PHP采集利器 Snoopy 试用心得_PHP教程

$url = "http://www.jb51.net";
include("snoopy.php");
$snoopy = new Snoopy;
$snoopy->fetch($url); //获取所有内容
echo $snoopy->results; //显示结果
$snoopy->fetchtext //获取文本内容（去掉html代码）
$snoopy->fetchlinks //获取链接
$snoopy->fetchform //获取表单

$formvars["username"] = "admin";
$formvars["pwd"] = "admin";
$action = "http://www.jb51.net";//表单提交地址
$snoopy->submit($action,$formvars);//$formvars为提交的数组
echo $snoopy->results; //获取表单提交后的 返回的结果
$snoopy->submittext; //提交后只返回 去除html的 文本
$snoopy->submitlinks;//提交后只返回 链接

$formvars["username"] = "admin";
$formvars["pwd"] = "admin";
$action = "http://www.jb51.net";
include "snoopy.php";
$snoopy = new Snoopy;
$snoopy->cookies["PHPSESSID"] = 'fc106b1918bd522cc863f36890e6fff7'; //伪装sessionid
$snoopy->agent = "(compatible; MSIE 4.01; MSN 2.5; AOL 4.0; Windows 98)"; //伪装浏览器
$snoopy->referer = "http://s.jb51.net"; //伪装来源页地址 http_referer
$snoopy->rawheaders["Pragma"] = "no-cache"; //cache 的http头信息
$snoopy->rawheaders["X_FORWARDED_FOR"] = "127.0.0.101"; //伪装ip
$snoopy->submit($action,$formvars);
echo $snoopy->results;

$snoopy->proxy_host = "www.jb51.net";
$snoopy->proxy_port = "8080"; //使用代理
$snoopy->maxredirs = 2; //重定向次数
$snoopy->expandlinks = true; //是否补全链接 在采集的时候经常用到
// 例如链接为 /images/taoav.gif 可改为它的全链接 http://www.jb51.net/images/taoav.gif，这个地方其实可以在最后输出的时候用ereg_replace函数自己替换
$snoopy->maxframes = 5 //允许的最大框架数
//注意抓取框架的时候 $snoopy->results 返回的是一个数组
$snoopy->error //返回报错信息

//echo var_dump($_SERVER);
include("Snoopy.class.php");
$snoopy = new Snoopy;
$snoopy->agent = "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-
CN; rv:1.9.0.5) Gecko/2008120122 Firefox/3.0.5 FirePHP/0.2.1";//这项是浏览器信
息，前面你用什么浏览器查看cookie，就用那个浏览器的信息(ps:$_SERVER可以查看到浏览器的信息)
$snoopy->referer = "http://bbs.jb51.net/index.php";
$snoopy->expandlinks = true;
$snoopy->rawheaders["COOKIE"]="__utmz=17229162.1227682761.29.7.utmccn=(referral)|utmcsr=jb51.net|utmcct=/html/index.html|utmcmd=referral; cdbphpchina_smile=1D2D0D1; cdbphpchina_cookietime=2592000; __utma=233700831.1562900865.1227113506.1229613449.1231233266.16; __utmz=233700831.1231233266.16.8.utmccn=(referral)|utmcsr=localhost:8080|utmcct=/test3.php|utmcmd=referral; __utma=17229162.1877703507.1227113568.1231228465.1231233160.58; uchome_loginuser=sinopf; xscdb_cookietime=2592000; __utmc=17229162; __utmb=17229162; cdbphpchina_sid=EX5w1V; __utmc=233700831; cdbphpchina_visitedfid=17; cdbphpchinaO766uPYGK6OWZaYlvHSuzJIP22VpwEMGnPQAuWCFL9Fd6CHp2e%2FKw0x4bKz0N9lGk; xscdb_auth=8106rAyhKpQL49eMs%2FyhLBf3C6ClZ%2B2idSk4bExJwbQr%2BHSZrVKgqPOttHVr%2B6KLPg3DtWpTMUI4ttqNNVpukUj6ElM; cdbphpchina_onlineusernum=3721";
$snoopy->fetch("http://bbs.jb51.net");
$n=ereg_replace("href=\"","href=\"http://bbs.jb51.net/",$snoopy->results );
echo ereg_replace("src=\"","src=\"http://bbs.jb51.net/",$n);
?>