Skip non-text elements in <a> without href in <figcaption>

java/org/chromium/distiller/extractors/embeds/ImageExtractor.java

 // Copyright 2015 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 package org.chromium.distiller.extractors.embeds;
 
 import com.google.gwt.dom.client.Document;
 import com.google.gwt.dom.client.Element;
 import com.google.gwt.dom.client.ImageElement;
 import com.google.gwt.dom.client.NodeList;
@@ skipping 48 matching lines @@
                 return null;
             }
             extractImageAttributes(ie);
             Element figcaption;
             Element cap = DomUtil.getFirstElementByTagName(e, "FIGCAPTION");
             if (cap != null) {
                 // We look for links because some sites put non-caption
                 // elements into <figcaption>. For example: image credit
                 // could contain a link. So we get the whole DOM structure within
                 // <figcaption> only when it contains links, otherwise we get the innerText.
-                figcaption = DomUtil.getFirstElementByTagName(cap, "A") != null ?
+                NodeList<Element> links = DomUtil.querySelectorAll(cap, "A[HREF]");
+                figcaption = links.getLength() > 0 ?
                         cap : createFigcaptionElement(cap);
             } else {
                 figcaption = createFigcaptionElement(e);
             }
             return new WebFigure(img, width, height, imgSrc, figcaption);
         }
 
         extractImageAttributes(ie);
         return new WebImage(e, width, height, imgSrc);
     }
@@ skipping 23 matching lines @@
             LogUtil.logToConsole("Extracted WebImage: " + imgSrc);
         }
     }
 
     private Element createFigcaptionElement(Element element) {
         Element figcaption = Document.get().createElement("FIGCAPTION");
         figcaption.setInnerText(DomUtil.getInnerText(element));
         return figcaption;
     }
 }