3 from .common
import InfoExtractor
15 class MainStreamingIE(InfoExtractor
):
16 _VALID_URL
= r
'https?://(?:webtools-?)?(?P<host>[A-Za-z0-9-]*\.msvdn.net)/(?:embed|amp_embed|content)/(?P<id>\w+)'
17 IE_DESC
= 'MainStreaming Player'
21 # Live stream offline, has alternative content id
22 'url': 'https://webtools-e18da6642b684f8aa9ae449862783a56.msvdn.net/embed/53EN6GxbWaJC',
25 'title': 'Diretta homepage 2021-12-31 12:00',
27 'live_status': 'was_live',
29 'thumbnail': r
're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
31 'expected_warnings': [
32 'Ignoring alternative content ID: WDAF1KOWUpH3',
33 'MainStreaming said: Live event is OFFLINE'
35 'skip': 'live stream offline'
38 'url': 'https://webtools-e18da6642b684f8aa9ae449862783a56.msvdn.net/embed/WDAF1KOWUpH3',
41 'title': 'Playlist homepage',
43 'playlist_mincount': 2
46 'url': 'https://webtools-859c1818ed614cc5b0047439470927b0.msvdn.net/embed/tDoFkZD3T1Lw',
49 'title': r
're:Class CNBC Live \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
50 'live_status': 'is_live',
52 'thumbnail': r
're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
56 'url': 'https://webtools-f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/EUlZfGWkGpOd?autoPlay=false',
59 'title': 'La Settimana ',
60 'description': '03 Ottobre ore 02:00',
62 'live_status': 'not_live',
63 'thumbnail': r
're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
67 # video without webtools- prefix
68 'url': 'https://f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/MfuWmzL2lGkA?autoplay=false&T=1635860445',
71 'title': 'TG Mattina',
72 'description': '06 Ottobre ore 08:00',
74 'live_status': 'not_live',
75 'thumbnail': r
're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
79 # always-on livestream with DVR
80 'url': 'https://webtools-f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/HVvPMzy',
83 'title': r
're:^Diretta LaC News24 \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
84 'description': 'canale all news',
85 'live_status': 'is_live',
87 'thumbnail': r
're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
90 'skip_download': True,
94 'url': 'https://webtools.msvdn.net/embed/MfuWmzL2lGkA',
97 'url': 'https://859c1818ed614cc5b0047439470927b0.msvdn.net/amp_embed/tDoFkZD3T1Lw',
100 'url': 'https://859c1818ed614cc5b0047439470927b0.msvdn.net/content/tDoFkZD3T1Lw#',
101 'only_matching': True
106 def _extract_urls(webpage
):
108 r
'<iframe[^>]+?src=["\']?
(?P
<url
>%s)["\']?' % MainStreamingIE._VALID_URL, webpage)
110 return [group[0] for group in mobj]
112 def _playlist_entries(self, host, playlist_content):
113 for entry in playlist_content:
114 content_id = entry.get('contentID')
117 'ie_key': MainStreamingIE.ie_key(),
119 'duration': int_or_none(traverse_obj(entry, ('duration', 'totalSeconds'))),
120 'title': entry.get('title'),
121 'url': f'https://{host}/embed/{content_id}'
125 def _get_webtools_host(host):
126 if not host.startswith('webtools'):
127 host = 'webtools' + ('-' if not host.startswith('.') else '') + host
130 def _get_webtools_base_url(self, host):
131 return f'{self.http_scheme()}//{self._get_webtools_host(host)}'
133 def _call_api(self, host: str, path: str, item_id: str, query=None, note='Downloading API JSON', fatal=False):
134 # JSON API, does not appear to be documented
135 return self._call_webtools_api(host, '/api/v2/' + path, item_id, query, note, fatal)
137 def _call_webtools_api(self, host: str, path: str, item_id: str, query=None, note='Downloading webtools API JSON', fatal=False):
138 # webtools docs: https://webtools.msvdn.net/
139 return self._download_json(
140 urljoin(self._get_webtools_base_url(host), path), item_id, query=query, note=note, fatal=fatal)
142 def _real_extract(self, url):
143 host, video_id = self._match_valid_url(url).groups()
144 content_info = try_get(
146 host, f'content/{video_id}', video_id, note='Downloading content info API JSON'), lambda x: x['playerContentInfo'])
149 webpage = self._download_webpage(url, video_id)
150 player_config = self._parse_json(
152 r'config\s*=\s*({.+?})\s*;', webpage, 'mainstreaming player config',
153 default='{}', flags=re.DOTALL),
154 video_id, transform_source=js_to_json, fatal=False) or {}
155 content_info = player_config['contentInfo']
157 host = content_info.get('host') or host
158 video_id = content_info.get('contentID') or video_id
159 title = content_info.get('title')
160 description = traverse_obj(content_info, 'longDescription', 'shortDescription', expected_type=str)
161 live_status = 'not_live'
162 if content_info.get('drmEnabled'):
163 self.report_drm(video_id)
165 alternative_content_id = content_info.get('alternativeContentID')
166 if alternative_content_id:
167 self.report_warning(f'Ignoring alternative content ID: {alternative_content_id}')
169 content_type = int_or_none(content_info.get('contentType'))
170 format_base_url = None
174 if content_type == 20:
175 dvr_enabled = traverse_obj(content_info, ('playerSettings', 'dvrEnabled'), expected_type=bool)
176 format_base_url = f"https
://{host}
/live
/{content_info['liveSourceID']}
/{video_id}
/%s{'?DVR' if dvr_enabled else ''}
"
177 live_status = 'is_live'
178 heartbeat = self._call_api(host, f'heartbeat/{video_id}', video_id, note='Checking stream status') or {}
179 if heartbeat.get('heartBeatUp') is False:
180 self.raise_no_formats(f'MainStreaming said: {heartbeat.get("responseMessage")}', expected=True)
181 live_status = 'was_live'
184 elif content_type == 31:
185 return self.playlist_result(
186 self._playlist_entries(host, content_info.get('playlistContents')), video_id, title, description)
187 # Normal video content?
188 elif content_type == 10:
189 format_base_url = f'https://{host}/vod/{video_id}/%s'
191 # Note: in https://webtools.msvdn.net/loader/playerV2.js there is mention of original.mp3 format,
192 # however it seems to be the same as original.mp4?
193 formats.append({'url': format_base_url % 'original.mp4', 'format_note': 'original', 'quality': 1})
195 self.raise_no_formats(f'Unknown content type {content_type}')
198 m3u8_formats, m3u8_subs = self._extract_m3u8_formats_and_subtitles(
199 format_base_url % 'playlist.m3u8', video_id=video_id, fatal=False)
200 mpd_formats, mpd_subs = self._extract_mpd_formats_and_subtitles(
201 format_base_url % 'manifest.mpd', video_id=video_id, fatal=False)
203 subtitles = self._merge_subtitles(m3u8_subs, mpd_subs)
204 formats.extend(m3u8_formats + mpd_formats)
206 self._sort_formats(formats)
211 'description': description,
213 'live_status': live_status,
214 'duration': parse_duration(content_info.get('duration')),
215 'tags': content_info.get('tags'),
216 'subtitles': subtitles,
217 'thumbnail': urljoin(self._get_webtools_base_url(host), f'image/{video_id}/poster')