Handle image lazy loading on Wikipedia

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;
 import org.chromium.distiller.DomUtil;
+import org.chromium.distiller.JavaScript;
 import org.chromium.distiller.LogUtil;
 import org.chromium.distiller.webdocument.WebFigure;
 import org.chromium.distiller.webdocument.WebImage;
 
 import java.util.HashSet;
 import java.util.Set;
 
 /**
  * This class treats images as another type of embed and provides heuristics for lead image
  * candidacy.
  */
 public class ImageExtractor implements EmbedExtractor {
     private static final Set<String> relevantTags = new HashSet<>();
     private String imgSrc;
     private int width;
     private int height;
 
     static {
         // TODO(mdjones): Add "DIV" to this list for css images and possibly captions.
         relevantTags.add("IMG");
         relevantTags.add("PICTURE");
         relevantTags.add("FIGURE");
+        relevantTags.add("SPAN");
     }
 
     private static final String[] LAZY_IMAGE_ATTRIBUTES =
             {"data-src", "data-original", "datasrc", "data-url"};
 
     @Override
     public Set<String> getRelevantTagNames() {
         return relevantTags;
     }
 
@@ skipping 24 matching lines @@
                 // <figcaption> only when it contains links, otherwise we get the innerText.
                 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);
         }
 
+        if ("SPAN".equals(e.getTagName())) {
+            if (!e.getAttribute("class").contains("lazy-image-placeholder")) {
+                return null;
+            }
+            // Image lazy loading on Wikipedia.
+            ie = Document.get().createImageElement();
+            imgSrc = e.getAttribute("data-src");
+            width = JavaScript.parseInt(e.getAttribute("data-width"));
+            height = JavaScript.parseInt(e.getAttribute("data-height"));
+            ie.setAttribute("srcset", e.getAttribute("data-srcset"));
+            return new WebImage(ie, width, height, imgSrc);
+        }
+
         extractImageAttributes(ie);
         return new WebImage(e, width, height, imgSrc);
     }
 
     private void extractImageAttributes(ImageElement imageElement) {
         // This will get the absolute URL of the image and
         // the displayed image dimension.
         // Try to get lazily-loaded images before falling back to get the src attribute.
         for (String attr : LAZY_IMAGE_ATTRIBUTES) {
             imgSrc = imageElement.getAttribute(attr);
@@ skipping 16 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;
     }
 }