最近在做校园图书馆图书信息的采集程序，既然是图书馆图书的采集，肯定有提交搜索的页面，无非是post提交，让我想到了curl模拟提交，首先通过firebug进行抓包查询下post提交后的格式如下：
txtWxlx=CN&hidWxlx=spanCNLx&txtPY=HZ&txtTm=%D2%F4%C0%D6&txtLx=%25&txtSearchType=1&nMaxCount=100&nSetPageSize=10&cSortFld=%D5%FD%CC%E2%C3%FB&B1=%BC%EC+%CB%F7；搜索的关键字name=txtTm，随后代码如下：
收藏
<?php
$keyword="音乐";$post="txtWxlx=CN&hidWxlx=spanCNLx&txtPY=HZ&txtTm={$keyword}&txtLx=%25&txtSearchType=1&nMaxCount=100&nSetPageSize=20&cSortFld=%D5%FD%CC%E2%C3%FB&B1=%BC%EC+%CB%F7";$url = "http://210.30.68.130/wxjs/tmjs.asp";//查询地址$ch = curl_init();
curl_setopt ($ch, CURLOPT_REFERER, "http://210.30.68.130/wxjs/tmjs_form.asp/ "); //模拟来源 curl_setopt($ch, CURLOPT_URL, $url);//URL curl_setopt($ch,CURLOPT_FOLLOWLOCATION,1);
curl_setopt($ch, CURLOPT_HEADER, false);
curl_setopt($ch, CURLOPT_POST, 1); //模拟POST curl_setopt($ch, CURLOPT_POSTFIELDS, $post);//POST内容 curl_exec($ch);
$output = curl_close($ch);
echo $output; ?>但返回的页面总是显示没有相关内容，如果把关键字改成英语或者数字就可以正常显示了，于是想到这应该是编码问题，然后在post上面可以看到txtTm=%D2%F4%C0%D6经过查询得知这是url编码，汉字会进行转化，如果是英语则不会发生任何改变，于是就把头信息也加了部分内容进去如下：
$header = array(); $header[] = 'User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:30.0) Gecko/20100101 Firefox/30.0'; $header[] = 'Accept:text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'; $header[] = 'Connection: keep-alive'; $header[] = 'Content-Type:application/x-www-form-urlencoded'; curl_setopt ( $ch, CURLOPT_HTTPHEADER, $header );
其实主要是$header[] = 'Content-Type:application/x-www-form-urlencoded';再次加载页面后如果是汉字显示还是没有相关的内容，随后想到了一个很简单的问题所在，php程序是utf8的，然而图书馆的网站是gb2312，好吧，再加上一句，$keyword = iconv('UTF-8', 'GB2312', $keyword);再次加载成功，这个应该才是问题关键所在，然后我把头信息删除后添加一句$keyword = urlencode($keyword);再次加载也就是下面的代码：
<?php $keyword="世界";
$keyword = iconv('UTF-8', 'GB2312', $keyword);
$keyword = urlencode($keyword);
$post="txtWxlx=CN&hidWxlx=spanCNLx&txtPY=HZ&txtTm={$keyword}&txtLx=%25&txtSearchType=1&nMaxCount=100&nSetPageSize=20&cSortFld=%D5%FD%CC%E2%C3%FB&B1=%BC%EC+%CB%F7";
$url = "http://210.30.68.130/wxjs/tmjs.asp";
//查询地址
$ch = curl_init();
curl_setopt ($ch, CURLOPT_REFERER, "http://210.30.68.130/wxjs/tmjs_form.asp/ "); //模拟来源
curl_setopt($ch, CURLOPT_URL, $url);//URL
curl_setopt($ch,CURLOPT_FOLLOWLOCATION,1);
curl_setopt($ch, CURLOPT_HEADER, false);
curl_setopt($ch, CURLOPT_POST, 1); //模拟POST
curl_setopt($ch, CURLOPT_POSTFIELDS, $post);//POST内容
curl_exec($ch);
$output = curl_close($ch);
echo $output;
?>CURL模拟POST ,实例1：
<?php
$uri = "http://tanteng.duapp.com/test.php";
//
参数数组
$data = array (
'name' => 'tanteng'
// 'pass
word
' => 'password'
);
$ch = curl_init ();
// print_r($ch);
curl_setopt
( $ch, CURLOPT_URL, $uri );
curl_setopt ( $ch, CURLOPT_POST, 1 );
curl_setopt ( $ch, CURLOPT_HEADER, 0 );
curl_setopt ( $ch, CURLOPT_RETURNTRANSFER, 1 );
curl_setopt ( $ch, CURLOPT_POSTFIELDS, $data );
$return = curl_exec ( $ch );
curl_close ( $ch );
print_r($return);
//接受php页面远程服务器：
<?php
if(isset($_POST['name'])){
if(!empty($_POST['name'])){
echo '您好，',$_POST['name'].'！';
}
}CURL模拟POST ,实例2
用CURL模拟POST请求抓取邮编与地址：
<?php
$runtime = new runtime ();
$runtime->start ();
$cookie_jar = tempnam('/tmp','cookie');
$filename = $argv[1];
$start_num= $argv[2];
$end_num = $argv[3];
for($i=$start_num; $i<$end_num; $i++){
$zip = sprintf('6s',$i);
$fields_post = array(
'postcode' => $zip,
'queryKind' => 2,
'reqCode' => 'gotoSearch',
'search_button.x'=>37,
'search_button.y'=>12
);
$fields_string = http_build_query ( $fields_post, '&' );
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, "URL?reqCode=gotoSearch&queryKind=2&postcode=".$zip);
curl_setopt($ch, CURLOPT_HEADER, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 120 );
curl_setopt($ch, CURLOPT_REFERER, $refer );
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers_login );
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_jar );
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_jar );
curl_setopt($ch, CURLOPT_USERAGENT, $_SERVER['HTTP_USER_AGENT']);
curl_setopt($ch, CURLOPT_POST, 1); // 发送一个常规的Post请求
curl_setopt($ch, CURLOPT_POSTFIELDS, $fields_string );
$data = curl_exec($ch);
preg_match_all('/id="table1">[s]*?<tr>[s]*?<td class="maintext">[sS]*?</td>[s]*?</tr>/', $data,
$matches);
if (!$handle = fopen($filename, 'a+')) {
echo "不能打开文件$filename";
echo "n";
exit;
}
if (fwrite($handle, $matches[0][1]) === FALSE) {
echo "不能写入到文件$filename";
echo "n";
exit;
}
echo "成功地将$somecontent 写入到文件$filename";
echo "n";
fclose($handle);
curl_close($ch);
}
class runtime
{
var $StartTime = 0;
var $StopTime = 0;
function get_microtime()
{
list($usec,$sec)=explode(' ',microtime());return((float)$usec+(float)$sec);
}
function start()
{
$this->StartTime=$this->get_microtime();
}
function stop(){
$this->StopTime=$this->get_microtime();
}
function spent()
{
return ($this->StopTime-$this->StartTime);
}
}
$runtime->stop ();
$con = 'Processed in'.$runtime->spent().'seconds';
echo 'Processed in'. $runtime->spent().'seconds';CURL模拟POST ,实例3
模拟POST请求提交数据或上传文件
http://www.a.com/a.php
发送POST请求
function execUpload(){
$file = '/doucment/Readme.txt';
$ch = curl_init();
$post_data = array(
'loginfield' => 'username',
'username' => 'ybb',
'password' => '123456',
'file' => '@d:usrwwww.shanxiwang.netwwtranslatedocumentReadme.txt'
);
curl_setopt($ch, CURLOPT_HEADER, false);
//启用时会发送一个常规的POST请求，类型为：application/x-www-form-urlencoded，就像表单提交的一样。
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch,CURLOPT_BINARYTRANSFER,true);
curl_setopt($ch, CURLOPT_POSTFIELDS,$post_data);
curl_setopt($ch, CURLOPT_URL, 'handleUpload.php');
$info= curl_exec($ch);
curl_close($ch);
print_r($info);
}
2.http://www.b.com/handleUpload.php
function handleUpload(){
print_r($_POST);
echo '===file upload info:';
print_r($_FILES);■cURL 函数
■curl_close —关闭一个cURL会话
■curl_copy_handle —复制一个cURL句柄和它的所有选项
■curl_errno —返回最后一次的错误号
■curl_error —返回一个保护当前会话最近一次错误的字符串
■curl_exec —执行一个cURL会话
■curl_getinfo —获取一个cURL连接资源句柄的信息
■curl_init —初始化一个cURL会话
■curl_multi_add_handle —向curl批处理会话中添加单独的curl句柄
■curl_multi_close —关闭一组cURL句柄
■curl_multi_exec —运行当前cURL 句柄的子连接
■curl_multi_getcontent—如果设置了CURLOPT_RETURNTRANSFER，则返回获取的输出的文本流
■curl_multi_info_read —获取当前解析的cURL的相关传输信息
■curl_multi_init —返回一个新cURL批处理句柄
■curl_multi_remove_handle — 移除curl批处理句柄资源中的某个句柄资源
■curl_multi_select—等待所有cURL批处理中的活动连接
■curl_setopt_array —为cURL传输会话批量设置选项
■curl_setopt —设置一个cURL传输选项
■curl_version —获取cURL版本信息
Copyright 2014-2025 https://www.php.cn/ All Rights Reserved | php.cn | 湘ICP备2023035733号
