Discource-C
/
discourse
mirror of https://github.com/discourse/discourse.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

FIX: Detect Wayback Machine using user agent (#9777)

This commit is contained in:
Dan Ungureanu 2020-05-14 14:10:07 +03:00 committed by GitHub
parent 321879a619
commit 3ed6a0e904
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lib/crawler_detection.rb
View File

@ -1,7 +1,7 @@
# frozen_string_literal: true
module CrawlerDetection
WAYBACK_MACHINE_URL = "web.archive.org"
WAYBACK_MACHINE_URL = "archive.org"
def self.to_matcher(string, type: nil)
escaped = string.split('|').map { |agent| Regexp.escape(agent) }.join('|')
@ -15,7 +15,7 @@ module CrawlerDetection
end
def self.crawler?(user_agent, via_header = nil)
return true if user_agent.nil? || via_header&.include?(WAYBACK_MACHINE_URL)
return true if user_agent.nil? || user_agent&.include?(WAYBACK_MACHINE_URL) || via_header&.include?(WAYBACK_MACHINE_URL)
# this is done to avoid regenerating regexes
@non_crawler_matchers ||= {}

4
spec/components/crawler_detection_spec.rb
View File

@ -51,7 +51,9 @@ describe CrawlerDetection do
end
it "returns true when VIA header contains 'web.archive.org'" do
crawler!("Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36", "HTTP/1.0 web.archive.org (Wayback Save Page)")
crawler! "Mozilla/5.0 (compatible; archive.org_bot +http://archive.org/details/archive.org_bot)"
crawler! "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36", "HTTP/1.0 web.archive.org (Wayback Save Page)"
crawler! "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36", "Mozilla/5.0 (compatible; archive.org_bot; Wayback Machine Live Record; http://archive.org/details/archive.org_bot), 1.1 warcprox"
end
it "returns false for non-crawler user agents" do