php 解析html的工具 嵌入式

zuier

　　PHP Simple HTML Dom Parser使用php5+编写，支持以一种超级简单的方式操纵HTML。
    * 需要php5以上版本
    * 支持html标签纠错
    * 支持jQuery风格选择器
    * 非常简洁的从HTML中抽取内容 加载整个页面，然后按HTML标记拆成树，然后再通过查找节点，最后读取需要节点的内容文本即可
　　index.php iframe包含采集页防止采集页js,css等与本站冲突

<div class="maincon">
<iframe id="mainiframe" frameborder=0 width="100%" height="960"
marginheight=0 marginwidth=0 scrolling=no src="http://localhost/appreciate/mobile/recharge"></iframe>
</div>
　　iframe中修改采集页的form提交action，提交到本站进行处理，将提交的数据在模拟采集页提交。（一个表单做2次提交

http://hudeyong926.iteye.com/blog/903490

public function rechargeAction()
{
include_once('lib/simple_html_dom.php');
$html = file_get_html(self::RECHARGE_URL);
$post_url = $html->find('form', 0)->action; //form action
$html->getElementById('mobileNo')->outertext = $html->find('input[id=mobileNo]', 0)->outertext . "<input type='hidden' name='post_url' value='$post_url'>"; //form中传递采集post_url
//$html->find('div.more-com',0)->outertext = '';
$html->find('form', 0)->setAttribute('action', 'http://localhost/appreciate/mobile/rechargePost'); //修改form action
$html->find('td a', 1)->setAttribute('href', 'http://localhost/appreciate/mobile/history'); //修改 订单查询链接
$ereg_rule_src_script = '/^(http|https|ftp):\/\/([A-Z0-9][A-Z0-9_-]*(?:\.[A-Z0-9][A-Z0-9_-]*)+):?(\d+)?\/bank\/ddl\/js\/utility\/utility.index.js?/i';
foreach ($html->find('script') as $script) {  //正则替换js
$script->src = preg_replace($ereg_rule_src_script, 'http://www.test.com/js/lib/dianyin_utility_index.js', $script->src);
}
$content = $html->save();
$html->clear();
unset($html);
die($content);
}
　　采集提交后页面

 
 simple_html_dom修改后


public function rechargeComfirmPage($post_url, $pdata){
include_once("lib/Snoopy.class.php");
$snoopy = new Snoopy; //Snoopy post提交
$snoopy->fetch(self::RECHARGE_URL); //获取所有内容
$snoopy->setcookies();
$cookies = $snoopy->cookies;
$snoopy->cookies = $cookies;
$snoopy->submit($post_url, $pdata);//$pdata为提交的数组,$post_url采集提交url
return $snoopy->results;
}
public function rechargePostAction(){
$pdata['tranCode'] = $this->getRequest()->getPost('tranCode');
$pdata['userCode']       = $this->getRequest()->getPost('userCode');
$pdata['runName']    = $this->getRequest()->getPost('runName');
$post_url      = $this->getRequest()->getPost('post_url');
$this->save2db();
$results = $this->rechargeComfirmPage($post_url, $pdata);
include_once('lib/simple_html_dom.php');
$html = str_get_html($results);//采集提交后页面
//修改UI
$rate = Mage::helper('recharge/data')->getCurrencyToMoney();
$ttt= $this->getLayout()->createBlock('virtualcurrency/customer_accounts_detail')->getCurrentMoney();
$html->find('div[id=testPoints]',0)->innertext = $html->find('div[id=testPoints]',0)->innertext*$rate."<input type='button'>";
$html->find('div[id=test]',0)->innertext='<table><tr>
<td width="30%" align="right"><label class="form-label">您的数:</label></td>
<td align="left">
<p class="B Font14 ml10 ">
'.$ttt.'
</p>
</td>
</tr>
<tr>
<td width="30%" align="right"><label class="form-label">绑定手机号:</label></td>
<td align="left">
<p class="B Font14 ml10 ">
'.$this->_getCustomer()->getMobile().'
</p>
</td>
</tr></table>';
die($html);
}