yt_dlp/extractor/crtvg.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import make_archive_id, remove_end
   5
   6
   7 class CrtvgIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?crtvg\.es/tvg/a-carta/(?P<id>[^/#?]+)'
   9     _TESTS = [{
  10         'url': 'https://www.crtvg.es/tvg/a-carta/os-caimans-do-tea-5839623',
  11         'md5': 'c0958d9ff90e4503a75544358758921d',
  12         'info_dict': {
  13             'id': 'os-caimans-do-tea-5839623',
  14             'title': 'Os caimáns do Tea',
  15             'ext': 'mp4',
  16             'description': 'md5:f71cfba21ae564f0a6f415b31de1f842',
  17             'thumbnail': r're:^https?://.*\.(?:jpg|png)',
  18             '_old_archive_ids': ['crtvg 5839623'],
  19         },
  20         'params': {'skip_download': 'm3u8'},
  21     }, {
  22         'url': 'https://www.crtvg.es/tvg/a-carta/a-parabolica-love-story',
  23         'md5': '9a47b95a1749db7b7eb3214904624584',
  24         'info_dict': {
  25             'id': 'a-parabolica-love-story',
  26             'title': 'A parabólica / Trabuco, o can mordedor / Love Story',
  27             'ext': 'mp4',
  28             'description': 'md5:f71cfba21ae564f0a6f415b31de1f842',
  29             'thumbnail': r're:^https?://.*\.(?:jpg|png)',
  30         },
  31         'params': {'skip_download': 'm3u8'},
  32     }]
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36         webpage = self._download_webpage(url, video_id)
  37         video_url = self._search_regex(r'var\s+url\s*=\s*["\']([^"\']+)', webpage, 'video url')
  38         formats = self._extract_m3u8_formats(video_url + '/playlist.m3u8', video_id, fatal=False)
  39         formats.extend(self._extract_mpd_formats(video_url + '/manifest.mpd', video_id, fatal=False))
  40
  41         old_video_id = None
  42         if mobj := re.fullmatch(r'[^/#?]+-(?P<old_id>\d{7})', video_id):
  43             old_video_id = [make_archive_id(self, mobj.group('old_id'))]
  44
  45         return {
  46             'id': video_id,
  47             '_old_archive_ids': old_video_id,
  48             'formats': formats,
  49             'title': remove_end(self._html_search_meta(
  50                 ['og:title', 'twitter:title'], webpage, 'title', default=None), ' | CRTVG'),
  51             'description': self._html_search_meta('description', webpage, 'description', default=None),
  52             'thumbnail': self._html_search_meta(['og:image', 'twitter:image'], webpage, 'thumbnail', default=None),
  53         }