yt-dlp/yt_dlp/extractor/photobucket.py

44 lines
1.7 KiB
Python
Raw Normal View History

2013-06-23 18:12:18 +00:00
import json
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
2013-06-23 18:12:18 +00:00
class PhotobucketIE(InfoExtractor):
_VALID_URL = r'https?://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
2013-06-27 18:46:46 +00:00
_TEST = {
2014-03-09 19:24:19 +00:00
'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',
'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99',
'info_dict': {
'id': 'zpsc0c3b9fa',
'ext': 'mp4',
'timestamp': 1367669341,
'upload_date': '20130504',
'uploader': 'rachaneronas',
'title': 'Tired of Link Building? Try BacklinkMyDomain.com!',
2013-06-27 18:46:46 +00:00
}
}
2013-06-23 18:12:18 +00:00
def _real_extract(self, url):
mobj = self._match_valid_url(url)
2013-06-23 18:12:18 +00:00
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\(Pb\.Data\.Shared\.MEDIA, (.*?)\);',
2014-11-23 20:39:15 +00:00
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,
2014-03-09 19:24:19 +00:00
'uploader': info['username'],
'timestamp': info['creationDate'],
2014-03-09 19:24:19 +00:00
'title': info['title'],
'ext': video_extension,
2014-03-09 19:24:19 +00:00
'thumbnail': info['thumbUrl'],
}