1 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..utils import int_or_none
10 class CollegeHumorIE(InfoExtractor):
11 _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
14 'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
15 'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
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.",
26 'url': 'http://www.collegehumor.com/video/3505939/font-conference',
27 'md5': '72fa701d8ef38664a4dbb9e2ab721816',
31 'title': 'Font Conference',
32 'description': "This video wasn't long enough, so we made it double-spaced.",
37 # embedded youtube video
39 'url': 'http://www.collegehumor.com/embed/6950306',
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',
50 'skip_download': True,
52 'add_ie': ['Youtube'],
56 def _real_extract(self, url):
57 mobj = re.match(self._VALID_URL, url)
58 video_id = mobj.group('videoid')
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'))
64 if vdata.get('youtubeId') is not None:
67 'url': vdata['youtubeId'],
71 AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0}
72 rating = vdata.get('rating')
74 age_limit = AGE_LIMITS.get(rating.lower())
76 age_limit = None # None = No idea
78 PREFS = {'high_quality': 2, 'low_quality': 0}
80 for format_key in ('mp4', 'webm'):
81 for qname, qurl in vdata.get(format_key, {}).items():
83 'format_id': format_key + '_' + qname,
86 'preference': PREFS.get(qname),
88 self._sort_formats(formats)
90 duration = int_or_none(vdata.get('duration'), 1000)
91 like_count = int_or_none(vdata.get('likes'))
95 'title': vdata['title'],
96 'description': vdata.get('description'),
97 'thumbnail': vdata.get('thumbnail'),
99 'age_limit': age_limit,
100 'duration': duration,
101 'like_count': like_count,