Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/drbonanza.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     js_to_json,
   8     parse_duration,
   9     unescapeHTML,
  10 )
  11
  12
  13 class DRBonanzaIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/[^/]+/\d+/[^/]+/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
  15     _TEST = {
  16         'url': 'http://www.dr.dk/bonanza/serie/154/matador/40312/matador---0824-komme-fremmede-',
  17         'info_dict': {
  18             'id': '40312',
  19             'display_id': 'matador---0824-komme-fremmede-',
  20             'ext': 'mp4',
  21             'title': 'MATADOR - 08:24. "Komme fremmede".',
  22             'description': 'md5:77b4c1ac4d4c1b9d610ab4395212ff84',
  23             'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
  24             'duration': 4613,
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id, display_id = mobj.group('id', 'display_id')
  31
  32         webpage = self._download_webpage(url, display_id)
  33
  34         info = self._parse_html5_media_entries(
  35             url, webpage, display_id, m3u8_id='hls',
  36             m3u8_entry_protocol='m3u8_native')[0]
  37         self._sort_formats(info['formats'])
  38
  39         asset = self._parse_json(
  40             self._search_regex(
  41                 r'(?s)currentAsset\s*=\s*({.+?})\s*</script', webpage, 'asset'),
  42             display_id, transform_source=js_to_json)
  43
  44         title = unescapeHTML(asset['AssetTitle']).strip()
  45
  46         def extract(field):
  47             return self._search_regex(
  48                 r'<div[^>]+>\s*<p>%s:<p>\s*</div>\s*<div[^>]+>\s*<p>([^<]+)</p>' % field,
  49                 webpage, field, default=None)
  50
  51         info.update({
  52             'id': asset.get('AssetId') or video_id,
  53             'display_id': display_id,
  54             'title': title,
  55             'description': extract('Programinfo'),
  56             'duration': parse_duration(extract('Tid')),
  57             'thumbnail': asset.get('AssetImageUrl'),
  58         })
  59         return info