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，必须要完全模拟浏览器才行,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

                $url = "http://www.google.com/search?q=$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 = "!<div\s*id=\"search\">(.*)</div>\s+<\!--z-->!";