FIX: use crawler layout when saving url in Wayback Machine (#7667)

This commit is contained in:
Maja Komel 2019-06-03 04:13:32 +02:00 committed by Sam
parent 28dcf445b7
commit 42809f4d69
5 changed files with 50 additions and 39 deletions

View File

@ -79,7 +79,9 @@ class ApplicationController < ActionController::Base
request.user_agent &&
(request.content_type.blank? || request.content_type.include?('html')) &&
!['json', 'rss'].include?(params[:format]) &&
(has_escaped_fragment? || CrawlerDetection.crawler?(request.user_agent) || params.key?("print"))
(has_escaped_fragment? || params.key?("print") ||
CrawlerDetection.crawler?(request.user_agent, request.headers["HTTP_VIA"])
)
end
def perform_refresh_session

View File

@ -1,6 +1,7 @@
# frozen_string_literal: true
module CrawlerDetection
WAYBACK_MACHINE_URL = "web.archive.org"
def self.to_matcher(string, type: nil)
escaped = string.split('|').map { |agent| Regexp.escape(agent) }.join('|')
@ -13,8 +14,8 @@ module CrawlerDetection
Regexp.new(escaped, Regexp::IGNORECASE)
end
def self.crawler?(user_agent)
return true if user_agent.nil?
def self.crawler?(user_agent, via_header = nil)
return true if user_agent.nil? || via_header&.include?(WAYBACK_MACHINE_URL)
# this is done to avoid regenerating regexes
@non_crawler_matchers ||= {}

View File

@ -62,7 +62,7 @@ module Middleware
@is_crawler ||=
begin
user_agent = @env[USER_AGENT]
if CrawlerDetection.crawler?(user_agent)
if CrawlerDetection.crawler?(user_agent, @env["HTTP_VIA"])
:true
else
user_agent.downcase.include?("discourse") ? :true : :false

View File

@ -5,9 +5,9 @@ require_dependency 'crawler_detection'
describe CrawlerDetection do
def crawler!(s)
if (!CrawlerDetection.crawler?(s))
raise "#{s} should be a crawler!"
def crawler!(user_agent, via = nil)
if (!CrawlerDetection.crawler?(user_agent, via))
raise "#{user_agent} should be a crawler!"
end
end
@ -50,6 +50,10 @@ describe CrawlerDetection do
crawler! "Mozilla/5.0 (compatible; Yahoo! Slurp; http://help.yahoo.com/help/us/ysearch/slurp)"
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)")
end
it "returns false for non-crawler user agents" do
not_crawler! "Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36"
not_crawler! "Mozilla/5.0 (Windows NT 6.3; Trident/7.0; rv:11.0) like Gecko"

View File

@ -2690,15 +2690,14 @@ RSpec.describe TopicsController do
end
context "when a crawler" do
it "renders with the crawler layout, and handles proper pagination" do
page1_time = 3.months.ago
page2_time = 2.months.ago
page3_time = 1.month.ago
let(:topic) { Fabricate(:topic) }
let(:page1_time) { 3.months.ago }
let(:page2_time) { 2.months.ago }
let(:page3_time) { 1.month.ago }
before do
freeze_time page1_time
topic = Fabricate(:topic)
Fabricate(:post, topic: topic)
Fabricate(:post, topic: topic)
@ -2712,10 +2711,11 @@ RSpec.describe TopicsController do
# ugly, but no inteface to set this and we don't want to create
# 100 posts to test this thing
TopicView.stubs(:chunk_size).returns(2)
end
user_agent = "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"
get topic.url, env: { "HTTP_USER_AGENT" => user_agent }
shared_examples "crawler layout" do |user_agent, via|
it "renders with the crawler layout, and handles proper pagination" do
get topic.url, env: { "HTTP_USER_AGENT" => user_agent, "HTTP_VIA" => via }
body = response.body
@ -2725,7 +2725,7 @@ RSpec.describe TopicsController do
expect(response.headers['Last-Modified']).to eq(page1_time.httpdate)
get topic.url + "?page=2", env: { "HTTP_USER_AGENT" => user_agent }
get topic.url + "?page=2", env: { "HTTP_USER_AGENT" => user_agent, "HTTP_VIA" => via }
body = response.body
expect(response.headers['Last-Modified']).to eq(page2_time.httpdate)
@ -2733,7 +2733,7 @@ RSpec.describe TopicsController do
expect(body).to include('<link rel="prev" href="' + topic.relative_url)
expect(body).to include('<link rel="next" href="' + topic.relative_url + "?page=3")
get topic.url + "?page=3", env: { "HTTP_USER_AGENT" => user_agent }
get topic.url + "?page=3", env: { "HTTP_USER_AGENT" => user_agent, "HTTP_VIA" => via }
body = response.body
expect(response.headers['Last-Modified']).to eq(page3_time.httpdate)
@ -2741,6 +2741,10 @@ RSpec.describe TopicsController do
end
end
include_examples "crawler layout", "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)", nil
include_examples "crawler layout", "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)"
end
end
describe "#reset_bump_date" do