mirror of
https://github.com/discourse/discourse.git
synced 2024-12-01 03:13:38 +08:00
758e160862
Googlebot handles no-index headers very elegantly. It advises to leave as many routes as possible open and uses headers for high fidelity rules regarding indexes.
Discourse adds special `x-robot-tags` noindex headers to users, badges, groups, search and tag routes.
Following up on b52143feff we now have it so Googlebot gets special handling.
Rest of the crawlers get a far more aggressive disallow list to protect against excessive crawling.
100 lines
2.9 KiB
Ruby
100 lines
2.9 KiB
Ruby
# frozen_string_literal: true
|
|
|
|
class RobotsTxtController < ApplicationController
|
|
layout false
|
|
skip_before_action :preload_json, :check_xhr, :redirect_to_login_if_required
|
|
|
|
OVERRIDDEN_HEADER = "# This robots.txt file has been customized at /admin/customize/robots\n"
|
|
|
|
# NOTE: order is important!
|
|
DISALLOWED_PATHS ||= %w{
|
|
/admin/
|
|
/auth/
|
|
/assets/browser-update*.js
|
|
/email/
|
|
/session
|
|
/user-api-key
|
|
/*?api_key*
|
|
/*?*api_key*
|
|
}
|
|
|
|
DISALLOWED_WITH_HEADER_PATHS ||= %w{
|
|
/badges
|
|
/u
|
|
/my
|
|
/search
|
|
/tag
|
|
/g
|
|
/t/*/*.rss
|
|
/c/*.rss
|
|
}
|
|
|
|
def index
|
|
if (overridden = SiteSetting.overridden_robots_txt.dup).present?
|
|
overridden.prepend(OVERRIDDEN_HEADER) if guardian.is_admin? && !is_api?
|
|
render plain: overridden
|
|
return
|
|
end
|
|
if SiteSetting.allow_index_in_robots_txt?
|
|
@robots_info = self.class.fetch_default_robots_info
|
|
render :index, content_type: 'text/plain'
|
|
else
|
|
render :no_index, content_type: 'text/plain'
|
|
end
|
|
end
|
|
|
|
# If you are hosting Discourse in a subfolder, you will need to create your robots.txt
|
|
# in the root of your web server with the appropriate paths. This method will return
|
|
# JSON that can be used by a script to create a robots.txt that works well with your
|
|
# existing site.
|
|
def builder
|
|
result = self.class.fetch_default_robots_info
|
|
overridden = SiteSetting.overridden_robots_txt
|
|
result[:overridden] = overridden if overridden.present?
|
|
render json: result
|
|
end
|
|
|
|
def self.fetch_default_robots_info
|
|
deny_paths_googlebot = DISALLOWED_PATHS.map { |p| Discourse.base_path + p }
|
|
deny_paths = deny_paths_googlebot + DISALLOWED_WITH_HEADER_PATHS.map { |p| Discourse.base_path + p }
|
|
deny_all = [ "#{Discourse.base_path}/" ]
|
|
|
|
result = {
|
|
header: "# See http://www.robotstxt.org/robotstxt.html for documentation on how to use the robots.txt file",
|
|
agents: []
|
|
}
|
|
|
|
if SiteSetting.allowed_crawler_user_agents.present?
|
|
SiteSetting.allowed_crawler_user_agents.split('|').each do |agent|
|
|
paths = agent == "Googlebot" ? deny_paths_googlebot : deny_paths
|
|
result[:agents] << { name: agent, disallow: paths }
|
|
end
|
|
|
|
result[:agents] << { name: '*', disallow: deny_all }
|
|
else
|
|
|
|
if SiteSetting.blocked_crawler_user_agents.present?
|
|
SiteSetting.blocked_crawler_user_agents.split('|').each do |agent|
|
|
result[:agents] << { name: agent, disallow: deny_all }
|
|
end
|
|
end
|
|
|
|
result[:agents] << { name: '*', disallow: deny_paths }
|
|
|
|
result[:agents] << { name: 'Googlebot', disallow: deny_paths_googlebot }
|
|
end
|
|
|
|
if SiteSetting.slow_down_crawler_user_agents.present?
|
|
SiteSetting.slow_down_crawler_user_agents.split('|').each do |agent|
|
|
result[:agents] << {
|
|
name: agent,
|
|
delay: SiteSetting.slow_down_crawler_rate,
|
|
disallow: deny_paths
|
|
}
|
|
end
|
|
end
|
|
|
|
result
|
|
end
|
|
end
|