yt_dlp/extractor/tv5mondeplus.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     determine_ext,
   7     extract_attributes,
   8     int_or_none,
   9     parse_duration,
  10     try_get,
  11 )
  12
  13
  14 class TV5MondePlusIE(InfoExtractor):
  15     IE_DESC = 'TV5MONDE+'
  16     _VALID_URL = r'https?://(?:www\.)?(?:tv5mondeplus|revoir\.tv5monde)\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)'
  17     _TESTS = [{
  18         # movie
  19         'url': 'https://revoir.tv5monde.com/toutes-les-videos/cinema/ceux-qui-travaillent',
  20         'md5': '32fa0cde16a4480d1251502a66856d5f',
  21         'info_dict': {
  22             'id': 'dc57a011-ec4b-4648-2a9a-4f03f8352ed3',
  23             'display_id': 'ceux-qui-travaillent',
  24             'ext': 'mp4',
  25             'title': 'Ceux qui travaillent',
  26             'description': 'md5:570e8bb688036ace873b2d50d24c026d',
  27             'upload_date': '20210819',
  28         },
  29     }, {
  30         # series episode
  31         'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/vestiaires-caro-actrice',
  32         'info_dict': {
  33             'id': '9e9d599e-23af-6915-843e-ecbf62e97925',
  34             'display_id': 'vestiaires-caro-actrice',
  35             'ext': 'mp4',
  36             'title': "Vestiaires - Caro actrice",
  37             'description': 'md5:db15d2e1976641e08377f942778058ea',
  38             'upload_date': '20210819',
  39             'series': "Vestiaires",
  40             'episode': 'Caro actrice',
  41         },
  42         'params': {
  43             'skip_download': True,
  44         },
  45     }, {
  46         'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/neuf-jours-en-hiver-neuf-jours-en-hiver',
  47         'only_matching': True,
  48     }, {
  49         'url': 'https://revoir.tv5monde.com/toutes-les-videos/info-societe/le-journal-de-la-rts-edition-du-30-01-20-19h30',
  50         'only_matching': True,
  51     }]
  52     _GEO_BYPASS = False
  53
  54     def _real_extract(self, url):
  55         display_id = self._match_id(url)
  56         webpage = self._download_webpage(url, display_id)
  57
  58         if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage:
  59             self.raise_geo_restricted(countries=['FR'])
  60
  61         title = episode = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
  62         vpl_data = extract_attributes(self._search_regex(
  63             r'(<[^>]+class="video_player_loader"[^>]+>)',
  64             webpage, 'video player loader'))
  65
  66         video_files = self._parse_json(
  67             vpl_data['data-broadcast'], display_id)
  68         formats = []
  69         for video_file in video_files:
  70             v_url = video_file.get('url')
  71             if not v_url:
  72                 continue
  73             video_format = video_file.get('format') or determine_ext(v_url)
  74             if video_format == 'm3u8':
  75                 formats.extend(self._extract_m3u8_formats(
  76                     v_url, display_id, 'mp4', 'm3u8_native',
  77                     m3u8_id='hls', fatal=False))
  78             else:
  79                 formats.append({
  80                     'url': v_url,
  81                     'format_id': video_format,
  82                 })
  83         self._sort_formats(formats)
  84
  85         metadata = self._parse_json(
  86             vpl_data['data-metadata'], display_id)
  87         duration = (int_or_none(try_get(metadata, lambda x: x['content']['duration']))
  88                     or parse_duration(self._html_search_meta('duration', webpage)))
  89
  90         description = self._html_search_regex(
  91             r'(?s)<div[^>]+class=["\']episode-texte[^>]+>(.+?)</div>', webpage,
  92             'description', fatal=False)
  93
  94         series = self._html_search_regex(
  95             r'<p[^>]+class=["\']episode-emission[^>]+>([^<]+)', webpage,
  96             'series', default=None)
  97
  98         if series and series != title:
  99             title = '%s - %s' % (series, title)
 100
 101         upload_date = self._search_regex(
 102             r'(?:date_publication|publish_date)["\']\s*:\s*["\'](\d{4}_\d{2}_\d{2})',
 103             webpage, 'upload date', default=None)
 104         if upload_date:
 105             upload_date = upload_date.replace('_', '')
 106
 107         video_id = self._search_regex(
 108             (r'data-guid=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
 109              r'id_contenu["\']\s:\s*(\d+)'), webpage, 'video id',
 110             default=display_id)
 111
 112         return {
 113             'id': video_id,
 114             'display_id': display_id,
 115             'title': title,
 116             'description': description,
 117             'thumbnail': vpl_data.get('data-image'),
 118             'duration': duration,
 119             'upload_date': upload_date,
 120             'formats': formats,
 121             'series': series,
 122             'episode': episode,
 123         }