1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-24 09:47:41 +00:00
youtube-dl/youtube_dl/extractor/photobucket.py
2014-11-23 21:39:15 +01:00

45 lines
1.7 KiB
Python

from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import compat_urllib_parse
class PhotobucketIE(InfoExtractor):
_VALID_URL = r'http://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
_TEST = {
'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',
'file': 'zpsc0c3b9fa.mp4',
'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99',
'info_dict': {
'timestamp': 1367669341,
'upload_date': '20130504',
'uploader': 'rachaneronas',
'title': 'Tired of Link Building? Try BacklinkMyDomain.com!',
}
}
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)
url = compat_urllib_parse.unquote(self._html_search_regex(r'file=(.+\.mp4)', info['linkcodes']['html'], 'url'))
return {
'id': video_id,
'url': url,
'uploader': info['username'],
'timestamp': info['creationDate'],
'title': info['title'],
'ext': video_extension,
'thumbnail': info['thumbUrl'],
}