New upstream version 2019.09.01

[youtubedl] / youtube_dl / extractor / generic.py

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 545e033711995d04544aa1dafea11110084fa58f..d1725d98b0c63f72031068a001ea150b54fd23ec 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -89,7 +89,10 @@ from .piksel import PikselIE
 from .videa import VideaIE
 from .twentymin import TwentyMinutenIE
 from .ustream import UstreamIE
 from .videa import VideaIE
 from .twentymin import TwentyMinutenIE
 from .ustream import UstreamIE

-from .openload import OpenloadIE
+from .openload import (
+    OpenloadIE,
+    VerystreamIE,
+)

 from .videopress import VideoPressIE
 from .rutube import RutubeIE
 from .limelight import LimelightBaseIE
 from .videopress import VideoPressIE
 from .rutube import RutubeIE
 from .limelight import LimelightBaseIE


@@ -109,11 +112,13 @@ from .vice import ViceIE
 from .xfileshare import XFileShareIE
 from .cloudflarestream import CloudflareStreamIE
 from .peertube import PeerTubeIE
 from .xfileshare import XFileShareIE
 from .cloudflarestream import CloudflareStreamIE
 from .peertube import PeerTubeIE

+from .teachable import TeachableIE

 from .indavideo import IndavideoEmbedIE
 from .apa import APAIE
 from .foxnews import FoxNewsIE
 from .viqeo import ViqeoIE
 from .expressen import ExpressenIE
 from .indavideo import IndavideoEmbedIE
 from .apa import APAIE
 from .foxnews import FoxNewsIE
 from .viqeo import ViqeoIE
 from .expressen import ExpressenIE

+from .zype import ZypeIE

 
 
 class GenericIE(InfoExtractor):
 
 
 class GenericIE(InfoExtractor):


@@ -428,7 +433,7 @@ class GenericIE(InfoExtractor):
             },
         },
         {
             },
         },
         {

-            # https://github.com/rg3/youtube-dl/issues/2253
+            # https://github.com/ytdl-org/youtube-dl/issues/2253

             'url': 'http://bcove.me/i6nfkrc3',
             'md5': '0ba9446db037002366bab3b3eb30c88c',
             'info_dict': {
             'url': 'http://bcove.me/i6nfkrc3',
             'md5': '0ba9446db037002366bab3b3eb30c88c',
             'info_dict': {


@@ -453,7 +458,7 @@ class GenericIE(InfoExtractor):
             },
         },
         {
             },
         },
         {

-            # https://github.com/rg3/youtube-dl/issues/3541
+            # https://github.com/ytdl-org/youtube-dl/issues/3541

             'add_ie': ['BrightcoveLegacy'],
             'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
             'info_dict': {
             'add_ie': ['BrightcoveLegacy'],
             'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
             'info_dict': {


@@ -917,7 +922,7 @@ class GenericIE(InfoExtractor):
             }
         },
         # Multiple brightcove videos
             }
         },
         # Multiple brightcove videos

-        # https://github.com/rg3/youtube-dl/issues/2283
+        # https://github.com/ytdl-org/youtube-dl/issues/2283

         {
             'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
             'info_dict': {
         {
             'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
             'info_dict': {


@@ -2070,6 +2075,36 @@ class GenericIE(InfoExtractor):
             },
             'playlist_count': 6,
         },
             },
             'playlist_count': 6,
         },

+        {
+            # Squarespace video embed, 2019-08-28
+            'url': 'http://ootboxford.com',
+            'info_dict': {
+                'id': 'Tc7b_JGdZfw',
+                'title': 'Out of the Blue, at Childish Things 10',
+                'ext': 'mp4',
+                'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
+                'uploader_id': 'helendouglashouse',
+                'uploader': 'Helen & Douglas House',
+                'upload_date': '20140328',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
+        {
+            # Zype embed
+            'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
+            'info_dict': {
+                'id': '5b400b834b32992a310622b9',
+                'ext': 'mp4',
+                'title': 'Smoky Barbecue Favorites',
+                'thumbnail': r're:^https?://.*\.jpe?g',
+            },
+            'add_ie': [ZypeIE.ie_key()],
+            'params': {
+                'skip_download': True,
+            },
+        },

         {
             # videojs embed
             'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
         {
             # videojs embed
             'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',


@@ -2085,6 +2120,23 @@ class GenericIE(InfoExtractor):
             },
             'expected_warnings': ['Failed to download MPD manifest'],
         },
             },
             '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
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject


@@ -2181,10 +2233,7 @@ class GenericIE(InfoExtractor):
 
     def _real_extract(self, url):
         if url.startswith('//'):
 
     def _real_extract(self, url):
         if url.startswith('//'):

-            return {
-                '_type': 'url',
-                'url': self.http_scheme() + url,
-            }
+            return self.url_result(self.http_scheme() + url)

 
         parsed_url = compat_urlparse.urlparse(url)
         if not parsed_url.scheme:
 
         parsed_url = compat_urlparse.urlparse(url)
         if not parsed_url.scheme:


@@ -2193,7 +2242,7 @@ class GenericIE(InfoExtractor):
                 default_search = 'fixup_error'
 
             if default_search in ('auto', 'auto_warning', 'fixup_error'):
                 default_search = 'fixup_error'
 
             if default_search in ('auto', 'auto_warning', 'fixup_error'):

-                if '/' in url:
+                if re.match(r'^[^\s/]+\.[^\s/]+/', url):

                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
                     return self.url_result('http://' + url)
                 elif default_search != 'fixup_error':
                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
                     return self.url_result('http://' + url)
                 elif default_search != 'fixup_error':


@@ -2358,10 +2407,16 @@ class GenericIE(InfoExtractor):
             return camtasia_res
 
         # Sometimes embedded video player is hidden behind percent encoding
             return camtasia_res
 
         # Sometimes embedded video player is hidden behind percent encoding

-        # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
+        # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)

         # Unescaping the whole page allows to handle those cases in a generic way
         webpage = compat_urllib_parse_unquote(webpage)
 
         # Unescaping the whole page allows to handle those cases in a generic way
         webpage = compat_urllib_parse_unquote(webpage)
 

+        # Unescape squarespace embeds to be detected by generic extractor,
+        # see https://github.com/ytdl-org/youtube-dl/issues/21294
+        webpage = re.sub(
+            r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
+            lambda x: unescapeHTML(x.group(0)), webpage)
+

         # it's tempting to parse this further, but you would
         # have to take into account all the variations like
         #   Video Title - Site Name
         # it's tempting to parse this further, but you would
         # have to take into account all the variations like
         #   Video Title - Site Name


@@ -2533,11 +2588,11 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'))
 
         # Look for Ooyala videos
             return self.url_result(mobj.group('url'))
 
         # Look for Ooyala videos

-        mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
-                re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
-                re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
-                re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
-                re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
+        mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
+                or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
+                or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
+                or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
+                or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))

         if mobj is not None:
             embed_token = self._search_regex(
                 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
         if mobj is not None:
             embed_token = self._search_regex(
                 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',


@@ -2567,19 +2622,6 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group(1), 'Mpora')
 
         if mobj is not None:
             return self.url_result(mobj.group(1), 'Mpora')
 

-        # Look for embedded NovaMov-based player
-        mobj = re.search(
-            r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
-                    (?P<url>http://(?:(?:embed|www)\.)?
-                        (?:novamov\.com|
-                           nowvideo\.(?:ch|sx|eu|at|ag|co)|
-                           videoweed\.(?:es|com)|
-                           movshare\.(?:net|sx|ag)|
-                           divxstage\.(?:eu|net|ch|co|at|ag))
-                        /embed\.php.+?)\1''', webpage)
-        if mobj is not None:
-            return self.url_result(mobj.group('url'))
-

         # Look for embedded Facebook player
         facebook_urls = FacebookIE._extract_urls(webpage)
         if facebook_urls:
         # Look for embedded Facebook player
         facebook_urls = FacebookIE._extract_urls(webpage)
         if facebook_urls:


@@ -3004,6 +3046,12 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
 
             return self.playlist_from_matches(
                 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
 

+        # Look for Verystream embeds
+        verystream_urls = VerystreamIE._extract_urls(webpage)
+        if verystream_urls:
+            return self.playlist_from_matches(
+                verystream_urls, video_id, video_title, ie=VerystreamIE.ie_key())
+

         # Look for VideoPress embeds
         videopress_urls = VideoPressIE._extract_urls(webpage)
         if videopress_urls:
         # Look for VideoPress embeds
         videopress_urls = VideoPressIE._extract_urls(webpage)
         if videopress_urls:


@@ -3097,6 +3145,10 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
 
             return self.playlist_from_matches(
                 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
 

+        teachable_url = TeachableIE._extract_url(webpage, url)
+        if teachable_url:
+            return self.url_result(teachable_url)
+

         indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
         if indavideo_urls:
             return self.playlist_from_matches(
         indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
         if indavideo_urls:
             return self.playlist_from_matches(


@@ -3129,6 +3181,11 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
 
             return self.playlist_from_matches(
                 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
 

+        zype_urls = ZypeIE._extract_urls(webpage)
+        if zype_urls:
+            return self.playlist_from_matches(
+                zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
+

         # Look for HTML5 media
         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
         if entries:
         # Look for HTML5 media
         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
         if entries:


@@ -3155,7 +3212,7 @@ class GenericIE(InfoExtractor):
                     jwplayer_data, video_id, require_title=False, base_url=url)
                 return merge_dicts(info, info_dict)
             except ExtractorError:
                     jwplayer_data, video_id, require_title=False, base_url=url)
                 return merge_dicts(info, info_dict)
             except ExtractorError:

-                # See https://github.com/rg3/youtube-dl/pull/16735
+                # See https://github.com/ytdl-org/youtube-dl/pull/16735

                 pass
 
         # Video.js embed
                 pass
 
         # Video.js embed


@@ -3190,8 +3247,8 @@ class GenericIE(InfoExtractor):
                 else:
                     formats.append({
                         'url': src,
                 else:
                     formats.append({
                         'url': src,

-                        'ext': (mimetype2ext(src_type) or
-                                ext if ext in KNOWN_EXTENSIONS else 'mp4'),
+                        'ext': (mimetype2ext(src_type)
+                                or ext if ext in KNOWN_EXTENSIONS else 'mp4'),

                     })
             if formats:
                 self._sort_formats(formats)
                     })
             if formats:
                 self._sort_formats(formats)