yt_dlp/extractor/cpac.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     int_or_none,
   5     str_or_none,
   6     try_get,
   7     unified_timestamp,
   8     update_url_query,
   9     urljoin,
  10 )
  11
  12 # compat_range
  13 try:
  14     if callable(xrange):
  15         range = xrange
  16 except (NameError, TypeError):
  17     pass
  18
  19
  20 class CPACIE(InfoExtractor):
  21     IE_NAME = 'cpac'
  22     _VALID_URL = r'https?://(?:www\.)?cpac\.ca/(?P<fr>l-)?episode\?id=(?P<id>[\da-f]{8}(?:-[\da-f]{4}){3}-[\da-f]{12})'
  23     _TEST = {
  24         # 'url': 'http://www.cpac.ca/en/programs/primetime-politics/episodes/65490909',
  25         'url': 'https://www.cpac.ca/episode?id=fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
  26         'md5': 'e46ad699caafd7aa6024279f2614e8fa',
  27         'info_dict': {
  28             'id': 'fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
  29             'ext': 'mp4',
  30             'upload_date': '20220215',
  31             'title': 'News Conference to Celebrate National Kindness Week – February 15, 2022',
  32             'description': 'md5:466a206abd21f3a6f776cdef290c23fb',
  33             'timestamp': 1644901200,
  34         },
  35         'params': {
  36             'format': 'bestvideo',
  37             'hls_prefer_native': True,
  38         },
  39     }
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43         url_lang = 'fr' if '/l-episode?' in url else 'en'
  44
  45         content = self._download_json(
  46             'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/episode/index.xml&crafterSite=cpacca&id=' + video_id,
  47             video_id)
  48         video_url = try_get(content, lambda x: x['page']['details']['videoUrl'], compat_str)
  49         formats = []
  50         if video_url:
  51             content = content['page']
  52             title = str_or_none(content['details']['title_%s_t' % (url_lang, )])
  53             formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', ext='mp4')
  54             for fmt in formats:
  55                 # prefer language to match URL
  56                 fmt_lang = fmt.get('language')
  57                 if fmt_lang == url_lang:
  58                     fmt['language_preference'] = 10
  59                 elif not fmt_lang:
  60                     fmt['language_preference'] = -1
  61                 else:
  62                     fmt['language_preference'] = -10
  63
  64         self._sort_formats(formats)
  65
  66         category = str_or_none(content['details']['category_%s_t' % (url_lang, )])
  67
  68         def is_live(v_type):
  69             return (v_type == 'live') if v_type is not None else None
  70
  71         return {
  72             'id': video_id,
  73             'formats': formats,
  74             'title': title,
  75             'description': str_or_none(content['details'].get('description_%s_t' % (url_lang, ))),
  76             'timestamp': unified_timestamp(content['details'].get('liveDateTime')),
  77             'category': [category] if category else None,
  78             'thumbnail': urljoin(url, str_or_none(content['details'].get('image_%s_s' % (url_lang, )))),
  79             'is_live': is_live(content['details'].get('type')),
  80         }
  81
  82
  83 class CPACPlaylistIE(InfoExtractor):
  84     IE_NAME = 'cpac:playlist'
  85     _VALID_URL = r'(?i)https?://(?:www\.)?cpac\.ca/(?:program|search|(?P<fr>emission|rechercher))\?(?:[^&]+&)*?(?P<id>(?:id=\d+|programId=\d+|key=[^&]+))'
  86
  87     _TESTS = [{
  88         'url': 'https://www.cpac.ca/program?id=6',
  89         'info_dict': {
  90             'id': 'id=6',
  91             'title': 'Headline Politics',
  92             'description': 'Watch CPAC’s signature long-form coverage of the day’s pressing political events as they unfold.',
  93         },
  94         'playlist_count': 10,
  95     }, {
  96         'url': 'https://www.cpac.ca/search?key=hudson&type=all&order=desc',
  97         'info_dict': {
  98             'id': 'key=hudson',
  99             'title': 'hudson',
 100         },
 101         'playlist_count': 22,
 102     }, {
 103         'url': 'https://www.cpac.ca/search?programId=50',
 104         'info_dict': {
 105             'id': 'programId=50',
 106             'title': '50',
 107         },
 108         'playlist_count': 9,
 109     }, {
 110         'url': 'https://www.cpac.ca/emission?id=6',
 111         'only_matching': True,
 112     }, {
 113         'url': 'https://www.cpac.ca/rechercher?key=hudson&type=all&order=desc',
 114         'only_matching': True,
 115     }]
 116
 117     def _real_extract(self, url):
 118         video_id = self._match_id(url)
 119         url_lang = 'fr' if any(x in url for x in ('/emission?', '/rechercher?')) else 'en'
 120         pl_type, list_type = ('program', 'itemList') if any(x in url for x in ('/program?', '/emission?')) else ('search', 'searchResult')
 121         api_url = (
 122             'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/%s/index.xml&crafterSite=cpacca&%s'
 123             % (pl_type, video_id, ))
 124         content = self._download_json(api_url, video_id)
 125         entries = []
 126         total_pages = int_or_none(try_get(content, lambda x: x['page'][list_type]['totalPages']), default=1)
 127         for page in range(1, total_pages + 1):
 128             if page > 1:
 129                 api_url = update_url_query(api_url, {'page': '%d' % (page, ), })
 130                 content = self._download_json(
 131                     api_url, video_id,
 132                     note='Downloading continuation - %d' % (page, ),
 133                     fatal=False)
 134
 135             for item in try_get(content, lambda x: x['page'][list_type]['item'], list) or []:
 136                 episode_url = urljoin(url, try_get(item, lambda x: x['url_%s_s' % (url_lang, )]))
 137                 if episode_url:
 138                     entries.append(episode_url)
 139
 140         return self.playlist_result(
 141             (self.url_result(entry) for entry in entries),
 142             playlist_id=video_id,
 143             playlist_title=try_get(content, lambda x: x['page']['program']['title_%s_t' % (url_lang, )]) or video_id.split('=')[-1],
 144             playlist_description=try_get(content, lambda x: x['page']['program']['description_%s_t' % (url_lang, )]),
 145         )