Home >Backend Development >PHP Tutorial >curl抓取网页正则匹配问题
curl抓取网页正则匹配问题
- WBOYOriginal
- 2016-06-06 20:16:121382browse
在Mac上写的PHP代码，可正常执行，但是在Web Server上运行时会匹配不到。
Mac上PHP Version 5.5.30，CentOS 7服务器上的是PHP Version 5.6.15。
就是在执行到第二个if时会保未找到该用户！
<code>//正则匹配页面中的用户信息，如果匹配成功则进入编辑页面
if ($c = preg_match_all ('/(\/UserManage\/edit\/id\/\d*)/is', $search_result, $matches))
{
$string1 = $matches[1][0];
//获取页面中的用户信息，并进入编辑页面
$match_user = curl_init();
curl_setopt($match_user, CURLOPT_URL, 'https://crm.pzoom.com'.$string1);//登陆后要从哪个页面获取信息
curl_setopt($match_user, CURLOPT_POST, 1);
curl_setopt($match_user, CURLOPT_COOKIEFILE, PZOOM_COOKIE_FILE);// 获取COOKIE文件
curl_setopt($match_user, CURLOPT_RETURNTRANSFER, 1);//设定返回 的数据是否自动显示
curl_setopt($match_user, CURLOPT_HEADER, false);//设定是否显示头信 息
curl_setopt($match_user, CURLOPT_NOBODY, false);//设定是否输出页面 内容
$edit_info = curl_exec($match_user);//返回结果
curl_close($match_user); //关闭
if ($c2=preg_match_all ('/(.*?value=\"(.*)\")/is', $edit_info, $edit_info_match))
{
if ($c3=preg_match_all ('/(.*?value=\"(.*)\") (checked)/is', $edit_info, $match_radio))
{
}else{
echo "匹配失败!";
}
if ($c4=preg_match_all ('/(textarea class="descript_cont" name="user\\[userDesc\\]" id="userDesc">)(.*)()/is', $edit_info, $match_textarea))
{
}else{
echo "匹配失败!";
}
$call_id = $edit_info_match[2][0];
$user_userid = $edit_info_match[2][1];
$user_name = $edit_info_match[2][2];
$user_sex = $match_radiop[1][0];
$user_tel = $edit_info_match[2][5];
$user_mobile = $edit_info_match[2][6];
$user_mail = $edit_info_match[2][7];
$user_departmentid = $edit_info_match[2][9];
$user_address = $edit_info_match[2][10];
$call_areacode = $edit_info_match[2][12];
$call_pwd = $edit_info_match[2][14];
$user_desc = $match_textarea[2][0];
$user_id = substr($string1,-4);
//发起新的请求，并提交用户输入的分机号
$edit_userinfor = curl_init();
curl_setopt($edit_userinfor, CURLOPT_URL, 'https://crm.pzoom.com/UserManage/edit');//登陆后要从哪个页面获取信息
curl_setopt($edit_userinfor, CURLOPT_POST, 1);
$submit_userinfo = "call[id2]=$call_id&user[userid]=$user_userid&user[username]=$user_name&user[sex]=$user_sex&user[usertel]=$user_tel&user[usermobile]=$user_mobile&user[useremail]=$user_mail&user[departmentid]=$user_departmentid&user[address]=$user_address&call[cno]=$tel_number&call[areaCode]=021&isManager=1&call[pwd]=Aa123456&user[userDesc]=$user_desc&user[num]=1&user[id]=$user_id";
curl_setopt($edit_userinfor, CURLOPT_POSTFIELDS, $submit_userinfo);//传递数据
curl_setopt($edit_userinfor, CURLOPT_COOKIEFILE, PZOOM_COOKIE_FILE);// 获取COOKIE文件
curl_setopt($edit_userinfor, CURLOPT_RETURNTRANSFER, 1);//设定返回 的数据是否自动显示
curl_setopt($edit_userinfor, CURLOPT_HEADER, false);//设定是否显示头信 息
$submint_userinfo = curl_exec($edit_userinfor);//返回结果
curl_close($edit_userinfor); //关闭
}else{
die("未找到该用户！");
}
}else{
die("未找到该用户！");
}
}</code>
难道PHP版本不同，正则表达式也不一样？
回复内容：
在Mac上写的PHP代码，可正常执行，但是在Web Server上运行时会匹配不到。
Mac上PHP Version 5.5.30，CentOS 7服务器上的是PHP Version 5.6.15。
就是在执行到第二个if时会保未找到该用户！
<code>//正则匹配页面中的用户信息，如果匹配成功则进入编辑页面
if ($c = preg_match_all ('/(\/UserManage\/edit\/id\/\d*)/is', $search_result, $matches))
{
$string1 = $matches[1][0];
//获取页面中的用户信息，并进入编辑页面
$match_user = curl_init();
curl_setopt($match_user, CURLOPT_URL, 'https://crm.pzoom.com'.$string1);//登陆后要从哪个页面获取信息
curl_setopt($match_user, CURLOPT_POST, 1);
curl_setopt($match_user, CURLOPT_COOKIEFILE, PZOOM_COOKIE_FILE);// 获取COOKIE文件
curl_setopt($match_user, CURLOPT_RETURNTRANSFER, 1);//设定返回 的数据是否自动显示
curl_setopt($match_user, CURLOPT_HEADER, false);//设定是否显示头信 息
curl_setopt($match_user, CURLOPT_NOBODY, false);//设定是否输出页面 内容
$edit_info = curl_exec($match_user);//返回结果
curl_close($match_user); //关闭
if ($c2=preg_match_all ('/(.*?value=\"(.*)\")/is', $edit_info, $edit_info_match))
{
if ($c3=preg_match_all ('/(.*?value=\"(.*)\") (checked)/is', $edit_info, $match_radio))
{
}else{
echo "匹配失败!";
}
if ($c4=preg_match_all ('/(textarea class="descript_cont" name="user\\[userDesc\\]" id="userDesc">)(.*)()/is', $edit_info, $match_textarea))
{
}else{
echo "匹配失败!";
}
$call_id = $edit_info_match[2][0];
$user_userid = $edit_info_match[2][1];
$user_name = $edit_info_match[2][2];
$user_sex = $match_radiop[1][0];
$user_tel = $edit_info_match[2][5];
$user_mobile = $edit_info_match[2][6];
$user_mail = $edit_info_match[2][7];
$user_departmentid = $edit_info_match[2][9];
$user_address = $edit_info_match[2][10];
$call_areacode = $edit_info_match[2][12];
$call_pwd = $edit_info_match[2][14];
$user_desc = $match_textarea[2][0];
$user_id = substr($string1,-4);
//发起新的请求，并提交用户输入的分机号
$edit_userinfor = curl_init();
curl_setopt($edit_userinfor, CURLOPT_URL, 'https://crm.pzoom.com/UserManage/edit');//登陆后要从哪个页面获取信息
curl_setopt($edit_userinfor, CURLOPT_POST, 1);
$submit_userinfo = "call[id2]=$call_id&user[userid]=$user_userid&user[username]=$user_name&user[sex]=$user_sex&user[usertel]=$user_tel&user[usermobile]=$user_mobile&user[useremail]=$user_mail&user[departmentid]=$user_departmentid&user[address]=$user_address&call[cno]=$tel_number&call[areaCode]=021&isManager=1&call[pwd]=Aa123456&user[userDesc]=$user_desc&user[num]=1&user[id]=$user_id";
curl_setopt($edit_userinfor, CURLOPT_POSTFIELDS, $submit_userinfo);//传递数据
curl_setopt($edit_userinfor, CURLOPT_COOKIEFILE, PZOOM_COOKIE_FILE);// 获取COOKIE文件
curl_setopt($edit_userinfor, CURLOPT_RETURNTRANSFER, 1);//设定返回 的数据是否自动显示
curl_setopt($edit_userinfor, CURLOPT_HEADER, false);//设定是否显示头信 息
$submint_userinfo = curl_exec($edit_userinfor);//返回结果
curl_close($edit_userinfor); //关闭
}else{
die("未找到该用户！");
}
}else{
die("未找到该用户！");
}
}</code>
难道PHP版本不同，正则表达式也不一样？
好歹给个数据让测试一下啊，光看能看出什么来
因为抓取的是公司的OA系统，所以不方便透露全部代码，而且我在匹配后是要连接本地的数据库，进行数据匹配，填入相应的值！
下面是我要匹配的页面的表单：
<code><form action="" method="post" id="myform">
<input type="hidden" value="1010" name="call[id2]">
<ul class="clearfix">
<li><label><span><em>*</em>用户名：</span><input type="text" name="user[userid]" id="userid" class="ipt custom_ipt" onblur="checkName()" value="yangtao"></label></li>
<li><label><span><em>*</em>真实姓名：</span><input type="text" name="user[username]" id="username" class="ipt custom_ipt" value="杨涛"></label></li>
<li><label><span>性别：</span>
<input type="radio" name="user[sex]" id="sex1" value="男">男
<input type="radio" name="user[sex]" id="sex2" value="女">女
</label></li>
<li><label><span>固定电话：</span><input type="text" name="user[usertel]" id="usertel" class="ipt" value=""></label></li>
<li><label><span>移动电话：</span><input type="text" name="user[usermobile]" id="usermobile" value="15800470152" class="ipt custom_ipt"></label></li>
<li><label><span><em>*</em>电子邮件：</span><input type="text" name="user[useremail]" id="useremail" value="yangtao@qiso360.com" class="ipt custom_ipt"></label></li>
<li style="position:relative;"><label><span><em>*</em>部门：</span>
<input type="text" class="ipt one_btn_client" id="departmentid" value="上分销售部">
<input type="hidden" class="one_btn_search" name="user[departmentid]" value="89">
<ul class="client_list">
</ul>
</label></li>
<li><label><span>详细地址：</span><input type="text" name="user[address]" value="" class="ipt custom_ipt"></label></li>
<li>
<label><span>坐席工号：</span><input type="text" value="8451" name="call[cno]" class="ipt custom_ipt"></label>(工号取值范围2000-9999)</li>
<li>
<label><span>坐席区号：</span><input type="text" value="021" name="call[areaCode]" class="ipt custom_ipt"></label>(座席所在地区区号)</li>
<li><label><span>是否管理人员：</span><input type="radio" name="isManager" value="1" checked>否 <input type="radio" name="isManager" value="2">是</label></li>
<li>
<label><span>坐席密码：</span><input type="text" value="Aa123456" name="call[pwd]" class="ipt custom_ipt"></label>(不填为默认密码123456)</li>
<li><label><span>描述信息：</span><textarea class="descript_cont" name="user[userDesc]" id="userDesc"></textarea></label></li>
<li>
<label><span>状态：</span><input type="radio" name="user[num]" value="1" checked>正常 <input type="radio" name="user[num]" value="2">冻结 <input type="radio" name="user[num]" value="3">离职</label>
</li>
</ul>
<div class="add_custom_add">
<input type="hidden" name="user[id]" id="uid" value="3408">
<input type="button" value="保存" class="btn_add" id="bbs">
<a href="/UserManage/userinfo" class="btn_add">返回</a>
</div>
</form></code>
Statement：
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn
Previous article：关于构建大型SPA的疑问Next article：yii2 为什么没有好的开源项目呢？