本文实例讲述了PHP实现抓取百度搜索结果页面【相关搜索词】并存储到txt文件。分享给大家供大家参考,具体如下:
一、百度搜索关键词【脚本之家】
【脚本之家】搜索链接
https://www.baidu.com/s?ie=utf-8f=8rsv_bp=0rsv_idx=1tn=baiduwd=%E8%84%9A%E6%9C%AC%E4%B9%8B%E5%AE%B6rsv_pq=ab33cfeb000086a2rsv_t=7c65vT3KzHCNfGYOIn%2FDSS%2BOQUiCycaspxWzSOBfkHYpgRIPKMI74WIi8K8rqlang=cnrsv_enter=1rsv_sug3=1
搜索结果部分源代码:
div id="rs">div class="tt">相关搜索/div>table cellpadding="0">tbody>tr>th>a href="/s?wd=%E6%B8%B8%E6%88%8F%E8%84%9A%E6%9C%AC%E4%B8%80%E8%88%AC%E9%83%BD%E5%9C%A8%E5%93%AA%E6%89%BErsf=4562rsp=0f=1oq=%E8%84%9A%E6%9C%AC%E4%B9%8B%E5%AE%B6ie=utf-8rsv_idx=1rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaMrqlang=cnrs_src=0rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaM" rel="external nofollow" >游戏脚本一般都在哪找/a>/th>td>/td>th>a href="/s?wd=%E8%84%9A%E6%9C%AC%E6%80%8E%E4%B9%88%E5%86%99rsf=4562rsp=1f=1oq=%E8%84%9A%E6%9C%AC%E4%B9%8B%E5%AE%B6ie=utf-8rsv_idx=1rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaMrqlang=cnrs_src=0rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaM" rel="external nofollow" >脚本怎么写/a>/th>td>/td>th>a href="/s?wd=%E8%84%9A%E6%9C%AC%E6%98%AF%E4%BB%80%E4%B9%88%E6%84%8F%E6%80%9Drsf=4562rsp=2f=1oq=%E8%84%9A%E6%9C%AC%E4%B9%8B%E5%AE%B6ie=utf-8rsv_idx=1rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaMrqlang=cnrs_src=0rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaM" rel="external nofollow" >脚本是什么意思/a>/th>/tr>tr>th>a href="/s?wd=%E8%84%9A%E6%9C%AC%E4%B9%8B%E5%AE%B6apprsf=4562rsp=3f=1oq=%E8%84%9A%E6%9C%AC%E4%B9%8B%E5%AE%B6ie=utf-8rsv_idx=1rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaMrqlang=cnrs_src=0rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaM" rel="external nofollow" >脚本之家app/a>/th>td>/td>th>a href="/s?wd=%E6%89%8B%E6%9C%BA%E8%84%9A%E6%9C%AC%E5%88%B6%E4%BD%9Crsf=4562rsp=4f=1oq=%E8%84%9A%E6%9C%AC%E4%B9%8B%E5%AE%B6ie=utf-8rsv_idx=1rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaMrqlang=cnrs_src=0rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaM" rel="external nofollow" >手机脚本制作/a>/th>td>/td>th>a href="/s?wd=%E6%89%8B%E6%9C%BA%E8%84%9A%E6%9C%AC%E5%A4%A7%E5%85%A8rsf=4562rsp=5f=1oq=%E8%84%9A%E6%9C%AC%E4%B9%8B%E5%AE%B6ie=utf-8rsv_idx=1rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaMrqlang=cnrs_src=0rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaM" rel="external nofollow" >手机脚本大全/a>/th>/tr>tr>th>a href="/s?wd=%E8%84%9A%E6%9C%AC%E6%B8%B8%E6%88%8F%E5%88%B6%E4%BD%9C%E5%A4%A7%E5%B8%88rsf=4562rsp=6f=1oq=%E8%84%9A%E6%9C%AC%E4%B9%8B%E5%AE%B6ie=utf-8rsv_idx=1rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaMrqlang=cnrs_src=0rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaM" rel="external nofollow" >脚本游戏制作大师/a>/th>td>/td>th>a href="/s?wd=%E6%B8%B8%E6%88%8F%E8%84%9A%E6%9C%AC%E5%88%B6%E4%BD%9C%E6%95%99%E7%A8%8Brsf=4562rsp=7f=1oq=%E8%84%9A%E6%9C%AC%E4%B9%8B%E5%AE%B6ie=utf-8rsv_idx=1rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaMrqlang=cnrs_src=0rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaM" rel="external nofollow" >游戏脚本制作教程/a>/th>td>/td>th>a href="/s?wd=%E8%84%9A%E6%9C%AC%E7%B2%BE%E7%81%B5rsf=4562rsp=8f=1oq=%E8%84%9A%E6%9C%AC%E4%B9%8B%E5%AE%B6ie=utf-8rsv_idx=1rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaMrqlang=cnrs_src=0rsv_pq=c1ff4bdb000208b4rsv_t=a1f2OCsgS6vkkBcxsdqfBfehkXoR65%2FtFlpSI30%2F%2FMmk6jQJEukZbv30XaM" rel="external nofollow" >脚本精灵/a>/th>/tr>/tbody>/table>/div>
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> ?php 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='div id="rs">'; $s_end='/div>'; $summary=$this->o_String->getPart($s_begin,$s_end); $s_begin='div class="tt">相关搜索/div>table cellpadding="0">tr>th>'; $s_end='/th>/tr>/table>/div>'; $content=$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 $pat = '/a(.*?)href="(.*?)" rel="external nofollow" (.*?)>(.*?)\/a>/i'; preg_match_all($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 $con; echo 'script>alert("success")/script>'; }else{ echo 'script>alert("error")/script>'; } fclose($file); } ?>
cls.StringEx.php:
?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; } } ?>
更多关于PHP相关内容感兴趣的读者可查看本站专题:《php curl用法总结》、《PHP网络编程技巧总结》、《PHP数组(Array)操作技巧大全》、《php字符串(string)用法总结》、《PHP数据结构与算法教程》及《PHP中json格式数据操作技巧汇总》
希望本文所述对大家PHP程序设计有所帮助。