sample.cf

harvest是一个下载html网页得机器人

# Demo to show some of the customization features for the Harvest output
# More information can be found in the manual at:
# http://harvest.sourceforge.net/harvest/doc/html/manual.html


# The PerObjectFunction is Perl code evaluated for every hit
<PerObjectFunction>
# Create description
# Is the descriptions provided by Harvest very short (e.g. missing <TITLE>)?
if (length($desc) < 5) {
  # Yes: use filename ($F) instead
  $description = "<I>File:</I> $F";
} else {
  # No: use description provided by Harvest
  $description = $desc;
}

# Format matched lines ("opaque data") if data is present
if ($opaque ne '') {
  $opaque = "<strong>matched lines:</strong><BR>$opaque"
}
</PerObjectFunction>


# PrintObject defines the apperance of hits
<PrintObject>
$objectnum <A HREF="$url"><STRONG>$description</STRONG></A> \
[<A HREF="$cs_a://$cs_h/Harvest/cgi-bin/displaySOIF.cgi?object=$cs_p">\
indexing data</A>]
<pre>
     $opaque
</pre>\n
</PrintObject>


# Format the appearance of the hit number
<ObjectNumPrintf>
(%2d)
</ObjectNumPrintf>


# Format the appearance of every matched line
<MatchedLineSub>
s/^Matched line: *//;            # Remove "Matched line:"
s/^([\w-]+# )[\w-]+{\d+}:\t/\1/; # Remove SOIF attributes of the form "partial-text{43}:"
s/^([\w-]+#)/<I>\1<\/I>/;        # Format attribute names as italics
s/^.*/     $&/;                  # Add spaces to indent text
</MatchedLineSub>


# Modifies the report of how many objects were matched
<EndBrokerResults>
<STRONG>Found $nopaquelines matched lines, $nobjects objects.</STRONG>
<P>\n
</EndBrokerResults>