Merge pull request #17 from smithclay/api-events

Support Invocation from API Gateway

Author: smithclay

README.md

@@ -3,10 +3,11 @@
 
 **Lambdium allows you to run a Selenium Webdriver script written in Javascript inside of an AWS Lambda function bundled with [Headless Chromium](https://developers.google.com/web/updates/2017/04/headless-chrome).**
 
-You can use this AWS Lambda function to:
+You can use this AWS Lambda function by itself or with other AWS services to:
 
 * Run many concurrent selenium scripts at the same time without worrying about the infrastructure
-* Configure Cloudwatch events to run script(s) on a schedule ([example app](/examples/apps/scheduled-event.yaml))
+* Run execute a selenium script via an HTTP call using API Gateway
+* Configure Cloudwatch events to run a script on a schedule ([example app](/examples/apps/scheduled-event.yaml))
 * Integrate selenium tests running in Chrome into different event-driven workflows (like CodeDeploy checks, webhooks, or uploads to an S3 bucket)
 
 Since this Lambda function is written using node.js, you can run almost any script written for [selenium-webdriver](https://www.npmjs.com/package/selenium-webdriver). Example scripts can be found in the `examples` directory.

event-api.json

@@ -0,0 +1,59 @@
+{
+  "body": "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",
+  "resource": "/{proxy+}",
+  "requestContext": {
+    "resourceId": "123456",
+    "apiId": "1234567890",
+    "resourcePath": "/{proxy+}",
+    "httpMethod": "POST",
+    "requestId": "c6af9ac6-7b61-11e6-9a41-93e8deadbeef",
+    "accountId": "123456789012",
+    "identity": {
+      "apiKey": null,
+      "userArn": null,
+      "cognitoAuthenticationType": null,
+      "caller": null,
+      "userAgent": "Custom User Agent String",
+      "user": null,
+      "cognitoIdentityPoolId": null,
+      "cognitoIdentityId": null,
+      "cognitoAuthenticationProvider": null,
+      "sourceIp": "127.0.0.1",
+      "accountId": null
+    },
+    "stage": "prod"
+  },
+  "queryStringParameters": {
+    "foo": "bar"
+  },
+  "headers": {
+    "Via": "1.1 08f323deadbeefa7af34d5feb414ce27.cloudfront.net (CloudFront)",
+    "Accept-Language": "en-US,en;q=0.8",
+    "CloudFront-Is-Desktop-Viewer": "true",
+    "CloudFront-Is-SmartTV-Viewer": "false",
+    "CloudFront-Is-Mobile-Viewer": "false",
+    "X-Forwarded-For": "127.0.0.1, 127.0.0.2",
+    "CloudFront-Viewer-Country": "US",
+    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
+    "Upgrade-Insecure-Requests": "1",
+    "X-Forwarded-Port": "443",
+    "Host": "1234567890.execute-api.us-east-1.amazonaws.com",
+    "X-Forwarded-Proto": "https",
+    "X-Amz-Cf-Id": "aaaaaaaaaae3VYQb9jd-nvCd-de396Uhbp027Y2JvkCPNLmGJHqlaA==",
+    "CloudFront-Is-Tablet-Viewer": "false",
+    "Cache-Control": "max-age=0",
+    "Content-Type": "multipart/form-data; boundary=------------------------76823bec752640d4",
+    "User-Agent": "Custom User Agent String",
+    "CloudFront-Forwarded-Proto": "https",
+    "Accept-Encoding": "gzip, deflate, sdch"
+  },
+  "pathParameters": {
+    "proxy": "/examplepath"
+  },
+  "httpMethod": "POST",
+  "stageVariables": {
+    "baz": "qux"
+  },
+  "isBase64Encoded": true,
+  "path": "/examplepath"
+}

examples/apps/api-gateway.yaml

@@ -0,0 +1,46 @@
+AWSTemplateFormatVersion : '2010-09-09'
+Transform: AWS::Serverless-2016-10-31
+Description: selenium with headless chromium
+Resources:
+  Lambdium:
+    Type: AWS::Serverless::Function
+    Properties:
+      Handler: index.postApiGatewayHandler
+      Runtime: nodejs6.10
+      FunctionName: lambdium
+      Description: headless chromium running selenium
+      # This needs to be fairly large: chromium needs a lot of memory
+      MemorySize: 1156
+      Timeout: 20
+      Environment:
+        Variables:
+          CLEAR_TMP: "true"
+      # packaged lambdium archive @ v0.2
+      CodeUri: <<replace>>
+      Events:
+        RunScript:
+          Properties:
+            Method: POST
+            Path: '/runScript'
+            RestApiId: !Ref Api
+          Type: Api
+  Api:
+    Type: AWS::Serverless::Api
+    Properties:
+      Name: RunScriptAPI
+      StageName: Prod
+      DefinitionBody:
+        swagger: "2.0"
+        schemes:
+          - "https"
+        paths:
+          '/runScript':
+            post:
+              responses: {}
+              x-amazon-apigateway-integration:
+                uri: !Sub arn:aws:apigateway:${AWS::Region}:lambda:path/2015-03-31/functions/${Lambdium.Arn}/invocations
+                passthroughBehavior: "when_no_match"
+                httpMethod: "POST"
+                type: aws_proxy
+        x-amazon-apigateway-binary-media-types:
+          - "*/*"

index.js

@@ -1,10 +1,13 @@
-const webdriver = require('selenium-webdriver');
-const child = require('child_process');
-const fs = require('fs');
 
 const chromium = require('./lib/chromium');
 const sandbox = require('./lib/sandbox');
 const log = require('lambda-log');
+const apiHandler = require('./lib/api-handler');
+
+if (process.env.DEBUG_ENV || process.env.SAM_LOCAL) {
+  log.config.debug = true;
+  log.config.dev = true;
+}
 
 log.info('Loading function');
 
@@ -13,53 +16,21 @@ if (!process.env.CLEAN_SESSIONS) {
   $browser = chromium.createSession();
 }
 
-const parseScriptInput = (event) => {
-  const inputParam = event.Base64Script || process.env.BASE64_SCRIPT;
-  if (typeof inputParam !== 'string') {
-    return null
-  }
-
-  return Buffer.from(inputParam, 'base64').toString('utf8');
-}
-
+// Handler for POST events from API gateway
+// curl -v -F "script=@examples/visitgoogle.js" <<API Gateway URL>>
+exports.postApiGatewayHandler = apiHandler;
+
+// Default function event handler
+// Accepts events:
+// * {"Base64Script": "<<encoded selenium script>>"}
+// * {"pageUrl": "<<URI to visit>>"}
+// Accepts environment variables:
+// * BASE64_SCRIPT: encoded selenium script
+// * PAGE_URL: URI to visit
 exports.handler = (event, context, callback) => {
-  context.callbackWaitsForEmptyEventLoop = false;
-  
-  if (process.env.CLEAN_SESSIONS) {
-    log.info('attempting to clear /tmp directory')
-    log.info(child.execSync('rm -rf /tmp/core*').toString());
-  }
-
-  if (process.env.DEBUG_ENV || process.env.SAM_LOCAL) {
-    log.config.debug = true;
-    log.config.dev = true;
-  }
-
-  if (process.env.LOG_DEBUG) {
-    log.debug(child.execSync('pwd').toString());
-    log.debug(child.execSync('ls -lhtra .').toString());
-    log.debug(child.execSync('ls -lhtra /tmp').toString());  
-  }
-
-  log.info(`Received event: ${JSON.stringify(event, null, 2)}`);
-  
-  // Creates a new session on each event (instead of reusing for performance benefits)
-  if (process.env.CLEAN_SESSIONS) {
-    $browser = chromium.createSession();
-  }
-
-  var opts = {
-    browser: $browser,
-    driver: webdriver
-  };
+  $browser = sandbox.initBrowser(event, context);
 
-  // Determine script to run: either a 1) base64-encoded selenium script or 2) a URL to visit
-  var inputBuffer = parseScriptInput(event);
-  if (inputBuffer !== null) {
-    opts.scriptText = inputBuffer;
-  } else if (event.pageUrl || process.env.PAGE_URL) {
-    opts.pageUrl = event.pageUrl || process.env.PAGE_URL;
-  }
+  var opts = sandbox.buildOptions(event, $browser);
 
   sandbox.executeScript(opts, function(err) {
     if (process.env.LOG_DEBUG) {

lib/api-handler.js

@@ -0,0 +1,67 @@
+const busboy = require('busboy');
+const path = require('path');
+const os = require('os');
+
+const sandbox = require('./sandbox');
+
+module.exports = function(event, context, callback) {
+    $browser = sandbox.initBrowser(event, context);
+    var errorMessage = '';
+    const response = {
+      statusCode: 200,
+      headers: {
+          "Content-Type": 'application/text',
+          "X-Error": errorMessage || null
+      },
+      body: '',
+      isBase64Encoded: false
+    };
+    var body = event.body;
+    if (event.isBase64Encoded) {
+      body = Buffer.from(event.body, 'base64').toString('utf8');
+    }
+    var scriptFile = new Buffer(0)
+    
+
+    const SCRIPT_FIELDNAME = 'script';
+  
+    var contentType = event.headers['Content-Type'] || event.headers['content-type'];
+    var bb = new busboy({ headers: { 'content-type': contentType }});
+    var result = {};
+    bb.on('file', function (fieldname, file, filename, encoding, mimetype) {
+      file.on('data', data => {
+        result.file = data;
+      });
+  
+      file.on('end', () => {
+        result.filename = filename;
+        result.contentType = mimetype;
+      });
+    })
+    .on('finish', () => {
+  
+      // Execute uploaded script
+      var scriptText = result.file.toString();
+      var opts = sandbox.buildOptions(event, $browser);
+      opts.scriptText = scriptText;
+      
+      sandbox.executeScript(opts, function(err, output) {
+        if (err) {
+          response.headers['X-Error'] = err;
+          response.body = err;
+          response.statusCode = 500;
+          return callback(null, response);
+        }
+        response.body = output;
+        callback(null, response);
+      });
+    })
+    .on('error', err => {
+      response.headers['X-Error'] = err;
+      response.body = err;
+      response.statusCode = 500;
+      callback(null, response);
+    });
+  
+    bb.end(body);
+  };

lib/sandbox.js

@@ -1,9 +1,47 @@
 const vm = require('vm');
 const log = require('lambda-log');
+const chromium = require('./chromium');
+const webdriver = require('selenium-webdriver');
+
+exports.initBrowser = function(event, context) {
+  context.callbackWaitsForEmptyEventLoop = false;
+  
+  if (process.env.CLEAN_SESSIONS) {
+    log.info('attempting to clear /tmp directory')
+    log.info(child.execSync('rm -rf /tmp/core*').toString());
+  }
+
+  log.info(`Received event: ${JSON.stringify(event, null, 2)}`);
+  
+  // Creates a new session on each event (instead of reusing for performance benefits)
+  if (process.env.CLEAN_SESSIONS) {
+    $browser = chromium.createSession();
+  }
+  return $browser;
+};
+
+exports.buildOptions = (event, browser) => {
+  var opts = opts = {
+    browser: $browser,
+    driver: webdriver
+  };
+
+  const inputParam = event.Base64Script || process.env.BASE64_SCRIPT;
+  if (typeof inputParam !== 'string') {
+    opts.pageUrl = event.pageUrl || process.env.PAGE_URL;
+    return opts;
+  }
+
+  var inputBuffer = Buffer.from(inputParam, 'base64').toString('utf8');
+  opts.scriptText = inputBuffer;
+
+  return opts;
+};
 
 exports.executeScript = function(opts = {}, cb) {
   const browser = opts.browser;
   const driver = opts.driver;
+  var output = '';
   var scriptText = opts.scriptText;
 
   // Just visit a web page if a script isn't specified
@@ -20,6 +58,7 @@ exports.executeScript = function(opts = {}, cb) {
     log: function(){
       var args = Array.prototype.slice.call(arguments);
       args.unshift('[lambdium-selenium]');
+      output = `${output}\n${args.join(' ')}`;
       console.log.apply(console, args);
     }
   };
@@ -46,15 +85,15 @@ exports.executeScript = function(opts = {}, cb) {
   // Reuse existing session, likely some edge cases around this...
   if (process.env.CLEAN_SESSIONS) {
     browser.quit().then(function() {
-      cb(null);
+      cb(null, output);
     });
   } else {
     browser.manage().deleteAllCookies().then(function() {
       return browser.get('about:blank').then(function() {
-        cb(null);
+        cb(null, output);
       });
     }).catch(function(err) {
-      cb(err);
+      cb(err, output);
     });
   }
 }