release 2014.06.24

* marcwebbie/gorillavid:
  Changed video url to a public video
  [GorillaVid] Added GorillaVid extractor

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

@@ -28,6 +28,7 @@ from youtube_dl.extractor import (
     SoundcloudSetIE,
     SoundcloudUserIE,
     SoundcloudPlaylistIE,
+    TeacherTubeClassroomIE,
     LivestreamIE,
     NHLVideocenterIE,
     BambuserChannelIE,
@@ -113,10 +114,10 @@ class TestPlaylists(unittest.TestCase):
     def test_ustream_channel(self):
         dl = FakeYDL()
         ie = UstreamChannelIE(dl)
-        result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty')
+        result = ie.extract('http://www.ustream.tv/channel/channeljapan')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '5124905')
-        self.assertTrue(len(result['entries']) >= 6)
+        self.assertEqual(result['id'], '10874166')
+        self.assertTrue(len(result['entries']) >= 54)
 
     def test_soundcloud_set(self):
         dl = FakeYDL()
@@ -360,5 +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_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

@@ -717,6 +717,17 @@ class YoutubeDL(object):
             info_dict['playlist'] = None
             info_dict['playlist_index'] = None
 
+        thumbnails = info_dict.get('thumbnails')
+        if thumbnails:
+            thumbnails.sort(key=lambda t: (
+                t.get('width'), t.get('height'), t.get('url')))
+            for t in thumbnails:
+                if 'width' in t and 'height' in t:
+                    t['resolution'] = '%dx%d' % (t['width'], t['height'])
+
+        if thumbnails and 'thumbnail' not in info_dict:
+            info_dict['thumbnail'] = thumbnails[-1]['url']
+
         if 'display_id' not in info_dict and 'id' in info_dict:
             info_dict['display_id'] = info_dict['id']
 

youtube_dl/__init__.py

@@ -57,6 +57,8 @@ __authors__  = (
     'Jason Normore',
     'Hoje Lee',
     'Adam Thalhammer',
+    'Georg Jähnig',
+    'Ralf Haring',
 )
 
 __license__ = 'Public Domain'

youtube_dl/downloader/hls.py

@@ -25,7 +25,7 @@ class HlsFD(FileDownloader):
             except (OSError, IOError):
                 pass
         else:
-            self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found')
+            self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
         cmd = [program] + args
 
         retval = subprocess.call(cmd)

youtube_dl/downloader/rtmp.py

@@ -96,6 +96,7 @@ class RtmpFD(FileDownloader):
         flash_version = info_dict.get('flash_version', None)
         live = info_dict.get('rtmp_live', False)
         conn = info_dict.get('rtmp_conn', None)
+        protocol = info_dict.get('rtmp_protocol', None)
 
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
@@ -105,7 +106,7 @@ class RtmpFD(FileDownloader):
         try:
             subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
         except (OSError, IOError):
-            self.report_error('RTMP download detected but "rtmpdump" could not be run')
+            self.report_error('RTMP download detected but "rtmpdump" could not be run. Please install it.')
             return False
 
         # Download using rtmpdump. rtmpdump returns exit code 2 when
@@ -133,6 +134,8 @@ class RtmpFD(FileDownloader):
                 basic_args += ['--conn', entry]
         elif isinstance(conn, compat_str):
             basic_args += ['--conn', conn]
+        if protocol is not None:
+            basic_args += ['--protocol', protocol]
         args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
 
         if sys.platform == 'win32' and sys.version_info < (3, 0):

youtube_dl/extractor/__init__.py

@@ -109,6 +109,7 @@ from .gdcvault import GDCVaultIE
 from .generic import GenericIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
+from .gorillavid import GorillaVidIE
 from .hark import HarkIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
@@ -142,6 +143,7 @@ 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
@@ -168,6 +170,7 @@ from .moviezine import MoviezineIE
 from .movshare import MovShareIE
 from .mtv import (
     MTVIE,
+    MTVServicesEmbeddedIE,
     MTVIggyIE,
 )
 from .musicplayon import MusicPlayOnIE
@@ -215,6 +218,7 @@ from .pornotube import PornotubeIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
 from .radiofrance import RadioFranceIE
+from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
 from .redtube import RedTubeIE
 from .ringtv import RingTVIE
@@ -258,6 +262,7 @@ 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 .steam import SteamIE
@@ -266,6 +271,12 @@ 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
@@ -298,6 +309,7 @@ from .veehd import VeeHDIE
 from .veoh import VeohIE
 from .vesti import VestiIE
 from .vevo import VevoIE
+from .vh1 import VH1IE
 from .viddler import ViddlerIE
 from .videobam import VideoBamIE
 from .videodetective import VideoDetectiveIE
@@ -323,6 +335,7 @@ from .viki import VikiIE
 from .vk import VKIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
+from .vulture import VultureIE
 from .washingtonpost import WashingtonPostIE
 from .wat import WatIE
 from .wdr import (
@@ -334,6 +347,7 @@ from .weibo import WeiboIE
 from .wimp import WimpIE
 from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
+from .wrzuta import WrzutaIE
 from .xbef import XBefIE
 from .xhamster import XHamsterIE
 from .xnxx import XNXXIE

youtube_dl/extractor/ard.py

@@ -39,38 +39,42 @@ class ARDIE(InfoExtractor):
 
         title = self._html_search_regex(
             [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')
 
         formats = []
-        for s in streams:
-            format = {
-                'quality': int(s['quality']),
-            }
-            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'])
+        for s in streams:
+            if type(s['_stream']) == list:
+                for index, url in enumerate(s['_stream'][::-1]):
+                    quality = s['_quality'] + index
+                    formats.append({
+                        'quality': quality,
+                        'url': url,
+                        'format_id': '%s-%s' % (determine_ext(url), quality)
+                        })
+                continue
+
+            format = {
+                'quality': s['_quality'],
+                'url': s['_stream'],
+            }
+
+            format['format_id'] = '%s-%s' % (
+                determine_ext(format['url']), format['quality'])
 
             formats.append(format)
 

youtube_dl/extractor/bilibili.py

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

youtube_dl/extractor/blinkx.py

@@ -4,9 +4,7 @@ import json
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    remove_start,
-)
+from ..utils import remove_start
 
 
 class BlinkxIE(InfoExtractor):
@@ -15,9 +13,10 @@ class BlinkxIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB',
-        'file': '8aQUy7GV.mp4',
         'md5': '2e9a07364af40163a908edbf10bb2492',
         'info_dict': {
+            'id': '8aQUy7GV',
+            'ext': 'mp4',
             'title': 'Police Car Rolls Away',
             'uploader': 'stupidvideos.com',
             'upload_date': '20131215',
@@ -27,6 +26,7 @@ class BlinkxIE(InfoExtractor):
             'thumbnails': [{
                 'width': 100,
                 'height': 76,
+                'resolution': '100x76',
                 'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg',
             }],
         },
@@ -37,7 +37,7 @@ class BlinkxIE(InfoExtractor):
         video_id = m.group('id')
         display_id = video_id[:8]
 
-        api_url = (u'https://apib4.blinkx.com/api.php?action=play_video&' +
+        api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' +
                    'video=%s' % video_id)
         data_json = self._download_webpage(api_url, display_id)
         data = json.loads(data_json)['api']['results'][0]
@@ -55,13 +55,13 @@ class BlinkxIE(InfoExtractor):
                 duration = m['d']
             elif m['type'] == 'youtube':
                 yt_id = m['link']
-                self.to_screen(u'Youtube video detected: %s' % yt_id)
+                self.to_screen('Youtube video detected: %s' % yt_id)
                 return self.url_result(yt_id, 'Youtube', video_id=yt_id)
             elif m['type'] in ('flv', 'mp4'):
                 vcodec = remove_start(m['vcodec'], 'ff')
                 acodec = remove_start(m['acodec'], 'ff')
                 tbr = (int(m['vbr']) + int(m['abr'])) // 1000
-                format_id = u'%s-%sk-%s' % (vcodec, tbr, m['w'])
+                format_id = '%s-%sk-%s' % (vcodec, tbr, m['w'])
                 formats.append({
                     'format_id': format_id,
                     'url': m['link'],

youtube_dl/extractor/br.py

@@ -17,15 +17,13 @@ class BRIE(InfoExtractor):
 
     _TESTS = [
         {
-            'url': 'http://www.br.de/mediathek/video/anselm-gruen-114.html',
-            'md5': 'c4f83cf0f023ba5875aba0bf46860df2',
+            'url': 'http://www.br.de/mediathek/video/sendungen/heimatsound/heimatsound-festival-2014-trailer-100.html',
+            'md5': '93556dd2bcb2948d9259f8670c516d59',
             'info_dict': {
-                'id': '2c8d81c5-6fb7-4a74-88d4-e768e5856532',
+                'id': '25e279aa-1ffd-40fd-9955-5325bd48a53a',
                 'ext': 'mp4',
-                'title': 'Feiern und Verzichten',
-                'description': 'Anselm Grün: Feiern und Verzichten',
-                'uploader': 'BR/Birgit Baier',
-                'upload_date': '20140301',
+                'title': 'Am 1. und 2. August in Oberammergau',
+                'description': 'md5:dfd224e5aa6819bc1fcbb7826a932021',
             }
         },
         {

youtube_dl/extractor/brightcove.py

@@ -15,6 +15,7 @@ from ..utils import (
     compat_urllib_request,
     compat_parse_qs,
 
+    determine_ext,
     ExtractorError,
     unsmuggle_url,
     unescapeHTML,
@@ -29,10 +30,11 @@ class BrightcoveIE(InfoExtractor):
         {
             # From http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/
             'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001',
-            'file': '2371591881001.mp4',
             'md5': '5423e113865d26e40624dce2e4b45d95',
             'note': 'Test Brightcove downloads and detection in GenericIE',
             'info_dict': {
+                'id': '2371591881001',
+                'ext': 'mp4',
                 'title': 'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”',
                 'uploader': '8TV',
                 'description': 'md5:a950cc4285c43e44d763d036710cd9cd',
@@ -41,8 +43,9 @@ class BrightcoveIE(InfoExtractor):
         {
             # From http://medianetwork.oracle.com/video/player/1785452137001
             'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1217746023001&flashID=myPlayer&%40videoPlayer=1785452137001',
-            'file': '1785452137001.flv',
             'info_dict': {
+                'id': '1785452137001',
+                'ext': 'flv',
                 'title': 'JVMLS 2012: Arrays 2.0 - Opportunities and Challenges',
                 'description': 'John Rose speaks at the JVM Language Summit, August 1, 2012.',
                 'uploader': 'Oracle',
@@ -70,7 +73,20 @@ class BrightcoveIE(InfoExtractor):
                 'description': 'md5:363109c02998fee92ec02211bd8000df',
                 'uploader': 'National Ballet of Canada',
             },
-        }
+        },
+        {
+            # test flv videos served by akamaihd.net
+            # From http://www.redbull.com/en/bike/stories/1331655643987/replay-uci-dh-world-cup-2014-from-fort-william
+            'url': 'http://c.brightcove.com/services/viewer/htmlFederated?%40videoPlayer=ref%3ABC2996102916001&linkBaseURL=http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fvideos%2F1331655630249%2Freplay-uci-fort-william-2014-dh&playerKey=AQ%7E%7E%2CAAAApYJ7UqE%7E%2Cxqr_zXk0I-zzNndy8NlHogrCb5QdyZRf&playerID=1398061561001#__youtubedl_smuggle=%7B%22Referer%22%3A+%22http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fstories%2F1331655643987%2Freplay-uci-dh-world-cup-2014-from-fort-william%22%7D',
+            # The md5 checksum changes on each download
+            'info_dict': {
+                'id': '2996102916001',
+                'ext': 'flv',
+                'title': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
+                'uploader': 'Red Bull TV',
+                'description': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
+            },
+        },
     ]
 
     @classmethod
@@ -187,7 +203,7 @@ class BrightcoveIE(InfoExtractor):
         webpage = self._download_webpage(req, video_id)
 
         self.report_extraction(video_id)
-        info = self._search_regex(r'var experienceJSON = ({.*?});', webpage, 'json')
+        info = self._search_regex(r'var experienceJSON = ({.*});', webpage, 'json')
         info = json.loads(info)['data']
         video_info = info['programmedContent']['videoPlayer']['mediaDTO']
         video_info['_youtubedl_adServerURL'] = info.get('adServerURL')
@@ -219,12 +235,26 @@ class BrightcoveIE(InfoExtractor):
 
         renditions = video_info.get('renditions')
         if renditions:
-            renditions = sorted(renditions, key=lambda r: r['size'])
-            info['formats'] = [{
-                'url': rend['defaultURL'],
-                'height': rend.get('frameHeight'),
-                'width': rend.get('frameWidth'),
-            } for rend in renditions]
+            formats = []
+            for rend in renditions:
+                url = rend['defaultURL']
+                if rend['remote']:
+                    # This type of renditions are served through akamaihd.net,
+                    # but they don't use f4m manifests
+                    url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB'
+                    ext = 'flv'
+                else:
+                    ext = determine_ext(url)
+                size = rend.get('size')
+                formats.append({
+                    'url': url,
+                    'ext': ext,
+                    'height': rend.get('frameHeight'),
+                    'width': rend.get('frameWidth'),
+                    'filesize': size if size != 0 else None,
+                })
+            self._sort_formats(formats)
+            info['formats'] = formats
         elif video_info.get('FLVFullLengthURL') is not None:
             info.update({
                 'url': video_info['FLVFullLengthURL'],

youtube_dl/extractor/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/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/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.

youtube_dl/extractor/dreisat.py

@@ -1,39 +1,37 @@
-# coding: utf-8
+from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    unified_strdate,
-)
+from ..utils import unified_strdate
 
 
 class DreiSatIE(InfoExtractor):
     IE_NAME = '3sat'
     _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
     _TEST = {
-        u"url": u"http://www.3sat.de/mediathek/index.php?obj=36983",
-        u'file': u'36983.mp4',
-        u'md5': u'9dcfe344732808dbfcc901537973c922',
-        u'info_dict': {
-            u"title": u"Kaffeeland Schweiz",
-            u"description": u"Über 80 Kaffeeröstereien liefern in der Schweiz das Getränk, in das das Land so vernarrt ist: Mehr als 1000 Tassen trinkt ein Schweizer pro Jahr. SCHWEIZWEIT nimmt die Kaffeekultur unter die...", 
-            u"uploader": u"3sat",
-            u"upload_date": u"20130622"
+        'url': 'http://www.3sat.de/mediathek/index.php?obj=36983',
+        'md5': '9dcfe344732808dbfcc901537973c922',
+        'info_dict': {
+            'id': '36983',
+            'ext': 'mp4',
+            'title': 'Kaffeeland Schweiz',
+            'description': 'md5:cc4424b18b75ae9948b13929a0814033',
+            'uploader': '3sat',
+            'upload_date': '20130622'
         }
     }
 
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
-        details_doc = self._download_xml(details_url, video_id, note=u'Downloading video details')
+        details_doc = self._download_xml(details_url, video_id, 'Downloading video details')
 
         thumbnail_els = details_doc.findall('.//teaserimage')
         thumbnails = [{
-            'width': te.attrib['key'].partition('x')[0],
-            'height': te.attrib['key'].partition('x')[2],
+            'width': int(te.attrib['key'].partition('x')[0]),
+            'height': int(te.attrib['key'].partition('x')[2]),
             'url': te.text,
         } for te in thumbnail_els]
 

youtube_dl/extractor/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/fc2.py

@@ -50,10 +50,13 @@ class FC2IE(InfoExtractor):
             raise ExtractorError('Error code: %s' % info['err_code'][0])
 
         video_url = info['filepath'][0] + '?mid=' + info['mid'][0]
+        title_info = info.get('title')
+        if title_info:
+            title = title_info[0]
 
         return {
             'id': video_id,
-            'title': info['title'][0],
+            'title': title,
             'url': video_url,
             'ext': 'flv',
             'thumbnail': thumbnail,

youtube_dl/extractor/firstpost.py

@@ -15,6 +15,7 @@ class FirstpostIE(InfoExtractor):
             'id': '1025403',
             'ext': 'mp4',
             'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
+            'description': 'md5:feef3041cb09724e0bdc02843348f5f4',
         }
     }
 
@@ -22,13 +23,16 @@ class FirstpostIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
+        page = self._download_webpage(url, video_id)
+        title = self._html_search_meta('twitter:title', page, 'title')
+        description = self._html_search_meta('twitter:description', page, 'title')
+
         data = self._download_xml(
             'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id,
             'Downloading video XML')
 
         item = data.find('./playlist/item')
         thumbnail = item.find('./image').text
-        title = item.find('./title').text
 
         formats = [
             {
@@ -42,6 +46,7 @@ class FirstpostIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
+            'description': description,
             'thumbnail': thumbnail,
             'formats': formats,
         }

youtube_dl/extractor/generic.py

@@ -260,7 +260,35 @@ class GenericIE(InfoExtractor):
                 'uploader': 'Spi0n',
             },
             'add_ie': ['Dailymotion'],
-        }
+        },
+        # YouTube embed
+        {
+            'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
+            'info_dict': {
+                'id': 'FXRb4ykk4S0',
+                'ext': 'mp4',
+                'title': 'The NBL Auction 2014',
+                'uploader': 'BADMINTON England',
+                'uploader_id': 'BADMINTONEvents',
+                'upload_date': '20140603',
+                'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
+            },
+            'add_ie': ['Youtube'],
+            'params': {
+                'skip_download': True,
+            }
+        },
+        # MTVSercices embed
+        {
+            'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
+            'md5': '35727f82f58c76d996fc188f9755b0d5',
+            'info_dict': {
+                'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
+                'ext': 'mp4',
+                'title': 'Review',
+                'description': 'Mario\'s life in the fast lane has never looked so good.',
+            },
+        },
     ]
 
     def report_download_webpage(self, video_id):
@@ -478,8 +506,13 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded YouTube player
         matches = re.findall(r'''(?x)
-            (?:<iframe[^>]+?src=|embedSWF\(\s*)
-            (["\'])(?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
+            (?:
+                <iframe[^>]+?src=|
+                <embed[^>]+?src=|
+                embedSWF\(?:\s*
+            )
+            (["\'])
+                (?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
                 (?:embed|v)/.+?)
             \1''', webpage)
         if matches:
@@ -646,6 +679,22 @@ class GenericIE(InfoExtractor):
             url = unescapeHTML(mobj.group('url'))
             return self.url_result(url)
 
+        # Look for embedded vulture.com player
+        mobj = re.search(
+            r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
+            webpage)
+        if mobj is not None:
+            url = unescapeHTML(mobj.group('url'))
+            return self.url_result(url, ie='Vulture')
+
+        # Look for embedded mtvservices player
+        mobj = re.search(
+            r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
+            webpage)
+        if mobj is not None:
+            url = unescapeHTML(mobj.group('url'))
+            return self.url_result(url, ie='MTVServicesEmbedded')
+
         # Start with something easy: JW Player in SWFObject
         found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if not found:

youtube_dl/extractor/gorillavid.py

@@ -0,0 +1,76 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+
+
+class GorillaVidIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?gorillavid\.in/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?'
+
+    _TESTS = [{
+        'url': 'http://gorillavid.in/06y9juieqpmi',
+        'md5': '5ae4a3580620380619678ee4875893ba',
+        'info_dict': {
+            'id': '06y9juieqpmi',
+            'ext': 'flv',
+            'title': 'Rebecca Black My Moment Official Music Video Reaction',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }, {
+        'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
+        'md5': 'c9e293ca74d46cad638e199c3f3fe604',
+        'info_dict': {
+            'id': 'z08zf8le23c6',
+            'ext': 'mp4',
+            'title': 'Say something nice',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        url = 'http://gorillavid.in/%s' % video_id
+
+        webpage = self._download_webpage(url, video_id)
+
+        fields = dict(re.findall(r'''(?x)<input\s+
+            type="hidden"\s+
+            name="([^"]+)"\s+
+            (?:id="[^"]+"\s+)?
+            value="([^"]*)"
+            ''', webpage))
+        
+        if fields['op'] == 'download1':
+            post = compat_urllib_parse.urlencode(fields)
+
+            req = compat_urllib_request.Request(url, post)
+            req.add_header('Content-type', 'application/x-www-form-urlencoded')
+
+            webpage = self._download_webpage(req, video_id, 'Downloading video page')
+
+        title = self._search_regex(r'style="z-index: [0-9]+;">([0-9a-zA-Z ]+)(?:-.+)?</span>', webpage, 'title')
+        thumbnail = self._search_regex(r'image:\'(http[^\']+)\',', webpage, 'thumbnail')
+        url = self._search_regex(r'file: \'(http[^\']+)\',', webpage, 'file url')
+
+        formats = [{
+            'format_id': 'sd',
+            'url': url,
+            'ext': determine_ext(url),
+            'quality': 1,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/hypem.py

@@ -1,10 +1,11 @@
+from __future__ import unicode_literals
+
 import json
 import re
 import time
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_str,
     compat_urllib_parse,
     compat_urllib_request,
 
@@ -13,59 +14,55 @@ from ..utils import (
 
 
 class HypemIE(InfoExtractor):
-    """Information Extractor for hypem"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
     _TEST = {
-        u'url': u'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
-        u'file': u'1v6ga.mp3',
-        u'md5': u'b9cc91b5af8995e9f0c1cee04c575828',
-        u'info_dict': {
-            u"title": u"Tame"
+        'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
+        'md5': 'b9cc91b5af8995e9f0c1cee04c575828',
+        'info_dict': {
+            'id': '1v6ga',
+            'ext': 'mp3',
+            'title': 'Tame',
+            'uploader': 'BODYWORK',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
         track_id = mobj.group(1)
 
         data = {'ax': 1, 'ts': time.time()}
         data_encoded = compat_urllib_parse.urlencode(data)
         complete_url = url + "?" + data_encoded
         request = compat_urllib_request.Request(complete_url)
-        response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url')
+        response, urlh = self._download_webpage_handle(
+            request, track_id, 'Downloading webpage with the url')
         cookie = urlh.headers.get('Set-Cookie', '')
 
-        self.report_extraction(track_id)
-
-        html_tracks = self._html_search_regex(r'<script type="application/json" id="displayList-data">(.*?)</script>',
-            response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip()
+        html_tracks = self._html_search_regex(
+            r'(?ms)<script type="application/json" id="displayList-data">\s*(.*?)\s*</script>',
+            response, 'tracks')
         try:
             track_list = json.loads(html_tracks)
-            track = track_list[u'tracks'][0]
+            track = track_list['tracks'][0]
         except ValueError:
-            raise ExtractorError(u'Hypemachine contained invalid JSON.')
+            raise ExtractorError('Hypemachine contained invalid JSON.')
 
-        key = track[u"key"]
-        track_id = track[u"id"]
-        artist = track[u"artist"]
-        title = track[u"song"]
+        key = track['key']
+        track_id = track['id']
+        artist = track['artist']
+        title = track['song']
 
-        serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key))
-        request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'})
+        serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key)
+        request = compat_urllib_request.Request(
+            serve_url, '', {'Content-Type': 'application/json'})
         request.add_header('cookie', cookie)
-        song_data_json = self._download_webpage(request, track_id, u'Downloading metadata')
-        try:
-            song_data = json.loads(song_data_json)
-        except ValueError:
-            raise ExtractorError(u'Hypemachine contained invalid JSON.')
-        final_url = song_data[u"url"]
+        song_data = self._download_json(request, track_id, 'Downloading metadata')
+        final_url = song_data["url"]
 
-        return [{
-            'id':       track_id,
-            'url':      final_url,
-            'ext':      "mp3",
-            'title':    title,
-            'artist':   artist,
-        }]
+        return {
+            'id': track_id,
+            'url': final_url,
+            'ext': 'mp3',
+            'title': title,
+            'uploader': artist,
+        }

youtube_dl/extractor/ku6.py

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

youtube_dl/extractor/lifenews.py

@@ -24,7 +24,7 @@ class LifeNewsIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом',
             'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.',
-            'thumbnail': 'http://lifenews.ru/static/posts/2014/1/126342/.video.jpg',
+            'thumbnail': 're:http://.*\.jpg',
             'upload_date': '20140130',
         }
     }

youtube_dl/extractor/livestream.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
@@ -6,31 +8,34 @@ from ..utils import (
     compat_urllib_parse_urlparse,
     compat_urlparse,
     xpath_with_ns,
+    compat_str,
 )
 
 
 class LivestreamIE(InfoExtractor):
-    IE_NAME = u'livestream'
+    IE_NAME = 'livestream'
     _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
     _TEST = {
-        u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
-        u'file': u'4719370.mp4',
-        u'md5': u'0d2186e3187d185a04b3cdd02b828836',
-        u'info_dict': {
-            u'title': u'Live from Webster Hall NYC',
-            u'upload_date': u'20121012',
+        'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
+        'md5': '53274c76ba7754fb0e8d072716f2292b',
+        'info_dict': {
+            'id': '4719370',
+            'ext': 'mp4',
+            'title': 'Live from Webster Hall NYC',
+            'upload_date': '20121012',
         }
     }
 
     def _extract_video_info(self, video_data):
         video_url = video_data.get('progressive_url_hd') or video_data.get('progressive_url')
-        return {'id': video_data['id'],
-                'url': video_url,
-                'ext': 'mp4',
-                'title': video_data['caption'],
-                'thumbnail': video_data['thumbnail_url'],
-                'upload_date': video_data['updated_at'].replace('-','')[:8],
-                }
+        return {
+            'id': compat_str(video_data['id']),
+            'url': video_url,
+            'ext': 'mp4',
+            'title': video_data['caption'],
+            'thumbnail': video_data['thumbnail_url'],
+            'upload_date': video_data['updated_at'].replace('-', '')[:8],
+        }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -40,36 +45,36 @@ class LivestreamIE(InfoExtractor):
 
         if video_id is None:
             # This is an event page:
-            config_json = self._search_regex(r'window.config = ({.*?});',
-                webpage, u'window config')
+            config_json = self._search_regex(
+                r'window.config = ({.*?});', webpage, 'window config')
             info = json.loads(config_json)['event']
             videos = [self._extract_video_info(video_data['data'])
-                for video_data in info['feed']['data'] if video_data['type'] == u'video']
+                for video_data in info['feed']['data'] if video_data['type'] == 'video']
             return self.playlist_result(videos, info['id'], info['full_name'])
         else:
-            og_video = self._og_search_video_url(webpage, name=u'player url')
+            og_video = self._og_search_video_url(webpage, 'player url')
             query_str = compat_urllib_parse_urlparse(og_video).query
             query = compat_urlparse.parse_qs(query_str)
             api_url = query['play_url'][0].replace('.smil', '')
-            info = json.loads(self._download_webpage(api_url, video_id,
-                                                     u'Downloading video info'))
+            info = json.loads(self._download_webpage(
+                api_url, video_id, 'Downloading video info'))
             return self._extract_video_info(info)
 
 
 # The original version of Livestream uses a different system
 class LivestreamOriginalIE(InfoExtractor):
-    IE_NAME = u'livestream:original'
+    IE_NAME = 'livestream:original'
     _VALID_URL = r'https?://www\.livestream\.com/(?P<user>[^/]+)/video\?.*?clipId=(?P<id>.*?)(&|$)'
     _TEST = {
-        u'url': u'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
-        u'info_dict': {
-            u'id': u'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
-            u'ext': u'flv',
-            u'title': u'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
+        'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
+        'info_dict': {
+            'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
+            'ext': 'flv',
+            'title': 'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
         },
-        u'params': {
+        'params': {
             # rtmp
-            u'skip_download': True,
+            'skip_download': True,
         },
     }
 
@@ -84,7 +89,7 @@ class LivestreamOriginalIE(InfoExtractor):
         ns = {'media': 'http://search.yahoo.com/mrss'}
         thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url']
         # Remove the extension and number from the path (like 1.jpg)
-        path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, u'path')
+        path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, 'path')
 
         return {
             'id': video_id,

youtube_dl/extractor/mailru.py

@@ -9,29 +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',
-            'timestamp': 1393232740,
-            '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']
@@ -40,6 +59,8 @@ 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']
 

youtube_dl/extractor/mtv.py

@@ -22,6 +22,7 @@ def _media_xml_tag(tag):
 
 class MTVServicesInfoExtractor(InfoExtractor):
     _MOBILE_TEMPLATE = None
+
     @staticmethod
     def _id_from_uri(uri):
         return uri.split(':')[-1]
@@ -35,6 +36,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
         base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
         return base + m.group('finalid')
 
+    def _get_feed_url(self, uri):
+        return self._FEED_URL
+
     def _get_thumbnail_url(self, uri, itemdoc):
         search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
         thumb_node = itemdoc.find(search_path)
@@ -80,6 +84,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
                                 })
             except (KeyError, TypeError):
                 raise ExtractorError('Invalid rendition field.')
+        self._sort_formats(formats)
         return formats
 
     def _get_video_info(self, itemdoc):
@@ -135,10 +140,10 @@ class MTVServicesInfoExtractor(InfoExtractor):
 
     def _get_videos_info(self, uri):
         video_id = self._id_from_uri(uri)
+        feed_url = self._get_feed_url(uri)
         data = compat_urllib_parse.urlencode({'uri': uri})
-
         idoc = self._download_xml(
-            self._FEED_URL + '?' + data, video_id,
+            feed_url + '?' + data, video_id,
             'Downloading info', transform_source=fix_xml_ampersands)
         return [self._get_video_info(item) for item in idoc.findall('.//item')]
 
@@ -159,6 +164,37 @@ class MTVServicesInfoExtractor(InfoExtractor):
         return self._get_videos_info(mgid)
 
 
+class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
+    IE_NAME = 'mtvservices:embedded'
+    _VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)'
+
+    _TEST = {
+        # From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/
+        'url': 'http://media.mtvnservices.com/embed/mgid:uma:video:mtv.com:1043906/cp~vid%3D1043906%26uri%3Dmgid%3Auma%3Avideo%3Amtv.com%3A1043906',
+        'md5': 'cb349b21a7897164cede95bd7bf3fbb9',
+        'info_dict': {
+            'id': '1043906',
+            'ext': 'mp4',
+            'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds',
+            'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.',
+        },
+    }
+
+    def _get_feed_url(self, uri):
+        video_id = self._id_from_uri(uri)
+        site_id = uri.replace(video_id, '')
+        config_url = 'http://media.mtvnservices.com/pmt/e1/players/{0}/config.xml'.format(site_id)
+        config_doc = self._download_xml(config_url, video_id)
+        feed_node = config_doc.find('.//feed')
+        feed_url = feed_node.text.strip().split('?')[0]
+        return feed_url
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        mgid = mobj.group('mgid')
+        return self._get_videos_info(mgid)
+
+
 class MTVIE(MTVServicesInfoExtractor):
     _VALID_URL = r'''(?x)^https?://
         (?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$|

youtube_dl/extractor/naver.py

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

youtube_dl/extractor/ndtv.py

@@ -1,22 +1,28 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import month_by_name
+from ..utils import (
+    month_by_name,
+    int_or_none,
+)
 
 
 class NDTVIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?ndtv\.com/video/player/[^/]*/[^/]*/(?P<id>[a-z0-9]+)'
 
     _TEST = {
-        u"url": u"http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710",
-        u"file": u"300710.mp4",
-        u"md5": u"39f992dbe5fb531c395d8bbedb1e5e88",
-        u"info_dict": {
-            u"title": u"NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal",
-            u"description": u"In an exclusive interview to NDTV, Aam Aadmi Party's Arvind Kejriwal says it makes no difference to him that Rahul Gandhi said the Congress needs to learn from his party.",
-            u"upload_date": u"20131208",
-            u"duration": 1327,
-            u"thumbnail": u"http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg",
+        'url': 'http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710',
+        'md5': '39f992dbe5fb531c395d8bbedb1e5e88',
+        'info_dict': {
+            'id': '300710',
+            'ext': 'mp4',
+            'title': "NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal",
+            'description': 'md5:ab2d4b4a6056c5cb4caa6d729deabf02',
+            'upload_date': '20131208',
+            'duration': 1327,
+            'thumbnail': 'http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg',
         },
     }
 
@@ -27,13 +33,12 @@ class NDTVIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         filename = self._search_regex(
-            r"__filename='([^']+)'", webpage, u'video filename')
-        video_url = (u'http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' %
+            r"__filename='([^']+)'", webpage, 'video filename')
+        video_url = ('http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' %
                      filename)
 
-        duration_str = filename = self._search_regex(
-            r"__duration='([^']+)'", webpage, u'duration', fatal=False)
-        duration = None if duration_str is None else int(duration_str)
+        duration = int_or_none(self._search_regex(
+            r"__duration='([^']+)'", webpage, 'duration', fatal=False))
 
         date_m = re.search(r'''(?x)
             <p\s+class="vod_dateline">\s*
@@ -41,7 +46,7 @@ class NDTVIE(InfoExtractor):
                 (?P<monthname>[A-Za-z]+)\s+(?P<day>[0-9]+),\s*(?P<year>[0-9]+)
             ''', webpage)
         upload_date = None
-        assert date_m
+
         if date_m is not None:
             month = month_by_name(date_m.group('monthname'))
             if month is not None:
@@ -49,14 +54,19 @@ class NDTVIE(InfoExtractor):
                     date_m.group('year'), month, int(date_m.group('day')))
 
         description = self._og_search_description(webpage)
-        READ_MORE = u' (Read more)'
+        READ_MORE = ' (Read more)'
         if description.endswith(READ_MORE):
             description = description[:-len(READ_MORE)]
 
+        title = self._og_search_title(webpage)
+        TITLE_SUFFIX = ' - NDTV'
+        if title.endswith(TITLE_SUFFIX):
+            title = title[:-len(TITLE_SUFFIX)]
+
         return {
             'id': video_id,
             'url': video_url,
-            'title': self._og_search_title(webpage),
+            'title': title,
             'description': description,
             'thumbnail': self._og_search_thumbnail(webpage),
             'duration': duration,

youtube_dl/extractor/noco.py

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

youtube_dl/extractor/nrk.py

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

youtube_dl/extractor/ntv.py

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

youtube_dl/extractor/nuvid.py

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

youtube_dl/extractor/prosiebensat1.py

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

youtube_dl/extractor/rai.py

@@ -0,0 +1,121 @@
+from __future__ import unicode_literals
+
+import re
+
+from .subtitles import SubtitlesInfoExtractor
+from ..utils import (
+    parse_duration,
+    unified_strdate,
+    compat_urllib_parse,
+)
+
+
+class RaiIE(SubtitlesInfoExtractor):
+    _VALID_URL = r'(?P<url>http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html)'
+    _TESTS = [
+        {
+            'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
+            'md5': 'c064c0b2d09c278fb293116ef5d0a32d',
+            'info_dict': {
+                'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
+                'ext': 'mp4',
+                'title': 'Report del 07/04/2014',
+                'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
+                'upload_date': '20140407',
+                'duration': 6160,
+            }
+        },
+        {
+            'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
+            'md5': '8bb9c151924ce241b74dd52ef29ceafa',
+            'info_dict': {
+                'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
+                'ext': 'mp4',
+                'title': 'TG PRIMO TEMPO',
+                'description': '',
+                'upload_date': '20140612',
+                'duration': 1758,
+            }
+        },
+        {
+            'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
+            'md5': '35cf7c229f22eeef43e48b5cf923bef0',
+            'info_dict': {
+                'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13',
+                'ext': 'mp4',
+                'title': 'State of the Net, Antonella La Carpia: regole virali',
+                'description': 'md5:b0ba04a324126903e3da7763272ae63c',
+                'upload_date': '20140613',
+            },
+            'skip': 'Error 404',
+        },
+        {
+            'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
+            'md5': '35694f062977fe6619943f08ed935730',
+            'info_dict': {
+                'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
+                'ext': 'mp4',
+                'title': 'Alluvione in Sardegna e dissesto idrogeologico',
+                'description': 'Edizione delle ore 20:30 ',
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        media = self._download_json('%s?json' % mobj.group('url'), video_id, 'Downloading video JSON')
+
+        title = media.get('name')
+        description = media.get('desc')
+        thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
+        duration = parse_duration(media.get('length'))
+        uploader = media.get('author')
+        upload_date = unified_strdate(media.get('date'))
+
+        formats = []
+
+        for format_id in ['wmv', 'm3u8', 'mediaUri', 'h264']:
+            media_url = media.get(format_id)
+            if not media_url:
+                continue
+            formats.append({
+                'url': media_url,
+                'format_id': format_id,
+                'ext': 'mp4',
+            })
+
+        if self._downloader.params.get('listsubtitles', False):
+            page = self._download_webpage(url, video_id)
+            self._list_available_subtitles(video_id, page)
+            return
+
+        subtitles = {}
+        if self._have_to_download_any_subtitles:
+            page = self._download_webpage(url, video_id)
+            subtitles = self.extract_subtitles(video_id, page)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'upload_date': upload_date,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+    def _get_available_subtitles(self, video_id, webpage):
+        subtitles = {}
+        m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
+        if m:
+            captions = m.group('captions')
+            STL_EXT = '.stl'
+            SRT_EXT = '.srt'
+            if captions.endswith(STL_EXT):
+                captions = captions[:-len(STL_EXT)] + SRT_EXT
+            subtitles['it'] = 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions)
+        return subtitles

youtube_dl/extractor/slutload.py

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

youtube_dl/extractor/soundcloud.py

@@ -1,7 +1,6 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import json
 import re
 import itertools
 
@@ -12,6 +11,7 @@ from ..utils import (
     compat_urllib_parse,
 
     ExtractorError,
+    int_or_none,
     unified_strdate,
 )
 
@@ -44,7 +44,8 @@ class SoundcloudIE(InfoExtractor):
                 "upload_date": "20121011",
                 "description": "No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd",
                 "uploader": "E.T. ExTerrestrial Music",
-                "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
+                "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1",
+                "duration": 143,
             }
         },
         # not streamable song
@@ -57,6 +58,7 @@ class SoundcloudIE(InfoExtractor):
                 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com',
                 'uploader': 'The Royal Concept',
                 'upload_date': '20120521',
+                'duration': 227,
             },
             'params': {
                 # rtmp
@@ -74,6 +76,7 @@ class SoundcloudIE(InfoExtractor):
                 'uploader': 'jaimeMF',
                 'description': 'test chars:  \"\'/\\ä↭',
                 'upload_date': '20131209',
+                'duration': 9,
             },
         },
         # downloadable song
@@ -87,6 +90,7 @@ class SoundcloudIE(InfoExtractor):
                 'description': 'Vocals',
                 'uploader': 'Sim Gretina',
                 'upload_date': '20130815',
+                #'duration': 42,
             },
         },
     ]
@@ -119,6 +123,7 @@ class SoundcloudIE(InfoExtractor):
             'title': info['title'],
             'description': info['description'],
             'thumbnail': thumbnail,
+            'duration': int_or_none(info.get('duration'), 1000),
         }
         formats = []
         if info.get('downloadable', False):

youtube_dl/extractor/spiegel.py

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

youtube_dl/extractor/spiegeltv.py

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

youtube_dl/extractor/steam.py

@@ -53,7 +53,7 @@ class SteamIE(InfoExtractor):
             'ext': 'mp4',
             'upload_date': '20140329',
             'title': 'FRONTIERS - Final Greenlight Trailer',
-            'description': "The final trailer for the Steam Greenlight launch. Hooray, progress! Here's the official Greenlight page: http://steamcommunity.com/sharedfiles/filedetails/?id=242472205",
+            'description': 'md5:6df4fe8dd494ae811869672b0767e025',
             'uploader': 'AAD Productions',
             'uploader_id': 'AtomicAgeDogGames',
         }

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 +1,106 @@
+# -*- 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',
+            'description': 'Measures of dispersion from a frequency table',
+            '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': 'Learn how to make paper dolls in this simple',
+            '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 TEHNI?KE ?KOLE P',
+        },
+    }]
+
+    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_meta('title', webpage, 'title')
+        TITLE_SUFFIX = ' - TeacherTube'
+        if title.endswith(TITLE_SUFFIX):
+            title = title[:-len(TITLE_SUFFIX)].strip()
+
+        description = self._html_search_meta('description', webpage, 'description')
+        if description:
+            description = description.strip()
+
+        quality = qualities(['mp3', 'flv', 'mp4'])
+
+        media_urls = re.findall(r'data-contenturl="([^"]+)"', webpage)
+        media_urls.extend(re.findall(r'var\s+filePath\s*=\s*"([^"]+)"', webpage))
+
+        formats = [
+            {
+                'url': media_url,
+                'quality': quality(determine_ext(media_url))
+            } for media_url in set(media_urls)
+        ]
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': self._html_search_regex(r'var\s+thumbUrl\s*=\s*"([^"]+)"', webpage, 'thumbnail'),
+            'formats': formats,
+            'description': description,
+        }
+
+
+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

@@ -27,7 +27,7 @@ class TEDIE(SubtitlesInfoExtractor):
         '''
     _TESTS = [{
         'url': 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html',
-        'md5': '4ea1dada91e4174b53dac2bb8ace429d',
+        'md5': 'fc94ac279feebbce69f21c0c6ee82810',
         'info_dict': {
             'id': '102',
             'ext': 'mp4',

youtube_dl/extractor/tube8.py

@@ -17,9 +17,10 @@ class Tube8IE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/){2}(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
-        'file': '229795.mp4',
-        'md5': 'e9e0b0c86734e5e3766e653509475db0',
+        'md5': '44bf12b98313827dd52d35b8706a4ea0',
         'info_dict': {
+            'id': '229795',
+            'ext': 'mp4',
             'description': 'hot teen Kasia grinding',
             'uploader': 'unknown',
             'title': 'Kasia music video',

youtube_dl/extractor/veoh.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_request,
     int_or_none,
+    ExtractorError,
 )
 
 
@@ -94,8 +95,12 @@ class VeohIE(InfoExtractor):
         if video_id.startswith('v'):
             rsp = self._download_xml(
                 r'http://www.veoh.com/api/findByPermalink?permalink=%s' % video_id, video_id, 'Downloading video XML')
-            if rsp.get('stat') == 'ok':
+            stat = rsp.get('stat')
+            if stat == 'ok':
                 return self._extract_video(rsp.find('./videoList/video'))
+            elif stat == 'fail':
+                raise ExtractorError(
+                    '%s said: %s' % (self.IE_NAME, rsp.find('./errorList/error').get('errorMessage')), expected=True)
 
         webpage = self._download_webpage(url, video_id)
         age_limit = 0

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/vulture.py

@@ -0,0 +1,69 @@
+from __future__ import unicode_literals
+
+import json
+import os.path
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class VultureIE(InfoExtractor):
+    IE_NAME = 'vulture.com'
+    _VALID_URL = r'https?://video\.vulture\.com/video/(?P<display_id>[^/]+)/'
+    _TEST = {
+        'url': 'http://video.vulture.com/video/Mindy-Kaling-s-Harvard-Speech/player?layout=compact&read_more=1',
+        'md5': '8d997845642a2b5152820f7257871bc8',
+        'info_dict': {
+            'id': '6GHRQL3RV7MSD1H4',
+            'ext': 'mp4',
+            'title': 'kaling-speech-2-MAGNIFY STANDARD CONTAINER REVISED',
+            'uploader_id': 'Sarah',
+            'thumbnail': 're:^http://.*\.jpg$',
+            'timestamp': 1401288564,
+            'upload_date': '20140528',
+            'description': 'Uplifting and witty, as predicted.',
+            'duration': 1015,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+        query_string = self._search_regex(
+            r"queryString\s*=\s*'([^']+)'", webpage, 'query string')
+        video_id = self._search_regex(
+            r'content=([^&]+)', query_string, 'video ID')
+        query_url = 'http://video.vulture.com/embed/player/container/1000/1000/?%s' % query_string
+
+        query_webpage = self._download_webpage(
+            query_url, display_id, note='Downloading query page')
+        params_json = self._search_regex(
+            r'(?sm)new MagnifyEmbeddablePlayer\({.*?contentItem:\s*(\{.*?\})\n,\n',
+            query_webpage,
+            'player params')
+        params = json.loads(params_json)
+
+        upload_timestamp = parse_iso8601(params['posted'].replace(' ', 'T'))
+        uploader_id = params.get('user', {}).get('handle')
+
+        media_item = params['media_item']
+        title = os.path.splitext(media_item['title'])[0]
+        duration = int_or_none(media_item.get('duration_seconds'))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': media_item['pipeline_xid'],
+            'title': title,
+            'timestamp': upload_timestamp,
+            'thumbnail': params.get('thumbnail_url'),
+            'uploader_id': uploader_id,
+            'description': params.get('description'),
+            'duration': duration,
+        }

youtube_dl/extractor/wrzuta.py

@@ -0,0 +1,81 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    qualities,
+)
+
+
+class WrzutaIE(InfoExtractor):
+    IE_NAME = 'wrzuta.pl'
+
+    _VALID_URL = r'https?://(?P<uploader>[0-9a-zA-Z]+)\.wrzuta\.pl/(?P<typ>film|audio)/(?P<id>[0-9a-zA-Z]+)'
+
+    _TESTS = [{
+        'url': 'http://laboratoriumdextera.wrzuta.pl/film/aq4hIZWrkBu/nike_football_the_last_game',
+        'md5': '9e67e05bed7c03b82488d87233a9efe7',
+        'info_dict': {
+            'id': 'aq4hIZWrkBu',
+            'ext': 'mp4',
+            'title': 'Nike Football: The Last Game',
+            'duration': 307,
+            'uploader_id': 'laboratoriumdextera',
+            'description': 'md5:7fb5ef3c21c5893375fda51d9b15d9cd',
+        },
+    }, {
+        'url': 'http://w729.wrzuta.pl/audio/9oXJqdcndqv/david_guetta_amp_showtek_ft._vassy_-_bad',
+        'md5': '1e546a18e1c22ac6e9adce17b8961ff5',
+        'info_dict': {
+            'id': '9oXJqdcndqv',
+            'ext': 'ogg',
+            'title': 'David Guetta & Showtek ft. Vassy - Bad',
+            'duration': 270,
+            'uploader_id': 'w729',
+            'description': 'md5:4628f01c666bbaaecefa83476cfa794a',
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        typ = mobj.group('typ')
+        uploader = mobj.group('uploader')
+
+        webpage = self._download_webpage(url, video_id)
+
+        quality = qualities(['SD', 'MQ', 'HQ', 'HD'])
+
+        audio_table = {'flv': 'mp3', 'webm': 'ogg'}
+
+        embedpage = self._download_json('http://www.wrzuta.pl/npp/embed/%s/%s' % (uploader, video_id), video_id)
+
+        formats = []
+        for media in embedpage['url']:
+            if typ == 'audio':
+                ext = audio_table[media['type'].split('@')[0]]
+            else:
+                ext = media['type'].split('@')[0]
+
+            formats.append({
+                'format_id': '%s_%s' % (ext, media['quality'].lower()),
+                'url': media['url'],
+                'ext': ext,
+                'quality': quality(media['quality']),
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': formats,
+            'duration': int_or_none(embedpage['duration']),
+            'uploader_id': uploader,
+            'description': self._og_search_description(webpage),
+            'age_limit': embedpage.get('minimalAge', 0),
+        }

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

@@ -223,6 +223,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         '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},
+        '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
 
         # Dash webm audio
         '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 48, 'preference': -50},
@@ -439,7 +441,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
 
     def _parse_sig_js(self, jscode):
         funcname = self._search_regex(
-            r'signature=([a-zA-Z]+)', jscode,
+            r'signature=([$a-zA-Z]+)', jscode,
              u'Initial JS player signature function name')
 
         jsi = JSInterpreter(jscode)
@@ -1140,7 +1142,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         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) on (.*?)</strong>',
+                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())
@@ -1385,13 +1387,13 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
                         |  p/
                         )
                         (
-                            (?:PL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,}
+                            (?:PL|LL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,}
                             # Top tracks, they can also include dots 
                             |(?:MC)[\w\.]*
                         )
                         .*
                      |
-                        ((?:PL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,})
+                        ((?:PL|LL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,})
                      )"""
     _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
     _MORE_PAGES_INDICATOR = r'data-link-type="next"'
@@ -1414,11 +1416,9 @@ 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)

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.05.31.1'
+__version__ = '2014.06.24'