#!/usr/bin/perl
package Metabot;

use warnings;
use strict;
use WWW::SimpleRobot;
use HTML::Entities;
require HTML::Parser;
use Lingua::EN::Summarize;
use HTML::Summary;
use HTML::TreeBuilder;
use Lingua::EN::Keywords; 
use HTML::Tree;
use LWP::Simple;
@Metabot::ISA = qw(HTML::Parser);

my $url = $ARGV[0];

my $parser = Metabot->new;

my $robot = WWW::SimpleRobot->new(
	URLS            => [ $url ],
	FOLLOW_REGEX    => "^$url",
	DEPTH           => 2,
	TRAVERSAL       => 'depth',
	VISIT_CALLBACK  => 
		sub { 
			my ( $url, $depth, $html, $links) = @_;
			print "\nURL: $url - depth $depth\n"; 
			$html = decode_entities($html);
			$html =~ s/document\.write\(.+?\)\;//g;
			$html =~ s/\&\#.+?\;//g;
			my ($tree, $title, $titleastext, $newtitle, $newtitleh1, $newtitleastexth1, $newtitleastexth1clipped, $newtitleh2, $newtitleastexth2, $newtitleastexth2clipped, $newtitleh3, $newtitleastexth3, $newtitleastexth3clipped, $newtitleh4, $newtitleastexth4, $newtitleastexth4clipped, $newtitlep, $newtitleastextp, $newtitleastextpclipped, $summary, $var, $newmetadescription, $newmetakeywords);
			$tree = HTML::Tree->new();
			$tree->parse($html);
			$title = $tree->look_down( '_tag' , 'title' );
			$titleastext = $title->as_text;
			
			use HTML::Element;
			if ($titleastext){
			print "\nTitle: $titleastext\n\n";
			} else {
			$newtitle = HTML::Element->new('title');
			$newtitle = $newtitleh1;
			$newtitleh1 = $tree->look_down( '_tag' , 'h1' );
			if ($newtitleh1){
			$newtitleastexth1 = $newtitleh1->as_text;
			}
			}
			if ($newtitleastexth1){
			$newtitleastexth1clipped = substr($newtitleastexth1, 0, 65);
			$html->push_content($newtitleastexth1clipped);
			print "\n$url does not have a title. We created one from\n 
			the first 66 characters your first headline tag \<h1\>:\n
			$newtitleastexth1clipped.\n
			Please change if desired.\n\n"} else {
			$newtitleh2 = $tree->look_down( '_tag' , 'h2' );
			if ($newtitleh2){
			$newtitleastexth2 = $newtitleh2->as_text;
			}
			}
			if ($newtitleastexth2){
			$newtitleastexth2clipped = substr($newtitleastexth2, 0, 65);
			$html->push_content($newtitleastexth2clipped);
			print "\n$url does not have a title. We created one from\n 
			the first 66 characters your first headline tag \<h2\>:\n
			$newtitleastexth2clipped.\n
			Please change if desired.\n\n"
			} else {
			$newtitleh3 = $tree->look_down( '_tag' , 'h3' );
			if ($newtitleh3){
			$newtitleastexth3 = $newtitleh3->as_text;
			}
			}
			if ($newtitleastexth3){
			$newtitleastexth3clipped = substr($newtitleastexth3, 0, 65);
			$html->push_content($newtitleastexth3clipped);
			print "\n$url does not have a title. We created one from\n 
			the first 66 characters your first headline tag \<h3\>:\n
			$newtitleastexth3clipped.\n
			Please change if desired.\n\n"
			} else {
			$newtitleh4 = $tree->look_down( '_tag' , 'h4' );
			if ($newtitleh4){
			$newtitleastexth4 = $newtitleh4->as_text;
			}
			}
			if ($newtitleastexth4){
			$newtitleastexth4clipped = substr($newtitleastexth4, 0, 65);
			$html->push_content($newtitleastexth4clipped);
			print "\n$url does not have a title. We created one from\n 
			the first 66 characters your first headline tag \<h4\>:\n
			$newtitleastexth4clipped.\n
			Please change if desired.\n\n"
			} else {
			$newtitlep = $tree->look_down( '_tag' , 'p' );
			if ($newtitlep){
			$newtitleastexth3 = $newtitlep->as_text;
			}
			}
			if ($newtitleastextp){
			$newtitleastextpclipped = substr($newtitleastextp, 0, 65);
			$html->push_content($newtitleastextpclipped);
			print "\n$url does not have a title. We created one from\n 
			the first 66 characters your first paragraph tag \<p\>:\n
			$newtitleastexth1clipped.\n
			Please change if desired.\n\n"
			} else {
			print "$url does not have a title and we are unable to suggest any.";
			}
			
			$tree = new HTML::TreeBuilder;
			$tree->parse($html);
			
			$summary = summarize( $html, filter => 'html', maxlength => 500 ); 
			$summary =~ s/\s+/ /gs;
			$var = substr($summary, 0, 155);
			print "Using Lingua::EN::Summarize Summary: $var\n\n"; 
			
			$newmetadescription = HTML::Element->new('meta', href => "$html");
			$newmetadescription->attr('name', 'description');
			$newmetadescription->attr('content', "$var");
			$html->push_content($newmetadescription);
			$newmetadescription = $newmetadescription->delete;
			
			my @keywords = keywords($title.$summary);
			print "Keywords: " . join(", ", @keywords) . "\n\n";
			
			$newmetakeywords = HTML::Element->new('meta', href => "$html");
			$newmetakeywords->attr('name', 'keywords');
			$newmetakeywords->attr('content', "@keywords");
			$html->push_content($newmetakeywords);
			$newmetakeywords = $newmetakeywords->delete;

# $tree = HTML::TreeBuilder->new_from_content($html);
	# foreach my $img ($tree->look_down('_tag', 'img')) {
	# my $alatt = $img->attr('alt')
		# if (!$alatt) {
		# $imgsrcattribute = $img->attr('src');
		# use File::Basename;
		# my @suffixlist = qw(gif jpg jpeg png bmp php ico GIF JPG JPEG PNG BMP PHP ICO);
		# my $imgfilenopathnoext = fileparse($imgsrcattribute,@suffixlist);
		# my $newalttag = HTML::Element->new('img', alt=>"");
		# $newalttag->attr('alt', "$imgfilenopathnoext");
		# $html->push_content($imgfilenopathnoext);
		# $imgfilenopathnoext = $imgfilenopathnoext->delete;
		# print "Alt tag not found for $imgsrcattribute \nInserted src file name $imgfilenopathnoext for alt attribute";
		# }
	# }
			
Second(@ARGV);
exit(0);

sub Second {
my ( $url, $depth, $html, $links) = @_;
			print "\nURL: $url - depth $depth\n"; 
			$html = decode_entities($html);
			$html =~ s/document\.write\(.+?\)\;//g;
			$html =~ s/\&amp;\#.+?\;//g;
    my $tree = HTML::TreeBuilder->new();
    $tree->parse($html);

    local $\ = $/;
    print $_->as_HTML
      for $tree->look_down( qw' _tag img ',
        sub { not defined $_[0]->attr('alt') } );

    print '---';

    print $_->as_HTML
      for $tree->look_down( qw' _tag img ',
        sub { not length $_[0]->attr('alt') } );

    print '---';

    $_->attr( alt => MAlt($_) )
      for $tree->look_down( qw' _tag img ',
        sub { not length $_[0]->attr('alt') } );
    print $_->as_HTML for $tree->look_down(qw' _tag img ');
} ## end sub Main

sub MAlt { 
my $imgscalar = $_[0];
my $imgsrc = $imgscalar->attr('src');
use File::Basename;
my @suffixlist = qw(gif jpg jpeg png bmp php ico GIF JPG JPEG PNG BMP PHP ICO);
my $imgfilenopathnoext = fileparse($imgsrc,@suffixlist);
'!' . $imgfilenopathnoext;
}	
		
}
	,
	BROKEN_LINK_CALLBACK  => 
		sub { 
			my ( $url, $linked_from, $depth ) = @_;
			print STDERR "$url looks like a broken link on $linked_from\n"; 
			print STDERR "Depth = $depth\n"; 
		}
);

$robot->traverse;

my @urls = @{$robot->urls};

my @pages = @{$robot->pages};

for my $page ( @pages )	{
	my $url = $page->{url};
	my $depth = $page->{depth};
	my $modification_time = $page->{modification_time};
}

sub text {
	my ($self,$text) = @_;
	$self->{TEXT} .= $text;
}

##</code><code>##

Can't call method "push_content" without a package or object reference at seo_f
xer.pl line 126.