CloudFormation config for redirecting crawlers to Prerender.io

prerender-cloudfront.yml

Parameters:
  PrerenderToken:
    Type: String
  S3BucketName:
    Type: String
Resources:
  WebBucket:
    Type: "AWS::S3::Bucket"
    Properties:
      BucketName:
        Ref: S3BucketName
      AccessControl: PublicRead
      WebsiteConfiguration:
        ErrorDocument: index.html
        IndexDocument: index.html
  WebBucketPolicy:
    Type: "AWS::S3::BucketPolicy"
    Properties:
      Bucket:
        Ref: S3BucketName
      PolicyDocument:
        Statement:
          -
            Action:
              - "s3:GetObject"
            Effect: "Allow"
            Principal: "*"
            Resource: 
              Fn::Join: 
                - ""
                - 
                  - "arn:aws:s3:::"
                  - 
                    Ref: S3BucketName
                  - "/*"
  LambdaEdgeExecutionRole:
    Type: AWS::IAM::Role
    Properties:
      AssumeRolePolicyDocument:
        Version: '2012-10-17'
        Statement:
        - Effect: Allow
          Principal:
            Service:
            - lambda.amazonaws.com
            - edgelambda.amazonaws.com
          Action:
          - sts:AssumeRole
      Policies:
        - PolicyName: logging
          PolicyDocument:
            Version: 2012-10-17
            Statement:
              - Resource: "*"
                Effect: Allow
                Action:
                  - "logs:CreateLogGroup"
                  - "logs:CreateLogStream"
                  - "logs:PutLogEvents"
  SetPrerenderHeader:
    Type: "AWS::Lambda::Function"
    Properties:
      Handler: "index.handler"
      Role:
        Fn::GetAtt:
          - "LambdaEdgeExecutionRole"
          - "Arn"
      Code:
        ZipFile:
          !Sub |
            'use strict';
            /* change the version number below whenever this code is modified */
            exports.handler = (event, context, callback) => {
                const request = event.Records[0].cf.request;
                const headers = request.headers;
                const user_agent = headers['user-agent'];
                const host = headers['host'];
                if (user_agent && host) {
                  var prerender = /googlebot|bingbot|yandex|baiduspider|Facebot|facebookexternalhit|twitterbot|rogerbot|linkedinbot|embedly|quora link preview|showyoubot|outbrain|pinterest|slackbot|vkShare|W3C_Validator/i.test(user_agent[0].value);
                  prerender = prerender || /_escaped_fragment_/.test(request.querystring);
                  prerender = prerender && ! /\.(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|svg|eot)$/i.test(request.uri);
                  if (prerender) {
                    headers['x-prerender-token'] = [{ key: 'X-Prerender-Token', value: '${PrerenderToken}'}];
                    headers['x-prerender-host'] = [{ key: 'X-Prerender-Host', value: host[0].value}];
                    headers['x-prerender-cachebuster'] = [{ key: 'X-Prerender-Cachebuster', value: Date.now().toString()}];
                  }
                }
                callback(null, request);
            };
      Runtime: "nodejs8.10"
  SetPrerenderHeaderVersion3:
    Type: "AWS::Lambda::Version"
    Properties:
      FunctionName:
        Ref: "SetPrerenderHeader"
      Description: "SetPrerenderHeader"
  RedirectToPrerender:
    Type: "AWS::Lambda::Function"
    Properties:
      Handler: "index.handler"
      Role:
        Fn::GetAtt:
          - "LambdaEdgeExecutionRole"
          - "Arn"
      Code:
        ZipFile: |
          'use strict';
          /* change the version number below whenever this code is modified */
          exports.handler = (event, context, callback) => {
               const request = event.Records[0].cf.request;
               if (request.headers['x-prerender-token'] && request.headers['x-prerender-host']) {
                 request.origin = {
                     custom: {
                         domainName: 'service.prerender.io',
                         port: 443,
                         protocol: 'https',
                         readTimeout: 20,
                         keepaliveTimeout: 5,
                         customHeaders: {},
                         sslProtocols: ['TLSv1', 'TLSv1.1'],
                         path: '/https%3A%2F%2F' + request.headers['x-prerender-host'][0].value
                     }
                 };
              }
              callback(null, request);
          };
      Runtime: "nodejs8.10"
  RedirectToPrerenderVersion1:
    Type: "AWS::Lambda::Version"
    Properties:
      FunctionName:
        Ref: "RedirectToPrerender"
      Description: "RedirectToPrerender"
  CloudFront:
    Type: "AWS::CloudFront::Distribution"
    Properties:
      DistributionConfig:
        DefaultCacheBehavior:
          Compress: true
          # NOTE: we let cloudfront cache heavily the resurces of the SPA. Your deploy
          #       step will need to include an invalidation of the cloudfromt cache.
          #       The requests to prerender.io are NOT cached thanks to the X-Prerender-Cachebuster
          #       header.
          MinTTL: 31536000
          DefaultTTL: 31536000
          ForwardedValues:
            QueryString: false
            Headers:
              - "X-Prerender-Token"
              - "X-Prerender-Host"
              - "X-Prerender-Cachebuster"
          TargetOriginId: origin
          ViewerProtocolPolicy : allow-all
          LambdaFunctionAssociations:
            - EventType: viewer-request
              LambdaFunctionARN: !Join [ ":", [ !GetAtt [SetPrerenderHeader, Arn], !GetAtt [SetPrerenderHeaderVersion3, Version] ] ]
            - EventType: origin-request
              LambdaFunctionARN: !Join [ ":", [ !GetAtt [RedirectToPrerender, Arn], !GetAtt [RedirectToPrerenderVersion1, Version] ] ]
        Enabled: true
        CustomErrorResponses:
          - ErrorCode: 404
            ResponseCode: 200
            ResponsePagePath: /index.html
        HttpVersion: http2
        Origins:
          - CustomOriginConfig:
              OriginProtocolPolicy: http-only
            DomainName: !Select [2, !Split [ '/', !GetAtt [WebBucket, WebsiteURL]]]
            Id: origin
        PriceClass: PriceClass_All