]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/hse.py
[extractor/huya] Fix stream extraction (#4798)
[yt-dlp.git] / yt_dlp / extractor / hse.py
1 from .common import InfoExtractor
2 from ..utils import (
3 ExtractorError,
4 traverse_obj,
5 unified_timestamp,
6 )
7
8
9 class HSEShowBaseInfoExtractor(InfoExtractor):
10 _GEO_COUNTRIES = ['DE']
11
12 def _extract_redux_data(self, url, video_id):
13 webpage = self._download_webpage(url, video_id)
14 redux = self._html_search_regex(
15 r'window\.__REDUX_DATA__\s*=\s*({.*});?', webpage, 'redux data')
16 return self._parse_json(redux.replace('\n', ''), video_id)
17
18 def _extract_formats_and_subtitles(self, sources, video_id):
19 if not sources:
20 raise ExtractorError('No video found', expected=True, video_id=video_id)
21 formats, subtitles = [], {}
22 for src in sources:
23 if src['mimetype'] != 'application/x-mpegURL':
24 continue
25 fmts, subs = self._extract_m3u8_formats_and_subtitles(src['url'], video_id, ext='mp4')
26 formats.extend(fmts)
27 subtitles = self._merge_subtitles(subtitles, subs)
28 self._sort_formats(formats)
29 return formats, subtitles
30
31
32 class HSEShowIE(HSEShowBaseInfoExtractor):
33 _VALID_URL = r'https?://(?:www\.)?hse\.de/dpl/c/tv-shows/(?P<id>[0-9]+)'
34 _TESTS = [{
35 'url': 'https://www.hse.de/dpl/c/tv-shows/505350',
36 'info_dict': {
37 'id': '505350',
38 'ext': 'mp4',
39 'title': 'Pfeffinger Mode & Accessoires',
40 'timestamp': 1638810000,
41 'upload_date': '20211206',
42 'channel': 'HSE24',
43 'uploader': 'Arina Pirayesh'
44 },
45 'params': {'skip_download': 'm3u8'},
46 }]
47
48 def _real_extract(self, url):
49 video_id = self._match_id(url)
50 json_data = self._extract_redux_data(url, video_id)
51 formats, subtitles = self._extract_formats_and_subtitles(
52 traverse_obj(json_data, ('tvShowPage', 'tvShowVideo', 'sources')), video_id)
53
54 show = traverse_obj(json_data, ('tvShowPage', 'tvShow')) or {}
55 return {
56 'id': video_id,
57 'title': show.get('title') or video_id,
58 'formats': formats,
59 'timestamp': unified_timestamp(f'{show.get("date")} {show.get("hour")}:00'),
60 'thumbnail': traverse_obj(json_data, ('tvShowVideo', 'poster')),
61 'channel': self._search_regex(
62 r'tvShow \| ([A-Z0-9]+)_', show.get('actionFieldText') or '', video_id, fatal=False),
63 'uploader': show.get('presenter'),
64 'subtitles': subtitles,
65 }
66
67
68 class HSEProductIE(HSEShowBaseInfoExtractor):
69 _VALID_URL = r'https?://(?:www\.)?hse\.de/dpl/p/product/(?P<id>[0-9]+)'
70 _TESTS = [{
71 'url': 'https://www.hse.de/dpl/p/product/408630',
72 'info_dict': {
73 'id': '408630',
74 'ext': 'mp4',
75 'title': 'Hose im Ponte-Mix',
76 'uploader': 'Judith Williams'
77 },
78 'params': {'skip_download': 'm3u8'},
79 }]
80
81 def _real_extract(self, url):
82 video_id = self._match_id(url)
83 json_data = self._extract_redux_data(url, video_id)
84 video = traverse_obj(json_data, ('productContent', 'productContent', 'videos', 0)) or {}
85 formats, subtitles = self._extract_formats_and_subtitles(video.get('sources'), video_id)
86
87 return {
88 'id': video_id,
89 'title': traverse_obj(json_data, ('productDetail', 'product', 'name', 'short')) or video_id,
90 'formats': formats,
91 'subtitles': subtitles,
92 'thumbnail': video.get('poster'),
93 'uploader': traverse_obj(json_data, ('productDetail', 'product', 'brand', 'brandName')),
94 }