release 2014.06.07

Conflicts:
	youtube_dl/extractor/__init__.py

.travis.yml

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

CHANGELOG

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

Makefile

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

README.md

@@ -1,11 +1,24 @@
-% YOUTUBE-DL(1)
-
-# NAME
 youtube-dl - download videos from youtube.com or other video platforms
 
 # SYNOPSIS
 **youtube-dl** [OPTIONS] URL [URL...]
 
+# INSTALLATION
+
+To install it right away for all UNIX users (Linux, OS X, etc.), type:
+
+    sudo curl https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl
+    sudo chmod a+x /usr/local/bin/youtube-dl
+
+If you do not have curl, you can alternatively use a recent wget:
+
+    sudo wget https://yt-dl.org/downloads/2014.05.13/youtube-dl -O /usr/local/bin/youtube-dl
+    sudo chmod a+x /usr/local/bin/youtube-dl
+
+Windows users can [download a .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in their home directory or any other location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29).
+
+Alternatively, refer to the developer instructions below for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html .
+
 # DESCRIPTION
 **youtube-dl** is a small command-line program to download videos from
 YouTube.com and a few more sites. It requires the Python interpreter, version
@@ -458,7 +471,7 @@ If your report is shorter than two lines, it is almost certainly missing some of
 
 For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
 
-Site support requests must contain an example URL. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
+Site support requests **must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
 
 ###  Are you using the latest version?
 

devscripts/make_readme.py

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

devscripts/prepare_manpage.py

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

devscripts/release.sh

@@ -45,9 +45,9 @@ fi
 /bin/echo -e "\n### Changing version in version.py..."
 sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
 
-/bin/echo -e "\n### Committing CHANGELOG README.md and youtube_dl/version.py..."
+/bin/echo -e "\n### Committing README.md and youtube_dl/version.py..."
 make README.md
-git add CHANGELOG README.md youtube_dl/version.py
+git add README.md youtube_dl/version.py
 git commit -m "release $version"
 
 /bin/echo -e "\n### Now tagging, signing and pushing..."

test/helper.py

@@ -85,7 +85,7 @@ def gettestcases(include_onlymatching=False):
         else:
             tests = getattr(ie, '_TESTS', [])
         for t in tests:
-            if not include_onlymatching and getattr(t, 'only_matching', False):
+            if not include_onlymatching and t.get('only_matching', False):
                 continue
             t['name'] = type(ie).__name__[:-len('IE')]
             yield t
@@ -107,7 +107,7 @@ def expect_info_dict(self, expected_dict, got_dict):
         elif isinstance(expected, type):
             got = got_dict.get(info_field)
             self.assertTrue(isinstance(got, expected),
-                u'Expected type %r, but got value %r of type %r' % (expected, got, type(got)))
+                u'Expected type %r for field %s, but got value %r of type %r' % (expected, info_field, got, type(got)))
         else:
             if isinstance(expected, compat_str) and expected.startswith('md5:'):
                 got = 'md5:' + md5(got_dict.get(info_field))
@@ -134,3 +134,17 @@ def expect_info_dict(self, expected_dict, got_dict):
             missing_keys,
             'Missing keys in test definition: %s' % (
                 ', '.join(sorted(missing_keys))))
+
+
+def assertRegexpMatches(self, text, regexp, msg=None):
+    if hasattr(self, 'assertRegexpMatches'):
+        return self.assertRegexpMatches(text, regexp, msg)
+    else:
+        m = re.match(regexp, text)
+        if not m:
+            note = 'Regexp didn\'t match: %r not found in %r' % (regexp, text)
+            if msg is None:
+                msg = note
+            else:
+                msg = note + ', ' + msg
+            self.assertTrue(m, msg)

test/test_YoutubeDL.py

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

test/test_age_restriction.py

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

test/test_playlists.py

@@ -10,6 +10,7 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
+    assertRegexpMatches,
     expect_info_dict,
     FakeYDL,
 )
@@ -22,9 +23,12 @@ from youtube_dl.extractor import (
     VimeoUserIE,
     VimeoAlbumIE,
     VimeoGroupsIE,
+    VineUserIE,
     UstreamChannelIE,
     SoundcloudSetIE,
     SoundcloudUserIE,
+    SoundcloudPlaylistIE,
+    TeacherTubeClassroomIE,
     LivestreamIE,
     NHLVideocenterIE,
     BambuserChannelIE,
@@ -100,6 +104,13 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['title'], 'Rolex Awards for Enterprise')
         self.assertTrue(len(result['entries']) > 72)
 
+    def test_vine_user(self):
+        dl = FakeYDL()
+        ie = VineUserIE(dl)
+        result = ie.extract('https://vine.co/Visa')
+        self.assertIsPlaylist(result)
+        self.assertTrue(len(result['entries']) >= 50)
+
     def test_ustream_channel(self):
         dl = FakeYDL()
         ie = UstreamChannelIE(dl)
@@ -124,6 +135,17 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['id'], '9615865')
         self.assertTrue(len(result['entries']) >= 12)
 
+    def test_soundcloud_playlist(self):
+        dl = FakeYDL()
+        ie = SoundcloudPlaylistIE(dl)
+        result = ie.extract('http://api.soundcloud.com/playlists/4110309')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '4110309')
+        self.assertEqual(result['title'], 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]')
+        assertRegexpMatches(
+            self, result['description'], r'TILT Brass - Bowery Poetry Club')
+        self.assertEqual(len(result['entries']), 6)
+
     def test_livestream_event(self):
         dl = FakeYDL()
         ie = LivestreamIE(dl)
@@ -188,20 +210,20 @@ class TestPlaylists(unittest.TestCase):
     def test_ivi_compilation(self):
         dl = FakeYDL()
         ie = IviCompilationIE(dl)
-        result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel')
+        result = ie.extract('http://www.ivi.ru/watch/dvoe_iz_lartsa')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'dezhurnyi_angel')
-        self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012)')
-        self.assertTrue(len(result['entries']) >= 23)
+        self.assertEqual(result['id'], 'dvoe_iz_lartsa')
+        self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008)')
+        self.assertTrue(len(result['entries']) >= 24)
 
     def test_ivi_compilation_season(self):
         dl = FakeYDL()
         ie = IviCompilationIE(dl)
-        result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel/season2')
+        result = ie.extract('http://www.ivi.ru/watch/dvoe_iz_lartsa/season1')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'dezhurnyi_angel/season2')
-        self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012) 2 сезон')
-        self.assertTrue(len(result['entries']) >= 7)
+        self.assertEqual(result['id'], 'dvoe_iz_lartsa/season1')
+        self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008) 1 сезон')
+        self.assertTrue(len(result['entries']) >= 12)
         
     def test_imdb_list(self):
         dl = FakeYDL()
@@ -339,5 +361,13 @@ class TestPlaylists(unittest.TestCase):
             result['title'], 'Brace Yourself - Today\'s Weirdest News')
         self.assertTrue(len(result['entries']) >= 10)
 
+    def test_TeacherTubeClassroom(self):
+        dl = FakeYDL()
+        ie = TeacherTubeClassroomIE(dl)
+        result = ie.extract('http://www.teachertube.com/view_classroom.php?user=rbhagwati2')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'rbhagwati2')
+        self.assertTrue(len(result['entries']) >= 20)
+
 if __name__ == '__main__':
     unittest.main()

test/test_subtitles.py

@@ -181,7 +181,7 @@ class TestTedSubtitles(BaseTestSubtitles):
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(len(subtitles.keys()), 28)
+        self.assertTrue(len(subtitles.keys()) >= 28)
 
     def test_list_subtitles(self):
         self.DL.expect_warning(u'Automatic Captions not supported by this server')

test/test_youtube_lists.py

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

youtube_dl/YoutubeDL.py

@@ -31,6 +31,7 @@ from .utils import (
     ContentTooShortError,
     date_from_str,
     DateRange,
+    DEFAULT_OUTTMPL,
     determine_ext,
     DownloadError,
     encodeFilename,
@@ -440,7 +441,8 @@ class YoutubeDL(object):
                                  if v is not None)
             template_dict = collections.defaultdict(lambda: 'NA', template_dict)
 
-            tmpl = os.path.expanduser(self.params['outtmpl'])
+            outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
+            tmpl = os.path.expanduser(outtmpl)
             filename = tmpl % template_dict
             return filename
         except ValueError as err:
@@ -715,6 +717,17 @@ class YoutubeDL(object):
             info_dict['playlist'] = None
             info_dict['playlist_index'] = None
 
+        thumbnails = info_dict.get('thumbnails')
+        if thumbnails:
+            thumbnails.sort(key=lambda t: (
+                t.get('width'), t.get('height'), t.get('url')))
+            for t in thumbnails:
+                if 'width' in t and 'height' in t:
+                    t['resolution'] = '%dx%d' % (t['width'], t['height'])
+
+        if thumbnails and 'thumbnail' not in info_dict:
+            info_dict['thumbnail'] = thumbnails[-1]['url']
+
         if 'display_id' not in info_dict and 'id' in info_dict:
             info_dict['display_id'] = info_dict['id']
 
@@ -1025,10 +1038,11 @@ class YoutubeDL(object):
 
     def download(self, url_list):
         """Download a given list of URLs."""
+        outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
         if (len(url_list) > 1 and
-                '%' not in self.params['outtmpl']
+                '%' not in outtmpl
                 and self.params.get('max_downloads') != 1):
-            raise SameFileError(self.params['outtmpl'])
+            raise SameFileError(outtmpl)
 
         for url in url_list:
             try:
@@ -1139,57 +1153,57 @@ class YoutubeDL(object):
             res = default
         return res
 
-    def list_formats(self, info_dict):
-        def format_note(fdict):
-            res = ''
-            if fdict.get('ext') in ['f4f', 'f4m']:
-                res += '(unsupported) '
-            if fdict.get('format_note') is not None:
-                res += fdict['format_note'] + ' '
-            if fdict.get('tbr') is not None:
-                res += '%4dk ' % fdict['tbr']
-            if fdict.get('container') is not None:
-                if res:
-                    res += ', '
-                res += '%s container' % fdict['container']
-            if (fdict.get('vcodec') is not None and
-                    fdict.get('vcodec') != 'none'):
-                if res:
-                    res += ', '
-                res += fdict['vcodec']
-                if fdict.get('vbr') is not None:
-                    res += '@'
-            elif fdict.get('vbr') is not None and fdict.get('abr') is not None:
-                res += 'video@'
+    def _format_note(self, fdict):
+        res = ''
+        if fdict.get('ext') in ['f4f', 'f4m']:
+            res += '(unsupported) '
+        if fdict.get('format_note') is not None:
+            res += fdict['format_note'] + ' '
+        if fdict.get('tbr') is not None:
+            res += '%4dk ' % fdict['tbr']
+        if fdict.get('container') is not None:
+            if res:
+                res += ', '
+            res += '%s container' % fdict['container']
+        if (fdict.get('vcodec') is not None and
+                fdict.get('vcodec') != 'none'):
+            if res:
+                res += ', '
+            res += fdict['vcodec']
             if fdict.get('vbr') is not None:
-                res += '%4dk' % fdict['vbr']
-            if fdict.get('acodec') is not None:
-                if res:
-                    res += ', '
-                if fdict['acodec'] == 'none':
-                    res += 'video only'
-                else:
-                    res += '%-5s' % fdict['acodec']
-            elif fdict.get('abr') is not None:
-                if res:
-                    res += ', '
-                res += 'audio'
-            if fdict.get('abr') is not None:
-                res += '@%3dk' % fdict['abr']
-            if fdict.get('asr') is not None:
-                res += ' (%5dHz)' % fdict['asr']
-            if fdict.get('filesize') is not None:
-                if res:
-                    res += ', '
-                res += format_bytes(fdict['filesize'])
-            return res
+                res += '@'
+        elif fdict.get('vbr') is not None and fdict.get('abr') is not None:
+            res += 'video@'
+        if fdict.get('vbr') is not None:
+            res += '%4dk' % fdict['vbr']
+        if fdict.get('acodec') is not None:
+            if res:
+                res += ', '
+            if fdict['acodec'] == 'none':
+                res += 'video only'
+            else:
+                res += '%-5s' % fdict['acodec']
+        elif fdict.get('abr') is not None:
+            if res:
+                res += ', '
+            res += 'audio'
+        if fdict.get('abr') is not None:
+            res += '@%3dk' % fdict['abr']
+        if fdict.get('asr') is not None:
+            res += ' (%5dHz)' % fdict['asr']
+        if fdict.get('filesize') is not None:
+            if res:
+                res += ', '
+            res += format_bytes(fdict['filesize'])
+        return res
 
+    def list_formats(self, info_dict):
         def line(format, idlen=20):
             return (('%-' + compat_str(idlen + 1) + 's%-10s%-12s%s') % (
                 format['format_id'],
                 format['ext'],
                 self.format_resolution(format),
-                format_note(format),
+                self._format_note(format),
             ))
 
         formats = info_dict.get('formats', [info_dict])
@@ -1197,8 +1211,8 @@ class YoutubeDL(object):
                     max(len(f['format_id']) for f in formats))
         formats_s = [line(f, idlen) for f in formats]
         if len(formats) > 1:
-            formats_s[0] += (' ' if format_note(formats[0]) else '') + '(worst)'
-            formats_s[-1] += (' ' if format_note(formats[-1]) else '') + '(best)'
+            formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)'
+            formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)'
 
         header_line = line({
             'format_id': 'format code', 'ext': 'extension',

youtube_dl/__init__.py

@@ -53,6 +53,12 @@ __authors__  = (
     'Mattias Harrysson',
     'phaer',
     'Sainyam Kapoor',
+    'Nicolas Évrard',
+    'Jason Normore',
+    'Hoje Lee',
+    'Adam Thalhammer',
+    'Georg Jähnig',
+    'Ralf Haring',
 )
 
 __license__ = 'Public Domain'
@@ -72,6 +78,7 @@ from .utils import (
     compat_getpass,
     compat_print,
     DateRange,
+    DEFAULT_OUTTMPL,
     decodeOption,
     get_term_width,
     DownloadError,
@@ -676,7 +683,7 @@ def _real_main(argv=None):
         if not opts.audioquality.isdigit():
             parser.error(u'invalid audio quality specified')
     if opts.recodevideo is not None:
-        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg']:
+        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
             parser.error(u'invalid video recode format specified')
     if opts.date is not None:
         date = DateRange.day(opts.date)
@@ -705,7 +712,7 @@ def _real_main(argv=None):
             or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s')
             or (opts.useid and u'%(id)s.%(ext)s')
             or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
-            or u'%(title)s-%(id)s.%(ext)s')
+            or DEFAULT_OUTTMPL)
     if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
         parser.error(u'Cannot download a video and extract audio into the same'
                      u' file! Use "{0}.%(ext)s" instead of "{0}" as the output'

youtube_dl/downloader/http.py

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

youtube_dl/downloader/rtmp.py

@@ -10,6 +10,7 @@ from .common import FileDownloader
 from ..utils import (
     encodeFilename,
     format_bytes,
+    compat_str,
 )
 
 
@@ -95,6 +96,7 @@ class RtmpFD(FileDownloader):
         flash_version = info_dict.get('flash_version', None)
         live = info_dict.get('rtmp_live', False)
         conn = info_dict.get('rtmp_conn', None)
+        protocol = info_dict.get('rtmp_protocol', None)
 
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
@@ -127,8 +129,13 @@ class RtmpFD(FileDownloader):
             basic_args += ['--flashVer', flash_version]
         if live:
             basic_args += ['--live']
-        if conn:
+        if isinstance(conn, list):
+            for entry in conn:
+                basic_args += ['--conn', entry]
+        elif isinstance(conn, compat_str):
             basic_args += ['--conn', conn]
+        if protocol is not None:
+            basic_args += ['--protocol', protocol]
         args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
 
         if sys.platform == 'win32' and sys.version_info < (3, 0):

youtube_dl/extractor/__init__.py

@@ -20,6 +20,7 @@ from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
+from .bilibili import BiliBiliIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
@@ -71,6 +72,7 @@ from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .eitb import EitbIE
 from .elpais import ElPaisIE
+from .empflix import EmpflixIE
 from .engadget import EngadgetIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
@@ -78,6 +80,7 @@ from .exfm import ExfmIE
 from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
+from .fc2 import FC2IE
 from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
@@ -108,10 +111,12 @@ from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
 from .hark import HarkIE
 from .helsinki import HelsinkiIE
+from .hentaistigma import HentaiStigmaIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
 from .huffpost import HuffPostIE
 from .hypem import HypemIE
+from .iconosquare import IconosquareIE
 from .ign import IGNIE, OneUPIE
 from .imdb import (
     ImdbIE,
@@ -137,6 +142,7 @@ from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
 from .kontrtube import KontrTubeIE
+from .ku6 import Ku6IE
 from .la7 import LA7IE
 from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
@@ -159,6 +165,7 @@ from .mofosex import MofosexIE
 from .mooshare import MooshareIE
 from .morningstar import MorningstarIE
 from .motorsport import MotorsportIE
+from .moviezine import MoviezineIE
 from .movshare import MovShareIE
 from .mtv import (
     MTVIE,
@@ -178,6 +185,7 @@ from .nbc import (
 from .ndr import NDRIE
 from .ndtv import NDTVIE
 from .newgrounds import NewgroundsIE
+from .newstube import NewstubeIE
 from .nfb import NFBIE
 from .nhl import NHLIE, NHLVideocenterIE
 from .niconico import NiconicoIE
@@ -187,7 +195,13 @@ from .normalboots import NormalbootsIE
 from .novamov import NovaMovIE
 from .nowness import NownessIE
 from .nowvideo import NowVideoIE
+from .nrk import (
+    NRKIE,
+    NRKTVIE,
+)
 from .ntv import NTVIE
+from .nytimes import NYTimesIE
+from .nuvid import NuvidIE
 from .oe1 import OE1IE
 from .ooyala import OoyalaIE
 from .orf import ORFIE
@@ -208,6 +222,7 @@ from .ringtv import RingTVIE
 from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
+from .rtbf import RTBFIE
 from .rtlnow import RTLnowIE
 from .rts import RTSIE
 from .rtve import RTVEALaCartaIE
@@ -219,9 +234,11 @@ from .rutube import (
 )
 from .rutv import RUTVIE
 from .savefrom import SaveFromIE
+from .scivee import SciVeeIE
 from .servingsys import ServingSysIE
 from .sina import SinaIE
 from .slideshare import SlideshareIE
+from .slutload import SlutloadIE
 from .smotri import (
     SmotriIE,
     SmotriCommunityIE,
@@ -229,7 +246,12 @@ from .smotri import (
     SmotriBroadcastIE,
 )
 from .sohu import SohuIE
-from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE
+from .soundcloud import (
+    SoundcloudIE,
+    SoundcloudSetIE,
+    SoundcloudUserIE,
+    SoundcloudPlaylistIE
+)
 from .southparkstudios import (
     SouthParkStudiosIE,
     SouthparkDeIE,
@@ -237,14 +259,21 @@ from .southparkstudios import (
 from .space import SpaceIE
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE
+from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
 from .stanfordoc import StanfordOpenClassroomIE
-from .statigram import StatigramIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
+from .swrmediathek import SWRMediathekIE
 from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
+from .tagesschau import TagesschauIE
+from .teachertube import (
+    TeacherTubeIE,
+    TeacherTubeClassroomIE,
+)
+from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
@@ -277,12 +306,14 @@ from .veehd import VeeHDIE
 from .veoh import VeohIE
 from .vesti import VestiIE
 from .vevo import VevoIE
+from .vh1 import VH1IE
 from .viddler import ViddlerIE
 from .videobam import VideoBamIE
 from .videodetective import VideoDetectiveIE
 from .videolecturesnet import VideoLecturesNetIE
 from .videofyme import VideofyMeIE
 from .videopremium import VideoPremiumIE
+from .videott import VideoTtIE
 from .videoweed import VideoWeedIE
 from .vimeo import (
     VimeoIE,
@@ -291,15 +322,21 @@ from .vimeo import (
     VimeoAlbumIE,
     VimeoGroupsIE,
     VimeoReviewIE,
+    VimeoWatchLaterIE,
+)
+from .vine import (
+    VineIE,
+    VineUserIE,
 )
-from .vine import VineIE
 from .viki import VikiIE
 from .vk import VKIE
 from .vube import VubeIE
+from .vuclip import VuClipIE
 from .washingtonpost import WashingtonPostIE
 from .wat import WatIE
 from .wdr import (
     WDRIE,
+    WDRMobileIE,
     WDRMausIE,
 )
 from .weibo import WeiboIE

youtube_dl/extractor/aftonbladet.py

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

youtube_dl/extractor/ard.py

@@ -38,15 +38,19 @@ class ARDIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         title = self._html_search_regex(
-            r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', webpage, 'title')
+            [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
+             r'<meta name="dcterms.title" content="(.*?)"/>',
+             r'<h4 class="headline">(.*?)</h4>'],
+            webpage, 'title')
         description = self._html_search_meta(
             'dcterms.abstract', webpage, 'description')
         thumbnail = self._og_search_thumbnail(webpage)
 
-        streams = [
-            mo.groupdict()
-            for mo in re.finditer(
-                r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)', webpage)]
+
+        media_info = self._download_json(
+            'http://www.ardmediathek.de/play/media/%s' % video_id, video_id)
+        # The second element of the _mediaArray contains the standard http urls
+        streams = media_info['_mediaArray'][1]['_mediaStreamArray']
         if not streams:
             if '"fsk"' in webpage:
                 raise ExtractorError('This video is only available after 20:00')
@@ -54,21 +58,12 @@ class ARDIE(InfoExtractor):
         formats = []
         for s in streams:
             format = {
-                'quality': int(s['quality']),
+                'quality': s['_quality'],
+                'url': s['_stream'],
             }
-            if s.get('rtmp_url'):
-                format['protocol'] = 'rtmp'
-                format['url'] = s['rtmp_url']
-                format['playpath'] = s['video_url']
-            else:
-                format['url'] = s['video_url']
 
-            quality_name = self._search_regex(
-                r'[,.]([a-zA-Z0-9_-]+),?\.mp4', format['url'],
-                'quality name', default='NA')
-            format['format_id'] = '%s-%s-%s-%s' % (
-                determine_ext(format['url']), quality_name, s['media_type'],
-                s['quality'])
+            format['format_id'] = '%s-%s' % (
+                determine_ext(format['url']), format['quality'])
 
             formats.append(format)
 

youtube_dl/extractor/arte.py

@@ -74,7 +74,8 @@ class ArteTVPlus7IE(InfoExtractor):
         return self._extract_from_webpage(webpage, video_id, lang)
 
     def _extract_from_webpage(self, webpage, video_id, lang):
-        json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
+        json_url = self._html_search_regex(
+            r'arte_vp_url="(.*?)"', webpage, 'json vp url')
         return self._extract_from_json_url(json_url, video_id, lang)
 
     def _extract_from_json_url(self, json_url, video_id, lang):
@@ -120,14 +121,17 @@ class ArteTVPlus7IE(InfoExtractor):
                 return ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality'])
         else:
             def sort_key(f):
+                versionCode = f.get('versionCode')
+                if versionCode is None:
+                    versionCode = ''
                 return (
                     # Sort first by quality
-                    int(f.get('height',-1)),
-                    int(f.get('bitrate',-1)),
+                    int(f.get('height', -1)),
+                    int(f.get('bitrate', -1)),
                     # The original version with subtitles has lower relevance
-                    re.match(r'VO-ST(F|A)', f.get('versionCode', '')) is None,
+                    re.match(r'VO-ST(F|A)', versionCode) is None,
                     # The version with sourds/mal subtitles has also lower relevance
-                    re.match(r'VO?(F|A)-STM\1', f.get('versionCode', '')) is None,
+                    re.match(r'VO?(F|A)-STM\1', versionCode) is None,
                     # Prefer http downloads over m3u8
                     0 if f['url'].endswith('m3u8') else 1,
                 )

youtube_dl/extractor/bandcamp.py

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

youtube_dl/extractor/bilibili.py

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

youtube_dl/extractor/blinkx.py

@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
-import datetime
 import json
 import re
 
@@ -19,15 +18,16 @@ class BlinkxIE(InfoExtractor):
         'file': '8aQUy7GV.mp4',
         'md5': '2e9a07364af40163a908edbf10bb2492',
         'info_dict': {
-            "title": "Police Car Rolls Away",
-            "uploader": "stupidvideos.com",
-            "upload_date": "20131215",
-            "description": "A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!",
-            "duration": 14.886,
-            "thumbnails": [{
-                "width": 100,
-                "height": 76,
-                "url": "http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg",
+            'title': 'Police Car Rolls Away',
+            'uploader': 'stupidvideos.com',
+            'upload_date': '20131215',
+            'timestamp': 1387068000,
+            'description': 'A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!',
+            'duration': 14.886,
+            'thumbnails': [{
+                'width': 100,
+                'height': 76,
+                'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg',
             }],
         },
     }
@@ -41,9 +41,6 @@ class BlinkxIE(InfoExtractor):
                    'video=%s' % video_id)
         data_json = self._download_webpage(api_url, display_id)
         data = json.loads(data_json)['api']['results'][0]
-        dt = datetime.datetime.fromtimestamp(data['pubdate_epoch'])
-        pload_date = dt.strftime('%Y%m%d')
-
         duration = None
         thumbnails = []
         formats = []
@@ -64,10 +61,7 @@ class BlinkxIE(InfoExtractor):
                 vcodec = remove_start(m['vcodec'], 'ff')
                 acodec = remove_start(m['acodec'], 'ff')
                 tbr = (int(m['vbr']) + int(m['abr'])) // 1000
-                format_id = (u'%s-%sk-%s' %
-                             (vcodec,
-                              tbr,
-                              m['w']))
+                format_id = u'%s-%sk-%s' % (vcodec, tbr, m['w'])
                 formats.append({
                     'format_id': format_id,
                     'url': m['link'],
@@ -88,7 +82,7 @@ class BlinkxIE(InfoExtractor):
             'title': data['title'],
             'formats': formats,
             'uploader': data['channel_name'],
-            'upload_date': pload_date,
+            'timestamp': data['pubdate_epoch'],
             'description': data.get('description'),
             'thumbnails': thumbnails,
             'duration': duration,

youtube_dl/extractor/bliptv.py

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

youtube_dl/extractor/canalplus.py

@@ -4,17 +4,20 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
+from ..utils import (
+    unified_strdate,
+    url_basename,
+)
 
 
 class CanalplusIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>\d+))'
+    _VALID_URL = r'https?://(?:www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
     IE_NAME = 'canalplus.fr'
 
     _TEST = {
         'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
-        'md5': '60c29434a416a83c15dae2587d47027d',
+        'md5': '3db39fb48b9685438ecf33a1078023e4',
         'info_dict': {
             'id': '922470',
             'ext': 'flv',
@@ -26,10 +29,13 @@ class CanalplusIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = mobj.groupdict().get('id')
+
+        # Beware, some subclasses do not define an id group
+        display_id = url_basename(mobj.group('path'))
 
         if video_id is None:
-            webpage = self._download_webpage(url, mobj.group('path'))
+            webpage = self._download_webpage(url, display_id)
             video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, 'video id')
 
         info_url = self._VIDEO_INFO_TEMPLATE % video_id
@@ -53,6 +59,7 @@ class CanalplusIE(InfoExtractor):
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
                                   infos.find('TITRAGE/SOUS_TITRE').text),
             'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),

youtube_dl/extractor/cinemassacre.py

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

youtube_dl/extractor/cmt.py

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

youtube_dl/extractor/cnet.py

@@ -33,7 +33,7 @@ class CNETIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
         data_json = self._html_search_regex(
-            r"<div class=\"cnetVideoPlayer\" data-cnet-video-options='([^']+)'",
+            r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'",
             webpage, 'data json')
         data = json.loads(data_json)
         vdata = data['video']

youtube_dl/extractor/cnn.py

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

youtube_dl/extractor/comedycentral.py

@@ -188,7 +188,7 @@ class ComedyCentralShowsIE(InfoExtractor):
                 })
                 formats.append({
                     'format_id': 'rtmp-%s' % format,
-                    'url': rtmp_video_url,
+                    'url': rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm'),
                     'ext': self._video_extensions.get(format, 'mp4'),
                     'height': h,
                     'width': w,

youtube_dl/extractor/common.py

@@ -92,8 +92,12 @@ class InfoExtractor(object):
                     unique, but available before title. Typically, id is
                     something like "4234987", title "Dancing naked mole rats",
                     and display_id "dancing-naked-mole-rats"
-    thumbnails:     A list of dictionaries (with the entries "resolution" and
-                    "url") for the varying thumbnails
+    thumbnails:     A list of dictionaries, with the following entries:
+                        * "url"
+                        * "width" (optional, int)
+                        * "height" (optional, int)
+                        * "resolution" (optional, string "{width}x{height"},
+                                        deprecated)
     thumbnail:      Full URL to a video thumbnail image.
     description:    One-line video description.
     uploader:       Full name of the video uploader.
@@ -113,6 +117,8 @@ class InfoExtractor(object):
     webpage_url:    The url to the video webpage, if given to youtube-dl it
                     should allow to get the same result again. (It will be set
                     by YoutubeDL if it's missing)
+    categories:     A list of categories that the video falls in, for example
+                    ["Sports", "Berlin"]
 
     Unless mentioned otherwise, the fields should be Unicode strings.
 
@@ -242,10 +248,11 @@ class InfoExtractor(object):
                 url = url_or_request.get_full_url()
             except AttributeError:
                 url = url_or_request
-            if len(url) > 200:
-                h = u'___' + hashlib.md5(url.encode('utf-8')).hexdigest()
-                url = url[:200 - len(h)] + h
-            raw_filename = ('%s_%s.dump' % (video_id, url))
+            basen = '%s_%s' % (video_id, url)
+            if len(basen) > 240:
+                h = u'___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
+                basen = basen[:240 - len(h)] + h
+            raw_filename = basen + '.dump'
             filename = sanitize_filename(raw_filename, restricted=True)
             self.to_screen(u'Saving request to ' + filename)
             with open(filename, 'wb') as outf:
@@ -279,9 +286,12 @@ class InfoExtractor(object):
 
     def _download_xml(self, url_or_request, video_id,
                       note=u'Downloading XML', errnote=u'Unable to download XML',
-                      transform_source=None):
+                      transform_source=None, fatal=True):
         """Return the xml as an xml.etree.ElementTree.Element"""
-        xml_string = self._download_webpage(url_or_request, video_id, note, errnote)
+        xml_string = self._download_webpage(
+            url_or_request, video_id, note, errnote, fatal=fatal)
+        if xml_string is False:
+            return xml_string
         if transform_source:
             xml_string = transform_source(xml_string)
         return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
@@ -545,6 +555,23 @@ class InfoExtractor(object):
             )
         formats.sort(key=_formats_key)
 
+    def http_scheme(self):
+        """ Either "https:" or "https:", depending on the user's preferences """
+        return (
+            'http:'
+            if self._downloader.params.get('prefer_insecure', False)
+            else 'https:')
+
+    def _proto_relative_url(self, url, scheme=None):
+        if url is None:
+            return url
+        if url.startswith('//'):
+            if scheme is None:
+                scheme = self.http_scheme()
+            return scheme + url
+        else:
+            return url
+
 
 class SearchInfoExtractor(InfoExtractor):
     """
@@ -588,3 +615,4 @@ class SearchInfoExtractor(InfoExtractor):
     @property
     def SEARCH_KEY(self):
         return self._SEARCH_KEY
+

youtube_dl/extractor/dailymotion.py

@@ -11,8 +11,8 @@ from ..utils import (
     orderedSet,
     str_to_int,
     int_or_none,
-
     ExtractorError,
+    unescapeHTML,
 )
 
 class DailymotionBaseInfoExtractor(InfoExtractor):
@@ -188,7 +188,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
             webpage = self._download_webpage(request,
                                              id, u'Downloading page %s' % pagenum)
 
-            video_ids.extend(re.findall(r'data-id="(.+?)"', webpage))
+            video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage))
 
             if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
                 break
@@ -217,9 +217,9 @@ class DailymotionUserIE(DailymotionPlaylistIE):
         mobj = re.match(self._VALID_URL, url)
         user = mobj.group('user')
         webpage = self._download_webpage(url, user)
-        full_user = self._html_search_regex(
-            r'<a class="label" href="/%s".*?>(.*?)</' % re.escape(user),
-            webpage, u'user', flags=re.DOTALL)
+        full_user = unescapeHTML(self._html_search_regex(
+            r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
+            webpage, u'user', flags=re.DOTALL))
 
         return {
             '_type': 'playlist',

youtube_dl/extractor/empflix.py

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

youtube_dl/extractor/extremetube.py

@@ -37,7 +37,7 @@ class ExtremeTubeIE(InfoExtractor):
         webpage = self._download_webpage(req, video_id)
 
         video_title = self._html_search_regex(
-            r'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, 'title')
+            r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
         uploader = self._html_search_regex(
             r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader',
             fatal=False)

youtube_dl/extractor/facebook.py

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

youtube_dl/extractor/fc2.py

@@ -0,0 +1,60 @@
+#! -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+import hashlib
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_request,
+    compat_urlparse,
+)
+
+
+class FC2IE(InfoExtractor):
+    _VALID_URL = r'^http://video\.fc2\.com/((?P<lang>[^/]+)/)?content/(?P<id>[^/]+)'
+    IE_NAME = 'fc2'
+    _TEST = {
+        'url': 'http://video.fc2.com/en/content/20121103kUan1KHs',
+        'md5': 'a6ebe8ebe0396518689d963774a54eb7',
+        'info_dict': {
+            'id': '20121103kUan1KHs',
+            'ext': 'flv',
+            'title': 'Boxing again with Puff',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        self._downloader.cookiejar.clear_session_cookies()  # must clear
+
+        title = self._og_search_title(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+        refer = url.replace('/content/', '/a/content/')
+
+        mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
+
+        info_url = (
+            "http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&".
+            format(video_id, mimi, compat_urllib_request.quote(refer, safe='').replace('.','%2E')))
+
+        info_webpage = self._download_webpage(
+            info_url, video_id, note='Downloading info page')
+        info = compat_urlparse.parse_qs(info_webpage)
+
+        if 'err_code' in info:
+            raise ExtractorError('Error code: %s' % info['err_code'][0])
+
+        video_url = info['filepath'][0] + '?mid=' + info['mid'][0]
+
+        return {
+            'id': video_id,
+            'title': info['title'][0],
+            'url': video_url,
+            'ext': 'flv',
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/fivemin.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     compat_str,
     compat_urllib_parse,
+    ExtractorError,
 )
 
 
@@ -58,9 +59,17 @@ class FiveMinIE(InfoExtractor):
             'isPlayerSeed': 'true',
             'url': embed_url,
         })
-        info = self._download_json(
+        response = self._download_json(
             'https://syn.5min.com/handlers/SenseHandler.ashx?' + query,
-            video_id)['binding'][0]
+            video_id)
+        if not response['success']:
+            err_msg = response['errorMessage']
+            if err_msg == 'ErrorVideoUserNotGeo':
+                msg = 'Video not available from your location'
+            else:
+                msg = 'Aol said: %s' % err_msg
+            raise ExtractorError(msg, expected=True, video_id=video_id)
+        info = response['binding'][0]
 
         second_id = compat_str(int(video_id[:-2]) + 1)
         formats = []

youtube_dl/extractor/francetv.py

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

youtube_dl/extractor/funnyordie.py

@@ -4,22 +4,32 @@ import json
 import re
 
 from .common import InfoExtractor
+from ..utils import ExtractorError
 
 
 class FunnyOrDieIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
-        'file': '0732f586d7.mp4',
-        'md5': 'f647e9e90064b53b6e046e75d0241fbd',
+        'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9',
         'info_dict': {
-            'description': ('Lyrics changed to match the video. Spoken cameo '
-                'by Obscurus Lupa (from ThatGuyWithTheGlasses.com). Based on a '
-                'concept by Dustin McLean (DustFilms.com). Performed, edited, '
-                'and written by David A. Scott.'),
+            'id': '0732f586d7',
+            'ext': 'mp4',
             'title': 'Heart-Shaped Box: Literal Video Version',
+            'description': 'md5:ea09a01bc9a1c46d9ab696c01747c338',
+            'thumbnail': 're:^http:.*\.jpg$',
         },
-    }
+    }, {
+        'url': 'http://www.funnyordie.com/embed/e402820827',
+        'md5': 'ff4d83318f89776ed0250634cfaa8d36',
+        'info_dict': {
+            'id': 'e402820827',
+            'ext': 'mp4',
+            'title': 'Please Use This Song (Jon Lajoie)',
+            'description': 'md5:2ed27d364f5a805a6dba199faaf6681d',
+            'thumbnail': 're:^http:.*\.jpg$',
+        },
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -27,27 +37,34 @@ class FunnyOrDieIE(InfoExtractor):
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
 
-        video_url = self._search_regex(
-            [r'type="video/mp4" src="(.*?)"', r'src="([^>]*?)" type=\'video/mp4\''],
-            webpage, 'video URL', flags=re.DOTALL)
+        links = re.findall(r'<source src="([^"]+/v)\d+\.([^"]+)" type=\'video', webpage)
+        if not links:
+            raise ExtractorError('No media links available for %s' % video_id)
 
-        if mobj.group('type') == 'embed':
-            post_json = self._search_regex(
-                r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details')
-            post = json.loads(post_json)
-            title = post['name']
-            description = post.get('description')
-            thumbnail = post.get('picture')
-        else:
-            title = self._og_search_title(webpage)
-            description = self._og_search_description(webpage)
-            thumbnail = None
+        links.sort(key=lambda link: 1 if link[1] == 'mp4' else 0)
+
+        bitrates = self._html_search_regex(r'<source src="[^"]+/v,((?:\d+,)+)\.mp4\.csmil', webpage, 'video bitrates')
+        bitrates = [int(b) for b in bitrates.rstrip(',').split(',')]
+        bitrates.sort()
+
+        formats = []
+
+        for bitrate in bitrates:
+            for link in links:
+                formats.append({
+                    'url': '%s%d.%s' % (link[0], bitrate, link[1]),
+                    'format_id': '%s-%d' % (link[1], bitrate),
+                    'vbr': bitrate,
+                })
+
+        post_json = self._search_regex(
+            r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details')
+        post = json.loads(post_json)
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
+            'title': post['name'],
+            'description': post.get('description'),
+            'thumbnail': post.get('picture'),
+            'formats': formats,
         }

youtube_dl/extractor/gamekings.py

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

youtube_dl/extractor/gamespot.py

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

youtube_dl/extractor/generic.py

@@ -248,6 +248,18 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Honda’s  New Asimo Robot Is More Human Than Ever',
             }
+        },
+        # Dailymotion embed
+        {
+            'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
+            'md5': '441aeeb82eb72c422c7f14ec533999cd',
+            'info_dict': {
+                'id': 'k2mm4bCdJ6CQ2i7c8o2',
+                'ext': 'mp4',
+                'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
+                'uploader': 'Spi0n',
+            },
+            'add_ie': ['Dailymotion'],
         }
     ]
 
@@ -333,6 +345,12 @@ class GenericIE(InfoExtractor):
         }
 
     def _real_extract(self, url):
+        if url.startswith('//'):
+            return {
+                '_type': 'url',
+                'url': self.http_scheme() + url,
+            }
+
         parsed_url = compat_urlparse.urlparse(url)
         if not parsed_url.scheme:
             default_search = self._downloader.params.get('default_search')
@@ -345,8 +363,13 @@ class GenericIE(InfoExtractor):
                     return self.url_result('http://' + url)
                 else:
                     if default_search == 'auto_warning':
-                        self._downloader.report_warning(
-                            'Falling back to youtube search for  %s . Set --default-search to "auto" to suppress this warning.' % url)
+                        if re.match(r'^(?:url|URL)$', url):
+                            raise ExtractorError(
+                                'Invalid URL:  %r . Call youtube-dl like this:  youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc"  ' % url,
+                                expected=True)
+                        else:
+                            self._downloader.report_warning(
+                                'Falling back to youtube search for  %s . Set --default-search to "auto" to suppress this warning.' % url)
                     return self.url_result('ytsearch:' + url)
             else:
                 assert ':' in default_search
@@ -469,7 +492,7 @@ class GenericIE(InfoExtractor):
         matches = re.findall(
             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
         if matches:
-            urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Dailymotion')
+            urlrs = [self.url_result(unescapeHTML(tuppl[1]))
                      for tuppl in matches]
             return self.playlist_result(
                 urlrs, playlist_id=video_id, playlist_title=video_title)
@@ -531,7 +554,7 @@ class GenericIE(InfoExtractor):
             return OoyalaIE._build_url_result(mobj.group('ec'))
 
         # Look for Aparat videos
-        mobj = re.search(r'<iframe src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
+        mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
         if mobj is not None:
             return self.url_result(mobj.group(1), 'Aparat')
 
@@ -542,7 +565,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded NovaMov-based player
         mobj = re.search(
-            r'''(?x)<iframe[^>]+?src=(["\'])
+            r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
                     (?P<url>http://(?:(?:embed|www)\.)?
                         (?:novamov\.com|
                            nowvideo\.(?:ch|sx|eu|at|ag|co)|
@@ -615,65 +638,86 @@ class GenericIE(InfoExtractor):
         if smotri_url:
             return self.url_result(smotri_url, 'Smotri')
 
-        # Start with something easy: JW Player in SWFObject
-        mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
-        if mobj is None:
-            # Look for gorilla-vid style embedding
-            mobj = re.search(r'(?s)(?:jw_plugins|JWPlayerOptions).*?file\s*:\s*["\'](.*?)["\']', webpage)
-        if mobj is None:
-            # Broaden the search a little bit
-            mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
-        if mobj is None:
-            # Broaden the search a little bit: JWPlayer JS loader
-            mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
+        # Look for embeded soundcloud player
+        mobj = re.search(
+            r'<iframe src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
+            webpage)
+        if mobj is not None:
+            url = unescapeHTML(mobj.group('url'))
+            return self.url_result(url)
 
-        if mobj is None:
+        # Start with something easy: JW Player in SWFObject
+        found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+        if not found:
+            # Look for gorilla-vid style embedding
+            found = re.findall(r'''(?sx)
+                (?:
+                    jw_plugins|
+                    JWPlayerOptions|
+                    jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
+                )
+                .*?file\s*:\s*["\'](.*?)["\']''', webpage)
+        if not found:
+            # Broaden the search a little bit
+            found = re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+        if not found:
+            # Broaden the findall a little bit: JWPlayer JS loader
+            found = re.findall(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
+        if not found:
             # Try to find twitter cards info
-            mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
-        if mobj is None:
+            found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
+        if not found:
             # We look for Open Graph info:
             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
-            m_video_type = re.search(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
+            m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
             if m_video_type is not None:
-                mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
-        if mobj is None:
+                found = re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
+        if not found:
             # HTML5 video
-            mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
-        if mobj is None:
-            mobj = re.search(
+            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage)
+        if not found:
+            found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
                 r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'([^\']+)\'"',
                 webpage)
-            if mobj:
-                new_url = mobj.group(1)
+            if found:
+                new_url = found.group(1)
                 self.report_following_redirect(new_url)
                 return {
                     '_type': 'url',
                     'url': new_url,
                 }
-        if mobj is None:
+        if not found:
             raise ExtractorError('Unsupported URL: %s' % url)
 
-        # It's possible that one of the regexes
-        # matched, but returned an empty group:
-        if mobj.group(1) is None:
-            raise ExtractorError('Did not find a valid video URL at %s' % url)
+        entries = []
+        for video_url in found:
+            video_url = compat_urlparse.urljoin(url, video_url)
+            video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
 
-        video_url = mobj.group(1)
-        video_url = compat_urlparse.urljoin(url, video_url)
-        video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
+            # Sometimes, jwplayer extraction will result in a YouTube URL
+            if YoutubeIE.suitable(video_url):
+                entries.append(self.url_result(video_url, 'Youtube'))
+                continue
 
-        # Sometimes, jwplayer extraction will result in a YouTube URL
-        if YoutubeIE.suitable(video_url):
-            return self.url_result(video_url, 'Youtube')
+            # here's a fun little line of code for you:
+            video_id = os.path.splitext(video_id)[0]
 
-        # here's a fun little line of code for you:
-        video_id = os.path.splitext(video_id)[0]
+            entries.append({
+                'id': video_id,
+                'url': video_url,
+                'uploader': video_uploader,
+                'title': video_title,
+            })
+
+        if len(entries) == 1:
+            return entries[0]
+        else:
+            for num, e in enumerate(entries, start=1):
+                e['title'] = '%s (%d)' % (e['title'], num)
+            return {
+                '_type': 'playlist',
+                'entries': entries,
+            }
 
-        return {
-            'id': video_id,
-            'url': video_url,
-            'uploader': video_uploader,
-            'title': video_title,
-        }

youtube_dl/extractor/hentaistigma.py

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

youtube_dl/extractor/iconosquare.py

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

youtube_dl/extractor/ivi.py

@@ -33,14 +33,14 @@ class IviIE(InfoExtractor):
         },
         # Serial's serie
         {
-            'url': 'http://www.ivi.ru/watch/dezhurnyi_angel/74791',
-            'md5': '3e6cc9a848c1d2ebcc6476444967baa9',
+            'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549',
+            'md5': '221f56b35e3ed815fde2df71032f4b3e',
             'info_dict': {
-                'id': '74791',
+                'id': '9549',
                 'ext': 'mp4',
-                'title': 'Дежурный ангел - 1 серия',
-                'duration': 2490,
-                'thumbnail': 'http://thumbs.ivi.ru/f7.vcp.digitalaccess.ru/contents/8/e/bc2f6c2b6e5d291152fdd32c059141.jpg',
+                'title': 'Двое из ларца - Серия 1',
+                'duration': 2655,
+                'thumbnail': 'http://thumbs.ivi.ru/f15.vcp.digitalaccess.ru/contents/8/4/0068dc0677041f3336b7c2baad8fc0.jpg',
             },
             'skip': 'Only works from Russia',
          }

youtube_dl/extractor/jukebox.py

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

youtube_dl/extractor/ku6.py

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

youtube_dl/extractor/mailru.py

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

youtube_dl/extractor/mixcloud.py

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

youtube_dl/extractor/moviezine.py

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

youtube_dl/extractor/mtv.py

@@ -80,6 +80,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
                                 })
             except (KeyError, TypeError):
                 raise ExtractorError('Invalid rendition field.')
+        self._sort_formats(formats)
         return formats
 
     def _get_video_info(self, itemdoc):

youtube_dl/extractor/naver.py

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

youtube_dl/extractor/nbc.py

@@ -1,6 +1,7 @@
 from __future__ import unicode_literals
 
 import re
+import json
 
 from .common import InfoExtractor
 from ..utils import find_xpath_attr, compat_str
@@ -31,30 +32,68 @@ class NBCIE(InfoExtractor):
 
 
 class NBCNewsIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
+    _VALID_URL = r'''(?x)https?://www\.nbcnews\.com/
+        ((video/.+?/(?P<id>\d+))|
+        (feature/[^/]+/(?P<title>.+)))
+        '''
 
-    _TEST = {
-        'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
-        'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
-        'info_dict': {
-            'id': '52753292',
-            'ext': 'flv',
-            'title': 'Crew emerges after four-month Mars food study',
-            'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
+    _TESTS = [
+        {
+            'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
+            'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
+            'info_dict': {
+                'id': '52753292',
+                'ext': 'flv',
+                'title': 'Crew emerges after four-month Mars food study',
+                'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
+            },
         },
-    }
+        {
+            'url': 'http://www.nbcnews.com/feature/edward-snowden-interview/how-twitter-reacted-snowden-interview-n117236',
+            'md5': 'b2421750c9f260783721d898f4c42063',
+            'info_dict': {
+                'id': 'I1wpAI_zmhsQ',
+                'ext': 'flv',
+                'title': 'How Twitter Reacted To The Snowden Interview',
+                'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
+            },
+            'add_ie': ['ThePlatform'],
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
-        info = all_info.find('video')
+        if video_id is not None:
+            all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
+            info = all_info.find('video')
 
-        return {
-            'id': video_id,
-            'title': info.find('headline').text,
-            'ext': 'flv',
-            'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
-            'description': compat_str(info.find('caption').text),
-            'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
-        }
+            return {
+                'id': video_id,
+                'title': info.find('headline').text,
+                'ext': 'flv',
+                'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
+                'description': compat_str(info.find('caption').text),
+                'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
+            }
+        else:
+            # "feature" pages use theplatform.com
+            title = mobj.group('title')
+            webpage = self._download_webpage(url, title)
+            bootstrap_json = self._search_regex(
+                r'var bootstrapJson = ({.+})\s*$', webpage, 'bootstrap json',
+                flags=re.MULTILINE)
+            bootstrap = json.loads(bootstrap_json)
+            info = bootstrap['results'][0]['video']
+            playlist_url = info['fallbackPlaylistUrl'] + '?form=MPXNBCNewsAPI'
+            mpxid = info['mpxId']
+            all_videos = self._download_json(playlist_url, title)['videos']
+            # The response contains additional videos
+            info = next(v for v in all_videos if v['mpxId'] == mpxid)
+
+            return {
+                '_type': 'url',
+                # We get the best quality video
+                'url': info['videoAssets'][-1]['publicUrl'],
+                'ie_key': 'ThePlatform',
+            }

youtube_dl/extractor/ndr.py

@@ -4,7 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    qualities,
+)
 
 
 class NDRIE(InfoExtractor):
@@ -45,17 +49,16 @@ class NDRIE(InfoExtractor):
 
         page = self._download_webpage(url, video_id, 'Downloading page')
 
-        title = self._og_search_title(page)
+        title = self._og_search_title(page).strip()
         description = self._og_search_description(page)
+        if description:
+            description = description.strip()
 
-        mobj = re.search(
-            r'<div class="duration"><span class="min">(?P<minutes>\d+)</span>:<span class="sec">(?P<seconds>\d+)</span></div>',
-            page)
-        duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+        duration = int_or_none(self._html_search_regex(r'duration: (\d+),\n', page, 'duration', fatal=False))
 
         formats = []
 
-        mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
+        mp3_url = re.search(r'''\{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
         if mp3_url:
             formats.append({
                 'url': mp3_url.group('audio'),
@@ -64,13 +67,15 @@ class NDRIE(InfoExtractor):
 
         thumbnail = None
 
-        video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
+        video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
         if video_url:
-            thumbnail = self._html_search_regex(r'(?m)title: "NDR PLAYER",\s*poster: "([^"]+)",',
-                page, 'thumbnail', fatal=False)
-            if thumbnail:
-                thumbnail = 'http://www.ndr.de' + thumbnail
-            for format_id in ['lo', 'hi', 'hq']:
+            thumbnails = re.findall(r'''\d+: \{src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
+            if thumbnails:
+                quality_key = qualities(['xs', 's', 'm', 'l', 'xl'])
+                largest = max(thumbnails, key=lambda thumb: quality_key(thumb[1]))
+                thumbnail = 'http://www.ndr.de' + largest[0]
+
+            for format_id in 'lo', 'hi', 'hq':
                 formats.append({
                     'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
                     'format_id': format_id,

youtube_dl/extractor/newstube.py

@@ -0,0 +1,87 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class NewstubeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?newstube\.ru/media/(?P<id>.+)'
+    _TEST = {
+        'url': 'http://newstube.ru/media/na-korable-progress-prodolzhaetsya-testirovanie-sistemy-kurs',
+        'info_dict': {
+            'id': 'd156a237-a6e9-4111-a682-039995f721f1',
+            'ext': 'flv',
+            'title': 'На корабле «Прогресс» продолжается тестирование системы «Курс»',
+            'description': 'md5:d0cbe7b4a6f600552617e48548d5dc77',
+            'duration': 20.04,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id, 'Downloading page')
+
+        video_guid = self._html_search_regex(
+            r'<meta property="og:video" content="https?://(?:www\.)?newstube\.ru/freshplayer\.swf\?guid=(?P<guid>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
+            page, 'video GUID')
+
+        player = self._download_xml(
+            'http://p.newstube.ru/v2/player.asmx/GetAutoPlayInfo6?state=&url=%s&sessionId=&id=%s&placement=profile&location=n2' % (url, video_guid),
+            video_guid, 'Downloading player XML')
+
+        def ns(s):
+            return s.replace('/', '/%(ns)s') % {'ns': '{http://app1.newstube.ru/N2SiteWS/player.asmx}'}
+
+        session_id = player.find(ns('./SessionId')).text
+        media_info = player.find(ns('./Medias/MediaInfo'))
+        title = media_info.find(ns('./Name')).text
+        description = self._og_search_description(page)
+        thumbnail = media_info.find(ns('./KeyFrame')).text
+        duration = int(media_info.find(ns('./Duration')).text) / 1000.0
+
+        formats = []
+
+        for stream_info in media_info.findall(ns('./Streams/StreamInfo')):
+            media_location = stream_info.find(ns('./MediaLocation'))
+            if media_location is None:
+                continue
+
+            server = media_location.find(ns('./Server')).text
+            app = media_location.find(ns('./App')).text
+            media_id = stream_info.find(ns('./Id')).text
+            quality_id = stream_info.find(ns('./QualityId')).text
+            name = stream_info.find(ns('./Name')).text
+            width = int(stream_info.find(ns('./Width')).text)
+            height = int(stream_info.find(ns('./Height')).text)
+
+            formats.append({
+                'url': 'rtmp://%s/%s' % (server, app),
+                'app': app,
+                'play_path': '01/%s' % video_guid.upper(),
+                'rtmp_conn': ['S:%s' % session_id, 'S:%s' % media_id, 'S:n2'],
+                'page_url': url,
+                'ext': 'flv',
+                'format_id': quality_id,
+                'format_note': name,
+                'width': width,
+                'height': height,
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_guid,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/nfb.py

@@ -73,14 +73,16 @@ class NFBIE(InfoExtractor):
                 title = media.find('title').text
                 description = media.find('description').text
                 # It seems assets always go from lower to better quality, so no need to sort
-                formats = [{
-                    'url': x.find('default/streamerURI').text,
-                    'app': x.find('default/streamerURI').text.split('/', 3)[3],
-                    'play_path': x.find('default/url').text,
-                    'rtmp_live': False,
-                    'ext': 'mp4',
-                    'format_id': x.get('quality'),
-                } for x in media.findall('assets/asset')]
+                for asset in media.findall('assets/asset'):
+                    for x in asset:
+                        formats.append({
+                            'url': x.find('streamerURI').text,
+                            'app': x.find('streamerURI').text.split('/', 3)[3],
+                            'play_path': x.find('url').text,
+                            'rtmp_live': False,
+                            'ext': 'mp4',
+                            'format_id': '%s-%s' % (x.tag, asset.get('quality')),
+                        })
 
         return {
             'id': video_id,

youtube_dl/extractor/ninegag.py

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

youtube_dl/extractor/noco.py

@@ -26,7 +26,8 @@ class NocoIE(InfoExtractor):
             'uploader': 'Nolife',
             'uploader_id': 'NOL',
             'duration': 2851.2,
-        }
+        },
+        'skip': 'Requires noco account',
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/nowness.py

@@ -4,9 +4,7 @@ import re
 
 from .brightcove import BrightcoveIE
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
+from ..utils import ExtractorError
 
 
 class NownessIE(InfoExtractor):
@@ -14,9 +12,10 @@ class NownessIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation',
-        'file': '2520295746001.mp4',
-        'md5': '0ece2f70a7bd252c7b00f3070182d418',
+        'md5': '068bc0202558c2e391924cb8cc470676',
         'info_dict': {
+            'id': '2520295746001',
+            'ext': 'mp4',
             'description': 'Candor: The Art of Gesticulation',
             'uploader': 'Nowness',
             'title': 'Candor: The Art of Gesticulation',

youtube_dl/extractor/nrk.py

@@ -0,0 +1,145 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    unified_strdate,
+)
+
+
+class NRKIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?nrk\.no/(?:video|lyd)/[^/]+/(?P<id>[\dA-F]{16})'
+
+    _TESTS = [
+        {
+            'url': 'http://www.nrk.no/video/dompap_og_andre_fugler_i_piip_show/D0FA54B5C8B6CE59/emne/piipshow/',
+            'md5': 'a6eac35052f3b242bb6bb7f43aed5886',
+            'info_dict': {
+                'id': '150533',
+                'ext': 'flv',
+                'title': 'Dompap og andre fugler i Piip-Show',
+                'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f'
+            }
+        },
+        {
+            'url': 'http://www.nrk.no/lyd/lyd_av_oppleser_for_blinde/AEFDDD5473BA0198/',
+            'md5': '3471f2a51718195164e88f46bf427668',
+            'info_dict': {
+                'id': '154915',
+                'ext': 'flv',
+                'title': 'Slik høres internett ut når du er blind',
+                'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id)
+
+        video_id = self._html_search_regex(r'<div class="nrk-video" data-nrk-id="(\d+)">', page, 'video id')
+
+        data = self._download_json(
+            'http://v7.psapi.nrk.no/mediaelement/%s' % video_id, video_id, 'Downloading media JSON')
+
+        if data['usageRights']['isGeoBlocked']:
+            raise ExtractorError('NRK har ikke rettig-heter til å vise dette programmet utenfor Norge', expected=True)
+
+        video_url = data['mediaUrl'] + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124'
+
+        images = data.get('images')
+        if images:
+            thumbnails = images['webImages']
+            thumbnails.sort(key=lambda image: image['pixelWidth'])
+            thumbnail = thumbnails[-1]['imageUrl']
+        else:
+            thumbnail = None
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'flv',
+            'title': data['title'],
+            'description': data['description'],
+            'thumbnail': thumbnail,
+        }
+
+
+class NRKTVIE(InfoExtractor):
+    _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-z]{4}\d{8})'
+
+    _TESTS = [
+        {
+            'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/muhh48000314/23-05-2014',
+            'md5': '7b96112fbae1faf09a6f9ae1aff6cb84',
+            'info_dict': {
+                'id': 'muhh48000314',
+                'ext': 'flv',
+                'title': '20 spørsmål',
+                'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
+                'upload_date': '20140523',
+                'duration': 1741.52,
+            }
+        },
+        {
+            'url': 'http://tv.nrk.no/program/mdfp15000514',
+            'md5': '383650ece2b25ecec996ad7b5bb2a384',
+            'info_dict': {
+                'id': 'mdfp15000514',
+                'ext': 'flv',
+                'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting',
+                'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
+                'upload_date': '20140524',
+                'duration': 4605.0,
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id)
+
+        title = self._html_search_meta('title', page, 'title')
+        description = self._html_search_meta('description', page, 'description')
+        thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False)
+        upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False))
+        duration = self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False)
+        if duration:
+            duration = float(duration)
+
+        formats = []
+
+        f4m_url = re.search(r'data-media="([^"]+)"', page)
+        if f4m_url:
+            formats.append({
+                'url': f4m_url.group(1) + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
+                'format_id': 'f4m',
+                'ext': 'flv',
+            })
+
+        m3u8_url = re.search(r'data-hls-media="([^"]+)"', page)
+        if m3u8_url:
+            formats.append({
+                'url': m3u8_url.group(1),
+                'format_id': 'm3u8',
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/ntv.py

@@ -24,9 +24,9 @@ class NTVIE(InfoExtractor):
                 'duration': 136,
             },
             'params': {
-                    # rtmp download
-                    'skip_download': True,
-                },
+                # rtmp download
+                'skip_download': True,
+            },
         },
         {
             'url': 'http://www.ntv.ru/video/novosti/750370/',
@@ -38,9 +38,9 @@ class NTVIE(InfoExtractor):
                 'duration': 172,
             },
             'params': {
-                    # rtmp download
-                    'skip_download': True,
-                },
+                # rtmp download
+                'skip_download': True,
+            },
         },
         {
             'url': 'http://www.ntv.ru/peredacha/segodnya/m23700/o232416',
@@ -52,9 +52,9 @@ class NTVIE(InfoExtractor):
                 'duration': 1496,
             },
             'params': {
-                    # rtmp download
-                    'skip_download': True,
-                },
+                # rtmp download
+                'skip_download': True,
+            },
         },
         {
             'url': 'http://www.ntv.ru/kino/Koma_film',
@@ -66,9 +66,9 @@ class NTVIE(InfoExtractor):
                 'duration': 5592,
             },
             'params': {
-                    # rtmp download
-                    'skip_download': True,
-                },
+                # rtmp download
+                'skip_download': True,
+            },
         },
         {
             'url': 'http://www.ntv.ru/serial/Delo_vrachey/m31760/o233916/',
@@ -80,33 +80,25 @@ class NTVIE(InfoExtractor):
                 'duration': 2590,
             },
             'params': {
-                    # rtmp download
-                    'skip_download': True,
-                },
+                # rtmp download
+                'skip_download': True,
+            },
         },
     ]
 
     _VIDEO_ID_REGEXES = [
         r'<meta property="og:url" content="http://www\.ntv\.ru/video/(\d+)',
         r'<video embed=[^>]+><id>(\d+)</id>',
-        r'<video restriction[^>]+><key>(\d+)</key>'
+        r'<video restriction[^>]+><key>(\d+)</key>',
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
-        page = self._download_webpage(url, video_id, 'Downloading page')
+        page = self._download_webpage(url, video_id)
 
-        for pattern in self._VIDEO_ID_REGEXES:
-            mobj = re.search(pattern, page)
-            if mobj:
-                break
-
-        if not mobj:
-            raise ExtractorError('No media links available for %s' % video_id)
-
-        video_id = mobj.group(1)
+        video_id = self._html_search_regex(self._VIDEO_ID_REGEXES, page, 'video id')
 
         player = self._download_xml('http://www.ntv.ru/vi%s/' % video_id, video_id, 'Downloading video XML')
         title = unescapeHTML(player.find('./data/title').text)
@@ -124,7 +116,7 @@ class NTVIE(InfoExtractor):
             '7': 'video2',
         }
 
-        app = apps[puid22] if puid22 in apps else apps['4']
+        app = apps.get(puid22, apps['4'])
 
         formats = []
         for format_id in ['', 'hi', 'webm']:

youtube_dl/extractor/nuvid.py

@@ -0,0 +1,48 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class NuvidIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://m.nuvid.com/video/1310741/',
+        'md5': 'eab207b7ac4fccfb4e23c86201f11277',
+        'info_dict': {
+            'id': '1310741',
+            'ext': 'mp4',
+            "title": "Horny babes show their awesome bodeis and",
+            "age_limit": 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        murl = url.replace('://www.', '://m.')
+        webpage = self._download_webpage(murl, video_id)
+
+        title = self._html_search_regex(
+            r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>',
+            webpage, 'title').strip()
+
+        url_end = self._html_search_regex(
+            r'href="(/[^"]+)"[^>]*data-link_type="mp4"',
+            webpage, 'video_url')
+        video_url = 'http://m.nuvid.com' + url_end
+
+        thumbnail = self._html_search_regex(
+            r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"',
+            webpage, 'thumbnail URL', fatal=False)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            'thumbnail': thumbnail,
+            'age_limit': 18,
+        }

youtube_dl/extractor/nytimes.py

@@ -0,0 +1,77 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import parse_iso8601
+
+
+class NYTimesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nytimes\.com/video/(?:[^/]+/)+(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
+        'md5': '18a525a510f942ada2720db5f31644c0',
+        'info_dict': {
+            'id': '100000002847155',
+            'ext': 'mov',
+            'title': 'Verbatim: What Is a Photocopier?',
+            'description': 'md5:93603dada88ddbda9395632fdc5da260',
+            'timestamp': 1398631707,
+            'upload_date': '20140427',
+            'uploader': 'Brett Weiner',
+            'duration': 419,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        video_data = self._download_json(
+            'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id, video_id, 'Downloading video JSON')
+
+        title = video_data['headline']
+        description = video_data['summary']
+        duration = video_data['duration'] / 1000.0
+
+        uploader = video_data['byline']
+        timestamp = parse_iso8601(video_data['publication_date'][:-8])
+
+        def get_file_size(file_size):
+            if isinstance(file_size, int):
+                return file_size
+            elif isinstance(file_size, dict):
+                return int(file_size.get('value', 0))
+            else:
+                return 0
+
+        formats = [
+            {
+                'url': video['url'],
+                'format_id': video['type'],
+                'vcodec': video['video_codec'],
+                'width': video['width'],
+                'height': video['height'],
+                'filesize': get_file_size(video['fileSize']),
+            } for video in video_data['renditions']
+        ]
+        self._sort_formats(formats)
+
+        thumbnails = [
+            {
+                'url': 'http://www.nytimes.com/%s' % image['url'],
+                'resolution': '%dx%d' % (image['width'], image['height']),
+            } for image in video_data['images']
+        ]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'duration': duration,
+            'formats': formats,
+            'thumbnails': thumbnails,
+        }

youtube_dl/extractor/photobucket.py

@@ -1,10 +1,10 @@
 from __future__ import unicode_literals
 
-import datetime
 import json
 import re
 
 from .common import InfoExtractor
+from ..utils import compat_urllib_parse
 
 
 class PhotobucketIE(InfoExtractor):
@@ -14,6 +14,7 @@ class PhotobucketIE(InfoExtractor):
         'file': 'zpsc0c3b9fa.mp4',
         'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99',
         'info_dict': {
+            'timestamp': 1367669341,
             'upload_date': '20130504',
             'uploader': 'rachaneronas',
             'title': 'Tired of Link Building? Try BacklinkMyDomain.com!',
@@ -32,11 +33,12 @@ class PhotobucketIE(InfoExtractor):
         info_json = self._search_regex(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (.*?)\);',
             webpage, 'info json')
         info = json.loads(info_json)
+        url = compat_urllib_parse.unquote(self._html_search_regex(r'file=(.+\.mp4)', info['linkcodes']['html'], 'url'))
         return {
             'id': video_id,
-            'url': info['downloadUrl'],
+            'url': url,
             'uploader': info['username'],
-            'upload_date': datetime.date.fromtimestamp(info['creationDate']).strftime('%Y%m%d'),
+            'timestamp': info['creationDate'],
             'title': info['title'],
             'ext': video_extension,
             'thumbnail': info['thumbUrl'],

youtube_dl/extractor/pornhub.py

@@ -45,7 +45,7 @@ class PornHubIE(InfoExtractor):
 
         video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
         video_uploader = self._html_search_regex(
-            r'(?s)<div class="video-info-row">\s*From:&nbsp;.+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<',
+            r'(?s)From:&nbsp;.+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<',
             webpage, 'uploader', fatal=False)
         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
         if thumbnail:

youtube_dl/extractor/prosiebensat1.py

@@ -8,8 +8,6 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
     unified_strdate,
-    clean_html,
-    RegexNotFoundError,
 )
 
 
@@ -188,16 +186,7 @@ class ProSiebenSat1IE(InfoExtractor):
 
         page = self._download_webpage(url, video_id, 'Downloading page')
 
-        def extract(patterns, name, page, fatal=False):
-            for pattern in patterns:
-                mobj = re.search(pattern, page)
-                if mobj:
-                    return clean_html(mobj.group(1))
-            if fatal:
-                raise RegexNotFoundError(u'Unable to extract %s' % name)
-            return None
-
-        clip_id = extract(self._CLIPID_REGEXES, 'clip id', page, fatal=True)
+        clip_id = self._html_search_regex(self._CLIPID_REGEXES, page, 'clip id')
 
         access_token = 'testclient'
         client_name = 'kolibri-1.2.5'
@@ -246,13 +235,12 @@ class ProSiebenSat1IE(InfoExtractor):
 
         urls = self._download_json(url_api_url, clip_id, 'Downloading urls JSON')
 
-        title = extract(self._TITLE_REGEXES, 'title', page, fatal=True)
-        description = extract(self._DESCRIPTION_REGEXES, 'description', page)
+        title = self._html_search_regex(self._TITLE_REGEXES, page, 'title')
+        description = self._html_search_regex(self._DESCRIPTION_REGEXES, page, 'description', fatal=False)
         thumbnail = self._og_search_thumbnail(page)
 
-        upload_date = extract(self._UPLOAD_DATE_REGEXES, 'upload date', page)
-        if upload_date:
-            upload_date = unified_strdate(upload_date)
+        upload_date = unified_strdate(self._html_search_regex(
+            self._UPLOAD_DATE_REGEXES, page, 'upload date', fatal=False))
 
         formats = []
 

youtube_dl/extractor/rtbf.py

@@ -0,0 +1,49 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class RTBFIE(InfoExtractor):
+    _VALID_URL = r'https?://www.rtbf.be/video/[^\?]+\?id=(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
+        'md5': '799f334ddf2c0a582ba80c44655be570',
+        'info_dict': {
+            'id': '1921274',
+            'ext': 'mp4',
+            'title': 'Les Diables au coeur (épisode 2)',
+            'description': 'Football - Diables Rouges',
+            'duration': 3099,
+            'timestamp': 1398456336,
+            'upload_date': '20140425',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage('https://www.rtbf.be/video/embed?id=%s' % video_id, video_id)
+
+        data = json.loads(self._html_search_regex(
+            r'<div class="js-player-embed" data-video="([^"]+)"', page, 'data video'))['data']
+
+        video_url = data.get('downloadUrl') or data.get('url')
+
+        if data['provider'].lower() == 'youtube':
+            return self.url_result(video_url, 'Youtube')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': data['title'],
+            'description': data.get('description') or data.get('subtitle'),
+            'thumbnail': data['thumbnail']['large'],
+            'duration': data.get('duration') or data.get('realDuration'),
+            'timestamp': data['created'],
+            'view_count': data['viewCount'],
+        }

youtube_dl/extractor/rutube.py

@@ -47,7 +47,7 @@ class RutubeIE(InfoExtractor):
         author = video.get('author') or {}
 
         options = self._download_json(
-            'http://rutube.ru/api/play/options/%s/?format=json' %video_id,
+            'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
             video_id, 'Downloading options JSON')
 
         m3u8_url = options['video_balancer'].get('m3u8')

youtube_dl/extractor/rutv.py

@@ -12,7 +12,12 @@ from ..utils import (
 
 class RUTVIE(InfoExtractor):
     IE_DESC = 'RUTV.RU'
-    _VALID_URL = r'https?://player\.(?:rutv\.ru|vgtrk\.com)/(?:flash2v/container\.swf\?id=|iframe/(?P<type>swf|video|live)/id/)(?P<id>\d+)'
+    _VALID_URL = r'''(?x)
+        https?://player\.(?:rutv\.ru|vgtrk\.com)/
+            (?P<path>flash2v/container\.swf\?id=
+            |iframe/(?P<type>swf|video|live)/id/
+            |index/iframe/cast_id/)
+            (?P<id>\d+)'''
 
     _TESTS = [
         {
@@ -90,7 +95,7 @@ class RUTVIE(InfoExtractor):
     @classmethod
     def _extract_url(cls, webpage):
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.rutv\.ru/iframe/(?:swf|video|live)/id/.+?)\1', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.rutv\.ru/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage)
         if mobj:
             return mobj.group('url')
 
@@ -103,10 +108,16 @@ class RUTVIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        video_type = mobj.group('type')
+        video_path = mobj.group('path')
 
-        if not video_type or video_type == 'swf':
+        if video_path.startswith('flash2v'):
             video_type = 'video'
+        elif video_path.startswith('iframe'):
+            video_type = mobj.group('type')
+            if video_type == 'swf':
+                video_type = 'video'
+        elif video_path.startswith('index/iframe/cast_id'):
+            video_type = 'live'
 
         json_data = self._download_json(
             'http://player.rutv.ru/iframe/%splay/id/%s' % ('live-' if video_type == 'live' else '', video_id),

youtube_dl/extractor/scivee.py

@@ -0,0 +1,56 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class SciVeeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?scivee\.tv/node/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.scivee.tv/node/62352',
+        'md5': 'b16699b74c9e6a120f6772a44960304f',
+        'info_dict': {
+            'id': '62352',
+            'ext': 'mp4',
+            'title': 'Adam Arkin at the 2014 DOE JGI Genomics of Energy & Environment Meeting',
+            'description': 'md5:81f1710638e11a481358fab1b11059d7',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        # annotations XML is malformed
+        annotations = self._download_webpage(
+            'http://www.scivee.tv/assets/annotations/%s' % video_id, video_id, 'Downloading annotations')
+
+        title = self._html_search_regex(r'<title>([^<]+)</title>', annotations, 'title')
+        description = self._html_search_regex(r'<abstract>([^<]+)</abstract>', annotations, 'abstract', fatal=False)
+        filesize = int_or_none(self._html_search_regex(
+            r'<filesize>([^<]+)</filesize>', annotations, 'filesize', fatal=False))
+
+        formats = [
+            {
+                'url': 'http://www.scivee.tv/assets/audio/%s' % video_id,
+                'ext': 'mp3',
+                'format_id': 'audio',
+            },
+            {
+                'url': 'http://www.scivee.tv/assets/video/%s' % video_id,
+                'ext': 'mp4',
+                'format_id': 'video',
+                'filesize': filesize,
+            },
+        ]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': 'http://www.scivee.tv/assets/videothumb/%s' % video_id,
+            'formats': formats,
+        }

youtube_dl/extractor/slutload.py

@@ -0,0 +1,47 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+
+class SlutloadIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
+    _TEST = {
+        'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
+        'md5': '0cf531ae8006b530bd9df947a6a0df77',
+        'info_dict': {
+            'id': 'TD73btpBqSxc',
+            'ext': 'mp4',
+            "title": "virginie baisee en cam",
+            "age_limit": 18,
+            'thumbnail': 're:https?://.*?\.jpg'
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
+            webpage, 'title').strip()
+
+        video_url = self._html_search_regex(
+            r'(?s)<div id="vidPlayer"\s+data-url="([^"]+)"',
+            webpage, 'video URL')
+        thumbnail = self._html_search_regex(
+            r'(?s)<div id="vidPlayer"\s+.*?previewer-file="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': video_title,
+            'thumbnail': thumbnail,
+            'age_limit': 18
+        }

youtube_dl/extractor/soundcloud.py

@@ -12,6 +12,7 @@ from ..utils import (
     compat_urllib_parse,
 
     ExtractorError,
+    int_or_none,
     unified_strdate,
 )
 
@@ -25,7 +26,7 @@ class SoundcloudIE(InfoExtractor):
        of the stream token and uid
      """
 
-    _VALID_URL = r'''^(?:https?://)?
+    _VALID_URL = r'''(?x)^(?:https?://)?
                     (?:(?:(?:www\.|m\.)?soundcloud\.com/
                             (?P<uploader>[\w\d-]+)/
                             (?!sets/)(?P<title>[\w\d-]+)/?
@@ -44,7 +45,8 @@ class SoundcloudIE(InfoExtractor):
                 "upload_date": "20121011",
                 "description": "No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd",
                 "uploader": "E.T. ExTerrestrial Music",
-                "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
+                "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1",
+                "duration": 143,
             }
         },
         # not streamable song
@@ -57,6 +59,7 @@ class SoundcloudIE(InfoExtractor):
                 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com',
                 'uploader': 'The Royal Concept',
                 'upload_date': '20120521',
+                'duration': 227,
             },
             'params': {
                 # rtmp
@@ -74,6 +77,7 @@ class SoundcloudIE(InfoExtractor):
                 'uploader': 'jaimeMF',
                 'description': 'test chars:  \"\'/\\ä↭',
                 'upload_date': '20131209',
+                'duration': 9,
             },
         },
         # downloadable song
@@ -87,6 +91,7 @@ class SoundcloudIE(InfoExtractor):
                 'description': 'Vocals',
                 'uploader': 'Sim Gretina',
                 'upload_date': '20130815',
+                #'duration': 42,
             },
         },
     ]
@@ -94,10 +99,6 @@ class SoundcloudIE(InfoExtractor):
     _CLIENT_ID = 'b45b1aa10f1ac2941910a7f0d10f8e28'
     _IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf'
 
-    @classmethod
-    def suitable(cls, url):
-        return re.match(cls._VALID_URL, url, flags=re.VERBOSE) is not None
-
     def report_resolve(self, video_id):
         """Report information extraction."""
         self.to_screen('%s: Resolving id' % video_id)
@@ -123,6 +124,7 @@ class SoundcloudIE(InfoExtractor):
             'title': info['title'],
             'description': info['description'],
             'thumbnail': thumbnail,
+            'duration': int_or_none(info.get('duration'), 1000),
         }
         formats = []
         if info.get('downloadable', False):
@@ -141,11 +143,10 @@ class SoundcloudIE(InfoExtractor):
         # We have to retrieve the url
         streams_url = ('http://api.soundcloud.com/i1/tracks/{0}/streams?'
             'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token))
-        stream_json = self._download_webpage(
+        format_dict = self._download_json(
             streams_url,
             track_id, 'Downloading track url')
 
-        format_dict = json.loads(stream_json)
         for key, stream_url in format_dict.items():
             if key.startswith('http'):
                 formats.append({
@@ -198,7 +199,7 @@ class SoundcloudIE(InfoExtractor):
             full_title = track_id
         elif mobj.group('player'):
             query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
-            return self.url_result(query['url'][0], ie='Soundcloud')
+            return self.url_result(query['url'][0])
         else:
             # extract uploader (which is in the url)
             uploader = mobj.group('uploader')
@@ -213,11 +214,11 @@ class SoundcloudIE(InfoExtractor):
     
             url = 'http://soundcloud.com/%s' % resolve_title
             info_json_url = self._resolv_url(url)
-        info_json = self._download_webpage(info_json_url, full_title, 'Downloading info JSON')
+        info = self._download_json(info_json_url, full_title, 'Downloading info JSON')
 
-        info = json.loads(info_json)
         return self._extract_info_dict(info, full_title, secret_token=token)
 
+
 class SoundcloudSetIE(SoundcloudIE):
     _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
     IE_NAME = 'soundcloud:set'
@@ -232,16 +233,15 @@ class SoundcloudSetIE(SoundcloudIE):
         # extract uploader (which is in the url)
         uploader = mobj.group(1)
         # extract simple title (uploader + slug of song title)
-        slug_title =  mobj.group(2)
+        slug_title = mobj.group(2)
         full_title = '%s/sets/%s' % (uploader, slug_title)
 
         self.report_resolve(full_title)
 
         url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
         resolv_url = self._resolv_url(url)
-        info_json = self._download_webpage(resolv_url, full_title)
+        info = self._download_json(resolv_url, full_title)
 
-        info = json.loads(info_json)
         if 'errors' in info:
             for err in info['errors']:
                 self._downloader.report_error('unable to download video webpage: %s' % compat_str(err['error_message']))
@@ -268,26 +268,55 @@ class SoundcloudUserIE(SoundcloudIE):
 
         url = 'http://soundcloud.com/%s/' % uploader
         resolv_url = self._resolv_url(url)
-        user_json = self._download_webpage(resolv_url, uploader,
-            'Downloading user info')
-        user = json.loads(user_json)
+        user = self._download_json(
+            resolv_url, uploader, 'Downloading user info')
+        base_url = 'http://api.soundcloud.com/users/%s/tracks.json?' % uploader
 
-        tracks = []
+        entries = []
         for i in itertools.count():
-            data = compat_urllib_parse.urlencode({'offset': i*50,
-                                                  'client_id': self._CLIENT_ID,
-                                                  })
-            tracks_url = 'http://api.soundcloud.com/users/%s/tracks.json?' % user['id'] + data
-            response = self._download_webpage(tracks_url, uploader, 
-                'Downloading tracks page %s' % (i+1))
-            new_tracks = json.loads(response)
-            tracks.extend(self._extract_info_dict(track, quiet=True) for track in new_tracks)
-            if len(new_tracks) < 50:
+            data = compat_urllib_parse.urlencode({
+                'offset': i * 50,
+                'client_id': self._CLIENT_ID,
+            })
+            new_entries = self._download_json(
+                base_url + data, uploader, 'Downloading track page %s' % (i + 1))
+            entries.extend(self._extract_info_dict(e, quiet=True) for e in new_entries)
+            if len(new_entries) < 50:
                 break
 
         return {
             '_type': 'playlist',
             'id': compat_str(user['id']),
             'title': user['username'],
-            'entries': tracks,
+            'entries': entries,
+        }
+
+
+class SoundcloudPlaylistIE(SoundcloudIE):
+    _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)'
+    IE_NAME = 'soundcloud:playlist'
+
+     # it's in tests/test_playlists.py
+    _TESTS = []
+
+    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({
+            'client_id': self._CLIENT_ID,
+        })
+        data = self._download_json(
+            base_url + data, playlist_id, 'Downloading playlist')
+
+        entries = [
+            self._extract_info_dict(t, quiet=True) for t in data['tracks']]
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': data.get('title'),
+            'description': data.get('description'),
+            'entries': entries,
         }

youtube_dl/extractor/spiegeltv.py

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

youtube_dl/extractor/streamcz.py

@@ -5,13 +5,16 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    compat_str,
+)
 
 
 class StreamCZIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<videoid>.+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti',
         'md5': '6d3ca61a8d0633c9c542b92fcb936b0c',
         'info_dict': {
@@ -22,7 +25,18 @@ class StreamCZIE(InfoExtractor):
             'thumbnail': 'http://im.stream.cz/episode/52961d7e19d423f8f06f0100',
             'duration': 256,
         },
-    }
+    }, {
+        'url': 'http://www.stream.cz/blanik/10002447-tri-roky-pro-mazanka',
+        'md5': '246272e753e26bbace7fcd9deca0650c',
+        'info_dict': {
+            'id': '10002447',
+            'ext': 'mp4',
+            'title': 'Kancelář Blaník: Tři roky pro Mazánka',
+            'description': 'md5:9177695a8b756a0a8ab160de4043b392',
+            'thumbnail': 'http://im.stream.cz/episode/537f838c50c11f8d21320000',
+            'duration': 368,
+        },
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -57,7 +71,7 @@ class StreamCZIE(InfoExtractor):
         self._sort_formats(formats)
 
         return {
-            'id': str(jsonData['id']),
+            'id': compat_str(jsonData['episode_id']),
             'title': self._og_search_title(webpage),
             'thumbnail': jsonData['episode_image_original_url'].replace('//', 'http://'),
             'formats': formats,

youtube_dl/extractor/swrmediathek.py

@@ -0,0 +1,104 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import parse_duration
+
+
+class SWRMediathekIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?swrmediathek\.de/player\.htm\?show=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
+
+    _TESTS = [{
+        'url': 'http://swrmediathek.de/player.htm?show=849790d0-dab8-11e3-a953-0026b975f2e6',
+        'md5': '8c5f6f0172753368547ca8413a7768ac',
+        'info_dict': {
+            'id': '849790d0-dab8-11e3-a953-0026b975f2e6',
+            'ext': 'mp4',
+            'title': 'SWR odysso',
+            'description': 'md5:2012e31baad36162e97ce9eb3f157b8a',
+            'thumbnail': 're:^http:.*\.jpg$',
+            'duration': 2602,
+            'upload_date': '20140515',
+            'uploader': 'SWR Fernsehen',
+            'uploader_id': '990030',
+        },
+    }, {
+        'url': 'http://swrmediathek.de/player.htm?show=0e1a8510-ddf2-11e3-9be3-0026b975f2e6',
+        'md5': 'b10ab854f912eecc5a6b55cd6fc1f545',
+        'info_dict': {
+            'id': '0e1a8510-ddf2-11e3-9be3-0026b975f2e6',
+            'ext': 'mp4',
+            'title': 'Nachtcafé - Alltagsdroge Alkohol - zwischen Sektempfang und Komasaufen',
+            'description': 'md5:e0a3adc17e47db2c23aab9ebc36dbee2',
+            'thumbnail': 're:http://.*\.jpg',
+            'duration': 5305,
+            'upload_date': '20140516',
+            'uploader': 'SWR Fernsehen',
+            'uploader_id': '990030',
+        },
+    }, {
+        'url': 'http://swrmediathek.de/player.htm?show=bba23e10-cb93-11e3-bf7f-0026b975f2e6',
+        'md5': '4382e4ef2c9d7ce6852535fa867a0dd3',
+        'info_dict': {
+            'id': 'bba23e10-cb93-11e3-bf7f-0026b975f2e6',
+            'ext': 'mp3',
+            'title': 'Saša Stanišic: Vor dem Fest',
+            'description': 'md5:5b792387dc3fbb171eb709060654e8c9',
+            'thumbnail': 're:http://.*\.jpg',
+            'duration': 3366,
+            'upload_date': '20140520',
+            'uploader': 'SWR 2',
+            'uploader_id': '284670',
+        }
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        video = self._download_json(
+            'http://swrmediathek.de/AjaxEntry?ekey=%s' % video_id, video_id, 'Downloading video JSON')
+
+        attr = video['attr']
+        media_type = attr['entry_etype']
+
+        formats = []
+        for entry in video['sub']:
+            if entry['name'] != 'entry_media':
+                continue
+
+            entry_attr = entry['attr']
+            codec = entry_attr['val0']
+            quality = int(entry_attr['val1'])
+
+            fmt = {
+                'url': entry_attr['val2'],
+                'quality': quality,
+            }
+
+            if media_type == 'Video':
+                fmt.update({
+                    'format_note': ['144p', '288p', '544p'][quality-1],
+                    'vcodec': codec,
+                })
+            elif media_type == 'Audio':
+                fmt.update({
+                    'acodec': codec,
+                })
+            formats.append(fmt)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': attr['entry_title'],
+            'description': attr['entry_descl'],
+            'thumbnail': attr['entry_image_16_9'],
+            'duration': parse_duration(attr['entry_durat']),
+            'upload_date': attr['entry_pdatet'][:-4],
+            'uploader': attr['channel_title'],
+            'uploader_id': attr['channel_idkey'],
+            'formats': formats,
+        }

youtube_dl/extractor/syfy.py

@@ -6,9 +6,9 @@ from .common import InfoExtractor
 
 
 class SyfyIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.syfy\.com/videos/.+?vid:(?P<id>\d+)'
+    _VALID_URL = r'https?://www\.syfy\.com/(?:videos/.+?vid:(?P<id>[0-9]+)|(?!videos)(?P<video_name>[^/]+)(?:$|[?#]))'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.syfy.com/videos/Robot%20Combat%20League/Behind%20the%20Scenes/vid:2631458',
         'md5': 'e07de1d52c7278adbb9b9b1c93a66849',
         'info_dict': {
@@ -18,10 +18,30 @@ class SyfyIE(InfoExtractor):
             'description': 'Listen to what insights George Lucas give his daughter Amanda.',
         },
         'add_ie': ['ThePlatform'],
-    }
+    }, {
+        'url': 'http://www.syfy.com/wilwheaton',
+        'md5': '94dfa54ee3ccb63295b276da08c415f6',
+        'info_dict': {
+            'id': '4yoffOOXC767',
+            'ext': 'flv',
+            'title': 'The Wil Wheaton Project - Premiering May 27th at 10/9c.',
+            'description': 'The Wil Wheaton Project premieres May 27th at 10/9c. Don\'t miss it.',
+        },
+        'add_ie': ['ThePlatform'],
+        'skip': 'Blocked outside the US',
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_name = mobj.group('video_name')
+        if video_name:
+            generic_webpage = self._download_webpage(url, video_name)
+            video_id = self._search_regex(
+                r'<iframe.*?class="video_iframe_page"\s+src="/_utils/video/thP_video_controller.php.*?_vid([0-9]+)">',
+                generic_webpage, 'video ID')
+            url = 'http://www.syfy.com/videos/%s/%s/vid:%s' % (
+                video_name, video_name, video_id)
+        else:
+            video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
         return self.url_result(self._og_search_video_url(webpage))

youtube_dl/extractor/tagesschau.py

@@ -0,0 +1,79 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class TagesschauIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/video/video(?P<id>-?[0-9]+)\.html'
+
+    _TESTS = [{
+        'url': 'http://www.tagesschau.de/multimedia/video/video1399128.html',
+        'md5': 'bcdeac2194fb296d599ce7929dfa4009',
+        'info_dict': {
+            'id': '1399128',
+            'ext': 'mp4',
+            'title': 'Harald Range, Generalbundesanwalt, zu den Ermittlungen',
+            'description': 'md5:69da3c61275b426426d711bde96463ab',
+            'thumbnail': 're:^http:.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.tagesschau.de/multimedia/video/video-196.html',
+        'md5': '8aaa8bf3ae1ca2652309718c03019128',
+        'info_dict': {
+            'id': '196',
+            'ext': 'mp4',
+            'title': 'Ukraine-Konflikt: Klitschko in Kiew als Bürgermeister vereidigt',
+            'description': 'md5:f22e4af75821d174fa6c977349682691',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }]
+
+    _FORMATS = {
+        's': {'width': 256, 'height': 144, 'quality': 1},
+        'm': {'width': 512, 'height': 288, 'quality': 2},
+        'l': {'width': 960, 'height': 544, 'quality': 3},
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        if video_id.startswith('-'):
+            display_id = video_id.strip('-')
+        else:
+            display_id = video_id
+
+        webpage = self._download_webpage(url, display_id)
+
+        playerpage = self._download_webpage(
+            'http://www.tagesschau.de/multimedia/video/video%s~player_autoplay-true.html' % video_id,
+            display_id, 'Downloading player page')
+
+        medias = re.findall(
+            r'"(http://media.+?)", type:"video/(.+?)", quality:"(.+?)"',
+            playerpage)
+
+        formats = []
+        for url, ext, res in medias:
+            f = {
+                'format_id': res + '_' + ext,
+                'url': url,
+                'ext': ext,
+            }
+            f.update(self._FORMATS.get(res, {}))
+            formats.append(f)
+
+        self._sort_formats(formats)
+
+        thumbnail = re.findall(r'"(/multimedia/.+?\.jpg)"', playerpage)[-1]
+
+        return {
+            'id': display_id,
+            'title': self._og_search_title(webpage).strip(),
+            'thumbnail': 'http://www.tagesschau.de' + thumbnail,
+            'formats': formats,
+            'description': self._og_search_description(webpage).strip(),
+        }

youtube_dl/extractor/teachertube.py

@@ -0,0 +1,93 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    qualities,
+    determine_ext,
+)
+
+
+class TeacherTubeIE(InfoExtractor):
+    IE_NAME = 'teachertube'
+    IE_DESC = 'teachertube.com videos'
+
+    _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=)(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997',
+        'md5': 'f9434ef992fd65936d72999951ee254c',
+        'info_dict': {
+            'id': '339997',
+            'ext': 'mp4',
+            'title': 'Measures of dispersion from a frequency table_x264',
+            'description': 'md5:a3e9853487185e9fcd7181a07164650b',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }, {
+        'url': 'http://www.teachertube.com/viewVideo.php?video_id=340064',
+        'md5': '0d625ec6bc9bf50f70170942ad580676',
+        'info_dict': {
+            'id': '340064',
+            'ext': 'mp4',
+            'title': 'How to Make Paper Dolls _ Paper Art Projects',
+            'description': 'md5:2ca52b20cd727773d1dc418b3d6bd07b',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }, {
+        'url': 'http://www.teachertube.com/music.php?music_id=8805',
+        'md5': '01e8352006c65757caf7b961f6050e21',
+        'info_dict': {
+            'id': '8805',
+            'ext': 'mp3',
+            'title': 'PER ASPERA AD ASTRA',
+            'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNIČKE ŠKOLE PER ASPERA AD ASTRA',
+        },
+    }]
+
+    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 = qualities(['mp3', 'flv', 'mp4'])
+
+        formats = [
+            {
+                'url': media_url,
+                'quality': quality(determine_ext(media_url))
+            } for media_url in set(zip(*re.findall(r'([\'"])file\1\s*:\s*"([^"]+)"', webpage))[1])
+        ]
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+        }
+
+
+class TeacherTubeClassroomIE(InfoExtractor):
+    IE_NAME = 'teachertube:classroom'
+    IE_DESC = 'teachertube.com online classrooms'
+
+    _VALID_URL = r'https?://(?:www\.)?teachertube\.com/view_classroom\.php\?user=(?P<user>[0-9a-zA-Z]+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        user_id = mobj.group('user')
+
+        rss = self._download_xml('http://www.teachertube.com/rssclassroom.php?mode=user&username=%s' % user_id,
+                                      user_id, 'Downloading classroom RSS')
+
+        entries = []
+        for url in rss.findall('.//{http://search.yahoo.com/mrss/}player'):
+            entries.append(self.url_result(url.attrib['url'], 'TeacherTube'))
+
+        return self.playlist_result(entries, user_id)

youtube_dl/extractor/teachingchannel.py

@@ -0,0 +1,33 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .ooyala import OoyalaIE
+
+
+class TeachingChannelIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.teachingchannel\.org/videos/(?P<title>.+)'
+
+    _TEST = {
+        'url': 'https://www.teachingchannel.org/videos/teacher-teaming-evolution',
+        'info_dict': {
+            'id': 'F3bnlzbToeI6pLEfRyrlfooIILUjz4nM',
+            'ext': 'mp4',
+            'title': 'A History of Teaming',
+            'description': 'md5:2a9033db8da81f2edffa4c99888140b3',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        title = mobj.group('title')
+        webpage = self._download_webpage(url, title)
+        ooyala_code = self._search_regex(
+            r'data-embed-code=\'(.+?)\'', webpage, 'ooyala code')
+
+        return OoyalaIE._build_url_result(ooyala_code)

youtube_dl/extractor/ted.py

@@ -51,16 +51,13 @@ class TEDIE(SubtitlesInfoExtractor):
         }
     }, {
         'url': 'http://www.ted.com/talks/gabby_giffords_and_mark_kelly_be_passionate_be_courageous_be_your_best',
+        'md5': '49144e345a899b8cb34d315f3b9cfeeb',
         'info_dict': {
             'id': '1972',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Be passionate. Be courageous. Be your best.',
             'uploader': 'Gabby Giffords and Mark Kelly',
-            'description': 'md5:d89e1d8ebafdac8e55df4c219ecdbfe9',
-        },
-        'params': {
-            # rtmp download
-            'skip_download': True,
+            'description': 'md5:5174aed4d0f16021b704120360f72b92',
         },
     }]
 
@@ -97,7 +94,7 @@ class TEDIE(SubtitlesInfoExtractor):
         playlist_info = info['playlist']
 
         playlist_entries = [
-            self.url_result(u'http://www.ted.com/talks/' + talk['slug'], self.ie_key())
+            self.url_result('http://www.ted.com/talks/' + talk['slug'], self.ie_key())
             for talk in info['talks']
         ]
         return self.playlist_result(
@@ -163,7 +160,7 @@ class TEDIE(SubtitlesInfoExtractor):
                 sub_lang_list[l] = url
             return sub_lang_list
         else:
-            self._downloader.report_warning(u'video doesn\'t have subtitles')
+            self._downloader.report_warning('video doesn\'t have subtitles')
             return {}
 
     def _watch_info(self, url, name):
@@ -178,7 +175,10 @@ class TEDIE(SubtitlesInfoExtractor):
         title = self._html_search_regex(
             r"(?s)<h1(?:\s+class='[^']+')?>(.+?)</h1>", webpage, 'title')
         description = self._html_search_regex(
-            r'(?s)<h4 class="[^"]+" id="h3--about-this-talk">.*?</h4>(.*?)</div>',
+            [
+                r'(?s)<h4 class="[^"]+" id="h3--about-this-talk">.*?</h4>(.*?)</div>',
+                r'(?s)<p><strong>About this talk:</strong>\s+(.*?)</p>',
+            ],
             webpage, 'description', fatal=False)
 
         return {

youtube_dl/extractor/theplatform.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
@@ -18,17 +20,17 @@ class ThePlatformIE(InfoExtractor):
 
     _TEST = {
         # from http://www.metacafe.com/watch/cb-e9I_cZgTgIPd/blackberrys_big_bold_z30/
-        u'url': u'http://link.theplatform.com/s/dJ5BDC/e9I_cZgTgIPd/meta.smil?format=smil&Tracking=true&mbr=true',
-        u'info_dict': {
-            u'id': u'e9I_cZgTgIPd',
-            u'ext': u'flv',
-            u'title': u'Blackberry\'s big, bold Z30',
-            u'description': u'The Z30 is Blackberry\'s biggest, baddest mobile messaging device yet.',
-            u'duration': 247,
+        'url': 'http://link.theplatform.com/s/dJ5BDC/e9I_cZgTgIPd/meta.smil?format=smil&Tracking=true&mbr=true',
+        'info_dict': {
+            'id': 'e9I_cZgTgIPd',
+            'ext': 'flv',
+            'title': 'Blackberry\'s big, bold Z30',
+            'description': 'The Z30 is Blackberry\'s biggest, baddest mobile messaging device yet.',
+            'duration': 247,
         },
-        u'params': {
+        'params': {
             # rtmp download
-            u'skip_download': True,
+            'skip_download': True,
         },
     }
 
@@ -39,7 +41,7 @@ class ThePlatformIE(InfoExtractor):
             error_msg = next(
                 n.attrib['abstract']
                 for n in meta.findall(_x('.//smil:ref'))
-                if n.attrib.get('title') == u'Geographic Restriction')
+                if n.attrib.get('title') == 'Geographic Restriction')
         except StopIteration:
             pass
         else:
@@ -52,7 +54,7 @@ class ThePlatformIE(InfoExtractor):
         head = meta.find(_x('smil:head'))
         body = meta.find(_x('smil:body'))
 
-        f4m_node = body.find(_x('smil:seq/smil:video'))
+        f4m_node = body.find(_x('smil:seq//smil:video'))
         if f4m_node is not None:
             f4m_url = f4m_node.attrib['src']
             if 'manifest.f4m?' not in f4m_url:
@@ -101,8 +103,7 @@ class ThePlatformIE(InfoExtractor):
             config_url = url+ '&form=json'
             config_url = config_url.replace('swf/', 'config/')
             config_url = config_url.replace('onsite/', 'onsite/config/')
-            config_json = self._download_webpage(config_url, video_id, u'Downloading config')
-            config = json.loads(config_json)
+            config = self._download_json(config_url, video_id, 'Downloading config')
             smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m'
         else:
             smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?'

youtube_dl/extractor/ustream.py

@@ -11,29 +11,36 @@ from ..utils import (
 
 
 class UstreamIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed)/(?P<videoID>\d+)'
+    _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed|embed/recorded)/(?P<videoID>\d+)'
     IE_NAME = 'ustream'
     _TEST = {
         'url': 'http://www.ustream.tv/recorded/20274954',
-        'file': '20274954.flv',
         'md5': '088f151799e8f572f84eb62f17d73e5c',
         'info_dict': {
-            "uploader": "Young Americans for Liberty",
-            "title": "Young Americans for Liberty February 7, 2012 2:28 AM",
+            'id': '20274954',
+            'ext': 'flv',
+            'uploader': 'Young Americans for Liberty',
+            'title': 'Young Americans for Liberty February 7, 2012 2:28 AM',
         },
     }
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
+        video_id = m.group('videoID')
+
+        # some sites use this embed format (see: http://github.com/rg3/youtube-dl/issues/2990)
+        if m.group('type') == 'embed/recorded':
+            video_id = m.group('videoID')
+            desktop_url = 'http://www.ustream.tv/recorded/' + video_id
+            return self.url_result(desktop_url, 'Ustream')
         if m.group('type') == 'embed':
             video_id = m.group('videoID')
             webpage = self._download_webpage(url, video_id)
-            desktop_video_id = self._html_search_regex(r'ContentVideoIds=\["([^"]*?)"\]', webpage, 'desktop_video_id')
+            desktop_video_id = self._html_search_regex(
+                r'ContentVideoIds=\["([^"]*?)"\]', webpage, 'desktop_video_id')
             desktop_url = 'http://www.ustream.tv/recorded/' + desktop_video_id
             return self.url_result(desktop_url, 'Ustream')
 
-        video_id = m.group('videoID')
-
         video_url = 'http://tcdn.ustream.tv/video/%s' % video_id
         webpage = self._download_webpage(url, video_id)
 

youtube_dl/extractor/vevo.py

@@ -16,7 +16,7 @@ class VevoIE(InfoExtractor):
     (currently used by MTVIE)
     """
     _VALID_URL = r'''(?x)
-        (?:https?://www\.vevo\.com/watch/(?:[^/]+/[^/]+/)?|
+        (?:https?://www\.vevo\.com/watch/(?:[^/]+/(?:[^/]+/)?)?|
            https?://cache\.vevo\.com/m/html/embed\.html\?video=|
            https?://videoplayer\.vevo\.com/embed/embedded\?videoId=|
            vevo:)
@@ -134,7 +134,13 @@ class VevoIE(InfoExtractor):
         video_id = mobj.group('id')
 
         json_url = 'http://videoplayer.vevo.com/VideoService/AuthenticateVideo?isrc=%s' % video_id
-        video_info = self._download_json(json_url, video_id)['video']
+        response = self._download_json(json_url, video_id)
+        video_info = response['video']
+
+        if not video_info:
+            if 'statusMessage' in response:
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusMessage']), expected=True)
+            raise ExtractorError('Unable to extract videos')
 
         formats = self._formats_from_json(video_info)
 

youtube_dl/extractor/vh1.py

@@ -0,0 +1,124 @@
+from __future__ import unicode_literals
+
+from .mtv import MTVIE
+
+import re
+from ..utils import fix_xml_ampersands
+
+
+class VH1IE(MTVIE):
+    IE_NAME = 'vh1.com'
+    _FEED_URL = 'http://www.vh1.com/player/embed/AS3/fullepisode/rss/'
+    _TESTS = [{
+        'url': 'http://www.vh1.com/video/metal-evolution/full-episodes/progressive-metal/1678612/playlist.jhtml',
+        'playlist': [
+            {
+                'md5': '7827a7505f59633983165bbd2c119b52',
+                'info_dict': {
+                    'id': '731565',
+                    'ext': 'mp4',
+                    'title': 'Metal Evolution: Ep. 11 Act 1',
+                    'description': 'Many rock academics have proclaimed that the truly progressive musicianship of the last 20 years has been found right here in the world of heavy metal, rather than obvious locales such as jazz, fusion or progressive rock. It stands to reason then, that much of this jaw-dropping virtuosity occurs within what\'s known as progressive metal, a genre that takes root with the likes of Rush in the \'70s, Queensryche and Fates Warning in the \'80s, and Dream Theater in the \'90s. Since then, the genre has exploded with creativity, spawning mind-bending, genre-defying acts such as Tool, Mastodon, Coheed And Cambria, Porcupine Tree, Meshuggah, A Perfect Circle and Opeth. Episode 12 looks at the extreme musicianship of these bands, as well as their often extreme literary prowess and conceptual strength, the end result being a rich level of respect and attention such challenging acts have brought upon the world of heavy metal, from a critical community usually dismissive of the form.'
+                }
+            },
+            {
+                'md5': '34fb4b7321c546b54deda2102a61821f',
+                'info_dict': {
+                    'id': '731567',
+                    'ext': 'mp4',
+                    'title': 'Metal Evolution: Ep. 11 Act 2',
+                    'description': 'Many rock academics have proclaimed that the truly progressive musicianship of the last 20 years has been found right here in the world of heavy metal, rather than obvious locales such as jazz, fusion or progressive rock. It stands to reason then, that much of this jaw-dropping virtuosity occurs within what\'s known as progressive metal, a genre that takes root with the likes of Rush in the \'70s, Queensryche and Fates Warning in the \'80s, and Dream Theater in the \'90s. Since then, the genre has exploded with creativity, spawning mind-bending, genre-defying acts such as Tool, Mastodon, Coheed And Cambria, Porcupine Tree, Meshuggah, A Perfect Circle and Opeth. Episode 11 looks at the extreme musicianship of these bands, as well as their often extreme literary prowess and conceptual strength, the end result being a rich level of respect and attention such challenging acts have brought upon the world of heavy metal, from a critical community usually dismissive of the form.'
+                }
+            },
+            {
+                'md5': '813f38dba4c1b8647196135ebbf7e048',
+                'info_dict': {
+                    'id': '731568',
+                    'ext': 'mp4',
+                    'title': 'Metal Evolution: Ep. 11 Act 3',
+                    'description': 'Many rock academics have proclaimed that the truly progressive musicianship of the last 20 years has been found right here in the world of heavy metal, rather than obvious locales such as jazz, fusion or progressive rock. It stands to reason then, that much of this jaw-dropping virtuosity occurs within what\'s known as progressive metal, a genre that takes root with the likes of Rush in the \'70s, Queensryche and Fates Warning in the \'80s, and Dream Theater in the \'90s. Since then, the genre has exploded with creativity, spawning mind-bending, genre-defying acts such as Tool, Mastodon, Coheed And Cambria, Porcupine Tree, Meshuggah, A Perfect Circle and Opeth. Episode 11 looks at the extreme musicianship of these bands, as well as their often extreme literary prowess and conceptual strength, the end result being a rich level of respect and attention such challenging acts have brought upon the world of heavy metal, from a critical community usually dismissive of the form.'
+                }
+            },
+            {
+                'md5': '51adb72439dfaed11c799115d76e497f',
+                'info_dict': {
+                    'id': '731569',
+                    'ext': 'mp4',
+                    'title': 'Metal Evolution: Ep. 11 Act 4',
+                    'description': 'Many rock academics have proclaimed that the truly progressive musicianship of the last 20 years has been found right here in the world of heavy metal, rather than obvious locales such as jazz, fusion or progressive rock. It stands to reason then, that much of this jaw-dropping virtuosity occurs within what\'s known as progressive metal, a genre that takes root with the likes of Rush in the \'70s, Queensryche and Fates Warning in the \'80s, and Dream Theater in the \'90s. Since then, the genre has exploded with creativity, spawning mind-bending, genre-defying acts such as Tool, Mastodon, Coheed And Cambria, Porcupine Tree, Meshuggah, A Perfect Circle and Opeth. Episode 11 looks at the extreme musicianship of these bands, as well as their often extreme literary prowess and conceptual strength, the end result being a rich level of respect and attention such challenging acts have brought upon the world of heavy metal, from a critical community usually dismissive of the form.'
+                }
+            },
+            {
+                'md5': '93d554aaf79320703b73a95288c76a6e',
+                'info_dict': {
+                    'id': '731570',
+                    'ext': 'mp4',
+                    'title': 'Metal Evolution: Ep. 11 Act 5',
+                    'description': 'Many rock academics have proclaimed that the truly progressive musicianship of the last 20 years has been found right here in the world of heavy metal, rather than obvious locales such as jazz, fusion or progressive rock. It stands to reason then, that much of this jaw-dropping virtuosity occurs within what\'s known as progressive metal, a genre that takes root with the likes of Rush in the \'70s, Queensryche and Fates Warning in the \'80s, and Dream Theater in the \'90s. Since then, the genre has exploded with creativity, spawning mind-bending, genre-defying acts such as Tool, Mastodon, Coheed And Cambria, Porcupine Tree, Meshuggah, A Perfect Circle and Opeth. Episode 11 looks at the extreme musicianship of these bands, as well as their often extreme literary prowess and conceptual strength, the end result being a rich level of respect and attention such challenging acts have brought upon the world of heavy metal, from a critical community usually dismissive of the form.'
+                }
+            }
+        ],
+        'skip': 'Blocked outside the US',
+    }, {
+        # Clip
+        'url': 'http://www.vh1.com/video/misc/706675/metal-evolution-episode-1-pre-metal-show-clip.jhtml#id=1674118',
+        'md5': '7d67cf6d9cdc6b4f3d3ac97a55403844',
+        'info_dict': {
+            'id': '706675',
+            'ext': 'mp4',
+            'title': 'Metal Evolution: Episode 1 Pre-Metal Show Clip',
+            'description': 'The greatest documentary ever made about Heavy Metal begins as our host Sam Dunn travels the globe to seek out the origins and influences that helped create Heavy Metal. Sam speaks to legends like Kirk Hammett, Alice Cooper, Slash, Bill Ward, Geezer Butler, Tom Morello, Ace Frehley, Lemmy Kilmister, Dave Davies, and many many more. This episode is the prologue for the 11 hour series, and Sam goes back to the very beginning to reveal how Heavy Metal was created.'
+        },
+        'skip': 'Blocked outside the US',
+    }, {
+        # Short link
+        'url': 'http://www.vh1.com/video/play.jhtml?id=1678353',
+        'md5': '853192b87ad978732b67dd8e549b266a',
+        'info_dict': {
+            'id': '730355',
+            'ext': 'mp4',
+            'title': 'Metal Evolution: Episode 11 Progressive Metal Sneak',
+            'description': 'In Metal Evolution\'s finale sneak, Sam sits with Michael Giles of King Crimson and gets feedback from Metallica guitarist Kirk Hammett on why the group was influential.'
+        },
+        'skip': 'Blocked outside the US',
+    }, {
+        'url': 'http://www.vh1.com/video/macklemore-ryan-lewis/900535/cant-hold-us-ft-ray-dalton.jhtml',
+        'md5': 'b1bcb5b4380c9d7f544065589432dee7',
+        'info_dict': {
+            'id': '900535',
+            'ext': 'mp4',
+            'title': 'Macklemore & Ryan Lewis - "Can\'t Hold Us ft. Ray Dalton"',
+            'description': 'The Heist'
+        },
+        'skip': 'Blocked outside the US',
+    }]
+
+    _VALID_URL = r'''(?x)
+        https?://www\.vh1\.com/video/
+        (?:
+            .+?/full-episodes/.+?/(?P<playlist_id>[^/]+)/playlist\.jhtml
+        |
+            (?:
+            play.jhtml\?id=|
+            misc/.+?/.+?\.jhtml\#id=
+            )
+            (?P<video_id>[0-9]+)$
+        |
+            [^/]+/(?P<music_id>[0-9]+)/[^/]+?
+        )
+    '''
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        if mobj.group('music_id'):
+            id_field = 'vid'
+            video_id = mobj.group('music_id')
+        else:
+            video_id = mobj.group('playlist_id') or mobj.group('video_id')
+            id_field = 'id'
+        doc_url = '%s?%s=%s' % (self._FEED_URL, id_field, video_id)
+
+        idoc = self._download_xml(
+            doc_url, video_id,
+            'Downloading info', transform_source=fix_xml_ampersands)
+        return [self._get_video_info(item) for item in idoc.findall('.//item')]

youtube_dl/extractor/videott.py

@@ -0,0 +1,58 @@
+from __future__ import unicode_literals
+
+import re
+import base64
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+
+class VideoTtIE(InfoExtractor):
+    ID_NAME = 'video.tt'
+    IE_DESC = 'video.tt - Your True Tube'
+    _VALID_URL = r'http://(?:www\.)?video\.tt/(?:video/|watch_video\.php\?v=)(?P<id>[\da-zA-Z]{9})'
+
+    _TEST = {
+        'url': 'http://www.video.tt/watch_video.php?v=amd5YujV8',
+        'md5': 'b13aa9e2f267effb5d1094443dff65ba',
+        'info_dict': {
+            'id': 'amd5YujV8',
+            'ext': 'flv',
+            'title': 'Motivational video Change your mind in just 2.50 mins',
+            'description': '',
+            'upload_date': '20130827',
+            'uploader': 'joseph313',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        settings = self._download_json(
+            'http://www.video.tt/player_control/settings.php?v=%s' % video_id, video_id,
+            'Downloading video JSON')['settings']
+
+        video = settings['video_details']['video']
+
+        formats = [
+            {
+                'url': base64.b64decode(res['u']).decode('utf-8'),
+                'ext': 'flv',
+                'format_id': res['l'],
+            } for res in settings['res'] if res['u']
+        ]
+
+        return {
+            'id': video_id,
+            'title': video['title'],
+            'description': video['description'],
+            'thumbnail': settings['config']['thumbnail'],
+            'upload_date': unified_strdate(video['added']),
+            'uploader': video['owner'],
+            'view_count': int(video['view_count']),
+            'comment_count': int(video['comment_count']),
+            'like_count': int(video['liked']),
+            'dislike_count': int(video['disliked']),
+            'formats': formats,
+        }

youtube_dl/extractor/vimeo.py

@@ -17,10 +17,39 @@ from ..utils import (
     RegexNotFoundError,
     std_headers,
     unsmuggle_url,
+    urlencode_postdata,
+    int_or_none,
 )
 
 
-class VimeoIE(SubtitlesInfoExtractor):
+class VimeoBaseInfoExtractor(InfoExtractor):
+    _NETRC_MACHINE = 'vimeo'
+    _LOGIN_REQUIRED = False
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            if self._LOGIN_REQUIRED:
+                raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
+            return
+        self.report_login()
+        login_url = 'https://vimeo.com/log_in'
+        webpage = self._download_webpage(login_url, None, False)
+        token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
+        data = urlencode_postdata({
+            'email': username,
+            'password': password,
+            'action': 'login',
+            'service': 'vimeo',
+            'token': token,
+        })
+        login_request = compat_urllib_request.Request(login_url, data)
+        login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        login_request.add_header('Cookie', 'xsrft=%s' % token)
+        self._download_webpage(login_request, None, False, 'Wrong login info')
+
+
+class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
     """Information extractor for vimeo.com."""
 
     # _VALID_URL matches Vimeo URLs
@@ -33,7 +62,6 @@ class VimeoIE(SubtitlesInfoExtractor):
         (?:videos?/)?
         (?P<id>[0-9]+)
         /?(?:[?&].*)?(?:[#].*)?$'''
-    _NETRC_MACHINE = 'vimeo'
     IE_NAME = 'vimeo'
     _TESTS = [
         {
@@ -47,40 +75,47 @@ class VimeoIE(SubtitlesInfoExtractor):
                 "uploader_id": "user7108434",
                 "uploader": "Filippo Valsorda",
                 "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
+                "duration": 10,
             },
         },
         {
             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
-            'file': '68093876.mp4',
             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
             'note': 'Vimeo Pro video (#1197)',
             'info_dict': {
+                'id': '68093876',
+                'ext': 'mp4',
                 'uploader_id': 'openstreetmapus',
                 'uploader': 'OpenStreetMap US',
                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
+                'duration': 1595,
             },
         },
         {
             'url': 'http://player.vimeo.com/video/54469442',
-            'file': '54469442.mp4',
             'md5': '619b811a4417aa4abe78dc653becf511',
             'note': 'Videos that embed the url in the player page',
             'info_dict': {
+                'id': '54469442',
+                'ext': 'mp4',
                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software',
                 'uploader': 'The BLN & Business of Software',
                 'uploader_id': 'theblnbusinessofsoftware',
+                'duration': 3610,
             },
         },
         {
             'url': 'http://vimeo.com/68375962',
-            'file': '68375962.mp4',
             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
             'note': 'Video protected with password',
             'info_dict': {
+                'id': '68375962',
+                'ext': 'mp4',
                 'title': 'youtube-dl password protected test video',
                 'upload_date': '20130614',
                 'uploader_id': 'user18948128',
                 'uploader': 'Jaime Marquínez Ferrándiz',
+                'duration': 10,
             },
             'params': {
                 'videopassword': 'youtube-dl',
@@ -98,6 +133,7 @@ class VimeoIE(SubtitlesInfoExtractor):
                 'upload_date': '20131015',
                 'uploader_id': 'staff',
                 'uploader': 'Vimeo Staff',
+                'duration': 62,
             }
         },
     ]
@@ -111,38 +147,21 @@ class VimeoIE(SubtitlesInfoExtractor):
         else:
             return super(VimeoIE, cls).suitable(url)
 
-    def _login(self):
-        (username, password) = self._get_login_info()
-        if username is None:
-            return
-        self.report_login()
-        login_url = 'https://vimeo.com/log_in'
-        webpage = self._download_webpage(login_url, None, False)
-        token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
-        data = compat_urllib_parse.urlencode({'email': username,
-                                              'password': password,
-                                              'action': 'login',
-                                              'service': 'vimeo',
-                                              'token': token,
-                                              })
-        login_request = compat_urllib_request.Request(login_url, data)
-        login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        login_request.add_header('Cookie', 'xsrft=%s' % token)
-        self._download_webpage(login_request, None, False, 'Wrong login info')
-
     def _verify_video_password(self, url, video_id, webpage):
         password = self._downloader.params.get('videopassword', None)
         if password is None:
             raise ExtractorError('This video is protected by a password, use the --video-password option')
         token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
-        data = compat_urllib_parse.urlencode({'password': password,
-                                              'token': token})
+        data = compat_urllib_parse.urlencode({
+            'password': password,
+            'token': token,
+        })
         # I didn't manage to use the password with https
         if url.startswith('https'):
-            pass_url = url.replace('https','http')
+            pass_url = url.replace('https', 'http')
         else:
             pass_url = url
-        password_request = compat_urllib_request.Request(pass_url+'/password', data)
+        password_request = compat_urllib_request.Request(pass_url + '/password', data)
         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         password_request.add_header('Cookie', 'xsrft=%s' % token)
         self._download_webpage(password_request, video_id,
@@ -249,8 +268,9 @@ class VimeoIE(SubtitlesInfoExtractor):
         # Extract video description
         video_description = None
         try:
-            video_description = get_element_by_attribute("itemprop", "description", webpage)
-            if video_description: video_description = clean_html(video_description)
+            video_description = get_element_by_attribute("class", "description_wrapper", webpage)
+            if video_description:
+                video_description = clean_html(video_description)
         except AssertionError as err:
             # On some pages like (http://player.vimeo.com/video/54469442) the
             # html tags are not closed, python 2.6 cannot handle it
@@ -259,6 +279,9 @@ class VimeoIE(SubtitlesInfoExtractor):
             else:
                 raise
 
+        # Extract video duration
+        video_duration = int_or_none(config["video"].get("duration"))
+
         # Extract upload date
         video_upload_date = None
         mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
@@ -296,7 +319,7 @@ class VimeoIE(SubtitlesInfoExtractor):
                     file_info = {}
                 if video_url is None:
                     video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
-                        %(video_id, sig, timestamp, quality, codec_name.upper())
+                        % (video_id, sig, timestamp, quality, codec_name.upper())
 
                 files[key].append({
                     'ext': codec_extension,
@@ -330,6 +353,7 @@ class VimeoIE(SubtitlesInfoExtractor):
             'title': video_title,
             'thumbnail': video_thumbnail,
             'description': video_description,
+            'duration': video_duration,
             'formats': formats,
             'webpage_url': url,
             'view_count': view_count,
@@ -355,7 +379,7 @@ class VimeoChannelIE(InfoExtractor):
         video_ids = []
         for pagenum in itertools.count(1):
             webpage = self._download_webpage(
-                self._page_url(base_url, pagenum) ,list_id,
+                self._page_url(base_url, pagenum), list_id,
                 'Downloading page %s' % pagenum)
             video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
@@ -371,7 +395,7 @@ class VimeoChannelIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        channel_id =  mobj.group('id')
+        channel_id = mobj.group('id')
         return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id)
 
 
@@ -438,3 +462,25 @@ class VimeoReviewIE(InfoExtractor):
         video_id = mobj.group('id')
         player_url = 'https://player.vimeo.com/player/' + video_id
         return self.url_result(player_url, 'Vimeo', video_id)
+
+
+class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
+    IE_NAME = 'vimeo:watchlater'
+    IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
+    _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater'
+    _LOGIN_REQUIRED = True
+    _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<'
+
+    def _real_initialize(self):
+        self._login()
+
+    def _page_url(self, base_url, pagenum):
+        url = '%s/page:%d/' % (base_url, pagenum)
+        request = compat_urllib_request.Request(url)
+        # Set the header to get a partial html page with the ids,
+        # the normal page doesn't contain them.
+        request.add_header('X-Requested-With', 'XMLHttpRequest')
+        return request
+
+    def _real_extract(self, url):
+        return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater')

youtube_dl/extractor/vine.py

@@ -2,6 +2,7 @@ from __future__ import unicode_literals
 
 import re
 import json
+import itertools
 
 from .common import InfoExtractor
 from ..utils import unified_strdate
@@ -57,4 +58,34 @@ class VineIE(InfoExtractor):
             'comment_count': data['comments']['count'],
             'repost_count': data['reposts']['count'],
             'formats': formats,
-        }
+        }
+
+
+class VineUserIE(InfoExtractor):
+    IE_NAME = 'vine:user'
+    _VALID_URL = r'(?:https?://)?vine\.co/(?P<user>[^/]+)/?(\?.*)?$'
+    _VINE_BASE_URL = "https://vine.co/"
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        user = mobj.group('user')
+
+        profile_url = "%sapi/users/profiles/vanity/%s" % (
+            self._VINE_BASE_URL, user)
+        profile_data = self._download_json(
+            profile_url, user, note='Downloading user profile data')
+
+        user_id = profile_data['data']['userId']
+        timeline_data = []
+        for pagenum in itertools.count(1):
+            timeline_url = "%sapi/timelines/users/%s?page=%s" % (
+                self._VINE_BASE_URL, user_id, pagenum)
+            timeline_page = self._download_json(
+                timeline_url, user, note='Downloading page %d' % pagenum)
+            timeline_data.extend(timeline_page['data']['records'])
+            if timeline_page['data']['nextPage'] is None:
+                break
+
+        entries = [
+            self.url_result(e['permalinkUrl'], 'Vine') for e in timeline_data]
+        return self.playlist_result(entries, user)

youtube_dl/extractor/vk.py

@@ -37,7 +37,7 @@ class VKIE(InfoExtractor):
             'info_dict': {
                 'id': '163339118',
                 'ext': 'mp4',
-                'uploader': 'Elvira Dzhonik',
+                'uploader': 'Elya Iskhakova',
                 'title': 'Dream Theater - Hollow Years Live at Budokan 720*',
                 'duration': 558,
             }
@@ -108,7 +108,7 @@ class VKIE(InfoExtractor):
 
         m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page)
         if m_yt is not None:
-            self.to_screen(u'Youtube video detected')
+            self.to_screen('Youtube video detected')
             return self.url_result(m_yt.group(1), 'Youtube')
         data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars')
         data = json.loads(data_json)

youtube_dl/extractor/vube.py

@@ -1,47 +1,69 @@
 from __future__ import unicode_literals
 
 import re
-import datetime
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class VubeIE(InfoExtractor):
     IE_NAME = 'vube'
     IE_DESC = 'Vube.com'
-    _VALID_URL = r'http://vube\.com/[^/]+/(?P<id>[\da-zA-Z]{10})'
+    _VALID_URL = r'http://vube\.com/(?:[^/]+/)+(?P<id>[\da-zA-Z]{10})\b'
 
-    _TEST = {
-        'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon',
-        'md5': 'db7aba89d4603dadd627e9d1973946fe',
-        'info_dict': {
-            'id': 'YL2qNPkqon',
-            'ext': 'mp4',
-            'title': 'Chiara Grispo - Price Tag by Jessie J',
-            'description': 'md5:8ea652a1f36818352428cb5134933313',
-            'thumbnail': 'http://frame.thestaticvube.com/snap/228x128/102e7e63057-5ebc-4f5c-4065-6ce4ebde131f.jpg',
-            'uploader': 'Chiara.Grispo',
-            'uploader_id': '1u3hX0znhP',
-            'upload_date': '20140103',
-            'duration': 170.56
+    _TESTS = [
+        {
+            'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon',
+            'md5': 'db7aba89d4603dadd627e9d1973946fe',
+            'info_dict': {
+                'id': 'YL2qNPkqon',
+                'ext': 'mp4',
+                'title': 'Chiara Grispo - Price Tag by Jessie J',
+                'description': 'md5:8ea652a1f36818352428cb5134933313',
+                'thumbnail': 'http://frame.thestaticvube.com/snap/228x128/102e7e63057-5ebc-4f5c-4065-6ce4ebde131f.jpg',
+                'uploader': 'Chiara.Grispo',
+                'uploader_id': '1u3hX0znhP',
+                'timestamp': 1388743358,
+                'upload_date': '20140103',
+                'duration': 170.56
+            }
+        },
+        {
+            'url': 'http://vube.com/SerainaMusic/my-7-year-old-sister-and-i-singing-alive-by-krewella/UeBhTudbfS?t=s&n=1',
+            'md5': '5d4a52492d76f72712117ce6b0d98d08',
+            'info_dict': {
+                'id': 'UeBhTudbfS',
+                'ext': 'mp4',
+                'title': 'My 7 year old Sister and I singing "Alive" by Krewella',
+                'description': 'md5:40bcacb97796339f1690642c21d56f4a',
+                'thumbnail': 'http://frame.thestaticvube.com/snap/228x128/102265d5a9f-0f17-4f6b-5753-adf08484ee1e.jpg',
+                'uploader': 'Seraina',
+                'uploader_id': 'XU9VE2BQ2q',
+                'timestamp': 1396492438,
+                'upload_date': '20140403',
+                'duration': 240.107
+            }
         }
-    }
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
-        video = self._download_json('http://vube.com/api/v2/video/%s' % video_id,
-            video_id, 'Downloading video JSON')
+        video = self._download_json(
+            'http://vube.com/api/v2/video/%s' % video_id, video_id, 'Downloading video JSON')
 
         public_id = video['public_id']
 
-        formats = [{'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (fmt['media_resolution_id'], public_id),
-                   'height': int(fmt['height']),
-                   'abr': int(fmt['audio_bitrate']),
-                   'vbr': int(fmt['video_bitrate']),
-                   'format_id': fmt['media_resolution_id']
-                   } for fmt in video['mtm'] if fmt['transcoding_status'] == 'processed']
+        formats = [
+            {
+                'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (fmt['media_resolution_id'], public_id),
+                'height': int(fmt['height']),
+                'abr': int(fmt['audio_bitrate']),
+                'vbr': int(fmt['video_bitrate']),
+                'format_id': fmt['media_resolution_id']
+            } for fmt in video['mtm'] if fmt['transcoding_status'] == 'processed'
+        ]
 
         self._sort_formats(formats)
 
@@ -52,16 +74,16 @@ class VubeIE(InfoExtractor):
             thumbnail = 'http:' + thumbnail
         uploader = video['user_alias']
         uploader_id = video['user_url_id']
-        upload_date = datetime.datetime.fromtimestamp(int(video['upload_time'])).strftime('%Y%m%d')
+        timestamp = int(video['upload_time'])
         duration = video['duration']
-        view_count = video['raw_view_count']
-        like_count = video['total_likes']
-        dislike_count= video['total_hates']
+        view_count = video.get('raw_view_count')
+        like_count = video.get('total_likes')
+        dislike_count= video.get('total_hates')
 
-        comment = self._download_json('http://vube.com/api/video/%s/comment' % video_id,
-            video_id, 'Downloading video comment JSON')
+        comment = self._download_json(
+            'http://vube.com/api/video/%s/comment' % video_id, video_id, 'Downloading video comment JSON')
 
-        comment_count = comment['total']
+        comment_count = int_or_none(comment.get('total'))
 
         return {
             'id': video_id,
@@ -71,7 +93,7 @@ class VubeIE(InfoExtractor):
             'thumbnail': thumbnail,
             'uploader': uploader,
             'uploader_id': uploader_id,
-            'upload_date': upload_date,
+            'timestamp': timestamp,
             'duration': duration,
             'view_count': view_count,
             'like_count': like_count,

youtube_dl/extractor/vuclip.py

@@ -0,0 +1,66 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse_urlparse,
+    parse_duration,
+    qualities,
+)
+
+
+class VuClipIE(InfoExtractor):
+    _VALID_URL = r'http://(?:m\.)?vuclip\.com/w\?.*?cid=(?P<id>[0-9]+)'
+
+    _TEST = {
+        'url': 'http://m.vuclip.com/w?cid=843902317&fid=63532&z=1007&nvar&frm=index.html&bu=4757321434',
+        'md5': '92ac9d1ccefec4f0bb474661ab144fcf',
+        'info_dict': {
+            'id': '843902317',
+            'ext': '3gp',
+            'title': 'Movie Trailer: Noah',
+            'duration': 139,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        ad_m = re.search(
+            r'''value="No.*?" onClick="location.href='([^"']+)'"''', webpage)
+        if ad_m:
+            urlr = compat_urllib_parse_urlparse(url)
+            adfree_url = urlr.scheme + '://' + urlr.netloc + ad_m.group(1)
+            webpage = self._download_webpage(
+                adfree_url, video_id, note='Download post-ad page')
+
+        links_code = self._search_regex(
+            r'(?s)<div class="social align_c".*?>(.*?)<hr\s*/?>', webpage,
+            'links')
+        title = self._html_search_regex(
+            r'<title>(.*?)-\s*Vuclip</title>', webpage, 'title').strip()
+
+        quality_order = qualities(['Reg', 'Hi'])
+        formats = []
+        for url, q in re.findall(
+                r'<a href="(?P<url>[^"]+)".*?>(?P<q>[^<]+)</a>', links_code):
+            format_id = compat_urllib_parse_urlparse(url).scheme + '-' + q
+            formats.append({
+                'format_id': format_id,
+                'url': url,
+                'quality': quality_order(q),
+            })
+        self._sort_formats(formats)
+
+        duration = parse_duration(self._search_regex(
+            r'\(([0-9:]+)\)</span></h1>', webpage, 'duration', fatal=False))
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'duration': duration,
+        }

youtube_dl/extractor/wdr.py

@@ -115,6 +115,34 @@ class WDRIE(InfoExtractor):
         }
 
 
+class WDRMobileIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://mobile-ondemand\.wdr\.de/
+        .*?/fsk(?P<age_limit>[0-9]+)
+        /[0-9]+/[0-9]+/
+        (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
+    IE_NAME = 'wdr:mobile'
+    _TEST = {
+        'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
+        'info_dict': {
+            'title': '4283021',
+            'id': '421735',
+            'age_limit': 0,
+        },
+        '_skip': 'Will be depublicized shortly'
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        return {
+            'id': mobj.group('id'),
+            'title': mobj.group('title'),
+            'age_limit': int(mobj.group('age_limit')),
+            'url': url,
+            'user_agent': 'mobile',
+        }
+
+
 class WDRMausIE(InfoExtractor):
     _VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
     IE_DESC = 'Sendung mit der Maus'

youtube_dl/extractor/xvideos.py

@@ -5,18 +5,21 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
+    ExtractorError,
+    clean_html,
 )
 
 
 class XVideosIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
     _TEST = {
-        'url': 'http://www.xvideos.com/video939581/funny_porns_by_s_-1',
-        'file': '939581.flv',
-        'md5': '1d0c835822f0a71a7bf011855db929d0',
+        'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
+        'md5': '4b46ae6ea5e6e9086e714d883313c0c9',
         'info_dict': {
-            "title": "Funny Porns By >>>>S<<<<<< -1",
-            "age_limit": 18,
+            'id': '4588838',
+            'ext': 'flv',
+            'title': 'Biker Takes his Girl',
+            'age_limit': 18,
         }
     }
 
@@ -28,6 +31,10 @@ class XVideosIE(InfoExtractor):
 
         self.report_extraction(video_id)
 
+        mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
+        if mobj:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
+
         # Extract video URL
         video_url = compat_urllib_parse.unquote(
             self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))

youtube_dl/extractor/yahoo.py

@@ -21,7 +21,7 @@ class YahooIE(InfoExtractor):
             'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
             'md5': '4962b075c08be8690a922ee026d05e69',
             'info_dict': {
-                'id': '214727115',
+                'id': '2d25e626-2378-391f-ada0-ddaf1417e588',
                 'ext': 'mp4',
                 'title': 'Julian Smith & Travis Legg Watch Julian Smith',
                 'description': 'Julian and Travis watch Julian Smith',
@@ -31,7 +31,7 @@ class YahooIE(InfoExtractor):
             'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html',
             'md5': 'd6e6fc6e1313c608f316ddad7b82b306',
             'info_dict': {
-                'id': '103000935',
+                'id': 'd1dedf8c-d58c-38c3-8963-e899929ae0a9',
                 'ext': 'mp4',
                 'title': 'Codefellas - The Cougar Lies with Spanish Moss',
                 'description': 'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?',
@@ -58,9 +58,11 @@ class YahooIE(InfoExtractor):
             r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE,
             default=None)
         if items_json is None:
-            long_id = self._search_regex(
+            CONTENT_ID_REGEXES = [
                 r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"',
-                webpage, 'content ID')
+                r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"'
+            ]
+            long_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID')
             video_id = long_id
         else:
             items = json.loads(items_json)
@@ -68,9 +70,9 @@ class YahooIE(InfoExtractor):
             # The 'meta' field is not always in the video webpage, we request it
             # from another page
             long_id = info['id']
-        return self._get_info(long_id, video_id)
+        return self._get_info(long_id, video_id, webpage)
 
-    def _get_info(self, long_id, video_id):
+    def _get_info(self, long_id, video_id, webpage):
         query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"'
                  ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="US"'
                  ' AND protocol="http"' % long_id)
@@ -113,7 +115,7 @@ class YahooIE(InfoExtractor):
             'title': meta['title'],
             'formats': formats,
             'description': clean_html(meta['description']),
-            'thumbnail': meta['thumbnail'],
+            'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage),
         }
 
 
@@ -137,7 +139,7 @@ class YahooNewsIE(YahooIE):
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
         long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, 'long id')
-        return self._get_info(long_id, video_id)
+        return self._get_info(long_id, video_id, webpage)
 
 
 class YahooSearchIE(SearchInfoExtractor):

youtube_dl/extractor/youtube.py

@@ -210,23 +210,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 256, 'preference': -50},
 
         # Dash webm
-        '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'acodec': 'none', 'preference': -40},
-        '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'acodec': 'none', 'preference': -40},
-        '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'acodec': 'none', 'preference': -40},
-        '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'acodec': 'none', 'preference': -40},
-        '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'acodec': 'none', 'preference': -40},
-        '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'acodec': 'none', 'preference': -40},
-        '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH webm', 'preference': -40},
-        '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH webm', 'preference': -40},
-        '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH webm', 'preference': -40},
-        '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH webm', 'preference': -40},
-        '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH webm', 'preference': -40},
-        '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH webm', 'preference': -40},
-        '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH webm', 'preference': -40},
+        '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
+        '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
+        '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
+        '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
+        '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
+        '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
+        '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
+        '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
+        '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
+        '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
+        '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
+        '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
+        '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
+        '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
 
         # Dash webm audio
-        '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH webm audio', 'abr': 48, 'preference': -50},
-        '172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH webm audio', 'abr': 256, 'preference': -50},
+        '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 48, 'preference': -50},
+        '172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50},
 
         # RTMP (unnamed)
         '_rtmp': {'protocol': 'rtmp'},
@@ -242,7 +243,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 u"uploader": u"Philipp Hagemeister",
                 u"uploader_id": u"phihag",
                 u"upload_date": u"20121002",
-                u"description": u"test chars:  \"'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de ."
+                u"description": u"test chars:  \"'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .",
+                u"categories": [u'Science & Technology'],
             }
         },
         {
@@ -252,7 +254,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             u"info_dict": {
                 u"upload_date": u"20120506",
                 u"title": u"Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]",
-                u"description": u"md5:5b292926389560516e384ac437c0ec07",
+                u"description": u"md5:fea86fda2d5a5784273df5c7cc994d9f",
                 u"uploader": u"Icona Pop",
                 u"uploader_id": u"IconaPop"
             }
@@ -304,7 +306,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 u'id': u'IB3lcPjvWLA',
                 u'ext': u'm4a',
                 u'title': u'Afrojack - The Spark ft. Spree Wilson',
-                u'description': u'md5:3199ed45ee8836572865580804d7ac0f',
+                u'description': u'md5:9717375db5a9a3992be4668bbf3bc0a8',
                 u'uploader': u'AfrojackVEVO',
                 u'uploader_id': u'AfrojackVEVO',
                 u'upload_date': u'20131011',
@@ -1082,9 +1084,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                     break
         if 'token' not in video_info:
             if 'reason' in video_info:
-                raise ExtractorError(u'YouTube said: %s' % video_info['reason'][0], expected=True)
+                raise ExtractorError(
+                    u'YouTube said: %s' % video_info['reason'][0],
+                    expected=True, video_id=video_id)
             else:
-                raise ExtractorError(u'"token" parameter not in video info for unknown reason')
+                raise ExtractorError(
+                    u'"token" parameter not in video info for unknown reason',
+                    video_id=video_id)
 
         if 'view_count' in video_info:
             view_count = int(video_info['view_count'][0])
@@ -1113,7 +1119,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
 
         # title
         if 'title' in video_info:
-            video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
+            video_title = video_info['title'][0]
         else:
             self._downloader.report_warning(u'Unable to extract video title')
             video_title = u'_'
@@ -1132,11 +1138,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
 
         # upload date
         upload_date = None
-        mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
+        mobj = re.search(r'(?s)id="eow-date.*?>(.*?)</span>', video_webpage)
+        if mobj is None:
+            mobj = re.search(
+                r'(?s)id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live) on (.*?)</strong>',
+                video_webpage)
         if mobj is not None:
             upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
             upload_date = unified_strdate(upload_date)
 
+        m_cat_container = get_element_by_id("eow-category", video_webpage)
+        if m_cat_container:
+            category = self._html_search_regex(
+                r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
+                default=None)
+            video_categories = None if category is None else [category]
+        else:
+            video_categories = None
+
         # description
         video_description = get_element_by_id("eow-description", video_webpage)
         if video_description:
@@ -1343,6 +1362,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             'title':        video_title,
             'thumbnail':    video_thumbnail,
             'description':  video_description,
+            'categories':   video_categories,
             'subtitles':    video_subtitles,
             'duration':     video_duration,
             'age_limit':    18 if age_gate else 0,
@@ -1395,11 +1415,9 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
         title_span = (search_title('playlist-title') or
             search_title('title long-title') or search_title('title'))
         title = clean_html(title_span)
-        video_re = r'''(?x)data-video-username="(.*?)".*?
+        video_re = r'''(?x)data-video-username=".*?".*?
                        href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id)
-        matches = orderedSet(re.findall(video_re, webpage, flags=re.DOTALL))
-        # Some of the videos may have been deleted, their username field is empty
-        ids = [video_id for (username, video_id) in matches if username]
+        ids = orderedSet(re.findall(video_re, webpage, flags=re.DOTALL))
         url_results = self._ids_to_results(ids)
 
         return self.playlist_result(url_results, playlist_id, title)
@@ -1432,6 +1450,13 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
         page = self._download_webpage(url, playlist_id)
         more_widget_html = content_html = page
 
+        # Check if the playlist exists or is private
+        if re.search(r'<div class="yt-alert-message">[^<]*?(The|This) playlist (does not exist|is private)[^<]*?</div>', page) is not None:
+            raise ExtractorError(
+                u'The playlist doesn\'t exist or is private, use --username or '
+                '--netrc to access it.',
+                expected=True)
+
         # Extract the video ids from the playlist pages
         ids = []
 
@@ -1749,9 +1774,12 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
             feed_entries.extend(
                 self.url_result(video_id, 'Youtube', video_id=video_id)
                 for video_id in ids)
-            if info['paging'] is None:
+            mobj = re.search(
+                r'data-uix-load-more-href="/?[^"]+paging=(?P<paging>\d+)',
+                feed_html)
+            if mobj is None:
                 break
-            paging = info['paging']
+            paging = mobj.group('paging')
         return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE)
 
 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):

youtube_dl/postprocessor/ffmpeg.py

@@ -9,6 +9,7 @@ from .common import AudioConversionError, PostProcessor
 from ..utils import (
     check_executable,
     compat_subprocess_get_DEVNULL,
+    encodeArgument,
     encodeFilename,
     PostProcessingError,
     prepend_extension,
@@ -48,7 +49,7 @@ class FFmpegPostProcessor(PostProcessor):
         for path in input_paths:
             files_cmd.extend(['-i', encodeFilename(path, True)])
         cmd = ([self._get_executable(), '-y'] + files_cmd
-               + opts +
+               + [encodeArgument(o) for o in opts] +
                [encodeFilename(self._ffmpeg_filename_argument(out_path), True)])
 
         if self._downloader.params.get('verbose', False):

youtube_dl/postprocessor/xattrpp.py

@@ -6,6 +6,7 @@ from .common import PostProcessor
 from ..utils import (
     check_executable,
     hyphenate_date,
+    subprocess_check_output
 )
 
 
@@ -57,7 +58,7 @@ class XAttrMetadataPP(PostProcessor):
                         elif user_has_xattr:
                             cmd = ['xattr', '-w', key, value, path]
 
-                        subprocess.check_output(cmd)
+                        subprocess_check_output(cmd)
 
                 else:
                     # On Unix, and can't find pyxattr, setfattr, or xattr.

youtube_dl/utils.py

@@ -540,6 +540,16 @@ def encodeFilename(s, for_subprocess=False):
         encoding = 'utf-8'
     return s.encode(encoding, 'ignore')
 
+
+def encodeArgument(s):
+    if not isinstance(s, compat_str):
+        # Legacy code that uses byte strings
+        # Uncomment the following line after fixing all post processors
+        #assert False, 'Internal error: %r should be of type %r, is %r' % (s, compat_str, type(s))
+        s = s.decode('ascii')
+    return encodeFilename(s, True)
+
+
 def decodeOption(optval):
     if optval is None:
         return optval
@@ -594,13 +604,15 @@ def make_HTTPS_handler(opts_no_check_certificate, **kwargs):
 
 class ExtractorError(Exception):
     """Error during info extraction."""
-    def __init__(self, msg, tb=None, expected=False, cause=None):
+    def __init__(self, msg, tb=None, expected=False, cause=None, video_id=None):
         """ tb, if given, is the original traceback (so that it can be printed out).
         If expected is set, this is a normal error message and most likely not a bug in youtube-dl.
         """
 
         if sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
             expected = True
+        if video_id is not None:
+            msg = video_id + ': ' + msg
         if not expected:
             msg = msg + u'; please report this issue on https://yt-dl.org/bug . Be sure to call youtube-dl with the --verbose flag and include its complete output. Make sure you are using the latest version; type  youtube-dl -U  to update.'
         super(ExtractorError, self).__init__(msg)
@@ -608,6 +620,7 @@ class ExtractorError(Exception):
         self.traceback = tb
         self.exc_info = sys.exc_info()  # preserve original exception
         self.cause = cause
+        self.video_id = video_id
 
     def format_traceback(self):
         if self.traceback is None:
@@ -923,7 +936,11 @@ def _windows_write_string(s, out):
         2: -12,
     }
 
-    fileno = out.fileno()
+    try:
+        fileno = out.fileno()
+    except AttributeError:
+        # If the output stream doesn't have a fileno, it's virtual
+        return False
     if fileno not in WIN_OUTPUT_IDS:
         return False
 
@@ -1245,7 +1262,10 @@ class HEADRequest(compat_urllib_request.Request):
         return "HEAD"
 
 
-def int_or_none(v, scale=1, default=None):
+def int_or_none(v, scale=1, default=None, get_attr=None):
+    if get_attr:
+        if v is not None:
+            v = getattr(v, get_attr, None)
     return default if v is None else (int(v) // scale)
 
 
@@ -1417,3 +1437,17 @@ def qualities(quality_ids):
             return -1
     return q
 
+
+DEFAULT_OUTTMPL = '%(title)s-%(id)s.%(ext)s'
+
+try:
+    subprocess_check_output = subprocess.check_output
+except AttributeError:
+    def subprocess_check_output(*args, **kwargs):
+        assert 'input' not in kwargs
+        p = subprocess.Popen(*args, stdout=subprocess.PIPE, **kwargs)
+        output, _ = p.communicate()
+        ret = p.poll()
+        if ret:
+            raise subprocess.CalledProcessError(ret, p.args, output=output)
+        return output

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.04.21.2'
+__version__ = '2014.06.07'