summaryrefslogtreecommitdiffstats
path: root/Lib/urllib/robotparser.py
diff options
context:
space:
mode:
authorMiss Islington (bot) <31488909+miss-islington@users.noreply.github.com>2019-06-16 07:07:54 (GMT)
committerGitHub <noreply@github.com>2019-06-16 07:07:54 (GMT)
commit58a1a76baefc92d9e2392a5dbf65e39e44fb8f55 (patch)
tree04b3001a1bc09863fcd62a0442d0da2445ad0fba /Lib/urllib/robotparser.py
parenta8e7ebe2880f4c1d3b91d40b9730bb4032d514d0 (diff)
downloadcpython-58a1a76baefc92d9e2392a5dbf65e39e44fb8f55.zip
cpython-58a1a76baefc92d9e2392a5dbf65e39e44fb8f55.tar.gz
cpython-58a1a76baefc92d9e2392a5dbf65e39e44fb8f55.tar.bz2
bpo-35922: Fix RobotFileParser when robots.txt has no relevant crawl delay or request rate (GH-11791)
Co-Authored-By: Tal Einat <taleinat+github@gmail.com> (cherry picked from commit 8047e0e1c620f69cc21f9ca48b24bf2cdd5c3668) Co-authored-by: Rémi Lapeyre <remi.lapeyre@henki.fr>
Diffstat (limited to 'Lib/urllib/robotparser.py')
-rw-r--r--Lib/urllib/robotparser.py8
1 files changed, 6 insertions, 2 deletions
diff --git a/Lib/urllib/robotparser.py b/Lib/urllib/robotparser.py
index 7089916..c58565e 100644
--- a/Lib/urllib/robotparser.py
+++ b/Lib/urllib/robotparser.py
@@ -186,7 +186,9 @@ class RobotFileParser:
for entry in self.entries:
if entry.applies_to(useragent):
return entry.delay
- return self.default_entry.delay
+ if self.default_entry:
+ return self.default_entry.delay
+ return None
def request_rate(self, useragent):
if not self.mtime():
@@ -194,7 +196,9 @@ class RobotFileParser:
for entry in self.entries:
if entry.applies_to(useragent):
return entry.req_rate
- return self.default_entry.req_rate
+ if self.default_entry:
+ return self.default_entry.req_rate
+ return None
def site_maps(self):
if not self.sitemaps: