How to modify this script to select multiple images and a text box?

Hi @dublove, here is one approach...

- Mark

/**
 * @file Align Caption Frame To Graphic Frames.js
 *
 * Usage:
 *   1. Select the caption, a text frame
 *   2. Also select one or more graphic frames
 *   3. Run script
 *
 * Script will align the left and right edges of the caption frame
 * to the left and right extremes of the graphic frame(s), and
 * also align the caption frame above or below the graphic frame(s).
 *
 * @author m1b
 * @version 2025-04-23
 * @discussion https://community.adobe.com/t5/indesign-discussions/how-to-modify-this-script-to-select-multiple-images-and-a-text-box/m-p/15282394
 */
function main() {

    var settings = {

        // distance between the graphic frame(s) and caption frame, in points
        gap: 0,

        // whether to adjust the final positioning to account for text frame insets [T, L, B, R].
        adjustForTextFrameInsets: [false, true, false, true],

    };

    var doc = app.activeDocument,
        items = doc.selection,
        graphicFrames = getThingsWithFilter(items, function (item) { return item.hasOwnProperty('graphics') && item.graphics.length > 0 }, false),
        captionFrame = getThingsWithFilter(items, function (item) { return item.hasOwnProperty('texts') && item.texts.length > 0 }, true);

    if (0 === graphicFrames.length)
        return alert('Please include one or more graphic frames in your selection.');

    if (!captionFrame)
        return alert('Please include one caption text frame in your selection.')

    app.scriptPreferences.measurementUnit = MeasurementUnits.POINTS;

    // insets to adjust for text frame insets
    var insets = [
        settings.adjustForTextFrameInsets[0] ? captionFrame.textFramePreferences.insetSpacing[0] : 0,
        settings.adjustForTextFrameInsets[1] ? captionFrame.textFramePreferences.insetSpacing[1] : 0,
        settings.adjustForTextFrameInsets[2] ? captionFrame.textFramePreferences.insetSpacing[2] : 0,
        settings.adjustForTextFrameInsets[3] ? captionFrame.textFramePreferences.insetSpacing[3] : 0,
    ];

    var minimumHeight = captionFrame.texts[0].characters[0].pointSize
        + (captionFrame.textFramePreferences.insetSpacing[2] + captionFrame.textFramePreferences.insetSpacing[0]);

    var left = Infinity,
        right = -Infinity,
        top = Infinity,
        bottom = -Infinity,
        anchor;

    for (var i = 0; i < graphicFrames.length; i++) {
        left = Math.min(graphicFrames[i].geometricBounds[1], left);
        right = Math.max(graphicFrames[i].geometricBounds[3], right);
        top = Math.min(graphicFrames[i].geometricBounds[0], top);
        bottom = Math.max(graphicFrames[i].geometricBounds[2], bottom);
    }

    if (top < captionFrame.geometricBounds[0]) {
        // align caption below graphic frames
        top = bottom + settings.gap;
        bottom = top + minimumHeight;
        anchor = AnchorPoint.TOP_LEFT_ANCHOR;
    }

    else {
        // align caption above graphic frames
        bottom = top - settings.gap;
        top = bottom - minimumHeight;
        anchor = AnchorPoint.BOTTOM_LEFT_ANCHOR;
    }

    // new bounds, adjusting for insets
    captionFrame.geometricBounds = [
        top - insets[0],
        left - insets[1],
        bottom + insets[2],
        right + insets[3],
    ];

    // now expand to fit the caption text
    while (captionFrame.overflows)
        captionFrame.resize(CoordinateSpaces.PARENT_COORDINATES, anchor, ResizeMethods.ADDING_CURRENT_DIMENSIONS_TO, [0, 2]);

};
app.doScript(main, ScriptLanguage.JAVASCRIPT, undefined, UndoModes.ENTIRE_SCRIPT, 'Align Caption To Graphic Frames');

/**
 * Returns any things which pass the `filter` function.
 * @author m1b
 * @version 2025-04-23
 * @param {Array<*>} things - the things to search.
 * @param {Function} filter - a function that, given a thing, returns true when it matches.
 * @param {Boolean} [returnFirstThing] - whether to return the first thing only (default: false).
 * @returns {Array<*>}
 */
function getThingsWithFilter(things, filter, returnFirstThing) {

    var found = [];

    for (var i = 0; i < things.length; i++) {

        if (
            'Group' === things[i].constructor.name
            && things[i].pageItems.length > 0
        ) {
            var moreThings = getThingsWithFilter(things[i].pageItems.everyItem().getElements(), filter, returnFirstThing);

            if (
                returnFirstThing
                && undefined != moreThings
                && 'Array' !== moreThings.constructor.name
            )
                return moreThings;

            if (moreThings.length > 0)
                found = found.concat(moreThings);

            continue;
        }

        if (!filter(things[i]))
            continue;

        if (returnFirstThing)
            return things[i];

        found.push(things[i]);

    }

    if (
        returnFirstThing
        && 0 === found.length
    )
        return;

    return found;

};

Edit 2025-04-22: added support for grouped items.

Edit 2025-04-23: fixed bug relating to minimum height of caption frame, added support for adjusting for text frame insets.

Edit 2025-04-23: added finer control over each text frame inset and fixed another bug relating to minimum height.