X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fdropbox.py;h=14b6c00b0bd1c4d3a306b5513477e2bb6c4cd52d;hb=9e1a5b845586a0a5431fb72467142046d8571e6f;hp=e4d60d17af353a3e300c16185e740f15ad31b511;hpb=6b79f40c3d37d33ac944241e205df8c5c4bbabca;p=youtube-dl diff --git a/youtube_dl/extractor/dropbox.py b/youtube_dl/extractor/dropbox.py index e4d60d17a..14b6c00b0 100644 --- a/youtube_dl/extractor/dropbox.py +++ b/youtube_dl/extractor/dropbox.py @@ -1,32 +1,40 @@ # coding: utf-8 from __future__ import unicode_literals +import os.path import re from .common import InfoExtractor +from ..compat import compat_urllib_parse_unquote +from ..utils import url_basename + class DropboxIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P[a-zA-Z0-9]{15})/(?P[^?#]*)' - _TEST = { - u'url': u'https://www.dropbox.com/s/mcnzehi9wo55th4/20131219_085616.mp4', - u'file': u'mcnzehi9wo55th4.mp4', - u'md5': u'2cec58eb277054eca0dbaaf3bdc72564', - u'info_dict': { - u'title': '20131219_085616' - } - } - - - def _real_extract(self,url): + _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') - title=mobj.group('title') - webpage = self._download_webpage(url, video_id) - video_url=url+'?dl=1' - return{ - 'id':video_id, - 'title':title, - 'url':video_url - - } - \ No newline at end of file + 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) + video_url += ('?' if '?' not in video_url else '&') + 'dl=1' + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + }