| <?xml version="1.0" ?> |
| <?xml:stylesheet type="text/xsl" href="nutch-conf.xsl"?> |
| |
| <!-- Overidden defaults for intranet use. --> |
| |
| <!-- Do not modify this file directly. Instead, copy entries that you --> |
| <!-- wish to modify from this file into nutch-site.xml and change them --> |
| <!-- there. If nutch-site.xml does not already exist, create it. --> |
| |
| <nutch-conf> |
| |
| <property> |
| <name>urlfilter.regex.file</name> |
| <value>crawl-urlfilter.txt</value> |
| </property> |
| |
| <property> |
| <name>indexer.boost.by.link.count</name> |
| <value>true</value> |
| <description>When true scores for a page are multipled by the log of |
| the number of incoming links to the page.</description> |
| </property> |
| |
| <property> |
| <name>db.ignore.internal.links</name> |
| <value>false</value> |
| <description>If true, when adding new links to a page, links from |
| the same host are ignored. This is an effective way to limit the |
| size of the link database, keeping the only the highest quality |
| links. |
| </description> |
| </property> |
| |
| <property> |
| <name>fetcher.server.delay</name> |
| <value>1.0</value> |
| <description>The number of seconds the fetcher will delay between |
| successive requests to the same server.</description> |
| </property> |
| |
| <property> |
| <name>http.max.delays</name> |
| <value>100</value> |
| <description>The number of times a thread will delay when trying to |
| fetch a page. When using the crawl tool there are likely to be very |
| few different hosts, so we need to be willing to wait longer for |
| each.</description> |
| </property> |
| |
| </nutch-conf> |