yt_dlp/extractor/cpac.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str
   6 from ..utils import (
   7     int_or_none,
   8     str_or_none,
   9     try_get,
  10     unified_timestamp,
  11     update_url_query,
  12     urljoin,
  13 )
  14
  15 # compat_range
  16 try:
  17     if callable(xrange):
  18         range = xrange
  19 except (NameError, TypeError):
  20     pass
  21
  22
  23 class CPACIE(InfoExtractor):
  24     IE_NAME = 'cpac'
  25     _VALID_URL = r'https?://(?:www\.)?cpac\.ca/(?P<fr>l-)?episode\?id=(?P<id>[\da-f]{8}(?:-[\da-f]{4}){3}-[\da-f]{12})'
  26     _TEST = {
  27         # 'url': 'http://www.cpac.ca/en/programs/primetime-politics/episodes/65490909',
  28         'url': 'https://www.cpac.ca/episode?id=fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
  29         'md5': 'e46ad699caafd7aa6024279f2614e8fa',
  30         'info_dict': {
  31             'id': 'fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
  32             'ext': 'mp4',
  33             'upload_date': '20220215',
  34             'title': 'News Conference to Celebrate National Kindness Week – February 15, 2022',
  35             'description': 'md5:466a206abd21f3a6f776cdef290c23fb',
  36             'timestamp': 1644901200,
  37         },
  38         'params': {
  39             'format': 'bestvideo',
  40             'hls_prefer_native': True,
  41         },
  42     }
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46         url_lang = 'fr' if '/l-episode?' in url else 'en'
  47
  48         content = self._download_json(
  49             'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/episode/index.xml&crafterSite=cpacca&id=' + video_id,
  50             video_id)
  51         video_url = try_get(content, lambda x: x['page']['details']['videoUrl'], compat_str)
  52         formats = []
  53         if video_url:
  54             content = content['page']
  55             title = str_or_none(content['details']['title_%s_t' % (url_lang, )])
  56             formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', ext='mp4')
  57             for fmt in formats:
  58                 # prefer language to match URL
  59                 fmt_lang = fmt.get('language')
  60                 if fmt_lang == url_lang:
  61                     fmt['language_preference'] = 10
  62                 elif not fmt_lang:
  63                     fmt['language_preference'] = -1
  64                 else:
  65                     fmt['language_preference'] = -10
  66
  67         self._sort_formats(formats)
  68
  69         category = str_or_none(content['details']['category_%s_t' % (url_lang, )])
  70
  71         def is_live(v_type):
  72             return (v_type == 'live') if v_type is not None else None
  73
  74         return {
  75             'id': video_id,
  76             'formats': formats,
  77             'title': title,
  78             'description': str_or_none(content['details'].get('description_%s_t' % (url_lang, ))),
  79             'timestamp': unified_timestamp(content['details'].get('liveDateTime')),
  80             'category': [category] if category else None,
  81             'thumbnail': urljoin(url, str_or_none(content['details'].get('image_%s_s' % (url_lang, )))),
  82             'is_live': is_live(content['details'].get('type')),
  83         }
  84
  85
  86 class CPACPlaylistIE(InfoExtractor):
  87     IE_NAME = 'cpac:playlist'
  88     _VALID_URL = r'(?i)https?://(?:www\.)?cpac\.ca/(?:program|search|(?P<fr>emission|rechercher))\?(?:[^&]+&)*?(?P<id>(?:id=\d+|programId=\d+|key=[^&]+))'
  89
  90     _TESTS = [{
  91         'url': 'https://www.cpac.ca/program?id=6',
  92         'info_dict': {
  93             'id': 'id=6',
  94             'title': 'Headline Politics',
  95             'description': 'Watch CPAC’s signature long-form coverage of the day’s pressing political events as they unfold.',
  96         },
  97         'playlist_count': 10,
  98     }, {
  99         'url': 'https://www.cpac.ca/search?key=hudson&type=all&order=desc',
 100         'info_dict': {
 101             'id': 'key=hudson',
 102             'title': 'hudson',
 103         },
 104         'playlist_count': 22,
 105     }, {
 106         'url': 'https://www.cpac.ca/search?programId=50',
 107         'info_dict': {
 108             'id': 'programId=50',
 109             'title': '50',
 110         },
 111         'playlist_count': 9,
 112     }, {
 113         'url': 'https://www.cpac.ca/emission?id=6',
 114         'only_matching': True,
 115     }, {
 116         'url': 'https://www.cpac.ca/rechercher?key=hudson&type=all&order=desc',
 117         'only_matching': True,
 118     }]
 119
 120     def _real_extract(self, url):
 121         video_id = self._match_id(url)
 122         url_lang = 'fr' if any(x in url for x in ('/emission?', '/rechercher?')) else 'en'
 123         pl_type, list_type = ('program', 'itemList') if any(x in url for x in ('/program?', '/emission?')) else ('search', 'searchResult')
 124         api_url = (
 125             'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/%s/index.xml&crafterSite=cpacca&%s'
 126             % (pl_type, video_id, ))
 127         content = self._download_json(api_url, video_id)
 128         entries = []
 129         total_pages = int_or_none(try_get(content, lambda x: x['page'][list_type]['totalPages']), default=1)
 130         for page in range(1, total_pages + 1):
 131             if page > 1:
 132                 api_url = update_url_query(api_url, {'page': '%d' % (page, ), })
 133                 content = self._download_json(
 134                     api_url, video_id,
 135                     note='Downloading continuation - %d' % (page, ),
 136                     fatal=False)
 137
 138             for item in try_get(content, lambda x: x['page'][list_type]['item'], list) or []:
 139                 episode_url = urljoin(url, try_get(item, lambda x: x['url_%s_s' % (url_lang, )]))
 140                 if episode_url:
 141                     entries.append(episode_url)
 142
 143         return self.playlist_result(
 144             (self.url_result(entry) for entry in entries),
 145             playlist_id=video_id,
 146             playlist_title=try_get(content, lambda x: x['page']['program']['title_%s_t' % (url_lang, )]) or video_id.split('=')[-1],
 147             playlist_description=try_get(content, lambda x: x['page']['program']['description_%s_t' % (url_lang, )]),
 148         )