lee/heritrix3
1
0
Fork 0
mirror of https://github.com/internetarchive/heritrix3.git synced 2026-09-27 16:15:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Allow xml extractor to handle urls in CDATA.

Browse Source
This commit is contained in:
Hunter Stern
2014-08-01 17:37:31 -07:00
parent 4298c3de69
commit 7f1700400b
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/ExtractorXML.java
+2 -1
View File
@@ -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*(?:<!\\[CDATA\\[)?([^<>\\s\'\"@]+)\\s*(?:\\]\\]>)?[\"\'<]");
// GROUPS:
// (G1) possible uri