From 5afd7e43c93617569df103709795f5f7ec95380d Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Fri, 3 Sep 2021 18:46:28 -0700 Subject: ingest: check URL blocklist again after redirects --- python/sandcrawler/ingest.py | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'python') diff --git a/python/sandcrawler/ingest.py b/python/sandcrawler/ingest.py index fa60e27..630c477 100644 --- a/python/sandcrawler/ingest.py +++ b/python/sandcrawler/ingest.py @@ -140,6 +140,7 @@ class IngestFileWorker(SandcrawlerWorker): "://osapublishing.org/captcha/", "/password-login", "://gateway.isiknowledge.com/", + "/login?TARGET=", ] self.cookie_blocklist = [ @@ -588,6 +589,12 @@ class IngestFileWorker(SandcrawlerWorker): result['status'] = resource.status return result + if resource.terminal_url: + for pattern in self.base_url_blocklist: + if pattern in resource.terminal_url: + result['status'] = 'skip-url-blocklist' + return result + if resource.terminal_url: for pattern in self.cookie_blocklist: if pattern in resource.terminal_url: -- cgit v1.2.3