From ae3531adf926998d42d1fb52453491c85e33b5f0 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 28 Aug 2013 12:04:44 +0200 Subject: [generic] Fix URL concatenation When the url is something like http://example.org/foo/bar?x=y and the added is file/video.mp4 , we want http://example.org/foo/file/video.mp4 Fixes #1268. --- youtube_dl/extractor/generic.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'youtube_dl/extractor/generic.py') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index d034a11bb..bfc9bff49 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -166,7 +166,12 @@ class GenericIE(InfoExtractor): if video_url.startswith('//'): video_url = compat_urllib_parse_urlparse(url).scheme + ':' + video_url if '://' not in video_url: - video_url = url + ('' if url.endswith('/') else '/') + video_url + up = compat_urllib_parse_urlparse(url) + if video_url.startswith('/'): + video_url = up.scheme + '://' + up.netloc + video_url + else: # relative path + video_url = (up.scheme + '://' + up.netloc + + up.path.rpartition('/')[0] + '/' + video_url) video_id = os.path.basename(video_url) # here's a fun little line of code for you: -- cgit v1.2.3 From a5caba1eb02665cdc982d6be4a933aafd79243de Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 28 Aug 2013 12:47:27 +0200 Subject: [generic] simply use urljoin --- youtube_dl/extractor/generic.py | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'youtube_dl/extractor/generic.py') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index bfc9bff49..dc4dea4ad 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -7,8 +7,8 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_error, compat_urllib_parse, - compat_urllib_parse_urlparse, compat_urllib_request, + compat_urlparse, ExtractorError, ) @@ -163,15 +163,7 @@ class GenericIE(InfoExtractor): raise ExtractorError(u'Invalid URL: %s' % url) video_url = compat_urllib_parse.unquote(mobj.group(1)) - if video_url.startswith('//'): - video_url = compat_urllib_parse_urlparse(url).scheme + ':' + video_url - if '://' not in video_url: - up = compat_urllib_parse_urlparse(url) - if video_url.startswith('/'): - video_url = up.scheme + '://' + up.netloc + video_url - else: # relative path - video_url = (up.scheme + '://' + up.netloc + - up.path.rpartition('/')[0] + '/' + video_url) + video_url = compat_urlparse.urljoin(url, video_url) video_id = os.path.basename(video_url) # here's a fun little line of code for you: -- cgit v1.2.3