crawlmapper.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

<TH ALIGN="left"><B>Methods inherited from class org.archive.crawler.settings.<A HREF="../../../../org/archive/crawler/settings/Type.html" title="class in org.archive.crawler.settings">Type</A></B></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD><CODE><A HREF="../../../../org/archive/crawler/settings/Type.html#addConstraint(org.archive.crawler.settings.Constraint)">addConstraint</A>, <A HREF="../../../../org/archive/crawler/settings/Type.html#equals(java.lang.Object)">equals</A>, <A HREF="../../../../org/archive/crawler/settings/Type.html#getConstraints()">getConstraints</A>, <A HREF="../../../../org/archive/crawler/settings/Type.html#getLegalValueType()">getLegalValueType</A>, <A HREF="../../../../org/archive/crawler/settings/Type.html#isExpertSetting()">isExpertSetting</A>, <A HREF="../../../../org/archive/crawler/settings/Type.html#isOverrideable()">isOverrideable</A>, <A HREF="../../../../org/archive/crawler/settings/Type.html#isTransient()">isTransient</A>, <A HREF="../../../../org/archive/crawler/settings/Type.html#setExpertSetting(boolean)">setExpertSetting</A>, <A HREF="../../../../org/archive/crawler/settings/Type.html#setLegalValueType(java.lang.Class)">setLegalValueType</A>, <A HREF="../../../../org/archive/crawler/settings/Type.html#setOverrideable(boolean)">setOverrideable</A>, <A HREF="../../../../org/archive/crawler/settings/Type.html#setTransient(boolean)">setTransient</A></CODE></TD>
</TR>
</TABLE>
&nbsp;<A NAME="methods_inherited_from_class_javax.management.Attribute"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left"><B>Methods inherited from class javax.management.Attribute</B></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD><CODE>getName</CODE></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, finalize, getClass, hashCode, notify, notifyAll, 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="ATTR_CHECK_URI"><!-- --></A><H3>
ATTR_CHECK_URI</H3>
<PRE>
public static final java.lang.String <B>ATTR_CHECK_URI</B></PRE>
<DL>
<DD>whether to map CrawlURI itself (if status nonpositive)
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.processor.CrawlMapper.ATTR_CHECK_URI">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="DEFAULT_CHECK_URI"><!-- --></A><H3>
DEFAULT_CHECK_URI</H3>
<PRE>
public static final java.lang.Boolean <B>DEFAULT_CHECK_URI</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="ATTR_CHECK_OUTLINKS"><!-- --></A><H3>
ATTR_CHECK_OUTLINKS</H3>
<PRE>
public static final java.lang.String <B>ATTR_CHECK_OUTLINKS</B></PRE>
<DL>
<DD>whether to map CrawlURI's outlinks (if CandidateURIs)
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.processor.CrawlMapper.ATTR_CHECK_OUTLINKS">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="DEFAULT_CHECK_OUTLINKS"><!-- --></A><H3>
DEFAULT_CHECK_OUTLINKS</H3>
<PRE>
public static final java.lang.Boolean <B>DEFAULT_CHECK_OUTLINKS</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="ATTR_MAP_OUTLINK_DECIDE_RULES"><!-- --></A><H3>
ATTR_MAP_OUTLINK_DECIDE_RULES</H3>
<PRE>
public static final java.lang.String <B>ATTR_MAP_OUTLINK_DECIDE_RULES</B></PRE>
<DL>
<DD>decide rules to determine if an outlink is subject to mapping
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.processor.CrawlMapper.ATTR_MAP_OUTLINK_DECIDE_RULES">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="ATTR_LOCAL_NAME"><!-- --></A><H3>
ATTR_LOCAL_NAME</H3>
<PRE>
public static final java.lang.String <B>ATTR_LOCAL_NAME</B></PRE>
<DL>
<DD>name of local crawler (URIs mapped to here are not diverted)
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.processor.CrawlMapper.ATTR_LOCAL_NAME">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="DEFAULT_LOCAL_NAME"><!-- --></A><H3>
DEFAULT_LOCAL_NAME</H3>
<PRE>
public static final java.lang.String <B>DEFAULT_LOCAL_NAME</B></PRE>
<DL>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.processor.CrawlMapper.DEFAULT_LOCAL_NAME">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="ATTR_DIVERSION_DIR"><!-- --></A><H3>
ATTR_DIVERSION_DIR</H3>
<PRE>
public static final java.lang.String <B>ATTR_DIVERSION_DIR</B></PRE>
<DL>
<DD>where to log diversions
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.processor.CrawlMapper.ATTR_DIVERSION_DIR">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="DEFAULT_DIVERSION_DIR"><!-- --></A><H3>
DEFAULT_DIVERSION_DIR</H3>
<PRE>
public static final java.lang.String <B>DEFAULT_DIVERSION_DIR</B></PRE>
<DL>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.processor.CrawlMapper.DEFAULT_DIVERSION_DIR">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="ATTR_ROTATION_DIGITS"><!-- --></A><H3>
ATTR_ROTATION_DIGITS</H3>
<PRE>
public static final java.lang.String <B>ATTR_ROTATION_DIGITS</B></PRE>
<DL>
<DD>rotate logs when change occurs within this # of digits of timestamp
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.processor.CrawlMapper.ATTR_ROTATION_DIGITS">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="DEFAULT_ROTATION_DIGITS"><!-- --></A><H3>
DEFAULT_ROTATION_DIGITS</H3>
<PRE>
public static final java.lang.Integer <B>DEFAULT_ROTATION_DIGITS</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="diversionLogs"><!-- --></A><H3>
diversionLogs</H3>
<PRE>
java.util.HashMap <B>diversionLogs</B></PRE>
<DL>
<DD>Mapping of target crawlers to logs (PrintWriters)
<P>
<DL>
</DL>
</DL>
<HR>

<A NAME="logGeneration"><!-- --></A><H3>
logGeneration</H3>
<PRE>
java.lang.String <B>logGeneration</B></PRE>
<DL>
<DD>Truncated timestamp prefix for diversion logs; when
 current time doesn't match, it's time to close all
 current logs.
<P>
<DL>
</DL>
</DL>
<HR>

<A NAME="localName"><!-- --></A><H3>
localName</H3>
<PRE>
protected java.lang.String <B>localName</B></PRE>
<DL>
<DD>name of the enclosing crawler (URIs mapped here stay put)
<P>
<DL>
</DL>
</DL>
<HR>

<A NAME="cache"><!-- --></A><H3>
cache</H3>
<PRE>
protected <A HREF="../../../../org/archive/util/fingerprint/ArrayLongFPCache.html" title="class in org.archive.util.fingerprint">ArrayLongFPCache</A> <B>cache</B></PRE>
<DL>
<DL>
</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="CrawlMapper(java.lang.String, java.lang.String)"><!-- --></A><H3>
CrawlMapper</H3>
<PRE>
public <B>CrawlMapper</B>(java.lang.String&nbsp;name,
                   java.lang.String&nbsp;description)</PRE>