diff --git a/modules/src/main/java/org/archive/modules/extractor/ExtractorXML.java b/modules/src/main/java/org/archive/modules/extractor/ExtractorXML.java index 64a1d500..92baf805 100644 --- a/modules/src/main/java/org/archive/modules/extractor/ExtractorXML.java +++ b/modules/src/main/java/org/archive/modules/extractor/ExtractorXML.java @@ -56,7 +56,8 @@ public class ExtractorXML extends ContentExtractor { Logger.getLogger(ExtractorXML.class.getName()); static final Pattern XML_URI_EXTRACTOR = Pattern - .compile("(?s)[\"\'>]\\s*([^<>\\s'\"@]+)\\s*[\"\'<]"); + .compile("(?s)[\"\'>]\\s*(?:\\s\'\"@]+)\\s*(?:\\]\\]>)?[\"\'<]"); + // GROUPS: // (G1) possible uri