yt_dlp/extractor/drbonanza.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     js_to_json,
   4     parse_duration,
   5     unescapeHTML,
   6 )
   7
   8
   9 class DRBonanzaIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/[^/]+/\d+/[^/]+/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
  11     _TEST = {
  12         'url': 'http://www.dr.dk/bonanza/serie/154/matador/40312/matador---0824-komme-fremmede-',
  13         'info_dict': {
  14             'id': '40312',
  15             'display_id': 'matador---0824-komme-fremmede-',
  16             'ext': 'mp4',
  17             'title': 'MATADOR - 08:24. "Komme fremmede".',
  18             'description': 'md5:77b4c1ac4d4c1b9d610ab4395212ff84',
  19             'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
  20             'duration': 4613,
  21         },
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = self._match_valid_url(url)
  26         video_id, display_id = mobj.group('id', 'display_id')
  27
  28         webpage = self._download_webpage(url, display_id)
  29
  30         info = self._parse_html5_media_entries(
  31             url, webpage, display_id, m3u8_id='hls',
  32             m3u8_entry_protocol='m3u8_native')[0]
  33
  34         asset = self._parse_json(
  35             self._search_regex(
  36                 r'(?s)currentAsset\s*=\s*({.+?})\s*</script', webpage, 'asset'),
  37             display_id, transform_source=js_to_json)
  38
  39         title = unescapeHTML(asset['AssetTitle']).strip()
  40
  41         def extract(field):
  42             return self._search_regex(
  43                 r'<div[^>]+>\s*<p>%s:<p>\s*</div>\s*<div[^>]+>\s*<p>([^<]+)</p>' % field,
  44                 webpage, field, default=None)
  45
  46         info.update({
  47             'id': asset.get('AssetId') or video_id,
  48             'display_id': display_id,
  49             'title': title,
  50             'description': extract('Programinfo'),
  51             'duration': parse_duration(extract('Tid')),
  52             'thumbnail': asset.get('AssetImageUrl'),
  53         })
  54         return info