yt_dlp/extractor/rts.py

   1 import re
   2
   3 from .srgssr import SRGSSRIE
   4 from ..utils import (
   5     determine_ext,
   6     int_or_none,
   7     parse_duration,
   8     parse_iso8601,
   9     unescapeHTML,
  10     urljoin,
  11 )
  12
  13
  14 class RTSIE(SRGSSRIE):  # XXX: Do not subclass from concrete IE
  15     _WORKING = False
  16     IE_DESC = 'RTS.ch'
  17     _VALID_URL = r'rts:(?P<rts_id>\d+)|https?://(?:.+?\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html'
  18
  19     _TESTS = [
  20         {
  21             'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
  22             'md5': '753b877968ad8afaeddccc374d4256a5',
  23             'info_dict': {
  24                 'id': '3449373',
  25                 'display_id': 'les-enfants-terribles',
  26                 'ext': 'mp4',
  27                 'duration': 1488,
  28                 'title': 'Les Enfants Terribles',
  29                 'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.',
  30                 'uploader': 'Divers',
  31                 'upload_date': '19680921',
  32                 'timestamp': -40280400,
  33                 'thumbnail': r're:^https?://.*\.image',
  34                 'view_count': int,
  35             },
  36             'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
  37         },
  38         {
  39             'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
  40             'info_dict': {
  41                 'id': '5624065',
  42                 'title': 'Passe-moi les jumelles',
  43             },
  44             'playlist_mincount': 4,
  45         },
  46         {
  47             'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
  48             'info_dict': {
  49                 'id': '5745975',
  50                 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
  51                 'ext': 'mp4',
  52                 'duration': 48,
  53                 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
  54                 'description': 'Hockey - Playoff',
  55                 'uploader': 'Hockey',
  56                 'upload_date': '20140403',
  57                 'timestamp': 1396556882,
  58                 'thumbnail': r're:^https?://.*\.image',
  59                 'view_count': int,
  60             },
  61             'params': {
  62                 # m3u8 download
  63                 'skip_download': True,
  64             },
  65             'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
  66             'skip': 'Blocked outside Switzerland',
  67         },
  68         {
  69             'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
  70             'md5': '9bb06503773c07ce83d3cbd793cebb91',
  71             'info_dict': {
  72                 'id': '5745356',
  73                 'display_id': 'londres-cachee-par-un-epais-smog',
  74                 'ext': 'mp4',
  75                 'duration': 33,
  76                 'title': 'Londres cachée par un épais smog',
  77                 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
  78                 'uploader': 'L\'actu en vidéo',
  79                 'upload_date': '20140403',
  80                 'timestamp': 1396537322,
  81                 'thumbnail': r're:^https?://.*\.image',
  82                 'view_count': int,
  83             },
  84             'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
  85         },
  86         {
  87             'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
  88             'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
  89             'info_dict': {
  90                 'id': '5706148',
  91                 'display_id': 'urban-hippie-de-damien-krisl-03-04-2014',
  92                 'ext': 'mp3',
  93                 'duration': 123,
  94                 'title': '"Urban Hippie", de Damien Krisl',
  95                 'description': 'Des Hippies super glam.',
  96                 'upload_date': '20140403',
  97                 'timestamp': 1396551600,
  98             },
  99         },
 100         {
 101             # article with videos on rhs
 102             'url': 'http://www.rts.ch/sport/hockey/6693917-hockey-davos-decroche-son-31e-titre-de-champion-de-suisse.html',
 103             'info_dict': {
 104                 'id': '6693917',
 105                 'title': 'Hockey: Davos décroche son 31e titre de champion de Suisse',
 106             },
 107             'playlist_mincount': 5,
 108         },
 109         {
 110             'url': 'http://pages.rts.ch/emissions/passe-moi-les-jumelles/5624065-entre-ciel-et-mer.html',
 111             'only_matching': True,
 112         },
 113     ]
 114
 115     def _real_extract(self, url):
 116         m = self._match_valid_url(url)
 117         media_id = m.group('rts_id') or m.group('id')
 118         display_id = m.group('display_id') or media_id
 119
 120         def download_json(internal_id):
 121             return self._download_json(
 122                 f'http://www.rts.ch/a/{internal_id}.html?f=json/article',
 123                 display_id)
 124
 125         all_info = download_json(media_id)
 126
 127         # media_id extracted out of URL is not always a real id
 128         if 'video' not in all_info and 'audio' not in all_info:
 129             entries = []
 130
 131             for item in all_info.get('items', []):
 132                 item_url = item.get('url')
 133                 if not item_url:
 134                     continue
 135                 entries.append(self.url_result(item_url, 'RTS'))
 136
 137             if not entries:
 138                 page, urlh = self._download_webpage_handle(url, display_id)
 139                 if re.match(self._VALID_URL, urlh.url).group('id') != media_id:
 140                     return self.url_result(urlh.url, 'RTS')
 141
 142                 # article with videos on rhs
 143                 videos = re.findall(
 144                     r'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+data-video-urn="urn:([^"]+)"',
 145                     page)
 146                 if not videos:
 147                     videos = re.findall(
 148                         r'(?s)<iframe[^>]+class="srg-player"[^>]+src="[^"]+urn:([^"]+)"',
 149                         page)
 150                 if videos:
 151                     entries = [self.url_result(f'srgssr:{video_urn}', 'SRGSSR') for video_urn in videos]
 152
 153             if entries:
 154                 return self.playlist_result(entries, media_id, all_info.get('title'))
 155
 156             internal_id = self._html_search_regex(
 157                 r'<(?:video|audio) data-id="([0-9]+)"', page,
 158                 'internal video id')
 159             all_info = download_json(internal_id)
 160
 161         media_type = 'video' if 'video' in all_info else 'audio'
 162
 163         # check for errors
 164         self._get_media_data('rts', media_type, media_id)
 165
 166         info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 167
 168         title = info['title']
 169
 170         def extract_bitrate(url):
 171             return int_or_none(self._search_regex(
 172                 r'-([0-9]+)k\.', url, 'bitrate', default=None))
 173
 174         formats = []
 175         streams = info.get('streams', {})
 176         for format_id, format_url in streams.items():
 177             if format_id == 'hds_sd' and 'hds' in streams:
 178                 continue
 179             if format_id == 'hls_sd' and 'hls' in streams:
 180                 continue
 181             ext = determine_ext(format_url)
 182             if ext in ('m3u8', 'f4m'):
 183                 format_url = self._get_tokenized_src(format_url, media_id, format_id)
 184                 if ext == 'f4m':
 185                     formats.extend(self._extract_f4m_formats(
 186                         format_url + ('?' if '?' not in format_url else '&') + 'hdcore=3.4.0',
 187                         media_id, f4m_id=format_id, fatal=False))
 188                 else:
 189                     formats.extend(self._extract_m3u8_formats(
 190                         format_url, media_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
 191             else:
 192                 formats.append({
 193                     'format_id': format_id,
 194                     'url': format_url,
 195                     'tbr': extract_bitrate(format_url),
 196                 })
 197
 198         download_base = 'http://rtsww{}-d.rts.ch/'.format('-a' if media_type == 'audio' else '')
 199         for media in info.get('media', []):
 200             media_url = media.get('url')
 201             if not media_url or re.match(r'https?://', media_url):
 202                 continue
 203             rate = media.get('rate')
 204             ext = media.get('ext') or determine_ext(media_url, 'mp4')
 205             format_id = ext
 206             if rate:
 207                 format_id += '-%dk' % rate
 208             formats.append({
 209                 'format_id': format_id,
 210                 'url': urljoin(download_base, media_url),
 211                 'tbr': rate or extract_bitrate(media_url),
 212             })
 213
 214         self._check_formats(formats, media_id)
 215
 216         duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
 217         if isinstance(duration, str):
 218             duration = parse_duration(duration)
 219
 220         return {
 221             'id': media_id,
 222             'display_id': display_id,
 223             'formats': formats,
 224             'title': title,
 225             'description': info.get('intro'),
 226             'duration': duration,
 227             'view_count': int_or_none(info.get('plays')),
 228             'uploader': info.get('programName'),
 229             'timestamp': parse_iso8601(info.get('broadcast_date')),
 230             'thumbnail': unescapeHTML(info.get('preview_image_url')),
 231         }