never4get 的記事本: Time php v 1.1

Time 雜誌網頁格式有少許更動
昨晚我把原來的程式也更新了
內定 time.php 為 U.S. edition

time.php?edition=asia 為亞洲版
分兩個檔案:

time.php

<?
header('Content-type:text/html; charset=utf-8');
$edtion = $_GET['edition'];
$link = "http://www.time.com/time/magazine";
$dirlink = dirname($link);
$mylogo = "<img src=http://static.flickr.com/60/219160214_e6ed15d559_o.gif> <br>\r\n<font size=\"2\">time.php v1.1</font>";
$content = file_get_contents($link);
preg_match('/(.*?)<\/ul>/s',$content,$edt);
$edition = $edt[1];
preg_match_all('/img src=\"(.*?)jpg/s',$edition,$cv);
preg_match_all('/<a href=\"(.*?)\"/s',$edition,$el);
$uscover = $cv[1][0].'jpg';
$asiacover = $cv[1][2].'jpg';
$uslink = $link;
$asialink = $el[1][1];
$link = $uslink;
$cover = $uscover;
if ($edtion == 'asia'){
$link = $dirlink.'/..'.$asialink;
$cover = $asiacover;
}
$content = file_get_contents($link);
preg_match("/<title>(.*)<\/title>/is",$content,$head);
$line = $head[0];
$line .= "<b>$head[1]</b><br><img src=$cover>\r\n<hr>\r\n";
preg_match_all("/<div class=\"toc_seched\">(.*?)<\/div></is",$content,$matches);
$z = count($matches[0]);
for ($i=0;$i<$z;$i++){
$area = $matches[0][$i];
preg_match("/<div class=\"toc_seched\">(.*?)<\/div>/is",$area,$h);
$line .= "<br>\r\n<b><font color=red>$h[1]</font></b><br>\r\n<ul>\r\n";
preg_match_all("/<a class=(.*?)<br \/>/is",$area,$t);
for ($j=0;$j<count($t[0]);$j++){
$title = $t[0][$j];
$title = eregi_replace("<br />","",$title);
$title = eregi_replace('/time/','time_view.php?link=http://www.time.com/time/',$title);
$line .= "<li>$title</li>\r\n";
}
$line .= "</ul><br>\r\n";
}
$line .= "<hr>\r\n$mylogo";
echo $line;
?>

time_view.php

<?
header('Content-type:text/html; charset=utf-8');
$link = $_GET['link'];
$mylogo = "<img src=http://static.flickr.com/60/219160214_e6ed15d559_o.gif> <br>\n<font size=\"2\">time.php v1.1</font>";
$content = file_get_contents($link);
preg_match("/<head>(.*?)<\/head>/is",$content,$css);
preg_match("/(.*)/is",$content,$pix);
preg_match("/<div class=\'print\'><a href=\'(.*?)\'/is",$content,$nl);
preg_match("/<div class=\"print\"><a href=\"(.*?)\"/is",$content,$nl2);
if ($nl[1]||$nl2[1]){
$newlink = $nl[1];
$newlink .= $nl2[1];
$newlink = 'http://www.time.com/'.$newlink;
$newlink = eregi_replace('"',"",$newlink);
$content = file_get_contents($newlink);
}
preg_match("/<title>(.*?)<\/title>/is",$content,$t);
$title = $t[0];
$title = eregi_replace("printout","",$title);
preg_match("/(.*?)/is",$content,$a);
$area = $a[1];
$line = $title."\r\n";
$line .= $area;
$allowed_tags = "<b>,<p>,<div>,<h1>,<span>,<title>,<br>,<hr>,<img>,<font>";
$line = strip_tags($line, $allowed_tags);
$line .=$pix[0];
$line = preg_replace('/<div id=\"copy\">(.*?)<\/span>/s','',$line);
$line = preg_replace('/<div class=\"enlarge\">(.*?)<\/div>/s','',$line);
$line = preg_replace('/<a id=\"enlargeImg\"(.*?)>/s','',$line);
$line = eregi_replace('a_','',$line);
$line = preg_replace('/width=(.*?)\//s','/',$line);
$line .= "<hr>\r\n$mylogo";
echo $line;
?>