quick-sum

harvest是一个下载html网页得机器人

: # *-*-perl-*-*
    eval 'exec perl -S $0 "$@"'
    if $running_under_some_shell;
#
#  quick-sum - Quick hack for people who would rather use this than
#              Essence's built-in quick-sum.
#
# $Id: quick-sum,v 2.1 1997/09/22 16:05:12 sxw Exp $
#
#######################################################################
#
#  Copyright (c) 1994, 1995.  All rights reserved.
#
#    The Harvest software was developed by the Internet Research Task
#    Force Research Group on Resource Discovery (IRTF-RD):
#
#          Mic Bowman of Transarc Corporation.
#          Peter Danzig of the University of Southern California.
#          Darren R. Hardy of the University of Colorado at Boulder.
#          Udi Manber of the University of Arizona.
#          Michael F. Schwartz of the University of Colorado at Boulder.
#          Duane Wessels of the University of Colorado at Boulder.
#
#    This copyright notice applies to software in the Harvest
#    ``src/'' directory only.  Users should consult the individual
#    copyright notices in the ``components/'' subdirectories for
#    copyright information about other software bundled with the
#    Harvest source code distribution.
#
#  TERMS OF USE
#
#    The Harvest software may be used and re-distributed without
#    charge, provided that the software origin and research team are
#    cited in any use of the system.  Most commonly this is
#    accomplished by including a link to the Harvest Home Page
#    (http://harvest.cs.colorado.edu/) from the query page of any
#    Broker you deploy, as well as in the query result pages.  These
#    links are generated automatically by the standard Broker
#    software distribution.
#
#    The Harvest software is provided ``as is'', without express or
#    implied warranty, and with no support nor obligation to assist
#    in its use, correction, modification or enhancement.  We assume
#    no liability with respect to the infringement of copyrights,
#    trade secrets, or any patents, and are not responsible for
#    consequential damages.  Proper use of the Harvest software is
#    entirely the responsibility of the user.
#
#  DERIVATIVE WORKS
#
#    Users may make derivative works from the Harvest software, subject
#    to the following constraints:
#
#      - You must include the above copyright notice and these
#        accompanying paragraphs in all forms of derivative works,
#        and any documentation and other materials related to such
#        distribution and use acknowledge that the software was
#        developed at the above institutions.
#
#      - You must notify IRTF-RD regarding your distribution of
#        the derivative work.
#
#      - You must clearly notify users that your are distributing
#        a modified version and not the original Harvest software.
#
#      - Any derivative product is also subject to these copyright
#        and use restrictions.
#
#    Note that the Harvest software is NOT in the public domain.  We
#    retain copyright, as specified above.
#
#  HISTORY OF FREE SOFTWARE STATUS
#
#    Originally we required sites to license the software in cases
#    where they were going to build commercial products/services
#    around Harvest.  In June 1995 we changed this policy.  We now
#    allow people to use the core Harvest software (the code found in
#    the Harvest ``src/'' directory) for free.  We made this change
#    in the interest of encouraging the widest possible deployment of
#    the technology.  The Harvest software is really a reference
#    implementation of a set of protocols and formats, some of which
#    we intend to standardize.  We encourage commercial
#    re-implementations of code complying to this set of standards.
#
#

usage() if ($#ARGV < 0);
$configfile = shift(@ARGV);	# always the first arg
$dotype = shift(@ARGV);
$found = 0;

open(CONFIG, "< $configfile") || die "Cannot read $configfile: $!";
while (<CONFIG>) {
	next if (/^#/o);
	next if (!/^$dotype\s+/o);
	$found = 1;
	chop;
	($type, $attribute, $re) = split(/\t+/, $_);
	$attribute =~ s/ //g;	# remove any spaces from the attribute name
	if (exists $matches{$re}) {
		print STDERR "Redefinition of \"$re\" for \"$attribute\" which is already used for \"$matches{$re}\".\n";
		exit(1);
	}
	$matches{$re} = $attribute;
}
close(CONFIG);
exit(1) if ($found == 0);

while (<>) {
	chop;
	foreach $k (keys %matches) {
		($tmp) = /($k)/;
		$matched{$matches{$k}} .= "$tmp\n" if ($tmp);
	}
}

foreach $k (sort keys %matched) {
	$n = length($matched{$k}) - 1;
	print "$k\{$n\}:\t";
	print $matched{$k};
}

exit(0);

sub usage {
	print STDERR "Usage: quick-sum cffile type [filename]\n";
	exit(1);
}