function(doc){ var File = java.io.File; var Iterator = java.util.Iterator; var Jsoup = org.jsoup.Jsoup; var Document = org.jsoup.nodes.Document; var Element = org.jsoup.nodes.Element; var Elements = org.jsoup.select.Elements; var content = doc.getFirstFieldValue("body"); var jdoc = org.jsoup.nodes.Document; var e = java.lang.Exception; var div = org.jsoup.nodes.Element; var img = org.jsoup.nodes.Element; var iter = java.util.Iterator; var divs = org.jsoup.select.Elements; try { jdoc = Jsoup.parse(content); divs = jdoc.select("div"); iter = divs.iterator(); div = null; // initialize our value to null while (iter.hasNext()) { div = iter.next(); if (div.attr("id").equals("bottom")) { // found the containing div of img break; // break out to there } } // break out to here to add field for img src if (div != null) { img = div.child(0); // get the image element logger.info("SRC: " + img.attr("src")); // log the image URL doc.addField("image_url", img.attr("src")); } else { logger.warn("div was null"); } } catch ( e) { logger.warn("something went wrong"); logger.error(e); } return doc; }