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