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

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