Update to ytdl-commit-dfbbe29

[redbulltv] fix embed data extraction
dfbbe2902f

yt_dlp/extractor/eroprofile.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 from ..compat import compat_urllib_parse_urlencode
 from ..utils import (
     ExtractorError,
-    unescapeHTML
+    merge_dicts,
 )
 
 
@@ -24,7 +24,8 @@ class EroProfileIE(InfoExtractor):
             'title': 'sexy babe softcore',
             'thumbnail': r're:https?://.*\.jpg',
             'age_limit': 18,
-        }
+        },
+        'skip': 'Video not found',
     }, {
         'url': 'http://www.eroprofile.com/m/videos/view/Try-It-On-Pee_cut_2-wmv-4shared-com-file-sharing-download-movie-file',
         'md5': '1baa9602ede46ce904c431f5418d8916',
@@ -77,19 +78,15 @@ class EroProfileIE(InfoExtractor):
             [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
             webpage, 'video id', default=None)
 
-        video_url = unescapeHTML(self._search_regex(
-            r'<source src="([^"]+)', webpage, 'video url'))
         title = self._html_search_regex(
-            r'Title:</th><td>([^<]+)</td>', webpage, 'title')
+            (r'Title:</th><td>([^<]+)</td>', r'<h1[^>]*>(.+?)</h1>'),
-        thumbnail = self._search_regex(
+            webpage, 'title')
-            r'onclick="showVideoPlayer\(\)"><img src="([^"]+)',
-            webpage, 'thumbnail', fatal=False)
 
-        return {
+        info = self._parse_html5_media_entries(url, webpage, video_id)[0]
+
+        return merge_dicts(info, {
             'id': video_id,
             'display_id': display_id,
-            'url': video_url,
             'title': title,
-            'thumbnail': thumbnail,
             'age_limit': 18,
-        }
+        })

yt_dlp/extractor/extractors.py

@@ -985,6 +985,7 @@ from .platzi import (
 from .playfm import PlayFMIE
 from .playplustv import PlayPlusTVIE
 from .plays import PlaysTVIE
+from .playstuff import PlayStuffIE
 from .playtvak import PlaytvakIE
 from .playvid import PlayvidIE
 from .playwire import PlaywireIE

yt_dlp/extractor/generic.py

@@ -126,6 +126,7 @@ from .viqeo import ViqeoIE
 from .expressen import ExpressenIE
 from .zype import ZypeIE
 from .odnoklassniki import OdnoklassnikiIE
+from .vk import VKIE
 from .kinja import KinjaEmbedIE
 from .gedidigital import GediDigitalIE
 from .rcs import RCSEmbedsIE
@@ -2252,6 +2253,10 @@ class GenericIE(InfoExtractor):
             'playlist_mincount': 52,
         },
         {
+            # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
+            'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
+            'only_matching': True,
+        }, {
             # WimTv embed player
             'url': 'http://www.msmotor.tv/wearefmi-pt-2-2021/',
             'info_dict': {
@@ -2803,6 +2808,11 @@ class GenericIE(InfoExtractor):
         if odnoklassniki_url:
             return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
 
+        # Look for sibnet embedded player
+        sibnet_urls = VKIE._extract_sibnet_urls(webpage)
+        if sibnet_urls:
+            return self.playlist_from_matches(sibnet_urls, video_id, video_title)
+
         # Look for embedded ivi player
         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
         if mobj is not None:
@@ -3454,6 +3464,9 @@ class GenericIE(InfoExtractor):
                         'url': src,
                         'ext': (mimetype2ext(src_type)
                                 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
+                        'http_headers': {
+                            'Referer': full_response.geturl(),
+                        },
                     })
             if formats:
                 self._sort_formats(formats)
@@ -3522,7 +3535,7 @@ class GenericIE(InfoExtractor):
             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
             if m_video_type is not None:
-                found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
+                found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
         if not found:
             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
             found = re.search(

yt_dlp/extractor/orf.py

@@ -182,7 +182,7 @@ class ORFRadioIE(InfoExtractor):
             duration = end - start if end and start else None
             entries.append({
                 'id': loop_stream_id.replace('.mp3', ''),
-                'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id),
+                'url': 'https://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id),
                 'title': title,
                 'description': clean_html(data.get('subtitle')),
                 'duration': duration,

yt_dlp/extractor/phoenix.py

@@ -9,8 +9,9 @@ from ..compat import compat_str
 from ..utils import (
     int_or_none,
     merge_dicts,
+    try_get,
     unified_timestamp,
-    xpath_text,
+    urljoin,
 )
 
 
@@ -27,10 +28,11 @@ class PhoenixIE(ZDFBaseIE):
             'title': 'Wohin führt der Protest in der Pandemie?',
             'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
             'duration': 1691,
-            'timestamp': 1613906100,
+            'timestamp': 1613902500,
             'upload_date': '20210221',
             'uploader': 'Phoenix',
-            'channel': 'corona nachgehakt',
+            'series': 'corona nachgehakt',
+            'episode': 'Wohin führt der Protest in der Pandemie?',
         },
     }, {
         # Youtube embed
@@ -79,50 +81,53 @@ class PhoenixIE(ZDFBaseIE):
 
         video_id = compat_str(video.get('basename') or video.get('content'))
 
-        details = self._download_xml(
+        details = self._download_json(
             'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
-            video_id, 'Downloading details XML', query={
+            video_id, 'Downloading details JSON', query={
                 'ak': 'web',
                 'ptmd': 'true',
                 'id': video_id,
                 'profile': 'player2',
             })
 
-        title = title or xpath_text(
+        title = title or details['title']
-            details, './/information/title', 'title', fatal=True)
+        content_id = details['tracking']['nielsen']['content']['assetid']
-        content_id = xpath_text(
-            details, './/video/details/basename', 'content id', fatal=True)
 
         info = self._extract_ptmd(
             'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/%s' % content_id,
             content_id, None, url)
 
-        timestamp = unified_timestamp(xpath_text(details, './/details/airtime'))
+        duration = int_or_none(try_get(
+            details, lambda x: x['tracking']['nielsen']['content']['length']))
+        timestamp = unified_timestamp(details.get('editorialDate'))
+        series = try_get(
+            details, lambda x: x['tracking']['nielsen']['content']['program'],
+            compat_str)
+        episode = title if details.get('contentType') == 'episode' else None
 
         thumbnails = []
-        for node in details.findall('.//teaserimages/teaserimage'):
+        teaser_images = try_get(details, lambda x: x['teaserImageRef']['layouts'], dict) or {}
-            thumbnail_url = node.text
+        for thumbnail_key, thumbnail_url in teaser_images.items():
+            thumbnail_url = urljoin(url, thumbnail_url)
             if not thumbnail_url:
                 continue
             thumbnail = {
                 'url': thumbnail_url,
             }
-            thumbnail_key = node.get('key')
+            m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
-            if thumbnail_key:
+            if m:
-                m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
+                thumbnail['width'] = int(m.group(1))
-                if m:
+                thumbnail['height'] = int(m.group(2))
-                    thumbnail['width'] = int(m.group(1))
-                    thumbnail['height'] = int(m.group(2))
             thumbnails.append(thumbnail)
 
         return merge_dicts(info, {
             'id': content_id,
             'title': title,
-            'description': xpath_text(details, './/information/detail'),
+            'description': details.get('leadParagraph'),
-            'duration': int_or_none(xpath_text(details, './/details/lengthSec')),
+            'duration': duration,
             'thumbnails': thumbnails,
             'timestamp': timestamp,
-            'uploader': xpath_text(details, './/details/channel'),
+            'uploader': details.get('tvService'),
-            'uploader_id': xpath_text(details, './/details/originChannelId'),
+            'series': series,
-            'channel': xpath_text(details, './/details/originChannelTitle'),
+            'episode': episode,
         })

yt_dlp/extractor/playstuff.py

@@ -0,0 +1,65 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    smuggle_url,
+    try_get,
+)
+
+
+class PlayStuffIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?play\.stuff\.co\.nz/details/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://play.stuff.co.nz/details/608778ac1de1c4001a3fa09a',
+        'md5': 'c82d3669e5247c64bc382577843e5bd0',
+        'info_dict': {
+            'id': '6250584958001',
+            'ext': 'mp4',
+            'title': 'Episode 1: Rotorua/Mt Maunganui/Tauranga',
+            'description': 'md5:c154bafb9f0dd02d01fd4100fb1c1913',
+            'uploader_id': '6005208634001',
+            'timestamp': 1619491027,
+            'upload_date': '20210427',
+        },
+        'add_ie': ['BrightcoveNew'],
+    }, {
+        # geo restricted, bypassable
+        'url': 'https://play.stuff.co.nz/details/_6155660351001',
+        'only_matching': True,
+    }]
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        state = self._parse_json(
+            self._search_regex(
+                r'__INITIAL_STATE__\s*=\s*({.+?})\s*;', webpage, 'state'),
+            video_id)
+
+        account_id = try_get(
+            state, lambda x: x['configurations']['accountId'],
+            compat_str) or '6005208634001'
+        player_id = try_get(
+            state, lambda x: x['configurations']['playerId'],
+            compat_str) or 'default'
+
+        entries = []
+        for item_id, video in state['items'].items():
+            if not isinstance(video, dict):
+                continue
+            asset_id = try_get(
+                video, lambda x: x['content']['attributes']['assetId'],
+                compat_str)
+            if not asset_id:
+                continue
+            entries.append(self.url_result(
+                smuggle_url(
+                    self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, asset_id),
+                    {'geo_countries': ['NZ']}),
+                'BrightcoveNew', video_id))
+
+        return self.playlist_result(entries, video_id)

yt_dlp/extractor/redbulltv.py

@@ -133,8 +133,10 @@ class RedBullEmbedIE(RedBullTVIE):
         rrn_id = self._match_id(url)
         asset_id = self._download_json(
             'https://edge-graphql.crepo-production.redbullaws.com/v1/graphql',
-            rrn_id, headers={'API-KEY': 'e90a1ff11335423998b100c929ecc866'},
+            rrn_id, headers={
-            query={
+                'Accept': 'application/json',
+                'API-KEY': 'e90a1ff11335423998b100c929ecc866',
+            }, query={
                 'query': '''{
   resource(id: "%s", enforceGeoBlocking: false) {
     %s

yt_dlp/extractor/shahid.py

@@ -21,6 +21,7 @@ from ..utils import (
 class ShahidBaseIE(AWSIE):
     _AWS_PROXY_HOST = 'api2.shahid.net'
     _AWS_API_KEY = '2RRtuMHx95aNI1Kvtn2rChEuwsCogUd4samGPjLh'
+    _VALID_URL_BASE = r'https?://shahid\.mbc\.net/[a-z]{2}/'
 
     def _handle_error(self, e):
         fail_data = self._parse_json(
@@ -49,7 +50,7 @@ class ShahidBaseIE(AWSIE):
 
 class ShahidIE(ShahidBaseIE):
     _NETRC_MACHINE = 'shahid'
-    _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
+    _VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AA%D8%AD%D9%81-%D8%A7%D9%84%D8%AF%D8%AD%D9%8A%D8%AD-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-816924',
         'info_dict': {
@@ -73,6 +74,9 @@ class ShahidIE(ShahidBaseIE):
         # shahid plus subscriber only
         'url': 'https://shahid.mbc.net/ar/series/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/episode-90511',
         'only_matching': True
+    }, {
+        'url': 'https://shahid.mbc.net/en/shows/Ramez-Fi-Al-Shallal-season-1-episode-1/episode-359319',
+        'only_matching': True
     }]
 
     def _real_initialize(self):
@@ -168,7 +172,7 @@ class ShahidIE(ShahidBaseIE):
 
 
 class ShahidShowIE(ShahidBaseIE):
-    _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)'
+    _VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://shahid.mbc.net/ar/shows/%D8%B1%D8%A7%D9%85%D8%B2-%D9%82%D8%B1%D8%B4-%D8%A7%D9%84%D8%A8%D8%AD%D8%B1/show-79187',
         'info_dict': {

yt_dlp/extractor/shared.py

@@ -86,10 +86,10 @@ class SharedIE(SharedBaseIE):
 
 class VivoIE(SharedBaseIE):
     IE_DESC = 'vivo.sx'
-    _VALID_URL = r'https?://vivo\.sx/(?P<id>[\da-z]{10})'
+    _VALID_URL = r'https?://vivo\.s[xt]/(?P<id>[\da-z]{10})'
     _FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://vivo.sx/d7ddda0e78',
         'md5': '15b3af41be0b4fe01f4df075c2678b2c',
         'info_dict': {
@@ -98,7 +98,10 @@ class VivoIE(SharedBaseIE):
             'title': 'Chicken',
             'filesize': 515659,
         },
-    }
+    }, {
+        'url': 'http://vivo.st/d7ddda0e78',
+        'only_matching': True,
+    }]
 
     def _extract_title(self, webpage):
         title = self._html_search_regex(

yt_dlp/extractor/vk.py

@@ -300,6 +300,13 @@ class VKIE(VKBaseIE):
             'only_matching': True,
         }]
 
+    @staticmethod
+    def _extract_sibnet_urls(webpage):
+        # https://help.sibnet.ru/?sibnet_video_embed
+        return [unescapeHTML(mobj.group('url')) for mobj in re.finditer(
+            r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//video\.sibnet\.ru/shell\.php\?.*?\bvideoid=\d+.*?)\1',
+            webpage)]
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
@@ -408,6 +415,10 @@ class VKIE(VKBaseIE):
         if odnoklassniki_url:
             return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
 
+        sibnet_urls = self._extract_sibnet_urls(info_page)
+        if sibnet_urls:
+            return self.url_result(sibnet_urls[0])
+
         m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
         if m_opts:
             m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))