youtube_dl/extractor/rts.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .srgssr import SRGSSRIE
   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(SRGSSRIE):
  21     IE_DESC = 'RTS.ch'
  22     _VALID_URL = r'rts:(?P<rts_id>\d+)|https?://(?:www\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html'
  23
  24     _TESTS = [
  25         {
  26             'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
  27             'md5': 'f254c4b26fb1d3c183793d52bc40d3e7',
  28             'info_dict': {
  29                 'id': '3449373',
  30                 'display_id': 'les-enfants-terribles',
  31                 'ext': 'flv',
  32                 'duration': 1488,
  33                 'title': 'Les Enfants Terribles',
  34                 'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.',
  35                 'uploader': 'Divers',
  36                 'upload_date': '19680921',
  37                 'timestamp': -40280400,
  38                 'thumbnail': 're:^https?://.*\.image',
  39                 'view_count': int,
  40             },
  41         },
  42         {
  43             'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
  44             'md5': 'f1077ac5af686c76528dc8d7c5df29ba',
  45             'info_dict': {
  46                 'id': '5742494',
  47                 'display_id': '5742494',
  48                 'ext': 'flv',
  49                 'duration': 3720,
  50                 'title': 'Les yeux dans les cieux - Mon homard au Canada',
  51                 'description': 'md5:d22ee46f5cc5bac0912e5a0c6d44a9f7',
  52                 'uploader': 'Passe-moi les jumelles',
  53                 'upload_date': '20140404',
  54                 'timestamp': 1396635300,
  55                 'thumbnail': 're:^https?://.*\.image',
  56                 'view_count': int,
  57             },
  58         },
  59         {
  60             'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
  61             'md5': 'b4326fecd3eb64a458ba73c73e91299d',
  62             'info_dict': {
  63                 'id': '5745975',
  64                 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
  65                 'ext': 'mp4',
  66                 'duration': 48,
  67                 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
  68                 'description': 'Hockey - Playoff',
  69                 'uploader': 'Hockey',
  70                 'upload_date': '20140403',
  71                 'timestamp': 1396556882,
  72                 'thumbnail': 're:^https?://.*\.image',
  73                 'view_count': int,
  74             },
  75             'skip': 'Blocked outside Switzerland',
  76         },
  77         {
  78             'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
  79             'md5': '9f713382f15322181bb366cc8c3a4ff0',
  80             'info_dict': {
  81                 'id': '5745356',
  82                 'display_id': 'londres-cachee-par-un-epais-smog',
  83                 'ext': 'flv',
  84                 'duration': 33,
  85                 'title': 'Londres cachée par un épais smog',
  86                 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
  87                 'uploader': 'Le Journal en continu',
  88                 'upload_date': '20140403',
  89                 'timestamp': 1396537322,
  90                 'thumbnail': 're:^https?://.*\.image',
  91                 'view_count': int,
  92             },
  93         },
  94         {
  95             'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
  96             'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
  97             'info_dict': {
  98                 'id': '5706148',
  99                 'display_id': 'urban-hippie-de-damien-krisl-03-04-2014',
 100                 'ext': 'mp3',
 101                 'duration': 123,
 102                 'title': '"Urban Hippie", de Damien Krisl',
 103                 'description': 'Des Hippies super glam.',
 104                 'upload_date': '20140403',
 105                 'timestamp': 1396551600,
 106             },
 107         },
 108         {
 109             # article with videos on rhs
 110             'url': 'http://www.rts.ch/sport/hockey/6693917-hockey-davos-decroche-son-31e-titre-de-champion-de-suisse.html',
 111             'info_dict': {
 112                 'id': '6693917',
 113                 'title': 'Hockey: Davos décroche son 31e titre de champion de Suisse',
 114             },
 115             'playlist_mincount': 5,
 116         }
 117     ]
 118
 119     def _real_extract(self, url):
 120         m = re.match(self._VALID_URL, url)
 121         media_id = m.group('rts_id') or m.group('id')
 122         display_id = m.group('display_id') or media_id
 123
 124         def download_json(internal_id):
 125             return self._download_json(
 126                 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id,
 127                 display_id)
 128
 129         all_info = download_json(media_id)
 130
 131         # media_id extracted out of URL is not always a real id
 132         if 'video' not in all_info and 'audio' not in all_info:
 133             page = self._download_webpage(url, display_id)
 134
 135             # article with videos on rhs
 136             videos = re.findall(
 137                 r'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+data-video-urn="urn:([^"]+)"',
 138                 page)
 139             if not videos:
 140                 videos = re.findall(
 141                     r'(?s)<iframe[^>]+class="srg-player"[^>]+src="[^"]+urn:([^"]+)"',
 142                     page)
 143             if videos:
 144                 entries = [self.url_result('srgssr:%s' % video_urn, 'SRGSSR') for video_urn in videos]
 145                 return self.playlist_result(entries, media_id, self._og_search_title(page))
 146
 147             internal_id = self._html_search_regex(
 148                 r'<(?:video|audio) data-id="([0-9]+)"', page,
 149                 'internal video id')
 150             all_info = download_json(internal_id)
 151
 152         media_type = 'video' if 'video' in all_info else 'audio'
 153
 154         # check for errors
 155         self.get_media_data('rts', media_type, media_id)
 156
 157         info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 158
 159         upload_timestamp = parse_iso8601(info.get('broadcast_date'))
 160         duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
 161         if isinstance(duration, compat_str):
 162             duration = parse_duration(duration)
 163         view_count = info.get('plays')
 164         thumbnail = unescapeHTML(info.get('preview_image_url'))
 165
 166         def extract_bitrate(url):
 167             return int_or_none(self._search_regex(
 168                 r'-([0-9]+)k\.', url, 'bitrate', default=None))
 169
 170         formats = []
 171         for format_id, format_url in info['streams'].items():
 172             if format_id == 'hds_sd' and 'hds' in info['streams']:
 173                 continue
 174             if format_id == 'hls_sd' and 'hls' in info['streams']:
 175                 continue
 176             if format_url.endswith('.f4m'):
 177                 token = self._download_xml(
 178                     'http://tp.srgssr.ch/token/akahd.xml?stream=%s/*' % compat_urllib_parse_urlparse(format_url).path,
 179                     media_id, 'Downloading %s token' % format_id)
 180                 auth_params = xpath_text(token, './/authparams', 'auth params')
 181                 if not auth_params:
 182                     continue
 183                 f4m_formats = self._extract_f4m_formats(
 184                     '%s?%s&hdcore=3.4.0&plugin=aasp-3.4.0.132.66' % (format_url, auth_params),
 185                     media_id, f4m_id=format_id, fatal=False)
 186                 if f4m_formats:
 187                     formats.extend(f4m_formats)
 188             elif format_url.endswith('.m3u8'):
 189                 m3u8_formats = self._extract_m3u8_formats(
 190                     format_url, media_id, 'mp4', m3u8_id=format_id, fatal=False)
 191                 if m3u8_formats:
 192                     formats.extend(m3u8_formats)
 193             else:
 194                 formats.append({
 195                     'format_id': format_id,
 196                     'url': format_url,
 197                     'tbr': extract_bitrate(format_url),
 198                 })
 199
 200         if 'media' in info:
 201             formats.extend([{
 202                 'format_id': '%s-%sk' % (media['ext'], media['rate']),
 203                 'url': 'http://download-video.rts.ch/%s' % media['url'],
 204                 'tbr': media['rate'] or extract_bitrate(media['url']),
 205             } for media in info['media'] if media.get('rate')])
 206
 207         self._check_formats(formats, media_id)
 208         self._sort_formats(formats)
 209
 210         return {
 211             'id': media_id,
 212             'display_id': display_id,
 213             'formats': formats,
 214             'title': info['title'],
 215             'description': info.get('intro'),
 216             'duration': duration,
 217             'view_count': view_count,
 218             'uploader': info.get('programName'),
 219             'timestamp': upload_timestamp,
 220             'thumbnail': thumbnail,
 221         }