Search code examples
javascriptangularjsnode.jsnginxprerender

Using prerender with proxy in nginx


I'm trying to use prerender.io to get an snapshot of angularjs pages. Currently I have an NodeJS instance for the web app and nginx reverse proxy redirects requests from port 80 to 4000.

According to prerender nginx manual (https://gist.github.com/thoop/8165802) I can forward search-engine bot requests to the prerender url but because I already have a proxy for NodeJS application, I don't know how can I prerender try_files directive.

My question is, how can I use both NodeJS application proxy and prerender directive?


Solution

  • I believe that the prerender example has the answer. If prerender is set to 1, it uses rewrite and then proxy_pass.

    So you would change this:

    if ($prerender = 0) {
                rewrite .* /index.html break;
            }
    

    to this:

    if ($prerender = 0) {
            rewrite .* /index.html break;
            proxy_pass http://[INTERNAL IP]:[PORT];
        }
    

    I would make further modifications since you are using Node and don't need some of the stuff set up for static files.

    Here is my final answer:

    server {
       listen 80;
       server_name example.com;
    
       location / {
           try_files $uri @prerender;
       }
    
    location @prerender {
        #proxy_set_header X-Prerender-Token YOUR_TOKEN;
    
        set $prerender 0;
        if ($http_user_agent ~* "baiduspider|twitterbot|facebookexternalhit|rogerbot|linkedinbot|embedly|quora link preview|showyoubot|outbrain|pinterest|slackbot|vkShare|W3C_Validator") {
            set $prerender 1;
        }
        if ($args ~ "_escaped_fragment_") {
            set $prerender 1;
        }
        if ($http_user_agent ~ "Prerender") {
            set $prerender 0;
        }
        if ($uri ~ "\.(js|css|xml|less|png|jpg|jpeg|gif|pdf|doc|txt|ico|rss|zip|mp3|rar|exe|wmv|doc|avi|ppt|mpg|mpeg|tif|wav|mov|psd|ai|xls|mp4|m4a|swf|dat|dmg|iso|flv|m4v|torrent|ttf|woff)") {
            set $prerender 0;
        }
    
        #resolve using Google's DNS server to force DNS resolution and prevent caching of IPs
        resolver 8.8.8.8;
    
        if ($prerender = 1) {
    
            #setting prerender as a variable forces DNS resolution since nginx caches IPs and doesnt play well with load balancing
            set $prerender "service.prerender.io";
            rewrite .* /$scheme://$host$request_uri? break;
            proxy_pass http://$prerender;
        }
        if ($prerender = 0) {
            proxy_pass http://[INTERNAL IP]:[PORT];
        }
    }
    } 
    

    I hope that helps. One thing that I will add is that I wouldn't use a prerender engine. Spiders can and do index links and pages that use javascript and PDFs even.

    Just my two cents.