Raphaël G. Git Repositories - youtubedl/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     int_or_none,
   9     parse_duration,
  10 )
  11
  12
  13 class TV5MondePlusIE(InfoExtractor):
  14     IE_DESC = 'TV5MONDE+'
  15     _VALID_URL = r'https?://(?:www\.)?(?:tv5mondeplus|revoir\.tv5monde)\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)'
  16     _TESTS = [{
  17         # movie
  18         'url': 'https://revoir.tv5monde.com/toutes-les-videos/cinema/rendez-vous-a-atlit',
  19         'md5': '8cbde5ea7b296cf635073e27895e227f',
  20         'info_dict': {
  21             'id': '822a4756-0712-7329-1859-a13ac7fd1407',
  22             'display_id': 'rendez-vous-a-atlit',
  23             'ext': 'mp4',
  24             'title': 'Rendez-vous à Atlit',
  25             'description': 'md5:2893a4c5e1dbac3eedff2d87956e4efb',
  26             'upload_date': '20200130',
  27         },
  28     }, {
  29         # series episode
  30         'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/c-est-la-vie-ennemie-juree',
  31         'info_dict': {
  32             'id': '0df7007c-4900-3936-c601-87a13a93a068',
  33             'display_id': 'c-est-la-vie-ennemie-juree',
  34             'ext': 'mp4',
  35             'title': "C'est la vie - Ennemie jurée",
  36             'description': 'md5:dfb5c63087b6f35fe0cc0af4fe44287e',
  37             'upload_date': '20200130',
  38             'series': "C'est la vie",
  39             'episode': 'Ennemie jurée',
  40         },
  41         'params': {
  42             'skip_download': True,
  43         },
  44     }, {
  45         'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/neuf-jours-en-hiver-neuf-jours-en-hiver',
  46         'only_matching': True,
  47     }, {
  48         'url': 'https://revoir.tv5monde.com/toutes-les-videos/info-societe/le-journal-de-la-rts-edition-du-30-01-20-19h30',
  49         'only_matching': True,
  50     }]
  51     _GEO_BYPASS = False
  52
  53     def _real_extract(self, url):
  54         display_id = self._match_id(url)
  55         webpage = self._download_webpage(url, display_id)
  56
  57         if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage:
  58             self.raise_geo_restricted(countries=['FR'])
  59
  60         title = episode = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
  61         vpl_data = extract_attributes(self._search_regex(
  62             r'(<[^>]+class="video_player_loader"[^>]+>)',
  63             webpage, 'video player loader'))
  64
  65         video_files = self._parse_json(
  66             vpl_data['data-broadcast'], display_id).get('files', [])
  67         formats = []
  68         for video_file in video_files:
  69             v_url = video_file.get('url')
  70             if not v_url:
  71                 continue
  72             video_format = video_file.get('format') or determine_ext(v_url)
  73             if video_format == 'm3u8':
  74                 formats.extend(self._extract_m3u8_formats(
  75                     v_url, display_id, 'mp4', 'm3u8_native',
  76                     m3u8_id='hls', fatal=False))
  77             else:
  78                 formats.append({
  79                     'url': v_url,
  80                     'format_id': video_format,
  81                 })
  82         self._sort_formats(formats)
  83
  84         description = self._html_search_regex(
  85             r'(?s)<div[^>]+class=["\']episode-texte[^>]+>(.+?)</div>', webpage,
  86             'description', fatal=False)
  87
  88         series = self._html_search_regex(
  89             r'<p[^>]+class=["\']episode-emission[^>]+>([^<]+)', webpage,
  90             'series', default=None)
  91
  92         if series and series != title:
  93             title = '%s - %s' % (series, title)
  94
  95         upload_date = self._search_regex(
  96             r'(?:date_publication|publish_date)["\']\s*:\s*["\'](\d{4}_\d{2}_\d{2})',
  97             webpage, 'upload date', default=None)
  98         if upload_date:
  99             upload_date = upload_date.replace('_', '')
 100
 101         video_id = self._search_regex(
 102             (r'data-guid=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
 103              r'id_contenu["\']\s:\s*(\d+)'), webpage, 'video id',
 104             default=display_id)
 105
 106         return {
 107             'id': video_id,
 108             'display_id': display_id,
 109             'title': title,
 110             'description': description,
 111             'thumbnail': vpl_data.get('data-image'),
 112             'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)),
 113             'upload_date': upload_date,
 114             'formats': formats,
 115             'series': series,
 116             'episode': episode,
 117         }