0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 03:33:02 +00:00
yt-dlp/youtube_dlc/extractor/photobucket.py
Unknown cefecac12c [skip travis] renaming
to avoid using same folder when using pip install for example
2020-09-02 20:25:25 +02:00

46 lines
1.7 KiB
Python

from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
class PhotobucketIE(InfoExtractor):
_VALID_URL = r'https?://(?:[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',
'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99',
'info_dict': {
'id': 'zpsc0c3b9fa',
'ext': 'mp4',
'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'],
}