Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/bild.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     unescapeHTML,
   8 )
   9
  10
  11 class BildIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html'
  13     IE_DESC = 'Bild.de'
  14     _TEST = {
  15         'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html',
  16         'md5': 'dd495cbd99f2413502a1713a1156ac8a',
  17         'info_dict': {
  18             'id': '38184146',
  19             'ext': 'mp4',
  20             'title': 'Das können die  neuen iPads',
  21             'description': 'md5:a4058c4fa2a804ab59c00d7244bbf62f',
  22             'thumbnail': 're:^https?://.*\.jpg$',
  23             'duration': 196,
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29
  30         video_data = self._download_json(
  31             url.split('.bild.html')[0] + ',view=json.bild.html', video_id)
  32
  33         return {
  34             'id': video_id,
  35             'title': unescapeHTML(video_data['title']).strip(),
  36             'description': unescapeHTML(video_data.get('description')),
  37             'url': video_data['clipList'][0]['srces'][0]['src'],
  38             'thumbnail': video_data.get('poster'),
  39             'duration': int_or_none(video_data.get('durationSec')),
  40         }