Created
October 22, 2015 17:21
-
-
Save eleclerc/5894799942938938ebe5 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
diff --git a/modules/src/main/java/org/archive/modules/extractor/ExtractorHTML.java b/modules/src/main/java/org/archive/modules/extractor/ExtractorHTML.java | |
index ef84964..dfb563b 100644 | |
--- a/modules/src/main/java/org/archive/modules/extractor/ExtractorHTML.java | |
+++ b/modules/src/main/java/org/archive/modules/extractor/ExtractorHTML.java | |
@@ -138,7 +138,7 @@ public class ExtractorHTML extends ContentExtractor implements InitializingBean | |
"(?is)<(?:((script[^>]*+)>.*?</script)" + // 1, 2 | |
"|((style[^>]*+)>.*?</style)" + // 3, 4 | |
"|(((meta)|(?:\\w{1,"+MAX_ELEMENT_REPLACE+"}))\\s+[^>]*+)" + // 5, 6, 7 | |
- "|(!--(?!\\[if).*?--))>"; // 8 | |
+ "|(!--(?!\\[if|>).*?--))>"; // 8 | |
// version w/ problems with unclosed script tags | |
// static final String RELEVANT_TAG_EXTRACTOR = |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment