Merge remote-tracking branch 'upstream/master' into yuvutu

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.10.02*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.10.07*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.10.02**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.10.07**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2016.10.02
+[debug] youtube-dl version 2016.10.07
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

ChangeLog

@@ -1,3 +1,32 @@
+version <unreleased>
+
+Core
+* [Makefile] Support for GNU make < 4 is fixed; BSD make dropped (#9387)
+
+Extractors
++ [nextmedia] Recognize action news on AppleDaily
+
+
+version 2016.10.07
+
+Extractors
++ [iprima] Detect geo restriction
+* [facebook] Fix video extraction (#10846)
++ [commonprotocols] Support direct MMS links (#10838)
++ [generic] Add support for multiple vimeo embeds (#10862)
++ [nzz] Add support for nzz.ch (#4407)
++ [npo] Detect geo restriction
++ [npo] Add support for 2doc.nl (#10842)
++ [lego] Add support for lego.com (#10369)
++ [tonline] Add support for t-online.de (#10376)
+* [techtalks] Relax URL regular expression (#10840)
+* [youtube:live] Extend URL regular expression (#10839)
++ [theweatherchannel] Add support for weather.com (#7188)
++ [thisoldhouse] Add support for thisoldhouse.com (#10837)
++ [nhl] Add support for wch2016.com (#10833)
+* [pornoxo] Use JWPlatform to improve metadata extraction
+
+
 version 2016.10.02
 
 Core

Makefile

@@ -12,7 +12,7 @@ SHAREDIR ?= $(PREFIX)/share
 PYTHON ?= /usr/bin/env python
 
 # set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
-SYSCONFDIR != if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi
+SYSCONFDIR = $(shell if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi)
 
 install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
 	install -d $(DESTDIR)$(BINDIR)
@@ -90,7 +90,7 @@ fish-completion: youtube-dl.fish
 
 lazy-extractors: youtube_dl/extractor/lazy_extractors.py
 
-_EXTRACTOR_FILES != find youtube_dl/extractor -iname '*.py' -and -not -iname 'lazy_extractors.py'
+_EXTRACTOR_FILES = $(shell find youtube_dl/extractor -iname '*.py' -and -not -iname 'lazy_extractors.py')
 youtube_dl/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
 	$(PYTHON) devscripts/make_lazy_extractors.py $@
 

README.md

@@ -923,7 +923,7 @@ To run the test, simply invoke your favorite test runner, or execute a test file
 If you want to create a build of youtube-dl yourself, you'll need
 
 * python
-* make (both GNU make and BSD make are supported)
+* make (only GNU make is supported)
 * pandoc
 * zip
 * nosetests

docs/supportedsites.md

@@ -364,6 +364,7 @@
  - **Le**: 乐视网
  - **Learnr**
  - **Lecture2Go**
+ - **LEGO**
  - **Lemonde**
  - **LePlaylist**
  - **LetvCloud**: 乐视云
@@ -507,6 +508,7 @@
  - **Nuvid**
  - **NYTimes**
  - **NYTimesArticle**
+ - **NZZ**
  - **ocw.mit.edu**
  - **OdaTV**
  - **Odnoklassniki**
@@ -692,6 +694,7 @@
  - **SWRMediathek**
  - **Syfy**
  - **SztvHu**
+ - **t-online.de**
  - **Tagesschau**
  - **tagesschau:player**
  - **Tass**
@@ -721,8 +724,10 @@
  - **TheScene**
  - **TheSixtyOne**
  - **TheStar**
+ - **TheWeatherChannel**
  - **ThisAmericanLife**
  - **ThisAV**
+ - **ThisOldHouse**
  - **tinypic**: tinypic.com videos
  - **tlc.de**
  - **TMZ**

youtube_dl/extractor/common.py

@@ -21,6 +21,7 @@ from ..compat import (
     compat_os_name,
     compat_str,
     compat_urllib_error,
+    compat_urllib_parse_unquote,
     compat_urllib_parse_urlencode,
     compat_urllib_request,
     compat_urlparse,
@@ -2020,6 +2021,12 @@ class InfoExtractor(object):
             headers['Ytdl-request-proxy'] = geo_verification_proxy
         return headers
 
+    def _generic_id(self, url):
+        return compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
+
+    def _generic_title(self, url):
+        return compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/commonprotocols.py

@@ -1,13 +1,9 @@
 from __future__ import unicode_literals
 
-import os
-
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse_unquote,
     compat_urlparse,
 )
-from ..utils import url_basename
 
 
 class RtmpIE(InfoExtractor):
@@ -23,8 +19,8 @@ class RtmpIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
+        video_id = self._generic_id(url)
-        title = compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
+        title = self._generic_title(url)
         return {
             'id': video_id,
             'title': title,
@@ -34,3 +30,31 @@ class RtmpIE(InfoExtractor):
                 'format_id': compat_urlparse.urlparse(url).scheme,
             }],
         }
+
+
+class MmsIE(InfoExtractor):
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'(?i)mms://.+'
+
+    _TEST = {
+        # Direct MMS link
+        'url': 'mms://kentro.kaist.ac.kr/200907/MilesReid(0709).wmv',
+        'info_dict': {
+            'id': 'MilesReid(0709)',
+            'ext': 'wmv',
+            'title': 'MilesReid(0709)',
+        },
+        'params': {
+            'skip_download': True,  # rtsp downloads, requiring mplayer or mpv
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._generic_id(url)
+        title = self._generic_title(url)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': url,
+        }

youtube_dl/extractor/extractors.py

@@ -186,7 +186,10 @@ from .comedycentral import (
 )
 from .comcarcoff import ComCarCoffIE
 from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
-from .commonprotocols import RtmpIE
+from .commonprotocols import (
+    MmsIE,
+    RtmpIE,
+)
 from .condenast import CondeNastIE
 from .cracked import CrackedIE
 from .crackle import CrackleIE
@@ -638,6 +641,7 @@ from .nytimes import (
     NYTimesArticleIE,
 )
 from .nuvid import NuvidIE
+from .nzz import NZZIE
 from .odatv import OdaTVIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE

youtube_dl/extractor/facebook.py

@@ -258,7 +258,7 @@ class FacebookIE(InfoExtractor):
 
         if not video_data:
             server_js_data = self._parse_json(self._search_regex(
-                r'handleServerJS\(({.+})\);', webpage, 'server js data', default='{}'), video_id)
+                r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id)
             for item in server_js_data.get('instances', []):
                 if item[1][0] == 'VideoConfig':
                     video_data = video_data_list2dict(item[2][0]['videoData'])

youtube_dl/extractor/generic.py

@@ -27,7 +27,6 @@ from ..utils import (
     unified_strdate,
     unsmuggle_url,
     UnsupportedError,
-    url_basename,
     xpath_text,
 )
 from .brightcove import (
@@ -1549,7 +1548,7 @@ class GenericIE(InfoExtractor):
             force_videoid = smuggled_data['force_videoid']
             video_id = force_videoid
         else:
-            video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
+            video_id = self._generic_id(url)
 
         self.to_screen('%s: Requesting header' % video_id)
 
@@ -1578,7 +1577,7 @@ class GenericIE(InfoExtractor):
 
         info_dict = {
             'id': video_id,
-            'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
+            'title': self._generic_title(url),
             'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
         }
 
@@ -1754,9 +1753,9 @@ class GenericIE(InfoExtractor):
         if matches:
             return _playlist_from_matches(matches, ie='RtlNl')
 
-        vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
+        vimeo_urls = VimeoIE._extract_urls(url, webpage)
-        if vimeo_url is not None:
+        if vimeo_urls:
-            return self.url_result(vimeo_url)
+            return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
 
         vid_me_embed_url = self._search_regex(
             r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',

youtube_dl/extractor/iprima.py

@@ -81,6 +81,9 @@ class IPrimaIE(InfoExtractor):
             for _, src in re.findall(r'src["\']\s*:\s*(["\'])(.+?)\1', playerpage):
                 extract_formats(src)
 
+        if not formats and '>GEO_IP_NOT_ALLOWED<' in playerpage:
+            self.raise_geo_restricted()
+
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/lego.py

@@ -1,45 +1,86 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
     unescapeHTML,
-    int_or_none,
+    parse_duration,
+    get_element_by_class,
 )
 
 
 class LEGOIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?lego\.com/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]+)'
+    _VALID_URL = r'https?://(?:www\.)?lego\.com/(?P<locale>[^/]+)/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.lego.com/en-us/videos/themes/club/blocumentary-kawaguchi-55492d823b1b4d5e985787fa8c2973b1',
         'md5': 'f34468f176cfd76488767fc162c405fa',
         'info_dict': {
             'id': '55492d823b1b4d5e985787fa8c2973b1',
             'ext': 'mp4',
             'title': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
-        }
+            'description': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
-    }
+        },
+    }, {
+        # geo-restricted but the contentUrl contain a valid url
+        'url': 'http://www.lego.com/nl-nl/videos/themes/nexoknights/episode-20-kingdom-of-heroes-13bdc2299ab24d9685701a915b3d71e7##sp=399',
+        'md5': '4c3fec48a12e40c6e5995abc3d36cc2e',
+        'info_dict': {
+            'id': '13bdc2299ab24d9685701a915b3d71e7',
+            'ext': 'mp4',
+            'title': 'Aflevering 20 - Helden van het koninkrijk',
+            'description': 'md5:8ee499aac26d7fa8bcb0cedb7f9c3941',
+        },
+    }, {
+        # special characters in title
+        'url': 'http://www.lego.com/en-us/starwars/videos/lego-star-wars-force-surprise-9685ee9d12e84ff38e84b4e3d0db533d',
+        'info_dict': {
+            'id': '9685ee9d12e84ff38e84b4e3d0db533d',
+            'ext': 'mp4',
+            'title': 'Force Surprise – LEGO® Star Wars™ Microfighters',
+            'description': 'md5:9c673c96ce6f6271b88563fe9dc56de3',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
     _BITRATES = [256, 512, 1024, 1536, 2560]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        locale, video_id = re.match(self._VALID_URL, url).groups()
-        webpage = self._download_webpage(
+        webpage = self._download_webpage(url, video_id)
-            'http://www.lego.com/en-US/mediaplayer/video/' + video_id, video_id)
+        title = get_element_by_class('video-header', webpage).strip()
-        title = self._search_regex(r'<title>(.+?)</title>', webpage, 'title')
+        progressive_base = 'https://lc-mediaplayerns-live-s.legocdn.com/'
-        video_data = self._parse_json(unescapeHTML(self._search_regex(
+        streaming_base = 'http://legoprod-f.akamaihd.net/'
-            r"video='([^']+)'", webpage, 'video data')), video_id)
+        content_url = self._html_search_meta('contentUrl', webpage)
-        progressive_base = self._search_regex(
+        path = self._search_regex(
-            r'data-video-progressive-url="([^"]+)"',
+            r'(?:https?:)?//[^/]+/(?:[iz]/s/)?public/(.+)_[0-9,]+\.(?:mp4|webm)',
-            webpage, 'progressive base', default='https://lc-mediaplayerns-live-s.legocdn.com/')
+            content_url, 'video path', default=None)
-        streaming_base = self._search_regex(
+        if not path:
-            r'data-video-streaming-url="([^"]+)"',
+            player_url = self._proto_relative_url(self._search_regex(
-            webpage, 'streaming base', default='http://legoprod-f.akamaihd.net/')
+                r'<iframe[^>]+src="((?:https?)?//(?:www\.)?lego\.com/[^/]+/mediaplayer/video/[^"]+)',
-        item_id = video_data['ItemId']
+                webpage, 'player url', default=None))
+            if not player_url:
+                base_url = self._proto_relative_url(self._search_regex(
+                    r'data-baseurl="([^"]+)"', webpage, 'base url',
+                    default='http://www.lego.com/%s/mediaplayer/video/' % locale))
+                player_url = base_url + video_id
+            player_webpage = self._download_webpage(player_url, video_id)
+            video_data = self._parse_json(unescapeHTML(self._search_regex(
+                r"video='([^']+)'", player_webpage, 'video data')), video_id)
+            progressive_base = self._search_regex(
+                r'data-video-progressive-url="([^"]+)"',
+                player_webpage, 'progressive base', default='https://lc-mediaplayerns-live-s.legocdn.com/')
+            streaming_base = self._search_regex(
+                r'data-video-streaming-url="([^"]+)"',
+                player_webpage, 'streaming base', default='http://legoprod-f.akamaihd.net/')
+            item_id = video_data['ItemId']
 
-        net_storage_path = video_data.get('NetStoragePath') or '/'.join([item_id[:2], item_id[2:4]])
+            net_storage_path = video_data.get('NetStoragePath') or '/'.join([item_id[:2], item_id[2:4]])
-        base_path = '_'.join([item_id, video_data['VideoId'], video_data['Locale'], compat_str(video_data['VideoVersion'])])
+            base_path = '_'.join([item_id, video_data['VideoId'], video_data['Locale'], compat_str(video_data['VideoVersion'])])
-        path = '/'.join([net_storage_path, base_path])
+            path = '/'.join([net_storage_path, base_path])
         streaming_path = ','.join(map(lambda bitrate: compat_str(bitrate), self._BITRATES))
 
         formats = self._extract_akamai_formats(
@@ -80,7 +121,8 @@ class LEGOIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'thumbnail': video_data.get('CoverImageUrl'),
+            'description': self._html_search_meta('description', webpage),
-            'duration': int_or_none(video_data.get('Length')),
+            'thumbnail': self._html_search_meta('thumbnail', webpage),
+            'duration': parse_duration(self._html_search_meta('duration', webpage)),
             'formats': formats,
         }

youtube_dl/extractor/nextmedia.py

@@ -93,7 +93,7 @@ class NextMediaActionNewsIE(NextMediaIE):
 
 class AppleDailyIE(NextMediaIE):
     IE_DESC = '臺灣蘋果日報'
-    _VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
+    _VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews|actionnews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
     _TESTS = [{
         'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
         'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
@@ -154,6 +154,9 @@ class AppleDailyIE(NextMediaIE):
             'description': 'md5:7b859991a6a4fedbdf3dd3b66545c748',
             'upload_date': '20140417',
         },
+    }, {
+        'url': 'http://www.appledaily.com.tw/actionnews/appledaily/7/20161003/960588/',
+        'only_matching': True,
     }]
 
     _URL_PATTERN = r'\{url: \'(.+)\'\}'

youtube_dl/extractor/npo.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_HTTPError
 from ..utils import (
     fix_xml_ampersands,
     orderedSet,
@@ -10,6 +11,7 @@ from ..utils import (
     qualities,
     strip_jsonp,
     unified_strdate,
+    ExtractorError,
 )
 
 
@@ -181,9 +183,16 @@ class NPOIE(NPOBaseIE):
                     continue
                 streams = format_info.get('streams')
                 if streams:
-                    video_info = self._download_json(
+                    try:
-                        streams[0] + '&type=json',
+                        video_info = self._download_json(
-                        video_id, 'Downloading %s stream JSON' % format_id)
+                            streams[0] + '&type=json',
+                            video_id, 'Downloading %s stream JSON' % format_id)
+                    except ExtractorError as ee:
+                        if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
+                            error = (self._parse_json(ee.cause.read().decode(), video_id, fatal=False) or {}).get('errorstring')
+                            if error:
+                                raise ExtractorError(error, expected=True)
+                        raise
                 else:
                     video_info = format_info
                 video_url = video_info.get('url')
@@ -459,8 +468,9 @@ class NPOPlaylistBaseIE(NPOIE):
 
 class VPROIE(NPOPlaylistBaseIE):
     IE_NAME = 'vpro'
-    _VALID_URL = r'https?://(?:www\.)?(?:tegenlicht\.)?vpro\.nl/(?:[^/]+/){2,}(?P<id>[^/]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
-    _PLAYLIST_TITLE_RE = r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)'
+    _PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)',
+                          r'<h5[^>]+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)')
     _PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
 
     _TESTS = [
@@ -492,6 +502,27 @@ class VPROIE(NPOPlaylistBaseIE):
                 'title': 'education education',
             },
             'playlist_count': 2,
+        },
+        {
+            'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
+            'info_dict': {
+                'id': 'de-tegenprestatie',
+                'title': 'De Tegenprestatie',
+            },
+            'playlist_count': 2,
+        }, {
+            'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
+            'info_dict': {
+                'id': 'VARA_101375237',
+                'ext': 'm4v',
+                'title': 'MH17: Het verdriet van Nederland',
+                'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
+                'upload_date': '20150716',
+            },
+            'params': {
+                # Skip because of m3u8 download
+                'skip_download': True
+            },
         }
     ]
 

youtube_dl/extractor/nzz.py

@@ -0,0 +1,36 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    extract_attributes,
+)
+
+
+class NZZIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nzz\.ch/(?:[^/]+/)*[^/?#]+-ld\.(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.nzz.ch/zuerich/gymizyte/gymizyte-schreiben-schueler-heute-noch-diktate-ld.9153',
+        'info_dict': {
+            'id': '9153',
+        },
+        'playlist_mincount': 6,
+    }
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+        webpage = self._download_webpage(url, page_id)
+
+        entries = []
+        for player_element in re.findall(r'(<[^>]+class="kalturaPlayer"[^>]*>)', webpage):
+            player_params = extract_attributes(player_element)
+            if player_params.get('data-type') not in ('kaltura_singleArticle',):
+                self.report_warning('Unsupported player type')
+                continue
+            entry_id = player_params['data-id']
+            entries.append(self.url_result(
+                'kaltura:1750922:' + entry_id, 'Kaltura', entry_id))
+
+        return self.playlist_result(entries, page_id)

youtube_dl/extractor/reverbnation.py

@@ -1,29 +1,29 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import str_or_none
+from ..utils import (
+    qualities,
+    str_or_none,
+)
 
 
 class ReverbNationIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$'
     _TESTS = [{
         'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa',
-        'md5': '3da12ebca28c67c111a7f8b262d3f7a7',
+        'md5': 'c0aaf339bcee189495fdf5a8c8ba8645',
         'info_dict': {
             'id': '16965047',
             'ext': 'mp3',
             'title': 'MONA LISA',
             'uploader': 'ALKILADOS',
             'uploader_id': '216429',
-            'thumbnail': 're:^https://gp1\.wac\.edgecastcdn\.net/.*?\.jpg$'
+            'thumbnail': 're:^https?://.*\.jpg',
         },
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        song_id = self._match_id(url)
-        song_id = mobj.group('id')
 
         api_res = self._download_json(
             'https://api.reverbnation.com/song/%s' % song_id,
@@ -31,14 +31,23 @@ class ReverbNationIE(InfoExtractor):
             note='Downloading information of song %s' % song_id
         )
 
+        THUMBNAILS = ('thumbnail', 'image')
+        quality = qualities(THUMBNAILS)
+        thumbnails = []
+        for thumb_key in THUMBNAILS:
+            if api_res.get(thumb_key):
+                thumbnails.append({
+                    'url': api_res[thumb_key],
+                    'preference': quality(thumb_key)
+                })
+
         return {
             'id': song_id,
-            'title': api_res.get('name'),
+            'title': api_res['name'],
-            'url': api_res.get('url'),
+            'url': api_res['url'],
             'uploader': api_res.get('artist', {}).get('name'),
             'uploader_id': str_or_none(api_res.get('artist', {}).get('id')),
-            'thumbnail': self._proto_relative_url(
+            'thumbnails': thumbnails,
-                api_res.get('image', api_res.get('thumbnail'))),
             'ext': 'mp3',
             'vcodec': 'none',
         }

youtube_dl/extractor/slutload.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -9,7 +7,7 @@ class SlutloadIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
     _TEST = {
         'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
-        'md5': '0cf531ae8006b530bd9df947a6a0df77',
+        'md5': '868309628ba00fd488cf516a113fd717',
         'info_dict': {
             'id': 'TD73btpBqSxc',
             'ext': 'mp4',
@@ -20,9 +18,7 @@ class SlutloadIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = mobj.group('id')
-
         webpage = self._download_webpage(url, video_id)
 
         video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',

youtube_dl/extractor/vimeo.py

@@ -355,23 +355,28 @@ class VimeoIE(VimeoBaseInfoExtractor):
         return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
 
     @staticmethod
-    def _extract_vimeo_url(url, webpage):
+    def _extract_urls(url, webpage):
+        urls = []
         # Look for embedded (iframe) Vimeo player
-        mobj = re.search(
+        for mobj in re.finditer(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
+                r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1',
-        if mobj:
+                webpage):
-            player_url = unescapeHTML(mobj.group('url'))
+            urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
-            return VimeoIE._smuggle_referrer(player_url, url)
+        PLAIN_EMBED_RE = (
-        # Look for embedded (swf embed) Vimeo player
+            # Look for embedded (swf embed) Vimeo player
-        mobj = re.search(
+            r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
-            r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
+            # Look more for non-standard embedded Vimeo player
-        if mobj:
+            r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
-            return mobj.group(1)
+        )
-        # Look more for non-standard embedded Vimeo player
+        for embed_re in PLAIN_EMBED_RE:
-        mobj = re.search(
+            for mobj in re.finditer(embed_re, webpage):
-            r'<video[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)(?P=q1)', webpage)
+                urls.append(mobj.group('url'))
-        if mobj:
+        return urls
-            return mobj.group('url')
+
+    @staticmethod
+    def _extract_url(url, webpage):
+        urls = VimeoIE._extract_urls(url, webpage)
+        return urls[0] if urls else None
 
     def _verify_player_video_password(self, url, video_id):
         password = self._downloader.params.get('videopassword')

youtube_dl/extractor/vk.py

@@ -341,7 +341,7 @@ class VKIE(VKBaseIE):
         if youtube_url:
             return self.url_result(youtube_url, 'Youtube')
 
-        vimeo_url = VimeoIE._extract_vimeo_url(url, info_page)
+        vimeo_url = VimeoIE._extract_url(url, info_page)
         if vimeo_url is not None:
             return self.url_result(vimeo_url)
 

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2016.10.02'
+__version__ = '2016.10.07'