]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/huajiao.py
[ie/matchtv] Fix extractor (#10190)
[yt-dlp.git] / yt_dlp / extractor / huajiao.py
1 from .common import InfoExtractor
2 from ..utils import (
3 parse_duration,
4 parse_iso8601,
5 )
6
7
8 class HuajiaoIE(InfoExtractor):
9 IE_DESC = '花椒直播'
10 _VALID_URL = r'https?://(?:www\.)?huajiao\.com/l/(?P<id>[0-9]+)'
11 _TEST = {
12 'url': 'http://www.huajiao.com/l/38941232',
13 'md5': 'd08bf9ac98787d24d1e4c0283f2d372d',
14 'info_dict': {
15 'id': '38941232',
16 'ext': 'mp4',
17 'title': '#新人求关注#',
18 'description': 're:.*',
19 'duration': 2424.0,
20 'thumbnail': r're:^https?://.*\.jpg$',
21 'timestamp': 1475866459,
22 'upload_date': '20161007',
23 'uploader': 'Penny_余姿昀',
24 'uploader_id': '75206005',
25 },
26 }
27
28 def _real_extract(self, url):
29 video_id = self._match_id(url)
30 webpage = self._download_webpage(url, video_id)
31
32 feed_json = self._search_regex(
33 r'var\s+feed\s*=\s*({.+})', webpage, 'feed json')
34 feed = self._parse_json(feed_json, video_id)
35
36 description = self._html_search_meta(
37 'description', webpage, 'description', fatal=False)
38
39 def get(section, field):
40 return feed.get(section, {}).get(field)
41
42 return {
43 'id': video_id,
44 'title': feed['feed']['formated_title'],
45 'description': description,
46 'duration': parse_duration(get('feed', 'duration')),
47 'thumbnail': get('feed', 'image'),
48 'timestamp': parse_iso8601(feed.get('creatime'), ' '),
49 'uploader': get('author', 'nickname'),
50 'uploader_id': get('author', 'uid'),
51 'formats': self._extract_m3u8_formats(
52 feed['feed']['m3u8'], video_id, 'mp4', 'm3u8_native'),
53 }