projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| 704df56d | 1 | from .common import InfoExtractor |
| 1cc79574 | 2 | from ..utils import ( |
| 10db0d2f | 3 | clean_html, |
| 4 | float_or_none, | |
| 5 | int_or_none, | |
| 704df56d | 6 | parse_iso8601, |
| 4dfbf869 | 7 | parse_qs, |
| 10db0d2f | 8 | strip_or_none, |
| 9 | try_get, | |
| 704df56d PH |
10 | ) |
| 11 | ||
| 12 | ||
| 13 | class SportDeutschlandIE(InfoExtractor): | |
| 10db0d2f | 14 | _VALID_URL = r'https?://sportdeutschland\.tv/(?P<id>(?:[^/]+/)?[^?#/&]+)' |
| 3524cc25 | 15 | _TESTS = [{ |
| 0d006fac | 16 | 'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0', |
| 704df56d | 17 | 'info_dict': { |
| 10db0d2f | 18 | 'id': '5318cac0275701382770543d7edaf0a0', |
| 704df56d | 19 | 'ext': 'mp4', |
| 10db0d2f | 20 | 'title': 'Re-live: Deutsche Meisterschaften 2020 - Halbfinals - Teil 1', |
| 21 | 'duration': 16106.36, | |
| 704df56d | 22 | }, |
| 10db0d2f | 23 | 'params': { |
| 24 | 'noplaylist': True, | |
| 25 | # m3u8 download | |
| 26 | 'skip_download': True, | |
| 27 | }, | |
| 28 | }, { | |
| 29 | 'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0', | |
| 30 | 'info_dict': { | |
| 31 | 'id': 'c6e2fdd01f63013854c47054d2ab776f', | |
| 32 | 'title': 'Re-live: Deutsche Meisterschaften 2020 - Halbfinals', | |
| 33 | 'description': 'md5:5263ff4c31c04bb780c9f91130b48530', | |
| 34 | 'duration': 31397, | |
| 35 | }, | |
| 36 | 'playlist_count': 2, | |
| 37 | }, { | |
| 38 | 'url': 'https://sportdeutschland.tv/freeride-world-tour-2021-fieberbrunn-oesterreich', | |
| 39 | 'only_matching': True, | |
| 3524cc25 | 40 | }] |
| 704df56d PH |
41 | |
| 42 | def _real_extract(self, url): | |
| 10db0d2f | 43 | display_id = self._match_id(url) |
| 44 | data = self._download_json( | |
| 45 | 'https://backend.sportdeutschland.tv/api/permalinks/' + display_id, | |
| 46 | display_id, query={'access_token': 'true'}) | |
| 704df56d | 47 | asset = data['asset'] |
| 10db0d2f | 48 | title = (asset.get('title') or asset['label']).strip() |
| 49 | asset_id = asset.get('id') or asset.get('uuid') | |
| 50 | info = { | |
| 51 | 'id': asset_id, | |
| 52 | 'title': title, | |
| 53 | 'description': clean_html(asset.get('body') or asset.get('description')) or asset.get('teaser'), | |
| 54 | 'duration': int_or_none(asset.get('seconds')), | |
| 55 | } | |
| 56 | videos = asset.get('videos') or [] | |
| 57 | if len(videos) > 1: | |
| 4dfbf869 | 58 | playlist_id = parse_qs(url).get('playlistId', [None])[0] |
| f40ee5e9 | 59 | if not self._yes_playlist(playlist_id, asset_id): |
| 60 | videos = [videos[int(playlist_id)]] | |
| 3524cc25 | 61 | |
| 10db0d2f | 62 | def entries(): |
| 63 | for i, video in enumerate(videos, 1): | |
| 64 | video_id = video.get('uuid') | |
| 65 | video_url = video.get('url') | |
| 66 | if not (video_id and video_url): | |
| 67 | continue | |
| 68 | formats = self._extract_m3u8_formats( | |
| 69 | video_url.replace('.smil', '.m3u8'), video_id, 'mp4', fatal=False) | |
| a06916d9 | 70 | if not formats and not self.get_param('ignore_no_formats'): |
| 10db0d2f | 71 | continue |
| 72 | yield { | |
| 73 | 'id': video_id, | |
| 74 | 'formats': formats, | |
| 75 | 'title': title + ' - ' + (video.get('label') or 'Teil %d' % i), | |
| 76 | 'duration': float_or_none(video.get('duration')), | |
| 77 | } | |
| 78 | info.update({ | |
| 79 | '_type': 'multi_video', | |
| 80 | 'entries': entries(), | |
| 81 | }) | |
| 3524cc25 | 82 | else: |
| 10db0d2f | 83 | formats = self._extract_m3u8_formats( |
| 84 | videos[0]['url'].replace('.smil', '.m3u8'), asset_id, 'mp4') | |
| 85 | section_title = strip_or_none(try_get(data, lambda x: x['section']['title'])) | |
| 86 | info.update({ | |
| 87 | 'formats': formats, | |
| 88 | 'display_id': asset.get('permalink'), | |
| 89 | 'thumbnail': try_get(asset, lambda x: x['images'][0]), | |
| 90 | 'categories': [section_title] if section_title else None, | |
| 91 | 'view_count': int_or_none(asset.get('views')), | |
| 92 | 'is_live': asset.get('is_live') is True, | |
| 93 | 'timestamp': parse_iso8601(asset.get('date') or asset.get('published_at')), | |
| 94 | }) | |
| 95 | return info |