Extracting XML tags on a given page

Hi @DavidSmerda  Are you using ExtendScript? If so, here is a quick script that might be helpful for you. Look at the attached demo.indd to see the set up. It's very simple and I'm not expert on XML Tags, but I use them this way quite a bit.

- Mark

/**
 * @file Read XML Tags.js
 *
 * Example showing reading XML tagged text from active document.
 *
 * @author m1b
 * @version 2025-11-05
 * @discussion https://community.adobe.com/t5/indesign-discussions/extracting-xml-tags-on-a-given-page/m-p/15577321/thread-id/640522
 */
function main() {

    var doc = app.activeDocument;

    var firstNames = findXmlElements({ doc: doc, tagName: 'FirstName', returnText: true });
    var lastNames = findXmlElements({ doc: doc, tagName: 'LastName', returnText: true });

    for (var i = 0, first, last, page; i < firstNames.length; i++) {

        if (0 === firstNames[i].parentTextFrames.length)
            continue;

        first = firstNames[i].contents;
        last = lastNames[i] ? lastNames[i].contents : '';
        page = firstNames[i].parentTextFrames[0].parentPage;

        alert('Page ' + page.name + ': ' + first + ' ' + last);

    }

}
app.doScript(main, ScriptLanguage.JAVASCRIPT, undefined, UndoModes.ENTIRE_SCRIPT, 'Do Script');

/**
 * Returns an array of XML Elements.
 * If no `tagName` or `xpath` is provided,
 * will return all the XML Elements except root.
 * @author m1b
 * @version 2025-11-05
 * @param {Object} options
 * @param {Document} options.doc - an Indesign Document.
 * @param {String} [options.tagName] - an XMLTag name (default: all tags).
 * @param {String} [options.xpath] - an XPath to the element (default: all `tagName` elements).
 * @param {Boolean} [options.untag] - whether to untag the XMLElement, if true then `returnText` will be true (default: false).
 * @param {Boolean} [options.returnText] - whether to return Text, if true will return Text (default: false).
 * @param {Boolean} [options.excludeOrphans] - whether to exclude orphans — texts that aren't actually in document (default: true).
 * @returns {Array<XMLElement>|Array<Text>} - array of found XMLElements or Texts.
 */
function findXmlElements(options) {

    options = options || {};

    if (options.doc == undefined)
        throw Error('findXmlElements: no `doc` supplied.');

    var doc = options.doc;
    var xpath = options.xpath || './/' + (options.tagName || '*');
    var result = [];

    var found = doc.xmlElements[0].evaluateXPathExpression(xpath);

    for (var i = 0, text; i < found.length; i++) {

        text = resolve(found[i].texts[0].toSpecifier());

        if (
            !text.isValid
            || !text.parentStory.isValid
            || (
                false !== options.excludeOrphans
                && 'XmlStory' === text.parent.constructor.name
            )
        )
            continue;

        var text = resolve(found[i].texts[0].toSpecifier());
        debugger; // 2025-11-05

        if (true === options.untag) {
            found[i].untag();
            options.returnText = true;
        }

        if (true === options.returnText)
            result.push(text);
        else
            result.push(found[i]);

    }

    return result;

};

 P.S.  The function abstracts the parts which are tricky to remember. The `untag` option is good for when you want to set the tagged text's contents once and only once (it will not be found if you run the script again).

Edit 2025-11-05: updated my old findXmlElements function so that it excludes "orphan" elements (XML elements that don't exist in the document).