google apps script - Get All Links in a Document

Question

Given a "normal document" in Google Docs/Drive (e.g. paragraphs, lists, tables) which contains external links scattered throughout the content, how do you compile a list of links present using Google Apps Script?

Specifically, I want to update all broken links in the document by searching for oldText in each url and replace it with newText in each url, but not the text.

I don't think the replacing text section of the Dev Documentation is what I need -- do I need to scan every element of the doc? Can I just editAsText and use an html regex? Examples would be appreciated.

Answer 1

This is only mostly painful! Code is available as part of a gist.

^{_{Yeah, I can't spell.}}

getAllLinks

Here's a utility function that scans the document for all LinkUrls, returning them in an array.

/**
 * 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}
 */
function getAllLinks(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 {
    var numChildren = element.getNumChildren();
    for (var i=0; i<numChildren; i++) {
      links = links.concat(getAllLinks(element.getChild(i)));
    }
  }

  return links;
}

findAndReplaceLinks

This utility builds on getAllLinks to do a find & replace function.

/**
 * Replace all or part of UrlLinks in the document.
 *
 * @param {String} searchPattern    the regex pattern to search for 
 * @param {String} replacement      the text to use as replacement
 *
 * @returns {Number}                number of Urls changed 
 */
function findAndReplaceLinks(searchPattern,replacement) {
  var links = getAllLinks();
  var numChanged = 0;
  
  for (var l=0; l<links.length; l++) {
    var link = links[l];
    if (link.url.match(searchPattern)) {
      // This link needs to be changed
      var newUrl = link.url.replace(searchPattern,replacement);
      link.element.setLinkUrl(link.startOffset, link.endOffsetInclusive, newUrl);
      numChanged++
    }
  }
  return numChanged;
}

Demo UI

To demonstrate the use of these utilities, here are a couple of UI extensions:

function onOpen() {
  // Add a menu with some items, some separators, and a sub-menu.
  DocumentApp.getUi().createMenu('Utils')
      .addItem('List Links', 'sidebarLinks')
      .addItem('Replace Link Text', 'searchReplaceLinks')
      .addToUi();
}

function searchReplaceLinks() {
  var ui = DocumentApp.getUi();
  var app = UiApp.createApplication()
                 .setWidth(250)
                 .setHeight(100)
                 .setTitle('Change Url text');
  var form = app.createFormPanel();
  var flow = app.createFlowPanel();
  flow.add(app.createLabel("Find: "));
  flow.add(app.createTextBox().setName("searchPattern"));
  flow.add(app.createLabel("Replace: "));
  flow.add(app.createTextBox().setName("replacement"));
  var handler = app.createServerHandler('myClickHandler');
  flow.add(app.createSubmitButton("Submit").addClickHandler(handler));
  form.add(flow);
  app.add(form);
  ui.showDialog(app);
}

// ClickHandler to close dialog
function myClickHandler(e) {
  var app = UiApp.getActiveApplication();

  app.close();
  return app;
}

function doPost(e) {
  var numChanged = findAndReplaceLinks(e.parameter.searchPattern,e.parameter.replacement);
  var ui = DocumentApp.getUi();
  var app = UiApp.createApplication();
  
  sidebarLinks(); // Update list

  var result = DocumentApp.getUi().alert(
      'Results',
      "Changed "+numChanged+" urls.",
      DocumentApp.getUi().ButtonSet.OK);
}


/**
 * Shows a custom HTML user interface in a sidebar in the Google Docs editor.
 */
function sidebarLinks() {
  var links = getAllLinks();
  var sidebar = HtmlService
          .createHtmlOutput()
          .setTitle('URL Links')
          .setWidth(350 /* pixels */);

  // Display list of links, url only.
  for (var l=0; l<links.length; l++) {
    var link = links[l];
    sidebar.append('<p>'+link.url);
  }
  
  DocumentApp.getUi().showSidebar(sidebar);
}