Changeset 80 for nutchez-0.1/conf/nutch-site.xml

Timestamp:

Jun 9, 2009, 6:08:55 PM (15 years ago)

Author:

waue

Message:

NutchEz ..0.1

File:

• nutchez-0.1/conf/nutch-site.xml (modified) (1 diff)

nutchez-0.1/conf/nutch-site.xml

@@ -66 +66 @@
   </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>