]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/collegehumor.py
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>.*)$'
15 'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
16 'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
20 'title': 'Comic-Con Cosplay Catastrophe',
21 '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
38 'url': 'http://www.collegehumor.com/embed/6950306',
42 'title': 'Young Americans Think President John F. Kennedy Died THIS MORNING IN A CAR ACCIDENT!!!',
43 'uploader': 'Mark Dice',
44 'uploader_id': 'MarkDice',
45 'description': 'md5:62c3dab9351fac7bb44b53b69511d87f',
46 'upload_date': '20140127',
49 'skip_download': True,
51 'add_ie': ['Youtube'],
55 def _real_extract(self
, url
):
56 mobj
= re
.match(self
._VALID
_URL
, url
)
57 video_id
= mobj
.group('videoid')
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'))
63 if vdata
.get('youtubeId') is not None:
66 'url': vdata
['youtubeId'],
70 AGE_LIMITS
= {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0}
71 rating
= vdata
.get('rating')
73 age_limit
= AGE_LIMITS
.get(rating
.lower())
75 age_limit
= None # None = No idea
77 PREFS
= {'high_quality': 2, 'low_quality': 0}
79 for format_key
in ('mp4', 'webm'):
80 for qname
, qurl
in vdata
.get(format_key
, {}).items():
82 'format_id': format_key
+ '_' + qname
,
85 'preference': PREFS
.get(qname
),
87 self
._sort
_formats
(formats
)
89 duration
= int_or_none(vdata
.get('duration'), 1000)
90 like_count
= int_or_none(vdata
.get('likes'))
94 'title': vdata
['title'],
95 'description': vdata
.get('description'),
96 'thumbnail': vdata
.get('thumbnail'),
98 'age_limit': age_limit
,
100 'like_count': like_count
,