Merge branch 'master' into fix.25.12.2018

youtube_dl/extractor/acast.py

@@ -7,6 +7,7 @@ import functools
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
+    clean_html,
     float_or_none,
     int_or_none,
     try_get,
@@ -27,7 +28,7 @@ class ACastIE(InfoExtractor):
                     '''
     _TESTS = [{
         'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
-        'md5': 'a02393c74f3bdb1801c3ec2695577ce0',
+        'md5': '16d936099ec5ca2d5869e3a813ee8dc4',
         'info_dict': {
             'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
             'ext': 'mp3',
@@ -46,28 +47,37 @@ class ACastIE(InfoExtractor):
     }, {
         'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22',
         'only_matching': True,
+    }, {
+        'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         channel, display_id = re.match(self._VALID_URL, url).groups()
         s = self._download_json(
-            'https://play-api.acast.com/stitch/%s/%s' % (channel, display_id),
+            'https://feeder.acast.com/api/v1/shows/%s/episodes/%s' % (channel, display_id),
-            display_id)['result']
+            display_id)
         media_url = s['url']
+        if re.search(r'[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12}', display_id):
+            episode_url = s.get('episodeUrl')
+            if episode_url:
+                display_id = episode_url
+            else:
+                channel, display_id = re.match(self._VALID_URL, s['link']).groups()
         cast_data = self._download_json(
             'https://play-api.acast.com/splash/%s/%s' % (channel, display_id),
             display_id)['result']
         e = cast_data['episode']
-        title = e['name']
+        title = e.get('name') or s['title']
         return {
             'id': compat_str(e['id']),
             'display_id': display_id,
             'url': media_url,
             'title': title,
-            'description': e.get('description') or e.get('summary'),
+            'description': e.get('summary') or clean_html(e.get('description') or s.get('description')),
             'thumbnail': e.get('image'),
-            'timestamp': unified_timestamp(e.get('publishingDate')),
+            'timestamp': unified_timestamp(e.get('publishingDate') or s.get('publishDate')),
-            'duration': float_or_none(s.get('duration') or e.get('duration')),
+            'duration': float_or_none(e.get('duration') or s.get('duration')),
             'filesize': int_or_none(e.get('contentLength')),
             'creator': try_get(cast_data, lambda x: x['show']['author'], compat_str),
             'series': try_get(cast_data, lambda x: x['show']['name'], compat_str),

youtube_dl/extractor/dailymotion.py

@@ -137,10 +137,16 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
 
     @staticmethod
     def _extract_urls(webpage):
+        urls = []
         # Look for embedded Dailymotion player
-        matches = re.findall(
+        # https://developer.dailymotion.com/player#player-parameters
-            r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
+        for mobj in re.finditer(
-        return list(map(lambda m: unescapeHTML(m[1]), matches))
+                r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage):
+            urls.append(unescapeHTML(mobj.group('url')))
+        for mobj in re.finditer(
+                r'(?s)DM\.player\([^,]+,\s*{.*?video[\'"]?\s*:\s*["\']?(?P<id>[0-9a-zA-Z]+).+?}\s*\);', webpage):
+            urls.append('https://www.dailymotion.com/embed/video/' + mobj.group('id'))
+        return urls
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/generic.py

@@ -2104,6 +2104,23 @@ class GenericIE(InfoExtractor):
             },
             'expected_warnings': ['Failed to download MPD manifest'],
         },
+        {
+            # DailyMotion embed with DM.player
+            'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
+            'info_dict': {
+                'id': 'k6aKkGHd9FJs4mtJN39',
+                'ext': 'mp4',
+                'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
+                'description': 'This video is private.',
+                'uploader_id': 'x1jf30l',
+                'uploader': 'beIN SPORTS USA',
+                'upload_date': '20190528',
+                'timestamp': 1559062971,
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject

youtube_dl/extractor/openload.py

@@ -243,7 +243,7 @@ class PhantomJSwrapper(object):
 
 
 class OpenloadIE(InfoExtractor):
-    _DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|life|live|space|services|website)|oladblock\.(?:services|xyz|me)|openloed\.co)'
+    _DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|life|live|space|services|website)|oladblock\.(?:services|xyz|me)|openloed\.co)'
     _VALID_URL = r'''(?x)
                     https?://
                         (?P<host>
@@ -365,6 +365,9 @@ class OpenloadIE(InfoExtractor):
     }, {
         'url': 'https://oload.life/embed/oOzZjNPw9Dc/',
         'only_matching': True,
+    }, {
+        'url': 'https://oload.biz/f/bEk3Gp8ARr4/',
+        'only_matching': True,
     }, {
         'url': 'https://oladblock.services/f/b8NWEgkqNLI/',
         'only_matching': True,

youtube_dl/extractor/twitter.py

@@ -2,7 +2,7 @@
 from __future__ import unicode_literals
 
 import re
-
+import time
 from .common import InfoExtractor
 from ..compat import compat_urlparse
 from ..utils import (
@@ -247,7 +247,7 @@ class TwitterCardIE(TwitterBaseIE):
                     '%s/guest/activate.json' % self._API_BASE, video_id,
                     'Downloading guest token', data=b'',
                     headers=headers)['guest_token']
-                self._set_cookie('api.twitter.com', 'gt', guest_token)
+                self._set_cookie('api.twitter.com', 'gt', guest_token, expire_time=time.time() + 3000)
             else:
                 guest_token = guest_token_c.value
 

youtube_dl/extractor/xiami.py

@@ -7,7 +7,7 @@ from ..utils import int_or_none
 
 
 class XiamiBaseIE(InfoExtractor):
-    _API_BASE_URL = 'http://www.xiami.com/song/playlist/cat/json/id'
+    _API_BASE_URL = 'https://emumo.xiami.com/song/playlist/cat/json/id'
 
     def _download_webpage_handle(self, *args, **kwargs):
         webpage = super(XiamiBaseIE, self)._download_webpage_handle(*args, **kwargs)

youtube_dl/extractor/yourporn.py

@@ -37,7 +37,7 @@ class YourPornIE(InfoExtractor):
             self._search_regex(
                 r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
                 group='data'),
-            video_id)[video_id]).replace('/cdn/', '/cdn4/')
+            video_id)[video_id]).replace('/cdn/', '/cdn5/')
 
         title = (self._search_regex(
             r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',