crawljobhandler.html

来自「网络爬虫开源代码」· HTML 代码 · 共 1,532 行 · 第 1/5 页

<DT><B>Parameters:</B><DD><CODE>orderFile</CODE> - Order file to use as the template for the new job.<DD><CODE>name</CODE> - The name of the new job.<DD><CODE>description</CODE> - Descriptions of the job.<DD><CODE>seeds</CODE> - The contents of the new settings' seed file.
<DT><B>Returns:</B><DD>The new crawl job.
<DT><B>Throws:</B>
<DD><CODE><A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A></CODE> - If a problem occurs creating the
             settings.</DL>
</DD>
</DL>
<HR>

<A NAME="checkDirectory(java.io.File)"><!-- --></A><H3>
checkDirectory</H3>
<PRE>
protected void <B>checkDirectory</B>(java.io.File&nbsp;dir)
                       throws <A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A></PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Throws:</B>
<DD><CODE><A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A></CODE></DL>
</DD>
</DL>
<HR>

<A NAME="createNewJob(java.io.File, java.lang.String, java.lang.String, java.lang.String, int)"><!-- --></A><H3>
createNewJob</H3>
<PRE>
protected <A HREF="../../../../org/archive/crawler/admin/CrawlJob.html" title="class in org.archive.crawler.admin">CrawlJob</A> <B>createNewJob</B>(java.io.File&nbsp;orderFile,
                                java.lang.String&nbsp;name,
                                java.lang.String&nbsp;description,
                                java.lang.String&nbsp;seeds,
                                int&nbsp;priority)
                         throws <A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A></PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Throws:</B>
<DD><CODE><A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A></CODE></DL>
</DD>
</DL>
<HR>

<A NAME="newProfile(org.archive.crawler.admin.CrawlJob, java.lang.String, java.lang.String, java.lang.String)"><!-- --></A><H3>
newProfile</H3>
<PRE>
public <A HREF="../../../../org/archive/crawler/admin/CrawlJob.html" title="class in org.archive.crawler.admin">CrawlJob</A> <B>newProfile</B>(<A HREF="../../../../org/archive/crawler/admin/CrawlJob.html" title="class in org.archive.crawler.admin">CrawlJob</A>&nbsp;baseOn,
                           java.lang.String&nbsp;name,
                           java.lang.String&nbsp;description,
                           java.lang.String&nbsp;seeds)
                    throws <A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A>,
                           java.io.IOException</PRE>
<DL>
<DD>Creates a new profile. The new profile will be returned and also
 registered as the handler's 'new job'. The new profile will be based on
 the settings provided but created in a new location on disk.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>baseOn</CODE> - A CrawlJob (with a valid settingshandler) to use as the
            template for the new profile.<DD><CODE>name</CODE> - The name of the new profile.<DD><CODE>description</CODE> - Description of the new profile<DD><CODE>seeds</CODE> - The contents of the new profiles' seed file
<DT><B>Returns:</B><DD>The new profile.
<DT><B>Throws:</B>
<DD><CODE><A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A></CODE>
<DD><CODE>java.io.IOException</CODE></DL>
</DD>
</DL>
<HR>

<A NAME="createSettingsHandler(java.io.File, java.lang.String, java.lang.String, java.lang.String, java.io.File, org.archive.crawler.admin.CrawlJobErrorHandler, java.lang.String, java.lang.String)"><!-- --></A><H3>
createSettingsHandler</H3>
<PRE>
protected <A HREF="../../../../org/archive/crawler/settings/XMLSettingsHandler.html" title="class in org.archive.crawler.settings">XMLSettingsHandler</A> <B>createSettingsHandler</B>(java.io.File&nbsp;orderFile,
                                                   java.lang.String&nbsp;name,
                                                   java.lang.String&nbsp;description,
                                                   java.lang.String&nbsp;seeds,
                                                   java.io.File&nbsp;newSettingsDir,
                                                   <A HREF="../../../../org/archive/crawler/admin/CrawlJobErrorHandler.html" title="class in org.archive.crawler.admin">CrawlJobErrorHandler</A>&nbsp;errorHandler,
                                                   java.lang.String&nbsp;filename,
                                                   java.lang.String&nbsp;seedfile)
                                            throws <A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A></PRE>
<DL>
<DD>Creates a new settings handler based on an existing job. Basically all
 the settings file for the 'based on' will be copied to the specified
 directory.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>orderFile</CODE> - Order file to base new order file on.  Cannot be null.<DD><CODE>name</CODE> - Name for the new settings<DD><CODE>description</CODE> - Description of the new settings.<DD><CODE>seeds</CODE> - The contents of the new settings' seed file.<DD><CODE>newSettingsDir</CODE> - <DD><CODE>errorHandler</CODE> - <DD><CODE>filename</CODE> - Name of new order file.<DD><CODE>seedfile</CODE> - Name of new seeds file.
<DT><B>Returns:</B><DD>The new settings handler.
<DT><B>Throws:</B>
<DD><CODE><A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A></CODE> - If there are problems with reading the 'base on'
             configuration, with writing the new configuration or it's
             seed file.</DL>
</DD>
</DL>
<HR>

<A NAME="updateRecoveryPaths(java.io.File, org.archive.crawler.settings.SettingsHandler, java.lang.String)"><!-- --></A><H3>
updateRecoveryPaths</H3>
<PRE>
protected void <B>updateRecoveryPaths</B>(java.io.File&nbsp;recover,
                                   <A HREF="../../../../org/archive/crawler/settings/SettingsHandler.html" title="class in org.archive.crawler.settings">SettingsHandler</A>&nbsp;sh,
                                   java.lang.String&nbsp;jobName)
                            throws <A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A></PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>recover</CODE> - Source to use recovering. Can be full path to a recovery log
            or full path to a checkpoint src dir.<DD><CODE>sh</CODE> - Settings Handler to update.<DD><CODE>jobName</CODE> - Name of this job.
<DT><B>Throws:</B>
<DD><CODE><A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A></CODE></DL>
</DD>
</DL>
<HR>

<A NAME="discardNewJob()"><!-- --></A><H3>
discardNewJob</H3>
<PRE>
public void <B>discardNewJob</B>()</PRE>
<DL>
<DD>Discard the handler's 'new job'. This will remove any files/directories
 written to disk.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="getNewJob()"><!-- --></A><H3>
getNewJob</H3>
<PRE>
public <A HREF="../../../../org/archive/crawler/admin/CrawlJob.html" title="class in org.archive.crawler.admin">CrawlJob</A> <B>getNewJob</B>()</PRE>
<DL>
<DD>Get the handler's 'new job'
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>the handler's 'new job'</DL>
</DD>
</DL>
<HR>

<A NAME="isRunning()"><!-- --></A><H3>
isRunning</H3>
<PRE>
public boolean <B>isRunning</B>()</PRE>
<DL>
<DD>Is the crawler accepting crawl jobs to run?
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>True if the next availible CrawlJob will be crawled. False otherwise.</DL>
</DD>
</DL>
<HR>

<A NAME="isCrawling()"><!-- --></A><H3>
isCrawling</H3>
<PRE>
public boolean <B>isCrawling</B>()</PRE>
<DL>
<DD>Is a crawl job being crawled?
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>True if a job is actually being crawled (even if it is paused).
         False if no job is being crawled.</DL>
</DD>
</DL>
<HR>

<A NAME="startCrawler()"><!-- --></A><H3>
startCrawler</H3>
<PRE>
public void <B>startCrawler</B>()</PRE>
<DL>
<DD>Allow jobs to be crawled.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="stopCrawler()"><!-- --></A><H3>
stopCrawler</H3>
<PRE>
public void <B>stopCrawler</B>()</PRE>
<DL>
<DD>Stop future jobs from being crawled.

 This action will not affect the current job.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="startNextJob()"><!-- --></A><H3>
startNextJob</H3>
<PRE>
protected final void <B>startNextJob</B>()</PRE>
<DL>
<DD>Start next crawl job.

 If a is job already running this method will do nothing.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="startNextJobInternal()"><!-- --></A><H3>
startNextJobInternal</H3>
<PRE>
protected void <B>startNextJobInternal</B>()</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="kickUpdate()"><!-- --></A><H3>
kickUpdate</H3>
<PRE>
public void <B>kickUpdate</B>()</PRE>
<DL>
<DD>Forward a 'kick' update to current job if any.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="loadOptions(java.lang.String)"><!-- --></A><H3>
loadOptions</H3>
<PRE>
public static java.util.ArrayList&lt;java.lang.String&gt; <B>loadOptions</B>(java.lang.String&nbsp;file)
                                                         throws java.io.IOException</PRE>
<DL>
<DD>Loads options from a file. Typically these are a list of available
 modules that can be plugged into some part of the configuration.
 For examples Processors, Frontiers, Filters etc. Leading and trailing
 spaces are trimmed from each line.
 
 <p>Options are loaded from the CLASSPATH.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>file</CODE> - the name of the option file (without path!)
<DT><B>Returns:</B><DD>The option file with each option line as a seperate entry in the
         ArrayList.
<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE> - when there is trouble reading the file.</DL>
</DD>
</DL>
<HR>

<A NAME="getInitialMarker(java.lang.String, boolean)"