yt_dlp/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 compat_str
   8 from ..utils import (
   9     determine_ext,
  10     int_or_none,
  11     parse_duration,
  12     parse_iso8601,
  13     unescapeHTML,
  14     urljoin,
  15 )
  16
  17
  18 class RTSIE(SRGSSRIE):
  19     IE_DESC = 'RTS.ch'
  20     _VALID_URL = r'rts:(?P<rts_id>\d+)|https?://(?:.+?\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html'
  21
  22     _TESTS = [
  23         {
  24             'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
  25             'md5': '753b877968ad8afaeddccc374d4256a5',
  26             'info_dict': {
  27                 'id': '3449373',
  28                 'display_id': 'les-enfants-terribles',
  29                 'ext': 'mp4',
  30                 'duration': 1488,
  31                 'title': 'Les Enfants Terribles',
  32                 'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.',
  33                 'uploader': 'Divers',
  34                 'upload_date': '19680921',
  35                 'timestamp': -40280400,
  36                 'thumbnail': r're:^https?://.*\.image',
  37                 'view_count': int,
  38             },
  39             'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
  40         },
  41         {
  42             'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
  43             'info_dict': {
  44                 'id': '5624065',
  45                 'title': 'Passe-moi les jumelles',
  46             },
  47             'playlist_mincount': 4,
  48         },
  49         {
  50             'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
  51             'info_dict': {
  52                 'id': '5745975',
  53                 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
  54                 'ext': 'mp4',
  55                 'duration': 48,
  56                 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
  57                 'description': 'Hockey - Playoff',
  58                 'uploader': 'Hockey',
  59                 'upload_date': '20140403',
  60                 'timestamp': 1396556882,
  61                 'thumbnail': r're:^https?://.*\.image',
  62                 'view_count': int,
  63             },
  64             'params': {
  65                 # m3u8 download
  66                 'skip_download': True,
  67             },
  68             'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
  69             'skip': 'Blocked outside Switzerland',
  70         },
  71         {
  72             'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
  73             'md5': '9bb06503773c07ce83d3cbd793cebb91',
  74             'info_dict': {
  75                 'id': '5745356',
  76                 'display_id': 'londres-cachee-par-un-epais-smog',
  77                 'ext': 'mp4',
  78                 'duration': 33,
  79                 'title': 'Londres cachée par un épais smog',
  80                 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
  81                 'uploader': 'L\'actu en vidéo',
  82                 'upload_date': '20140403',
  83                 'timestamp': 1396537322,
  84                 'thumbnail': r're:^https?://.*\.image',
  85                 'view_count': int,
  86             },
  87             'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
  88         },
  89         {
  90             'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
  91             'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
  92             'info_dict': {
  93                 'id': '5706148',
  94                 'display_id': 'urban-hippie-de-damien-krisl-03-04-2014',
  95                 'ext': 'mp3',
  96                 'duration': 123,
  97                 'title': '"Urban Hippie", de Damien Krisl',
  98                 'description': 'Des Hippies super glam.',
  99                 'upload_date': '20140403',
 100                 'timestamp': 1396551600,
 101             },
 102         },
 103         {
 104             # article with videos on rhs
 105             'url': 'http://www.rts.ch/sport/hockey/6693917-hockey-davos-decroche-son-31e-titre-de-champion-de-suisse.html',
 106             'info_dict': {
 107                 'id': '6693917',
 108                 'title': 'Hockey: Davos décroche son 31e titre de champion de Suisse',
 109             },
 110             'playlist_mincount': 5,
 111         },
 112         {
 113             'url': 'http://pages.rts.ch/emissions/passe-moi-les-jumelles/5624065-entre-ciel-et-mer.html',
 114             'only_matching': True,
 115         }
 116     ]
 117
 118     def _real_extract(self, url):
 119         m = self._match_valid_url(url)
 120         media_id = m.group('rts_id') or m.group('id')
 121         display_id = m.group('display_id') or media_id
 122
 123         def download_json(internal_id):
 124             return self._download_json(
 125                 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id,
 126                 display_id)
 127
 128         all_info = download_json(media_id)
 129
 130         # media_id extracted out of URL is not always a real id
 131         if 'video' not in all_info and 'audio' not in all_info:
 132             entries = []
 133
 134             for item in all_info.get('items', []):
 135                 item_url = item.get('url')
 136                 if not item_url:
 137                     continue
 138                 entries.append(self.url_result(item_url, 'RTS'))
 139
 140             if not entries:
 141                 page, urlh = self._download_webpage_handle(url, display_id)
 142                 if re.match(self._VALID_URL, urlh.geturl()).group('id') != media_id:
 143                     return self.url_result(urlh.geturl(), 'RTS')
 144
 145                 # article with videos on rhs
 146                 videos = re.findall(
 147                     r'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+data-video-urn="urn:([^"]+)"',
 148                     page)
 149                 if not videos:
 150                     videos = re.findall(
 151                         r'(?s)<iframe[^>]+class="srg-player"[^>]+src="[^"]+urn:([^"]+)"',
 152                         page)
 153                 if videos:
 154                     entries = [self.url_result('srgssr:%s' % video_urn, 'SRGSSR') for video_urn in videos]
 155
 156             if entries:
 157                 return self.playlist_result(entries, media_id, all_info.get('title'))
 158
 159             internal_id = self._html_search_regex(
 160                 r'<(?:video|audio) data-id="([0-9]+)"', page,
 161                 'internal video id')
 162             all_info = download_json(internal_id)
 163
 164         media_type = 'video' if 'video' in all_info else 'audio'
 165
 166         # check for errors
 167         self._get_media_data('rts', media_type, media_id)
 168
 169         info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 170
 171         title = info['title']
 172
 173         def extract_bitrate(url):
 174             return int_or_none(self._search_regex(
 175                 r'-([0-9]+)k\.', url, 'bitrate', default=None))
 176
 177         formats = []
 178         streams = info.get('streams', {})
 179         for format_id, format_url in streams.items():
 180             if format_id == 'hds_sd' and 'hds' in streams:
 181                 continue
 182             if format_id == 'hls_sd' and 'hls' in streams:
 183                 continue
 184             ext = determine_ext(format_url)
 185             if ext in ('m3u8', 'f4m'):
 186                 format_url = self._get_tokenized_src(format_url, media_id, format_id)
 187                 if ext == 'f4m':
 188                     formats.extend(self._extract_f4m_formats(
 189                         format_url + ('?' if '?' not in format_url else '&') + 'hdcore=3.4.0',
 190                         media_id, f4m_id=format_id, fatal=False))
 191                 else:
 192                     formats.extend(self._extract_m3u8_formats(
 193                         format_url, media_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
 194             else:
 195                 formats.append({
 196                     'format_id': format_id,
 197                     'url': format_url,
 198                     'tbr': extract_bitrate(format_url),
 199                 })
 200
 201         download_base = 'http://rtsww%s-d.rts.ch/' % ('-a' if media_type == 'audio' else '')
 202         for media in info.get('media', []):
 203             media_url = media.get('url')
 204             if not media_url or re.match(r'https?://', media_url):
 205                 continue
 206             rate = media.get('rate')
 207             ext = media.get('ext') or determine_ext(media_url, 'mp4')
 208             format_id = ext
 209             if rate:
 210                 format_id += '-%dk' % rate
 211             formats.append({
 212                 'format_id': format_id,
 213                 'url': urljoin(download_base, media_url),
 214                 'tbr': rate or extract_bitrate(media_url),
 215             })
 216
 217         self._check_formats(formats, media_id)
 218         self._sort_formats(formats)
 219
 220         duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
 221         if isinstance(duration, compat_str):
 222             duration = parse_duration(duration)
 223
 224         return {
 225             'id': media_id,
 226             'display_id': display_id,
 227             'formats': formats,
 228             'title': title,
 229             'description': info.get('intro'),
 230             'duration': duration,
 231             'view_count': int_or_none(info.get('plays')),
 232             'uploader': info.get('programName'),
 233             'timestamp': parse_iso8601(info.get('broadcast_date')),
 234             'thumbnail': unescapeHTML(info.get('preview_image_url')),
 235         }