From b9d3e1635fd2f5724452130bf2f05ea0112cd1ab Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sat, 13 Jul 2013 22:52:12 +0200 Subject: [PATCH] Strip hash info from URL when making requests (Fixes #1038) --- youtube_dl/extractor/common.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 52ae98be3..ec988fc90 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -125,6 +125,11 @@ class InfoExtractor(object): def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None): """ Returns a tuple (page content as string, URL handle) """ + + # Strip hashes from the URL (#1038) + if isinstance(url_or_request, (compat_str, str)): + url_or_request = url_or_request.partition('#')[0] + urlh = self._request_webpage(url_or_request, video_id, note, errnote) content_type = urlh.headers.get('Content-Type', '') m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)