php抓取百度快照、百度收录、百度热词程序代码，抓取百度快照
<?<br />/*<br />抓取百度收录代码<br />*/<br />function baidu($s){<br /> $baidu="http://www.baidu.com/s?wd=site%3A".$s;<br /> $site=file_get_contents($baidu);<br /> //$site=iconv("gb2312", "UTF-8", $site);<br /> ereg("找到相关网页(.*)篇，", $site,$count);<br /> $count=str_replace("找到相关网页","",$count);<br /> $count=str_replace("篇，","",$count);<br /> $count=str_replace("约","",$count);<br /> $count=str_replace(",","",$count);<br /> return $count[0];<br />}<br /><br />echo baidu(www.hzhuti.com); //获取好主题在百度中的收录数量<br /><br />?>
获取百度的热词
<?php <br />/** <br />* * @user 小杰 <br />* @return array 返回百度的热词数据(数组返回) <br />*/ <br />function getBaiduHotKeyWord() <br />{ <br />$templateRss = file_get_contents('http://top.baidu.com/rss_xml.php?p=top10'); <br />If (preg_match('/<table>(.*)</table>/is', $templateRss, $_description)) { <br />$templateRss = $_description [0]; <br />$templateRss = str_replace("&", "&", $templateRss); <br />} <br />$templateRss = "<?xml version="1.0" encoding="GBK"?>" . $templateRss; <br />$xml = simplexml_load_String($templateRss); <br />foreach ($xml->tbody->tr as $temp) { <br />if (!empty ($temp->td->a)) { <br />$keyArray [] = trim(($temp->td->a)); <br />} <br />} <br />return $keyArray; <br />} <br />print_r(getBaiduHotKeyWord());
这是在网上找的 稍微修改了下 将下面代码写入php文件
百度收录和百度快照时间
<?php<br /> $domain = “http://www.hzhuti.com/nokia/5230/ *欲查询的域名*/<br /> $site_url = ‘http://www.baidu.com/s?wd=site%3A’;<br /> $all = $site_url.$domain; /*域名所有收录的网址*/<br /> $today = $all.’&lm=1′; /*域名今日收录的网址*/<br /> $utf_pattern = “/找到相关结果数(.*)个/”;<br /> $kz_pattern = “/<span class=”g”>(.*)</span>/”; /*用以匹配快照日期的字符串*/<br /> $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*/<br /> $s0 = @file_get_contents($all); /*将site:www.ninthday.net的网页置入$s0字符串中*/<br /> $s1 = @file_get_contents($today);<br /> preg_match($utf_pattern,$s0,$all_num); /*匹配”找到相关结果数*个”*/<br /> preg_match($utf_pattern,$s1,$today_num);<br /> preg_match($kz_pattern,$s0,$temp);<br /> preg_match($times,$temp[0],$screenshot);<br /> if($all_num[1] == “”)<br /> $all_num[1] = 0;<br /> if($today_num[1] == “”)<br /> $today_num[1] = 0;<br /> if($screenshot[0] == “”)<br /> $screenshot[0] = “暂无快照”;<br />?><br /><html><br /> <head><br /> <title>Test</title><br /> </head><br /><body><br /> <table><br /> <tr><br /> <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><br /> </tr><br /> <tr><br /> <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><br /> </tr><br /><br /> </table><br /> <p>百度收录：<a href=”<?php echo $all; ?>” target=”_blank”><?php echo $all_num[1]; ?></a></p><p><span>立即学习</span>“<a href="https://pan.quark.cn/s/7fc7563c4182" style="text-decoration: underline !important; color: blue; font-weight: bolder;" rel="nofollow" target="_blank">PHP免费学习笔记（深入）</a>”；</p><br /> <p>百度今日收录：<a href=”<?php echo $today; ?>” target=”_blank”><?php echo $today_num[1]; ?></a></p><br /> <p>百度快照日期：<a href=”<?php echo $all; ?>”><?php echo $screenshot[0]; ?></a></p><br /></body><br /></html>
上面的方法未经过严格考虑，如果服务器不支持file_get_contents函数我们就无法操作了，所以还可以利用curl操作，这个更方便可以模仿用户哦。
