Hopiu/linkchecker
1
0
Fork 0
mirror of https://github.com/Hopiu/linkchecker.git synced 2026-04-25 08:34:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

accept unicode in robots.txt can_fetch

Browse source 
git-svn-id: https://linkchecker.svn.sourceforge.net/svnroot/linkchecker/trunk/linkchecker@1924 e7d03fd6-7b0d-0410-9947-9c21f3af8025
This commit is contained in:
calvin 2004-11-09 00:00:59 +00:00
parent 0113eb9fcb
commit c97f68f70a
1 changed files with 4 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
linkcheck/robotparser2.py
View file

@ -224,6 +224,10 @@ class RobotFileParser (object):
"""using the parsed robots.txt decide if useragent can fetch url""" """using the parsed robots.txt decide if useragent can fetch url"""
debug("Checking robot.txt allowance for:\n"\ debug("Checking robot.txt allowance for:\n"\
" user agent: %r\n url: %r" % (useragent, url)) " user agent: %r\n url: %r" % (useragent, url))
if not isinstance(useragent, str):
useragent = useragent.encode("ascii", "ignore")
if not isinstance(url, str):
url = url.encode("ascii", "ignore")
if self.disallow_all: if self.disallow_all:
return False return False
if self.allow_all: if self.allow_all: