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     clean_html,
   7     determine_ext,
   8     extract_attributes,
   9     get_element_by_class,
  10     int_or_none,
  11     parse_duration,
  12     parse_iso8601,
  13 )
  14
  15
  16 class TV5MondePlusIE(InfoExtractor):
  17     IE_DESC = 'TV5MONDE+'
  18     _VALID_URL = r'https?://(?:www\.)?tv5mondeplus\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)'
  19     _TEST = {
  20         'url': 'http://www.tv5mondeplus.com/toutes-les-videos/documentaire/tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants',
  21         'md5': '12130fc199f020673138a83466542ec6',
  22         'info_dict': {
  23             'id': 'tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants',
  24             'ext': 'mp4',
  25             'title': 'Tdah, mon amour - Enfants',
  26             'description': 'md5:230e3aca23115afcf8006d1bece6df74',
  27             'upload_date': '20170401',
  28             'timestamp': 1491022860,
  29         }
  30     }
  31     _GEO_BYPASS = False
  32
  33     def _real_extract(self, url):
  34         display_id = self._match_id(url)
  35         webpage = self._download_webpage(url, display_id)
  36
  37         if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage:
  38             self.raise_geo_restricted(countries=['FR'])
  39
  40         series = get_element_by_class('video-detail__title', webpage)
  41         title = episode = get_element_by_class(
  42             'video-detail__subtitle', webpage) or series
  43         if series and series != title:
  44             title = '%s - %s' % (series, title)
  45         vpl_data = extract_attributes(self._search_regex(
  46             r'(<[^>]+class="video_player_loader"[^>]+>)',
  47             webpage, 'video player loader'))
  48
  49         video_files = self._parse_json(
  50             vpl_data['data-broadcast'], display_id).get('files', [])
  51         formats = []
  52         for video_file in video_files:
  53             v_url = video_file.get('url')
  54             if not v_url:
  55                 continue
  56             video_format = video_file.get('format') or determine_ext(v_url)
  57             if video_format == 'm3u8':
  58                 formats.extend(self._extract_m3u8_formats(
  59                     v_url, display_id, 'mp4', 'm3u8_native',
  60                     m3u8_id='hls', fatal=False))
  61             else:
  62                 formats.append({
  63                     'url': v_url,
  64                     'format_id': video_format,
  65                 })
  66         self._sort_formats(formats)
  67
  68         return {
  69             'id': display_id,
  70             'display_id': display_id,
  71             'title': title,
  72             'description': clean_html(get_element_by_class('video-detail__description', webpage)),
  73             'thumbnail': vpl_data.get('data-image'),
  74             'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)),
  75             'timestamp': parse_iso8601(self._html_search_meta('uploadDate', webpage)),
  76             'formats': formats,
  77             'episode': episode,
  78             'series': series,
  79         }