_ Git - youtube-dl/blob - youtube_dl/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     get_element_by_class,
   9     int_or_none,
  10     parse_duration,
  11     parse_iso8601,
  12 )
  13
  14
  15 class TV5MondePlusIE(InfoExtractor):
  16     IE_DESC = 'TV5MONDE+'
  17     _VALID_URL = r'https?://(?:www\.)?tv5mondeplus\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)'
  18     _TEST = {
  19         'url': 'http://www.tv5mondeplus.com/toutes-les-videos/documentaire/tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants',
  20         'md5': '12130fc199f020673138a83466542ec6',
  21         'info_dict': {
  22             'id': '0a774110-dc60-4037-f769-996439514f1f',
  23             'ext': 'mp4',
  24             'title': 'Tdah, mon amour - Enfants',
  25             'description': 'md5:b65f0cc50e46947e62e5d352e9916cc4',
  26             'upload_date': '20170401',
  27             'timestamp': 1491022860,
  28         }
  29     }
  30     _GEO_BYPASS = False
  31
  32     def _real_extract(self, url):
  33         display_id = self._match_id(url)
  34         webpage = self._download_webpage(url, display_id)
  35
  36         if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage:
  37             self.raise_geo_restricted(countries=['FR'])
  38
  39         series = get_element_by_class('video-detail__title', webpage)
  40         title = episode = get_element_by_class(
  41             'video-detail__subtitle', webpage) or series
  42         if series and series != title:
  43             title = '%s - %s' % (series, title)
  44         vpl_data = extract_attributes(self._search_regex(
  45             r'(<[^>]+class="video_player_loader"[^>]+>)',
  46             webpage, 'video player loader'))
  47
  48         video_files = self._parse_json(
  49             vpl_data['data-broadcast'], display_id).get('files', [])
  50         formats = []
  51         for video_file in video_files:
  52             v_url = video_file.get('url')
  53             if not v_url:
  54                 continue
  55             video_format = video_file.get('format') or determine_ext(v_url)
  56             if video_format == 'm3u8':
  57                 formats.extend(self._extract_m3u8_formats(
  58                     v_url, display_id, 'mp4', 'm3u8_native',
  59                     m3u8_id='hls', fatal=False))
  60             else:
  61                 formats.append({
  62                     'url': v_url,
  63                     'format_id': video_format,
  64                 })
  65         self._sort_formats(formats)
  66
  67         return {
  68             'id': vpl_data.get('data-guid') or display_id,
  69             'display_id': display_id,
  70             'title': title,
  71             'description': get_element_by_class('video-detail__description', webpage),
  72             'thumbnail': vpl_data.get('data-image'),
  73             'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)),
  74             'timestamp': parse_iso8601(self._html_search_meta('uploadDate', webpage)),
  75             'formats': formats,
  76             'episode': episode,
  77             'series': series,
  78         }