statisticstracker.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

<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="lastPagesFetchedCount"><!-- --></A><H3>
lastPagesFetchedCount</H3>
<PRE>
protected long <B>lastPagesFetchedCount</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="lastProcessedBytesCount"><!-- --></A><H3>
lastProcessedBytesCount</H3>
<PRE>
protected long <B>lastProcessedBytesCount</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="discoveredUriCount"><!-- --></A><H3>
discoveredUriCount</H3>
<PRE>
protected long <B>discoveredUriCount</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="queuedUriCount"><!-- --></A><H3>
queuedUriCount</H3>
<PRE>
protected long <B>queuedUriCount</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="finishedUriCount"><!-- --></A><H3>
finishedUriCount</H3>
<PRE>
protected long <B>finishedUriCount</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="downloadedUriCount"><!-- --></A><H3>
downloadedUriCount</H3>
<PRE>
protected long <B>downloadedUriCount</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="downloadFailures"><!-- --></A><H3>
downloadFailures</H3>
<PRE>
protected long <B>downloadFailures</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="downloadDisregards"><!-- --></A><H3>
downloadDisregards</H3>
<PRE>
protected long <B>downloadDisregards</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="docsPerSecond"><!-- --></A><H3>
docsPerSecond</H3>
<PRE>
protected double <B>docsPerSecond</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="currentDocsPerSecond"><!-- --></A><H3>
currentDocsPerSecond</H3>
<PRE>
protected double <B>currentDocsPerSecond</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="currentKBPerSec"><!-- --></A><H3>
currentKBPerSec</H3>
<PRE>
protected int <B>currentKBPerSec</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="totalKBPerSec"><!-- --></A><H3>
totalKBPerSec</H3>
<PRE>
protected long <B>totalKBPerSec</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="busyThreads"><!-- --></A><H3>
busyThreads</H3>
<PRE>
protected int <B>busyThreads</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="totalProcessedBytes"><!-- --></A><H3>
totalProcessedBytes</H3>
<PRE>
protected long <B>totalProcessedBytes</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="congestionRatio"><!-- --></A><H3>
congestionRatio</H3>
<PRE>
protected float <B>congestionRatio</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="deepestUri"><!-- --></A><H3>
deepestUri</H3>
<PRE>
protected long <B>deepestUri</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="averageDepth"><!-- --></A><H3>
averageDepth</H3>
<PRE>
protected long <B>averageDepth</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="mimeTypeDistribution"><!-- --></A><H3>
mimeTypeDistribution</H3>
<PRE>
protected java.util.Hashtable <B>mimeTypeDistribution</B></PRE>
<DL>
<DD>Keep track of the file types we see (mime type -> count)
<P>
<DL>
</DL>
</DL>
<HR>

<A NAME="mimeTypeBytes"><!-- --></A><H3>
mimeTypeBytes</H3>
<PRE>
protected java.util.Hashtable <B>mimeTypeBytes</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="statusCodeDistribution"><!-- --></A><H3>
statusCodeDistribution</H3>
<PRE>
protected java.util.Hashtable <B>statusCodeDistribution</B></PRE>
<DL>
<DD>Keep track of fetch status codes
<P>
<DL>
</DL>
</DL>
<HR>

<A NAME="hostsDistribution"><!-- --></A><H3>
hostsDistribution</H3>
<PRE>
protected transient java.util.Map <B>hostsDistribution</B></PRE>
<DL>
<DD>Keep track of hosts. 
 
 Each of these Maps are individually unsynchronized, and cannot 
 be trivially synchronized with the Collections wrapper. Thus
 their synchronized access is enforced by this class.
 
 <p>They're transient because usually bigmaps that get reconstituted
 on recover from checkpoint.
<P>
<DL>
</DL>
</DL>
<HR>

<A NAME="hostsBytes"><!-- --></A><H3>
hostsBytes</H3>
<PRE>
protected transient java.util.Map <B>hostsBytes</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="hostsLastFinished"><!-- --></A><H3>
hostsLastFinished</H3>
<PRE>
protected transient java.util.Map <B>hostsLastFinished</