 
 from .common import InfoExtractor
 from ..utils import (
+    compat_urllib_request,
+    compat_urllib_parse,
     ExtractorError,
+    clean_html,
     unified_strdate,
     compat_str,
 )
@@ -13,6 +18,9 @@ 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'
+    _API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s'
+    _NETRC_MACHINE = 'noco'
 
     _TEST = {
         'url': 'http://noco.tv/emission/11538/nolife/ami-ami-idol-hello-france/',
@@ -30,31 +38,72 @@ 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 _call_api(self, path, video_id, note):
+        ts = compat_str(int(time.time() * 1000))
+        tk = hashlib.md5((hashlib.md5(ts.encode('ascii')).hexdigest() + '#8S?uCraTedap6a').encode('ascii')).hexdigest()
+        url = self._API_URL_TEMPLATE % (path, ts, tk)
+
+        resp = self._download_json(url, video_id, note)
+
+        if isinstance(resp, dict) and resp.get('error'):
+            self._raise_error(resp['error'], resp['description'])
+
+        return resp
+
+    def _raise_error(self, error, description):
+        raise ExtractorError(
+            '%s returned error: %s - %s' % (self.IE_NAME, error, description),
+            expected=True)
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
-        medias = self._download_json(
-            'https://api.noco.tv/1.0/video/medias/%s' % video_id, video_id, 'Downloading video JSON')
+        medias = self._call_api(
+            'shows/%s/medias' % video_id,
+            video_id, 'Downloading video JSON')
+
+        qualities = self._call_api(
+            'qualities',
+            video_id, 'Downloading qualities JSON')
 
         formats = []
 
-        for fmt in medias['fr']['video_list']['default']['quality_list']:
-            format_id = fmt['quality_key']
+        for format_id, fmt in medias['fr']['video_list']['none']['quality_list'].items():
 
-            file = self._download_json(
-                'https://api.noco.tv/1.0/video/file/%s/fr/%s' % (format_id.lower(), video_id),
+            video = self._call_api(
+                'shows/%s/video/%s/fr' % (video_id, format_id.lower()),
                 video_id, 'Downloading %s video JSON' % format_id)
 
-            file_url = file['file']
+            file_url = video['file']
             if not file_url:
                 continue
 
-            if file_url == 'forbidden':
-                raise ExtractorError(
-                    '%s returned error: %s - %s' % (
-                        self.IE_NAME, file['popmessage']['title'], file['popmessage']['message']),
-                    expected=True)
+            if file_url in ['forbidden', 'not found']:
+                popmessage = video['popmessage']
+                self._raise_error(popmessage['title'], popmessage['message'])
 
             formats.append({
                 'url': file_url,
@@ -64,20 +113,31 @@ class NocoIE(InfoExtractor):
                 'abr': fmt['audiobitrate'],
                 'vbr': fmt['videobitrate'],
                 'filesize': fmt['filesize'],
-                'format_note': fmt['quality_name'],
-                'preference': fmt['priority'],
+                'format_note': qualities[format_id]['quality_name'],
+                'preference': qualities[format_id]['priority'],
             })
 
         self._sort_formats(formats)
 
-        show = self._download_json(
-            'https://api.noco.tv/1.0/shows/show/%s' % video_id, video_id, 'Downloading show JSON')[0]
+        show = self._call_api(
+            'shows/by_id/%s' % video_id,
+            video_id, 'Downloading show JSON')[0]
 
-        upload_date = unified_strdate(show['indexed'])
+        upload_date = unified_strdate(show['online_date_start_utc'])
         uploader = show['partner_name']
         uploader_id = show['partner_key']
         duration = show['duration_ms'] / 1000.0
-        thumbnail = show['screenshot']
+
+        thumbnails = []
+        for thumbnail_key, thumbnail_url in show.items():
+            m = re.search(r'^screenshot_(?P<width>\d+)x(?P<height>\d+)$', thumbnail_key)
+            if not m:
+                continue
+            thumbnails.append({
+                'url': thumbnail_url,
+                'width': int(m.group('width')),
+                'height': int(m.group('height')),
+            })
 
         episode = show.get('show_TT') or show.get('show_OT')
         family = show.get('family_TT') or show.get('family_OT')
@@ -97,7 +157,7 @@ class NocoIE(InfoExtractor):
             'id': video_id,
             'title': title,
             'description': description,
-            'thumbnail': thumbnail,
+            'thumbnails': thumbnails,
             'upload_date': upload_date,
             'uploader': uploader,
             'uploader_id': uploader_id,

youtube_dl/extractor/nosvideo.py

@@ -0,0 +1,76 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_request,
+    urlencode_postdata,
+    xpath_text,
+    xpath_with_ns,
+)
+
+_x = lambda p: xpath_with_ns(p, {'xspf': 'http://xspf.org/ns/0/'})
+
+
+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'))
+        if track is None:
+            raise ExtractorError(
+                'XML playlist is missing the \'track\' element',
+                expected=True)
+        title = xpath_text(track, _x('./xspf:title'), 'title')
+        url = xpath_text(track, _x('./xspf:file'), 'URL', fatal=True)
+        thumbnail = xpath_text(track, _x('./xspf:image'), 'thumbnail')
+        if title is not None:
+            title = title.strip()
+
+        formats = [{
+            'format_id': 'sd',
+            'url': url,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/npo.py

@@ -5,6 +5,9 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     unified_strdate,
+    parse_duration,
+    qualities,
+    url_basename,
 )
 
 
@@ -12,22 +15,50 @@ class NPOIE(InfoExtractor):
     IE_NAME = 'npo.nl'
     _VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?P<id>[^/?]+)'
 
-    _TEST = {
-        'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
-        'md5': '4b3f9c429157ec4775f2c9cb7b911016',
-        'info_dict': {
-            'id': 'VPWON_1220719',
-            'ext': 'mp4',
-            'title': 'Nieuwsuur',
-            'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
-            'upload_date': '20140622',
+    _TESTS = [
+        {
+            'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
+            'md5': '4b3f9c429157ec4775f2c9cb7b911016',
+            'info_dict': {
+                'id': 'VPWON_1220719',
+                'ext': 'm4v',
+                'title': 'Nieuwsuur',
+                'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
+                'upload_date': '20140622',
+            },
         },
-    }
+        {
+            'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
+            'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
+            'info_dict': {
+                'id': 'VARA_101191800',
+                'ext': 'm4v',
+                'title': 'De Mega Mike & Mega Thomas show',
+                'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
+                'upload_date': '20090227',
+                'duration': 2400,
+            },
+        },
+        {
+            'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
+            'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
+            'info_dict': {
+                'id': 'VPWON_1169289',
+                'ext': 'm4v',
+                'title': 'Tegenlicht',
+                'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
+                'upload_date': '20130225',
+                'duration': 3000,
+            },
+        }
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        return self._get_info(video_id)
 
+    def _get_info(self, video_id):
         metadata = self._download_json(
             'http://e.omroep.nl/metadata/aflevering/%s' % video_id,
             video_id,
@@ -39,24 +70,69 @@ 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', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
+        for format_id in metadata['pubopties']:
+            format_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 JSON' % format_id)
+            if format_info.get('error_code', 0) or format_info.get('errorcode', 0):
+                continue
+            streams = format_info.get('streams')
+            if streams:
+                video_info = self._download_json(
+                    streams[0] + '&type=json',
+                    video_id, 'Downloading %s stream JSON' % format_id)
+            else:
+                video_info = format_info
+            video_url = video_info.get('url')
+            if not video_url:
+                continue
+            if format_id == 'adaptive':
+                formats.extend(self._extract_m3u8_formats(video_url, video_id))
+            else:
+                formats.append({
+                    'url': video_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']),
+            'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
+            'upload_date': unified_strdate(metadata.get('gidsdatum')),
+            'duration': parse_duration(metadata.get('tijdsduur')),
+            'formats': formats,
         }
+
+
+class TegenlichtVproIE(NPOIE):
+    IE_NAME = 'tegenlicht.vpro.nl'
+    _VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?'
+
+    _TESTS = [
+        {
+            'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
+            'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
+            'info_dict': {
+                'id': 'VPWON_1169289',
+                'ext': 'm4v',
+                'title': 'Tegenlicht',
+                'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
+                'upload_date': '20130225',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        name = url_basename(url)
+        webpage = self._download_webpage(url, name)
+        urn = self._html_search_meta('mediaurn', webpage)
+        info_page = self._download_json(
+            'http://rs.vpro.nl/v2/api/media/%s.json' % urn, name)
+        return self._get_info(info_page['mid'])

youtube_dl/extractor/playfm.py

@@ -10,6 +10,7 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
+    str_to_int,
 )
 
 
@@ -29,6 +30,7 @@ class PlayFMIE(InfoExtractor):
             'duration': 5627.428,
             'upload_date': '20140712',
             'view_count': int,
+            'comment_count': int,
             'thumbnail': 're:^https?://.*\.jpg$',
         },
     }
@@ -51,7 +53,8 @@ class PlayFMIE(InfoExtractor):
 
         recording = rec_doc.find('./recording')
         title = recording.find('./title').text
-        view_count = int_or_none(recording.find('./stats/playcount').text)
+        view_count = str_to_int(recording.find('./stats/playcount').text)
+        comment_count = str_to_int(recording.find('./stats/comments').text)
         duration = float_or_none(recording.find('./duration').text, scale=1000)
         thumbnail = recording.find('./image').text
 
@@ -75,6 +78,7 @@ class PlayFMIE(InfoExtractor):
             'title': title,
             'upload_date': upload_date,
             'view_count': view_count,
+            'comment_count': comment_count,
             'duration': duration,
             'thumbnail': thumbnail,
             'uploader': uploader,

youtube_dl/extractor/pornhd.py

@@ -27,47 +27,40 @@ class PornHdIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        title = self._og_search_title(webpage)
-        TITLE_SUFFIX = ' porn HD Video | PornHD.com '
-        if title.endswith(TITLE_SUFFIX):
-            title = title[:-len(TITLE_SUFFIX)]
-
+        title = self._html_search_regex(
+            r'<title>(.+) porn HD.+?</title>', webpage, 'title')
         description = self._html_search_regex(
             r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
         view_count = int_or_none(self._html_search_regex(
-            r'(\d+) views 	</span>', webpage, 'view count', fatal=False))
+            r'(\d+) views\s*</span>', webpage, 'view count', fatal=False))
 
-        formats = [
-            {
-                'url': format_url,
-                'ext': format.lower(),
-                'format_id': '%s-%s' % (format.lower(), quality.lower()),
-                'quality': 1 if quality.lower() == 'high' else 0,
-            } for format, quality, format_url in re.findall(
-                r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage)
-        ]
+        videos = re.findall(
+            r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage)
 
         mobj = re.search(r'flashVars = (?P<flashvars>{.+?});', webpage)
         if mobj:
             flashvars = json.loads(mobj.group('flashvars'))
-            formats.extend([
-                {
-                    'url': flashvars['hashlink'].replace('?noProxy=1', ''),
-                    'ext': 'flv',
-                    'format_id': 'flv-low',
-                    'quality': 0,
-                },
-                {
-                    'url': flashvars['hd'].replace('?noProxy=1', ''),
-                    'ext': 'flv',
-                    'format_id': 'flv-high',
-                    'quality': 1,
-                }
-            ])
+            for key, quality in [('hashlink', 'low'), ('hd', 'high')]:
+                redirect_url = flashvars.get(key)
+                if redirect_url:
+                    videos.append(('flv', quality, redirect_url))
             thumbnail = flashvars['urlWallpaper']
         else:
             thumbnail = self._og_search_thumbnail(webpage)
 
+        formats = []
+        for format_, quality, redirect_url in videos:
+            format_id = '%s-%s' % (format_.lower(), quality.lower())
+            video_url = self._download_webpage(
+                redirect_url, video_id, 'Downloading %s video link' % format_id, fatal=False)
+            if not video_url:
+                continue
+            formats.append({
+                'url': video_url,
+                'ext': format_.lower(),
+                'format_id': format_id,
+                'quality': 1 if quality.lower() == 'high' else 0,
+            })
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/pornoxo.py

@@ -0,0 +1,65 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    str_to_int,
+)
+
+
+class PornoXOIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?pornoxo\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)\.html'
+    _TEST = {
+        'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html',
+        'md5': '582f28ecbaa9e6e24cb90f50f524ce87',
+        'info_dict': {
+            'id': '7564',
+            'ext': 'flv',
+            'title': 'Striptease From Sexy Secretary!',
+            'description': 'Striptease From Sexy Secretary!',
+            '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)
+
+        video_url = self._html_search_regex(
+            r'\'file\'\s*:\s*"([^"]+)"', webpage, 'video_url')
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)\s*-\s*PornoXO', webpage, 'title')
+
+        description = self._html_search_regex(
+            r'<meta name="description" content="([^"]+)\s*featuring',
+            webpage, 'description', fatal=False)
+
+        thumbnail = self._html_search_regex(
+            r'\'image\'\s*:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
+
+        view_count = str_to_int(self._html_search_regex(
+            r'[vV]iews:\s*([0-9,]+)', webpage, 'view count', fatal=False))
+
+        categories_str = self._html_search_regex(
+            r'<meta name="description" content=".*featuring\s*([^"]+)"',
+            webpage, 'categories', fatal=False)
+        categories = (
+            None if categories_str is None
+            else categories_str.split(','))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'view_count': view_count,
+            'age_limit': 18,
+        }

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/prosiebensat1.py

@@ -145,7 +145,6 @@ class ProSiebenSat1IE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Kurztrips zum Valentinstag',
                 'description': 'md5:8ba6301e70351ae0bedf8da00f7ba528',
-                'upload_date': '20130206',
                 'duration': 307.24,
             },
             'params': {
@@ -240,7 +239,7 @@ class ProSiebenSat1IE(InfoExtractor):
         thumbnail = self._og_search_thumbnail(page)
 
         upload_date = unified_strdate(self._html_search_regex(
-            self._UPLOAD_DATE_REGEXES, page, 'upload date', fatal=False))
+            self._UPLOAD_DATE_REGEXES, page, 'upload date', default=None))
 
         formats = []
 
@@ -249,7 +248,7 @@ class ProSiebenSat1IE(InfoExtractor):
             urls_sources = urls_sources.values()
 
         def fix_bitrate(bitrate):
-            return bitrate / 1000 if bitrate % 1000 == 0 else bitrate
+            return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate
 
         for source in urls_sources:
             protocol = source['protocol']

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/sbs.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class SBSIE(InfoExtractor):
     IE_DESC = 'sbs.com.au'
-    _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/single/(?P<id>[0-9]+)/'
+    _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/(?:single/)?(?P<id>[0-9]+)'
 
     _TESTS = [{
         # Original URL is handled by the generic IE which finds the iframe:
@@ -21,12 +21,16 @@ class SBSIE(InfoExtractor):
         'md5': '3150cf278965eeabb5b4cea1c963fe0a',
         'info_dict': {
             'id': '320403011771',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Dingo Conservation',
             'description': 'Dingoes are on the brink of extinction; most of the animals we think are dingoes are in fact crossbred with wild dogs. This family run a dingo conservation park to prevent their extinction',
             'thumbnail': 're:http://.*\.jpg',
         },
         'add_ies': ['generic'],
+    },
+    {
+        'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',
+        'only_matching': True,
     }]
 
     def _real_extract(self, 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/soundcloud.py

@@ -31,7 +31,8 @@ class SoundcloudIE(InfoExtractor):
                             (?!sets/|likes/?(?:$|[?#]))
                             (?P<title>[\w\d-]+)/?
                             (?P<token>[^?]+?)?(?:[?].*)?$)
-                       |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
+                       |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)
+                          (?:/?\?secret_token=(?P<secret_token>[^&]+?))?$)
                        |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*)
                     )
                     '''
@@ -80,6 +81,20 @@ class SoundcloudIE(InfoExtractor):
                 'duration': 9,
             },
         },
+        # private link (alt format)
+        {
+            'url': 'https://api.soundcloud.com/tracks/123998367?secret_token=s-8Pjrp',
+            'md5': 'aa0dd32bfea9b0c5ef4f02aacd080604',
+            'info_dict': {
+                'id': '123998367',
+                'ext': 'mp3',
+                'title': 'Youtube - Dl Test Video \'\' Ä↭',
+                'uploader': 'jaimeMF',
+                'description': 'test chars:  \"\'/\\ä↭',
+                'upload_date': '20131209',
+                'duration': 9,
+            },
+        },
         # downloadable song
         {
             'url': 'https://soundcloud.com/oddsamples/bus-brakes',
@@ -197,6 +212,9 @@ class SoundcloudIE(InfoExtractor):
         if track_id is not None:
             info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
             full_title = track_id
+            token = mobj.group('secret_token')
+            if token:
+                info_json_url += "&secret_token=" + token
         elif mobj.group('player'):
             query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
             return self.url_result(query['url'][0])
@@ -220,7 +238,7 @@ class SoundcloudIE(InfoExtractor):
 
 
 class SoundcloudSetIE(SoundcloudIE):
-    _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
+    _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/(?P<uploader>[\w\d-]+)/sets/(?P<slug_title>[\w\d-]+)(?:/(?P<token>[^?/]+))?'
     IE_NAME = 'soundcloud:set'
     _TESTS = [{
         'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep',
@@ -234,14 +252,19 @@ class SoundcloudSetIE(SoundcloudIE):
         mobj = re.match(self._VALID_URL, url)
 
         # extract uploader (which is in the url)
-        uploader = mobj.group(1)
+        uploader = mobj.group('uploader')
         # extract simple title (uploader + slug of song title)
-        slug_title = mobj.group(2)
+        slug_title = mobj.group('slug_title')
         full_title = '%s/sets/%s' % (uploader, slug_title)
+        url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
+
+        token = mobj.group('token')
+        if token:
+            full_title += '/' + token
+            url += '/' + token
 
         self.report_resolve(full_title)
 
-        url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
         resolv_url = self._resolv_url(url)
         info = self._download_json(resolv_url, full_title)
 
@@ -252,7 +275,7 @@ class SoundcloudSetIE(SoundcloudIE):
 
         return {
             '_type': 'playlist',
-            'entries': [self._extract_info_dict(track) for track in info['tracks']],
+            'entries': [self._extract_info_dict(track, secret_token=token) for track in info['tracks']],
             'id': info['id'],
             'title': info['title'],
         }
@@ -315,34 +338,38 @@ class SoundcloudUserIE(SoundcloudIE):
 
 
 class SoundcloudPlaylistIE(SoundcloudIE):
-    _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$'
     IE_NAME = 'soundcloud:playlist'
-    _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,
-        }
-    ]
+    _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)
         playlist_id = mobj.group('id')
         base_url = '%s//api.soundcloud.com/playlists/%s.json?' % (self.http_scheme(), playlist_id)
 
-        data = compat_urllib_parse.urlencode({
+        data_dict = {
             'client_id': self._CLIENT_ID,
-        })
+        }
+        token = mobj.group('token')
+
+        if token:
+            data_dict['secret_token'] = token
+
+        data = compat_urllib_parse.urlencode(data_dict)
         data = self._download_json(
             base_url + data, playlist_id, 'Downloading playlist')
 
         entries = [
-            self._extract_info_dict(t, quiet=True) for t in data['tracks']]
+            self._extract_info_dict(t, quiet=True, secret_token=token)
+                for t in data['tracks']]
 
         return {
             '_type': 'playlist',

youtube_dl/extractor/spiegel.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import compat_urlparse
 
 
 class SpiegelIE(InfoExtractor):
@@ -28,16 +29,6 @@ class SpiegelIE(InfoExtractor):
             'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
             'duration': 983,
         },
-    }, {
-        'url': 'http://www.spiegel.de/video/johann-westhauser-videobotschaft-des-hoehlenforschers-video-1502367.html',
-        'md5': '54f58ba0e752e3c07bc2a26222dd0acf',
-        'info_dict': {
-            'id': '1502367',
-            'ext': 'mp4',
-            'title': 'Videobotschaft: Höhlenforscher Westhauser dankt seinen Rettern',
-            'description': 'md5:c6f1ec11413ebd1088b6813943e5fc91',
-            'duration': 42,
-        },
     }]
 
     def _real_extract(self, url):
@@ -82,3 +73,34 @@ class SpiegelIE(InfoExtractor):
             'duration': duration,
             'formats': formats,
         }
+
+
+class SpiegelArticleIE(InfoExtractor):
+    _VALID_URL = 'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
+    IE_NAME = 'Spiegel:Article'
+    IE_DESC = 'Articles on spiegel.de'
+    _TEST = {
+        'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
+        'info_dict': {
+            'id': '1516455',
+            'ext': 'mp4',
+            'title': 'Faszination Badminton: Nennt es bloß nicht Federball',
+            'description': 're:^Patrick Kämnitz gehört.{100,}',
+        },
+    }
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        video_link = self._search_regex(
+            r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage,
+            'video page URL')
+        video_url = compat_urlparse.urljoin(
+            self.http_scheme() + '//spiegel.de/', video_link)
+
+        return {
+            '_type': 'url',
+            'url': video_url,
+        }

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/swrmediathek.py

@@ -52,20 +52,6 @@ class SWRMediathekIE(InfoExtractor):
             'uploader': 'SWR 2',
             'uploader_id': '284670',
         }
-    }, {
-        'url': 'http://swrmediathek.de/content/player.htm?show=52dc7e00-15c5-11e4-84bc-0026b975f2e6',
-        'md5': '881531487d0633080a8cc88d31ef896f',
-        'info_dict': {
-            'id': '52dc7e00-15c5-11e4-84bc-0026b975f2e6',
-            'ext': 'mp4',
-            'title': 'Familienspaß am Bodensee',
-            'description': 'md5:0b591225a32cfde7be1629ed49fe4315',
-            'thumbnail': 're:http://.*\.jpg',
-            'duration': 1784,
-            'upload_date': '20140727',
-            'uploader': 'SWR Fernsehen BW',
-            'uploader_id': '281130',
-        }
     }]
 
     def _real_extract(self, url):

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/telemb.py

@@ -0,0 +1,78 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import remove_start
+
+
+class TeleMBIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?telemb\.be/(?P<display_id>.+?)_d_(?P<id>\d+)\.html'
+    _TESTS = [
+        {
+            'url': 'http://www.telemb.be/mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-_d_13466.html',
+            'md5': 'f45ea69878516ba039835794e0f8f783',
+            'info_dict': {
+                'id': '13466',
+                'display_id': 'mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-',
+                'ext': 'mp4',
+                'title': 'Mons - Cook with Danielle : des cours de cuisine en anglais ! - Les reportages',
+                'description': 'md5:bc5225f47b17c309761c856ad4776265',
+                'thumbnail': 're:^http://.*\.(?:jpg|png)$',
+            }
+        },
+        {
+            # non-ASCII characters in download URL
+            'url': 'http://telemb.be/les-reportages-havre-incendie-mortel_d_13514.html',
+            'md5': '6e9682736e5ccd4eab7f21e855350733',
+            'info_dict': {
+                'id': '13514',
+                'display_id': 'les-reportages-havre-incendie-mortel',
+                'ext': 'mp4',
+                'title': 'Havré - Incendie mortel - Les reportages',
+                'description': 'md5:5e54cb449acb029c2b7734e2d946bd4a',
+                'thumbnail': 're:^http://.*\.(?:jpg|png)$',
+            }
+        },
+    ]
+
+    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)
+
+        formats = []
+        for video_url in re.findall(r'file\s*:\s*"([^"]+)"', webpage):
+            fmt = {
+                'url': video_url,
+                'format_id': video_url.split(':')[0]
+            }
+            rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', video_url)
+            if rtmp:
+                fmt.update({
+                    'play_path': rtmp.group('playpath'),
+                    'app': rtmp.group('app'),
+                    'player_url': 'http://p.jwpcdn.com/6/10/jwplayer.flash.swf',
+                    'page_url': 'http://www.telemb.be',
+                    'preference': -1,
+                })
+            formats.append(fmt)
+        self._sort_formats(formats)
+
+        title = remove_start(self._og_search_title(webpage), 'TéléMB : ')
+        description = self._html_search_regex(
+            r'<meta property="og:description" content="(.+?)" />',
+            webpage, 'description', fatal=False)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/theplatform.py

@@ -5,6 +5,7 @@ import json
 
 from .common import InfoExtractor
 from ..utils import (
+    compat_str,
     ExtractorError,
     xpath_with_ns,
 )
@@ -55,36 +56,44 @@ class ThePlatformIE(InfoExtractor):
         body = meta.find(_x('smil:body'))
 
         f4m_node = body.find(_x('smil:seq//smil:video'))
-        if f4m_node is not None:
+        if f4m_node is not None and '.f4m' in f4m_node.attrib['src']:
             f4m_url = f4m_node.attrib['src']
             if 'manifest.f4m?' not in f4m_url:
                 f4m_url += '?'
             # the parameters are from syfy.com, other sites may use others,
             # they also work for nbc.com
             f4m_url += '&g=UXWGVKRWHFSP&hdcore=3.0.3'
-            formats = [{
-                'ext': 'flv',
-                'url': f4m_url,
-            }]
+            formats = self._extract_f4m_formats(f4m_url, video_id)
         else:
-            base_url = head.find(_x('smil:meta')).attrib['base']
-            switch = body.find(_x('smil:switch'))
             formats = []
-            for f in switch.findall(_x('smil:video')):
-                attr = f.attrib
-                width = int(attr['width'])
-                height = int(attr['height'])
-                vbr = int(attr['system-bitrate']) // 1000
-                format_id = '%dx%d_%dk' % (width, height, vbr)
-                formats.append({
-                    'format_id': format_id,
-                    'url': base_url,
-                    'play_path': 'mp4:' + attr['src'],
-                    'ext': 'flv',
-                    'width': width,
-                    'height': height,
-                    'vbr': vbr,
-                })
+            switch = body.find(_x('smil:switch'))
+            if switch is not None:
+                base_url = head.find(_x('smil:meta')).attrib['base']
+                for f in switch.findall(_x('smil:video')):
+                    attr = f.attrib
+                    width = int(attr['width'])
+                    height = int(attr['height'])
+                    vbr = int(attr['system-bitrate']) // 1000
+                    format_id = '%dx%d_%dk' % (width, height, vbr)
+                    formats.append({
+                        'format_id': format_id,
+                        'url': base_url,
+                        'play_path': 'mp4:' + attr['src'],
+                        'ext': 'flv',
+                        'width': width,
+                        'height': height,
+                        'vbr': vbr,
+                    })
+            else:
+                switch = body.find(_x('smil:seq//smil:switch'))
+                for f in switch.findall(_x('smil:video')):
+                    attr = f.attrib
+                    vbr = int(attr['system-bitrate']) // 1000
+                    formats.append({
+                        'format_id': compat_str(vbr),
+                        'url': attr['src'],
+                        'vbr': vbr,
+                    })
             self._sort_formats(formats)
 
         return {

youtube_dl/extractor/thvideo.py

@@ -0,0 +1,59 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    unified_strdate
+)
+
+
+class THVideoIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?thvideo\.tv/(?:v/th|mobile\.php\?cid=)(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://thvideo.tv/v/th1987/',
+        'md5': 'fa107b1f73817e325e9433505a70db50',
+        'info_dict': {
+            'id': '1987',
+            'ext': 'mp4',
+            'title': '【动画】秘封活动记录 ～ The Sealed Esoteric History.分镜稿预览',
+            'display_id': 'th1987',
+            'thumbnail': 'http://thvideo.tv/uploadfile/2014/0722/20140722013459856.jpg',
+            'description': '社团京都幻想剧团的第一个东方二次同人动画作品「秘封活动记录 ～ The Sealed Esoteric History.」 本视频是该动画第一期的分镜草稿...',
+            'upload_date': '20140722'
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        # extract download link from mobile player page
+        webpage_player = self._download_webpage(
+            'http://thvideo.tv/mobile.php?cid=%s-0' % (video_id),
+            video_id, note='Downloading video source page')
+        video_url = self._html_search_regex(
+            r'<source src="(.*?)" type', webpage_player, 'video url')
+
+        # extract video info from main page
+        webpage = self._download_webpage(
+            'http://thvideo.tv/v/th%s' % (video_id), video_id)
+        title = self._og_search_title(webpage)
+        display_id = 'th%s' % video_id
+        thumbnail = self._og_search_thumbnail(webpage)
+        description = self._og_search_description(webpage)
+        upload_date = unified_strdate(self._html_search_regex(
+            r'span itemprop="datePublished" content="(.*?)">', webpage,
+            'upload date', fatal=False))
+
+        return {
+            'id': video_id,
+            'ext': 'mp4',
+            'url': video_url,
+            'title': title,
+            'display_id': display_id,
+            'thumbnail': thumbnail,
+            'description': description,
+            'upload_date': upload_date
+        }

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

@@ -47,7 +47,7 @@ class ToypicsUserIE(InfoExtractor):
         'info_dict': {
             'id': 'Mikey',
         },
-        'playlist_mincount': 9917,
+        'playlist_mincount': 19,
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/tube8.py

@@ -14,27 +14,35 @@ from ..aes import aes_decrypt_text
 
 
 class Tube8IE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/){2}(?P<id>\d+)'
-    _TEST = {
-        'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
-        'md5': '44bf12b98313827dd52d35b8706a4ea0',
-        'info_dict': {
-            'id': '229795',
-            'ext': 'mp4',
-            'description': 'hot teen Kasia grinding',
-            'uploader': 'unknown',
-            'title': 'Kasia music video',
-            'age_limit': 18,
-        }
-    }
+    _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
+    _TESTS = [
+        {
+            'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
+            'md5': '44bf12b98313827dd52d35b8706a4ea0',
+            'info_dict': {
+                'id': '229795',
+                'display_id': 'kasia-music-video',
+                'ext': 'mp4',
+                'description': 'hot teen Kasia grinding',
+                'uploader': 'unknown',
+                'title': 'Kasia music video',
+                'age_limit': 18,
+            }
+        },
+        {
+            'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
+            'only_matching': True,
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, video_id)
+        webpage = self._download_webpage(req, display_id)
 
         flashvars = json.loads(self._html_search_regex(
             r'var flashvars\s*=\s*({.+?})', webpage, 'flashvars'))
@@ -70,6 +78,7 @@ class Tube8IE(InfoExtractor):
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'url': video_url,
             'title': title,
             'description': description,

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/tumblr.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class TumblrIE(InfoExtractor):
-    _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)($|/)'
+    _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/(?:post|video)/(?P<id>[0-9]+)(?:$|[/?#])'
     _TESTS = [{
         'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
         'md5': '479bb068e5b16462f5176a6828829767',
@@ -56,13 +56,15 @@ class TumblrIE(InfoExtractor):
 
         # The only place where you can get a title, it's not complete,
         # but searching in other places doesn't work for all videos
-        video_title = self._html_search_regex(r'<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
-            webpage, 'title', flags=re.DOTALL)
+        video_title = self._html_search_regex(
+            r'(?s)<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
+            webpage, 'title')
 
-        return [{'id': video_id,
-                 'url': video_url,
-                 'title': video_title,
-                 'description': self._html_search_meta('description', webpage),
-                 'thumbnail': video_thumbnail,
-                 'ext': ext
-                 }]
+        return {
+            'id': video_id,
+             'url': video_url,
+             'title': video_title,
+             'description': self._html_search_meta('description', webpage),
+             'thumbnail': video_thumbnail,
+             'ext': ext,
+        }

youtube_dl/extractor/turbo.py

@@ -0,0 +1,67 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    qualities,
+    xpath_text,
+)
+
+
+class TurboIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?turbo\.fr/videos-voiture/(?P<id>[0-9]+)-'
+    _API_URL = 'http://www.turbo.fr/api/tv/xml.php?player_generique=player_generique&id={0:}'
+    _TEST = {
+        'url': 'http://www.turbo.fr/videos-voiture/454443-turbo-du-07-09-2014-renault-twingo-3-bentley-continental-gt-speed-ces-guide-achat-dacia.html',
+        'md5': '33f4b91099b36b5d5a91f84b5bcba600',
+        'info_dict': {
+            'id': '454443',
+            'ext': 'mp4',
+            'duration': 3715,
+            'title': 'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia... ',
+            'description': 'Retrouvez dans cette rubrique toutes les vidéos de l\'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia... ',
+            '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)
+
+        playlist = self._download_xml(self._API_URL.format(video_id), video_id)
+        item = playlist.find('./channel/item')
+        if item is None:
+            raise ExtractorError('Playlist item was not found', expected=True)
+
+        title = xpath_text(item, './title', 'title')
+        duration = int_or_none(xpath_text(item, './durate', 'duration'))
+        thumbnail = xpath_text(item, './visuel_clip', 'thumbnail')
+        description = self._og_search_description(webpage)
+
+        formats = []
+        get_quality = qualities(['3g', 'sd', 'hq'])
+        for child in item:
+            m = re.search(r'url_video_(?P<quality>.+)', child.tag)
+            if m:
+                quality = m.group('quality')
+                formats.append({
+                    'format_id': quality,
+                    'url': child.text,
+                    'quality': get_quality(quality),
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'duration': duration,
+            'thumbnail': thumbnail,
+            'description': description,
+            'formats': formats,
+        }

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/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/videomega.py

@@ -0,0 +1,57 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    remove_start,
+)
+
+
+class VideoMegaIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://
+        (?:www\.)?videomega\.tv/
+        (?:iframe\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
+        '''
+    _TEST = {
+        'url': 'http://videomega.tv/?ref=GKeGPVedBe',
+        'md5': '240fb5bcf9199961f48eb17839b084d6',
+        'info_dict': {
+            'id': 'GKeGPVedBe',
+            'ext': 'mp4',
+            'title': 'XXL - All Sports United',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id)
+        webpage = self._download_webpage(url, video_id)
+
+        escaped_data = self._search_regex(
+            r'unescape\("([^"]+)"\)', webpage, 'escaped data')
+        playlist = compat_urllib_parse.unquote(escaped_data)
+
+        thumbnail = self._search_regex(
+            r'image:\s*"([^"]+)"', playlist, 'thumbnail', fatal=False)
+        url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL')
+        title = remove_start(self._html_search_regex(
+            r'<title>(.*?)</title>', webpage, 'title'), 'VideoMega.tv - ')
+
+        formats = [{
+            'format_id': 'sd',
+            'url': url,
+        }]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/vporn.py

@@ -0,0 +1,125 @@
+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+)'
+    _TESTS = [
+        {
+            '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$',
+                'uploader': 'kileyGrope',
+                'categories': ['Masturbation', 'Teen'],
+                'duration': 393,
+                'age_limit': 18,
+                'view_count': int,
+                'like_count': int,
+                'dislike_count': int,
+                'comment_count': int,
+            }
+        },
+        {
+            'url': 'http://www.vporn.com/female/hana-shower/523564/',
+            'md5': 'ced35a4656198a1664cf2cda1575a25f',
+            'info_dict': {
+                'id': '523564',
+                'display_id': 'hana-shower',
+                'ext': 'mp4',
+                'title': 'Hana Shower',
+                'description': 'Hana showers at the bathroom.',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'uploader': 'Hmmmmm',
+                'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female'],
+                'duration': 588,
+                'age_limit': 18,
+                'view_count': int,
+                'like_count': int,
+                'dislike_count': int,
+                'comment_count': int,
+            }
+        },
+    ]
+
+    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*"(https?://[^"]+)"', 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

@@ -5,7 +5,10 @@ import re
 import hashlib
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
+from ..utils import (
+    ExtractorError,
+    unified_strdate,
+)
 
 
 class WatIE(InfoExtractor):
@@ -57,6 +60,11 @@ class WatIE(InfoExtractor):
 
         video_info = self.download_video_info(real_id)
 
+        error_desc = video_info.get('error_desc')
+        if error_desc:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, error_desc), expected=True)
+
         geo_list = video_info.get('geoList')
         country = geo_list[0] if geo_list else ''
 

youtube_dl/extractor/xhamster.py

@@ -18,7 +18,6 @@ class XHamsterIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
-            'md5': '8281348b8d3c53d39fffb377d24eac4e',
             'info_dict': {
                 'id': '1509445',
                 'ext': 'mp4',
@@ -31,7 +30,6 @@ class XHamsterIE(InfoExtractor):
         },
         {
             'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
-            'md5': '4cbd8d56708ecb4fb4124c23e4acb81a',
             'info_dict': {
                 'id': '2221348',
                 'ext': 'mp4',

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/youporn.py

@@ -23,7 +23,6 @@ class YouPornIE(InfoExtractor):
     _VALID_URL = r'^(?P<proto>https?://)(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
     _TEST = {
         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
-        'md5': '71ec5fcfddacf80f495efa8b6a8d9a89',
         'info_dict': {
             'id': '505835',
             'ext': 'mp4',