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 o

Answer 1

I was playing around and incorporated @Mogsdad's answer -- here's the really complicated version:

var _ = Underscorejs.load(); // loaded via http://googleappsdeveloper.blogspot.com/2012/11/using-open-source-libraries-in-apps.html, rolled my own
var ui = DocumentApp.getUi();

// #region --------------------- Utilities -----------------------------

var gDocsHelper = (function(P, un) {
  // heavily based on answer https://stackoverflow.com/a/18731628/1037948

  var updatedLinkText = function(link, offset) {
    return function() { return 'Text: ' + link.getText().substring(offset,100) + ((link.getText().length-offset) > 100 ? '...' : ''); }
  }

  P.updateLink = function updateLink(link, oldText, newText, start, end) {
    var oldLink = link.getLinkUrl(start);

    if(0 > oldLink.indexOf(oldText)) return false;

    var newLink = oldLink.replace(new RegExp(oldText, 'g'), newText);
    link.setLinkUrl(start || 0, (end || oldLink.length), newLink);
    log(true, "Updating Link: ", oldLink, newLink, start, end, updatedLinkText(link, start) );

    return { old: oldLink, "new": newLink, getText: updatedLinkText(link, start) };
  };

  // moving this reused block out to 'private' fn
  var updateLinkResult = function(text, oldText, newText, link, urls, sidebar, updateResult) {
    // and may as well update the link while we're here
    if(false !== (updateResult = P.updateLink(text, oldText, newText, link.start, link.end))) {
       sidebar.append('
' + updateResult['old'] + ' → ' + updateResult['new'] + ' at ' + updateResult['getText']() + '
'); 
    }

    urls.push(link.url); // so multiple links get added to list
  };

  P.updateLinksMenu = function() {
    // https://developers.google.com/apps-script/reference/base/prompt-response
    var oldText = ui.prompt('Old link text to replace').getResponseText();
    var newText = ui.prompt('New link text to replace with').getResponseText();

    log('Replacing: ' + oldText + ', ' + newText);
    var sidebar = gDocUiHelper.createSidebar('Update All Links', '
Replacing
' + oldText + ' → ' + newText + '
');

    // current doc available to script
    var doc = DocumentApp.getActiveDocument().getBody();//.getActiveSection();

    // Search until a link is found
    var links = P.findAllElementsFor(doc, function(text) {
      var i = -1, n = text.getText().length, link = false, url, urls = [], updateResult;

      // note: the following only gets the FIRST link in the text -- while(i < n && !(url = text.getLinkUrl(i++)));

      // scan the text element for links
      while(++i < n) {

        // getLinkUrl will continue to get a link while INSIDE the stupid link, so only do this once
        if(url = text.getLinkUrl(i)) {
          if(false === link) {
            link = { start: i, end: -1, url: url };
            // log(true, 'Type: ' + text.getType(), 'Link: ' + url, function() { return 'Text: ' + text.getText().substring(i,100) + ((n-i) > 100 ? '...' : '')});
          }
          else {
            link.end = i; // keep updating the end position until we leave
          }
        }
        // just left the link -- reset link tracking
        else if(false !== link) {
          // and may as well update the link while we're here
          updateLinkResult(text, oldText, newText, link, urls, sidebar);
          link = false; // reset "counter"
        }

      }

      // once we've reached the end of the text, must also check to see if the last thing we found was a link
      if(false !== link) updateLinkResult(text, oldText, newText, link, urls, sidebar);

      return urls;
    });

    sidebar.append('
' + links.length + ' links reviewed
');
    gDocUiHelper.attachSidebar(sidebar);

    log(links);
  };

  P.findAllElementsFor = function(el, test) {
    // generic utility function to recursively find all elements; heavily based on https://stackoverflow.com/a/18731628/1037948

    var results = [], searchResult = null, i, result;
    // https://developers.google.com/apps-script/reference/document/body#findElement(ElementType)
    while (searchResult = el.findElement(DocumentApp.ElementType.TEXT, searchResult)) {
      var t = searchResult.getElement().editAsText(); // .asParagraph()

      // check to add to list
      if(test && (result = test(t))) {
        if( _.isArray(result) ) results = results.concat(result); // could be big? http://jsperf.com/self-concatenation/
        else results.push(result);
      }
    }
    // recurse children if not plain text item
    if(el.getType() !== DocumentApp.ElementType.TEXT) {
      i = el.getNumChildren();

      var result;
      while(--i > 0) {
        result = P.findAllElementsFor(el.getChild(i));
        if(result && result.length > 0) results = results.concat(result);
      }
    }

    return results;
  };

  return P;  
})({});

// really? it can't handle object properties?
function gDocsUpdateLinksMenu() {
  gDocsHelper.updateLinksMenu();
}

gDocUiHelper.addMenu('Zaus', [ ['Update links', 'gDocsUpdateLinksMenu'] ]);

// #endregion --------------------- Utilities -----------------------------

---

And I'm including the "extra" utility classes for creating menus, sidebars, etc below for completeness:

var log = function() {
  // return false;

  var args = Array.prototype.slice.call(arguments);

  // allowing functions delegates execution so we can save some non-debug cycles if code left in?

  if(args[0] === true) Logger.log(_.map(args, function(v) { return _.isFunction(v) ? v() : v; }).join('; '));
  else
    _.each(args, function(v) {
      Logger.log(_.isFunction(v) ? v() : v);
    });
}

// #region --------------------- Menu -----------------------------

var gDocUiHelper = (function(P, un) {

  P.addMenuToSheet = function addMenu(spreadsheet, title, items) {
    var menu = ui.createMenu(title);
    // make sure menu items are correct format
    _.each(items, function(v,k) {
      var err = [];

      // provided in format [ [name, fn],... ] instead
      if( _.isArray(v) ) {
        if ( v.length === 2 ) {
          menu.addItem(v[0], v[1]);
        }
        else {
          err.push('Menu item ' + k + ' missing name or function: ' + v.join(';'))
        }
      }
      else {
        if( !v.name ) err.push('Menu item ' + k + ' lacks name');
        if( !v.functionName ) err.push('Menu item ' + k + ' lacks function');

        if(!err.length) menu.addItem(v.name, v.functionName);
      }

      if(err.length) {
        log(err);
        ui.alert(err.join('; '));
      }

    });

    menu.addToUi();
  };

  // list of things to hook into
  var initializers = {};

  P.addMenu = function(menuTitle, menuItems) {
    if(initializers[menuTitle] === un) {
      initializers[menuTitle] = [];
    }
    initializers[menuTitle] = initializers[menuTitle].concat(menuItems);
  };

  P.createSidebar = function(title, content, options) {
    var sidebar = HtmlService
    .createHtmlOutput()
    .setTitle(title)
    .setWidth( (options && options.width) ? width : 350 /* pixels */);

    sidebar.append(content);

    if(options && options.on) DocumentApp.getUi().showSidebar(sidebar);
    // else { sidebar.attach = function() { DocumentApp.getUi().showSidebar(this); }; } // should really attach to prototype...

    return sidebar;
  };

  P.attachSidebar = function(sidebar) {
    DocumentApp.getUi().showSidebar(sidebar);
  };


  P.onOpen = function() {
    var spreadsheet = SpreadsheetApp.getActive();
    log(initializers);
    _.each(initializers, function(v,k) {
      P.addMenuToSheet(spreadsheet, k, v);
    });
  };

  return P;
})({});

// #endregion --------------------- Menu -----------------------------

/**
 * A special function that runs when the spreadsheet is open, used to add a
 * custom menu to the spreadsheet.
 */
function onOpen() {
  gDocUiHelper.onOpen();
}