Index: /nutchez-0.1/conf/crawl-urlfilter.txt
===================================================================
--- /nutchez-0.1/conf/crawl-urlfilter.txt	(revision 73)
+++ /nutchez-0.1/conf/crawl-urlfilter.txt	(revision 74)
@@ -29,5 +29,5 @@
 
 # skip image and other suffixes we can't yet parse
--\.(gif|GIF|jpg|JPG|png|PNG|ico|ICO|css|sit|eps|wmf|mpg|xls|gz|rpm|tgz|mov|MOV|exe|jpeg|JPEG|bmp|BMP)$
+-\.(gif|GIF|jpg|JPG|png|PNG|ico|ICO|css|sit|eps|wmf|mpg|xls|gz|rpm|tgz|mov|MOV|exe|jpeg|JPEG|bmp|BMP|js|swf)$
 
 # skip URLs containing certain characters as probable queries, etc.
Index: /nutchez-0.1/conf/nutch-site.xml
===================================================================
--- /nutchez-0.1/conf/nutch-site.xml	(revision 73)
+++ /nutchez-0.1/conf/nutch-site.xml	(revision 74)
@@ -28,5 +28,5 @@
 <property>
   <name>plugin.includes</name>
-  <value>protocol-http|urlfilter-regex|parse-(text|html|js|ext|msexcel|mspowerpoint|msword|oo|pdf|rss|swf|zip)|index-(more|basic|anchor)|query-(more|basic|site|url)|response-(json|xml)|summary-basic|scoring-opic|urlnormalizer-(pass|regex|basic)</value>
+  <value>protocol-http|urlfilter-regex|parse-(text|html|ext|msexcel|mspowerpoint|msword|oo|pdf|rss|zip)|index-(more|basic|anchor)|query-(more|basic|site|url)|response-(json|xml)|summary-basic|scoring-opic|urlnormalizer-(pass|regex|basic)</value>
   <description> Regular expression naming plugin directory names</description>
  </property>
Index: /nutchez-0.1/conf/sav/n.url.txt
===================================================================
--- /nutchez-0.1/conf/sav/n.url.txt	(revision 73)
+++ /nutchez-0.1/conf/sav/n.url.txt	(revision 74)
@@ -1,2 +1,2 @@
-www.nchc.org.tw
-www.hadoop.tw
+http://www.nchc.org.tw
+http://www.hadoop.tw