用php抓取google关键词排名

 

说下思路，利用php的curl函数储存cookie，google搜索页面是无法用file_get_connents打开的，必须要完全模拟才行,百度就不同了，直接用file_get_conntens抓取页面，然后用正则处理下就行了，这里就不列举百度了。

 <?php

header("content-type: text/html;charset=utf-8");

 

function ggsearch($url_s, $keyword, $page = 1) {

        $enkeyword = urlencode($keyword);

 

        $rsstate = false;

 

        $page_num = ($page -1) * 10;

 

 

        if ($page <= 10) {

                $interface = "eth0:" . rand(1, 4); //避免gg封ip

                $cookie_file = dirname(__file__) . "/temp/google.txt"; //存储cookie值

                $url = "https://www.google.com/search?q=$enkeyword&hl=en&prmd=imvns&ei=jpnjtvlfi8hlggexwbrl&start=$page_num&sa=n";

                $ch = curl_init();

 

                curl_setopt($ch, curlopt_url, $url);

 

                //curl_setopt($ch, curlopt_useragent, $_server['http_user_agent']);//获取浏览器类型

                curl_setopt($ch, curlopt_useragent, "mozilla/5.0 (windows; u; windows nt 6.1; en-us; rv:1.9.1.2) gecko/20090729 firefox/3.5.2 gtb5");

                curl_setopt($ch, curlopt_interface, "$interface"); //指定访问ip地址

                curl_setopt($ch, curlopt_returntransfer, 1);

 

                curl_setopt($ch, curlopt_followlocation, 1);

 

                curl_setopt($ch, curlopt_cookiejar, $cookie_file);

 

                $contents = curl_exec($ch);

 

                curl_close($ch);

 

                $match = "!<p\s*id=\"search\">(.*)</p>\s+<\!--z-->!";

                preg_match_all("$match", "$contents", $line);

                while (list ($k, $v) = each($line[0])) {

                        preg_match_all("!<h3\s+class=\"r\"><a[^>]+>(.*?)</a>!", $v, $title);

                        $num = count($title[1]);

                        for ($i = 0; $i < $num; $i++) {

                                if (strstr($title[0][$i], $url_s)) {

                                        $rsstate = true;

                                        $j = $i +1;

                                        $sum = $j + (($page) * 10 - 10);

                                        //echo $contents;

                                        echo "关键字" . $keyword . "<br>" . "排名：" . '<font color="red" size="20" >' . $sum . '</font>' . "####" . "第" . '<font color="#00ffff" size="18" >'.$page . '</font>'. " 页" . "第" .'<font color="#8000ff" size="15" >'.$j . '</font>'. "名" . $title[0][$i] . "<br>";

                                        echo "<a href='" . $url . "'>" . "点击搜索结果" . "</a>" . "<br>";

                                        echo "<hr>";

                                        break;

                                }

                        }

                }

                unset ($contents);

                if ($rsstate === false) {

                        ggsearch($url_s, $keyword, ++ $page); //找不到搜索页面的继续往下搜索

 

                }

        } else {

 

                echo '关键字' . $keyword . '10页之内没有该网站排名' . '<br>';

                echo "<hr>";

        }

}

if (!empty ($_post['submit'])) {

 

        $time = explode(' ', microtime());

        $start = $time[0] + $time[1];

        $more_key = trim($_post['textarea']);

        $url_s = trim($_post['url']);

        if (!empty ($more_key) && !empty ($url_s)) {

                /*判断输入字符的规律*/

                if (strstr($more_key, "\n")) {

                        $exkey = explode("\n", $more_key);

                }

                if(strstr($more_key, "|")) {

                        $exkey = explode("|", $more_key);

                }

                if(!strstr($more_key, "\n")&&!strstr($more_key, "|")){

                $exkey=array($more_key);

                }

/*判断是否有www或者https://之类的东西*/

                if (count(explode('.', $url_s)) <= 2) {

 

                        $url = ltrim($url_s, 'https://www');

                        $url = 'www.' . $url_s;

                }

                foreach ($exkey as $keyword) {

                        //$keyword;

                        ggsearch($url_s, $keyword);

                }

                $endtime = explode(' ', microtime());

 

                $end = $endtime[0] + $endtime[1];

 

                echo '<hr>';

                echo '程序运行时间: ';

                echo $end - $start;

                //die();

        }

}

?>

<!doctype html public "-//w3c//dtd xhtml 1.0 transitional//en" "https://www.w3.org/tr/xhtml1/dtd/xhtml1-transitional.dtd">

<html xmlns="https://www.w3.org/1999/xhtml">

<head>

<title>抓取排名</title>

 

</head>

 

<body>

<form action="" method="post">

 

 

                        <span>关键字：</span> <textarea name="textarea" rows="20" cols="40" wrap="off">

格式例如：keyword1|keyword2|keyword3

  或者:      keyword1

          keyword2

          keyword3

  </textarea>

 

 

                        <span>url地址：</span><input type="text" name="url">

 

                        <input type="submit" name="submit" value="搜索">

www.2cto.com

 

</form>

</body>

</html>

 

 

摘自shine的圣天堂-〃敏〃