Strip hash info from URL when making requests (Fixes #1038)

pull/1043/head
Philipp Hagemeister 2013-07-13 22:52:12 +02:00
parent aa6b734e02
commit b9d3e1635f
1 changed files with 5 additions and 0 deletions

View File

@ -125,6 +125,11 @@ class InfoExtractor(object):
def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None): def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
""" Returns a tuple (page content as string, URL handle) """ """ 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) urlh = self._request_webpage(url_or_request, video_id, note, errnote)
content_type = urlh.headers.get('Content-Type', '') content_type = urlh.headers.get('Content-Type', '')
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)