这篇文章主要介绍了php获取百度收录、百度热词及百度快照的方法,实例分析了php抓取百度页面及对应字符串分析的技巧,非常具有实用价值,需要的朋友可以参考下：
获取百度收录：
<?php
/*
抓取百度收录代码
*/
function baidu($s){
$baidu="http://www.baidu.com/s?wd=site%3A".$s; $site=file_get_contents($baidu);
//$site=iconv("gb2312", "UTF-8", $site);
ereg("找到相关网页(.*)篇，", $site,$count);
$count=str_replace("找到相关网页","",$count);
$count=str_replace("篇，","",$count);
$count=str_replace("约","",$count);
$count=str_replace(",","",$count);
return $count[0]; }
echo baidu(www.webmy.cn);
//获取绵阳动力网络建设公司在百度中的收录数量
?>
获取百度的热词：
<?php
/**
* @return array 返回百度的热词数据(数组返回)
*/
function getBaiduHotKeyWord()
{ $templateRss = file_get_contents('http://top.baidu.com/rss_xml.php?p=top10');
if (preg_match('/<table>(.*)<\/table>/is',
$templateRss, $_description)) {
$templateRss = $_description [0];
$templateRss = str_replace("&", "&", $templateRss); }
$templateRss = "<?xml version=1.0 encoding=GBK?>" .
$templateRss; $xml = @simplexml_load_String($templateRss);
foreach ($xml->tbody->tr as $temp) {
if (!empty ($temp->td->a)) {
$keyArray [] = trim(($temp->td->a)); }
} return $keyArray; }
print_r(getBaiduHotKeyWord());
?>
百度收录和百度快照时间：
<?php
$domain = "http://www.webmy.cn/ *欲查询的域名*/
$site_url = 'http://www.baidu.com/s?wd=site%3A';
$all = $site_url.$domain; /*域名所有收录的网址*/
$today = $all.'&lm=1′;
/*域名今日收录的网址*/
$utf_pattern = "/找到相关结果数(.*)个/";
$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}/"; /*匹配快照日期的正则表达式，如:2011-8-4*/
$s0 = @file_get_contents($all); /*将site:www.webmy.cn的网页置入$s0字符串中*/
$s1 = @file_get_contents($today);
preg_match($utf_pattern,$s0,$all_num); /*匹配"找到相关结果数*个"*/
preg_match($utf_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] = "暂无快照";
?>
<html>
<head>
<title>Test</title>
</head> <body>
<table>
<tr>
<td>日期</td><td>百度收录</td><td>百度今日收录</td><td>百度快照日期</td>
</tr>
<tr>
<td><?php echo date('m月d日G时');?> </td>
<td> <?php echo $all_num[1]; ?></td><td>
<?php echo $today_num[1]; ?></td><td>
<?php echo $screenshot[0]; ?></td>
</tr>
</table>
<p>百度收录：<a href="<?php echo $all; ?>" target="_blank"> <?php echo $all_num[1]; ?></a></p>
<p>百度今日收录：<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>
网站