FEATURE: Oneboxer cache response body (#12562)

* FEATURE: Cache successful HTTP GET requests during Oneboxing

Some oneboxes may fail if when making excessive and/or odd requests against the target domains. This change provides a simple mechanism to cache the results of succesful GET requests as part of the oneboxing process, with the goal of reducing repeated requests and ultimately improving the rate of successful oneboxing.

To enable:

Set `SiteSetting.cache_onebox_response_body` to `true`

Add the domains you’re interesting in caching to `SiteSetting. cache_onebox_response_body_domains` e.g. `example.com|example.org|example.net`

Optionally set `SiteSetting.cache_onebox_user_agent` to a user agent string of your choice to use when making requests against domains in the above list.

* FIX: Swap order of duration and value in redis call

The correct order for `setex` arguments is `key`, `duration`, and `value`.

Duration and value had been flipped, however the code would not have thrown an error because we were caching the value of `1.day.to_i` for a period of 1 seconds… The intention appears to be to set a value of 1 (purely as a flag) for a period of 1 day.

lib/oneboxer.rb

@@ -26,13 +26,17 @@ module Oneboxer
     @ignore_redirects ||= ['http://www.dropbox.com', 'http://store.steampowered.com', 'http://vimeo.com', Discourse.base_url]
   end
 
-  def self.force_get_hosts
-    @force_get_hosts ||= begin
-      hosts = ['http://us.battle.net', 'https://news.yahoo.com']
-      amazon_suffixes = %w(com com.br ca cn fr de in it co.jp com.mx nl pl sa sg es se com.tr ae co.uk)
+  def self.amazon_domains
+    amazon_suffixes = %w(com com.br ca cn fr de in it co.jp com.mx nl pl sa sg es se com.tr ae co.uk)
+    amazon_suffixes.collect { |suffix| "https://www.amazon.#{suffix}" }
+  end
 
-      hosts + amazon_suffixes.collect { |suffix| "https://www.amazon.#{suffix}" }
-    end
+  def self.force_get_hosts
+    hosts = ['http://us.battle.net', 'https://news.yahoo.com']
+    hosts += SiteSetting.cache_onebox_response_body_domains.split('|').collect { |domain| "https://www.#{domain}" }
+    hosts += amazon_domains
+
+    hosts.uniq
   end
 
   def self.force_custom_user_agent_hosts
@@ -80,6 +84,33 @@ module Oneboxer
     Discourse.cache.delete(onebox_failed_cache_key(url))
   end
 
+  def self.cache_response_body?(uri)
+    uri = URI.parse(uri) if uri.is_a?(String)
+
+    if SiteSetting.cache_onebox_response_body?
+      SiteSetting.cache_onebox_response_body_domains.split("|").any? { |domain| uri.hostname.ends_with?(domain) }
+    end
+  end
+
+  def self.cache_response_body(uri, response)
+    key = redis_cached_response_body_key(uri)
+    Discourse.redis.without_namespace.setex(key, 1.minutes.to_i, response)
+  end
+
+  def self.cached_response_body_exists?(uri)
+    key = redis_cached_response_body_key(uri)
+    Discourse.redis.without_namespace.exists(key).to_i > 0
+  end
+
+  def self.fetch_cached_response_body(uri)
+    key = redis_cached_response_body_key(uri)
+    Discourse.redis.without_namespace.get(key)
+  end
+
+  def self.redis_cached_response_body_key(uri)
+    "CACHED_RESPONSE_#{uri}"
+  end
+
   # Parse URLs out of HTML, returning the document when finished.
   def self.each_onebox_link(string_or_doc, extra_paths: [])
     doc = string_or_doc
@@ -368,12 +399,18 @@ module Oneboxer
 
   def self.external_onebox(url)
     Discourse.cache.fetch(onebox_cache_key(url), expires_in: 1.day) do
-      fd = FinalDestination.new(url,
-                                ignore_redirects: ignore_redirects,
-                                ignore_hostnames: blocked_domains,
-                                force_get_hosts: force_get_hosts,
-                                force_custom_user_agent_hosts: force_custom_user_agent_hosts,
-                                preserve_fragment_url_hosts: preserve_fragment_url_hosts)
+      fd_options = {
+        ignore_redirects: ignore_redirects,
+        ignore_hostnames: blocked_domains,
+        force_get_hosts: force_get_hosts,
+        force_custom_user_agent_hosts: force_custom_user_agent_hosts,
+        preserve_fragment_url_hosts: preserve_fragment_url_hosts
+      }
+
+      user_agent_override = SiteSetting.cache_onebox_user_agent if Oneboxer.cache_response_body?(url) && SiteSetting.cache_onebox_user_agent.present?
+      fd_options[:default_user_agent] = user_agent_override if user_agent_override
+
+      fd = FinalDestination.new(url, fd_options)
       uri = fd.resolve
 
       if fd.status != :resolved
@@ -389,20 +426,22 @@ module Oneboxer
         return error_box
       end
 
-      return blank_onebox if uri.blank? || blocked_domains.map { |hostname| uri.hostname.match?(hostname) }.any?
+      return blank_onebox if uri.blank? || blocked_domains.any? { |hostname| uri.hostname.match?(hostname) }
 
-      options = {
+      onebox_options = {
         max_width: 695,
         sanitize_config: Onebox::DiscourseOneboxSanitizeConfig::Config::DISCOURSE_ONEBOX,
         allowed_iframe_origins: allowed_iframe_origins,
         hostname: GlobalSetting.hostname,
         facebook_app_access_token: SiteSetting.facebook_app_access_token,
-        disable_media_download_controls: SiteSetting.disable_onebox_media_download_controls
+        disable_media_download_controls: SiteSetting.disable_onebox_media_download_controls,
+        body_cacher: self
       }
 
-      options[:cookie] = fd.cookie if fd.cookie
+      onebox_options[:cookie] = fd.cookie if fd.cookie
+      onebox_options[:user_agent] = user_agent_override if user_agent_override
 
-      r = Onebox.preview(uri.to_s, options)
+      r = Onebox.preview(uri.to_s, onebox_options)
       result = { onebox: r.to_s, preview: r&.placeholder_html.to_s }
 
       # NOTE: Call r.errors after calling placeholder_html