willwillis · October 8, 2011 05:36
diff --git a/Xtract_links.pl b/Xtract_links.pl
 #!/usr/bin/perl -w
 use strict;

 use LWP::Simple;
 use HTML::TokeParser;
 use HTML::Entities;

 #  @newspages are pages I don't really wanna read, but I'd rather just have the links

 my @newspages = qw(
 http://www.surfstation.lu/00_news.asp
 http://www.cubadust.com/news.htm
 http://www.caffemocha.com/cgi-bin/index.htm
 http://www.halfproject.com/news.php
 http://www.reinvent.co.nz/v2/skins/news2002.asp
 );

 my $body = <<END_HTML;
 <html>
 <head>
 <title>Silent11 helps out</title>
 <style>
 body {margin:0; background-color:e25805;font-family: arial; color:black;font-size:10px;}
 a {font-family: arial; color: yellow; text-decoration: none; font-size: 10px;}
 	a:hover {text-decoration: underline overline; background-color:orange}
 	td {font-size:10px; color: darkred;}
 </style>
 </head>
 <body>
 <table>
 <tr>
 END_HTML

 for (@newspages) {   
 	my $html = $_;
 	my ($junk,$short) = split(/\./,$html); # get domain name
 	$body .= "<td valign=top>$short<br>";
 	my $get = get("$html");
 	my $p = HTML::TokeParser->new(\$get);
 	while (my $token = $p->get_tag("a")) {
 		my $url = $token->[1]{href} || "-";
 		my $text = $p->get_trimmed_text("/a");
 		unless ($url =~ /^mailto|^javascript/){  # don't grab javascript or mailto's (not perfect)
 		$body .= "<a href=\"$url\" target=\"new\">$text</a><br>\n"; }
 							
 		} $body .= "</td>"
 }
 $body .= "</tr></table>";

 open(OUT,">news.file.html"); # send to an html file
 print OUT "$body";
	#!/usr/bin/perl -w
	use strict;

	use LWP::Simple;
	use HTML::TokeParser;
	use HTML::Entities;

	# @newspages are pages I don't really wanna read, but I'd rather just have the links

	my @newspages = qw(
	http://www.surfstation.lu/00_news.asp
	http://www.cubadust.com/news.htm
	http://www.caffemocha.com/cgi-bin/index.htm
	http://www.halfproject.com/news.php
	http://www.reinvent.co.nz/v2/skins/news2002.asp
	);

	my $body = <<END_HTML;
	<html>
	<head>
	<title>Silent11 helps out</title>
	<style>
	body {margin:0; background-color:e25805;font-family: arial; color:black;font-size:10px;}
	a {font-family: arial; color: yellow; text-decoration: none; font-size: 10px;}
	a:hover {text-decoration: underline overline; background-color:orange}
	td {font-size:10px; color: darkred;}
	</style>
	</head>
	<body>
	<table>
	<tr>
	END_HTML

	for (@newspages) {
	my $html = $_;
	my ($junk,$short) = split(/\./,$html); # get domain name
	$body .= "<td valign=top>$short<br>";
	my $get = get("$html");
	my $p = HTML::TokeParser->new(\$get);
	while (my $token = $p->get_tag("a")) {
	my $url = $token->[1]{href} \|\| "-";
	my $text = $p->get_trimmed_text("/a");
	unless ($url =~ /^mailto\|^javascript/){ # don't grab javascript or mailto's (not perfect)
	$body .= "<a href=\"$url\" target=\"new\">$text</a><br>\n"; }

	} $body .= "</td>"
	}
	$body .= "</tr></table>";

	open(OUT,">news.file.html"); # send to an html file
	print OUT "$body";