[ie/dplay] Fix extractors (#10471)
[yt-dlp3.git] / yt_dlp / extractor / c56.py
blob6264803dd683c2a4a340174ddc5e584effec9130
1 from .common import InfoExtractor
2 from ..utils import js_to_json
5 class C56IE(InfoExtractor):
6 _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
7 IE_NAME = '56.com'
8 _TESTS = [{
9 'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
10 'md5': 'e59995ac63d0457783ea05f93f12a866',
11 'info_dict': {
12 'id': '93440716',
13 'ext': 'flv',
14 'title': '网事知多少 第32期:车怒',
15 'duration': 283.813,
17 }, {
18 'url': 'http://www.56.com/u47/v_MTM5NjQ5ODc2.html',
19 'md5': '',
20 'info_dict': {
21 'id': '82247482',
22 'title': '爱的诅咒之杜鹃花开',
24 'playlist_count': 7,
25 'add_ie': ['Sohu'],
28 def _real_extract(self, url):
29 mobj = self._match_valid_url(url)
30 text_id = mobj.group('textid')
32 webpage = self._download_webpage(url, text_id)
33 sohu_video_info_str = self._search_regex(
34 r'var\s+sohuVideoInfo\s*=\s*({[^}]+});', webpage, 'Sohu video info', default=None)
35 if sohu_video_info_str:
36 sohu_video_info = self._parse_json(
37 sohu_video_info_str, text_id, transform_source=js_to_json)
38 return self.url_result(sohu_video_info['url'], 'Sohu')
40 page = self._download_json(
41 f'http://vxml.56.com/json/{text_id}/', text_id, 'Downloading video info')
43 info = page['info']
45 formats = [
47 'format_id': f['type'],
48 'filesize': int(f['filesize']),
49 'url': f['url'],
50 } for f in info['rfiles']
53 return {
54 'id': info['vid'],
55 'title': info['Subject'],
56 'duration': int(info['duration']) / 1000.0,
57 'formats': formats,
58 'thumbnail': info.get('bimg') or info.get('img'),