crawlorder.html

一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫

<!-- ========= 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="CrawlOrder()"><!-- --></A><H3>
CrawlOrder</H3>
<PRE>
public <B>CrawlOrder</B>()</PRE>
<DL>
<DD>Construct a CrawlOrder.
<P>
</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="getUserAgent(org.archive.crawler.datamodel.CrawlURI)"><!-- --></A><H3>
getUserAgent</H3>
<PRE>
public java.lang.String <B>getUserAgent</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>curi</CODE> - 
<DT><B>Returns:</B><DD>user-agent header value to use</DL>
</DD>
</DL>
<HR>

<A NAME="getFrom(org.archive.crawler.datamodel.CrawlURI)"><!-- --></A><H3>
getFrom</H3>
<PRE>
public java.lang.String <B>getFrom</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>curi</CODE> - 
<DT><B>Returns:</B><DD>from header value to use</DL>
</DD>
</DL>
<HR>

<A NAME="getMaxToes()"><!-- --></A><H3>
getMaxToes</H3>
<PRE>
public int <B>getMaxToes</B>()</PRE>
<DL>
<DD>Returns the set number of maximum toe threads.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>Number of maximum toe threads</DL>
</DD>
</DL>
<HR>

<A NAME="getRobotsHonoringPolicy()"><!-- --></A><H3>
getRobotsHonoringPolicy</H3>
<PRE>
public <A HREF="../../../../org/archive/crawler/datamodel/RobotsHonoringPolicy.html" title="class in org.archive.crawler.datamodel">RobotsHonoringPolicy</A> <B>getRobotsHonoringPolicy</B>()</PRE>
<DL>
<DD>This method gets the RobotsHonoringPolicy object from the orders file.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>the new RobotsHonoringPolicy</DL>
</DD>
</DL>
<HR>

<A NAME="getCrawlOrderName()"><!-- --></A><H3>
getCrawlOrderName</H3>
<PRE>
public java.lang.String <B>getCrawlOrderName</B>()</PRE>
<DL>
<DD>Get the name of the order file.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>the name of the order file.</DL>
</DD>
</DL>
<HR>

<A NAME="getController()"><!-- --></A><H3>
getController</H3>
<PRE>
public <A HREF="../../../../org/archive/crawler/framework/CrawlController.html" title="class in org.archive.crawler.framework">CrawlController</A> <B>getController</B>()</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>The crawl controller.</DL>
</DD>
</DL>
<HR>

<A NAME="setController(org.archive.crawler.framework.CrawlController)"><!-- --></A><H3>
setController</H3>
<PRE>
public void <B>setController</B>(<A HREF="../../../../org/archive/crawler/framework/CrawlController.html" title="class in org.archive.crawler.framework">CrawlController</A>&nbsp;controller)</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>controller</CODE> - </DL>
</DD>
</DL>
<HR>

<A NAME="getLoggers()"><!-- --></A><H3>
getLoggers</H3>
<PRE>
public <A HREF="../../../../org/archive/crawler/settings/MapType.html" title="class in org.archive.crawler.settings">MapType</A> <B>getLoggers</B>()</PRE>
<DL>
<DD>Returns the Map of the StatisticsTracking modules that are included in the
 configuration that the current instance of this class is representing.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>Map of the StatisticsTracking modules</DL>
</DD>
</DL>
<HR>

<A NAME="checkUserAgentAndFrom()"><!-- --></A><H3>
checkUserAgentAndFrom</H3>
<PRE>
public void <B>checkUserAgentAndFrom</B>()
                           throws <A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A></PRE>
<DL>
<DD>Checks if the User Agent and From field are set 'correctly' in
 the specified Crawl Order.
<P>
<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="getCheckpointsDirectory()"><!-- --></A><H3>
getCheckpointsDirectory</H3>
<PRE>
public java.io.File <B>getCheckpointsDirectory</B>()</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>Checkpoint directory.</DL>
</DD>
</DL>
<HR>

<A NAME="getSettingsDir(java.lang.String)"><!-- --></A><H3>
getSettingsDir</H3>
<PRE>
public java.io.File <B>getSettingsDir</B>(java.lang.String&nbsp;key)
                            throws javax.management.AttributeNotFoundException</PRE>
<DL>
<DD>Return fullpath to the directory named by <code>key</code>
 in settings.
 If directory does not exist, it and all intermediary dirs
 will be created.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>key</CODE> - Key to use going to settings.
<DT><B>Returns:</B><DD>Full path to directory named by <code>key</code>.
<DT><B>Throws:</B>
<DD><CODE>javax.management.AttributeNotFoundException</CODE></DL>
</DD>
</DL>
<!-- ========= END OF CLASS DATA ========= -->
<HR>


<!-- ======= START OF BOTTOM NAVBAR ====== -->
<A NAME="navbar_bottom"><!-- --></A>
<A HREF="#skip-navbar_bottom" title="Skip navigation links"></A>
<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY="">
<TR>
<TD COLSPAN=2 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
<A NAME="navbar_bottom_firstrow"><!-- --></A>
<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY="">
  <TR ALIGN="center" VALIGN="top">
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="class-use/CrawlOrder.html"><FONT CLASS="NavBarFont1"><B>Use</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../index-all.html"><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>
  </TR>
</TABLE>
</TD>
<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
</EM>
</TD>
</TR>

<TR>
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
&nbsp;<A HREF="../../../../org/archive/crawler/datamodel/CrawlHost.html" title="class in org.archive.crawler.datamodel"><B>PREV CLASS</B></A>&nbsp;
&nbsp;<A HREF="../../../../org/archive/crawler/datamodel/CrawlServer.html" title="class in org.archive.crawler.datamodel"><B>NEXT CLASS</B></A></FONT></TD>
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
  <A HREF="../../../../index.html?org/archive/crawler/datamodel/CrawlOrder.html" target="_top"><B>FRAMES</B></A>  &nbsp;
&nbsp;<A HREF="CrawlOrder.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;
&nbsp;<SCRIPT type="text/javascript">
  <!--
  if(window==top) {
    document.writeln('<A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A>');
  }
  //-->
</SCRIPT>
<NOSCRIPT>
  <A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A>
</NOSCRIPT>


</FONT></TD>
</TR>
<TR>
<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
  SUMMARY:&nbsp;<A HREF="#nested_classes_inherited_from_class_org.archive.crawler.settings.ComplexType">NESTED</A>&nbsp;|&nbsp;<A HREF="#field_summary">FIELD</A>&nbsp;|&nbsp;<A HREF="#constructor_summary">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>
<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
DETAIL:&nbsp;<A HREF="#field_detail">FIELD</A>&nbsp;|&nbsp;<A HREF="#constructor_detail">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>
</TR>
</TABLE>
<A NAME="skip-navbar_bottom"></A>
<!-- ======== END OF BOTTOM NAVBAR ======= -->

<HR>
Copyright &copy; 2003-2006 Internet Archive. All Rights Reserved.
</BODY>
</HTML>