PHP curl模拟登录带验证码的网站
发布时间：2015-11-30 作者：等你归去来 来源：转载
最近接了个项目，其中有需求是要登录带验证码的网站，获取数据，但是我们不可能人为的一直去记录数据，想通过自动采集的方式进行，下面小编给大家带来的相关代码，对phpcurl模拟登录带验证码的网站感兴趣的朋友一起学习吧
需求是这样的，需要登录带验证码的网站，获取数据，但是不可能人为一直去记录数据，想通过自动采集的方式进行，如下是试验出来的结果代码！有需要的可以参考下！
<?php
namespace HomeController;
use ThinkController;
class LoginController extends Controller
{
protected $cookieName = array('cookie_verify', 'cookie_verify');
protected $cookiePath = '/cookie/';
protected $cookiePathFile = array();
public function index()
{
$this->display();
}
public function _initialize(){
foreach($this->cookieName as $key => $name)
{
$this->cookiePathFile[] = ROOT_PATH . $this->cookiePath . $this->cookieName[$key] . '_xxx.txt';
}
}
/**
* 登录xxx
*/
public function xxxLogin()
{
$username = I('username');
$password = I('password');
$verifyCode = I('verify');
$loginData = array(
'__VIEWSTATE' => '/wEPDwUKMTU0MzAzOTU4NmQYAQUeX19Db250cm9sc1JlcXVpcmVQb3N0QmFja0tleV9fFgEFDExvZ2luX1N1Ym1pdL/yae69NsY163G3yuP0lxjz8oXu', //不把参数补全可能会不被响应哦
'__VIEWSTATEGENERATOR' => 'DC42DE27',
'txt_UserName' => $username,
'txt_PWD' => $password,
'txt_VerifyCode' => $verifyCode,
'SMONEY' => 'ABC',
'Login_Submit.x' => '52',
'Login_Submit.y' => '19',
);
$getBack = $this->_cookieRequest('http://xxx.com/noLogin.aspx', $loginData);
if(preg_match('/(.*?)/s', $getBack, $match)){
echo 'matchedrn';
print_r($match);
}else{
echo $getBack, '
';
$paramsFull = parse_url($getBack);
parse_str($paramsFull['query'], $paramsFull['parsedQuery']);
if(!empty($paramsFull['parsedQuery']['Warn'])) {
$msg = "您好，欢迎来P，请先登录。";
switch ($paramsFull['parsedQuery']['Warn'])
{
case '2':
$msg = '您输入的验证码错误，请重试';
break;
case '3':
$msg = '该帐号不存在，还没帐号？';
break;
case '5':
$msg = '账户已注销';
break;
case '6':
$msg = '密码错误，如果连续错误3次半小时内不能登录！';
break;
case '20':
$msg = '今日密码错误3次及以上，请于半小时后再来登录！';
break;
case '21':
$msg = '今日您所在IP的所有帐号密码错误9次以上，请于半小时后再来登录！';
break;
case '22':
$msg = '登录失败，您所在IP今日登录的帐号过多！';
break;
case '23':
$msg = '登录失败，验证码失效！';
break;
case '32':
$msg = '该帐号已经绑定其他xx帐号！';
break;
case '33':
$msg = '一台电脑一天只能注册一个帐号！';
break;
}
$this->error($msg, '', 5);
}else{
$_SESSION['user_id'] = '123456'; //登录设置session
$this->success('登录P网站成功', U('Index/index'), 5);
}
}
}
/**
* 获取验证码
*/
public function getVerifyCode()
{
$img = $this->_cookieRequest('http://xxx.com/VerifyCode_Login.aspx?id=' . rand(10000,999999), null, true, 1);
echo $img;
}
/**
* 删除cookie
*/
public function clearCookie()
{
for($i = 0; $i <count($this->cookieName); $i++)
{
setcookie($this->cookieName[$i], '', time() - 3600);
}
// unlink($this->cookiePathFile);
$this->success('清除cookie成功！');
}
/**
* 带COOKIE的访问curl
* @param $url 访问地址
* @param bool|array $data 传递的数据
* @param bool $redirect 是否获取重定向的地址
* @return mixed 地址或者返回内容
*/
public function _cookieRequest($url, $data = null, $redirect = false, $cookieNum = 0)
{
$ch = curl_init();
$params[CURLOPT_URL] = $url; //请求url地址
$params[CURLOPT_HEADER] = false; //是否返回响应头信息
$params[CURLOPT_RETURNTRANSFER] = true; //是否将结果返回
$params[CURLOPT_FOLLOWLOCATION] = true; //是否重定向
$params[CURLOPT_USERAGENT] = 'Mozilla/5.0 (Windows NT 5.1; rv:9.0.1) Gecko/20100101 Firefox/9.0.1';
if($data)
{
$params[CURLOPT_POST] = true;
$params[CURLOPT_POSTFIELDS] = http_build_query($data);
}
//判断是否有cookie,有的话直接使用
if (!empty($_COOKIE[$this->cookieName[$cookieNum]]) && is_file($this->cookiePathFile[$cookieNum]))
{
$params[CURLOPT_COOKIEFILE] = $this->cookiePathFile[$cookieNum]; //这里判断cookie
}
else
{
// $cookie_jar = tempnam($cookie_path, 'cookie'); //产生一个cookie文件
$params[CURLOPT_COOKIEJAR] = $this->cookiePathFile[$cookieNum]; //写入cookie信息
setcookie($this->cookieName[$cookieNum], $this->cookiePathFile[$cookieNum], time() + 120); //保存cookie路径
}
curl_setopt_array($ch, $params); //传入curl参数
$content = curl_exec($ch);
$headers = curl_getinfo($ch);
// echo $content;
curl_close($ch);
if ($url != $headers["url"] && $redirect == false)
{
return $headers["url"];
}
return $content;
}
}
登录以后，就可以使用带cookie的访问其他页面了！
ps：php curl 登录淘宝
提交上去后显示为填写验证码，登录不上去
填写验证码提交：
<?php
session_start();
if(empty($_SESSION['cookie_jar'])) exit();
$cookie_jar=$_SESSION['cookie_jar'];
$post_fields=$_POST["vv"];
$ch = curl_init('https://login.taobao.com/member/login.jhtml');
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_USERAGENT,
"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; QQWubi 133; Embedded Web Browser from: http://bsalsa.com/; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Tablet PC 2.0; .NET4.0C; .NET4.0E; InfoPath.3; Media Center PC 6.0)");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, $post_fields);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 1);
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_jar);
$data = curl_exec($ch);
curl_close($ch);
echo $data;exit;
$ch = curl_init('http://www.taobao.com');
curl_setopt($ch, CURLOPT_USERAGENT,
"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; QQWubi 133; Embedded Web Browser from: http://bsalsa.com/; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Tablet PC 2.0; .NET4.0C; .NET4.0E; InfoPath.3; Media Center PC 6.0)");
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 0);
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_jar);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, TRUE);
curl_exec($ch);
curl_close($ch);
?>
提取验证码
<?php
session_start();
$cookie_jar=tempnam("./temp/","cookie");
$_SESSION['cookie_jar']=$cookie_jar;
$post_fields = "action=Authenticator&event_submit_do_login=anything&from=tb&fc=default&style=default&css_style=&tid=XOR_1_000000000000000000000000000000_635045544
70A7C717F750278&support=000001&CtrlVersion=1,0,0,7&loginType=3&minititle=&minipara=&pstrong=&llnick=&sign=&need_sign=&isIgnore=&full_redirect=&popid=&callback=&guf=¬_duplite_str=&need_user_id=&poy=XOR_1_000000000000000000000000000000_625A424A45137C6F7A7F0B786D08&gvfdcname=&gvfdcre=&from_encoding=&TPL_redirect_url=http:www.taobao.com&TPL_username=xxx&TPL_password=xxx";
$ch = curl_init('https://login.taobao.com/member/login.jhtml');
curl_setopt($ch, CURLOPT_USERAGENT,
"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; QQWubi 133; Embedded Web Browser from: http://bsalsa.com/; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Tablet PC 2.0; .NET4.0C; .NET4.0E; InfoPath.3; Media Center PC 6.0)");
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 2);
$data = curl_exec($ch);
curl_close($ch);
preg_match("/id="um_to" name="umto" value="(.*?)"/>/", $data, $arr);
$post_fields = "umto=" . $arr[1] . "&" . $post_fields."&TPL_checkcode=";
echo "" ;
$ch = curl_init('https://login.taobao.com/member/login.jhtml');
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_USERAGENT,
"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; QQWubi 133; Embedded Web Browser from: http://bsalsa.com/; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Tablet PC 2.0; .NET4.0C; .NET4.0E; InfoPath.3; Media Center PC 6.0)");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, $post_fields);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 2);
curl_setopt($ch,CURLOPT_COOKIEJAR,$cookie_jar);
curl_setopt($ch,CURLOPT_COOKIEFILE,$cookie_jar);
$data = curl_exec($ch);
curl_close($ch);
preg_match("/img id="J_StandardCode_m" src="(.*?)" data-src=/", $data, $arr1);
echo "
";
exit;
?>
