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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 from .common import InfoExtractor
   6
   7 from ..utils import int_or_none
   8
   9
  10 class VidioIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?vidio\.com/watch/(?P<id>\d{6})-(?P<display_id>[^/?]+)'
  12     _TEST = {
  13         'url': 'http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015',
  14         'info_dict': {
  15             'id': '165683',
  16             'title': 'DJ_AMBRED - Booyah (Live 2015)',
  17             'ext': 'mp4',
  18             'thumbnail': 'https://cdn0-a.production.vidio.static6.com/uploads/video/image/165683/dj_ambred-booyah-live-2015-bfb2ba.jpg',
  19             'description': 'md5:27dc15f819b6a78a626490881adbadf8',
  20             'duration': 149,
  21         },
  22         'params': {
  23             # m3u8 download
  24             'skip_download': True
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id, display_id = mobj.group('id', 'display_id')
  31
  32         webpage = self._download_webpage(url, display_id)
  33
  34         video_data = self._parse_json(self._html_search_regex(
  35             r'data-json-clips\s*=\s*"\[(.+)\]"', webpage, 'video data'), display_id)
  36
  37         formats = self._extract_m3u8_formats(
  38             video_data['sources'][0]['file'],
  39             display_id, ext='mp4')
  40
  41         return {
  42             'id': video_id,
  43             'title': self._og_search_title(webpage),
  44             'formats': formats,
  45             'thumbnail': video_data.get('image'),
  46             'description': self._og_search_description(webpage),
  47             'duration': int_or_none(video_data.get('clip_duration')),
  48         }