linux 启动nutch
[root@localhost nutch]# export JAVA_HOME=/usr/java/jdk1.7.0 [root@localhost nutch]# bin/nutch crawl Usage: Crawl <urlDir> -solr <solrURL> [-dir d] [-threads n] [-depth i] [-topN N] [root@localhost nutch]# bin/nutch crawl urls -dir urls -threads 3 -depth 5 -topN 1000