Git-Mirrors/brozzler
1
0
Fork 0
mirror of https://github.com/internetarchive/brozzler.git synced 2025-06-20 04:44:12 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

avoid exception in case of url without host part

Browse source
This commit is contained in:
Noah Levitt 2016-10-26 12:45:24 -07:00
parent 332912acd7
commit f30c143c66
2 changed files with 9 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

6
brozzler/site.py
View file

@ -54,11 +54,15 @@ class Url:
return self._host return self._host
def matches_ip_or_domain(self, ip_or_domain): def matches_ip_or_domain(self, ip_or_domain):
"""Returns true if """
Returns true if
- ip_or_domain is an ip address and self.host is the same ip address - ip_or_domain is an ip address and self.host is the same ip address
- ip_or_domain is a domain and self.host is the same domain - ip_or_domain is a domain and self.host is the same domain
- ip_or_domain is a domain and self.host is a subdomain of it - ip_or_domain is a domain and self.host is a subdomain of it
""" """
if not self.host:
return False
if ip_or_domain == self.host: if ip_or_domain == self.host:
return True return True

2
setup.py
View file

@ -32,7 +32,7 @@ def find_package_data(package):
setuptools.setup( setuptools.setup(
name='brozzler', name='brozzler',
version='1.1b7.dev107', version='1.1b7.dev108',
description='Distributed web crawling with browsers', description='Distributed web crawling with browsers',
url='https://github.com/internetarchive/brozzler', url='https://github.com/internetarchive/brozzler',
author='Noah Levitt', author='Noah Levitt',