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 from ..utils import int_or_none
   8
   9
  10 class CollegeHumorIE(InfoExtractor):
  11     _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
  12
  13     _TESTS = [{
  14         'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
  15         'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
  16         'info_dict': {
  17             'id': '6902724',
  18             'ext': 'mp4',
  19             'title': 'Comic-Con Cosplay Catastrophe',
  20             'description': "Fans get creative this year at San Diego.  Too creative.  And yes, that's really Joss Whedon.",
  21             'age_limit': 13,
  22             'duration': 187,
  23         },
  24     },
  25     {
  26         'url': 'http://www.collegehumor.com/video/3505939/font-conference',
  27         'md5': '72fa701d8ef38664a4dbb9e2ab721816',
  28         'info_dict': {
  29             'id': '3505939',
  30             'ext': 'mp4',
  31             'title': 'Font Conference',
  32             'description': "This video wasn't long enough, so we made it double-spaced.",
  33             'age_limit': 10,
  34             'duration': 179,
  35         },
  36     },
  37     # embedded youtube video
  38     {
  39         'url': 'http://www.collegehumor.com/embed/6950306',
  40         'info_dict': {
  41             'id': 'Z-bao9fg6Yc',
  42             'ext': 'mp4',
  43             'title': 'Young Americans Think President John F. Kennedy Died THIS MORNING IN A CAR ACCIDENT!!!',
  44             'uploader': 'Mark Dice',
  45             'uploader_id': 'MarkDice',
  46             'description': 'md5:62c3dab9351fac7bb44b53b69511d87f',
  47             'upload_date': '20140127',
  48         },
  49         'params': {
  50             'skip_download': True,
  51         },
  52         'add_ie': ['Youtube'],
  53     },
  54     ]
  55
  56     def _real_extract(self, url):
  57         mobj = re.match(self._VALID_URL, url)
  58         video_id = mobj.group('videoid')
  59
  60         jsonUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id + '.json'
  61         data = json.loads(self._download_webpage(
  62             jsonUrl, video_id, 'Downloading info JSON'))
  63         vdata = data['video']
  64         if vdata.get('youtubeId') is not None:
  65             return {
  66                 '_type': 'url',
  67                 'url': vdata['youtubeId'],
  68                 'ie_key': 'Youtube',
  69             }
  70
  71         AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0}
  72         rating = vdata.get('rating')
  73         if rating:
  74             age_limit = AGE_LIMITS.get(rating.lower())
  75         else:
  76             age_limit = None  # None = No idea
  77
  78         PREFS = {'high_quality': 2, 'low_quality': 0}
  79         formats = []
  80         for format_key in ('mp4', 'webm'):
  81             for qname, qurl in vdata.get(format_key, {}).items():
  82                 formats.append({
  83                     'format_id': format_key + '_' + qname,
  84                     'url': qurl,
  85                     'format': format_key,
  86                     'preference': PREFS.get(qname),
  87                 })
  88         self._sort_formats(formats)
  89
  90         duration = int_or_none(vdata.get('duration'), 1000)
  91         like_count = int_or_none(vdata.get('likes'))
  92
  93         return {
  94             'id': video_id,
  95             'title': vdata['title'],
  96             'description': vdata.get('description'),
  97             'thumbnail': vdata.get('thumbnail'),
  98             'formats': formats,
  99             'age_limit': age_limit,
 100             'duration': duration,
 101             'like_count': like_count,
 102         }