PHP新浪博客采集程序

注意：看到还有人在找用这个程序，我在此说明一下，新浪博客在去年做过改版调整，以下抓取程序已经不能用了，请周知

仅做为学习PHP代码的示例，如果以后有空再写新版的抓取程序，多谢！

<?php    
error_reporting(0);    
set_time_limit(0);    
header("Content-Type:text/html; charset=utf-8");    
function get_url_content($url) {    
    if(extension_loaded('curl')) {    
        $ch = curl_init($url);    
        curl_setopt($ch, CURLOPT_HEADER, 0);    
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);    
        $content = curl_exec($ch);    
        curl_close($ch);    
    } else {    
        $content = file_get_contents($url);    
    }    
    !$content && die("获取地址：$url 内容出错.");    
    return $content;    
}    
//新浪博客用户名    

$username = empty($ _GET['username']) ? 'liuxingliang' : $ _GET['username'];    
$home_url = "http://blog.sina.com.cn/$username";    
$content = get_url_content($home_url);    
//博客名称    

preg_match('/id="blogname"\s*><a\s*.*?>(.*?)<\/a>/', $content, $matches);    
if($matches) {    
    $blog_title = $matches[1];    
}    
//用户编号    
preg_match("/\"([0-9]+)\"/i", $content, $matches);    
!$matches && die("获取用户编号出错.");    
$uid = $matches[1];    
//博文总数    
$config_url = "http://blogcnf.sinajs.cn/acate?jv=x&{$uid}";    
$content = get_url_content($config_url);    
preg_match('/:{"total":([0-9]+)/', $content, $matches);    
!$matches && die("获取博客总数出错.");    
//博文总数    
$total = $matches[1];    
$perpage = 50;    
//博文页数    
$totalpage = ceil($total/$perpage);    
//博文页列表

$page = empty($ _GET['page']) ? 1 : intval($ _GET['page']);    
$page = ($page > $totalpage ? $totalpage : $page);    
$blog_url = "http://blog.sina.com.cn/s/articlelist_{$uid}_0_{$page}.html";    
   
if(!empty($blog_title)) {    
    echo "<h1>新浪博客：<a href=\"$home_url\" target=\"_blank\">$blog_title</a></h1>";    
}    
   
echo "<table><thead>记录总数：$total</thead>";    
$blog_url_content = get_url_content($blog_url);    
//文章列表    
$pattern = '/<div class="articleTitle_d">\s*<div class="floatLeft">.*?<a.*?href="(http:\/\/blog.sina.com.cn\/s\/blog_.*?\.html)".*?>(.*?)<\/a>.*?<span class="time space_d01">\((.*?)\)<\/span><\/div>/s';    
if(!preg_match_all($pattern, $blog_url_content, $matches)) {    
        die("没有匹配的记录");                 
}    
//var_dump($matches);    
   
$count = count($matches[0]);    
for($i=0; $i<$count; $i++) {    
    echo "<tr><td><a href=\"{$matches[1][$i]}\" target=\"_blank\">{$matches[2][$i]}</a></td><td>{$matches[3][$i]}</td></tr>";    
}    
echo "</table>";    
   
//分页    
if($total > $perpage) {    
    $php_self = $ _SERVER['PHP_SELF'] ? $ _SERVER['PHP_SELF'] : $ _SERVER['SCRIPT_NAME'];    
    $php_self .= '?username=' . $username;    
    $range = range(1, $totalpage);    
    foreach ($range as $num) {    
        if($page == $num) {    
            echo $num . " ";    
        } else {    
            echo "<a href=\"{$php_self}&page=$num\">$num</a> ";    
        }    
    }    
}    
?>