#!/usr/bin/perl -w

######################################################################
#
#   Parse-href.pl      2001-05
#
#   Grab the content of all "href" attributes of the HTML "<a>" tag,
#   Insert a redirection URL in the "href" and then UrlEncode the Old 
#   Url to pass it in parameter.
# 
#   Greetings flys out to OeufMayo for his help.
#
#   Nicolas Crovatti  <ncrovatti@ifrance.com>
#   http://www.gencoding.com
#
######################################################################


use strict;
use URI::Escape;
use warnings;
use CGI ':standard';

my @forminputs;
my $JavascriptLinks;
my %results;
my $name;
my $html;
my $OUTHTML;
my $INHTML;
my $dDate     = time();
my $RedirURL  = "http://127.0.0.1/rapport/rnews.php?dt=" . $dDate . "&url=";
my $File      = param("file");

{
  package myParser;
  use base qw(HTML::Parser);
    sub start
    {
      # We fill Scalars using predefined array "@_"
      ####################################################################
      my ($self, $tagname, $attr, $attrseq, $origtext) = @_;
      my $at;
      # For each <a> tag, we  grab the content of the "href" attribute, then we
      # uri_escape it with URI::Escape module, and we rebuild the integrality 
      # of the tag including our $RedirURL .
      ##########################################################################
      if ($tagname eq 'a'){
        #Here, if we reach a <a> tag,i don't want to parse '<a href="#">' 
        #links, we incremment the $LiensJavascript counter.
        ###################################################################
        if ($attr->{href} && $attr->{href} eq "#") {
          $JavascriptLinks++;
          print $origtext;
        } else {
            $attr->{href} =  $RedirURL . main::uri_escape($attr->{href}, "^A-Za-z0-9");
            print '<a';
            print qq' $_="$attr->{$_}"' foreach @{$attrseq};
            print ">";
        }
      } else {
        # If we don't find <a> tag, we print the original text
        ######################################################
        print $origtext;
      }
    }
    sub end {
      my ($self, undef, $origtext) = @_;
      print $origtext;
    }
    sub text
    {
      my ($self, $origtext) = @_;
      print $origtext;
    }
}

# Getting all params
####################
@forminputs=param();
foreach $name (@forminputs){
  $results{$name}=param($name);
}

# Opening the HTML file in read mode only
############################################
open(INHTML, "<$File") || die <<"EOT_";
 -[Erreur prevue]---------------------
 Usage :
 perl parse.pl file=file_name.htm
 $!
 -------------------------------------
EOT_


open(OUTHTML, ">News-ok.htm") || die <<"EOT_";
 -[Erreur]----------------------------
 Cannot open file:
 $!
 -------------------------------------
EOT_

# $html is filled with all the content of the input file
########################################################
while ($_=<INHTML>){$html .= $_;}
close INHTML;


# Initialising the Parser
#########################
my $p = myParser->new();

# Parsing $html
###############
select OUTHTML;
$p->parse($html);
select STDOUT;

close OUTHTML;

print "
 -[Result ok]---------------

 Everything goes Ok!
 
 not modified links : $JavascriptLinks
 
 -[eot]-----------------------------
";
exit;