配置nutch

sudo gedit /etc/profile

#set nutch
export PATH=/home/nutch/runtime/local/bin:$PATH

nutch

//结果如下：
Usage: nutch COMMAND
where COMMAND is one of:
 inject		inject new urls into the database
 hostinject     creates or updates an existing host table from a text file
 generate 	generate new batches to fetch from crawl db
 fetch 		fetch URLs marked during generate
 parse 		parse URLs marked during fetch
 updatedb 	update web table after parsing
 updatehostdb   update host table after parsing
 readdb 	read/dump records from page database
 readhostdb     display entries from the hostDB
 elasticindex   run the elasticsearch indexer
 solrindex 	run the solr indexer on parsed batches
 solrdedup 	remove duplicates from solr
 parsechecker   check the parser for a given url
 indexchecker   check the indexing filters for a given url
 plugin 	load a plugin and run one of its classes main()
 nutchserver    run a (local) Nutch server on a user defined port
 junit         	runs the given JUnit test
 or
 CLASSNAME 	run the class named CLASSNAME
Most commands print help when invoked w/o parameters.

crawl

//结果如下：
Missing seedDir : crawl <seedDir> <crawlID> <solrURL> <numberOfRounds>