Merge pull request #149 from eleclerc/patch-1

Update to ExtractorHTML.java for cond. comments
2026-09-23 14:15:47 +00:00 · 2016-02-19 09:49:34 +00:00
parent 847400776b 5f431de215
commit ae413b1d9e
1 changed files with 1 additions and 1 deletions
@@ -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 =