Windows 下运行Nutch批处理脚本

Windows 下运行Nutch批处理脚本 日期：2007-08-03   点击： <script src="/plus/count.php?view=yes&amp;aid=39"></script> 403   作者：不会游泳的鱼   来源：   字体：[ 大 中 小 ]

<script type="text/javascript"></script><script src="http://pagead2.googlesyndication.com/pagead/show_ads.js" type="text/javascript"></script><script src="http://pagead2.googlesyndication.com/pagead/show_ads_sra.js"></script>

将以下文本内容存放入NUTCH_HOME\bin 目录下 ， 命名随便，设置以下JAVA_HOME 和 NUTCH_HOME，然后在命令行运行 %NUTCH_HOME%\bin\nutch

 @echo off
set JAVA_HEAP_MAX="-Xmx512M"
if not "%1"=="" goto INIT else goto echoMSG
:echoMSG
  echo Title:欢迎使用北京线点科技 Nutch 运行脚本
  echo Author:jaddy0302 mail:jaddy0302@126.com QQ:5622928
  echo Site:http://www.xd-tech.com.cn 线点科技 专业垂直搜索引擎产品
  echo Nutch Version: 0.7.2
  echo Usage: nutch COMMAND
  echo where COMMAND is one of:
  echo   crawl             one-step crawler for intranets
  echo   admin             database administration, including creation
  echo   inject            inject new urls into the database
  echo   generate          generate new segments to fetch
  echo   fetchlist         print the fetchlist of a segment
  echo   fetch             fetch a segment's pages
  echo   parse             parse a segment's pages
  echo   index             run the indexer on a segment's fetcher output
  echo   merge             merge several segment indexes
  echo   dedup             remove duplicates from a set of segment indexes
  echo   updatedb          update db from segments after fetching
  echo   updatesegs        update segments with link data from the db
  echo   mergesegs         merge multiple segments into a single segment
  echo   readdb            examine arbitrary fields of the database
  echo   analyze           adjust database link-analysis scoring
  echo   prune             prune segment index(es) of unwanted content
  echo   segread           read, fix and dump segment data
  echo   segslice          append, join and slice segment data
  echo   server            run a search server
  echo   namenode          run the NDFS namenode
  echo   datanode          run an NDFS datanode
  echo   ndfs              run an NDFS admin client
  echo   jobtracker        run the MapReduce job Tracker node
  echo   tasktracker       run a MapReduce task Tracker node
  echo  or
  echo   CLASSNAME         run the class named CLASSNAME
  echo Most commands print help when invoked w/o parameters.
  goto end;
:INIT 
  set NUTCH_HOME=C:\work\nutch-0.7.2
  if "%NUTCH_HOME%"=="" set NUTCH_HOME=.. 
  set CLASSPATH=%NUTCH_HOME%;%NUTCH_HOME%\conf;%NUTCH_HOME%\plugin
  @echo @echo off>setclasspath.bat
  for %%i in (%NUTCH_HOME%\nutch-*.jar) do @echo set CLASSPATH=%%CLASSPATH%%;%%i>>setclasspath.bat;& for %%i in (%NUTCH_HOME%\lib\*.jar) do @echo set CLASSPATH=%%CLASSPATH%%;%%i>>setclasspath.bat;
  goto EXEC
:EXEC
  call setclasspath
  if  "%1" == "crawl" set CLASS=org.apache.nutch.tools.CrawlTool
  if  "%1" == "admin" set CLASS=org.apache.nutch.tools.WebDBAdminTool
  if  "%1" == "inject" set CLASS=org.apache.nutch.db.WebDBInjector
  if  "%1" == "generate" set CLASS=org.apache.nutch.tools.FetchListTool
  if  "%1" == "fetchlist" set CLASS=org.apache.nutch.pagedb.FetchListEntry
  if  "%1" == "fetch" set CLASS=org.apache.nutch.fetcher.Fetcher
  if  "%1" == "parse" set CLASS=org.apache.nutch.tools.ParseSegment
  if  "%1" == "index" set CLASS=org.apache.nutch.indexer.IndexSegment
  if  "%1" == "merge" set CLASS=org.apache.nutch.indexer.IndexMerger
  if  "%1" == "dedup" set CLASS=org.apache.nutch.indexer.DeleteDuplicates
  if  "%1" == "updatedb" set CLASS=org.apache.nutch.tools.UpdateDatabaseTool
  if  "%1" == "updatesegs" set CLASS=org.apache.nutch.tools.UpdateSegmentsFromDb
  if  "%1" == "mergesegs" set CLASS=org.apache.nutch.tools.SegmentMergeTool
  if  "%1" == "readdb" set CLASS=org.apache.nutch.db.WebDBReader
  if  "%1" == "prune" set CLASS=org.apache.nutch.tools.PruneIndexTool
  if  "%1" == "segread" set CLASS=org.apache.nutch.segment.SegmentReader
  if  "%1" == "segslice" set CLASS=org.apache.nutch.segment.SegmentSlicer
  if  "%1" == "analyze" set CLASS=org.apache.nutch.tools.LinkAnalysisTool
  if  "%1" == "server" set CLASS=org.apache.nutch.searcher.DistributedSearch$Server
  if  "%1" == "namenode" set CLASS=org.apache.nutch.ndfs.NDFS$NameNode
  if  "%1" == "datanode" set CLASS=org.apache.nutch.ndfs.NDFS$DataNode
  if  "%1" == "ndfs" set CLASS=org.apache.nutch.fs.TestClient
  if  "%1" == "jobtracker" set CLASS=org.apache.nutch.mapReduce.JobTracker
  if  "%1" == "tasktracker" set CLASS=org.apache.nutch.mapReduce.TaskTracker
  call "%JAVA_HOME%\bin\java" %JAVA_HEAP_MAX% -classpath "%CLASSPATH%" %CLASS% %2 %3 %4 %5 %6 %7 %8 %9
:end