Index: /nutchez-0.1/bin/nutchez-func.sh
===================================================================
--- /nutchez-0.1/bin/nutchez-func.sh	(revision 79)
+++ /nutchez-0.1/bin/nutchez-func.sh	(revision 80)
@@ -169,5 +169,5 @@
   echo_vb "/opt/nutch/bin/nutch crawl ~/.nutchez/urls -dir ~/.nutchez/search -depth $DEPTH"
   echo_vb "nutch conf dir = $NUTCH_CONF_DIR"
-  /opt/nutch/bin/nutch crawl ~/.nutchez/urls -dir ~/.nutchez/search -depth $DEPTH
+  /opt/nutch/bin/nutch crawl ~/.nutchez/urls -dir ~/.nutchez/search -depth $DEPTH -topN 5000 -threads 1000
 }
 
Index: /nutchez-0.1/conf/nutch-site.xml
===================================================================
--- /nutchez-0.1/conf/nutch-site.xml	(revision 79)
+++ /nutchez-0.1/conf/nutch-site.xml	(revision 80)
@@ -66,5 +66,20 @@
   </description>
 </property>
-
+<property>
+  <name>db.ignore.external.links</name>
+  <value>false</value>
+  <description>If true, outlinks leading from a page to external hosts
+  will be ignored. This is an effective way to limit the crawl to include
+  only initially injected hosts, without creating complex URLFilters.
+  </description>
+</property>
+<property>
+  <name>file.content.limit</name>
+  <value>1000000</value>
+  <description>The length limit for downloaded content, in bytes.
+  If this value is nonnegative (>=0), content longer than it will be truncated;
+  otherwise, no truncation at all.
+  </description>
+</property>
 </configuration>
 
Index: /nutchez-0.1/conf/sav/n.urls.txt
===================================================================
--- /nutchez-0.1/conf/sav/n.urls.txt	(revision 79)
+++ /nutchez-0.1/conf/sav/n.urls.txt	(revision 80)
@@ -1,2 +1,2 @@
-http://www.nchc.org.tw
+http://www.nchc.org.tw/tw/
 http://www.hadoop.tw
Index: /nutchez-0.1/debian/nutchez.install
===================================================================
--- /nutchez-0.1/debian/nutchez.install	(revision 79)
+++ /nutchez-0.1/debian/nutchez.install	(revision 80)
@@ -1,5 +1,5 @@
 conf/*		etc/nutch
 bin		opt/nutch
-bin/nutchez*	usr/local/sbin
+bin/nutchez*	usr/local/bin
 lib		opt/nutch
 webapps		opt/nutch
Index: /nutchez-0.1/debian/nutchez.postrm
===================================================================
--- /nutchez-0.1/debian/nutchez.postrm	(revision 79)
+++ /nutchez-0.1/debian/nutchez.postrm	(revision 80)
@@ -14,5 +14,5 @@
   if [ -d $i ];then
     echo "delete this dir :  $i"
-    rm -ir $i
+    rm -r $i
   fi
 done