]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/newsy.py
[ie/orf:on] Improve extraction (#9677)
[yt-dlp.git] / yt_dlp / extractor / newsy.py
1 from .common import InfoExtractor
2 from ..utils import (
3 js_to_json,
4 merge_dicts,
5 )
6
7
8 class NewsyIE(InfoExtractor):
9 _VALID_URL = r'https?://(?:www\.)?newsy\.com/stories/(?P<id>[^/?#$&]+)'
10
11 _TESTS = [{
12 'url': 'https://www.newsy.com/stories/nft-trend-leads-to-fraudulent-art-auctions/',
13 'info_dict': {
14 'id': '609d65125b086c24fb529312',
15 'ext': 'mp4',
16 'title': 'NFT Art Auctions Have A Piracy Problem',
17 'description': 'md5:971e52ab8bc97e50305475cde8284c83',
18 'display_id': 'nft-trend-leads-to-fraudulent-art-auctions',
19 'timestamp': 1621339200,
20 'duration': 339630,
21 'thumbnail': 'https://cdn.newsy.com/images/videos/x/1620927824_xyrrP4.jpg',
22 'upload_date': '20210518'
23 },
24 'params': {'skip_download': True}
25 }]
26
27 def _real_extract(self, url):
28 display_id = self._match_id(url)
29 webpage = self._download_webpage(url, display_id)
30 data_json = self._parse_json(self._html_search_regex(
31 r'data-video-player\s?=\s?"({[^"]+})">', webpage, 'data'), display_id, js_to_json)
32 ld_json = self._search_json_ld(webpage, display_id, fatal=False)
33
34 formats, subtitles = [], {}
35 if data_json.get('stream'):
36 fmts, subs = self._extract_m3u8_formats_and_subtitles(data_json['stream'], display_id)
37 formats.extend(fmts)
38 subtitles = self._merge_subtitles(subtitles, subs)
39 return merge_dicts(ld_json, {
40 'id': data_json['id'],
41 'display_id': display_id,
42 'title': data_json.get('headline'),
43 'duration': data_json.get('duration'),
44 'thumbnail': data_json.get('image'),
45 'formats': formats,
46 'subtitles': subtitles,
47 })