1 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from ..compat
import compat_urllib_parse_unquote
10 class PhotobucketIE(InfoExtractor
):
11 _VALID_URL
= r
'https?://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
13 'url': 'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0',
14 'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99',
18 'timestamp': 1367669341,
19 'upload_date': '20130504',
20 'uploader': 'rachaneronas',
21 'title': 'Tired of Link Building? Try BacklinkMyDomain.com!',
25 def _real_extract(self
, url
):
26 mobj
= re
.match(self
._VALID
_URL
, url
)
27 video_id
= mobj
.group('id')
28 video_extension
= mobj
.group('ext')
30 webpage
= self
._download
_webpage
(url
, video_id
)
32 # Extract URL, uploader, and title from webpage
33 self
.report_extraction(video_id
)
34 info_json
= self
._search
_regex
(r
'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (.*?)\);',
36 info
= json
.loads(info_json
)
37 url
= compat_urllib_parse_unquote(self
._html
_search
_regex
(r
'file=(.+\.mp4)', info
['linkcodes']['html'], 'url'))
41 'uploader': info
['username'],
42 'timestamp': info
['creationDate'],
43 'title': info
['title'],
44 'ext': video_extension
,
45 'thumbnail': info
['thumbUrl'],