[dropbox] Recognize 'https://www.dropbox.com/sh/*' urls (fixes #3795)

And extract the title from the url last path component.
pull/3828/head
Jaime Marquínez Ferrándiz 2014-09-21 13:40:22 +02:00
parent 522c55b7f2
commit 7bd4b4229a
1 changed files with 10 additions and 5 deletions

View File

@ -5,24 +5,29 @@ import os.path
import re
from .common import InfoExtractor
from ..utils import compat_urllib_parse_unquote
from ..utils import compat_urllib_parse_unquote, url_basename
class DropboxIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P<id>[a-zA-Z0-9]{15})/(?P<title>[^?#]*)'
_TEST = {
_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(mobj.group('title'))
fn = compat_urllib_parse_unquote(url_basename(url))
title = os.path.splitext(fn)[0]
video_url = (
re.sub(r'[?&]dl=0', '', url) +