youtube-dl/youtube_dl/extractor/photobucket.py

44 lines
1.6 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2013-06-23 20:12:18 +02:00
import datetime
import json
import re
from .common import InfoExtractor
class PhotobucketIE(InfoExtractor):
_VALID_URL = r'http://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
2013-06-27 20:46:46 +02:00
_TEST = {
u'url': u'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0',
u'file': u'zpsc0c3b9fa.mp4',
u'md5': u'7dabfb92b0a31f6c16cebc0f8e60ff99',
u'info_dict': {
'upload_date': '20130504',
'uploader': 'rachaneronas',
'title': 'Tired of Link Building? Try BacklinkMyDomain.com!',
2013-06-27 20:46:46 +02:00
}
}
2013-06-23 20:12:18 +02:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_extension = mobj.group('ext')
webpage = self._download_webpage(url, video_id)
# Extract URL, uploader, and title from webpage
self.report_extraction(video_id)
info_json = self._search_regex(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (.*?)\);',
webpage, 'info json')
info = json.loads(info_json)
return {
'id': video_id,
'url': info[u'downloadUrl'],
'uploader': info[u'username'],
'upload_date': datetime.date.fromtimestamp(info[u'creationDate']).strftime('%Y%m%d'),
'title': info[u'title'],
'ext': video_extension,
'thumbnail': info[u'thumbUrl'],
}