From 5f431de215373e3f1f031e2a4aa593d5a04f62ea Mon Sep 17 00:00:00 2001 From: Eric Leclerc Date: Wed, 17 Feb 2016 14:49:50 -0500 Subject: [PATCH] Update to ExtractorHTML.java for cond. comments Lot's of websites are using "Downlevel Revealed" conditional comments with a twist to have a page with valid html. this is an update to the RegEx to allow such a case. ex: HTML - reference: https://css-tricks.com/downlevel-hidden-downlevel-revealed/ - reference: http://www.sitepoint.com/web-foundations/internet-explorer-conditional-comments/ - example site where this type of tag can be found: https://www.canada.ca/index.html --- .../main/java/org/archive/modules/extractor/ExtractorHTML.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 ef849642..dfb563b5 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[^>]*+)>.*?]*+)>.*?]*+)" + // 5, 6, 7 - "|(!--(?!\\[if).*?--))>"; // 8 + "|(!--(?!\\[if|>).*?--))>"; // 8 // version w/ problems with unclosed script tags // static final String RELEVANT_TAG_EXTRACTOR =