Validate External Links in Google Docs

Validate External Links in Google Docs.md

Validate External Links in Google Docs

1. In Google Docs, click the Extensions > Apps Scripts menu item.
2. Rename the project "Validate External Links"
3. Replace content of code.gs with the code in this Gist.
4. Save the script.
5. Reload the Google Doc.
6. Activate by clicking the Extensions > Validate External URLs > Highlight Broken URLs menu item.
7. Accept the permissions.
8. Re-run the extension.

Links that require log in, like private Github repos will appear as broken.

I investigated adding a comment instead of highlighting, but gave up on the API.

validate_urls.js

/**
 * Creates a menu entry in the Google Docs UI when the document is opened.
 * This method is only used by the regular add-on, and is never called by
 * the mobile add-on version.
 *
 * @param {object} e The event parameter for a simple onOpen trigger. To
 *     determine which authorization mode (ScriptApp.AuthMode) the trigger is
 *     running in, inspect e.authMode.
 */
function onOpen(e) {
  DocumentApp.getUi().createAddonMenu()
      .addItem('Highlight Broken Links', 'validateUrlsInDoc')
      .addToUi();
}


function validateUrlsInDoc() {

  var doc = DocumentApp.getActiveDocument();
  var body = doc.getBody();
  
  // Find all links in doc
  var textLinks = getAllTextLinks(body);
  var richLinks = getAllRichLinks(body);
  var links = textLinks.concat(richLinks);

  var brokenLinks = [];

  for (var link of links) {
    var url = link.url;
    var error = null;
    if (isExternalUrl(url)) {
      try {
        var response = UrlFetchApp.fetch(url, {'muteHttpExceptions': true});
      }
      catch (err) {
        error = err.message
      }
      
      var responseCode = response.getResponseCode();
      if (responseCode >= 400) {
        error = responseCode;
      }

      if (error) {
        brokenLinks.push(link)
        var message = "Invalid URL: " + url + " (response code: " + error + ")";
        console.log(message);
      }
    }
  }

  // Highlight in yellow
  for (var brokenLink of brokenLinks) {
    brokenLink.element.setBackgroundColor("#ffff00"); 
  }
}


function isExternalUrl(url) {
  return url.indexOf("http://") === 0 || url.indexOf("https://") === 0;
}


/**
 * Get an array of all RICH_URL in the document. 
 *
 * @param {Element} element The document element to operate on. 
 * .
 * @returns {Array}         Array of objects, vis
 *                              {element,
 *                               startOffset,
 *                               endOffsetInclusive, 
 *                               url}
 * 
 */
function getAllRichLinks(element) {
  var links = [];
  element = element || DocumentApp.getActiveDocument().getBody();

  // Define the search parameters.
  var searchType = DocumentApp.ElementType.RICH_LINK;
  var searchResult = null;

  // Search until the paragraph is found.
  while (searchResult = element.findElement(searchType, searchResult)) {
    var childElement = searchResult.getElement();
    links.push({
      'element': childElement,
      'startOffset': searchResult.getStartOffset(), 
      'endOffsetInclusive': searchResult.getEndOffsetInclusive(), 
      'url': childElement.getUrl()
    })
  }
  
  return links;
}


/**
 * Get an array of all LinkUrls in the document. The function is
 * recursive, and if no element is provided, it will default to
 * the active document's Body element.
 *
 * @param {Element} element The document element to operate on. 
 * .
 * @returns {Array}         Array of objects, vis
 *                              {element,
 *                               startOffset,
 *                               endOffsetInclusive, 
 *                               url}
 * 
 * From: https://stackoverflow.com/questions/18727341/get-all-links-in-a-document
 * It's gnarly, but GDocs doesn't have the equivalent of find_all("a") in 
 * BeautifulSoup.
 */
function getAllTextLinks(element) {
  var links = [];
  element = element || DocumentApp.getActiveDocument().getBody();
  
  if (element.getType() === DocumentApp.ElementType.TEXT) {
    var textObj = element.editAsText();
    var text = element.getText();
    var inUrl = false;
    for (var ch=0; ch < text.length; ch++) {
      var url = textObj.getLinkUrl(ch);
      if (url != null) {
        if (!inUrl) {
          // We are now!
          inUrl = true;
          var curUrl = {};
          curUrl.element = element;
          curUrl.url = String( url ); // grab a copy
          curUrl.startOffset = ch;
        }
        else {
          curUrl.endOffsetInclusive = ch;
        }          
      }
      else {
        if (inUrl) {
          // Not any more, we're not.
          inUrl = false;
          links.push(curUrl);  // add to links
          curUrl = {};
        }
      }
    }
    if (inUrl) {
      // in case the link ends on the same char that the element does
      links.push(curUrl); 
    }
  }
  else {
    try {
      var numChildren = element.getNumChildren();
    }
    catch(err) {
      return [];
    }
    
    for (var i=0; i<numChildren; i++) {
      links = links.concat(getAllTextLinks(element.getChild(i)));
    }
  }

  return links;
}