ExtractorChrome: Don't capture data: URIs

They are already captured as part of their containing document. There's
no need to record them separately.

#430

contrib/src/main/java/org/archive/modules/extractor/ExtractorChrome.java

@@ -29,6 +29,7 @@ import org.archive.modules.ProcessorChain;
 import org.archive.net.chrome.*;
 import org.archive.spring.KeyedProperties;
 import org.archive.util.Recorder;
+import org.archive.util.UriUtils;
 import org.json.JSONArray;
 import org.springframework.context.ApplicationEventPublisher;
 
@@ -220,7 +221,7 @@ public class ExtractorChrome extends ContentExtractor {
     }
 
     private void handleCapturedRequest(CrawlURI via, ChromeRequest request) {
-        if (request.isResponseFulfilledByInterception()) {
+        if (request.isResponseFulfilledByInterception() || UriUtils.isDataUri(request.getUrl())) {
             return;
         }
 

contrib/src/test/java/org/archive/modules/extractor/ExtractorChromeTest.java

@@ -67,6 +67,7 @@ public class ExtractorChromeTest {
                         response.setContentType("text/html");
                         response.getWriter().write("<a href=http://example.org/page2.html>link</a>" +
                                 "<img src=/blue.png>" +
+                                "<img src='data:image/gif;base64,R0lGODlhAQABAAAAACH5BAEKAAEALAAAAAABAAEAAAICTAEAOw=='>" +
                                 "<script>fetch('/post', {method: 'POST', body: 'hello'});</script>" +
                                 "<link rel=stylesheet href=style.css>");
                         baseRequest.setHandled(true);