现在正对搜索引擎有兴趣,
我的搜索基于nutch,并结合了ICTCLAS,分词和速度都不错。
这样做可以不用crywin来模拟linux
下面是在win nt下调用nutch的脚本,
你可以自己改一下,这样就可以很方便的实现自动运行了。
有兴趣的朋友可以用一下,大大方便了操作。
nutch.bat
@cmd /V:on /c %~dp0nutch1.bat %*
nutch1.bat
@echo on
rem *********************************************************************
我的搜索基于nutch,并结合了ICTCLAS,分词和速度都不错。
这样做可以不用crywin来模拟linux
下面是在win nt下调用nutch的脚本,
你可以自己改一下,这样就可以很方便的实现自动运行了。
有兴趣的朋友可以用一下,大大方便了操作。
nutch.bat
@cmd /V:on /c %~dp0nutch1.bat %*
nutch1.bat
@echo on
rem *********************************************************************
rem * A script to launch nutch on Windows 2000/XP System.
rem *
rem * Written by babatu
rem * babatu@gmail.com blog: blog.babatu.com
rem *
rem * Because delayed environment is used, cmd /V:on should be used to
rem * run this script.
rem ****************************** ******************************
*****
if "%OS%"=="Windows_NT" @setlocal
if "%OS%"=="WINNT" @setlocal
if "%1" == "" goto :msg
goto :begin
:msg
echo "Usage: nutch COMMAND"
echo "where COMMAND is one of:"
echo " crawl one-step crawler for intranets"
echo " readdb read / dump crawl db"
echo " readlinkdb read / dump link db"
echo " inject inject new urls into the database"
<script type="text/javascript"> </script> echo " generate generate new segments to fetch"
echo " fetch fetch a segment's pages"
echo " parse parse a segment's pages"
echo " segread read / dump segment data"
echo " updatedb update crawl db from segments after fetching"
echo " invertlinks create a linkdb from parsed segments"
echo " index run the indexer on parsed segments and linkdb"
echo " merge merge several segment indexes"
echo " dedup remove duplicates from a set of segment indexes"
echo " plugin load a plugin and run one of its classes main()"
echo " server run a search server"
echo " or"
echo " CLASSNAME run the class named CLASSNAME"
echo "Most commands print help when invoked w/o parameters."
pause
goto :end
:begin
rem %~dp0 这个脚本的扩展path ( expanded pathname of the current script under NT)
set DEFAULT_NUTCH_HOME=%~dp0..
rem set DEFAULT_NUTCH_HOME=..
if "%NUTCH_HOME%"=="" set NUTCH_HOME=%DEFAULT_NUTCH_HOME %
set DEFAULT_NUTCH_HOME=""
rem 设置默认DEFAULT_NUTCH_HOME
echo %NUTCH_HOME%
rem set _USE_CLASSPATH=yes
if "%CLASSPATH%"=="" ( set CLASSPATH=%JAVA_HOME%/lib /tools.jar) ELSE set
CLASSPATH=%CLASSPATH%;%JAVA _HOME%/lib/tools.jar
<script type="text/javascript"> </script> set CLASSPATH=%CLASSPATH%;%NUTCH _HOME%/conf;
echo %CLASSPATH%
echo before other
rem for developers, add plugins, job & test code to CLASSPATH
if exist %NUTCH_HOME%/build/plugins set
CLASSPATH=%CLASSPATH%;%NUTCH _HOME%/build
for /R %NUTCH_HOME%/build %%i in (nutch*.job) do set
CLASSPATH=!CLASSPATH!;%%i
if exist %NUTCH_HOME%/build/test /classes set
CLASSPATH=%CLASSPATH%;%NUTCH _HOME%/build/test/classes
rem for releases, add Nutch job to CLASSPATH
for /R %NUTCH_HOME% %%i in (nutch*.job) do set CLASSPATH=!CLASSPATH!;%%i
rem add plugins to classpath
if exist %NUTCH_HOME%/plugins set CLASSPATH=%CLASSPATH%;%NUTCH _HOME%
rem add libs to CLASSPATH
for /R %NUTCH_HOME%/lib %%f in (*.jar) do set CLASSPATH=!CLASSPATH!;%%f
echo %CLASSPATH%
rem translate command
if "%1"=="crawl" set CLASS=org.apache.nutch.crawl.Crawl
if "%1"=="inject" set CLASS=org.apache.nutch.crawl.Injecto r
if "%1"=="generate" set CLASS=org.apache.nutch.crawl.Generat or
if "%1"=="fetch" set CLASS=org.apache.nutch.fetcher .Fetcher
if "%1"=="parse" set CLASS=org.apache.nutch.parse.ParseSe gment
if "%1"=="readdb" set CLASS=org.apache.nutch.crawl.CrawlDb Reader
if "%1"=="readlinkdb" set CLASS=org.apache.nutch.crawl.LinkDbR eader
if "%1"=="segread" set CLASS=org.apache.nutch.segment .SegmentReader
if "%1"=="updatedb" set CLASS=org.apache.nutch.crawl.CrawlDb
if "%1"=="invertlinks" set CLASS=org.apache.nutch.crawl.LinkDb
if "%1"=="index" set CLASS=org.apache.nutch.indexer .Indexer
if "%1"=="dedup" set CLASS=org.apache.nutch.indexer <script type="text/javascript">
</script> .DeleteDuplicates
if "%1"=="merge" set CLASS=org.apache.nutch.indexer .IndexMerger
if "%1"=="plugin" set CLASS=org.apache.nutch.plugin .PluginRepository
if "%1"=="server" set CLASS='
org.apache.nutch.searcher .DistributedSearch$Server'
if "%CLASS%"=="" set CLASS=%1
%JAVA_HOME%/bin/java -cp %CLASSPATH% %CLASS% %*
if "%OS%"=="Windows_NT" @endlocal
if "%OS%"=="WINNT" @endlocal
:end
rem *
rem * Written by babatu
rem * babatu@gmail.com blog: blog.babatu.com
rem *
rem * Because delayed environment is used, cmd /V:on should be used to
rem * run this script.
rem ******************************
if "%OS%"=="Windows_NT" @setlocal
if "%OS%"=="WINNT" @setlocal
if "%1" == "" goto :msg
goto :begin
:msg
echo "Usage: nutch COMMAND"
echo "where COMMAND is one of:"
echo " crawl one-step crawler for intranets"
echo " readdb read / dump crawl db"
echo " readlinkdb read / dump link db"
echo " inject inject new urls into the database"
<script type="text/javascript"> </script> echo " generate generate new segments to fetch"
echo " fetch fetch a segment's pages"
echo " parse parse a segment's pages"
echo " segread read / dump segment data"
echo " updatedb update crawl db from segments after fetching"
echo " invertlinks create a linkdb from parsed segments"
echo " index run the indexer on parsed segments and linkdb"
echo " merge merge several segment indexes"
echo " dedup remove duplicates from a set of segment indexes"
echo " plugin load a plugin and run one of its classes main()"
echo " server run a search server"
echo " or"
echo " CLASSNAME run the class named CLASSNAME"
echo "Most commands print help when invoked w/o parameters."
pause
goto :end
:begin
rem %~dp0 这个脚本的扩展path ( expanded pathname of the current script under NT)
set DEFAULT_NUTCH_HOME=%~dp0..
rem set DEFAULT_NUTCH_HOME=..
if "%NUTCH_HOME%"=="" set NUTCH_HOME=%DEFAULT_NUTCH_HOME
set DEFAULT_NUTCH_HOME=""
rem 设置默认DEFAULT_NUTCH_HOME
echo %NUTCH_HOME%
rem set _USE_CLASSPATH=yes
if "%CLASSPATH%"=="" ( set CLASSPATH=%JAVA_HOME%/lib
CLASSPATH=%CLASSPATH%;%JAVA
<script type="text/javascript"> </script> set CLASSPATH=%CLASSPATH%;%NUTCH
echo %CLASSPATH%
echo before other
rem for developers, add plugins, job & test code to CLASSPATH
if exist %NUTCH_HOME%/build/plugins set
CLASSPATH=%CLASSPATH%;%NUTCH
for /R %NUTCH_HOME%/build %%i in (nutch*.job) do set
CLASSPATH=!CLASSPATH!;%%i
if exist %NUTCH_HOME%/build/test
CLASSPATH=%CLASSPATH%;%NUTCH
rem for releases, add Nutch job to CLASSPATH
for /R %NUTCH_HOME% %%i in (nutch*.job) do set CLASSPATH=!CLASSPATH!;%%i
rem add plugins to classpath
if exist %NUTCH_HOME%/plugins set CLASSPATH=%CLASSPATH%;%NUTCH
rem add libs to CLASSPATH
for /R %NUTCH_HOME%/lib %%f in (*.jar) do set CLASSPATH=!CLASSPATH!;%%f
echo %CLASSPATH%
rem translate command
if "%1"=="crawl" set CLASS=org.apache.nutch.crawl.Crawl
if "%1"=="inject" set CLASS=org.apache.nutch.crawl.Injecto
if "%1"=="generate" set CLASS=org.apache.nutch.crawl.Generat
if "%1"=="fetch" set CLASS=org.apache.nutch.fetcher
if "%1"=="parse" set CLASS=org.apache.nutch.parse.ParseSe
if "%1"=="readdb" set CLASS=org.apache.nutch.crawl.CrawlDb
if "%1"=="readlinkdb" set CLASS=org.apache.nutch.crawl.LinkDbR
if "%1"=="segread" set CLASS=org.apache.nutch.segment
if "%1"=="updatedb" set CLASS=org.apache.nutch.crawl.CrawlDb
if "%1"=="invertlinks" set CLASS=org.apache.nutch.crawl.LinkDb
if "%1"=="index" set CLASS=org.apache.nutch.indexer
if "%1"=="dedup" set CLASS=org.apache.nutch.indexer
if "%1"=="merge" set CLASS=org.apache.nutch.indexer
if "%1"=="plugin" set CLASS=org.apache.nutch.plugin
if "%1"=="server" set CLASS='
org.apache.nutch.searcher
if "%CLASS%"=="" set CLASS=%1
%JAVA_HOME%/bin/java -cp %CLASSPATH% %CLASS% %*
if "%OS%"=="Windows_NT" @endlocal
if "%OS%"=="WINNT" @endlocal
:end