Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rts.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_str,
   9     compat_urllib_parse_urlparse,
  10 )
  11 from ..utils import (
  12     int_or_none,
  13     parse_duration,
  14     parse_iso8601,
  15     unescapeHTML,
  16     xpath_text,
  17 )
  18
  19
  20 class RTSIE(InfoExtractor):
  21     IE_DESC = 'RTS.ch'
  22     _VALID_URL = r'''(?x)
  23                     (?:
  24                         rts:(?P<rts_id>\d+)|
  25                         https?://
  26                             (?:www\.)?rts\.ch/
  27                             (?:
  28                                 (?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html|
  29                                 play/tv/[^/]+/video/(?P<display_id_new>.+?)\?id=(?P<id_new>[0-9]+)
  30                             )
  31                     )'''
  32
  33     _TESTS = [
  34         {
  35             'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
  36             'md5': '753b877968ad8afaeddccc374d4256a5',
  37             'info_dict': {
  38                 'id': '3449373',
  39                 'display_id': 'les-enfants-terribles',
  40                 'ext': 'mp4',
  41                 'duration': 1488,
  42                 'title': 'Les Enfants Terribles',
  43                 'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.',
  44                 'uploader': 'Divers',
  45                 'upload_date': '19680921',
  46                 'timestamp': -40280400,
  47                 'thumbnail': 're:^https?://.*\.image',
  48                 'view_count': int,
  49             },
  50         },
  51         {
  52             'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
  53             'md5': 'c148457a27bdc9e5b1ffe081a7a8337b',
  54             'info_dict': {
  55                 'id': '5624067',
  56                 'display_id': 'entre-ciel-et-mer',
  57                 'ext': 'mp4',
  58                 'duration': 3720,
  59                 'title': 'Les yeux dans les cieux - Mon homard au Canada',
  60                 'description': 'md5:d22ee46f5cc5bac0912e5a0c6d44a9f7',
  61                 'uploader': 'Passe-moi les jumelles',
  62                 'upload_date': '20140404',
  63                 'timestamp': 1396635300,
  64                 'thumbnail': 're:^https?://.*\.image',
  65                 'view_count': int,
  66             },
  67         },
  68         {
  69             'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
  70             'md5': 'b4326fecd3eb64a458ba73c73e91299d',
  71             'info_dict': {
  72                 'id': '5745975',
  73                 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
  74                 'ext': 'mp4',
  75                 'duration': 48,
  76                 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
  77                 'description': 'Hockey - Playoff',
  78                 'uploader': 'Hockey',
  79                 'upload_date': '20140403',
  80                 'timestamp': 1396556882,
  81                 'thumbnail': 're:^https?://.*\.image',
  82                 'view_count': int,
  83             },
  84             'skip': 'Blocked outside Switzerland',
  85         },
  86         {
  87             'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
  88             'md5': '9bb06503773c07ce83d3cbd793cebb91',
  89             'info_dict': {
  90                 'id': '5745356',
  91                 'display_id': 'londres-cachee-par-un-epais-smog',
  92                 'ext': 'mp4',
  93                 'duration': 33,
  94                 'title': 'Londres cachée par un épais smog',
  95                 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
  96                 'uploader': 'Le Journal en continu',
  97                 'upload_date': '20140403',
  98                 'timestamp': 1396537322,
  99                 'thumbnail': 're:^https?://.*\.image',
 100                 'view_count': int,
 101             },
 102         },
 103         {
 104             'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
 105             'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
 106             'info_dict': {
 107                 'id': '5706148',
 108                 'display_id': 'urban-hippie-de-damien-krisl-03-04-2014',
 109                 'ext': 'mp3',
 110                 'duration': 123,
 111                 'title': '"Urban Hippie", de Damien Krisl',
 112                 'description': 'Des Hippies super glam.',
 113                 'upload_date': '20140403',
 114                 'timestamp': 1396551600,
 115             },
 116         },
 117         {
 118             'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260',
 119             'md5': '968777c8779e5aa2434be96c54e19743',
 120             'info_dict': {
 121                 'id': '6348260',
 122                 'display_id': 'le-19h30',
 123                 'ext': 'mp4',
 124                 'duration': 1796,
 125                 'title': 'Le 19h30',
 126                 'description': '',
 127                 'uploader': 'Le 19h30',
 128                 'upload_date': '20141201',
 129                 'timestamp': 1417458600,
 130                 'thumbnail': 're:^https?://.*\.image',
 131                 'view_count': int,
 132             },
 133         },
 134         {
 135             # article with videos on rhs
 136             'url': 'http://www.rts.ch/sport/hockey/6693917-hockey-davos-decroche-son-31e-titre-de-champion-de-suisse.html',
 137             'info_dict': {
 138                 'id': '6693917',
 139                 'title': 'Hockey: Davos décroche son 31e titre de champion de Suisse',
 140             },
 141             'playlist_mincount': 5,
 142         },
 143         {
 144             'url': 'http://www.rts.ch/play/tv/le-19h30/video/le-chantier-du-nouveau-parlement-vaudois-a-permis-une-trouvaille-historique?id=6348280',
 145             'only_matching': True,
 146         }
 147     ]
 148
 149     def _real_extract(self, url):
 150         m = re.match(self._VALID_URL, url)
 151         video_id = m.group('rts_id') or m.group('id') or m.group('id_new')
 152         display_id = m.group('display_id') or m.group('display_id_new')
 153
 154         def download_json(internal_id):
 155             return self._download_json(
 156                 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id,
 157                 display_id)
 158
 159         all_info = download_json(video_id)
 160
 161         # video_id extracted out of URL is not always a real id
 162         if 'video' not in all_info and 'audio' not in all_info:
 163             page = self._download_webpage(url, display_id)
 164
 165             # article with videos on rhs
 166             videos = re.findall(
 167                 r'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+data-video-urn="urn:rts:video:(\d+)"',
 168                 page)
 169             if videos:
 170                 entries = [self.url_result('rts:%s' % video_urn, 'RTS') for video_urn in videos]
 171                 return self.playlist_result(entries, video_id, self._og_search_title(page))
 172
 173             internal_id = self._html_search_regex(
 174                 r'<(?:video|audio) data-id="([0-9]+)"', page,
 175                 'internal video id')
 176             all_info = download_json(internal_id)
 177
 178         info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 179
 180         upload_timestamp = parse_iso8601(info.get('broadcast_date'))
 181         duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
 182         if isinstance(duration, compat_str):
 183             duration = parse_duration(duration)
 184         view_count = info.get('plays')
 185         thumbnail = unescapeHTML(info.get('preview_image_url'))
 186
 187         def extract_bitrate(url):
 188             return int_or_none(self._search_regex(
 189                 r'-([0-9]+)k\.', url, 'bitrate', default=None))
 190
 191         formats = []
 192         for format_id, format_url in info['streams'].items():
 193             if format_url.endswith('.f4m'):
 194                 token = self._download_xml(
 195                     'http://tp.srgssr.ch/token/akahd.xml?stream=%s/*' % compat_urllib_parse_urlparse(format_url).path,
 196                     video_id, 'Downloading %s token' % format_id)
 197                 auth_params = xpath_text(token, './/authparams', 'auth params')
 198                 if not auth_params:
 199                     continue
 200                 formats.extend(self._extract_f4m_formats(
 201                     '%s?%s&hdcore=3.4.0&plugin=aasp-3.4.0.132.66' % (format_url, auth_params),
 202                     video_id, f4m_id=format_id))
 203             elif format_url.endswith('.m3u8'):
 204                 formats.extend(self._extract_m3u8_formats(
 205                     format_url, video_id, 'mp4', m3u8_id=format_id))
 206             else:
 207                 formats.append({
 208                     'format_id': format_id,
 209                     'url': format_url,
 210                     'tbr': extract_bitrate(format_url),
 211                 })
 212
 213         if 'media' in info:
 214             formats.extend([{
 215                 'format_id': '%s-%sk' % (media['ext'], media['rate']),
 216                 'url': 'http://download-video.rts.ch/%s' % media['url'],
 217                 'tbr': media['rate'] or extract_bitrate(media['url']),
 218             } for media in info['media'] if media.get('rate')])
 219
 220         self._check_formats(formats, video_id)
 221         self._sort_formats(formats)
 222
 223         return {
 224             'id': video_id,
 225             'display_id': display_id,
 226             'formats': formats,
 227             'title': info['title'],
 228             'description': info.get('intro'),
 229             'duration': duration,
 230             'view_count': view_count,
 231             'uploader': info.get('programName'),
 232             'timestamp': upload_timestamp,
 233             'thumbnail': thumbnail,
 234         }