lee/heritrix3
1
0
Fork 0
mirror of https://github.com/internetarchive/heritrix3.git synced 2026-09-28 08:35:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Strip quotes from URL value.

Browse Source
This commit is contained in:
Neil Minton
2020-08-14 10:54:18 -04:00
parent f879226c8e
commit 941c6c50ad
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/src/main/java/org/archive/modules/extractor/ExtractorHTML.java
+2 -1
View File
@@ -981,7 +981,8 @@ public class ExtractorHTML extends ContentExtractor implements InitializingBean
} else if ("refresh".equalsIgnoreCase(httpEquiv) && content != null) {
int urlIndex = content.indexOf("=") + 1;
if(urlIndex>0) {
String refreshUri = content.substring(urlIndex);
// strip any quotes ("') characters from the URL value.
String refreshUri = TextUtils.replaceAll("[\"']", content.substring(urlIndex), "");
try {
int max = getExtractorParameters().getMaxOutlinks();
addRelativeToBase(curi, max, refreshUri,