release 2016.01.15

This reverts commit ffbc0baf72.

AUTHORS

@@ -151,3 +151,5 @@ Muratcan Simsek
 Evan Lu
 flatgreen
 Brian Foley
+Vignesh Venkat
+Tom Gijselinck

devscripts/gh-pages/update-copyright.py

@@ -5,7 +5,7 @@ from __future__ import with_statement, unicode_literals
 
 import datetime
 import glob
-import io  # For Python 2 compatibilty
+import io  # For Python 2 compatibility
 import os
 import re
 

docs/supportedsites.md

@@ -24,6 +24,7 @@
  - **AdobeTVShow**
  - **AdobeTVVideo**
  - **AdultSwim**
+ - **AE**
  - **Aftonbladet**
  - **AirMozilla**
  - **AlJazeera**
@@ -65,6 +66,7 @@
  - **Beeg**
  - **BehindKink**
  - **Bet**
+ - **Bigflix**
  - **Bild**: Bild.de
  - **BiliBili**
  - **BleacherReport**
@@ -84,6 +86,7 @@
  - **CamdemyFolder**
  - **canalc2.tv**
  - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
+ - **Canvas**
  - **CBS**
  - **CBSNews**: CBS News
  - **CBSSports**
@@ -121,6 +124,7 @@
  - **CSpan**: C-SPAN
  - **CtsNews**: 華視新聞
  - **culturebox.francetvinfo.fr**
+ - **CWTV**
  - **dailymotion**
  - **dailymotion:playlist**
  - **dailymotion:user**
@@ -228,7 +232,6 @@
  - **Helsinki**: helsinki.fi
  - **HentaiStigma**
  - **HistoricFilms**
- - **History**
  - **hitbox**
  - **hitbox:live**
  - **HornBunny**
@@ -251,7 +254,7 @@
  - **Instagram**
  - **instagram:user**: Instagram user profile
  - **InternetVideoArchive**
- - **IPrima**
+ - **IPrima** (Currently broken)
  - **iqiyi**: 爱奇艺
  - **Ir90Tv**
  - **ivi**: ivi.ru
@@ -602,7 +605,9 @@
  - **TruTube**
  - **Tube8**
  - **TubiTv**
- - **Tudou**
+ - **tudou**
+ - **tudou:album**
+ - **tudou:playlist**
  - **Tumblr**
  - **tunein:clip**
  - **tunein:program**
@@ -655,12 +660,12 @@
  - **video.mit.edu**
  - **VideoDetective**
  - **videofy.me**
- - **VideoMega**
+ - **VideoMega** (Currently broken)
  - **videomore**
  - **videomore:season**
  - **videomore:video**
  - **VideoPremium**
- - **VideoTt**: video.tt - Your True Tube
+ - **VideoTt**: video.tt - Your True Tube (Currently broken)
  - **videoweed**: VideoWeed
  - **Vidme**
  - **Vidzi**

test/test_YoutubeDL.py

@@ -12,7 +12,7 @@ import copy
 
 from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
-from youtube_dl.compat import compat_str
+from youtube_dl.compat import compat_str, compat_urllib_error
 from youtube_dl.extractor import YoutubeIE
 from youtube_dl.postprocessor.common import PostProcessor
 from youtube_dl.utils import ExtractorError, match_filter_func
@@ -631,6 +631,11 @@ class TestYoutubeDL(unittest.TestCase):
         result = get_ids({'playlist_items': '10'})
         self.assertEqual(result, [])
 
+    def test_urlopen_no_file_protocol(self):
+        # see https://github.com/rg3/youtube-dl/issues/8227
+        ydl = YDL()
+        self.assertRaises(compat_urllib_error.URLError, ydl.urlopen, 'file:///etc/passwd')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_write_annotations.py

@@ -66,7 +66,7 @@ class TestAnnotations(unittest.TestCase):
                 textTag = a.find('TEXT')
                 text = textTag.text
                 self.assertTrue(text in expected)  # assertIn only added in python 2.7
-                # remove the first occurance, there could be more than one annotation with the same text
+                # remove the first occurrence, there could be more than one annotation with the same text
                 expected.remove(text)
         # We should have seen (and removed) all the expected annotation texts.
         self.assertEqual(len(expected), 0, 'Not all expected annotations were found.')

youtube_dl/YoutubeDL.py

@@ -1312,7 +1312,7 @@ class YoutubeDL(object):
             # only set the 'formats' fields if the original info_dict list them
             # otherwise we end up with a circular reference, the first (and unique)
             # element in the 'formats' field in info_dict is info_dict itself,
-            # wich can't be exported to json
+            # which can't be exported to json
             info_dict['formats'] = formats
         if self.params.get('listformats'):
             self.list_formats(info_dict)
@@ -1986,8 +1986,19 @@ class YoutubeDL(object):
         https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
         ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
         data_handler = compat_urllib_request_DataHandler()
+
+        # When passing our own FileHandler instance, build_opener won't add the
+        # default FileHandler and allows us to disable the file protocol, which
+        # can be used for malicious purposes (see
+        # https://github.com/rg3/youtube-dl/issues/8227)
+        file_handler = compat_urllib_request.FileHandler()
+
+        def file_open(*args, **kwargs):
+            raise compat_urllib_error.URLError('file:// scheme is explicitly disabled in youtube-dl for security reasons')
+        file_handler.file_open = file_open
+
         opener = compat_urllib_request.build_opener(
-            proxy_handler, https_handler, cookie_processor, ydlh, data_handler)
+            proxy_handler, https_handler, cookie_processor, ydlh, data_handler, file_handler)
 
         # Delete the default user-agent header, which would otherwise apply in
         # cases where our custom HTTP handler doesn't come into play

youtube_dl/downloader/fragment.py

@@ -59,37 +59,43 @@ class FragmentFD(FileDownloader):
             'filename': ctx['filename'],
             'tmpfilename': ctx['tmpfilename'],
         }
+
         start = time.time()
-        ctx['started'] = start
+        ctx.update({
+            'started': start,
+            # Total complete fragments downloaded so far in bytes
+            'complete_frags_downloaded_bytes': 0,
+            # Amount of fragment's bytes downloaded by the time of the previous
+            # frag progress hook invocation
+            'prev_frag_downloaded_bytes': 0,
+        })
 
         def frag_progress_hook(s):
             if s['status'] not in ('downloading', 'finished'):
                 return
 
-            frag_total_bytes = s.get('total_bytes', 0)
-            if s['status'] == 'finished':
-                state['downloaded_bytes'] += frag_total_bytes
-                state['frag_index'] += 1
+            frag_total_bytes = s.get('total_bytes') or 0
 
             estimated_size = (
-                (state['downloaded_bytes'] + frag_total_bytes) /
+                (ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) /
                 (state['frag_index'] + 1) * total_frags)
             time_now = time.time()
             state['total_bytes_estimate'] = estimated_size
             state['elapsed'] = time_now - start
 
             if s['status'] == 'finished':
-                progress = self.calc_percent(state['frag_index'], total_frags)
+                state['frag_index'] += 1
+                state['downloaded_bytes'] += frag_total_bytes - ctx['prev_frag_downloaded_bytes']
+                ctx['complete_frags_downloaded_bytes'] = state['downloaded_bytes']
+                ctx['prev_frag_downloaded_bytes'] = 0
             else:
                 frag_downloaded_bytes = s['downloaded_bytes']
-                frag_progress = self.calc_percent(frag_downloaded_bytes,
-                                                  frag_total_bytes)
-                progress = self.calc_percent(state['frag_index'], total_frags)
-                progress += frag_progress / float(total_frags)
-
+                state['downloaded_bytes'] += frag_downloaded_bytes - ctx['prev_frag_downloaded_bytes']
                 state['eta'] = self.calc_eta(
-                    start, time_now, estimated_size, state['downloaded_bytes'] + frag_downloaded_bytes)
+                    start, time_now, estimated_size,
+                    state['downloaded_bytes'])
                 state['speed'] = s.get('speed')
+                ctx['prev_frag_downloaded_bytes'] = frag_downloaded_bytes
             self._hook_progress(state)
 
         ctx['dl'].add_progress_hook(frag_progress_hook)

youtube_dl/extractor/__init__.py

@@ -15,6 +15,7 @@ from .adobetv import (
     AdobeTVVideoIE,
 )
 from .adultswim import AdultSwimIE
+from .ae import AEIE
 from .aftonbladet import AftonbladetIE
 from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
@@ -61,6 +62,7 @@ from .beeg import BeegIE
 from .behindkink import BehindKinkIE
 from .beatportpro import BeatportProIE
 from .bet import BetIE
+from .bigflix import BigflixIE
 from .bild import BildIE
 from .bilibili import BiliBiliIE
 from .bleacherreport import (
@@ -85,6 +87,7 @@ from .camdemy import (
 )
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
+from .canvas import CanvasIE
 from .cbs import CBSIE
 from .cbsnews import CBSNewsIE
 from .cbssports import CBSSportsIE
@@ -127,6 +130,7 @@ from .crunchyroll import (
 )
 from .cspan import CSpanIE
 from .ctsnews import CtsNewsIE
+from .cwtv import CWTVIE
 from .dailymotion import (
     DailymotionIE,
     DailymotionPlaylistIE,
@@ -261,7 +265,6 @@ from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
 from .historicfilms import HistoricFilmsIE
-from .history import HistoryIE
 from .hitbox import HitboxIE, HitboxLiveIE
 from .hornbunny import HornBunnyIE
 from .hotnewhiphop import HotNewHipHopIE
@@ -722,7 +725,11 @@ from .trilulilu import TriluliluIE
 from .trutube import TruTubeIE
 from .tube8 import Tube8IE
 from .tubitv import TubiTvIE
-from .tudou import TudouIE
+from .tudou import (
+    TudouIE,
+    TudouPlaylistIE,
+    TudouAlbumIE,
+)
 from .tumblr import TumblrIE
 from .tunein import (
     TuneInClipIE,

youtube_dl/extractor/ae.py

@@ -0,0 +1,58 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import smuggle_url
+
+
+class AEIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])'
+
+    _TESTS = [{
+        'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
+        'info_dict': {
+            'id': 'g12m5Gyt3fdR',
+            'ext': 'mp4',
+            'title': "Bet You Didn't Know: Valentine's Day",
+            'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'add_ie': ['ThePlatform'],
+    }, {
+        'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
+        'info_dict': {
+            'id': 'eg47EERs_JsZ',
+            'ext': 'mp4',
+            'title': "Winter Is Coming",
+            'description': 'md5:a40e370925074260b1c8a633c632c63a',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'add_ie': ['ThePlatform'],
+    }, {
+        'url': 'http://www.aetv.com/shows/duck-dynasty/video/inlawful-entry',
+        'only_matching': True
+    }, {
+        'url': 'http://www.fyi.tv/shows/tiny-house-nation/videos/207-sq-ft-minnesota-prairie-cottage',
+        'only_matching': True
+    }, {
+        'url': 'http://www.mylifetime.com/shows/project-runway-junior/video/season-1/episode-6/superstar-clients',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url_re = [
+            r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id,
+            r"media_url\s*=\s*'([^']+)'"
+        ]
+        video_url = self._search_regex(video_url_re, webpage, 'video url')
+
+        return self.url_result(smuggle_url(video_url, {'sig': {'key': 'crazyjava', 'secret': 's3cr3t'}}))

youtube_dl/extractor/beeg.py

@@ -34,7 +34,7 @@ class BeegIE(InfoExtractor):
         video_id = self._match_id(url)
 
         video = self._download_json(
-            'http://beeg.com/api/v5/video/%s' % video_id, video_id)
+            'https://api.beeg.com/api/v5/video/%s' % video_id, video_id)
 
         def split(o, e):
             def cut(s, x):
@@ -60,7 +60,7 @@ class BeegIE(InfoExtractor):
 
         def decrypt_url(encrypted_url):
             encrypted_url = self._proto_relative_url(
-                encrypted_url.replace('{DATA_MARKERS}', ''), 'http:')
+                encrypted_url.replace('{DATA_MARKERS}', ''), 'https:')
             key = self._search_regex(
                 r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None)
             if not key:

youtube_dl/extractor/bigflix.py

@@ -0,0 +1,85 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import base64
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
+
+
+class BigflixIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.bigflix.com/Hindi-movies/Action-movies/Singham-Returns/16537',
+        'md5': 'ec76aa9b1129e2e5b301a474e54fab74',
+        'info_dict': {
+            'id': '16537',
+            'ext': 'mp4',
+            'title': 'Singham Returns',
+            'description': 'md5:3d2ba5815f14911d5cc6a501ae0cf65d',
+        }
+    }, {
+        # 2 formats
+        'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
+        'info_dict': {
+            'id': '16070',
+            'ext': 'mp4',
+            'title': 'Madarasapatinam',
+            'description': 'md5:63b9b8ed79189c6f0418c26d9a3452ca',
+            'formats': 'mincount:2',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        # multiple formats
+        'url': 'http://www.bigflix.com/Malayalam-movies/Drama-movies/Indian-Rupee/15967',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+            r'<div[^>]+class=["\']pagetitle["\'][^>]*>(.+?)</div>',
+            webpage, 'title')
+
+        def decode_url(quoted_b64_url):
+            return base64.b64decode(compat_urllib_parse_unquote(
+                quoted_b64_url).encode('ascii')).decode('utf-8')
+
+        formats = []
+        for height, encoded_url in re.findall(
+                r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage):
+            video_url = decode_url(encoded_url)
+            f = {
+                'url': video_url,
+                'format_id': '%sp' % height,
+                'height': int(height),
+            }
+            if video_url.startswith('rtmp'):
+                f['ext'] = 'flv'
+            formats.append(f)
+
+        file_url = self._search_regex(
+            r'file=([^&]+)', webpage, 'video url', default=None)
+        if file_url:
+            video_url = decode_url(file_url)
+            if all(f['url'] != video_url for f in formats):
+                formats.append({
+                    'url': decode_url(file_url),
+                })
+
+        self._sort_formats(formats)
+
+        description = self._html_search_meta('description', webpage)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'formats': formats
+        }

youtube_dl/extractor/canalc2.py

@@ -9,9 +9,9 @@ from ..utils import parse_duration
 
 class Canalc2IE(InfoExtractor):
     IE_NAME = 'canalc2.tv'
-    _VALID_URL = r'https?://(?:www\.)?canalc2\.tv/video/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:(?:www\.)?canalc2\.tv/video/|archives-canalc2\.u-strasbg\.fr/video\.asp\?.*\bidVideo=)(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.canalc2.tv/video/12163',
         'md5': '060158428b650f896c542dfbb3d6487f',
         'info_dict': {
@@ -23,24 +23,36 @@ class Canalc2IE(InfoExtractor):
         'params': {
             'skip_download': True,  # Requires rtmpdump
         }
-    }
+    }, {
+        'url': 'http://archives-canalc2.u-strasbg.fr/video.asp?idVideo=11427&voir=oui',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        video_url = self._search_regex(
-            r'jwplayer\((["\'])Player\1\)\.setup\({[^}]*file\s*:\s*(["\'])(?P<file>.+?)\2',
-            webpage, 'video_url', group='file')
-        formats = [{'url': video_url}]
-        if video_url.startswith('rtmp://'):
-            rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
-            formats[0].update({
-                'url': rtmp.group('url'),
-                'ext': 'flv',
-                'app': rtmp.group('app'),
-                'play_path': rtmp.group('play_path'),
-                'page_url': url,
-            })
+
+        webpage = self._download_webpage(
+            'http://www.canalc2.tv/video/%s' % video_id, video_id)
+
+        formats = []
+        for _, video_url in re.findall(r'file\s*=\s*(["\'])(.+?)\1', webpage):
+            if video_url.startswith('rtmp://'):
+                rtmp = re.search(
+                    r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
+                formats.append({
+                    'url': rtmp.group('url'),
+                    'format_id': 'rtmp',
+                    'ext': 'flv',
+                    'app': rtmp.group('app'),
+                    'play_path': rtmp.group('play_path'),
+                    'page_url': url,
+                })
+            else:
+                formats.append({
+                    'url': video_url,
+                    'format_id': 'http',
+                })
+        self._sort_formats(formats)
 
         title = self._html_search_regex(
             r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')

youtube_dl/extractor/canvas.py

@@ -0,0 +1,65 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import float_or_none
+
+
+class CanvasIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?canvas\.be/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',
+        'md5': 'ea838375a547ac787d4064d8c7860a6c',
+        'info_dict': {
+            'id': 'mz-ast-5e5f90b6-2d72-4c40-82c2-e134f884e93e',
+            'display_id': 'de-afspraak-veilt-voor-de-warmste-week',
+            'ext': 'mp4',
+            'title': 'De afspraak veilt voor de Warmste Week',
+            'description': 'md5:24cb860c320dc2be7358e0e5aa317ba6',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 49.02,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._search_regex(
+            r'<h1[^>]+class="video__body__header__title"[^>]*>(.+?)</h1>',
+            webpage, 'title', default=None) or self._og_search_title(webpage)
+
+        video_id = self._html_search_regex(
+            r'data-video=(["\'])(?P<id>.+?)\1', webpage, 'video id', group='id')
+
+        data = self._download_json(
+            'https://mediazone.vrt.be/api/v1/canvas/assets/%s' % video_id, display_id)
+
+        formats = []
+        for target in data['targetUrls']:
+            format_url, format_type = target.get('url'), target.get('type')
+            if not format_url or not format_type:
+                continue
+            if format_type == 'HLS':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, display_id, entry_protocol='m3u8_native',
+                    ext='mp4', preference=0, fatal=False, m3u8_id=format_type))
+            elif format_type == 'HDS':
+                formats.extend(self._extract_f4m_formats(
+                    format_url, display_id, f4m_id=format_type, fatal=False))
+            else:
+                formats.append({
+                    'format_id': format_type,
+                    'url': format_url,
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'formats': formats,
+            'duration': float_or_none(data.get('duration'), 1000),
+            'thumbnail': data.get('posterImageUrl'),
+        }

youtube_dl/extractor/common.py

@@ -313,9 +313,9 @@ class InfoExtractor(object):
         except ExtractorError:
             raise
         except compat_http_client.IncompleteRead as e:
-            raise ExtractorError('A network error has occured.', cause=e, expected=True)
+            raise ExtractorError('A network error has occurred.', cause=e, expected=True)
         except (KeyError, StopIteration) as e:
-            raise ExtractorError('An extractor error has occured.', cause=e)
+            raise ExtractorError('An extractor error has occurred.', cause=e)
 
     def set_downloader(self, downloader):
         """Sets the downloader for this IE."""

youtube_dl/extractor/cwtv.py

@@ -0,0 +1,88 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class CWTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cw(?:tv|seed)\.com/shows/(?:[^/]+/){2}\?play=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
+    _TESTS = [{
+        'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63',
+        'info_dict': {
+            'id': '6b15e985-9345-4f60-baf8-56e96be57c63',
+            'ext': 'mp4',
+            'title': 'Legends of Yesterday',
+            'description': 'Oliver and Barry Allen take Kendra Saunders and Carter Hall to a remote location to keep them hidden from Vandal Savage while they figure out how to defeat him.',
+            'duration': 2665,
+            'series': 'Arrow',
+            'season_number': 4,
+            'season': '4',
+            'episode_number': 8,
+            'upload_date': '20151203',
+            'timestamp': 1449122100,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://www.cwseed.com/shows/whose-line-is-it-anyway/jeff-davis-4/?play=24282b12-ead2-42f2-95ad-26770c2c6088',
+        'info_dict': {
+            'id': '24282b12-ead2-42f2-95ad-26770c2c6088',
+            'ext': 'mp4',
+            'title': 'Jeff Davis 4',
+            'description': 'Jeff Davis is back to make you laugh.',
+            'duration': 1263,
+            'series': 'Whose Line Is It Anyway?',
+            'season_number': 11,
+            'season': '11',
+            'episode_number': 20,
+            'upload_date': '20151006',
+            'timestamp': 1444107300,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._download_json(
+            'http://metaframe.digitalsmiths.tv/v2/CWtv/assets/%s/partner/132?format=json' % video_id, video_id)
+
+        formats = self._extract_m3u8_formats(
+            video_data['videos']['variantplaylist']['uri'], video_id, 'mp4')
+
+        thumbnails = [{
+            'url': image['uri'],
+            'width': image.get('width'),
+            'height': image.get('height'),
+        } for image_id, image in video_data['images'].items() if image.get('uri')] if video_data.get('images') else None
+
+        video_metadata = video_data['assetFields']
+
+        subtitles = {
+            'en': [{
+                'url': video_metadata['UnicornCcUrl'],
+            }],
+        } if video_metadata.get('UnicornCcUrl') else None
+
+        return {
+            'id': video_id,
+            'title': video_metadata['title'],
+            'description': video_metadata.get('description'),
+            'duration': int_or_none(video_metadata.get('duration')),
+            'series': video_metadata.get('seriesName'),
+            'season_number': int_or_none(video_metadata.get('seasonNumber')),
+            'season': video_metadata.get('seasonName'),
+            'episode_number': int_or_none(video_metadata.get('episodeNumber')),
+            'timestamp': parse_iso8601(video_data.get('startTime')),
+            'thumbnails': thumbnails,
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/dailymotion.py

@@ -149,14 +149,15 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                     ext = determine_ext(media_url)
                     if type_ == 'application/x-mpegURL' or ext == 'm3u8':
                         formats.extend(self._extract_m3u8_formats(
-                            media_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+                            media_url, video_id, 'mp4', preference=-1,
+                            m3u8_id='hls', fatal=False))
                     elif type_ == 'application/f4m' or ext == 'f4m':
                         formats.extend(self._extract_f4m_formats(
                             media_url, video_id, preference=-1, f4m_id='hds', fatal=False))
                     else:
                         f = {
                             'url': media_url,
-                            'format_id': quality,
+                            'format_id': 'http-%s' % quality,
                         }
                         m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url)
                         if m:

youtube_dl/extractor/dcn.py

@@ -5,7 +5,10 @@ import re
 import base64
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import (
+    compat_urllib_parse,
+    compat_str,
+)
 from ..utils import (
     int_or_none,
     parse_iso8601,
@@ -186,7 +189,8 @@ class DCNSeasonIE(InfoExtractor):
 
                 entries = []
                 for video in show['videos']:
+                    video_id = compat_str(video['id'])
                     entries.append(self.url_result(
-                        'http://www.dcndigital.ae/media/%s' % video['id'], 'DCNVideo'))
+                        'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo', video_id))
 
                 return self.playlist_result(entries, season_id, title)

youtube_dl/extractor/facebook.py

@@ -105,7 +105,7 @@ class FacebookIE(InfoExtractor):
                     login_results, 'login error', default=None, group='error')
                 if error:
                     raise ExtractorError('Unable to login: %s' % error, expected=True)
-                self._downloader.report_warning('unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
+                self._downloader.report_warning('unable to log in: bad username/password, or exceeded login rate limit (~3/min). Check credentials or wait.')
                 return
 
             fb_dtsg = self._search_regex(
@@ -126,7 +126,7 @@ class FacebookIE(InfoExtractor):
             check_response = self._download_webpage(check_req, None,
                                                     note='Confirming login')
             if re.search(r'id="checkpointSubmitButton"', check_response) is not None:
-                self._downloader.report_warning('Unable to confirm login, you have to login in your brower and authorize the login.')
+                self._downloader.report_warning('Unable to confirm login, you have to login in your browser and authorize the login.')
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
             self._downloader.report_warning('unable to log in: %s' % error_to_compat_str(err))
             return

youtube_dl/extractor/generic.py

@@ -487,7 +487,7 @@ class GenericIE(InfoExtractor):
                 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
             }
         },
-        # Embeded Ustream video
+        # Embedded Ustream video
         {
             'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
             'md5': '27b99cdb639c9b12a79bca876a073417',
@@ -1644,7 +1644,7 @@ class GenericIE(InfoExtractor):
         if myvi_url:
             return self.url_result(myvi_url)
 
-        # Look for embeded soundcloud player
+        # Look for embedded soundcloud player
         mobj = re.search(
             r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
             webpage)

youtube_dl/extractor/history.py

@@ -1,31 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import smuggle_url
-
-
-class HistoryIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?history\.com/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])'
-
-    _TESTS = [{
-        'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
-        'md5': '6fe632d033c92aa10b8d4a9be047a7c5',
-        'info_dict': {
-            'id': 'bLx5Dv5Aka1G',
-            'ext': 'mp4',
-            'title': "Bet You Didn't Know: Valentine's Day",
-            'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
-        },
-        'add_ie': ['ThePlatform'],
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        video_url = self._search_regex(
-            r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id,
-            webpage, 'video url')
-
-        return self.url_result(smuggle_url(video_url, {'sig': {'key': 'crazyjava', 'secret': 's3cr3t'}}))

youtube_dl/extractor/iprima.py

@@ -14,6 +14,7 @@ from ..utils import (
 
 
 class IPrimaIE(InfoExtractor):
+    _WORKING = False
     _VALID_URL = r'https?://play\.iprima\.cz/(?:[^/]+/)*(?P<id>[^?#]+)'
 
     _TESTS = [{

youtube_dl/extractor/ivi.py

@@ -32,7 +32,7 @@ class IviIE(InfoExtractor):
             },
             'skip': 'Only works from Russia',
         },
-        # Serial's serie
+        # Serial's series
         {
             'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549',
             'md5': '221f56b35e3ed815fde2df71032f4b3e',

youtube_dl/extractor/mdr.py

@@ -17,7 +17,7 @@ class MDRIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+(?P<id>\d+)(?:_.+?)?\.html'
 
     _TESTS = [{
-        # MDR regularily deletes its videos
+        # MDR regularly deletes its videos
         'url': 'http://www.mdr.de/fakt/video189002.html',
         'only_matching': True,
     }, {

youtube_dl/extractor/nbc.py

@@ -100,7 +100,7 @@ class NBCSportsVPlayerIE(InfoExtractor):
 
 
 class NBCSportsIE(InfoExtractor):
-    # Does not include https becuase its certificate is invalid
+    # Does not include https because its certificate is invalid
     _VALID_URL = r'http://www\.nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
 
     _TEST = {

youtube_dl/extractor/nhl.py

@@ -223,7 +223,7 @@ class NHLVideocenterIE(NHLBaseInfoExtractor):
         response = self._download_webpage(request_url, playlist_title)
         response = self._fix_json(response)
         if not response.strip():
-            self._downloader.report_warning('Got an empty reponse, trying '
+            self._downloader.report_warning('Got an empty response, trying '
                                             'adding the "newvideos" parameter')
             response = self._download_webpage(request_url + '&newvideos=true',
                                               playlist_title)

youtube_dl/extractor/ntvde.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     int_or_none,
     js_to_json,
@@ -34,7 +35,7 @@ class NTVDeIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         info = self._parse_json(self._search_regex(
-            r'(?s)ntv.pageInfo.article =\s(\{.*?\});', webpage, 'info'),
+            r'(?s)ntv\.pageInfo\.article\s*=\s*(\{.*?\});', webpage, 'info'),
             video_id, transform_source=js_to_json)
         timestamp = int_or_none(info.get('publishedDateAsUnixTimeStamp'))
         vdata = self._parse_json(self._search_regex(
@@ -42,18 +43,24 @@ class NTVDeIE(InfoExtractor):
             webpage, 'player data'),
             video_id, transform_source=js_to_json)
         duration = parse_duration(vdata.get('duration'))
-        formats = [{
-            'format_id': 'flash',
-            'url': 'rtmp://fms.n-tv.de/' + vdata['video'],
-        }, {
-            'format_id': 'mobile',
-            'url': 'http://video.n-tv.de' + vdata['videoMp4'],
-            'tbr': 400,  # estimation
-        }]
-        m3u8_url = 'http://video.n-tv.de' + vdata['videoM3u8']
-        formats.extend(self._extract_m3u8_formats(
-            m3u8_url, video_id, ext='mp4',
-            entry_protocol='m3u8_native', preference=0))
+
+        formats = []
+        if vdata.get('video'):
+            formats.append({
+                'format_id': 'flash',
+                'url': 'rtmp://fms.n-tv.de/%s' % vdata['video'],
+            })
+        if vdata.get('videoMp4'):
+            formats.append({
+                'format_id': 'mobile',
+                'url': compat_urlparse.urljoin('http://video.n-tv.de', vdata['videoMp4']),
+                'tbr': 400,  # estimation
+            })
+        if vdata.get('videoM3u8'):
+            m3u8_url = compat_urlparse.urljoin('http://video.n-tv.de', vdata['videoM3u8'])
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native',
+                preference=0, m3u8_id='hls', fatal=False))
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/ora.py

@@ -37,7 +37,7 @@ class OraTVIE(InfoExtractor):
             formats = self._extract_m3u8_formats(
                 m3u8_url, display_id, 'mp4', 'm3u8_native',
                 m3u8_id='hls', fatal=False)
-            # simular to GameSpotIE
+            # similar to GameSpotIE
             m3u8_path = compat_urlparse.urlparse(m3u8_url).path
             QUALITIES_RE = r'((,[a-z]+\d+)+,?)'
             available_qualities = self._search_regex(

youtube_dl/extractor/orf.py

@@ -170,7 +170,21 @@ class ORFOE1IE(InfoExtractor):
 class ORFFM4IE(InfoExtractor):
     IE_NAME = 'orf:fm4'
     IE_DESC = 'radio FM4'
-    _VALID_URL = r'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)'
+    _VALID_URL = r'http://fm4\.orf\.at/(?:7tage/?#|player/)(?P<date>[0-9]+)/(?P<show>\w+)'
+
+    _TEST = {
+        'url': 'http://fm4.orf.at/player/20160110/IS/',
+        'md5': '01e736e8f1cef7e13246e880a59ad298',
+        'info_dict': {
+            'id': '2016-01-10_2100_tl_54_7DaysSun13_11244',
+            'ext': 'mp3',
+            'title': 'Im Sumpf',
+            'description': 'md5:384c543f866c4e422a55f66a62d669cd',
+            'duration': 7173,
+            'timestamp': 1452456073,
+            'upload_date': '20160110',
+        },
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/pluralsight.py

@@ -232,7 +232,7 @@ class PluralsightIE(PluralsightBaseIE):
         # { a = author, cn = clip_id, lc = end, m = name }
 
         return {
-            'id': clip['clipName'],
+            'id': clip.get('clipName') or clip['name'],
             'title': '%s - %s' % (module['title'], clip['title']),
             'duration': int_or_none(clip.get('duration')) or parse_duration(clip.get('formattedDuration')),
             'creator': author,

youtube_dl/extractor/prosiebensat1.py

@@ -20,7 +20,7 @@ from ..utils import (
 class ProSiebenSat1IE(InfoExtractor):
     IE_NAME = 'prosiebensat1'
     IE_DESC = 'ProSiebenSat.1 Digital'
-    _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at|ch)|ran\.de|fem\.com)/(?P<id>.+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany|7tv)\.(?:de|at|ch)|ran\.de|fem\.com)/(?P<id>.+)'
 
     _TESTS = [
         {
@@ -32,7 +32,7 @@ class ProSiebenSat1IE(InfoExtractor):
             'url': 'http://www.prosieben.de/tv/circus-halligalli/videos/218-staffel-2-episode-18-jahresrueckblick-ganze-folge',
             'info_dict': {
                 'id': '2104602',
-                'ext': 'mp4',
+                'ext': 'flv',
                 'title': 'Episode 18 - Staffel 2',
                 'description': 'md5:8733c81b702ea472e069bc48bb658fc1',
                 'upload_date': '20131231',
@@ -138,14 +138,13 @@ class ProSiebenSat1IE(InfoExtractor):
             'url': 'http://www.the-voice-of-germany.de/video/31-andreas-kuemmert-rocket-man-clip',
             'info_dict': {
                 'id': '2572814',
-                'ext': 'mp4',
+                'ext': 'flv',
                 'title': 'Andreas Kümmert: Rocket Man',
                 'description': 'md5:6ddb02b0781c6adf778afea606652e38',
                 'upload_date': '20131017',
                 'duration': 469.88,
             },
             'params': {
-                # rtmp download
                 'skip_download': True,
             },
         },
@@ -153,13 +152,12 @@ class ProSiebenSat1IE(InfoExtractor):
             'url': 'http://www.fem.com/wellness/videos/wellness-video-clip-kurztripps-zum-valentinstag.html',
             'info_dict': {
                 'id': '2156342',
-                'ext': 'mp4',
+                'ext': 'flv',
                 'title': 'Kurztrips zum Valentinstag',
-                'description': 'Romantischer Kurztrip zum Valentinstag? Wir verraten, was sich hier wirklich lohnt.',
+                'description': 'Romantischer Kurztrip zum Valentinstag? Nina Heinemann verrät, was sich hier wirklich lohnt.',
                 'duration': 307.24,
             },
             'params': {
-                # rtmp download
                 'skip_download': True,
             },
         },
@@ -172,12 +170,26 @@ class ProSiebenSat1IE(InfoExtractor):
             },
             'playlist_count': 2,
         },
+        {
+            'url': 'http://www.7tv.de/circus-halligalli/615-best-of-circus-halligalli-ganze-folge',
+            'info_dict': {
+                'id': '4187506',
+                'ext': 'flv',
+                'title': 'Best of Circus HalliGalli',
+                'description': 'md5:8849752efd90b9772c9db6fdf87fb9e9',
+                'upload_date': '20151229',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
     ]
 
     _CLIPID_REGEXES = [
         r'"clip_id"\s*:\s+"(\d+)"',
         r'clipid: "(\d+)"',
         r'clip[iI]d=(\d+)',
+        r'clip[iI]d\s*=\s*["\'](\d+)',
         r"'itemImageUrl'\s*:\s*'/dynamic/thumbnails/full/\d+/(\d+)",
     ]
     _TITLE_REGEXES = [
@@ -186,12 +198,16 @@ class ProSiebenSat1IE(InfoExtractor):
         r'<!-- start video -->\s*<h1>(.+?)</h1>',
         r'<h1 class="att-name">\s*(.+?)</h1>',
         r'<header class="module_header">\s*<h2>([^<]+)</h2>\s*</header>',
+        r'<h2 class="video-title" itemprop="name">\s*(.+?)</h2>',
+        r'<div[^>]+id="veeseoTitle"[^>]*>(.+?)</div>',
     ]
     _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 class="att-description">\s*(.+?)\s*</p>',
+        r'<p class="video-description" itemprop="description">\s*(.+?)</p>',
+        r'<div[^>]+id="veeseoDescription"[^>]*>(.+?)</div>',
     ]
     _UPLOAD_DATE_REGEXES = [
         r'<meta property="og:published_time" content="(.+?)">',

youtube_dl/extractor/shahid.py

@@ -73,6 +73,9 @@ class ShahidIE(InfoExtractor):
             'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-%s.html'
             % (video_id, api_vars['type']), video_id, 'Downloading player JSON')
 
+        if player.get('drm'):
+            raise ExtractorError('This video is DRM protected.', expected=True)
+
         formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
 
         video = self._download_json(

youtube_dl/extractor/testurl.py

@@ -7,7 +7,7 @@ from ..utils import ExtractorError
 
 
 class TestURLIE(InfoExtractor):
-    """ Allows adressing of the test cases as test:yout.*be_1 """
+    """ Allows addressing of the test cases as test:yout.*be_1 """
 
     IE_DESC = False  # Do not list
     _VALID_URL = r'test(?:url)?:(?P<id>(?P<extractor>.+?)(?:_(?P<num>[0-9]+))?)$'

youtube_dl/extractor/theplatform.py

@@ -85,7 +85,7 @@ class ThePlatformBaseIE(InfoExtractor):
 class ThePlatformIE(ThePlatformBaseIE):
     _VALID_URL = r'''(?x)
         (?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
-           (?:(?P<media>(?:[^/]+/)+select/media/)|(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/))?
+           (?:(?P<media>(?:(?:[^/]+/)+select/)?media/)|(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/))?
          |theplatform:)(?P<id>[^/\?&]+)'''
 
     _TESTS = [{

youtube_dl/extractor/tudou.py

@@ -4,10 +4,16 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    float_or_none,
+    unescapeHTML,
+)
 
 
 class TudouIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:listplay|programs(?:/view)?|albumplay)/([^/]+/)*(?P<id>[^/?#]+?)(?:\.html)?/?(?:$|[?#])'
+    IE_NAME = 'tudou'
+    _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:(?:programs|wlplay)/view|(?:listplay|albumplay)/[\w-]{11})/(?P<id>[\w-]{11})'
     _TESTS = [{
         'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
         'md5': '140a49ed444bd22f93330985d8475fcb',
@@ -16,6 +22,11 @@ class TudouIE(InfoExtractor):
             'ext': 'f4v',
             'title': '卡马乔国足开大脚长传冲吊集锦',
             'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1372113489000,
+            'description': '卡马乔卡家军，开大脚先进战术不完全集锦！',
+            'duration': 289.04,
+            'view_count': int,
+            'filesize': int,
         }
     }, {
         'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/',
@@ -24,10 +35,12 @@ class TudouIE(InfoExtractor):
             'ext': 'f4v',
             'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012',
             'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1349207518000,
+            'description': 'md5:294612423894260f2dcd5c6c04fe248b',
+            'duration': 5478.33,
+            'view_count': int,
+            'filesize': int,
         }
-    }, {
-        'url': 'http://www.tudou.com/albumplay/cJAHGih4yYg.html',
-        'only_matching': True,
     }]
 
     _PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf'
@@ -42,24 +55,20 @@ class TudouIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        item_data = self._download_json(
+            'http://www.tudou.com/tvp/getItemInfo.action?ic=%s' % video_id, video_id)
 
-        youku_vcode = self._search_regex(
-            r'vcode\s*:\s*[\'"]([^\'"]*)[\'"]', webpage, 'youku vcode', default=None)
+        youku_vcode = item_data.get('vcode')
         if youku_vcode:
             return self.url_result('youku:' + youku_vcode, ie='Youku')
 
-        title = self._search_regex(
-            r',kw\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'title')
-        thumbnail_url = self._search_regex(
-            r',pic\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'thumbnail URL', fatal=False)
+        title = unescapeHTML(item_data['kw'])
+        description = item_data.get('desc')
+        thumbnail_url = item_data.get('pic')
+        view_count = int_or_none(item_data.get('playTimes'))
+        timestamp = int_or_none(item_data.get('pt'))
 
-        player_url = self._search_regex(
-            r'playerUrl\s*:\s*[\'"]([^\'"]+\.swf)[\'"]',
-            webpage, 'player URL', default=self._PLAYER_URL)
-
-        segments = self._parse_json(self._search_regex(
-            r'segs: \'([^\']+)\'', webpage, 'segments'), video_id)
+        segments = self._parse_json(item_data['itemSegs'], video_id)
         # It looks like the keys are the arguments that have to be passed as
         # the hd field in the request url, we pick the higher
         # Also, filter non-number qualities (see issue #3643).
@@ -80,8 +89,13 @@ class TudouIE(InfoExtractor):
                 'ext': ext,
                 'title': title,
                 'thumbnail': thumbnail_url,
+                'description': description,
+                'view_count': view_count,
+                'timestamp': timestamp,
+                'duration': float_or_none(part.get('seconds'), 1000),
+                'filesize': int_or_none(part.get('size')),
                 'http_headers': {
-                    'Referer': player_url,
+                    'Referer': self._PLAYER_URL,
                 },
             }
             result.append(part_info)
@@ -92,3 +106,47 @@ class TudouIE(InfoExtractor):
             'id': video_id,
             'title': title,
         }
+
+
+class TudouPlaylistIE(InfoExtractor):
+    IE_NAME = 'tudou:playlist'
+    _VALID_URL = r'https?://(?:www\.)?tudou\.com/listplay/(?P<id>[\w-]{11})\.html'
+    _TESTS = [{
+        'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo.html',
+        'info_dict': {
+            'id': 'zzdE77v6Mmo',
+        },
+        'playlist_mincount': 209,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        playlist_data = self._download_json(
+            'http://www.tudou.com/tvp/plist.action?lcode=%s' % playlist_id, playlist_id)
+        entries = [self.url_result(
+            'http://www.tudou.com/programs/view/%s' % item['icode'],
+            'Tudou', item['icode'],
+            item['kw']) for item in playlist_data['items']]
+        return self.playlist_result(entries, playlist_id)
+
+
+class TudouAlbumIE(InfoExtractor):
+    IE_NAME = 'tudou:album'
+    _VALID_URL = r'https?://(?:www\.)?tudou\.com/album(?:cover|play)/(?P<id>[\w-]{11})'
+    _TESTS = [{
+        'url': 'http://www.tudou.com/albumplay/v5qckFJvNJg.html',
+        'info_dict': {
+            'id': 'v5qckFJvNJg',
+        },
+        'playlist_mincount': 45,
+    }]
+
+    def _real_extract(self, url):
+        album_id = self._match_id(url)
+        album_data = self._download_json(
+            'http://www.tudou.com/tvp/alist.action?acode=%s' % album_id, album_id)
+        entries = [self.url_result(
+            'http://www.tudou.com/programs/view/%s' % item['icode'],
+            'Tudou', item['icode'],
+            item['kw']) for item in album_data['items']]
+        return self.playlist_result(entries, album_id)

youtube_dl/extractor/tv4.py

@@ -67,7 +67,7 @@ class TV4IE(InfoExtractor):
         info = self._download_json(
             'http://www.tv4play.se/player/assets/%s.json' % video_id, video_id, 'Downloading video info JSON')
 
-        # If is_geo_restricted is true, it doesn't neceserally mean we can't download it
+        # If is_geo_restricted is true, it doesn't necessarily mean we can't download it
         if info['is_geo_restricted']:
             self.report_warning('This content might not be available in your country due to licensing restrictions.')
         if info['requires_subscription']:

youtube_dl/extractor/unistra.py

@@ -38,7 +38,7 @@ class UnistraIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        files = set(re.findall(r'file\s*:\s*"([^"]+)"', webpage))
+        files = set(re.findall(r'file\s*:\s*"(/[^"]+)"', webpage))
 
         quality = qualities(['SD', 'HD'])
         formats = []

youtube_dl/extractor/videomega.py

@@ -8,6 +8,7 @@ from ..utils import sanitized_Request
 
 
 class VideoMegaIE(InfoExtractor):
+    _WORKING = False
     _VALID_URL = r'(?:videomega:|https?://(?:www\.)?videomega\.tv/(?:(?:view|iframe|cdn)\.php)?\?ref=)(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'http://videomega.tv/cdn.php?ref=AOSQBJYKIDDIKYJBQSOA',

youtube_dl/extractor/videomore.py

@@ -170,7 +170,7 @@ class VideomoreVideoIE(InfoExtractor):
             'skip_download': True,
         },
     }, {
-        # season single serie with og:video:iframe
+        # season single series with og:video:iframe
         'url': 'http://videomore.ru/poslednii_ment/1_sezon/14_seriya',
         'only_matching': True,
     }, {

youtube_dl/extractor/videott.py

@@ -11,6 +11,7 @@ from ..utils import (
 
 
 class VideoTtIE(InfoExtractor):
+    _WORKING = False
     ID_NAME = 'video.tt'
     IE_DESC = 'video.tt - Your True Tube'
     _VALID_URL = r'http://(?:www\.)?video\.tt/(?:(?:video|embed)/|watch_video\.php\?v=)(?P<id>[\da-zA-Z]{9})'

youtube_dl/extractor/vodlocker.py

@@ -5,12 +5,13 @@ from .common import InfoExtractor
 from ..compat import compat_urllib_parse
 from ..utils import (
     ExtractorError,
+    NO_DEFAULT,
     sanitized_Request,
 )
 
 
 class VodlockerIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
+    _VALID_URL = r'https?://(?:www\.)?vodlocker\.(?:com|city)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
 
     _TESTS = [{
         'url': 'http://vodlocker.com/e8wvyzz4sl42',
@@ -43,16 +44,31 @@ class VodlockerIE(InfoExtractor):
             webpage = self._download_webpage(
                 req, video_id, 'Downloading video page')
 
+        def extract_file_url(html, default=NO_DEFAULT):
+            return self._search_regex(
+                r'file:\s*"(http[^\"]+)",', html, 'file url', default=default)
+
+        video_url = extract_file_url(webpage, default=None)
+
+        if not video_url:
+            embed_url = self._search_regex(
+                r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?vodlocker\.(?:com|city)/embed-.+?)\1',
+                webpage, 'embed url', group='url')
+            embed_webpage = self._download_webpage(
+                embed_url, video_id, 'Downloading embed webpage')
+            video_url = extract_file_url(embed_webpage)
+            thumbnail_webpage = embed_webpage
+        else:
+            thumbnail_webpage = webpage
+
         title = self._search_regex(
             r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
         thumbnail = self._search_regex(
-            r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail')
-        url = self._search_regex(
-            r'file:\s*"(http[^\"]+)",', webpage, 'file url')
+            r'image:\s*"(http[^\"]+)",', thumbnail_webpage, 'thumbnail', fatal=False)
 
         formats = [{
             'format_id': 'sd',
-            'url': url,
+            'url': video_url,
         }]
 
         return {

youtube_dl/extractor/xhamster.py

@@ -6,7 +6,6 @@ from .common import InfoExtractor
 from ..utils import (
     float_or_none,
     int_or_none,
-    str_to_int,
     unified_strdate,
 )
 

youtube_dl/extractor/xtube.py

@@ -1,10 +1,12 @@
 from __future__ import unicode_literals
 
+import itertools
 import re
 
 from .common import InfoExtractor
 from ..compat import compat_urllib_parse_unquote
 from ..utils import (
+    int_or_none,
     parse_duration,
     sanitized_Request,
     str_to_int,
@@ -12,7 +14,7 @@ from ..utils import (
 
 
 class XTubeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<id>[^/?&#]+))'
+    _VALID_URL = r'(?:xtube:|https?://(?:www\.)?xtube\.com/watch\.php\?.*\bv=)(?P<id>[^/?&#]+)'
     _TEST = {
         'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
         'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
@@ -30,7 +32,7 @@ class XTubeIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        req = sanitized_Request(url)
+        req = sanitized_Request('http://www.xtube.com/watch.php?v=%s' % video_id)
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
@@ -88,45 +90,43 @@ class XTubeIE(InfoExtractor):
 
 class XTubeUserIE(InfoExtractor):
     IE_DESC = 'XTube user profile'
-    _VALID_URL = r'https?://(?:www\.)?xtube\.com/community/profile\.php\?(.*?)user=(?P<username>[^&#]+)(?:$|[&#])'
+    _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
     _TEST = {
-        'url': 'http://www.xtube.com/community/profile.php?user=greenshowers',
+        'url': 'http://www.xtube.com/profile/greenshowers-4056496',
         'info_dict': {
-            'id': 'greenshowers',
+            'id': 'greenshowers-4056496',
             'age_limit': 18,
         },
         'playlist_mincount': 155,
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        username = mobj.group('username')
+        user_id = self._match_id(url)
 
-        profile_page = self._download_webpage(
-            url, username, note='Retrieving profile page')
+        entries = []
+        for pagenum in itertools.count(1):
+            request = sanitized_Request(
+                'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
+                headers={
+                    'Cookie': 'popunder=4',
+                    'X-Requested-With': 'XMLHttpRequest',
+                    'Referer': url,
+                })
 
-        video_count = int(self._search_regex(
-            r'<strong>%s\'s Videos \(([0-9]+)\)</strong>' % username, profile_page,
-            'video count'))
+            page = self._download_json(
+                request, user_id, 'Downloading videos JSON page %d' % pagenum)
 
-        PAGE_SIZE = 25
-        urls = []
-        page_count = (video_count + PAGE_SIZE + 1) // PAGE_SIZE
-        for n in range(1, page_count + 1):
-            lpage_url = 'http://www.xtube.com/user_videos.php?page=%d&u=%s' % (n, username)
-            lpage = self._download_webpage(
-                lpage_url, username,
-                note='Downloading page %d/%d' % (n, page_count))
-            urls.extend(
-                re.findall(r'addthis:url="([^"]+)"', lpage))
+            html = page.get('html')
+            if not html:
+                break
 
-        return {
-            '_type': 'playlist',
-            'id': username,
-            'age_limit': 18,
-            'entries': [{
-                '_type': 'url',
-                'url': eurl,
-                'ie_key': 'XTube',
-            } for eurl in urls]
-        }
+            for _, video_id in re.findall(r'data-plid=(["\'])(.+?)\1', html):
+                entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
+
+            page_count = int_or_none(page.get('pageCount'))
+            if not page_count or pagenum == page_count:
+                break
+
+        playlist = self.playlist_result(entries, user_id)
+        playlist['age_limit'] = 18
+        return playlist

youtube_dl/extractor/youtube.py

@@ -1487,7 +1487,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             if codecs:
                                 codecs = codecs.split(',')
                                 if len(codecs) == 2:
-                                    acodec, vcodec = codecs[0], codecs[1]
+                                    acodec, vcodec = codecs[1], codecs[0]
                                 else:
                                     acodec, vcodec = (codecs[0], 'none') if kind == 'audio' else ('none', codecs[0])
                                 dct.update({

youtube_dl/swfinterp.py

@@ -689,7 +689,7 @@ class SWFInterpreter(object):
                     elif mname in _builtin_classes:
                         res = _builtin_classes[mname]
                     else:
-                        # Assume unitialized
+                        # Assume uninitialized
                         # TODO warn here
                         res = undefined
                     stack.append(res)

youtube_dl/utils.py

@@ -984,7 +984,7 @@ def date_from_str(date_str):
         if sign == '-':
             time = -time
         unit = match.group('unit')
-        # A bad aproximation?
+        # A bad approximation?
         if unit == 'month':
             unit = 'day'
             time *= 30
@@ -1307,7 +1307,7 @@ def parse_filesize(s):
     if s is None:
         return None
 
-    # The lower-case forms are of course incorrect and inofficial,
+    # The lower-case forms are of course incorrect and unofficial,
     # but we support those too
     _UNIT_TABLE = {
         'B': 1,

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2016.01.09'
+__version__ = '2016.01.15'