heritrix.html

用JAVA编写的,在做实验的时候留下来的,本来想删的,但是传上来,大家分享吧

<CODE>static&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../org/archive/crawler/Heritrix.html#shutdown()">shutdown</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>static&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../org/archive/crawler/Heritrix.html#shutdown(int)">shutdown</A></B>(int&nbsp;exitCode)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Shutdown all running heritrix instances and the JVM.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../org/archive/crawler/Heritrix.html#start()">start</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Start Heritrix.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../org/archive/crawler/Heritrix.html#startCrawling()">startCrawling</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected static&nbsp;java.lang.String</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../org/archive/crawler/Heritrix.html#startEmbeddedWebserver(java.util.Collection, int, java.lang.String)">startEmbeddedWebserver</A></B>(java.util.Collection&lt;java.lang.String&gt;&nbsp;hosts,
                       int&nbsp;port,
                       java.lang.String&nbsp;adminLoginPassword)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Start up the embedded Jetty webserver instance.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected static&nbsp;java.lang.String</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../org/archive/crawler/Heritrix.html#startEmbeddedWebserver(int, boolean, java.lang.String)">startEmbeddedWebserver</A></B>(int&nbsp;port,
                       boolean&nbsp;lho,
                       java.lang.String&nbsp;adminLoginPassword)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;<B>Deprecated.</B>&nbsp;<I>Use startEmbeddedWebserver(hosts, port, adminLoginPassword)</I></TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../org/archive/crawler/Heritrix.html#stop()">stop</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Stop Heritrix.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../org/archive/crawler/Heritrix.html#stopCrawling()">stopCrawling</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected static&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../org/archive/crawler/Heritrix.html#unregisterHeritrix(org.archive.crawler.Heritrix)">unregisterHeritrix</A></B>(<A HREF="../../../org/archive/crawler/Heritrix.html" title="class in org.archive.crawler">Heritrix</A>&nbsp;h)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>static&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../org/archive/crawler/Heritrix.html#unregisterMBean(javax.management.MBeanServer, javax.management.ObjectName)">unregisterMBean</A></B>(javax.management.MBeanServer&nbsp;server,
                javax.management.ObjectName&nbsp;name)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>static&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../org/archive/crawler/Heritrix.html#unregisterMBean(javax.management.MBeanServer, java.lang.String, java.lang.String)">unregisterMBean</A></B>(javax.management.MBeanServer&nbsp;server,
                java.lang.String&nbsp;name,
                java.lang.String&nbsp;type)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
</TABLE>
&nbsp;<A NAME="methods_inherited_from_class_java.lang.Object"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left"><B>Methods inherited from class java.lang.Object</B></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD><CODE>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</CODE></TD>
</TR>
</TABLE>
&nbsp;
<P>

<!-- ============ FIELD DETAIL =========== -->

<A NAME="field_detail"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
<TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2">
<B>Field Detail</B></FONT></TH>
</TR>
</TABLE>

<A NAME="DEFAULT_ENCODING"><!-- --></A><H3>
DEFAULT_ENCODING</H3>
<PRE>
public static final java.lang.String <B>DEFAULT_ENCODING</B></PRE>
<DL>
<DD>Default encoding.
 
 Used for content when fetching if none specified.
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../constant-values.html#org.archive.crawler.Heritrix.DEFAULT_ENCODING">Constant Field Values</A></DL>
</DL>

<!-- ========= CONSTRUCTOR DETAIL ======== -->

<A NAME="constructor_detail"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
<TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2">
<B>Constructor Detail</B></FONT></TH>
</TR>
</TABLE>

<A NAME="Heritrix()"><!-- --></A><H3>
Heritrix</H3>
<PRE>
public <B>Heritrix</B>()
         throws java.io.IOException</PRE>
<DL>
<DD>Constructor.
 Does not register the created instance with JMX.  Assumed this
 constructor is used by such as JMX agent creating an instance of
 Heritrix at the commmand of a remote client (In this case Heritrix will
 be registered by the invoking agent).
<P>
<DL>

<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE></DL>
</DL>
<HR>

<A NAME="Heritrix(boolean)"><!-- --></A><H3>
Heritrix</H3>
<PRE>
public <B>Heritrix</B>(boolean&nbsp;jmxregister)
         throws java.io.IOException</PRE>
<DL>
<DL>

<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE></DL>
</DL>
<HR>

<A NAME="Heritrix(java.lang.String, boolean)"><!-- --></A><H3>
Heritrix</H3>
<PRE>
public <B>Heritrix</B>(java.lang.String&nbsp;name,
                boolean&nbsp;jmxregister)
         throws java.io.IOException</PRE>
<DL>
<DD>Constructor.
<P>
<DL>
<DT><B>Parameters:</B><DD><CODE>name</CODE> - If null, we bring up the default Heritrix instance.<DD><CODE>jmxregister</CODE> - True if we are to register this instance with JMX
 agent.
<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE></DL>
</DL>
<HR>

<A NAME="Heritrix(java.lang.String, boolean, org.archive.crawler.admin.CrawlJobHandler)"><!-- --></A><H3>
Heritrix</H3>
<PRE>
public <B>Heritrix</B>(java.lang.String&nbsp;name,
                boolean&nbsp;jmxregister,
                <A HREF="../../../org/archive/crawler/admin/CrawlJobHandler.html" title="class in org.archive.crawler.admin">CrawlJobHandler</A>&nbsp;cjh)
         throws java.io.IOException</PRE>
<DL>
<DD>Constructor.
<P>
<DL>
<DT><B>Parameters:</B><DD><CODE>name</CODE> - If null, we bring up the default Heritrix instance.<DD><CODE>jmxregister</CODE> - True if we are to register this instance with JMX
 agent.<DD><CODE>cjh</CODE> - CrawlJobHandler to use.
<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE></DL>
</DL>

<!-- ============ METHOD DETAIL ========== -->

<A NAME="method_detail"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
<TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2">
<B>Method Detail</B></FONT></TH>
</TR>
</TABLE>

<A NAME="containerInitialization()"><!-- --></A><H3>
containerInitialization</H3>
<PRE>
protected static void <B>containerInitialization</B>()
                                       throws java.io.IOException</PRE>
<DL>
<DD>Run setup tasks for this 'container'. Idempotent.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE></DL>
</DD>
</DL>
<HR>

<A NAME="destroy()"><!-- --></A><H3>
destroy</H3>
<PRE>
public void <B>destroy</B>()</PRE>
<DL>
<DD>Do inverse of construction. Used by anyone who does a 'new Heritrix' when
 they want to cleanup the instance.
 Of note, there may be Heritrix threads still hanging around after the
 call to destroy completes.  They'll eventually go down after they've
 finished their cleanup routines.  In particular, if you are watching
 Heritrix via JMX, you can see the Heritrix instance JMX bean unregister
 ahead of the CrawlJob JMX bean that its hosting.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="main(java.lang.String[])"><!-- --></A><H3>
main</H3>
<PRE>
public static void <B>main</B>(java.lang.String[]&nbsp;args)
                 throws java.lang.Exception</PRE>
<DL>
<DD>Launch program.
 Optionally will launch a web server to host UI.  Will also register
 Heritrix MBean with first found JMX Agent (Usually the 1.5.0 JVM
 Agent).
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>args</CODE> - Command line arguments.
<DT><B>Throws:</B>
<DD><CODE>java.lang.Exception</CODE></DL>
</DD>
</DL>
<HR>

<A NAME="doCmdLineArgs(java.lang.String[])"><!-- --></A><H3>
doCmdLineArgs</H3>
<PRE>
protected static java.lang.String <B>doCmdLineArgs</B>(java.lang.String[]&nbsp;args)
                                         throws java.lang.Exception</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Throws:</B>
<DD><CODE>java.lang.Exception</CODE></DL>
</DD>
</DL>
<HR>

<A NAME="getHeritrixOut()"><!-- --></A><H3>
getHeritrixOut</H3>
<PRE>
public static java.lang.String <B>getHeritrixOut</B>()</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>The file we dump stdout and stderr into.</DL>
</DD>
</DL>
<HR>