|
这篇文章主要介绍了PHP实现登录搜狐广告获取广告联盟数据的方法,涉及php基于curl的远程数据操作相关技巧,需要的朋友可以参考下
本文实例讲述了PHP实现登录搜狐广告获取广告联盟数据的方法。分享给大家供大家参考，具体如下：
一直有一个想法，每次都要登录去看联盟昨天收益多少？每天都要登录和麻烦，能不能做一个汇总发邮件的功能呢？
可惜了，验证码绕不过去，只能想一个办法。先在服务器手动打一次验证码，然后在通过定时器，每隔10分钟请求一个页面
这样的话Cookies就不会失效，，然后每周只需要跟我汇总数据就Ok了。。
远程提交表单的原理，可以参考：PHP基于curl后台远程登录正方教务系统的方法
参考的代码还是一样的如下
获取验证码Code.php
define("SITE_PATH", $_SERVER['DOCUMENT_ROOT']);
$LoginUrl = "http://union.sogou.com/";
$url = $LoginUrl."validateCode";
$filedir = SITE_PATH."/TMP/Cookies";
$cookie_file = $filedir."/cookie.txt";
if(!mkdirs($filedir))
{
echo "目录创建失败";
exit;
}
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_HEADER, 0); //不返回header部分
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0)");
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file);
//curl_setopt($ch, CURLOPT_REFERER, "http://125.89.69.234");
curl_setopt($ch, CURLOPT_RETURNTRANSFER,1);
curl_setopt($ch, CURLOPT_TIMEOUT, "10");
$response = curl_exec($ch);
curl_close($ch);
header("Content-type:image/gif");
echo $response;
//创建目录
function mkdirs($dir)
{
if(!is_dir($dir))
{
if(!mkdirs(dirname($dir))){
return false;
}
if(!mkdir($dir,0777)){
return false;
}
}
return true;
}
获取数据的页面，这里需要通过表单来提交手动的验证码
define("SITE_PATH", $_SERVER['DOCUMENT_ROOT']);
require_once SITE_PATH.'/class/SimpleHtmlDom.class.php';
class GetData{
private $url ;
public function __construct(){
$this->url = "http://union.sogou.com/index.action?searchBean.timeSegment=yestoday";
$this->LoginUrl = "http://union.sogou.com/";
$this->PostData = $this->LoginUrl."loginauth.action";
$this->table = "dwz_union";
}
public function post($code)
{
$POST['loginFromPage'] = "homePage";
$POST['username'] = "xxxxxx";
$POST['password'] = "xxxxx";
$POST['activecode'] = $code;
$POST['button.x']="14";
$POST['button.y']="16";
foreach($POST as $key=>$value)
{
$tmp[] = $key."=".$value;
}
$postStr = implode("&", $tmp);
$filedir = SITE_PATH."/TMP/Cookies";
$cookie_file = $filedir."/cookie.txt";
$result = $this->curl($this->PostData, "http://union.sogou.com/loginauth.action", $postStr, $cookie_file);
$url = "http://union.sogou.com/index.action";
$postArr = "searchBean.timeSegment=yestoday";
$response = $this->curl($url, " http://union.sogou.com/index.action?pid=dengwz7788", $postArr, $cookie_file);
$this->saveData($response);
}
private function saveData($response)
{
$dom = str_get_html($response);
$tmp = $dom->find('div.rtable table tbody tr',1)->plaintext;
$data = preg_split("/\s+/i", $tmp);
$this->link();
$date = date('Y-m-d',strtotime('-1 day'));
$datetime = date('Y-m-d H:i:s');
$money = $data['4'];
$shows = $data['2'];
$times = $data['3'];
$sql = "select sum(money) as total from {$this->table}";
$query = mysql_query($sql);
$totaTmp = mysql_fetch_row($query);
var_dump($totalTmp);
if(empty($totaTmp['0']))
{
$total = $money;
}else{
$total = $totaTmp['0']+$money;
}
$sql = "insert into {$this->table}(date,datetime,money,shows,times,total) values('{$date}','{$datetime}','{$money}','{$shows}','{$times}','{$total}')";
mysql_query($sql);
}
private function link()
{
$link = mysql_connect('localhost', 'root', '');
mysql_select_db('dblog', $link);
mysql_query('SET NAMES utf8');
}
private function saveHtml($infomation,$filedir,$filename)
{
if(!$this->mkdirs($filedir))
{
return 0;
}
$sf = $filedir."/".$filename;
$fp=fopen($sf,"w"); //写方式打开文件
fwrite($fp,$infomation); //存入内容
fclose($fp); //关闭文件
}
//创建目录
private function mkdirs($dir)
{
if(!is_dir($dir))
{
if(!$this->mkdirs(dirname($dir))){
return false;
}
if(!mkdir($dir,0777)){
return false;
}
}
return true;
}
public function login()
{
$filedir = SITE_PATH."/TMP/Cookies";
if(!$this->mkdirs($filedir))
{
echo "目录创建失败";
exit;
}
$cookie_file = $filedir."/cookie.txt";
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $this->LoginUrl);
curl_setopt($ch, CURLOPT_HEADER, 0); //不返回header部分
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0)");
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file);
//curl_setopt($ch, CURLOPT_REFERER, "http://125.89.69.234");
curl_setopt($ch, CURLOPT_RETURNTRANSFER,1);
curl_setopt($ch, CURLOPT_TIMEOUT, "10");
$response = curl_exec($ch);
curl_close($ch);
// 鍏抽棴CURL浼氳瘽
}
private function curl($url,$url2,$fields,$cookie_file)
{
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_HEADER, 0); //不返回header部分
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0)");
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, $fields);
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_file);
curl_setopt($ch, CURLOPT_RETURNTRANSFER,1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION,1);
curl_setopt($ch, CURLOPT_HTTPHEADER, array("Host: union.sogou.com" ));
curl_setopt($ch, CURLOPT_REFERER,$url2);
$response = curl_exec($ch);
//echo curl_error($ch);
curl_close($ch);
return $response;
}
}
$GetData = new GetData();
if(isset($_POST['code']))
{
$GetData->POST($_POST['code']);
}
完整实例代码点击此处本站下载。
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数组(Array)操作技巧大全》、《php排序算法总结》、《PHP常用遍历算法与技巧总结》、《PHP数据结构与算法教程》、《php程序设计算法总结》、《PHP数学运算技巧总结》、《php正则表达式用法总结》、《PHP运算与运算符用法总结》、《php字符串(string)用法总结》及《php常见数据库操作技巧汇总》
希望本文所述对大家PHP程序设计有所帮助。 |
发表于 2016-10-14 15:58:25
