$ cd /usr/local/nutch-0.9
$ mkdir urls-kazmuzikblog
$ vi urls-kazmuzikblog/nutch
$ cat urls-kazmuzikblog/nutch
http://kazuomik.livejournal.com/
$ vi conf/conf/crawl-urlfilter.txt
$ cat conf/conf/crawl-urlfilter.txt
+^http://kazuomik.livejournal.com/
-.
$ export NUTCH_JAVA_HOME=/usr/java/jdk1.6.0_01
$ bin/nutch crawl urls-kazmuzikblog -dir crawl-1 -depth 3
crawl started in: crawl-1
rootUrlDir = urls-kazmuzikblog
threads = 10
depth = 3
...
crawl finished: crawl-1
$
|