1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-22 00:32:58 +08:00
youtube-dl/youtube_dl/extractor/dropbox.py
Jaime Marquínez Ferrándiz 7bd4b4229a [dropbox] Recognize 'https://www.dropbox.com/sh/*' urls (fixes #3795)
And extract the title from the url last path component.
2014-09-21 13:42:08 +02:00

41 lines
1.2 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import os.path
import re
from .common import InfoExtractor
from ..utils import compat_urllib_parse_unquote, url_basename
class DropboxIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dropbox[.]com/sh?/(?P<id>[a-zA-Z0-9]{15})/.*'
_TESTS = [{
'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0',
'info_dict': {
'id': 'nelirfsxnmcfbfh',
'ext': 'mp4',
'title': 'youtube-dl test video \'ä"BaW_jenozKc'
}
},
{
'url': 'https://www.dropbox.com/sh/662glsejgzoj9sr/AAByil3FGH9KFNZ13e08eSa1a/Pregame%20Ceremony%20Program%20PA%2020140518.m4v',
'only_matching': True,
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
fn = compat_urllib_parse_unquote(url_basename(url))
title = os.path.splitext(fn)[0]
video_url = (
re.sub(r'[?&]dl=0', '', url) +
('?' if '?' in url else '&') + 'dl=1')
return {
'id': video_id,
'title': title,
'url': video_url,
}