release 2014.12.13

apply ratelimit to f4m

AUTHORS

@@ -92,3 +92,4 @@ Tithen-Firion
 Zack Fernandes
 cryptonaut
 Adrian Kretz
+Mathias Rav

test/test_unicode_literals.py

@@ -20,7 +20,7 @@ IGNORED_FILES = [
 ]
 
 
-from helper import assertRegexpMatches
+from test.helper import assertRegexpMatches
 
 
 class TestUnicodeLiterals(unittest.TestCase):

youtube_dl/downloader/common.py

@@ -5,8 +5,8 @@ import re
 import sys
 import time
 
+from ..compat import compat_str
 from ..utils import (
-    compat_str,
     encodeFilename,
     format_bytes,
     timeconvert,

youtube_dl/downloader/f4m.py

@@ -9,10 +9,12 @@ import xml.etree.ElementTree as etree
 
 from .common import FileDownloader
 from .http import HttpFD
+from ..compat import (
+    compat_urlparse,
+)
 from ..utils import (
     struct_pack,
     struct_unpack,
-    compat_urlparse,
     format_bytes,
     encodeFilename,
     sanitize_open,
@@ -231,6 +233,7 @@ class F4mFD(FileDownloader):
                 'continuedl': True,
                 'quiet': True,
                 'noprogress': True,
+                'ratelimit': self.params.get('ratelimit', None),
                 'test': self.params.get('test', False),
             }
         )

youtube_dl/downloader/hls.py

@@ -6,9 +6,11 @@ import subprocess
 
 from ..postprocessor.ffmpeg import FFmpegPostProcessor
 from .common import FileDownloader
-from ..utils import (
+from ..compat import (
     compat_urlparse,
     compat_urllib_request,
+)
+from ..utils import (
     check_executable,
     encodeFilename,
 )

youtube_dl/downloader/http.py

@@ -4,11 +4,12 @@ import os
 import time
 
 from .common import FileDownloader
-from ..utils import (
+from ..compat import (
     compat_urllib_request,
     compat_urllib_error,
+)
+from ..utils import (
     ContentTooShortError,
-
     encodeFilename,
     sanitize_open,
     format_bytes,

youtube_dl/downloader/rtmp.py

@@ -7,9 +7,9 @@ import sys
 import time
 
 from .common import FileDownloader
+from ..compat import compat_str
 from ..utils import (
     check_executable,
-    compat_str,
     encodeFilename,
     format_bytes,
     get_exe_version,

youtube_dl/extractor/__init__.py

@@ -65,6 +65,7 @@ from .cnn import (
 )
 from .collegehumor import CollegeHumorIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
+from .comcarcoff import ComCarCoffIE
 from .condenast import CondeNastIE
 from .cracked import CrackedIE
 from .criterion import CriterionIE
@@ -159,6 +160,7 @@ from .googlesearch import GoogleSearchIE
 from .gorillavid import GorillaVidIE
 from .goshgay import GoshgayIE
 from .grooveshark import GroovesharkIE
+from .groupon import GrouponIE
 from .hark import HarkIE
 from .heise import HeiseIE
 from .helsinki import HelsinkiIE
@@ -314,6 +316,7 @@ from .radiofrance import RadioFranceIE
 from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
 from .redtube import RedTubeIE
+from .restudy import RestudyIE
 from .reverbnation import ReverbNationIE
 from .ringtv import RingTVIE
 from .ro220 import Ro220IE
@@ -322,6 +325,7 @@ from .roxwel import RoxwelIE
 from .rtbf import RTBFIE
 from .rtlnl import RtlXlIE
 from .rtlnow import RTLnowIE
+from .rtp import RTPIE
 from .rts import RTSIE
 from .rtve import RTVEALaCartaIE, RTVELiveIE
 from .ruhd import RUHDIE

youtube_dl/extractor/adultswim.py

@@ -7,6 +7,8 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    xpath_text,
+    float_or_none,
 )
 
 
@@ -128,7 +130,8 @@ class AdultSwimIE(InfoExtractor):
                 segment_url, segment_title,
                 'Downloading segment information', 'Unable to download segment information')
 
-            segment_duration = idoc.find('.//trt').text.strip()
+            segment_duration = float_or_none(
+                xpath_text(idoc, './/trt', 'segment duration').strip())
 
             formats = []
             file_els = idoc.findall('.//files/file')

youtube_dl/extractor/allocine.py

@@ -5,10 +5,9 @@ import re
 import json
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
-    compat_str,
     qualities,
-    determine_ext,
 )
 
 
@@ -75,9 +74,7 @@ class AllocineIE(InfoExtractor):
                     'format_id': format_id,
                     'quality': quality(format_id),
                     'url': v,
-                    'ext': determine_ext(v),
                 })
-
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/aol.py

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from .fivemin import FiveMinIE
 
 
 class AolIE(InfoExtractor):
@@ -42,9 +41,10 @@ class AolIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-
         playlist_id = mobj.group('playlist_id')
-        if playlist_id and not self._downloader.params.get('noplaylist'):
+        if not playlist_id or self._downloader.params.get('noplaylist'):
+            return self.url_result('5min:%s' % video_id)
+
         self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
 
         webpage = self._download_webpage(url, playlist_id)
@@ -68,5 +68,3 @@ class AolIE(InfoExtractor):
             'title': title,
             'entries': entries,
         }
-
-        return FiveMinIE._build_result(video_id)

youtube_dl/extractor/appletrailers.py

@@ -4,8 +4,8 @@ import re
 import json
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
-    compat_urlparse,
     int_or_none,
 )
 

youtube_dl/extractor/auengine.py

@@ -3,8 +3,8 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse
 from ..utils import (
-    compat_urllib_parse,
     determine_ext,
     ExtractorError,
 )

youtube_dl/extractor/bambuser.py

@@ -5,7 +5,7 @@ import json
 import itertools
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_request,
 )
 

youtube_dl/extractor/bandcamp.py

@@ -4,9 +4,11 @@ import json
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_str,
     compat_urlparse,
+)
+from ..utils import (
     ExtractorError,
 )
 
@@ -104,7 +106,7 @@ class BandcampIE(InfoExtractor):
 
 class BandcampAlbumIE(InfoExtractor):
     IE_NAME = 'Bandcamp:album'
-    _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))'
+    _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))?'
 
     _TESTS = [{
         'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
@@ -139,6 +141,12 @@ class BandcampAlbumIE(InfoExtractor):
             'title': 'Hierophany of the Open Grave',
         },
         'playlist_mincount': 9,
+    }, {
+        'url': 'http://dotscale.bandcamp.com',
+        'info_dict': {
+            'title': 'Loom',
+        },
+        'playlist_mincount': 7,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/bbccouk.py

@@ -209,7 +209,7 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
         webpage = self._download_webpage(url, group_id, 'Downloading video page')
 
         programme_id = self._search_regex(
-            r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False)
+            r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
         if programme_id:
             player = self._download_json(
                 'http://www.bbc.co.uk/iplayer/episode/%s.json' % group_id,

youtube_dl/extractor/bet.py

@@ -1,8 +1,8 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse
 from ..utils import (
-    compat_urllib_parse,
     xpath_text,
     xpath_with_ns,
     int_or_none,

youtube_dl/extractor/bilibili.py

@@ -4,8 +4,8 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_parse_qs
 from ..utils import (
-    compat_parse_qs,
     ExtractorError,
     int_or_none,
     unified_strdate,
@@ -29,10 +29,9 @@ class BiliBiliIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
+
         video_code = self._search_regex(
             r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
 

youtube_dl/extractor/brightcove.py

@@ -6,20 +6,21 @@ import json
 import xml.etree.ElementTree
 
 from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse,
-    find_xpath_attr,
-    fix_xml_ampersands,
-    compat_urlparse,
-    compat_str,
-    compat_urllib_request,
+from ..compat import (
     compat_parse_qs,
+    compat_str,
+    compat_urllib_parse,
     compat_urllib_parse_urlparse,
-
+    compat_urllib_request,
+    compat_urlparse,
+)
+from ..utils import (
     determine_ext,
     ExtractorError,
-    unsmuggle_url,
+    find_xpath_attr,
+    fix_xml_ampersands,
     unescapeHTML,
+    unsmuggle_url,
 )
 
 

youtube_dl/extractor/ceskatelevize.py

@@ -4,10 +4,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_request,
     compat_urllib_parse,
     compat_urllib_parse_urlparse,
+)
+from ..utils import (
     ExtractorError,
 )
 

youtube_dl/extractor/comcarcoff.py

@@ -0,0 +1,57 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..utils import parse_iso8601
+
+
+class ComCarCoffIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)'
+    _TESTS = [{
+        'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/',
+        'info_dict': {
+            'id': 'miranda-sings-happy-thanksgiving-miranda',
+            'ext': 'mp4',
+            'upload_date': '20141127',
+            'timestamp': 1417107600,
+            'title': 'Happy Thanksgiving Miranda',
+            'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.',
+            'thumbnail': 'http://ccc.crackle.com/images/s5e4_thumb.jpg',
+        },
+        'params': {
+            'skip_download': 'requires ffmpeg',
+        }
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        if not display_id:
+            display_id = 'comediansincarsgettingcoffee.com'
+        webpage = self._download_webpage(url, display_id)
+
+        full_data = json.loads(self._search_regex(
+            r'<script type="application/json" id="videoData">(?P<json>.+?)</script>',
+            webpage, 'full data json'))
+
+        video_id = full_data['activeVideo']['video']
+        video_data = full_data['videos'][video_id]
+        thumbnails = [{
+            'url': video_data['images']['thumb'],
+        }, {
+            'url': video_data['images']['poster'],
+        }]
+        formats = self._extract_m3u8_formats(
+            video_data['mediaUrl'], video_id, ext='mp4')
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': video_data['title'],
+            'description': video_data.get('description'),
+            'timestamp': parse_iso8601(video_data.get('pubDate')),
+            'thumbnails': thumbnails,
+            'formats': formats,
+            'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))),
+        }

youtube_dl/extractor/comedycentral.py

@@ -3,9 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .mtv import MTVServicesInfoExtractor
-from ..utils import (
+from ..compat import (
     compat_str,
     compat_urllib_parse,
+)
+from ..utils import (
     ExtractorError,
     float_or_none,
     unified_strdate,

youtube_dl/extractor/condenast.py

@@ -5,12 +5,14 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
-    orderedSet,
     compat_urllib_parse_urlparse,
     compat_urlparse,
 )
+from ..utils import (
+    orderedSet,
+)
 
 
 class CondeNastIE(InfoExtractor):

youtube_dl/extractor/crunchyroll.py

@@ -10,10 +10,12 @@ import xml.etree.ElementTree
 from hashlib import sha1
 from math import pow, sqrt, floor
 from .subtitles import SubtitlesInfoExtractor
-from ..utils import (
-    ExtractorError,
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
+)
+from ..utils import (
+    ExtractorError,
     bytes_to_intlist,
     intlist_to_bytes,
     unified_strdate,

youtube_dl/extractor/dailymotion.py

@@ -8,13 +8,15 @@ import itertools
 from .common import InfoExtractor
 from .subtitles import SubtitlesInfoExtractor
 
-from ..utils import (
-    compat_urllib_request,
+from ..compat import (
     compat_str,
+    compat_urllib_request,
+)
+from ..utils import (
+    ExtractorError,
+    int_or_none,
     orderedSet,
     str_to_int,
-    int_or_none,
-    ExtractorError,
     unescapeHTML,
 )
 

youtube_dl/extractor/daum.py

@@ -5,7 +5,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
 )
 

youtube_dl/extractor/ebaumsworld.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -20,8 +18,7 @@ class EbaumsWorldIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         config = self._download_xml(
             'http://www.ebaumsworld.com/video/player/%s' % video_id, video_id)
         video_url = config.find('file').text

youtube_dl/extractor/ehow.py

@@ -1,8 +1,6 @@
 from __future__ import unicode_literals
 
-import re
-
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
 )
 from .common import InfoExtractor
@@ -24,11 +22,10 @@ class EHowIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)',
-                                       webpage, 'video URL')
+        video_url = self._search_regex(
+            r'(?:file|source)=(http[^\'"&]*)', webpage, 'video URL')
         final_url = compat_urllib_parse.unquote(video_url)
         uploader = self._html_search_meta('uploader', webpage)
         title = self._og_search_title(webpage).replace(' | eHow', '')

youtube_dl/extractor/eighttracks.py

@@ -6,7 +6,7 @@ import random
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_str,
 )
 

youtube_dl/extractor/engadget.py

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from .fivemin import FiveMinIE
 from ..utils import (
     url_basename,
 )
@@ -27,11 +26,10 @@ class EngadgetIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         if video_id is not None:
-            return FiveMinIE._build_result(video_id)
+            return self.url_result('5min:%s' % video_id)
         else:
             title = url_basename(url)
             webpage = self._download_webpage(url, title)
@@ -39,5 +37,5 @@ class EngadgetIE(InfoExtractor):
             return {
                 '_type': 'playlist',
                 'title': title,
-                'entries': [FiveMinIE._build_result(id) for id in ids]
+                'entries': [self.url_result('5min:%s' % vid) for vid in ids]
             }

youtube_dl/extractor/escapist.py

@@ -3,9 +3,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
-
+)
+from ..utils import (
     ExtractorError,
 )
 

youtube_dl/extractor/everyonesmixtape.py

@@ -3,8 +3,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_request,
+)
+from ..utils import (
     ExtractorError,
 )
 

youtube_dl/extractor/extremetube.py

@@ -3,16 +3,18 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
+)
+from ..utils import (
     str_to_int,
 )
 
 
 class ExtremeTubeIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'
     _TESTS = [{
         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
         'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
@@ -31,7 +33,7 @@ class ExtremeTubeIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
+        video_id = mobj.group('id')
         url = 'http://www.' + mobj.group('url')
 
         req = compat_urllib_request.Request(url)

youtube_dl/extractor/fc2.py

@@ -1,19 +1,20 @@
 #! -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import re
 import hashlib
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
+from ..compat import (
     compat_urllib_request,
     compat_urlparse,
 )
+from ..utils import (
+    ExtractorError,
+)
 
 
 class FC2IE(InfoExtractor):
-    _VALID_URL = r'^http://video\.fc2\.com/((?P<lang>[^/]+)/)?content/(?P<id>[^/]+)'
+    _VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)?content/(?P<id>[^/]+)'
     IE_NAME = 'fc2'
     _TEST = {
         'url': 'http://video.fc2.com/en/content/20121103kUan1KHs',
@@ -26,9 +27,7 @@ class FC2IE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         self._downloader.cookiejar.clear_session_cookies()  # must clear
 

youtube_dl/extractor/firedrive.py

@@ -4,11 +4,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
 )
+from ..utils import (
+    ExtractorError,
+)
 
 
 class FiredriveIE(InfoExtractor):
@@ -28,11 +30,8 @@ class FiredriveIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         url = 'http://firedrive.com/file/%s' % video_id
-
         webpage = self._download_webpage(url, video_id)
 
         if re.search(self._FILE_DELETED_REGEX, webpage) is not None:

youtube_dl/extractor/fivemin.py

@@ -1,11 +1,11 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_str,
     compat_urllib_parse,
+)
+from ..utils import (
     ExtractorError,
 )
 
@@ -13,7 +13,7 @@ from ..utils import (
 class FiveMinIE(InfoExtractor):
     IE_NAME = '5min'
     _VALID_URL = r'''(?x)
-        (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(.*?&)?playList=|
+        (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?:.*?&)?playList=|
             5min:)
         (?P<id>\d+)
         '''
@@ -41,13 +41,8 @@ class FiveMinIE(InfoExtractor):
         },
     ]
 
-    @classmethod
-    def _build_result(cls, video_id):
-        return cls.url_result('5min:%s' % video_id, cls.ie_key())
-
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id
         embed_page = self._download_webpage(embed_url, video_id,
                                             'Downloading embed page')

youtube_dl/extractor/fourtube.py

@@ -3,12 +3,14 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_request,
-    unified_strdate,
-    str_to_int,
-    parse_duration,
+)
+from ..utils import (
     clean_html,
+    parse_duration,
+    str_to_int,
+    unified_strdate,
 )
 
 
@@ -31,9 +33,7 @@ class FourTubeIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage_url = 'http://www.4tube.com/videos/' + video_id
         webpage = self._download_webpage(webpage_url, video_id)
 

youtube_dl/extractor/franceculture.py

@@ -5,7 +5,7 @@ import json
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_parse_qs,
     compat_urlparse,
 )

youtube_dl/extractor/francetv.py

@@ -6,13 +6,15 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
-    compat_urlparse,
-    ExtractorError,
-    clean_html,
-    parse_duration,
+from ..compat import (
     compat_urllib_parse_urlparse,
+    compat_urlparse,
+)
+from ..utils import (
+    clean_html,
+    ExtractorError,
     int_or_none,
+    parse_duration,
 )
 
 

youtube_dl/extractor/gamespot.py

@@ -4,9 +4,11 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urlparse,
+)
+from ..utils import (
     unescapeHTML,
 )
 

youtube_dl/extractor/gdcvault.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
 )

youtube_dl/extractor/golem.py

@@ -2,8 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urlparse,
+)
+from ..utils import (
     determine_ext,
 )
 

youtube_dl/extractor/googlesearch.py

@@ -4,7 +4,7 @@ import itertools
 import re
 
 from .common import SearchInfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
 )
 

youtube_dl/extractor/gorillavid.py

@@ -4,11 +4,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    determine_ext,
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
+)
+from ..utils import (
+    ExtractorError,
     int_or_none,
 )
 
@@ -106,7 +107,6 @@ class GorillaVidIE(InfoExtractor):
         formats = [{
             'format_id': 'sd',
             'url': video_url,
-            'ext': determine_ext(video_url),
             'quality': 1,
         }]
 

youtube_dl/extractor/groupon.py

@@ -0,0 +1,50 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class GrouponIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.groupon\.com/deals/(?P<id>[^?#]+)'
+
+    _TEST = {
+        'url': 'https://www.groupon.com/deals/bikram-yoga-huntington-beach-2#ooid=tubGNycTo_9Uxg82uESj4i61EYX8nyuf',
+        'info_dict': {
+            'id': 'bikram-yoga-huntington-beach-2',
+            'title': '$49 for 10 Yoga Classes or One Month of Unlimited Classes at Bikram Yoga Huntington Beach ($180 Value)',
+            'description': 'Studio kept at 105 degrees and 40% humidity with anti-microbial and anti-slip Flotex flooring; certified instructors',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'tubGNycTo_9Uxg82uESj4i61EYX8nyuf',
+                'ext': 'mp4',
+                'title': 'Bikram Yoga Huntington Beach | Orange County',
+            },
+        }],
+        'params': {
+            'skip_download': 'HLS',
+        }
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        payload = self._parse_json(self._search_regex(
+            r'var\s+payload\s*=\s*(.*?);\n', webpage, 'payload'), playlist_id)
+        videos = payload['carousel'].get('dealVideos', [])
+        entries = []
+        for v in videos:
+            if v.get('provider') != 'OOYALA':
+                self.report_warning(
+                    '%s: Unsupported video provider %s, skipping video' %
+                    (playlist_id, v.get('provider')))
+                continue
+            entries.append(self.url_result('ooyala:%s' % v['media']))
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'entries': entries,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+        }

youtube_dl/extractor/hostingbulk.py

@@ -4,9 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_request,
+)
 from ..utils import (
     ExtractorError,
-    compat_urllib_request,
     int_or_none,
     urlencode_postdata,
 )
@@ -30,9 +32,7 @@ class HostingBulkIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         url = 'http://hostingbulk.com/{0:}.html'.format(video_id)
 
         # Custom request with cookie to set language to English, so our file

youtube_dl/extractor/hypem.py

@@ -1,20 +1,20 @@
 from __future__ import unicode_literals
 
 import json
-import re
 import time
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
-
+)
+from ..utils import (
     ExtractorError,
 )
 
 
 class HypemIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?hypem\.com/track/(?P<id>[^/]+)/'
     _TEST = {
         'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
         'md5': 'b9cc91b5af8995e9f0c1cee04c575828',
@@ -27,8 +27,7 @@ class HypemIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        track_id = mobj.group(1)
+        track_id = self._match_id(url)
 
         data = {'ax': 1, 'ts': time.time()}
         data_encoded = compat_urllib_parse.urlencode(data)

youtube_dl/extractor/imdb.py

@@ -4,7 +4,7 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urlparse,
 )
 

youtube_dl/extractor/infoq.py

@@ -1,10 +1,9 @@
 from __future__ import unicode_literals
 
 import base64
-import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
 )
 
@@ -24,9 +23,7 @@ class InfoQIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')

youtube_dl/extractor/internetvideoarchive.py

@@ -3,9 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urlparse,
     compat_urllib_parse,
+)
+from ..utils import (
     xpath_with_ns,
 )
 

youtube_dl/extractor/iprima.py

@@ -6,8 +6,10 @@ from random import random
 from math import floor
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_request,
+)
+from ..utils import (
     ExtractorError,
 )
 

youtube_dl/extractor/ivi.py

@@ -5,8 +5,10 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_request,
+)
+from ..utils import (
     ExtractorError,
 )
 

youtube_dl/extractor/keek.py

@@ -1,34 +1,39 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
 class KeekIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
+    _VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<id>\w+)'
     IE_NAME = 'keek'
     _TEST = {
         'url': 'https://www.keek.com/ytdl/keeks/NODfbab',
-        'file': 'NODfbab.mp4',
-        'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83',
+        'md5': '09c5c109067536c1cec8bac8c21fea05',
         'info_dict': {
-            'uploader': 'ytdl',
+            'id': 'NODfbab',
+            'ext': 'mp4',
+            'uploader': 'youtube-dl project',
+            'uploader_id': 'ytdl',
             'title': 'test chars: "\'/\\\u00e4<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de .',
         },
     }
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('videoID')
+        video_id = self._match_id(url)
 
         video_url = 'http://cdn.keek.com/keek/video/%s' % video_id
         thumbnail = 'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
         webpage = self._download_webpage(url, video_id)
 
+        raw_desc = self._html_search_meta('description', webpage)
+        if raw_desc:
             uploader = self._html_search_regex(
-            r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
-            webpage, 'uploader', fatal=False)
+                r'Watch (.*?)\s+\(', raw_desc, 'uploader', fatal=False)
+            uploader_id = self._html_search_regex(
+                r'Watch .*?\(@(.+?)\)', raw_desc, 'uploader_id', fatal=False)
+        else:
+            uploader = None
+            uploader_id = None
 
         return {
             'id': video_id,
@@ -36,5 +41,6 @@ class KeekIE(InfoExtractor):
             'ext': 'mp4',
             'title': self._og_search_title(webpage),
             'thumbnail': thumbnail,
-            'uploader': uploader
+            'uploader': uploader,
+            'uploader_id': uploader_id,
         }

youtube_dl/extractor/keezmovies.py

@@ -4,7 +4,7 @@ import os
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
@@ -15,7 +15,7 @@ from ..aes import (
 
 
 class KeezMoviesIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?keezmovies\.com/video/.+?(?P<videoid>[0-9]+)(?:[/?&]|$)'
+    _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
     _TEST = {
         'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
         'file': '1214711.mp4',
@@ -27,8 +27,7 @@ class KeezMoviesIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
+        video_id = self._match_id(url)
 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')

youtube_dl/extractor/livestream.py

@@ -4,10 +4,12 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_str,
     compat_urllib_parse_urlparse,
     compat_urlparse,
+)
+from ..utils import (
     ExtractorError,
     find_xpath_attr,
     int_or_none,

youtube_dl/extractor/lynda.py

@@ -5,12 +5,14 @@ import json
 
 from .subtitles import SubtitlesInfoExtractor
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
+    compat_str,
     compat_urllib_parse,
     compat_urllib_request,
+)
+from ..utils import (
     ExtractorError,
     int_or_none,
-    compat_str,
 )
 
 

youtube_dl/extractor/malemotion.py

@@ -1,43 +1,33 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
 )
 
 
 class MalemotionIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)'
+    _VALID_URL = r'https?://malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)'
     _TEST = {
-        'url': 'http://malemotion.com/video/bien-dur.10ew',
-        'file': '10ew.mp4',
-        'md5': 'b3cc49f953b107e4a363cdff07d100ce',
+        'url': 'http://malemotion.com/video/bete-de-concours.ltc',
+        'md5': '3013e53a0afbde2878bc39998c33e8a5',
         'info_dict': {
-            "title": "Bien dur",
-            "age_limit": 18,
+            'id': 'ltc',
+            'ext': 'mp4',
+            'title': 'Bête de Concours',
+            'age_limit': 18,
         },
-        'skip': 'This video has been deleted.'
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group("id")
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        self.report_extraction(video_id)
-
-        # Extract video URL
-        video_url = compat_urllib_parse.unquote(
-            self._search_regex(r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL'))
-
-        # Extract title
+        video_url = compat_urllib_parse.unquote(self._search_regex(
+            r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL'))
         video_title = self._html_search_regex(
             r'<title>(.*?)</title', webpage, 'title')
-
-        # Extract video thumbnail
         video_thumbnail = self._search_regex(
             r'<video .+?poster="(.+?)"', webpage, 'thumbnail', fatal=False)
 
@@ -47,14 +37,12 @@ class MalemotionIE(InfoExtractor):
             'format_id': 'mp4',
             'preference': 1,
         }]
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
             'formats': formats,
-            'uploader': None,
-            'upload_date': None,
             'title': video_title,
             'thumbnail': video_thumbnail,
-            'description': None,
             'age_limit': 18,
         }

youtube_dl/extractor/metacafe.py

@@ -3,10 +3,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_parse_qs,
     compat_urllib_parse,
     compat_urllib_request,
+)
+from ..utils import (
     determine_ext,
     ExtractorError,
     int_or_none,

youtube_dl/extractor/mit.py

@@ -5,8 +5,10 @@ import json
 
 from .common import InfoExtractor
 from .youtube import YoutubeIE
-from ..utils import (
+from ..compat import (
     compat_urlparse,
+)
+from ..utils import (
     clean_html,
     ExtractorError,
     get_element_by_id,

youtube_dl/extractor/mitele.py

@@ -1,12 +1,13 @@
 from __future__ import unicode_literals
 
-import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urlparse,
+)
+from ..utils import (
     get_element_by_attribute,
     parse_duration,
     strip_jsonp,
@@ -15,7 +16,7 @@ from ..utils import (
 
 class MiTeleIE(InfoExtractor):
     IE_NAME = 'mitele.es'
-    _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<episode>[^/]+)/'
+    _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
 
     _TEST = {
         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
@@ -31,12 +32,10 @@ class MiTeleIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        episode = mobj.group('episode')
+        episode = self._match_id(url)
         webpage = self._download_webpage(url, episode)
         embed_data_json = self._search_regex(
-            r'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
-            flags=re.DOTALL
+            r'(?s)MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
         ).replace('\'', '"')
         embed_data = json.loads(embed_data_json)
 

youtube_dl/extractor/mixcloud.py

@@ -3,8 +3,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
+)
+from ..utils import (
     ExtractorError,
     HEADRequest,
     int_or_none,

youtube_dl/extractor/moevideo.py

@@ -5,10 +5,12 @@ import json
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
+)
+from ..utils import (
+    ExtractorError,
     int_or_none,
 )
 

youtube_dl/extractor/mofosex.py

@@ -4,7 +4,7 @@ import os
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class MofosexIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<id>[0-9]+)/.*?\.html)'
     _TEST = {
         'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
         'md5': '1b2eb47ac33cc75d4a80e3026b613c5a',
@@ -26,7 +26,7 @@ class MofosexIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
+        video_id = mobj.group('id')
         url = 'http://www.' + mobj.group('url')
 
         req = compat_urllib_request.Request(url)

youtube_dl/extractor/moniker.py

@@ -5,7 +5,7 @@ import os.path
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
 )
@@ -37,10 +37,9 @@ class MonikerIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         orig_webpage = self._download_webpage(url, video_id)
+
         fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
         data = dict(fields)
 

youtube_dl/extractor/mooshare.py

@@ -4,11 +4,13 @@ import re
 import time
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
+from ..compat import (
     compat_urllib_request,
     compat_urllib_parse,
 )
+from ..utils import (
+    ExtractorError,
+)
 
 
 class MooshareIE(InfoExtractor):
@@ -43,9 +45,7 @@ class MooshareIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         page = self._download_webpage(url, video_id, 'Downloading page')
 
         if re.search(r'>Video Not Found or Deleted<', page) is not None:

youtube_dl/extractor/motorsport.py

@@ -3,13 +3,14 @@ from __future__ import unicode_literals
 
 import hashlib
 import json
-import re
 import time
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_parse_qs,
     compat_str,
+)
+from ..utils import (
     int_or_none,
 )
 
@@ -32,10 +33,9 @@ class MotorsportIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('id')
-
+        display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
+
         flashvars_code = self._html_search_regex(
             r'<embed id="player".*?flashvars="([^"]+)"', webpage, 'flashvars')
         flashvars = compat_parse_qs(flashvars_code)

youtube_dl/extractor/movieclips.py

@@ -3,9 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+)
 from ..utils import (
     ExtractorError,
-    compat_str,
     clean_html,
 )
 

youtube_dl/extractor/mtv.py

@@ -3,9 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
+)
+from ..utils import (
     ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,

youtube_dl/extractor/myspass.py

@@ -2,9 +2,10 @@ from __future__ import unicode_literals
 import os.path
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse_urlparse,
-
+)
+from ..utils import (
     ExtractorError,
 )
 

youtube_dl/extractor/naver.py

@@ -4,8 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
+)
+from ..utils import (
     ExtractorError,
     clean_html,
 )
@@ -26,9 +28,9 @@ class NaverIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
+
         m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
                          webpage)
         if m_id is None:

youtube_dl/extractor/nbc.py

@@ -4,8 +4,10 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_str,
+)
+from ..utils import (
     ExtractorError,
     find_xpath_attr,
 )

youtube_dl/extractor/nfb.py

@@ -1,9 +1,7 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_request,
     compat_urllib_parse,
 )
@@ -12,7 +10,7 @@ from ..utils import (
 class NFBIE(InfoExtractor):
     IE_NAME = 'nfb'
     IE_DESC = 'National Film Board of Canada'
-    _VALID_URL = r'https?://(?:www\.)?(nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)'
 
     _TEST = {
         'url': 'https://www.nfb.ca/film/qallunaat_why_white_people_are_funny',
@@ -32,10 +30,10 @@ class NFBIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
-        page = self._download_webpage('https://www.nfb.ca/film/%s' % video_id, video_id, 'Downloading film page')
+        video_id = self._match_id(url)
+        page = self._download_webpage(
+            'https://www.nfb.ca/film/%s' % video_id, video_id,
+            'Downloading film page')
 
         uploader_id = self._html_search_regex(r'<a class="director-link" href="/explore-all-directors/([^/]+)/"',
                                               page, 'director id', fatal=False)

youtube_dl/extractor/nfl.py

@@ -4,9 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse_urlparse,
+)
 from ..utils import (
     ExtractorError,
-    compat_urllib_parse_urlparse,
     int_or_none,
     remove_end,
 )

youtube_dl/extractor/niconico.py

@@ -5,14 +5,16 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
     compat_urlparse,
-    unified_strdate,
-    parse_duration,
-    int_or_none,
+)
+from ..utils import (
     ExtractorError,
+    int_or_none,
+    parse_duration,
+    unified_strdate,
 )
 
 

youtube_dl/extractor/ninegag.py

@@ -23,6 +23,9 @@ class NineGagIE(InfoExtractor):
             "ext": "mp4",
             "description": "This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)",
             "title": "\"People Are Awesome 2013\" Is Absolutely Awesome",
+            'uploader_id': 'UCdEH6EjDKwtTe-sO2f0_1XA',
+            'uploader': 'CompilationChannel',
+            'upload_date': '20131110',
             "view_count": int,
             "thumbnail": "re:^https?://",
         },
@@ -35,6 +38,9 @@ class NineGagIE(InfoExtractor):
             'display_id': 'alternate-banned-opening-scene-of-gravity',
             "description": "While Gravity was a pretty awesome movie already, YouTuber Krishna Shenoi came up with a way to improve upon it, introducing a much better solution to Sandra Bullock's seemingly endless tumble in space. The ending is priceless.",
             'title': "Banned Opening Scene Of \"Gravity\" That Changes The Whole Movie",
+            'uploader': 'Krishna Shenoi',
+            'upload_date': '20140401',
+            'uploader_id': 'krishnashenoi93',
         },
     }]
 

youtube_dl/extractor/noco.py

@@ -6,13 +6,15 @@ import time
 import hashlib
 
 from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_request,
-    compat_urllib_parse,
-    ExtractorError,
-    clean_html,
-    unified_strdate,
+from ..compat import (
     compat_str,
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    unified_strdate,
 )
 
 

youtube_dl/extractor/nosvideo.py

@@ -4,9 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_request,
+)
 from ..utils import (
     ExtractorError,
-    compat_urllib_request,
     urlencode_postdata,
     xpath_text,
     xpath_with_ns,
@@ -32,8 +34,7 @@ class NosVideoIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         fields = {
             'id': video_id,

youtube_dl/extractor/novamov.py

@@ -3,9 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_urlparse,
+)
 from ..utils import (
     ExtractorError,
-    compat_urlparse
 )
 
 

youtube_dl/extractor/nowvideo.py

@@ -7,7 +7,7 @@ class NowVideoIE(NovaMovIE):
     IE_NAME = 'nowvideo'
     IE_DESC = 'NowVideo'
 
-    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|sx|eu|at|ag|co)'}
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|sx|eu|at|ag|co|li)'}
 
     _HOST = 'www.nowvideo.ch'
 

youtube_dl/extractor/nuvid.py

@@ -3,15 +3,17 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_request,
+)
 from ..utils import (
     parse_duration,
     unified_strdate,
-    compat_urllib_request,
 )
 
 
 class NuvidIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://m.nuvid.com/video/1310741/',
         'md5': 'eab207b7ac4fccfb4e23c86201f11277',
@@ -26,8 +28,7 @@ class NuvidIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         formats = []
 

youtube_dl/extractor/ooyala.py

@@ -16,7 +16,6 @@ class OoyalaIE(InfoExtractor):
         {
             # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video
             'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
-            'md5': '3f5cceb3a7bf461d6c29dc466cf8033c',
             'info_dict': {
                 'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
                 'ext': 'mp4',
@@ -26,7 +25,6 @@ class OoyalaIE(InfoExtractor):
         }, {
             # Only available for ipad
             'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
-            'md5': '4b9754921fddb68106e48c142e2a01e6',
             'info_dict': {
                 'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
                 'ext': 'mp4',

youtube_dl/extractor/orf.py

@@ -20,21 +20,23 @@ class ORFTVthekIE(InfoExtractor):
     _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics/.+?|program/[^/]+)/(?P<id>\d+)'
 
     _TEST = {
-        'url': 'http://tvthek.orf.at/program/matinee-Was-Sie-schon-immer-ueber-Klassik-wissen-wollten/7317210/Was-Sie-schon-immer-ueber-Klassik-wissen-wollten/7319746/Was-Sie-schon-immer-ueber-Klassik-wissen-wollten/7319747',
-        'file': '7319747.mp4',
-        'md5': 'bd803c5d8c32d3c64a0ea4b4eeddf375',
+        'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
+        'playlist': [{
+            'md5': '2942210346ed779588f428a92db88712',
             'info_dict': {
-            'title': 'Was Sie schon immer über Klassik wissen wollten',
-            'description': 'md5:0ddf0d5f0060bd53f744edaa5c2e04a4',
-            'duration': 3508,
-            'upload_date': '20140105',
+                'id': '8896777',
+                'ext': 'mp4',
+                'title': 'Aufgetischt: Mit der Steirischen Tafelrunde',
+                'description': 'md5:c1272f0245537812d4e36419c207b67d',
+                'duration': 2668,
+                'upload_date': '20141208',
             },
+        }],
         'skip': 'Blocked outside of Austria',
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        playlist_id = mobj.group('id')
+        playlist_id = self._match_id(url)
         webpage = self._download_webpage(url, playlist_id)
 
         data_json = self._search_regex(
@@ -120,9 +122,7 @@ class ORFOE1IE(InfoExtractor):
     _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)'
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        show_id = mobj.group('id')
-
+        show_id = self._match_id(url)
         data = self._download_json(
             'http://oe1.orf.at/programm/%s/konsole' % show_id,
             show_id

youtube_dl/extractor/photobucket.py

@@ -4,16 +4,17 @@ import json
 import re
 
 from .common import InfoExtractor
-from ..utils import compat_urllib_parse
+from ..compat import compat_urllib_parse
 
 
 class PhotobucketIE(InfoExtractor):
     _VALID_URL = r'http://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
     _TEST = {
         'url': 'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0',
-        'file': 'zpsc0c3b9fa.mp4',
         'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99',
         'info_dict': {
+            'id': 'zpsc0c3b9fa',
+            'ext': 'mp4',
             'timestamp': 1367669341,
             'upload_date': '20130504',
             'uploader': 'rachaneronas',

youtube_dl/extractor/played.py

@@ -5,11 +5,13 @@ import re
 import os.path
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
 )
+from ..utils import (
+    ExtractorError,
+)
 
 
 class PlayedIE(InfoExtractor):
@@ -28,7 +30,6 @@ class PlayedIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
         orig_webpage = self._download_webpage(url, video_id)
 
         m_error = re.search(

youtube_dl/extractor/playfm.py

@@ -4,9 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
+)
+from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,

youtube_dl/extractor/playvid.py

@@ -3,31 +3,31 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    clean_html,
+from ..compat import (
     compat_urllib_parse,
 )
+from ..utils import (
+    clean_html,
+    ExtractorError,
+)
 
 
 class PlayvidIE(InfoExtractor):
-    _VALID_URL = r'^https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
+    _VALID_URL = r'https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
     _TEST = {
-        'url': 'http://www.playvid.com/watch/agbDDi7WZTV',
-        'md5': '44930f8afa616efdf9482daf4fe53e1e',
+        'url': 'http://www.playvid.com/watch/RnmBNgtrrJu',
+        'md5': 'ffa2f6b2119af359f544388d8c01eb6c',
         'info_dict': {
-            'id': 'agbDDi7WZTV',
+            'id': 'RnmBNgtrrJu',
             'ext': 'mp4',
-            'title': 'Michelle Lewin in Miami Beach',
-            'duration': 240,
+            'title': 'md5:9256d01c6317e3f703848b5906880dc8',
+            'duration': 82,
             'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         m_error = re.search(

youtube_dl/extractor/pornhub.py

@@ -4,10 +4,12 @@ import os
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
+    compat_urllib_parse,
     compat_urllib_parse_urlparse,
     compat_urllib_request,
-    compat_urllib_parse,
+)
+from ..utils import (
     str_to_int,
 )
 from ..aes import (
@@ -16,7 +18,7 @@ from ..aes import (
 
 
 class PornHubIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
+    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
     _TEST = {
         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
         'md5': '882f488fa1f0026f023f33576004a2ed',

youtube_dl/extractor/pornotube.py

@@ -1,56 +1,94 @@
 from __future__ import unicode_literals
 
-import re
+import json
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_request,
+)
 from ..utils import (
-    compat_urllib_parse,
-
-    unified_strdate,
+    int_or_none,
 )
 
 
 class PornotubeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
+    _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com/(?:[^?#]*?)/video/(?P<id>[0-9]+)'
     _TEST = {
-        'url': 'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
-        'md5': '374dd6dcedd24234453b295209aa69b6',
+        'url': 'http://www.pornotube.com/orientation/straight/video/4964/title/weird-hot-and-wet-science',
+        'md5': '60fc5a4f0d93a97968fc7999d98260c9',
         'info_dict': {
-            'id': '1689755',
-            'ext': 'flv',
-            'upload_date': '20090708',
-            'title': 'Marilyn-Monroe-Bathing',
-            'age_limit': 18
+            'id': '4964',
+            'ext': 'mp4',
+            'upload_date': '20141203',
+            'title': 'Weird Hot and Wet Science',
+            'description': 'md5:a8304bef7ef06cb4ab476ca6029b01b0',
+            'categories': ['Adult Humor', 'Blondes'],
+            'uploader': 'Alpha Blue Archives',
+            'thumbnail': 're:^https?://.*\\.jpg$',
+            'timestamp': 1417582800,
+            'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
 
-        video_id = mobj.group('videoid')
-        video_title = mobj.group('title')
+        # Fetch origin token
+        js_config = self._download_webpage(
+            'http://www.pornotube.com/assets/src/app/config.js', video_id,
+            note='Download JS config')
+        originAuthenticationSpaceKey = self._search_regex(
+            r"constant\('originAuthenticationSpaceKey',\s*'([^']+)'",
+            js_config, 'originAuthenticationSpaceKey')
 
-        # Get webpage content
-        webpage = self._download_webpage(url, video_id)
+        # Fetch actual token
+        token_req_data = {
+            'authenticationSpaceKey': originAuthenticationSpaceKey,
+            'credentials': 'Clip Application',
+        }
+        token_req = compat_urllib_request.Request(
+            'https://api.aebn.net/auth/v1/token/primal',
+            data=json.dumps(token_req_data).encode('utf-8'))
+        token_req.add_header('Content-Type', 'application/json')
+        token_req.add_header('Origin', 'http://www.pornotube.com')
+        token_answer = self._download_json(
+            token_req, video_id, note='Requesting primal token')
+        token = token_answer['tokenKey']
 
-        # Get the video URL
-        VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
-        video_url = self._search_regex(VIDEO_URL_RE, webpage, 'video url')
-        video_url = compat_urllib_parse.unquote(video_url)
+        # Get video URL
+        delivery_req = compat_urllib_request.Request(
+            'https://api.aebn.net/delivery/v1/clips/%s/MP4' % video_id)
+        delivery_req.add_header('Authorization', token)
+        delivery_info = self._download_json(
+            delivery_req, video_id, note='Downloading delivery information')
+        video_url = delivery_info['mediaUrl']
 
-        # Get the uploaded date
-        VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
-        upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, 'upload date', fatal=False)
-        if upload_date:
-            upload_date = unified_strdate(upload_date)
-        age_limit = self._rta_search(webpage)
+        # Get additional info (title etc.)
+        info_req = compat_urllib_request.Request(
+            'https://api.aebn.net/content/v1/clips/%s?expand='
+            'title,description,primaryImageNumber,startSecond,endSecond,'
+            'movie.title,movie.MovieId,movie.boxCoverFront,movie.stars,'
+            'movie.studios,stars.name,studios.name,categories.name,'
+            'clipActive,movieActive,publishDate,orientations' % video_id)
+        info_req.add_header('Authorization', token)
+        info = self._download_json(
+            info_req, video_id, note='Downloading metadata')
+
+        timestamp = int_or_none(info.get('publishDate'), scale=1000)
+        uploader = info.get('studios', [{}])[0].get('name')
+        movie_id = info['movie']['movieId']
+        thumbnail = 'http://pic.aebn.net/dis/t/%s/%s_%08d.jpg' % (
+            movie_id, movie_id, info['primaryImageNumber'])
+        categories = [c['name'] for c in info.get('categories')]
 
         return {
             'id': video_id,
             'url': video_url,
-            'upload_date': upload_date,
-            'title': video_title,
-            'ext': 'flv',
-            'format': 'flv',
-            'age_limit': age_limit,
+            'title': info['title'],
+            'description': info.get('description'),
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'age_limit': 18,
         }

youtube_dl/extractor/promptfile.py

@@ -4,12 +4,14 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    determine_ext,
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
 )
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+)
 
 
 class PromptFileIE(InfoExtractor):

youtube_dl/extractor/prosiebensat1.py

@@ -5,8 +5,10 @@ import re
 
 from hashlib import sha1
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
+)
+from ..utils import (
     unified_strdate,
 )
 

youtube_dl/extractor/quickvid.py

@@ -3,8 +3,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urlparse,
+)
+from ..utils import (
     determine_ext,
     int_or_none,
 )

youtube_dl/extractor/rai.py

@@ -3,10 +3,12 @@ from __future__ import unicode_literals
 import re
 
 from .subtitles import SubtitlesInfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+)
 from ..utils import (
     parse_duration,
     unified_strdate,
-    compat_urllib_parse,
 )
 
 

youtube_dl/extractor/restudy.py

@@ -0,0 +1,40 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class RestudyIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?restudy\.dk/video/play/id/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://www.restudy.dk/video/play/id/1637',
+        'info_dict': {
+            'id': '1637',
+            'ext': 'flv',
+            'title': 'Leiden-frosteffekt',
+            'description': 'Denne video er et eksperiment med flydende kvælstof.',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._og_search_title(webpage).strip()
+        description = self._og_search_description(webpage).strip()
+
+        formats = self._extract_smil_formats(
+            'https://www.restudy.dk/awsmedia/SmilDirectory/video_%s.xml' % video_id,
+            video_id)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'formats': formats,
+        }

youtube_dl/extractor/rtp.py

@@ -0,0 +1,57 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..utils import js_to_json
+
+
+class RTPIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P<program_id>[0-9]+)/e(?P<id>[0-9]+)/?'
+    _TEST = {
+        'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas',
+        'info_dict': {
+            'id': '174042',
+            'ext': 'mp3',
+            'title': 'Paixões Cruzadas',
+            'description': 'As paixões musicais de António Cartaxo e António Macedo',
+            'thumbnail': 're:^https?://.*\.jpg',
+        },
+        'params': {
+            'skip_download': True,  # RTMP download
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_meta(
+            'twitter:title', webpage, display_name='title', fatal=True)
+        description = self._html_search_meta('description', webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        player_config = self._search_regex(
+            r'(?s)RTPPLAY\.player\.newPlayer\(\s*(\{.*?\})\s*\)', webpage, 'player config')
+        config = json.loads(js_to_json(player_config))
+
+        path, ext = config.get('file').rsplit('.', 1)
+        formats = [{
+            'app': config.get('application'),
+            'play_path': '{ext:s}:{path:s}'.format(ext=ext, path=path),
+            'page_url': url,
+            'url': 'rtmp://{streamer:s}/{application:s}'.format(**config),
+            'rtmp_live': config.get('live', False),
+            'ext': ext,
+            'vcodec': config.get('type') == 'audio' and 'none' or None,
+            'player_url': 'http://programas.rtp.pt/play/player.swf?v3',
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/rts.py

@@ -4,12 +4,14 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+)
 from ..utils import (
     int_or_none,
     parse_duration,
     parse_iso8601,
     unescapeHTML,
-    compat_str,
 )
 
 

youtube_dl/extractor/rutube.py

@@ -5,10 +5,12 @@ import re
 import itertools
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_str,
-    unified_strdate,
+)
+from ..utils import (
     ExtractorError,
+    unified_strdate,
 )
 
 
@@ -36,9 +38,7 @@ class RutubeIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         video = self._download_json(
             'http://rutube.ru/api/video/%s/?format=json' % video_id,
             video_id, 'Downloading video JSON')
@@ -114,8 +114,7 @@ class RutubeMovieIE(RutubeChannelIE):
     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        movie_id = mobj.group('id')
+        movie_id = self._match_id(url)
         movie = self._download_json(
             self._MOVIE_TEMPLATE % movie_id, movie_id,
             'Downloading movie JSON')

youtube_dl/extractor/screencast.py

@@ -1,14 +1,14 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
+from ..compat import (
     compat_parse_qs,
     compat_urllib_request,
 )
+from ..utils import (
+    ExtractorError,
+)
 
 
 class ScreencastIE(InfoExtractor):
@@ -57,8 +57,7 @@ class ScreencastIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_url = self._html_search_regex(

youtube_dl/extractor/shared.py

@@ -4,10 +4,12 @@ import re
 import base64
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urllib_request,
+)
 from ..utils import (
     ExtractorError,
-    compat_urllib_request,
-    compat_urllib_parse,
     int_or_none,
 )
 
@@ -26,26 +28,30 @@ class SharedIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
 
-        page = self._download_webpage(url, video_id)
+        if '>File does not exist<' in webpage:
+            raise ExtractorError(
+                'Video %s does not exist' % video_id, expected=True)
 
-        if re.search(r'>File does not exist<', page) is not None:
-            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
-
-        download_form = dict(re.findall(r'<input type="hidden" name="([^"]+)" value="([^"]*)"', page))
-
-        request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(download_form))
+        download_form = dict(re.findall(
+            r'<input type="hidden" name="([^"]+)" value="([^"]*)"', webpage))
+        request = compat_urllib_request.Request(
+            url, compat_urllib_parse.urlencode(download_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 
-        video_page = self._download_webpage(request, video_id, 'Downloading video page')
+        video_page = self._download_webpage(
+            request, video_id, 'Downloading video page')
 
-        video_url = self._html_search_regex(r'data-url="([^"]+)"', video_page, 'video URL')
-        title = base64.b64decode(self._html_search_meta('full:title', page, 'title')).decode('utf-8')
-        filesize = int_or_none(self._html_search_meta('full:size', page, 'file size', fatal=False))
+        video_url = self._html_search_regex(
+            r'data-url="([^"]+)"', video_page, 'video URL')
+        title = base64.b64decode(self._html_search_meta(
+            'full:title', webpage, 'title')).decode('utf-8')
+        filesize = int_or_none(self._html_search_meta(
+            'full:size', webpage, 'file size', fatal=False))
         thumbnail = self._html_search_regex(
-            r'data-poster="([^"]+)"', video_page, 'thumbnail', fatal=False, default=None)
+            r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None)
 
         return {
             'id': video_id,

youtube_dl/extractor/sharesix.py

@@ -4,9 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
+)
+from ..utils import (
     parse_duration,
 )
 

youtube_dl/extractor/sina.py

@@ -4,7 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_request,
     compat_urllib_parse,
 )