rfc.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;
#
#  RFC.sum - Summarizes an ASCII Request for Comments
#
#  RFC.sum,v 1.5 1995/09/05 20:17:29 hardy 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);
open(IN, "< $ARGV[0]") || die "Cannot open $ARGV[0]: $!";

while (<IN>) {
	process_header($_), last if (/^Network Working Group/o);
}

while (<IN>) {
	$_ = add_section("Abstract") if (/^abstract/io);
	$_ = add_section("Table-of-Contents") if (/^table\s+of\s+content/io);
}
close(IN);

foreach $k (sort keys %values) {
	print $k , "{" , length($values{$k}) , "}:\t";
	print "$values{$k}\n";
}
exit(0);	# END OF PROGRAM

sub add_section {
	local($attribute) = @_;
	while (<IN>) {
		last if (/^\S+/o);
		$values{$attribute} .= $_;
	}
	return $_;
}

sub add_line {
	local($attribute, $line) = @_;
	$values{$attribute} .= $line . "\n";
}

sub usage {
	print STDERR "Usage: RFC.sum file\n";
	exit(1);
}

sub process_header {
	local($top_line) = @_;

	$top_line =~ s/^.*Network Working Group\s+//;
	$rightcol = $top_line . "\n";

	#  Read in the header information
	while (<IN>) {
		last if (/^\s+$/o);		# clear line
		if (/^Request for Comments:\s+(\d+)\s+(.*)$/o) {
			$values{"RFC-Number"} = $1;
			$rightcol .= $2 . "\n";
		} elsif (/^Category:/o) {
			s/^Category:\s+//;
			if (/^(\w+)\s(\w+)\s+(.*)$/o) {
				$values{"RFC-Category"} = $1 . " " . $2;
				$rightcol .= $3 . "\n";
			} elsif (/^(\w+)\s+(.*)$/o) {
				$values{"RFC-Category"} = $1;
				$rightcol .= $2 . "\n";
			}
		} elsif (/^Obsoletes:\s+(\d+)\s+(.*)$/o) {
			$values{"RFC-Obsoletes"} = $1;
			$rightcol .= $2 . "\n";
		} elsif (/^\s+(.*)$/o) {
			$rightcol .= $1 . "\n";
		} elsif (/^\S+/o) {
			($l, $r) = split(/\s{2,}/);
			$rightcol .= "\n". $r;
		}
	}
	$rightcol =~ s/\s+$//;	# strip tailing whitespace
	die "Unknown RFC format: $ARGV[0]" if (!$rightcol);
	@rcol = split(/\n/, $rightcol);
	$values{"RFC-Date"} = $rcol[$#rcol];
	$rcol[$#rcol] = "";
	$values{"Author"} = join("\n", @rcol);
	#  Clear until title
	while (<IN>) {
		last if (/\S+/o);		# data on the line
	}
	$values{"Title"} = $_;
	#  Read in title
	while (<IN>) {
		last if (/^\s+$/o);		# clear line
		$values{"Title"} .= $_;
	}
}