mktemplate

harvest是一个下载html网页得机器人

: # *-*-perl-*-*
    eval 'exec perl -S $0 "$@"'
    if $running_under_some_shell;  
#
#  mktemplate - Converts an easy-to-write template into a SOIF template.
#               Not very robust.
#
#  Usage: mktemplate [file ...]
#
#  Input format: 
#
#      @FILE { url
#      Attribute-Name-1:\tDATA
#      Attribute-Name-2:\tDATA
#      ...
#      Attribute-Name-n:\tDATA
#      }
#
#  The Attributes must begin in column 0 and have one tab after the colon.
#  And the DATA must be on a single line.
#
#  Darren Hardy, [e-mail], May 1994
#
#######################################################################
#
#  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.  
#  
#
#######################################################################
while (<>) {
	next if (/^\n/o);
	&print_template() if (/^}/o);
	$top_line = $_ if (/^\@\w+/o);
	&grab_av($_) if (/^\w+/o);
}

sub grab_av {
	local($line) = @_;
	$attribute = $1, $data = $2 if ($line =~ /^([^:]*):\t(.*)$/o);
	$attribute =~ s/\{\d+\}//;	# remove length if present
	$values{$attribute} = $data;
}

sub print_template {
	print $top_line;
	foreach $k (sort keys %values) {
		next if (length($values{$k}) < 1);
		print $k, "{" , length($values{$k}) , "}:\t";
		print "$values{$k}\n";
	}
	print "}\n\n";

	undef $top_line;
	foreach $k (sort keys %values) {
		undef $values{$k};
	}
}