newsarticle.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;
#
#  NewsArticle.sum - Summarizes a USENET article
#
#  NewsArticle.sum,v 1.5 1995/11/07 01:34:38 duane 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.
#
#
$TTL = 86400 * 14;       # 2 weeks

$len = length($TTL);
print "Time-to-Live\{$len\}:\t$TTL\n";

$file = shift(@ARGV);
open(IN, "<$file") || die "NewsArticle.sum: Cannot read $file.\n";

#  Read the header
$att = "";
while (<IN>) {
    	s/\r//g;            	# strip CR
    	last if (/^\s*$/o);	# end of the header
    	if (/^\t/o && $att ne "") {
        	chop $_;
        	$SOIF{$att} .= "\n$_";
        	next;
    	}
    	$i = index ($_, ":");
    	next if ($i == $[-1);
    	$att = substr ($_, 0, $i);
    	$val = substr ($_, $i+2);
    	chop $val;
    	$SOIF{$att} = $val;
}


#  Text summarize the body
$| = 1;
open(TEXTSUM, "| Text.sum") || die "NewsArticle.sum: Cannot run Text summarizer.\n";
print TEXTSUM <IN>;
close(TEXTSUM);
close(IN);

$SOIF{'Description'} = $SOIF{'Subject'} if (defined($SOIF{'Subject'}));
$SOIF{'Description'} = $SOIF{'Summary'} if (defined($SOIF{'Summary'}));

while (($k, $v) = each %SOIF) {
	next if ($k eq "Path");
	next if ($k =~ /^X-/o);
    	next if ($k =~ /[ \t]/o);  # don't output atts with whitespace
	$len = length($v);
	next if ($len < 1);
	print "$k\{$len\}:\t$v\n";
}
exit 0;		# END OF PROGRAM