yt_dlp/extractor/bfmtv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import extract_attributes
   8
   9
  10 class BFMTVBaseIE(InfoExtractor):
  11     _VALID_URL_BASE = r'https?://(?:www\.)?bfmtv\.com/'
  12     _VALID_URL_TMPL = _VALID_URL_BASE + r'(?:[^/]+/)*[^/?&#]+_%s[A-Z]-(?P<id>\d{12})\.html'
  13     _VIDEO_BLOCK_REGEX = r'(<div[^>]+class="video_block"[^>]*>)'
  14     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
  15
  16     def _brightcove_url_result(self, video_id, video_block):
  17         account_id = video_block.get('accountid') or '876450612001'
  18         player_id = video_block.get('playerid') or 'I2qBTln4u'
  19         return self.url_result(
  20             self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id),
  21             'BrightcoveNew', video_id)
  22
  23
  24 class BFMTVIE(BFMTVBaseIE):
  25     IE_NAME = 'bfmtv'
  26     _VALID_URL = BFMTVBaseIE._VALID_URL_TMPL % 'V'
  27     _TESTS = [{
  28         'url': 'https://www.bfmtv.com/politique/emmanuel-macron-l-islam-est-une-religion-qui-vit-une-crise-aujourd-hui-partout-dans-le-monde_VN-202010020146.html',
  29         'info_dict': {
  30             'id': '6196747868001',
  31             'ext': 'mp4',
  32             'title': 'Emmanuel Macron: "L\'Islam est une religion qui vit une crise aujourd’hui, partout dans le monde"',
  33             'description': 'Le Président s\'exprime sur la question du séparatisme depuis les Mureaux, dans les Yvelines.',
  34             'uploader_id': '876450610001',
  35             'upload_date': '20201002',
  36             'timestamp': 1601629620,
  37         },
  38     }]
  39
  40     def _real_extract(self, url):
  41         bfmtv_id = self._match_id(url)
  42         webpage = self._download_webpage(url, bfmtv_id)
  43         video_block = extract_attributes(self._search_regex(
  44             self._VIDEO_BLOCK_REGEX, webpage, 'video block'))
  45         return self._brightcove_url_result(video_block['videoid'], video_block)
  46
  47
  48 class BFMTVLiveIE(BFMTVIE):
  49     IE_NAME = 'bfmtv:live'
  50     _VALID_URL = BFMTVBaseIE._VALID_URL_BASE + '(?P<id>(?:[^/]+/)?en-direct)'
  51     _TESTS = [{
  52         'url': 'https://www.bfmtv.com/en-direct/',
  53         'info_dict': {
  54             'id': '5615950982001',
  55             'ext': 'mp4',
  56             'title': r're:^le direct BFMTV WEB \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
  57             'uploader_id': '876450610001',
  58             'upload_date': '20171018',
  59             'timestamp': 1508329950,
  60         },
  61         'params': {
  62             'skip_download': True,
  63         },
  64     }, {
  65         'url': 'https://www.bfmtv.com/economie/en-direct/',
  66         'only_matching': True,
  67     }]
  68
  69
  70 class BFMTVArticleIE(BFMTVBaseIE):
  71     IE_NAME = 'bfmtv:article'
  72     _VALID_URL = BFMTVBaseIE._VALID_URL_TMPL % 'A'
  73     _TESTS = [{
  74         'url': 'https://www.bfmtv.com/sante/covid-19-un-responsable-de-l-institut-pasteur-se-demande-quand-la-france-va-se-reconfiner_AV-202101060198.html',
  75         'info_dict': {
  76             'id': '202101060198',
  77             'title': 'Covid-19: un responsable de l\'Institut Pasteur se demande "quand la France va se reconfiner"',
  78             'description': 'md5:947974089c303d3ac6196670ae262843',
  79         },
  80         'playlist_count': 2,
  81     }, {
  82         'url': 'https://www.bfmtv.com/international/pour-bolsonaro-le-bresil-est-en-faillite-mais-il-ne-peut-rien-faire_AD-202101060232.html',
  83         'only_matching': True,
  84     }, {
  85         'url': 'https://www.bfmtv.com/sante/covid-19-oui-le-vaccin-de-pfizer-distribue-en-france-a-bien-ete-teste-sur-des-personnes-agees_AN-202101060275.html',
  86         'only_matching': True,
  87     }]
  88
  89     def _real_extract(self, url):
  90         bfmtv_id = self._match_id(url)
  91         webpage = self._download_webpage(url, bfmtv_id)
  92
  93         entries = []
  94         for video_block_el in re.findall(self._VIDEO_BLOCK_REGEX, webpage):
  95             video_block = extract_attributes(video_block_el)
  96             video_id = video_block.get('videoid')
  97             if not video_id:
  98                 continue
  99             entries.append(self._brightcove_url_result(video_id, video_block))
 100
 101         return self.playlist_result(
 102             entries, bfmtv_id, self._og_search_title(webpage, fatal=False),
 103             self._html_search_meta(['og:description', 'description'], webpage))