yt_dlp/extractor/rts.py

   1 import re
   2
   3 from .srgssr import SRGSSRIE
   4 from ..compat import compat_str
   5 from ..utils import (
   6     determine_ext,
   7     int_or_none,
   8     parse_duration,
   9     parse_iso8601,
  10     unescapeHTML,
  11     urljoin,
  12 )
  13
  14
  15 class RTSIE(SRGSSRIE):  # XXX: Do not subclass from concrete IE
  16     _WORKING = False
  17     IE_DESC = 'RTS.ch'
  18     _VALID_URL = r'rts:(?P<rts_id>\d+)|https?://(?:.+?\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html'
  19
  20     _TESTS = [
  21         {
  22             'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
  23             'md5': '753b877968ad8afaeddccc374d4256a5',
  24             'info_dict': {
  25                 'id': '3449373',
  26                 'display_id': 'les-enfants-terribles',
  27                 'ext': 'mp4',
  28                 'duration': 1488,
  29                 'title': 'Les Enfants Terribles',
  30                 'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.',
  31                 'uploader': 'Divers',
  32                 'upload_date': '19680921',
  33                 'timestamp': -40280400,
  34                 'thumbnail': r're:^https?://.*\.image',
  35                 'view_count': int,
  36             },
  37             'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
  38         },
  39         {
  40             'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
  41             'info_dict': {
  42                 'id': '5624065',
  43                 'title': 'Passe-moi les jumelles',
  44             },
  45             'playlist_mincount': 4,
  46         },
  47         {
  48             'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
  49             'info_dict': {
  50                 'id': '5745975',
  51                 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
  52                 'ext': 'mp4',
  53                 'duration': 48,
  54                 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
  55                 'description': 'Hockey - Playoff',
  56                 'uploader': 'Hockey',
  57                 'upload_date': '20140403',
  58                 'timestamp': 1396556882,
  59                 'thumbnail': r're:^https?://.*\.image',
  60                 'view_count': int,
  61             },
  62             'params': {
  63                 # m3u8 download
  64                 'skip_download': True,
  65             },
  66             'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
  67             'skip': 'Blocked outside Switzerland',
  68         },
  69         {
  70             'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
  71             'md5': '9bb06503773c07ce83d3cbd793cebb91',
  72             'info_dict': {
  73                 'id': '5745356',
  74                 'display_id': 'londres-cachee-par-un-epais-smog',
  75                 'ext': 'mp4',
  76                 'duration': 33,
  77                 'title': 'Londres cachée par un épais smog',
  78                 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
  79                 'uploader': 'L\'actu en vidéo',
  80                 'upload_date': '20140403',
  81                 'timestamp': 1396537322,
  82                 'thumbnail': r're:^https?://.*\.image',
  83                 'view_count': int,
  84             },
  85             'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
  86         },
  87         {
  88             'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
  89             'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
  90             'info_dict': {
  91                 'id': '5706148',
  92                 'display_id': 'urban-hippie-de-damien-krisl-03-04-2014',
  93                 'ext': 'mp3',
  94                 'duration': 123,
  95                 'title': '"Urban Hippie", de Damien Krisl',
  96                 'description': 'Des Hippies super glam.',
  97                 'upload_date': '20140403',
  98                 'timestamp': 1396551600,
  99             },
 100         },
 101         {
 102             # article with videos on rhs
 103             'url': 'http://www.rts.ch/sport/hockey/6693917-hockey-davos-decroche-son-31e-titre-de-champion-de-suisse.html',
 104             'info_dict': {
 105                 'id': '6693917',
 106                 'title': 'Hockey: Davos décroche son 31e titre de champion de Suisse',
 107             },
 108             'playlist_mincount': 5,
 109         },
 110         {
 111             'url': 'http://pages.rts.ch/emissions/passe-moi-les-jumelles/5624065-entre-ciel-et-mer.html',
 112             'only_matching': True,
 113         }
 114     ]
 115
 116     def _real_extract(self, url):
 117         m = self._match_valid_url(url)
 118         media_id = m.group('rts_id') or m.group('id')
 119         display_id = m.group('display_id') or media_id
 120
 121         def download_json(internal_id):
 122             return self._download_json(
 123                 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id,
 124                 display_id)
 125
 126         all_info = download_json(media_id)
 127
 128         # media_id extracted out of URL is not always a real id
 129         if 'video' not in all_info and 'audio' not in all_info:
 130             entries = []
 131
 132             for item in all_info.get('items', []):
 133                 item_url = item.get('url')
 134                 if not item_url:
 135                     continue
 136                 entries.append(self.url_result(item_url, 'RTS'))
 137
 138             if not entries:
 139                 page, urlh = self._download_webpage_handle(url, display_id)
 140                 if re.match(self._VALID_URL, urlh.url).group('id') != media_id:
 141                     return self.url_result(urlh.url, 'RTS')
 142
 143                 # article with videos on rhs
 144                 videos = re.findall(
 145                     r'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+data-video-urn="urn:([^"]+)"',
 146                     page)
 147                 if not videos:
 148                     videos = re.findall(
 149                         r'(?s)<iframe[^>]+class="srg-player"[^>]+src="[^"]+urn:([^"]+)"',
 150                         page)
 151                 if videos:
 152                     entries = [self.url_result('srgssr:%s' % video_urn, 'SRGSSR') for video_urn in videos]
 153
 154             if entries:
 155                 return self.playlist_result(entries, media_id, all_info.get('title'))
 156
 157             internal_id = self._html_search_regex(
 158                 r'<(?:video|audio) data-id="([0-9]+)"', page,
 159                 'internal video id')
 160             all_info = download_json(internal_id)
 161
 162         media_type = 'video' if 'video' in all_info else 'audio'
 163
 164         # check for errors
 165         self._get_media_data('rts', media_type, media_id)
 166
 167         info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 168
 169         title = info['title']
 170
 171         def extract_bitrate(url):
 172             return int_or_none(self._search_regex(
 173                 r'-([0-9]+)k\.', url, 'bitrate', default=None))
 174
 175         formats = []
 176         streams = info.get('streams', {})
 177         for format_id, format_url in streams.items():
 178             if format_id == 'hds_sd' and 'hds' in streams:
 179                 continue
 180             if format_id == 'hls_sd' and 'hls' in streams:
 181                 continue
 182             ext = determine_ext(format_url)
 183             if ext in ('m3u8', 'f4m'):
 184                 format_url = self._get_tokenized_src(format_url, media_id, format_id)
 185                 if ext == 'f4m':
 186                     formats.extend(self._extract_f4m_formats(
 187                         format_url + ('?' if '?' not in format_url else '&') + 'hdcore=3.4.0',
 188                         media_id, f4m_id=format_id, fatal=False))
 189                 else:
 190                     formats.extend(self._extract_m3u8_formats(
 191                         format_url, media_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
 192             else:
 193                 formats.append({
 194                     'format_id': format_id,
 195                     'url': format_url,
 196                     'tbr': extract_bitrate(format_url),
 197                 })
 198
 199         download_base = 'http://rtsww%s-d.rts.ch/' % ('-a' if media_type == 'audio' else '')
 200         for media in info.get('media', []):
 201             media_url = media.get('url')
 202             if not media_url or re.match(r'https?://', media_url):
 203                 continue
 204             rate = media.get('rate')
 205             ext = media.get('ext') or determine_ext(media_url, 'mp4')
 206             format_id = ext
 207             if rate:
 208                 format_id += '-%dk' % rate
 209             formats.append({
 210                 'format_id': format_id,
 211                 'url': urljoin(download_base, media_url),
 212                 'tbr': rate or extract_bitrate(media_url),
 213             })
 214
 215         self._check_formats(formats, media_id)
 216
 217         duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
 218         if isinstance(duration, compat_str):
 219             duration = parse_duration(duration)
 220
 221         return {
 222             'id': media_id,
 223             'display_id': display_id,
 224             'formats': formats,
 225             'title': title,
 226             'description': info.get('intro'),
 227             'duration': duration,
 228             'view_count': int_or_none(info.get('plays')),
 229             'uploader': info.get('programName'),
 230             'timestamp': parse_iso8601(info.get('broadcast_date')),
 231             'thumbnail': unescapeHTML(info.get('preview_image_url')),
 232         }