yt_dlp/extractor/cpac.py

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