Extract also property attributes of HTML meta elements, this fixes #67

sebastian-nagel · sebastian-nagel · commit bd08143577ea · 2017-05-02T14:00:11.000+02:00
diff --git a/src/main/java/org/archive/resource/html/ExtractingParseObserver.java b/src/main/java/org/archive/resource/html/ExtractingParseObserver.java
@@ -406,7 +406,7 @@ public void extract(HTMLMetaData data, TagNode node, ExtractingParseObserver obs
 
 	private static class MetaTagExtractor implements TagExtractor {
 		public void extract(HTMLMetaData data, TagNode node, ExtractingParseObserver obs) {
-			ArrayList<String> l = getAttrList(node,"name","rel","content","http-equiv");
+			ArrayList<String> l = getAttrList(node,"name","rel","content","http-equiv","property");
 			if(l != null) {
 				data.addMeta(l);
 			}

Original file line number	Diff line number	Diff line change
`@@ -406,7 +406,7 @@ public void extract(HTMLMetaData data, TagNode node, ExtractingParseObserver obs`
`406`	`406`
`407`	`407`	`private static class MetaTagExtractor implements TagExtractor {`
`408`	`408`	`public void extract(HTMLMetaData data, TagNode node, ExtractingParseObserver obs) {`
`409`		`- ArrayList<String> l = getAttrList(node,"name","rel","content","http-equiv");`
	`409`	`+ ArrayList<String> l = getAttrList(node,"name","rel","content","http-equiv","property");`
`410`	`410`	`if(l != null) {`
`411`	`411`	`data.addMeta(l);`
`412`	`412`	`}`