忍者ブログの元開発者が送る愛と感動と涙のスペクタクル。プログラムの開発日誌やタダの日記です。
# wget http://download.oracle.com/otn-pub/java/jdk/6u33-b03/jdk-6u33-linux-x64.bin
# chmod a+x jdk-6u33-linux-x64.bin
# ./jdk-6u33-linux-x64.bin
# vi /etc/profile
export JAVA_HOME=/usr/java/default
export PATH=$PATH:$JAVA_HOME/bin
export CLASSPATH=.:$JAVA_HOME/jre/lib:$JAVA_HOME/lib:$JAVA_HOME/lib/tools.jar
# source /etc/profile
# cd /etc/yum.repos.d/
# wget http://archive.cloudera.com/redhat/cdh/cloudera-cdh3.repo
# yum install hadoop-hbase hadoop-hbase-master hadoop-0.20-namenode hadoop-0.20-jobtracker hadoop-0.20-secondarynamenode hadoop-0.20-tasktracker hadoop-zookeeper
# vi /etc/hbase/conf/hbase-evn.sh #以下の行のコメントアウトを外す
export HBASE_MANAGES_ZK=true
# vi /etc/hbase/conf/hbase-site.xml #<configuration>の中に以下を追加
<property>
<name>hbase.zookeeper.quorum</name>
<value>127.0.0.1</value>
</property>
<property>
<name>hbase.zookeeper.property.clientPort</name>
<value>2181</value>
</property>
<property>
<name>hbase.zookeeper.property.maxClientCnxns</name>
<value>200</value>
</property>
# service hadoop-0.20-datanode start
# service hadoop-0.20-jobtracker start
# service hadoop-0.20-namenode start
# service hadoop-0.20-secondarynamenode start
# service hadoop-0.20-tasktracker start
# service hadoop-hbase-master start
# wget ftp://ftp.riken.jp/net/apache/maven/binaries/apache-maven-3.0.4-bin.tar.gz
# tar zxf ./apache-maven-3.0.4-bin.tar.gz
# mv /usr/local/src/apache-maven-3.0.4 /usr/share/maven
# vi /etc/profile
export M2_HOME=/usr/share/maven
export M2=$M2_HOME/bin
export PATH=$PATH:$M2
# source /etc/profile
# wget ftp://ftp.meisei-u.ac.jp/mirror/apache/dist/gora/gora-0.2-src.tar.gz
# tar zxvf ./gora-0.2-src.tar.gz
# cd ./apache-gora-0.2/
# mvn clean compile
# cd /usr/local/src
# wget http://ftp.riken.jp/net/apache//ant/binaries/apache-ant-1.8.4-bin.tar.gz
# tar zxf ./apache-ant-1.8.4-bin.tar.gz
# cp -R /usr/local/src/apache-ant-1.8.4 /usr/share/ant
# vi /etc/profile
export ANT_HOME=/usr/share/ant
export PATH=$PATH:$ANT_HOME/bin
# cd /usr/local/src
# mkdir ./nutch2.0
# cd ./nutch2.0
# wget ftp://ftp.riken.jp/net/apache/nutch/2.0/apache-nutch-2.0-src.tar.gz
# tar zxvf ./apache-nutch-2.0-src.tar.gz
# vi conf/nutch-site.xml #<configuration></configuration>の中に以下を追加
<property>
<name>storage.data.store.class</name>
<value>org.apache.gora.hbase.store.HBaseStore</value>
<property>
<property>
<name>http.agent.name</name>
<value>nutch2.0</value>
</property>
# vi ivy/ivy.xml #108行目付近にある下記の記述のコメントアウトを外す
<dependency org="org.apache.gora" name="gora-hbase" rev="0.2" conf="*->default" />
#vi conf/gora.properties
gora.datastore.default=org.apache.gora.hbase.store.HBaseStore
# ant
BUILD SUCCESSFUL
Total time: 3 minutes 33 seconds
# cd /usr/local/src/nutch2.0
# ./runtime/deploy/bin/nutch
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 segments 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
solrindex run the solr indexer on parsed segments and linkdb
solrdedup remove duplicates from solr
parsechecker check the parser for a given url
plugin load a plugin and run one of its classes main()
junit runs the given JUnit test
or
CLASSNAME run the class named CLASSNAME
Most commands print help when invoked w/o parameters.
画像RSS
おまとめボタン
カテゴリー
忍者カウンター
忍者ビジター
忍者アド
ブログ内検索
リンクなどなど
最新コメント
プロフィール
アーカイブ
フリーエリア
忍者ツールズプロフィール