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',
  21             'age_limit': 13,
  22         },
  23     },
  24     {
  25         'url': 'http://www.collegehumor.com/video/3505939/font-conference',
  26         'md5': '72fa701d8ef38664a4dbb9e2ab721816',
  27         'info_dict': {
  28             'id': '3505939',
  29             'ext': 'mp4',
  30             'title': 'Font Conference',
  31             'description': 'This video wasn\'t long enough,',
  32             'age_limit': 10,
  33             'duration': 179,
  34         },
  35     },
  36     # embedded youtube video
  37     {
  38         'url': 'http://www.collegehumor.com/embed/6950457',
  39         'info_dict': {
  40             'id': 'W5gMp3ZjYg4',
  41             'ext': 'mp4',
  42             'title': 'Funny Dogs Protecting Babies Compilation 2014 [NEW HD]',
  43             'uploader': 'Funnyplox TV',
  44             'uploader_id': 'funnyploxtv',
  45             'description': 'md5:7ded37421526d54afdf005e25bc2b7a3',
  46             'upload_date': '20140128',
  47         },
  48         'params': {
  49             'skip_download': True,
  50         },
  51         'add_ie': ['Youtube'],
  52     },
  53     ]
  54
  55     def _real_extract(self, url):
  56         mobj = re.match(self._VALID_URL, url)
  57         video_id = mobj.group('videoid')
  58
  59         jsonUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id + '.json'
  60         data = json.loads(self._download_webpage(
  61             jsonUrl, video_id, 'Downloading info JSON'))
  62         vdata = data['video']
  63         if vdata.get('youtubeId') is not None:
  64             return {
  65                 '_type': 'url',
  66                 'url': vdata['youtubeId'],
  67                 'ie_key': 'Youtube',
  68             }
  69
  70         AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0}
  71         rating = vdata.get('rating')
  72         if rating:
  73             age_limit = AGE_LIMITS.get(rating.lower())
  74         else:
  75             age_limit = None  # None = No idea
  76
  77         PREFS = {'high_quality': 2, 'low_quality': 0}
  78         formats = []
  79         for format_key in ('mp4', 'webm'):
  80             for qname, qurl in vdata.get(format_key, {}).items():
  81                 formats.append({
  82                     'format_id': format_key + '_' + qname,
  83                     'url': qurl,
  84                     'format': format_key,
  85                     'preference': PREFS.get(qname),
  86                 })
  87         self._sort_formats(formats)
  88
  89         duration = int_or_none(vdata.get('duration'), 1000)
  90
  91         return {
  92             'id': video_id,
  93             'title': vdata['title'],
  94             'description': vdata.get('description'),
  95             'thumbnail': vdata.get('thumbnail'),
  96             'formats': formats,
  97             'age_limit': age_limit,
  98             'duration': duration,
  99         }