youtube-dl

Another place where youtube-dl lives on
git clone git://git.oshgnacknak.de/youtube-dl.git
Log | Files | Refs | README | LICENSE

sportdeutschland.py (4320B)


      1 # coding: utf-8
      2 from __future__ import unicode_literals
      3 
      4 from .common import InfoExtractor
      5 from ..compat import (
      6     compat_parse_qs,
      7     compat_urllib_parse_urlparse,
      8 )
      9 from ..utils import (
     10     clean_html,
     11     float_or_none,
     12     int_or_none,
     13     parse_iso8601,
     14     strip_or_none,
     15     try_get,
     16 )
     17 
     18 
     19 class SportDeutschlandIE(InfoExtractor):
     20     _VALID_URL = r'https?://sportdeutschland\.tv/(?P<id>(?:[^/]+/)?[^?#/&]+)'
     21     _TESTS = [{
     22         'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0',
     23         'info_dict': {
     24             'id': '5318cac0275701382770543d7edaf0a0',
     25             'ext': 'mp4',
     26             'title': 'Re-live: Deutsche Meisterschaften 2020 - Halbfinals - Teil 1',
     27             'duration': 16106.36,
     28         },
     29         'params': {
     30             'noplaylist': True,
     31             # m3u8 download
     32             'skip_download': True,
     33         },
     34     }, {
     35         'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0',
     36         'info_dict': {
     37             'id': 'c6e2fdd01f63013854c47054d2ab776f',
     38             'title': 'Re-live: Deutsche Meisterschaften 2020 - Halbfinals',
     39             'description': 'md5:5263ff4c31c04bb780c9f91130b48530',
     40             'duration': 31397,
     41         },
     42         'playlist_count': 2,
     43     }, {
     44         'url': 'https://sportdeutschland.tv/freeride-world-tour-2021-fieberbrunn-oesterreich',
     45         'only_matching': True,
     46     }]
     47 
     48     def _real_extract(self, url):
     49         display_id = self._match_id(url)
     50         data = self._download_json(
     51             'https://backend.sportdeutschland.tv/api/permalinks/' + display_id,
     52             display_id, query={'access_token': 'true'})
     53         asset = data['asset']
     54         title = (asset.get('title') or asset['label']).strip()
     55         asset_id = asset.get('id') or asset.get('uuid')
     56         info = {
     57             'id': asset_id,
     58             'title': title,
     59             'description': clean_html(asset.get('body') or asset.get('description')) or asset.get('teaser'),
     60             'duration': int_or_none(asset.get('seconds')),
     61         }
     62         videos = asset.get('videos') or []
     63         if len(videos) > 1:
     64             playlist_id = compat_parse_qs(compat_urllib_parse_urlparse(url).query).get('playlistId', [None])[0]
     65             if playlist_id:
     66                 if self._downloader.params.get('noplaylist'):
     67                     videos = [videos[int(playlist_id)]]
     68                     self.to_screen('Downloading just a single video because of --no-playlist')
     69                 else:
     70                     self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % asset_id)
     71 
     72             def entries():
     73                 for i, video in enumerate(videos, 1):
     74                     video_id = video.get('uuid')
     75                     video_url = video.get('url')
     76                     if not (video_id and video_url):
     77                         continue
     78                     formats = self._extract_m3u8_formats(
     79                         video_url.replace('.smil', '.m3u8'), video_id, 'mp4', fatal=False)
     80                     if not formats:
     81                         continue
     82                     yield {
     83                         'id': video_id,
     84                         'formats': formats,
     85                         'title': title + ' - ' + (video.get('label') or 'Teil %d' % i),
     86                         'duration': float_or_none(video.get('duration')),
     87                     }
     88             info.update({
     89                 '_type': 'multi_video',
     90                 'entries': entries(),
     91             })
     92         else:
     93             formats = self._extract_m3u8_formats(
     94                 videos[0]['url'].replace('.smil', '.m3u8'), asset_id, 'mp4')
     95             section_title = strip_or_none(try_get(data, lambda x: x['section']['title']))
     96             info.update({
     97                 'formats': formats,
     98                 'display_id': asset.get('permalink'),
     99                 'thumbnail': try_get(asset, lambda x: x['images'][0]),
    100                 'categories': [section_title] if section_title else None,
    101                 'view_count': int_or_none(asset.get('views')),
    102                 'is_live': asset.get('is_live') is True,
    103                 'timestamp': parse_iso8601(asset.get('date') or asset.get('published_at')),
    104             })
    105         return info