Extract image URLs in srcset as well

java/org/chromium/distiller/webdocument/WebDocument.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.webdocument;
 
 import org.chromium.distiller.document.TextDocument;
 import org.chromium.distiller.document.TextBlock;
 
 import java.util.ArrayList;
@@ skipping 23 matching lines @@
     }
 
     public void addEmbed(WebElement embed) {
         elements.add(embed);
     }
 
     public List<WebElement> getElements() {
         return elements;
     }
 
-    public List<WebImage> getContentImages() {
-        List<WebImage> images = new ArrayList<>();
+    public List<String> getImageUrls() {
+        List<String> images = new ArrayList<>();
         for (WebElement e : elements) {
-            if (e instanceof WebImage && e.getIsContent()) {
-                images.add((WebImage) e);
+            if (!e.getIsContent()) continue;
+            if (e instanceof WebImage) {
+                images.addAll(((WebImage) e).getUrlList());
             }
         }
         return images;
     }
 
     /**
      * This method generates a web document to be processed by boilerpipe. Text groups have been
      * introduced to help retain element order when adding images and embeds.
      * @return TextDocument object built from this web document.
      */
@@ skipping 42 matching lines @@
             if (!e.getIsContent()) continue;
             output.append(e.generateOutput(textOnly));
             if (textOnly) {
                 // Put some space between paragraphs in text-only mode.
                 output.append("\n");
             }
         }
         return output.toString();
     }
 }