Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(119)

Unified Diff: java/org/chromium/distiller/extractors/embeds/ImageExtractor.java

Issue 2729143003: Handle image lazy loading on Wikipedia (Closed)
Patch Set: fixup non-matching case Created 3 years, 9 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « no previous file | javatests/org/chromium/distiller/ContentExtractorTest.java » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: java/org/chromium/distiller/extractors/embeds/ImageExtractor.java
diff --git a/java/org/chromium/distiller/extractors/embeds/ImageExtractor.java b/java/org/chromium/distiller/extractors/embeds/ImageExtractor.java
index b1d6e5b5a08a2f3868c7210a5a8365e8542c4101..a615b730804d9916d42f445e21c1d2b07155b866 100644
--- a/java/org/chromium/distiller/extractors/embeds/ImageExtractor.java
+++ b/java/org/chromium/distiller/extractors/embeds/ImageExtractor.java
@@ -9,6 +9,7 @@ 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;
@@ -31,6 +32,7 @@ public class ImageExtractor implements EmbedExtractor {
relevantTags.add("IMG");
relevantTags.add("PICTURE");
relevantTags.add("FIGURE");
+ relevantTags.add("SPAN");
}
private static final String[] LAZY_IMAGE_ATTRIBUTES =
@@ -75,6 +77,19 @@ public class ImageExtractor implements EmbedExtractor {
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);
}
« no previous file with comments | « no previous file | javatests/org/chromium/distiller/ContentExtractorTest.java » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698