2 from __future__ import unicode_literals
4 from .common import InfoExtractor
11 class HuajiaoIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:www\.)?huajiao\.com/l/(?P<id>[0-9]+)'
15 'url': 'http://www.huajiao.com/l/38941232',
16 'md5': 'd08bf9ac98787d24d1e4c0283f2d372d',
21 'description': 're:.*',
23 'thumbnail': r're:^https?://.*\.jpg$',
24 'timestamp': 1475866459,
25 'upload_date': '20161007',
26 'uploader': 'Penny_余姿昀',
27 'uploader_id': '75206005',
31 def _real_extract(self, url):
32 video_id = self._match_id(url)
33 webpage = self._download_webpage(url, video_id)
35 feed_json = self._search_regex(
36 r'var\s+feed\s*=\s*({.+})', webpage, 'feed json')
37 feed = self._parse_json(feed_json, video_id)
39 description = self._html_search_meta(
40 'description', webpage, 'description', fatal=False)
42 def get(section, field):
43 return feed.get(section, {}).get(field)
47 'title': feed['feed']['formated_title'],
48 'description': description,
49 'duration': parse_duration(get('feed', 'duration')),
50 'thumbnail': get('feed', 'image'),
51 'timestamp': parse_iso8601(feed.get('creatime'), ' '),
52 'uploader': get('author', 'nickname'),
53 'uploader_id': get('author', 'uid'),
54 'formats': self._extract_m3u8_formats(
55 feed['feed']['m3u8'], video_id, 'mp4', 'm3u8_native'),