Don't check robotstxt for local files

This commit is contained in:
Cj Malone 2023-01-26 16:10:57 +00:00 committed by GitHub
parent e71eab6932
commit 3054235dc0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 0 deletions

View File

@ -38,6 +38,8 @@ class RobotsTxtMiddleware:
def process_request(self, request, spider):
if request.meta.get("dont_obey_robotstxt"):
return
if request.url.startswith("data:") or request.url.startswith("file:"):
return
d = maybeDeferred(self.robot_parser, request, spider)
d.addCallback(self.process_request_2, request, spider)
return d