130201 腾讯微博采集 代码 分享

前段时间看有人在做关于美女图片的采集 ，随自己随手写了个 ，发现正则真的是薄弱了，哎 不知道为什么正则的规则一直记不住 why ?

腾讯微博代码采集Demo非API接口

$str = "比基尼";
$url = "http://k.t.qq.com/k/" . urlencode($str); 

$html_list = get_html($url);
preg_match("/\<ul id=\"talkList\" class=\"LC\"\>(.+?)\<\/li\>\<\/ul\>/ms", $html_list, $preg_list);

$str_arr = $preg_list[0];

preg_match_all("/\<div class=\"msgCnt\"\>(.+?)\<\/div\>(.+?)\<div class=\"picBox \"\>\<a href=\"(.+?)\" target=\"_blank/ms", $str_arr, $new_arr);

for($i = 0;$i < count($new_arr[1]);$i++)
{
        echo strip_tags($new_arr[1][$i]) . "<img src='" . $new_arr[3][$i] . "'><br>";
}

function get_html($url)
{
        while (true)
        {
                $ch = curl_init();
                curl_setopt($ch, CURLOPT_URL, $url);
                curl_setopt($ch, CURLOPT_TIMEOUT, 3);
                curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
                curl_setopt($ch, CURLOPT_USERAGENT,
                        "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)");
                curl_setopt($ch, CURLOPT_COOKIE, "TIEBAPB=OLDPB");
                $html = curl_exec($ch);
                curl_close($ch);
                if (!empty($html))
                {
                        return $html;
                }
                sleep(1);
        }
}