aboutsummaryrefslogtreecommitdiffstats
path: root/hypervideo_dl/extractor/sportdeutschland.py
diff options
context:
space:
mode:
Diffstat (limited to 'hypervideo_dl/extractor/sportdeutschland.py')
-rw-r--r--hypervideo_dl/extractor/sportdeutschland.py191
1 files changed, 119 insertions, 72 deletions
diff --git a/hypervideo_dl/extractor/sportdeutschland.py b/hypervideo_dl/extractor/sportdeutschland.py
index 75074b3..30dbcf3 100644
--- a/hypervideo_dl/extractor/sportdeutschland.py
+++ b/hypervideo_dl/extractor/sportdeutschland.py
@@ -1,95 +1,142 @@
from .common import InfoExtractor
from ..utils import (
- clean_html,
- float_or_none,
- int_or_none,
- parse_iso8601,
- parse_qs,
+ join_nonempty,
strip_or_none,
- try_get,
+ traverse_obj,
+ unified_timestamp,
)
class SportDeutschlandIE(InfoExtractor):
_VALID_URL = r'https?://sportdeutschland\.tv/(?P<id>(?:[^/]+/)?[^?#/&]+)'
_TESTS = [{
- 'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0',
+ 'url': 'https://sportdeutschland.tv/blauweissbuchholztanzsport/buchholzer-formationswochenende-2023-samstag-1-bundesliga-landesliga',
'info_dict': {
- 'id': '5318cac0275701382770543d7edaf0a0',
+ 'id': '9839a5c7-0dbb-48a8-ab63-3b408adc7b54',
'ext': 'mp4',
- 'title': 'Re-live: Deutsche Meisterschaften 2020 - Halbfinals - Teil 1',
- 'duration': 16106.36,
- },
- 'params': {
- 'noplaylist': True,
- # m3u8 download
- 'skip_download': True,
- },
+ 'title': 'Buchholzer Formationswochenende 2023 - Samstag - 1. Bundesliga / Landesliga',
+ 'display_id': 'blauweissbuchholztanzsport/buchholzer-formationswochenende-2023-samstag-1-bundesliga-landesliga',
+ 'description': 'md5:a288c794a5ee69e200d8f12982f81a87',
+ 'live_status': 'was_live',
+ 'channel': 'Blau-Weiss Buchholz Tanzsport',
+ 'channel_url': 'https://sportdeutschland.tv/blauweissbuchholztanzsport',
+ 'channel_id': '93ec33c9-48be-43b6-b404-e016b64fdfa3',
+ 'duration': 32447,
+ 'upload_date': '20230114',
+ 'timestamp': 1673733618,
+ }
+ }, {
+ 'url': 'https://sportdeutschland.tv/deutscherbadmintonverband/bwf-tour-1-runde-feld-1-yonex-gainward-german-open-2022-0',
+ 'info_dict': {
+ 'id': '95c80c52-6b9a-4ae9-9197-984145adfced',
+ 'ext': 'mp4',
+ 'title': 'BWF Tour: 1. Runde Feld 1 - YONEX GAINWARD German Open 2022',
+ 'display_id': 'deutscherbadmintonverband/bwf-tour-1-runde-feld-1-yonex-gainward-german-open-2022-0',
+ 'description': 'md5:2afb5996ceb9ac0b2ac81f563d3a883e',
+ 'live_status': 'was_live',
+ 'channel': 'Deutscher Badminton Verband',
+ 'channel_url': 'https://sportdeutschland.tv/deutscherbadmintonverband',
+ 'channel_id': '93ca5866-2551-49fc-8424-6db35af58920',
+ 'duration': 41097,
+ 'upload_date': '20220309',
+ 'timestamp': 1646860727.0,
+ }
}, {
- 'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0',
+ 'url': 'https://sportdeutschland.tv/ggcbremen/formationswochenende-latein-2023',
'info_dict': {
- 'id': 'c6e2fdd01f63013854c47054d2ab776f',
- 'title': 'Re-live: Deutsche Meisterschaften 2020 - Halbfinals',
- 'description': 'md5:5263ff4c31c04bb780c9f91130b48530',
- 'duration': 31397,
+ 'id': '9889785e-55b0-4d97-a72a-ce9a9f157cce',
+ 'title': 'Formationswochenende Latein 2023 - Samstag',
+ 'display_id': 'ggcbremen/formationswochenende-latein-2023',
+ 'description': 'md5:6e4060d40ff6a8f8eeb471b51a8f08b2',
+ 'live_status': 'was_live',
+ 'channel': 'Grün-Gold-Club Bremen e.V.',
+ 'channel_id': '9888f04e-bb46-4c7f-be47-df960a4167bb',
+ 'channel_url': 'https://sportdeutschland.tv/ggcbremen',
},
- 'playlist_count': 2,
+ 'playlist_count': 3,
+ 'playlist': [{
+ 'info_dict': {
+ 'id': '988e1fea-9d44-4fab-8c72-3085fb667547',
+ 'ext': 'mp4',
+ 'channel_url': 'https://sportdeutschland.tv/ggcbremen',
+ 'channel_id': '9888f04e-bb46-4c7f-be47-df960a4167bb',
+ 'channel': 'Grün-Gold-Club Bremen e.V.',
+ 'duration': 86,
+ 'title': 'Formationswochenende Latein 2023 - Samstag Part 1',
+ 'upload_date': '20230225',
+ 'timestamp': 1677349909,
+ 'live_status': 'was_live',
+ }
+ }]
}, {
- 'url': 'https://sportdeutschland.tv/freeride-world-tour-2021-fieberbrunn-oesterreich',
- 'only_matching': True,
+ 'url': 'https://sportdeutschland.tv/dtb/gymnastik-international-tag-1',
+ 'info_dict': {
+ 'id': '95d71b8a-370a-4b87-ad16-94680da18528',
+ 'ext': 'mp4',
+ 'title': r're:Gymnastik International - Tag 1 .+',
+ 'display_id': 'dtb/gymnastik-international-tag-1',
+ 'channel_id': '936ecef1-2f4a-4e08-be2f-68073cb7ecab',
+ 'channel': 'Deutscher Turner-Bund',
+ 'channel_url': 'https://sportdeutschland.tv/dtb',
+ 'description': 'md5:07a885dde5838a6f0796ee21dc3b0c52',
+ 'live_status': 'is_live',
+ },
+ 'skip': 'live',
}]
+ def _process_video(self, asset_id, video):
+ is_live = video['type'] == 'mux_live'
+ token = self._download_json(
+ f'https://api.sportdeutschland.tv/api/frontend/asset-token/{asset_id}',
+ video['id'], query={'type': video['type'], 'playback_id': video['src']})['token']
+ formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+ f'https://stream.mux.com/{video["src"]}.m3u8?token={token}', video['id'], live=is_live)
+
+ return {
+ 'is_live': is_live,
+ 'formats': formats,
+ 'subtitles': subtitles,
+ **traverse_obj(video, {
+ 'id': 'id',
+ 'duration': ('duration', {lambda x: float(x) > 0 and float(x)}),
+ 'timestamp': ('created_at', {unified_timestamp})
+ }),
+ }
+
def _real_extract(self, url):
display_id = self._match_id(url)
- data = self._download_json(
- 'https://backend.sportdeutschland.tv/api/permalinks/' + display_id,
+ meta = self._download_json(
+ f'https://api.sportdeutschland.tv/api/stateless/frontend/assets/{display_id}',
display_id, query={'access_token': 'true'})
- asset = data['asset']
- title = (asset.get('title') or asset['label']).strip()
- asset_id = asset.get('id') or asset.get('uuid')
+
info = {
- 'id': asset_id,
- 'title': title,
- 'description': clean_html(asset.get('body') or asset.get('description')) or asset.get('teaser'),
- 'duration': int_or_none(asset.get('seconds')),
+ 'display_id': display_id,
+ **traverse_obj(meta, {
+ 'id': (('id', 'uuid'), ),
+ 'title': (('title', 'name'), {strip_or_none}),
+ 'description': 'description',
+ 'channel': ('profile', 'name'),
+ 'channel_id': ('profile', 'id'),
+ 'is_live': 'currently_live',
+ 'was_live': 'was_live',
+ 'channel_url': ('profile', 'slug', {lambda x: f'https://sportdeutschland.tv/{x}'}),
+ }, get_all=False)
}
- videos = asset.get('videos') or []
- if len(videos) > 1:
- playlist_id = parse_qs(url).get('playlistId', [None])[0]
- if not self._yes_playlist(playlist_id, asset_id):
- videos = [videos[int(playlist_id)]]
- def entries():
- for i, video in enumerate(videos, 1):
- video_id = video.get('uuid')
- video_url = video.get('url')
- if not (video_id and video_url):
- continue
- formats = self._extract_m3u8_formats(
- video_url.replace('.smil', '.m3u8'), video_id, 'mp4', fatal=False)
- if not formats and not self.get_param('ignore_no_formats'):
- continue
- yield {
- 'id': video_id,
- 'formats': formats,
- 'title': title + ' - ' + (video.get('label') or 'Teil %d' % i),
- 'duration': float_or_none(video.get('duration')),
- }
- info.update({
- '_type': 'multi_video',
- 'entries': entries(),
- })
- else:
- formats = self._extract_m3u8_formats(
- videos[0]['url'].replace('.smil', '.m3u8'), asset_id, 'mp4')
- section_title = strip_or_none(try_get(data, lambda x: x['section']['title']))
- info.update({
- 'formats': formats,
- 'display_id': asset.get('permalink'),
- 'thumbnail': try_get(asset, lambda x: x['images'][0]),
- 'categories': [section_title] if section_title else None,
- 'view_count': int_or_none(asset.get('views')),
- 'is_live': asset.get('is_live') is True,
- 'timestamp': parse_iso8601(asset.get('date') or asset.get('published_at')),
- })
- return info
+ parts = traverse_obj(meta, (('livestream', ('videos', ...)), ))
+ entries = [{
+ 'title': join_nonempty(info.get('title'), f'Part {i}', delim=' '),
+ **traverse_obj(info, {'channel': 'channel', 'channel_id': 'channel_id',
+ 'channel_url': 'channel_url', 'was_live': 'was_live'}),
+ **self._process_video(info['id'], video),
+ } for i, video in enumerate(parts, 1)]
+
+ return {
+ '_type': 'multi_video',
+ **info,
+ 'entries': entries,
+ } if len(entries) > 1 else {
+ **info,
+ **entries[0],
+ 'title': info.get('title'),
+ }