_ Git - youtube-dl/blob - youtube_dl/extractor/huajiao.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from ..utils import parse_duration, parse_iso8601
   5 from .common import InfoExtractor
   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': '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 str')
  34         feed = self._parse_json(feed_json, video_id)
  35
  36         description = self._html_search_meta(
  37             'description', webpage, 'description', fatal=False)
  38
  39         return {
  40             'id': video_id,
  41             'title': feed['feed']['formated_title'],
  42             'description': description,
  43             'duration': parse_duration(feed['feed']['duration']),
  44             'thumbnail': feed['feed']['image'],
  45             'timestamp': parse_iso8601(feed['creatime'], ' '),
  46             'uploader': feed['author']['nickname'],
  47             'uploader_id': feed['author']['uid'],
  48             'formats': self._extract_m3u8_formats(
  49                 feed['feed']['m3u8'], video_id, 'mp4', 'm3u8_native'),
  50         }