本文章介紹了利用php來獲取baidu的快照與收錄代碼,下面我們來看看在php利用什麼樣的函數與編碼轉換函數的本實例中的應用吧。
先來看看效果代碼如下
代碼如下 復制代碼<?php
$domain = "www.hzhuti.com"; /*欲查詢的域名*/
$site_url = 'http://www.baidu.com/s?wd=site%3A';
$all = $site_url.$domain; /*域名所有收錄的網址*/
$today = $all.'&lm=1'; /*域名今日收錄的網址*/
$utf_pattern = "/找到相關結果數(.*)個/";
$gb2312_pattern = iconv("UTF-8","GB2312",$utf_pattern); /*因為百度為GB2312編碼*/
$kz_pattern = "/<span class="g">(.*)</span>/"; /*用以匹配快照日期的字符串*/
$times = "/d{4}-d{1,2}-d{1,2}/"; /*匹配快照日期的正則表達式,如:2011-8-4*/
$s0 = @file_get_contents($all); /*將site:www.hzhuti.com的網頁置入$s0字符串中*/
$s1 = @file_get_contents($today);
preg_match($gb2312_pattern,$s0,$all_num); /*匹配"找到相關結果數*個"*/
preg_match($gb2312_pattern,$s1,$today_num);
preg_match($kz_pattern,$s0,$temp);
preg_match($times,$temp[0],$screenshot);
if($all_num[1] == "")
$all_num[1] = 0;
if($today_num[1] == "")
$today_num[1] = 0;
if($screenshot[0] == "")
$screenshot[0] = "暫無快照";
?>
<html>
<head>
<title>Test</title>
</head>
<body>
<p>百度收錄:<a href="<?php echo $all; ?>" target="_blank"><?php echo $all_num[1]; ?></a></p>
<p>百度今日收錄:<a href="<?php echo $today; ?>" target="_blank"><?php echo $today_num[1]; ?></a></p>
<p>百度快照日期:<a href="<?php echo $all; ?>"><?php echo $screenshot[0]; ?></a></p>
</body>
</html>