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

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class CollegeHumorIE(InfoExtractor):
  10     _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
  11
  12     _TESTS = [{
  13         'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
  14         'file': '6902724.mp4',
  15         'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
  16         'info_dict': {
  17             'title': 'Comic-Con Cosplay Catastrophe',
  18             'description': 'Fans get creative this year at San Diego.  Too',
  19             'age_limit': 13,
  20         },
  21     },
  22     {
  23         'url': 'http://www.collegehumor.com/video/3505939/font-conference',
  24         'file': '3505939.mp4',
  25         'md5': '72fa701d8ef38664a4dbb9e2ab721816',
  26         'info_dict': {
  27             'title': 'Font Conference',
  28             'description': 'This video wasn\'t long enough, so we made it double-spaced.',
  29             'age_limit': 10,
  30         },
  31     }]
  32
  33     def _real_extract(self, url):
  34         mobj = re.match(self._VALID_URL, url)
  35         video_id = mobj.group('videoid')
  36
  37         jsonUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id + '.json'
  38         data = json.loads(self._download_webpage(
  39             jsonUrl, video_id, 'Downloading info JSON'))
  40         vdata = data['video']
  41
  42         AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0}
  43         rating = vdata.get('rating')
  44         if rating:
  45             age_limit = AGE_LIMITS.get(rating.lower())
  46         else:
  47             age_limit = None  # None = No idea
  48
  49         PREFS = {'high_quality': 2, 'low_quality': 0}
  50         formats = []
  51         for format_key in ('mp4', 'webm'):
  52             for qname, qurl in vdata[format_key].items():
  53                 formats.append({
  54                     'format_id': format_key + '_' + qname,
  55                     'url': qurl,
  56                     'format': format_key,
  57                     'preference': PREFS.get(qname),
  58                 })
  59         self._sort_formats(formats)
  60
  61         return {
  62             'id': video_id,
  63             'title': vdata['title'],
  64             'description': vdata.get('description'),
  65             'thumbnail': vdata.get('thumbnail'),
  66             'formats': formats,
  67             'age_limit': age_limit,
  68         }