yt_dlp/extractor/bild.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     traverse_obj,
   5     unescapeHTML,
   6 )
   7
   8
   9 class BildIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html'
  11     IE_DESC = 'Bild.de'
  12     _TESTS = [{
  13         'note': 'static MP4 only',
  14         'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html',
  15         'md5': 'dd495cbd99f2413502a1713a1156ac8a',
  16         'info_dict': {
  17             'id': '38184146',
  18             'ext': 'mp4',
  19             'title': 'Das können die  neuen iPads',
  20             'description': 'md5:a4058c4fa2a804ab59c00d7244bbf62f',
  21             'thumbnail': r're:^https?://.*\.jpg$',
  22             'duration': 196,
  23         }
  24     }, {
  25         'note': 'static MP4 and HLS',
  26         'url': 'https://www.bild.de/video/clip/news-ausland/deftiger-abgang-vom-10m-turm-bademeister-sorgt-fuer-skandal-85158620.bild.html',
  27         'md5': 'fb0ed4f09c495d4ba7ce2eee0bb90de1',
  28         'info_dict': {
  29             'id': '85158620',
  30             'ext': 'mp4',
  31             'title': 'Der Sprungturm-Skandal',
  32             'description': 'md5:709b543c24dc31bbbffee73bccda34ad',
  33             'thumbnail': r're:^https?://.*\.jpg$',
  34             'duration': 69,
  35         }
  36     }]
  37
  38     def _real_extract(self, url):
  39         video_id = self._match_id(url)
  40
  41         video_data = self._download_json(
  42             url.split('.bild.html')[0] + ',view=json.bild.html', video_id)
  43
  44         formats = []
  45         for src in traverse_obj(video_data, ('clipList', 0, 'srces', lambda _, v: v['src'])):
  46             src_type = src.get('type')
  47             if src_type == 'application/x-mpegURL':
  48                 formats.extend(
  49                     self._extract_m3u8_formats(
  50                         src['src'], video_id, 'mp4', m3u8_id='hls', fatal=False))
  51             elif src_type == 'video/mp4':
  52                 formats.append({'url': src['src'], 'format_id': 'http-mp4'})
  53             else:
  54                 self.report_warning(f'Skipping unsupported format type: "{src_type}"')
  55
  56         return {
  57             'id': video_id,
  58             'title': unescapeHTML(video_data['title']).strip(),
  59             'description': unescapeHTML(video_data.get('description')),
  60             'formats': formats,
  61             'thumbnail': video_data.get('poster'),
  62             'duration': int_or_none(video_data.get('durationSec')),
  63         }