PHP抓取百度搜索结果页面的【相关搜索词】并存储

一、百度搜索关键词【知了壳公司转让】

【知了壳公司转让】搜索链接
https://www.baidu.com/s?wd=%E7%9F%A5%E4%BA%86%E5%A3%B3%E5%85%AC%E5%8F%B8%E8%BD%AC%E8%AE%A9

**搜索结果部分源代码**

"rs">
"tt">相关搜索</div>
.....
.....
%E5%85%AC%E5%8F%B8%E8%BD%AC%E8%AE%A9%E6%B5%81%E7%A8%8B%E7%9F%A5%E4%BA%86%E5%A3%B3&rsp=0&f=1&oq=%E7%9F%A5%E4%BA%86%E5%A3%B3%E5%85%AC%E5%8F%B8%E8%BD%AC%E8%AE%A9&tn=baiduhome_pg&ie=utf-8&rsv_idx=2&rsv_pq=88c7804a0000c417&rsv_t=b5f3JkJIsj6Nkp61K%2BmmVGeev7UP95o1HSJTUoIS2xV4SsmZxvOoVf%2BAZaVoihB%2BT3bg&rqlang=cn&rsv_ers=xn0&rs_src=0&rsv_pq=88c7804a0000c417&rsv_t=b5f3JkJIsj6Nkp61K%2BmmVGeev7UP95o1HSJTUoIS2xV4SsmZxvOoVf%2BAZaVoihB%2BT3bg">公司转让流程知了壳
s?wd=%E7%9F%A5%E4%BA%86%E5%A3%B3%E5%85%AC%E5%8F%B8%E6%B3%A8%E5%86%8C&rsp=8&f=1&oq=%E7%9F%A5%E4%BA%86%E5%A3%B3%E5%85%AC%E5%8F%B8%E8%BD%AC%E8%AE%A9&tn=baiduhome_pg&ie=utf-8&rsv_idx=2&rsv_pq=88c7804a0000c417&rsv_t=b5f3JkJIsj6Nkp61K%2BmmVGeev7UP95o1HSJTUoIS2xV4SsmZxvOoVf%2BAZaVoihB%2BT3bg&rqlang=cn&rsv_ers=xn0&rs_src=0&rsv_pq=88c7804a0000c417&rsv_t=b5f3JkJIsj6Nkp61K%2BmmVGeev7UP95o1HSJTUoIS2xV4SsmZxvOoVf%2BAZaVoihB%2BT3bg">知了壳公司注册

二、抓取并保存本地

源代码

index.php------------

<form action="index.php" method="post">
<input name="q" type="text" />
<input type="submit" value="Get Keywords" />
form>


header('Content-Type:text/html;charset=gbk');
class ComBaike{
    private $o_String=NULL;
    public function __construct(){
        include('cls.StringEx.php');
        $this->o_String=new StringEx();
    }
    public function getItem($word){
        $url = "http://www.baidu.com/s?wd=".$word;
        // 构造包头，模拟浏览器请求
        $header = array (
            "Host:www.baidu.com",
            "Content-Type:application/x-www-form-urlencoded",//post请求
            "Connection: keep-alive",
            'Referer:http://www.baidu.com',
            'User-Agent: Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; BIDUBrowser 2.6)'
        );
        $ch = curl_init ();
        curl_setopt ( $ch, CURLOPT_URL, $url );
        curl_setopt ( $ch, CURLOPT_HTTPHEADER, $header );
        curl_setopt ( $ch, CURLOPT_RETURNTRANSFER, 1 );
        $content = curl_exec ( $ch );
        if ($content == FALSE) {
        echo "error:" . curl_error ( $ch );
        }
        curl_close ( $ch );
        //输出结果echo $content;
        $this->o_String->string=$content;
        $s_begin='
';
        $s_end='
';
        $summary=$this->o_String->getPart($s_begin,$s_end);
        $s_begin='
相关搜索
';
        $s_end='

'; $content=$this->o_String->getPart($s_begin,$s_end); return $content; } public function __destruct(){ unset($this->o_String); } } if($_POST){ $com = new ComBaike(); $q = $_POST['q']; $str = $com->getItem($q); //获取搜索内容 $pat = '/(.*?)<\/a>/i'; preg_match_all($pat, $str, $m); //print_r($m[4]); 链接文字 $con = implode(",", $m[4]); //生成文件夹 $dates = date("Ymd"); $path="./Search/".$dates."/"; if(!is_dir($path)){ mkdir($path,0777,true); } //生成文件 $file = fopen($path.iconv("UTF-8","GBK",$q).".txt",'w'); if(fwrite($file,$con)){ echo $con; echo ''; }else{ echo ''; } fclose($file); } ?> cls.StringEx.php------------- header('Content-Type: text/html; charset=UTF-8'); class StringEx{ public $string=''; public function __construct($string=''){ $this->string=$string; } public function pregGetPart($s_begin,$s_end){ $s_begin==preg_quote($s_begin); $s_begin=str_replace('/','\/',$s_begin); $s_end=preg_quote($s_end); $s_end=str_replace('/','\/',$s_end); $pattern='/'.$s_begin.'(.*?)'.$s_end.'/'; $result=preg_match($pattern,$this->string,$a_match); if(!$result){ return $result; }else{ return isset($a_match[1])?$a_match[1]:''; } } public function strstrGetPart($s_begin,$s_end){ $string=strstr($this->string,$s_begin); $string=strstr($string,$s_end,true); $string=str_replace($s_begin,'',$string); $string=str_replace($s_end,'',$string); return $string; } public function getPart($s_begin,$s_end){ $result=$this->pregGetPart($s_begin,$s_end); if(!$result){ $result=$this->strstrGetPart($s_begin,$s_end); } return $result; } } ?>