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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import parse_iso8601
   8
   9
  10 class ComCarCoffIE(InfoExtractor):
  11     _VALID_URL = r'http://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)'
  12     _TESTS = [{
  13         'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/',
  14         'info_dict': {
  15             'id': 'miranda-sings-happy-thanksgiving-miranda',
  16             'ext': 'mp4',
  17             'upload_date': '20141127',
  18             'timestamp': 1417107600,
  19             'title': 'Happy Thanksgiving Miranda',
  20             'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.',
  21             'thumbnail': 'http://ccc.crackle.com/images/s5e4_thumb.jpg',
  22         },
  23         'params': {
  24             'skip_download': 'requires ffmpeg',
  25         }
  26     }]
  27
  28     def _real_extract(self, url):
  29         display_id = self._match_id(url)
  30         if not display_id:
  31             display_id = 'comediansincarsgettingcoffee.com'
  32         webpage = self._download_webpage(url, display_id)
  33
  34         full_data = json.loads(self._search_regex(
  35             r'<script type="application/json" id="videoData">(?P<json>.+?)</script>',
  36             webpage, 'full data json'))
  37
  38         video_id = full_data['activeVideo']['video']
  39         video_data = full_data.get('videos', {}).get(video_id) or full_data['singleshots'][video_id]
  40         thumbnails = [{
  41             'url': video_data['images']['thumb'],
  42         }, {
  43             'url': video_data['images']['poster'],
  44         }]
  45         formats = self._extract_m3u8_formats(
  46             video_data['mediaUrl'], video_id, ext='mp4')
  47
  48         return {
  49             'id': video_id,
  50             'display_id': display_id,
  51             'title': video_data['title'],
  52             'description': video_data.get('description'),
  53             'timestamp': parse_iso8601(video_data.get('pubDate')),
  54             'thumbnails': thumbnails,
  55             'formats': formats,
  56             'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))),
  57         }