@govtechsg/oobee 0.10.65 → 0.10.68

package/Dockerfile

@@ -1,6 +1,6 @@
 # Use Microsoft Playwright image as base image
 # Node version is v22
-FROM mcr.microsoft.com/playwright:v1.50.1-noble
+FROM mcr.microsoft.com/playwright:v1.55.0-noble
 
 # Installation of packages for oobee and runner (locked versions from build log)
 RUN apt-get update && apt-get install -y \

package/README.md

@@ -562,6 +562,26 @@ For details on which accessibility scan results triggers a "Must Fix" / "Good to
 
 Please refer to the information below to assist in debugging. Most errors below are due to the switching between Node.js versions.
 
+### URL Validation Errors
+The following URL and file validation error codes are provided to troubleshoot the scan.
+
+| Code | Error Name           | Error Message                                                                 | Troubleshooting Steps |
+|------|----------------------|-------------------------------------------------------------------------------|------------------------|
+| 0    | success              | (undefined)                                                                     | No action needed. Connection successful. |
+| 11   | invalidUrl           | Invalid URL. Please check and try again.                                | • Ensure the URL starts with `http://` or `https://`.<br>• Check for typos in the URL. |
+| 12   | cannotBeResolved     | URL cannot be accessed. Please verify whether the website exists.     | • Confirm the domain name is correct.<br>• Check DNS resolution with `ping` or `nslookup`.<br>• Ensure the site is publicly accessible (not behind VPN/firewall). |
+| 14   | systemError          | Something went wrong when verifying the URL. Please try again in a few minutes. If this issue persists, please contact the Oobee team.          | • Retry after a few minutes.<br>• Check internet connection.<br>• If persistent, report as a system issue. |
+| 15   | notASitemap          | Invalid sitemap URL format. Please enter a valid sitemap URL ending with .XML e.g. https://www.example.com/sitemap.xml.                                                | • Ensure the URL points to a valid XML sitemap.<br>• View [Examples of sitemaps sitemaps.org - Protocol](https://www.sitemaps.org/protocol.html)<br>• Test the URL in a browser to confirm it returns XML. |
+| 16   | unauthorised         | Login required. Please enter your credentials and try again.                                       | • Check if the site requires username/password.<br>• Provide credentials in Oobee if supported. |
+| 17   | browserError         | Incompatible browser. Please ensure you are using Chrome or Edge browser. | • Install the latest version of Chrome or Edge.|
+| 18   | sslProtocolError     | SSL certificate  error. Please check the SSL configuration of your website and try again. | • Verify SSL certificate validity (not expired, issued by trusted CA).<br>• Check for mismatched TLS versions or cipher issues.<br>• Use an SSL checker tool (e.g., Qualys SSL Labs). |
+| 19   | notALocalFile        | Uploaded file format is incorrect. Please upload a HTML, PDF, XML or TXT file.                  | • Verify the file format.<br>• Ensure you are selecting `.html`, `.pdf`, `.xml`, or `.txt`. |
+| 20   | notAPdf              | URL/file format is incorrect. Please upload a PDF file.                                       | • Ensure the file ends with `.pdf`.<br>• Open the file manually to confirm it is a valid PDF. |
+| 21   | notASupportedDocument| Uploaded file format is incorrect. Please upload a HTML, PDF, XML or TXT file.                 | • Confirm file format.<br>• Convert to a supported type if necessary. |
+| 22   | connectionRefused    | Connection refused. Please try again in a few minutes. If this issue persists, please contact the Oobee team.                                   | • Check if the server is running.<br>• Verify firewall settings.<br>• Retry after a short interval. |
+| 23   | timedOut             | Request timed out. Please try again in a few minutes. If this issue persists, please contact the Oobee team.                                    | • Check your internet speed and stability.<br>• Retry when the server load is lower. |
+
+
 ### Incompatible Node.js versions
 
 **Issue**: When your Node.js version is incompatible, you may face the following syntax error.

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@govtechsg/oobee",
   "main": "dist/npmIndex.js",
-  "version": "0.10.65",
+  "version": "0.10.68",
   "type": "module",
   "author": "Government Technology Agency <info@tech.gov.sg>",
   "dependencies": {
@@ -22,10 +22,11 @@
     "jsdom": "^21.1.2",
     "jszip": "^3.10.1",
     "lodash": "^4.17.21",
+    "mime": "^4.0.7",
     "mime-types": "^2.1.35",
     "minimatch": "^9.0.3",
     "pdfjs-dist": "github:veraPDF/pdfjs-dist#v4.4.168-taggedPdf-0.1.20",
-    "playwright": "1.50.1",
+    "playwright": "^1.55.0",
     "prettier": "^3.1.0",
     "print-message": "^3.0.1",
     "safe-regex": "^2.1.1",
@@ -48,6 +49,7 @@
     "@types/fs-extra": "^11.0.4",
     "@types/inquirer": "^9.0.7",
     "@types/lodash": "^4.17.7",
+    "@types/mime": "^3.0.4",
     "@types/mime-types": "^2.1.4",
     "@types/safe-regex": "^1.1.6",
     "@types/validator": "^13.11.10",

package/scripts/install_oobee_dependencies.command

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-NODE_VERSION="22.13.1"
+NODE_VERSION="22.19.0"
 
 # Get current shell command
 SHELL_COMMAND=$(ps -o comm= -p $$)

package/scripts/install_oobee_dependencies.ps1

@@ -9,11 +9,11 @@ $ErrorActionPreference = 'Stop'
 # Install NodeJS binaries
 if (-Not (Test-Path nodejs-win\node.exe)) {
     Write-Output "Downloading Node"
-    Invoke-WebRequest -o ./nodejs-win.zip "https://nodejs.org/dist/v22.13.1/node-v22.13.1-win-x64.zip"     
+    Invoke-WebRequest -o ./nodejs-win.zip "https://nodejs.org/dist/v22.19.0/node-v22.19.0-win-x64.zip"     
     
     Write-Output "Unzip Node"
     Expand-Archive .\nodejs-win.zip -DestinationPath .
-    Rename-Item node-v22.13.1-win-x64 -NewName nodejs-win
+    Rename-Item node-v22.19.0-win-x64 -NewName nodejs-win
     Remove-Item -Force .\nodejs-win.zip
 }
 

package/src/cli.ts

@@ -211,18 +211,19 @@ Usage: npm run cli -- -c <crawler> -d <device> -w <viewport> -u <url> OPTIONS`,
   .parse() as unknown as Answers;
 
 const scanInit = async (argvs: Answers): Promise<string> => {
-  let isCustomFlow = false;
-  if (argvs.scanner === ScannerTypes.CUSTOM) {
-    isCustomFlow = true;
-  }
-
   const updatedArgvs = { ...argvs };
 
   // Cannot use data.browser and data.isHeadless as the connectivity check comes first before prepareData
   setHeadlessMode(updatedArgvs.browserToRun, updatedArgvs.headless);
   const statuses = constants.urlCheckStatuses;
 
-  const data = await prepareData(updatedArgvs);
+  let data;
+  try {
+    data = await prepareData(updatedArgvs);
+  } catch (e) {
+    consoleLogger.error(`Error preparing data: ${e.message}\n${e.stack}`);
+    cleanUpAndExit(1);
+  }
 
   // Executes cleanUp script if error encountered
   listenForCleanUp(data.randomToken);
@@ -233,83 +234,27 @@ const scanInit = async (argvs: Answers): Promise<string> => {
     data.browser,
     data.userDataDirectory,
     data.playwrightDeviceDetailsObject,
-    data.extraHTTPHeaders
+    data.extraHTTPHeaders,
+    data.fileTypes
   );
 
   if (res.httpStatus) consoleLogger.info(`Connectivity Check HTTP Response Code: ${res.httpStatus}`);
 
-  switch (res.status) {
-    case statuses.success.code: {
-      data.url = res.url;
-      if (process.env.OOBEE_VALIDATE_URL) {
-        console.log('Url is valid');
-        cleanUpAndExit(0, data.randomToken);
-      }
-
-      break;
-    }
-    case statuses.unauthorised.code: {
-      printMessage([statuses.unauthorised.message], messageOptions);
-      consoleLogger.info(statuses.unauthorised.message);
-      cleanUpAndExit(res.status);
-    }
-    case statuses.cannotBeResolved.code: {
-      printMessage([statuses.cannotBeResolved.message], messageOptions);
-      consoleLogger.info(statuses.cannotBeResolved.message);
-      cleanUpAndExit(res.status);
-    }
-    case statuses.systemError.code: {
-      printMessage([statuses.systemError.message], messageOptions);
-      consoleLogger.info(statuses.systemError.message);
-      cleanUpAndExit(res.status);
-    }
-    case statuses.invalidUrl.code: {
-      if (
-        updatedArgvs.scanner !== ScannerTypes.SITEMAP &&
-        updatedArgvs.scanner !== ScannerTypes.LOCALFILE
-      ) {
-        printMessage([statuses.invalidUrl.message], messageOptions);
-        consoleLogger.info(statuses.invalidUrl.message);
-        cleanUpAndExit(res.status);
-      }
-
-      const finalFilePath = getFileSitemap(updatedArgvs.url);
-      if (finalFilePath) {
-        data.isLocalFileScan = true;
-        data.url = finalFilePath;
-
-        if (process.env.OOBEE_VALIDATE_URL) {
-          console.log('Url is valid');
-          cleanUpAndExit(0);
-        }
-      } else if (updatedArgvs.scanner === ScannerTypes.LOCALFILE) {
-        printMessage([statuses.notALocalFile.message], messageOptions);
-        consoleLogger.info(statuses.notALocalFile.message);
-        cleanUpAndExit(statuses.notALocalFile.code);
-      } else if (updatedArgvs.scanner !== ScannerTypes.SITEMAP) {
-        printMessage([statuses.notASitemap.message], messageOptions);
-        consoleLogger.info(statuses.notASitemap.message);
-        cleanUpAndExit(statuses.notASitemap.code);
-      }
-      break;
-    }
-    case statuses.notASitemap.code: {
-      printMessage([statuses.notASitemap.message], messageOptions);
-      consoleLogger.info(statuses.notASitemap.message);
-      cleanUpAndExit(res.status);
-    }
-    case statuses.notALocalFile.code: {
-      printMessage([statuses.notALocalFile.message], messageOptions);
-      consoleLogger.info(statuses.notALocalFile.message);
-      cleanUpAndExit(res.status);
-    }
-    case statuses.browserError.code: {
-      printMessage([statuses.browserError.message], messageOptions);
-      consoleLogger.info(statuses.browserError.message);
-      cleanUpAndExit(res.status);
+  if (res.status === statuses.success.code) {
+    data.url = res.url;
+    if (process.env.OOBEE_VALIDATE_URL) {
+      consoleLogger.info('Url is valid');
+      cleanUpAndExit(0, data.randomToken);
+      return;
     }
-    default:
-      break;
+    // fall through (continue normal flow after success)
+  } else {
+    const match = Object.values(statuses).find((s: any) => s.code === res.status);
+    const msg = match && 'message' in match ? match.message : 'Unknown error';
+    printMessage([msg], messageOptions);
+    consoleLogger.info(msg);
+    cleanUpAndExit(res.status);
+    return;
   }
 
   if (process.env.OOBEE_VERBOSE) {

package/src/constants/common.ts

@@ -14,6 +14,7 @@ import url, { fileURLToPath, pathToFileURL } from 'url';
 import safe from 'safe-regex';
 import * as https from 'https';
 import os from 'os';
+import mime from 'mime';
 import { minimatch } from 'minimatch';
 import { globSync, GlobOptionsWithFileTypesFalse } from 'glob';
 import { LaunchOptions, Locator, Page, devices, webkit } from 'playwright';
@@ -27,6 +28,8 @@ import constants, {
   // Legacy code end - Google Sheets submission
   ScannerTypes,
   BrowserTypes,
+  FileTypes,
+  getEnumKey,
 } from './constants.js';
 import { consoleLogger } from '../logs.js';
 import { isUrlPdf } from '../crawlers/commonCrawlerFunc.js';
@@ -172,9 +175,14 @@ export const messageOptions = {
 };
 
 const urlOptions = {
-  protocols: ['http', 'https'],
+  // http and https for normal scans, file for local file scan
+  protocols: ['http', 'https', 'file'],
   require_protocol: true,
   require_tld: false,
+  require_host: false,
+  // being explicit; fragments/queries are fine for local files
+  allow_fragments: true,
+  allow_query_components: true,
 };
 
 const queryCheck = (s: string) => document.createDocumentFragment().querySelector(s);
@@ -187,8 +195,9 @@ export const isSelectorValid = (selector: string): boolean => {
   return true;
 };
 
-// Refer to NPM validator's special characters under sanitizers for escape()
-const blackListCharacters = '\\<>&\'"';
+// Don't sanitise for now as we have changed the logic for URL validation / local file scan
+// Only use this when we find characters to validate against
+const blackListCharacters = '';
 
 export const validateXML = (content: string): { isValid: boolean; parsedContent: string } => {
   let isValid: boolean;
@@ -271,12 +280,25 @@ export const isInputValid = (inputString: string): boolean => {
 export const sanitizeUrlInput = (url: string): { isValid: boolean; url: string } => {
   // Sanitize that there is no blacklist characters
   const sanitizeUrl = validator.blacklist(url, blackListCharacters);
-  if (validator.isURL(sanitizeUrl, urlOptions)) {
+  if (url.toLowerCase().startsWith('file://') || validator.isURL(sanitizeUrl, urlOptions)) {
     return { isValid: true, url: sanitizeUrl };
   }
   return { isValid: false, url: sanitizeUrl };
 };
 
+const isAllowedContentType = (ct: string): boolean => {
+  const c = (ct || '').toLowerCase();
+  return (
+    c.startsWith('text/html') ||              // html
+    c.startsWith('application/xhtml+xml') ||  // xhtml
+    c.startsWith('text/plain') ||             // txt
+    c.startsWith('application/xml') ||        // xml
+    c.startsWith('text/xml')        ||        // xml (alt)
+    c.startsWith('application/pdf')           // pdf
+  );
+};
+
+
 const checkUrlConnectivityWithBrowser = async (
   url: string,
   browserToRun: string,
@@ -292,6 +314,44 @@ const checkUrlConnectivityWithBrowser = async (
     return res;
   }
 
+    // STEP 1: For local file scans
+  let contentType = '';
+
+  const protocol = new URL(url).protocol;
+
+  if (protocol !== 'http:' && protocol !== 'https:') {
+    try {
+      const filePath = fileURLToPath(url);
+      const stat = fs.statSync(filePath);
+
+      if (!stat.isFile()) {
+        res.status = constants.urlCheckStatuses.notALocalFile.code;
+        return res;
+      }
+
+      const statusCode = 200;
+      contentType = mime.getType(filePath) || 'application/octet-stream';
+
+      if (!isAllowedContentType(contentType)) {
+        res.status = constants.urlCheckStatuses.notASupportedDocument.code;
+        return res;
+      }
+
+      // Short-circuit for pdfs
+      if (contentType.includes('pdf')) {
+        res.status = constants.urlCheckStatuses.success.code;
+        res.httpStatus = statusCode;
+        res.url = url;
+        res.content = '%PDF-'; // Avoid putting the binary in memory
+        return res;
+      }
+    } catch (e) {
+      consoleLogger.info(`Local file check failed: ${e.message}`);
+      res.status = constants.urlCheckStatuses.systemError.code;
+      return res;
+    }
+  }
+
   // Ensure Accept header for non-html content fallback
   extraHTTPHeaders['Accept'] ||= 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8';
 
@@ -302,6 +362,7 @@ const checkUrlConnectivityWithBrowser = async (
     browserContext = await constants.launcher.launchPersistentContext(clonedDataDir, {
       ...(extraHTTPHeaders && { extraHTTPHeaders }),
       ignoreHTTPSErrors: true,
+      headless: true,
       ...getPlaywrightLaunchOptions(browserToRun),
       ...playwrightDeviceDetailsObject,
       ...(process.env.OOBEE_DISABLE_BROWSER_DOWNLOAD && { acceptDownloads: false }),
@@ -317,77 +378,94 @@ const checkUrlConnectivityWithBrowser = async (
   try {
     const page = await browserContext.newPage();
 
-    // STEP 1: HEAD request before actual navigation
-    let statusCode = 0;
-    let contentType = '';
-    let disposition = '';
-
+    // Block native Chrome download UI
     try {
-      const headResp = await page.request.fetch(url, {
-        method: 'HEAD',
-        headers: extraHTTPHeaders,
-      });
-
-      statusCode = headResp.status();
-      contentType = headResp.headers()['content-type'] || '';
-      disposition = headResp.headers()['content-disposition'] || '';
+      const cdp = await browserContext.newCDPSession(page as any);
+      await cdp.send('Page.setDownloadBehavior', { behavior: 'deny' });
+    } catch (e) {
+      consoleLogger.info(`Unable to set download deny: ${(e as Error).message}`);
+    }
 
-      // If it looks like a downloadable file, skip goto entirely
-      if (
-        contentType.includes('pdf') ||
-        contentType.includes('octet-stream') ||
-        disposition.includes('attachment')
-      ) {
-        res.status = statusCode === 401
-          ? constants.urlCheckStatuses.unauthorised.code
-          : constants.urlCheckStatuses.success.code;
+    // STEP 2: Navigate (follows server-side redirects)
+    page.once('download', () => { 
+      res.status = constants.urlCheckStatuses.notASupportedDocument.code;
+      return res;
+    });
+    
+    const response = await page.goto(url, {
+      timeout: 15000,
+      waitUntil: 'domcontentloaded', // enough to get status + allow potential client redirects to kick in
+    });
 
-        res.httpStatus = statusCode;
-        res.url = url;
-        res.content = ''; // Don't try to render binary
+    // Give client-side redirects (meta refresh / JS location.*) a moment
+    try {
+      await page.waitForLoadState('networkidle', { timeout: 8000 });
+    } catch {
+      consoleLogger.info('networkidle not reached; proceeding with verification GET');
+    }
 
-        await browserContext.close();
-        return res;
-      }
+    // STEP 3: Verify final URL with a GET (follows redirects)
+    const finalUrl = page.url();
+    let verifyResp = response;
+    try {
+      verifyResp = await page.request.fetch(finalUrl, {
+        method: 'GET',
+        headers: extraHTTPHeaders,
+      });
     } catch (e) {
-      consoleLogger.info(`HEAD request failed: ${e.message}`);
-      res.status = constants.urlCheckStatuses.systemError.code;
-      await browserContext.close();
-      return res;
+      consoleLogger.info(`Verification GET failed, falling back to navigation response: ${e.message}`);
     }
 
-    // STEP 2: Safe to proceed with navigation
-    const response = await page.goto(url, {
-      timeout: 30000,
-      waitUntil: 'commit', // Don't wait for full load
-    });
+    // Prefer verification GET; fall back to nav response
+    const finalStatus = verifyResp?.status?.() ?? response?.status?.() ?? 0;
+    const headers = (verifyResp?.headers?.() ?? response?.headers?.()) || {};
+    contentType = headers['content-type'] || '';
 
-    const finalStatus = statusCode || (response?.status?.() ?? 0);
-    res.status = finalStatus === 401
-      ? constants.urlCheckStatuses.unauthorised.code
-      : constants.urlCheckStatuses.success.code;
+    if (!isAllowedContentType(contentType)) {
+      res.status = constants.urlCheckStatuses.notASupportedDocument.code;
+      return res;
+    } 
 
     res.httpStatus = finalStatus;
-    res.url = page.url();
+    res.url = finalUrl;
 
-    contentType = response?.headers()?.['content-type'] || '';
+    if (finalStatus === 401) {
+      res.status = constants.urlCheckStatuses.unauthorised.code;
+    } else if (finalStatus >= 200 && finalStatus < 400) {
+      res.status = constants.urlCheckStatuses.success.code;
+    } else if (finalStatus === 405 || finalStatus === 501) {
+      // Some origins 405/501 but the browser-rendered page is still reachable after client redirects.
+      // As a last resort, consider DOM presence as success if we actually have a document.
+      const hasDOM = await page.evaluate(() => !!document && !!document.documentElement);
+      res.status = hasDOM ? constants.urlCheckStatuses.success.code : constants.urlCheckStatuses.systemError.code;
+    } else {
+      res.status = constants.urlCheckStatuses.systemError.code;
+    }
+
+    // Content handling
     if (contentType.includes('pdf') || contentType.includes('octet-stream')) {
-      res.content = ''; // Avoid triggering render/download
+      res.content = '%PDF-'; // avoid binary in memory / download
     } else {
       try {
-        await page.waitForLoadState('networkidle', { timeout: 10000 });
-      } catch {
-        consoleLogger.info('Unable to detect networkidle');
-      }
-
+        // Try to get a stable DOM; don't fail the check if it times out
+        await page.waitForLoadState('domcontentloaded', { timeout: 5000 });
+      } catch {}
       res.content = await page.content();
     }
 
   } catch (error) {
     if (error.message.includes('net::ERR_INVALID_AUTH_CREDENTIALS')) {
       res.status = constants.urlCheckStatuses.unauthorised.code;
+    } else if (error.message.includes('net::ERR_NAME_NOT_RESOLVED')) {
+      res.status = constants.urlCheckStatuses.cannotBeResolved.code;
+    } else if (error.message.includes('net::ERR_CONNECTION_REFUSED')) {
+      res.status = constants.urlCheckStatuses.connectionRefused.code;
+    } else if (error.message.includes('net::ERR_TIMED_OUT')) {
+      res.status = constants.urlCheckStatuses.timedOut.code;
+    } else if (error.message.includes('net::ERR_SSL_PROTOCOL_ERROR')) {
+      res.status = constants.urlCheckStatuses.sslProtocolError.code;
     } else {
-      console.log(error);
+      consoleLogger.error(error);
       res.status = constants.urlCheckStatuses.systemError.code;
     }
   } finally {
@@ -397,6 +475,16 @@ const checkUrlConnectivityWithBrowser = async (
   return res;
 };
 
+export const isPdfContent = (content: Buffer | string): boolean => {
+  let header: string;
+  if (Buffer.isBuffer(content)) {
+    header = content.toString('utf8', 0, 5);
+  } else {
+    header = content.substring(0, 5);
+  }
+  return header === '%PDF-';
+};
+
 export const isSitemapContent = (content: string) => {
   const { isValid } = validateXML(content);
   if (isValid) {
@@ -426,27 +514,43 @@ export const checkUrl = async (
   clonedDataDir: string,
   playwrightDeviceDetailsObject: DeviceDescriptor,
   extraHTTPHeaders: Record<string, string>,
+  fileTypes: FileTypes
 ) => {
+
   const res = await checkUrlConnectivityWithBrowser(
-    url,
-    browser,
-    clonedDataDir,
-    playwrightDeviceDetailsObject,
-    extraHTTPHeaders,
+      url,
+      browser,
+      clonedDataDir,
+      playwrightDeviceDetailsObject,
+      extraHTTPHeaders,
   );
 
-  if (
-    res.status === constants.urlCheckStatuses.success.code &&
-    (scanner === ScannerTypes.SITEMAP || scanner === ScannerTypes.LOCALFILE)
-  ) {
-    const isSitemap = isSitemapContent(res.content);
+  // If response is 200 (meaning no other code was set earlier)
+  if (res.status === constants.urlCheckStatuses.success.code) {
+
+    // Check if document is pdf type
+    const isPdf = isPdfContent(res.content);
+
+    // Check if only HTML document is allowed to be scanned
+    if (fileTypes === FileTypes.HtmlOnly && isPdf) {
+      res.status = constants.urlCheckStatuses.notASupportedDocument.code;
+    
+    // Check if only PDF document is allowed to be scanned
+    } else if (fileTypes === FileTypes.PdfOnly && !isPdf) {
+      res.status = constants.urlCheckStatuses.notAPdf.code;
 
-    if (!isSitemap && scanner === ScannerTypes.LOCALFILE) {
-      res.status = constants.urlCheckStatuses.notALocalFile.code;
-    } else if (!isSitemap) {
-      res.status = constants.urlCheckStatuses.notASitemap.code;
+    // Check if sitemap is expected
+    } else if (scanner === ScannerTypes.SITEMAP) {
+      const isSitemap = isSitemapContent(res.content);
+
+      if (!isSitemap) {
+        res.status = constants.urlCheckStatuses.notASitemap.code;
+      }
     }
+
+    // else proceed as normal
   }
+  
   return res;
 };
 
@@ -486,7 +590,7 @@ export const prepareData = async (argv: Answers): Promise<Data> => {
     viewportWidth,
     maxpages,
     strategy,
-    isLocalFileScan = false,
+    isLocalFileScan = argv.scanner === ScannerTypes.LOCALFILE,
     browserToRun,
     nameEmail,
     customFlowLabel,
@@ -511,30 +615,34 @@ export const prepareData = async (argv: Answers): Promise<Data> => {
   let username = '';
   let password = '';
 
+  // If a file path is provided
   if (isFilePath(url)) {
-    argv.isLocalFileScan = true;
-  }
+    // Set is as local file scan if not already so
+    isLocalFileScan = true;
 
-  // Remove credentials from URL if not a local file scan
-  url = argv.isLocalFileScan 
-    ? url 
-    : (() => {
-        const temp = new URL(url);
-        username = temp.username;
-        password = temp.password;
+    // Convert to absolute path
+    url = path.resolve(url);
 
-        if (username !== '' || password !== '') {
-          extraHTTPHeaders['Authorization'] = `Basic ${Buffer.from(`${username}:${password}`).toString('base64')}`;
-        } 
+    // Convert to file:// URL
+    url = convertPathToLocalFile(url);
+  } else {
+    // Check URL for basic auth embedded and move it to extraHTTPHeaders
+    const temp = new URL(url);
+    username = temp.username;
+    password = temp.password;
 
-        temp.username = '';
-        temp.password = '';
-        return temp.toString();
-      })();
+    if (username !== '' || password !== '') {
+      extraHTTPHeaders['Authorization'] = `Basic ${Buffer.from(`${username}:${password}`).toString('base64')}`;
+    } 
+
+    temp.username = '';
+    temp.password = '';
+    url = temp.toString();
+  }
 
   // construct filename for scan results
   const [date, time] = new Date().toLocaleString('sv').replaceAll(/-|:/g, '').split(' ');
-  const domain = argv.isLocalFileScan ? path.basename(argv.url) : new URL(argv.url).hostname;
+  const domain = isLocalFileScan ? path.basename(url) : new URL(url).hostname;
 
   const sanitisedLabel = customFlowLabel ? `_${customFlowLabel.replaceAll(' ', '_')}` : '';
   let resultFilename: string;
@@ -586,7 +694,7 @@ export const prepareData = async (argv: Answers): Promise<Data> => {
     customFlowLabel,
     specifiedMaxConcurrency,
     randomToken: resultFilename,
-    fileTypes,
+    fileTypes: FileTypes[getEnumKey(FileTypes, fileTypes) as keyof typeof FileTypes],
     blacklistedPatternsFilename,
     includeScreenshots: !(additional === 'none'),
     metadata,
@@ -1335,26 +1443,28 @@ export const cloneChromeProfiles = (randomToken: string): string => {
   destDir = path.join(baseDir, `oobee-${randomToken}`);
 
   if (fs.existsSync(destDir)) {
-      deleteClonedChromeProfiles(randomToken);
-  }
-
-  if (!fs.existsSync(destDir)) {
-    fs.mkdirSync(destDir, { recursive: true });
-  }
+    // Don't delete since it will be handled at the end of the scan  
+    // deleteClonedChromeProfiles(randomToken);
+    // Assume it cloned and don't re-clone
+  } else {
+    if (!fs.existsSync(destDir)) {
+      fs.mkdirSync(destDir, { recursive: true });
+    }
 
-  const baseOptions = {
-    cwd: baseDir,
-    recursive: true,
-    absolute: true,
-    nodir: true,
-  };
-  const cloneLocalStateFileSuccess = cloneLocalStateFile(baseOptions, destDir);
-  if (cloneChromeProfileCookieFiles(baseOptions, destDir) && cloneLocalStateFileSuccess) {
-    return destDir;
-  }
+    const baseOptions = {
+      cwd: baseDir,
+      recursive: true,
+      absolute: true,
+      nodir: true,
+    };
+    const cloneLocalStateFileSuccess = cloneLocalStateFile(baseOptions, destDir);
+    if (cloneChromeProfileCookieFiles(baseOptions, destDir) && cloneLocalStateFileSuccess) {
+      return destDir;
+    }
 
-  consoleLogger.error('Failed to clone Chrome profiles. You may be logged out of your accounts.');
+    consoleLogger.error('Failed to clone Chrome profiles. You may be logged out of your accounts.');
 
+  }
   // For future reference, return a null instead to halt the scan
   return destDir;
 };
@@ -1371,10 +1481,11 @@ export const cloneChromiumProfiles = (randomToken: string): string => {
   destDir = path.join(baseDir, `oobee-${randomToken}`);
 
   if (fs.existsSync(destDir)) {
-      deleteClonedChromiumProfiles(randomToken);
-  }
-
-  if (!fs.existsSync(destDir)) {
+     
+    // Don't delete since it will be handled at the end of the scan  
+    // deleteClonedChromiumProfiles(randomToken);
+    // Assume it cloned and don't re-clone
+  } else {
     fs.mkdirSync(destDir, { recursive: true });
   }
 
@@ -1401,26 +1512,31 @@ export const cloneEdgeProfiles = (randomToken: string): string => {
   destDir = path.join(baseDir, `oobee-${randomToken}`);
 
   if (fs.existsSync(destDir)) {
-      deleteClonedEdgeProfiles(randomToken);
-  }
 
-  if (!fs.existsSync(destDir)) {
-    fs.mkdirSync(destDir, { recursive: true });
-  }
+    // Don't delete since it will be handled at the end of the scan  
+    // deleteClonedEdgeProfiles(randomToken);
+    // Assume it cloned and don't re-clone
 
-  const baseOptions = {
-    cwd: baseDir,
-    recursive: true,
-    absolute: true,
-    nodir: true,
-  };
+  } else {
+    if (!fs.existsSync(destDir)) {
+      fs.mkdirSync(destDir, { recursive: true });
+    }
 
-  const cloneLocalStateFileSuccess = cloneLocalStateFile(baseOptions, destDir);
-  if (cloneEdgeProfileCookieFiles(baseOptions, destDir) && cloneLocalStateFileSuccess) {
-    return destDir;
-  }
+    const baseOptions = {
+      cwd: baseDir,
+      recursive: true,
+      absolute: true,
+      nodir: true,
+    };
+
+    const cloneLocalStateFileSuccess = cloneLocalStateFile(baseOptions, destDir);
+    if (cloneEdgeProfileCookieFiles(baseOptions, destDir) && cloneLocalStateFileSuccess) {
+      return destDir;
+    }
+
+    consoleLogger.error('Failed to clone Edge profiles. You may be logged out of your accounts.');
 
-  consoleLogger.error('Failed to clone Edge profiles. You may be logged out of your accounts.');
+  }
 
   // For future reference, return a null instead to halt the scan
   return destDir;
@@ -1863,10 +1979,13 @@ export const isFilePath = (url: string): boolean => {
   const driveLetterPattern = /^[A-Z]:/i;
   const backslashPattern = /\\/;
   return (
-    url.startsWith('file://') ||
     url.startsWith('/') ||
     driveLetterPattern.test(url) ||
-    backslashPattern.test(url)
+    backslashPattern.test(url) ||
+    url.startsWith('./') ||
+    url.startsWith('../') ||
+    url.startsWith('.\\') ||
+    url.startsWith('..\\')
   );
 };
 

package/src/constants/constants.ts

@@ -252,6 +252,16 @@ export enum ScannerTypes {
 }
 /* eslint-enable no-unused-vars */
 
+export enum FileTypes {
+  All = 'all',
+  PdfOnly = 'pdf-only',
+  HtmlOnly = 'html-only',
+}
+
+export function getEnumKey<E extends Record<string, string>>(enumObj: E, value: string): keyof E | undefined {
+  return (Object.keys(enumObj) as Array<keyof E>).find(k => enumObj[k] === value);
+}
+
 export const guiInfoStatusTypes = {
   SCANNED: 'scanned',
   SKIPPED: 'skipped',
@@ -379,31 +389,28 @@ const wcagLinks = {
 
 const urlCheckStatuses = {
   success: { code: 0 },
-  invalidUrl: { code: 11, message: 'Invalid URL or URL is not using http or https.' },
-  cannotBeResolved: {
-    code: 12,
-    message:
-      'Provided URL cannot be accessed. Please verify your internet connectivity and the correctness of the domain.',
-  },
+  invalidUrl: { code: 11, message: 'Invalid URL. Please check and try again.' },
+  cannotBeResolved: { code: 12, message: 'URL cannot be accessed. Please verify whether the website exists.' },
   errorStatusReceived: {
     // unused for now
     code: 13,
     message: 'Provided URL cannot be accessed. Server responded with code ', // append it with the response code received,
   },
-  systemError: {
-    code: 14,
-    message: 'Something went wrong when verifying the URL. Please try again later.',
-  },
-  notASitemap: { code: 15, message: 'Provided URL is not a sitemap.' },
-  unauthorised: { code: 16, message: 'Provided URL needs basic authorisation.' },
+  systemError: { code: 14, message: 'Something went wrong when verifying the URL. Please try again in a few minutes. If this issue persists, please contact the Oobee team.'},
+  notASitemap: { code: 15, message: 'Invalid sitemap URL format. Please enter a valid sitemap URL ending with .XML e.g. https://www.example.com/sitemap.xml.' },
+  unauthorised: { code: 16, message: 'Login required. Please enter your credentials and try again.' },
+  // browserError means engine could not find a browser to run the scan
   browserError: {
     code: 17,
     message:
-      'No browser available to run scans. Please ensure you have Chrome or Edge (for Windows only) installed.',
+      'Incompatible browser. Please ensure you are using Chrome or Edge browser.',
   },
-  axiosTimeout: { code: 18, message: 'Axios timeout exceeded. Falling back on browser checks.' },
-  notALocalFile: { code: 19, message: 'Provided filepath is not a local html or sitemap file.' },
-  terminationRequested: { code: 15, message: 'Termination requested.' }
+  sslProtocolError: { code: 18, message: 'SSL certificate  error. Please check the SSL configuration of your website and try again.' },
+  notALocalFile: { code: 19, message: 'Uploaded file format is incorrect. Please upload a HTML, PDF, XML or TXT file.' },
+  notAPdf: { code: 20, message: 'URL/file format is incorrect. Please upload a PDF file.' },
+  notASupportedDocument: { code: 21, message: 'Uploaded file format is incorrect. Please upload a HTML, PDF, XML or TXT file.' },
+  connectionRefused: { code: 22, message: 'Connection refused. Please try again in a few minutes. If this issue persists, please contact the Oobee team.' },
+  timedOut: { code: 23, message: 'Request timed out. Please try again in a few minutes. If this issue persists, please contact the Oobee team.' },
 };
 
 /* eslint-disable no-unused-vars */

package/src/constants/questions.ts

@@ -3,7 +3,6 @@ import { Answers } from '../index.js';
 import { getUserDataTxt, randomThreeDigitNumberString, setHeadlessMode } from '../utils.js';
 import {
   checkUrl,
-  deleteClonedProfiles,
   getBrowserToRun,
   getPlaywrightDeviceDetailsObject,
   getUrlMessage,
@@ -14,7 +13,7 @@ import {
   validateCustomFlowLabel,
   parseHeaders,
 } from './common.js';
-import constants, { BrowserTypes, ScannerTypes } from './constants.js';
+import constants, { BrowserTypes, FileTypes, ScannerTypes } from './constants.js';
 import { random } from 'lodash';
 
 const userData = getUserDataTxt();
@@ -58,6 +57,13 @@ const startScanQuestions = [
     name: 'viewportWidth',
     message: 'Specify width of the viewport in pixels (e.g. 360):',
     when: (answers: Answers) => answers.customDevice === 'Specify viewport',
+    filter: (input) => {
+    if (input === '' || input === undefined) {
+      return undefined; // return nothing instead of NaN
+    }
+    const n = Number(input);
+    return Number.isInteger(n) ? n : undefined;
+    },
     validate: (viewport: number) => {
       if (!Number.isInteger(viewport)) {
         return 'Invalid viewport width. Please provide an integer.';
@@ -117,39 +123,16 @@ const startScanQuestions = [
         clonedBrowserDataDir,
         playwrightDeviceDetailsObject,
         parseHeaders(answers.header),
+        FileTypes.All,
       );
       
-      switch (res.status) {
-        case statuses.success.code:
-          answers.finalUrl = res.url;
-          return true;
-        case statuses.cannotBeResolved.code:
-          return statuses.cannotBeResolved.message;
-        case statuses.systemError.code:
-          return statuses.systemError.message;
-        case statuses.invalidUrl.code:
-          if (answers.scanner !== (ScannerTypes.SITEMAP || ScannerTypes.LOCALFILE)) {
-            return statuses.invalidUrl.message;
-          }
-
-          /* if sitemap scan is selected, treat this URL as a filepath
-              isFileSitemap will tell whether the filepath exists, and if it does, whether the
-              file is a sitemap */
-          const finalFilePath = getFileSitemap(url);
-          if (finalFilePath) {
-            answers.isLocalFileScan = true;
-            answers.finalUrl = finalFilePath;
-            return true;
-          }
-          if (answers.scanner === ScannerTypes.LOCALFILE) {
-            return statuses.notALocalFile.message;
-          }
-          return statuses.notASitemap.message;
-
-        case statuses.notASitemap.code:
-          return statuses.notASitemap.message;
-        case statuses.notALocalFile.code:
-          return statuses.notALocalFile.message;
+      if (res.status === statuses.success.code) {
+        answers.finalUrl = res.url;
+        return true;
+      } else {
+        const match = Object.values(statuses).find((s: any) => s.code === res.status);
+        const msg = match && 'message' in match ? match.message : 'Unknown error';
+        return msg;
       }
     },
     filter: (input: string) => sanitizeUrlInput(input.trim()).url,

package/src/crawlers/commonCrawlerFunc.ts

@@ -318,9 +318,9 @@ export const runAxeScript = async ({
   page.on('console', msg => {
     const type = msg.type();
     if (type === 'error') {
-      consoleLogger.log({ level: 'error', message: msg.text() });
+      consoleLogger.error(msg.text());
     } else {
-      consoleLogger.log({ level: 'info', message: msg.text() });
+      consoleLogger.info(msg.text());
     }
   });
   */

package/src/crawlers/crawlDomain.ts

@@ -20,6 +20,7 @@ import constants, {
   STATUS_CODE_METADATA,
   disallowedListOfPatterns,
   disallowedSelectorPatterns,
+  FileTypes,
 } from '../constants/constants.js';
 import {
   getPlaywrightLaunchOptions,
@@ -88,7 +89,7 @@ const crawlDomain = async ({
   userDataDirectory: string;
   strategy: EnqueueStrategy;
   specifiedMaxConcurrency: number;
-  fileTypes: string;
+  fileTypes: FileTypes;
   blacklistedPatterns: string[];
   includeScreenshots: boolean;
   followRobots: boolean;
@@ -117,8 +118,8 @@ const crawlDomain = async ({
 
   const pdfDownloads: Promise<void>[] = [];
   const uuidToPdfMapping: Record<string, string> = {};
-  const isScanHtml = ['all', 'html-only'].includes(fileTypes);
-  const isScanPdfs = ['all', 'pdf-only'].includes(fileTypes);
+  const isScanHtml = [FileTypes.All, FileTypes.HtmlOnly].includes(fileTypes as FileTypes);
+  const isScanPdfs = [FileTypes.All, FileTypes.PdfOnly].includes(fileTypes as FileTypes);
   const { maxConcurrency } = constants;
   const { playwrightDeviceDetailsObject } = viewportSettings;
 
@@ -484,6 +485,9 @@ const crawlDomain = async ({
         // handle pdfs
         if (shouldSkipDueToUnsupportedContent(response, request.url) || (request.skipNavigation && actualUrl === 'about:blank')) {
           if (!isScanPdfs) {
+
+            // Don't inform the user it is skipped since web crawler is best-effort.
+            /*
             guiInfoLog(guiInfoStatusTypes.SKIPPED, {
               numScanned: urlsCrawled.scanned.length,
               urlScanned: request.url,
@@ -495,6 +499,7 @@ const crawlDomain = async ({
               metadata: STATUS_CODE_METADATA[1],
               httpStatusCode: 0,
             });
+            */
 
             return;
           }
@@ -511,6 +516,9 @@ const crawlDomain = async ({
         }
 
         if (isBlacklistedFileExtensions(actualUrl, blackListedFileExtensions)) {
+
+          // Don't inform the user it is skipped since web crawler is best-effort.
+          /*
           guiInfoLog(guiInfoStatusTypes.SKIPPED, {
             numScanned: urlsCrawled.scanned.length,
             urlScanned: request.url,
@@ -522,7 +530,7 @@ const crawlDomain = async ({
             metadata: STATUS_CODE_METADATA[1],
             httpStatusCode: 0,
           });
-
+          */
           return;
         }
 
@@ -631,6 +639,9 @@ const crawlDomain = async ({
             }
           }
         } else {
+
+          // Don't inform the user it is skipped since web crawler is best-effort.
+          /*
           guiInfoLog(guiInfoStatusTypes.SKIPPED, {
             numScanned: urlsCrawled.scanned.length,
             urlScanned: request.url,
@@ -642,6 +653,7 @@ const crawlDomain = async ({
             metadata: STATUS_CODE_METADATA[1],
             httpStatusCode: 0,
           });
+          */
         }
 
         if (followRobots) await getUrlsFromRobotsTxt(request.url, browser, userDataDirectory, extraHTTPHeaders);

package/src/crawlers/crawlIntelligentSitemap.ts

@@ -1,7 +1,7 @@
 import fs from 'fs';
 import { chromium, Page } from 'playwright';
 import { createCrawleeSubFolders } from './commonCrawlerFunc.js';
-import constants, { guiInfoStatusTypes, sitemapPaths } from '../constants/constants.js';
+import constants, { FileTypes, guiInfoStatusTypes, sitemapPaths } from '../constants/constants.js';
 import { consoleLogger, guiInfoLog } from '../logs.js';
 import crawlDomain from './crawlDomain.js';
 import crawlSitemap from './crawlSitemap.js';
@@ -20,7 +20,7 @@ const crawlIntelligentSitemap = async (
   userDataDirectory: string,
   strategy: EnqueueStrategy,
   specifiedMaxConcurrency: number,
-  fileTypes: string,
+  fileTypes: FileTypes,
   blacklistedPatterns: string[],
   includeScreenshots: boolean,
   followRobots: boolean,

package/src/crawlers/crawlLocalFile.ts

@@ -7,6 +7,7 @@ import constants, {
   basicAuthRegex,
   UrlsCrawled,
   STATUS_CODE_METADATA,
+  FileTypes,
 } from '../constants/constants.js';
 import { ViewportSettingsClass } from '../combine.js';
 import {
@@ -47,7 +48,7 @@ export const crawlLocalFile = async ({
   browser: string;
   userDataDirectory: string;
   specifiedMaxConcurrency: number;
-  fileTypes: string;
+  fileTypes: FileTypes;
   blacklistedPatterns: string[];
   includeScreenshots: boolean;
   extraHTTPHeaders: Record<string, string>;

package/src/crawlers/crawlSitemap.ts

@@ -12,6 +12,7 @@ import constants, {
   guiInfoStatusTypes,
   UrlsCrawled,
   disallowedListOfPatterns,
+  FileTypes,
 } from '../constants/constants.js';
 import {
   getLinksFromSitemap,
@@ -55,7 +56,7 @@ const crawlSitemap = async ({
   browser: string;
   userDataDirectory: string;
   specifiedMaxConcurrency: number;
-  fileTypes: string;
+  fileTypes: FileTypes;
   blacklistedPatterns: string[];
   includeScreenshots: boolean;
   extraHTTPHeaders: Record<string, string>;
@@ -97,8 +98,8 @@ const crawlSitemap = async ({
 
   const pdfDownloads: Promise<void>[] = [];
   const uuidToPdfMapping: Record<string, string> = {};
-  const isScanHtml = ['all', 'html-only'].includes(fileTypes);
-  const isScanPdfs = ['all', 'pdf-only'].includes(fileTypes);
+  const isScanHtml = [FileTypes.All, FileTypes.HtmlOnly].includes(fileTypes as FileTypes);
+  const isScanPdfs = [FileTypes.All, FileTypes.PdfOnly].includes(fileTypes as FileTypes);
   const { playwrightDeviceDetailsObject } = viewportSettings;
   const { maxConcurrency } = constants;
 

package/src/crawlers/pdfScanFunc.ts

@@ -288,30 +288,31 @@ export const handlePdfDownload = (
         downloadFile.write(buf, 'binary');
         downloadFile.end();
 
-        if (isPDF(buf)) {
-          guiInfoLog(guiInfoStatusTypes.SCANNED, {
-            numScanned: urlsCrawled.scanned.length,
-            urlScanned: request.url,
-          });
-          urlsCrawled.scanned.push({
-            url: request.url,
-            pageTitle,
-            actualUrl: url,
-          });
-        } else {
-          guiInfoLog(guiInfoStatusTypes.SKIPPED, {
-            numScanned: urlsCrawled.scanned.length,
-            urlScanned: request.url,
-          });
-          urlsCrawled.invalid.push({
-            url: request.url,
-            pageTitle: url,
-            actualUrl: url,
-            metadata: STATUS_CODE_METADATA[1],
-          });
-        }
-
-        resolve();
+        downloadFile.on('finish', () => {
+          if (isPDF(buf)) {
+            guiInfoLog(guiInfoStatusTypes.SCANNED, {
+              numScanned: urlsCrawled.scanned.length,
+              urlScanned: request.url,
+            });
+            urlsCrawled.scanned.push({
+              url: request.url,
+              pageTitle,
+              actualUrl: url,
+            });
+          } else {
+            guiInfoLog(guiInfoStatusTypes.SKIPPED, {
+              numScanned: urlsCrawled.scanned.length,
+              urlScanned: request.url,
+            });
+            urlsCrawled.invalid.push({
+              url: request.url,
+              pageTitle: url,
+              actualUrl: url,
+              metadata: STATUS_CODE_METADATA[1],
+            });
+          }
+          resolve();
+        });
 
     }),
   );
@@ -346,6 +347,9 @@ export const runPdfScan = async (randomToken: string) => {
   ];
 
   const ls = spawnSync(veraPdfExe, veraPdfCmdArgs, { shell: true });
+  if (ls.stderr && ls.stderr.length > 0)
+    consoleLogger.error(ls.stderr.toString());
+
   fs.writeFileSync(intermediateResultPath, ls.stdout, { encoding: 'utf-8' });
 };
 
@@ -363,7 +367,7 @@ export const mapPdfScanResults = async (
   try {
     parsedJsonData = JSON.parse(rawdata);
   } catch (err) {
-    consoleLogger.log(err);
+    consoleLogger.error(err);
   }
 
   const errorMeta = require('../constants/errorMeta.json');

package/src/index.ts

@@ -4,7 +4,6 @@ import inquirer from 'inquirer';
 import { EnqueueStrategy } from 'crawlee';
 import {
   getVersion,
-  cleanUp,
   getUserDataTxt,
   writeToUserDataTxt,
   listenForCleanUp,
@@ -21,7 +20,7 @@ import {
 } from './constants/common.js';
 import questions from './constants/questions.js';
 import combineRun from './combine.js';
-import { BrowserTypes, RuleFlags, ScannerTypes } from './constants/constants.js';
+import { BrowserTypes, FileTypes, RuleFlags, ScannerTypes } from './constants/constants.js';
 import { DeviceDescriptor } from './types/types.js';
 
 export type Answers = {
@@ -35,7 +34,7 @@ export type Answers = {
   clonedBrowserDataDir: string;
   playwrightDeviceDetailsObject: DeviceDescriptor;
   nameEmail: string;
-  fileTypes: string;
+  fileTypes: FileTypes;
   metadata: string;
   maxpages: number;
   strategy: string;
@@ -72,7 +71,7 @@ export type Data = {
   customFlowLabel: string;
   specifiedMaxConcurrency: number;
   randomToken: string;
-  fileTypes: string;
+  fileTypes: FileTypes;
   blacklistedPatternsFilename: string;
   includeScreenshots: boolean;
   metadata: string;
@@ -104,7 +103,7 @@ const runScan = async (answers: Answers) => {
     answers.nameEmail = `${userData.name}:${userData.email}`;
   }
 
-  answers.fileTypes = 'html-only';
+  answers.fileTypes = FileTypes.All;
   answers.metadata = '{}';
 
   const data: Data = await prepareData(answers);

package/src/mergeAxeResults.ts

@@ -970,7 +970,7 @@ const writeSummaryPdf = async (storagePath: string, pagesScanned: number, filena
     ? userDataDirectory
     : '';
   const context = await constants.launcher.launchPersistentContext(effectiveUserDataDirectory, {
-        headless: process.env.CRAWLEE_HEADLESS === '1',
+        headless: true,
         ...getPlaywrightLaunchOptions(browser),
       });
 
@@ -2014,35 +2014,35 @@ const generateArtifacts = async (
     constants.cliZipFileName = path.join(storagePath, constants.cliZipFileName);
   }
 
-  await fs
-    .ensureDir(storagePath)
-    .then(() => {
-      zipResults(constants.cliZipFileName, storagePath);
-      const messageToDisplay = [
-        `Report of this run is at ${constants.cliZipFileName}`,
-        `Results directory is at ${storagePath}`,
-      ];
-
-      if (process.send && process.env.OOBEE_VERBOSE) {
-        const zipFileNameMessage = {
-          type: 'zipFileName',
-          payload: `${constants.cliZipFileName}`,
-        };
-        const storagePathMessage = {
-          type: 'storagePath',
-          payload: `${storagePath}`,
-        };
+  try {
+    await fs.ensureDir(storagePath);
 
-        process.send(JSON.stringify(storagePathMessage));
+    await zipResults(constants.cliZipFileName, storagePath);
 
-        process.send(JSON.stringify(zipFileNameMessage));
-      }
+    const messageToDisplay = [
+      `Report of this run is at ${constants.cliZipFileName}`,
+      `Results directory is at ${storagePath}`,
+    ];
 
-      printMessage(messageToDisplay);
-    })
-    .catch(error => {
-      printMessage([`Error in zipping results: ${error}`]);
-    });
+    if (process.send && process.env.OOBEE_VERBOSE) {
+      const zipFileNameMessage = {
+        type: 'zipFileName',
+        payload: `${constants.cliZipFileName}`,
+      };
+      const storagePathMessage = {
+        type: 'storagePath',
+        payload: `${storagePath}`,
+      };
+
+      process.send(JSON.stringify(storagePathMessage));
+
+      process.send(JSON.stringify(zipFileNameMessage));
+    }
+
+    printMessage(messageToDisplay);
+  } catch (error) {
+    printMessage([`Error in zipping results: ${error}`]);
+  }
 
   // Generate scrubbed HTML Code Snippets
   const ruleIdJson = createRuleIdJson(allIssues);

package/src/utils.ts

@@ -1002,8 +1002,6 @@ export const zipResults = async (zipName: string, resultsPath: string): Promise<
     }
   }
 
-  await addFolderToZip(resultsPath, new JSZip());
-
   const zip = new JSZip();
   await addFolderToZip(resultsPath, zip);