本节内容:
PHP实现的POP3类,可以直接使用。
基于 POP3/SMTP 协议写的一个操作类,使用 fsockopen ,然后写入/接收数据,只实现了最核心的部分功能,当作是学习 Socket 操作的练手。
其中参考了 RFC 2449和一个国外的简单Web邮件系统 Uebimiau 的部分代码。
例子:
<?php
/**
* PHP Socket POP3类
* by www.
*/
class SocketPOPClient
{
var $strMessage = '';
var $intErrorNum = 0;
var $bolDebug = false;
var $strEmail = '';
var $strPasswd = '';
var $strHost = '';
var $intPort = 110;
var $intConnSecond = 30;
var $intBuffSize = 8192;
var $resHandler = NULL;
var $bolIsLogin = false;
var $strRequest = '';
var $strResponse = '';
var $arrRequest = array();
var $arrResponse = array();
//---------------
// 基础操作
//---------------
//构造函数
function SocketPOP3Client($strLoginEmail, $strLoginPasswd, $strPopHost='', $intPort='')
{
$this->strEmail = trim(strtolower()($strLoginEmail));
$this->strPasswd = trim($strLoginPasswd);
$this->strHost = trim(strtolower($strPopHost));
if ($this->strEmail=='' || $this->strPasswd=='')
{
$this->setMessage('Email address or Passwd is empty', 1001);
return false;
}
if (!PReg_match("/^[\w-]+(\.[\w-]+)*@[\w-]+(\.[\w-]+)+$/i", $this->strEmail))
{
$this->setMessage('Email address invalid', 1002);
return false;
}
if ($this->strHost=='')
{
$this->strHost = substr(strrchr($this->strEmail, "@"), 1);
}
if ($intPort!='')
{
$this->intPort = $intPort;
}
$this->connectHost();
}
//连接服务器
function connectHost()
{
if ($this->bolDebug)
{
echo "Connection ".$this->strHost." ...\r\n";
}
if (!$this->getIsConnect())
{
if ($this->strHost=='' || $this->intPort=='')
{
$this->setMessage('POP3 host or Port is empty', 1003);
return false;
}
$this->resHandler = @fsockopen($this->strHost, $this->intPort, &$this->intErrorNum, &$this->strMessage, $this->intConnSecond);
if (!$this->resHandler)
{
$strErrMsg = 'Connection POP3 host: '.$this->strHost.' failed';
$intErrNum = 2001;
$this->setMessage($strErrMsg, $intErrNum);
return false;
}
$this->getLineResponse();
if (!$this->getRestIsSucceed())
{
return false;
}
}
return true;
}
//关闭连接
function closeHost()
{
if ($this->resHandler)
{
fclose($this->resHandler);
}
return true;
}
//发送指令
function sendCommand($strCommand)
{
if ($this->bolDebug)
{
if (!preg_match("/PASS/", $strCommand))
{
echo "Send Command: ".$strCommand."\r\n";
}
else
{
echo "Send Command: PASS ******\r\n";
}
}
if (!$this->getIsConnect())
{
return false;
}
if (trim($strCommand)=='')
{
$this->setMessage('Request command is empty', 1004);
return false;
}
$this->strRequest = $strCommand."\r\n";
$this->arrRequest[] = $strCommand;
fputs($this->resHandler, $this->strRequest);
return true;
}
//提取响应信息第一行
function getLineResponse()
{
if (!$this->getIsConnect())
{
return false;
}
$this->strResponse = fgets($this->resHandler, $this->intBuffSize);
$this->arrResponse[] = $this->strResponse;
return $this->strResponse;
}
//提取若干响应信息,$intReturnType是返回值类型, 1为字符串, 2为数组
function getRespMessage($intReturnType)
{
if (!$this->getIsConnect())
{
return false;
}
if ($intReturnType == 1)
{
$strAllResponse = '';
while(!feof($this->resHandler))
{
$strLineResponse = $this->getLineResponse();
if (preg_match("/^\+OK/", $strLineResponse))
{
continue;
}
if (trim($strLineResponse)=='.')
{
break;
}
$strAllResponse .= $strLineResponse;
}
return $strAllResponse;
}
else
{
$arrAllResponse = array();
while(!feof($this->resHandler))
{
$strLineResponse = $this->getLineResponse();
if (preg_match("/^\+OK/", $strLineResponse))
{
continue;
}
if (trim($strLineResponse)=='.')
{
break;
}
$arrAllResponse[] = $strLineResponse;
}
return $arrAllResponse;
}
}
//提取请求是否成功
function getRestIsSucceed($strRespMessage='')
{
if (trim($responseMessage)=='')
{
if ($this->strResponse=='')
{
$this->getLineResponse();
}
$strRespMessage = $this->strResponse;
}
if (trim($strRespMessage)=='')
{
$this->setMessage('Response message is empty', 2003);
return false;
}
if (!preg_match("/^\+OK/", $strRespMessage))
{
$this->setMessage($strRespMessage, 2000);
return false;
}
return true;
}
//获取是否已连接
function getIsConnect()
{
if (!$this->resHandler)
{
$this->setMessage("Nonexistent availability connection handler", 2002);
return false;
}
return true;
}
//设置消息
function setMessage($strMessage, $intErrorNum)
{
if (trim($strMessage)=='' || $intErrorNum=='')
{
return false;
}
$this->strMessage = $strMessage;
$this->intErrorNum = $intErrorNum;
return true;
}
//获取消息
function getMessage()
{
return $this->strMessage;
}
//获取错误号
function getErrorNum()
{
return $this->intErrorNum;
}
//获取请求信息
function getRequest()
{
return $this->strRequest;
}
//获取响应信息
function getResponse()
{
return $this->strResponse;
}
//---------------
// 邮件原子操作
//---------------
//登录邮箱
function popLogin()
{
if (!$this->getIsConnect())
{
return false;
}
$this->sendCommand("USER ".$this->strEmail);
$this->getLineResponse();
$bolUserRight = $this->getRestIsSucceed();
$this->sendCommand("PASS ".$this->strPasswd);
$this->getLineResponse();
$bolPassRight = $this->getRestIsSucceed();
if (!$bolUserRight || !$bolPassRight)
{
$this->setMessage($this->strResponse, 2004);
return false;
}
$this->bolIsLogin = true;
return true;
}
//退出登录
function popLogout()
{
if (!$this->getIsConnect() && $this->bolIsLogin)
{
return false;
}
$this->sendCommand("QUIT");
$this->getLineResponse();
if (!$this->getRestIsSucceed())
{
return false;
}
return true;
}
//获取是否在线
function getIsOnline()
{
if (!$this->getIsConnect() && $this->bolIsLogin)
{
return false;
}
$this->sendCommand("NOOP");
$this->getLineResponse();
if (!$this->getRestIsSucceed())
{
return false;
}
return true;
}
//获取邮件数量和字节数(返回数组)
function getMailSum($intReturnType=2)
{
if (!$this->getIsConnect() && $this->bolIsLogin)
{
return false;
}
$this->sendCommand("STAT");
$strLineResponse = $this->getLineResponse();
if (!$this->getRestIsSucceed())
{
return false;
}
if ($intReturnType==1)
{
return $this->strResponse;
}
else
{
$arrResponse = explode()(" ", $this->strResponse);
if (!is_array($arrResponse) || count($arrResponse)<=0)
{
$this->setMessage('STAT command response message is error', 2006);
return false;
}
return array($arrResponse[1], $arrResponse[2]);
}
}
//获取指定邮件得session Id
function getMailSessId($intMailId, $intReturnType=2)
{
if (!$this->getIsConnect() && $this->bolIsLogin)
{
return false;
}
if (!$intMailId = intval($intMailId))
{
$this->setMessage('Mail message id invalid', 1005);
return false;
}
$this->sendCommand("UIDL ". $intMailId);
$this->getLineResponse();
if (!$this->getRestIsSucceed())
{
return false;
}
if ($intReturnType == 1)
{
return $this->strResponse;
}
else
{
$arrResponse = explode(" ", $this->strResponse);
if (!is_array($arrResponse) || count($arrResponse)<=0)
{
$this->setMessage('UIDL command response message is error', 2006);
return false;
}
return array($arrResponse[1], $arrResponse[2]);
}
}
//取得某个邮件的大小
function getMailSize($intMailId, $intReturnType=2)
{
if (!$this->getIsConnect() && $this->bolIsLogin)
{
return false;
}
$this->sendCommand("LIST ".$intMailId);
$this->getLineResponse();
if (!$this->getRestIsSucceed())
{
return false;
}
if ($intReturnType == 1)
{
return $this->strResponse;
}
else
{
$arrMessage = explode(' ', $this->strResponse);
return array($arrMessage[1], $arrMessage[2]);
}
}
//获取邮件基本列表数组
function getMailBaseList($intReturnType=2)
{
if (!$this->getIsConnect() && $this->bolIsLogin)
{
return false;
}
$this->sendCommand("LIST");
$this->getLineResponse();
if (!$this->getRestIsSucceed())
{
return false;
}
return $this->getRespMessage($intReturnType);
}
//获取指定邮件所有信息,intReturnType是返回值类型,1是字符串,2是数组
function getMailMessage($intMailId, $intReturnType=1)
{
if (!$this->getIsConnect() && $this->bolIsLogin)
{
return false;
}
if (!$intMailId = intval($intMailId))
{
$this->setMessage('Mail message id invalid', 1005);
return false;
}
$this->sendCommand("RETR ". $intMailId);
$this->getLineResponse();
if (!$this->getRestIsSucceed())
{
return false;
}
return $this->getRespMessage($intReturnType);
}
//获取某邮件前指定行, $intReturnType 返回值类型,1是字符串,2是数组
function getMailTopMessage($intMailId, $intTopLines=10, $intReturnType=1)
{
if (!$this->getIsConnect() && $this->bolIsLogin)
{
return false;
}
if (!$intMailId=intval($intMailId) || !$intTopLines=int($intTopLines))
{
$this->setMessage('Mail message id or Top lines number invalid', 1005);
return false;
}
$this->sendCommand("TOP ". $intMailId ." ". $intTopLines);
$this->getLineResponse();
if (!$this->getRestIsSucceed())
{
return false;
}
return $this->getRespMessage($intReturnType);
}
//删除邮件
function delMail($intMailId)
{
if (!$this->getIsConnect() && $this->bolIsLogin)
{
return false;
}
if (!$intMailId=intval($intMailId))
{
$this->setMessage('Mail message id invalid', 1005);
return false;
}
$this->sendCommand("DELE ".$intMailId);
$this->getLineResponse();
if (!$this->getRestIsSucceed())
{
return false;
}
return true;
}
//重置被删除得邮件标记为未删除
function resetDeleMail()
{
if (!$this->getIsConnect() && $this->bolIsLogin)
{
return false;
}
$this->sendCommand("RSET");
$this->getLineResponse();
if (!$this->getRestIsSucceed())
{
return false;
}
return true;
}
//---------------
// 调试操作
//---------------
//输出对象信息
function printObject()
{
print_r($this);
exit;
}
//输出错误信息
function printError()
{
echo "[Error Msg] : $strMessage <br>\n";
echo "[Error Num] : $intErrorNum <br>\n";
exit;
}
//输出主机信息
function printHost()
{
echo "[Host] : $this->strHost <br>\n";
echo "[Port] : $this->intPort <br>\n";
echo "[Email] : $this->strEmail <br>\n";
echo "[Passwd] : ******** <br>\n";
exit;
}
//输出连接信息
function printConnect()
{
echo "[Connect] : $this->resHandler <br>\n";
echo "[Request] : $this->strRequest <br>\n";
echo "[Response] : $this->strResponse <br>\n";
exit;
}
}
?>
调用示例:
//测试代码
//例如:$o = SocketPOP3Client('邮箱地址', '密码', 'POP3服务器', 'POP3端口')
/*
set_time_limit(0);
$o = new SocketPOPClient('abc@126.com', '123456', 'pop.126.com', '110');
$o->popLogin();
print_r($o->getMailBaseList());
print_r($o->getMailSum(1));
print_r($o->getMailTopMessage(2, 2, 2));
$o->popLogout();
$o->closeHost();
$o->printObject();
*/
?>
本节内容:
php分页代码
1、前言
分页显示是一种非常常见的浏览和显示大量数据的方法,属于web编程中最常处理的事件之一。
对于web编程的老手来说,编写这种代码实在是和呼吸一样自然,但是对于初学者来说,常常对这个问题摸不着头绪,因此特地撰写此文对这个问题进行详细的讲解,力求让看完这篇文章的朋友在看完以后对于分页显示的原理和实现方法有所了解。
本文适合初学者阅读,所有示例代码均使用php编写。
2、原理
所谓分页显示,也就是将数据库中的结果集人为的分成一段一段的来显示,这里需要两个初始的参数:
每页多少条记录($PageSize)?
当前是第几页($CurrentPageID)?
现在只要再给我一个结果集,我就可以显示某段特定的结果出来。
至于其他的参数,比如:上一页($PReviousPageID)、下一页($NextPageID)、总页数($numPages)等等,都可以根据前边这几个东西得到。
以MySQL数据库为例,如果要从表内截取某段内容,sql语句可以用:select * from table limit offset, rows。
分页规律:
第11至20条记录:select * from table limit 10,10
第21至30条记录:select * from table limit 20,10
……
这一组sql语句其实就是当$PageSize=10的时候取表内每一页数据的sql语句,我们可以总结出这样一个模板:
select * from table limit ($CurrentPageID - 1) * $PageSize, $PageSize
拿这个模板代入对应的值和上边那一组sql语句对照一下看看是不是那么回事。
搞定了最重要的如何获取数据的问题以后,剩下的就仅仅是传递参数,构造合适的sql语句然后使用php从数据库内获取数据并显示了。
3、代码
<?php
// 建立数据库连接
$link = mysql_connect()("localhost", "mysql_user", "mysql_passWord")
or die("Could not connect: " . mysql_error());
// 获取当前页数
if( isset()($_GET['page']) ){
$page = intval( $_GET['page'] );
}
else{
$page = 1;
}
// 每页数量
$PageSize = 10;
// 获取总数据量
$sql = "select count(*) as amount from table";
$result = mysql_query()($sql);
$row = mysql_fetch_row($result);
$amount = $row['amount'];
// 记算总共有多少页
if( $amount ){
if( $amount < $page_size ){ $page_count = 1; } //如果总数据量小于$PageSize,那么只有一页
if( $amount % $page_size ){ //取总数据量除以每页数的余数
$page_count = (int)($amount / $page_size) + 1; //如果有余数,则页数等于总数据量除以每页数的结果取整再加一
}else{
$page_count = $amount / $page_size; //如果没有余数,则页数等于总数据量除以每页数的结果
}
}
else{
$page_count = 0;
}
// 翻页链接
$page_string = '';
if( $page == 1 ){
$page_string .= '第一页|上一页|';
}
else{
$page_string .= '<a href=/blog_article/page/1/gt;第一页/lt;/a/gt;_/lt;a.html href=/blog_article/page/.html'.($page-1).'>上一页</a>|';
}
if( ($page == $page_count) || ($page_count == 0) ){
$page_string .= '下一页|尾页';
}
else{
$page_string .= '<a href=/blog_article/page/.html'.($page+1).'>下一页</a>|<a href=/blog_article/page/.html'.$page_count.'>尾页</a>';
}
// 获取数据,以二维数组格式返回结果
if( $amount ){
$sql = "select * from table order by id desc limit ". ($page-1)*$page_size .", $page_size";
$result = mysql_query($sql);
while ( $row = mysql_fetch_row($result) ){
$rowset[] = $row;
}
}else{
$rowset = array();
}
// 没有包含显示结果的代码,那不在讨论范围,只要用foreach就可以很简单的用得到的二维数组来显示结果
?>
4、OO风格代码
数据库连接使用pear db类进行处理。
<?php
// FileName: Pager.class.php
// 分页类,此类仅用于处理数据结构,不负责处理显示
Class Pager
{
var $PageSize; //每页的数量
var $CurrentPageID; //当前的页数
var $NextPageID; //下一页
var $PreviousPageID; //上一页
var $numPages; //总页数
var $numItems; //总记录数
var $isFirstPage; //是否第一页
var $isLastPage; //是否最后一页
var $sql; //sql查询语句
function Pager($option)
{
global $db;
$this->_setOptions($option);
// 总条数
if ( !isset($this->numItems) )
{
$res = $db->query($this->sql);
$this->numItems = $res->numRows();
}
// 总页数
if ( $this->numItems > 0 )
{
if ( $this->numItems < $this->PageSize ){ $this->numPages = 1; }
if ( $this->numItems % $this->PageSize )
{
$this->numPages= (int)($this->numItems / $this->PageSize) + 1;
}
else
{
$this->numPages = $this->numItems / $this->PageSize;
}
}
else
{
$this->numPages = 0;
}
switch ( $this->CurrentPageID )
{
case $this->numPages == 1:
$this->isFirstPage = true;
$this->isLastPage = true;
break;
case 1:
$this->isFirstPage = true;
$this->isLastPage = false;
break;
case $this->numPages:
$this->isFirstPage = false;
$this->isLastPage = true;
break;
default:
$this->isFirstPage = false;
$this->isLastPage = false;
}
if ( $this->numPages > 1 )
{
if ( !$this->isLastPage ) { $this->NextPageID = $this->CurrentPageID + 1; }
if ( !$this->isFirstPage ) { $this->PreviousPageID = $this->CurrentPageID - 1; }
}
return true;
}
/***
*
* 返回结果集的数据库连接
* 在结果集比较大的时候可以直接使用这个方法获得数据库连接,然后在类之外遍历,这样开销较小
* 如果结果集不是很大,可以直接使用getPageData的方式获取二维数组格式的结果
* getPageData方法也是调用本方法来获取结果的
*
***/
function getDataLink()
{
if ( $this->numItems )
{
global $db;
$PageID = $this->CurrentPageID;
$from = ($PageID - 1)*$this->PageSize;
$count = $this->PageSize;
$link = $db->limitQuery($this->sql, $from, $count); //使用Pear DB::limitQuery方法保证数据库兼容性
return $link;
}
else
{
return false;
}
}
/***
*
* 以二维数组的格式返回结果集
*
***/
function getPageData()
{
if ( $this->numItems )
{
if ( $res = $this->getDataLink() )
{
if ( $res->numRows() )
{
while ( $row = $res->fetchRow() )
{
$result[] = $row;
}
}
else
{
$result = array();
}
return $result;
}
else
{
return false;
}
}
else
{
return false;
}
}
function _setOptions($option)
{
$allow_options = array(
'PageSize',
'CurrentPageID',
'sql',
'numItems'
);
foreach ( $option as $key => $value )
{
if ( in_array($key, $allow_options) && ($value != null) )
{
$this->$key = $value;
}
}
return true;
}
}
?>
调用示例:
<?php
// FileName: test_pager.php
// 省略了使用pear db类建立数据库连接的代码
require "Pager.class.php";
if ( isset($_GET['page']) )
{
$page = (int)$_GET['page'];
}
else
{
$page = 1;
}
$sql = "select * from table order by id";
$pager_option = array(
"sql" => $sql,
"PageSize" => 10,
"CurrentPageID" => $page
);
if ( isset($_GET['numItems']) )
{
$pager_option['numItems'] = (int)$_GET['numItems'];
}
$pager = @new Pager($pager_option);
$data = $pager->getPageData();
if ( $pager->isFirstPage )
{
$turnover = "首页|上一页|";
}
else
{
$turnover = "<a href='/blog_article/page/1/amp;numItems/.html".$pager->numItems."'>首页</a>|<a href='/blog_article/page/.html".$pager->PreviousPageID."&numItems=".$pager->numItems."'>上一页</a>|";
}
if ( $pager->isLastPage )
{
$turnover .= "下一页|尾页";
}
else
{
$turnover .= "<a href='/blog_article/page/.html".$pager->NextPageID."&numItems=".$pager->numItems."'>下一页</a>|<a href='/blog_article/page/.html".$pager->numPages."&numItems=".$pager->numItems."'>尾页</a>";
}
?>
说明两点:
这个类仅仅处理数据,并不负责处理显示,因为我觉得将数据的处理和结果的显示都放到一个类里边实在是有些勉强。
显示的时候情况和要求多变,不如自己根据类给出的结果处理,更好的方法是根据这个Pager类继承一个自己的子类来显示不同的分页,比如显示用户分页列表:
<?php
Class MemberPager extends Pager
{
function showMemberList()
{
global $db;
$data = $this->getPageData();
// 显示结果的代码
// ......
}
}
/// 调用
if ( isset($_GET['page']) )
{
$page = (int)$_GET['page'];
}
else
{
$page = 1;
}
$sql = "select * from members order by id";
$pager_option = array(
"sql" => $sql,
"PageSize" => 10,
"CurrentPageID" => $page
);
if ( isset($_GET['numItems']) )
{
$pager_option['numItems'] = (int)$_GET['numItems'];
}
$pager = @new MemberPager($pager_option);
$pager->showMemberList();
?>
说明:不同数据库的兼容性,在不同的数据库里截获一段结果的写法是不一样的。
mysql: select * from table limit offset, rows
pgsql: select * from table limit m offset n
......
因此,在类里边获取结果时,需要使用pear db类的limitQuery方法。
本节内容:
腾讯QQ微博API接口获取微博内容的实例。
例子:
<?php
/**
* 使用腾讯QQ微博API接口获取微博内容
* by www.
*/
define('HDOM_TYPE_ELEMENT', 1);
define('HDOM_TYPE_COMMENT', 2);
define('HDOM_TYPE_TEXT', 3);
define('HDOM_TYPE_ENDTAG', 4);
define('HDOM_TYPE_ROOT', 5);
define('HDOM_TYPE_UNKNOWN', 6);
define('HDOM_QUOTE_DOUBLE', 0);
define('HDOM_QUOTE_SINGLE', 1);
define('HDOM_QUOTE_NO', 3);
define('HDOM_INFO_BEGIN', 0);
define('HDOM_INFO_END', 1);
define('HDOM_INFO_QUOTE', 2);
define('HDOM_INFO_SPACE', 3);
define('HDOM_INFO_TEXT', 4);
define('HDOM_INFO_INNER', 5);
define('HDOM_INFO_OUTER', 6);
define('HDOM_INFO_ENDSPACE',7);
// helper functions
// ---------------
// get html dom form file
function file_get_html() {
$dom = new simple_html_dom;
$args = func_get_args();
$dom->load(call_user_func_array('file_get_contents', $args), true);
return $dom;
}
// get html dom form string
function str_get_html($str, $lowercase=true) {
$dom = new simple_html_dom;
$dom->load($str, $lowercase);
return $dom;
}
// dump html dom tree
function dump_html_tree($node, $show_attr=true, $deep=0) {
$lead = str_repeat(' ', $deep);
echo $lead.$node->tag;
if ($show_attr && count($node->attr)>0) {
echo '(';
foreach($node->attr as $k=>$v)
echo "[$k]=>\"".$node->$k.'", ';
echo ')';
}
echo "\n";
foreach($node->nodes as $c)
dump_html_tree($c, $show_attr, $deep+1);
}
// get dom form file (dePRecated)
function file_get_dom() {
$dom = new simple_html_dom;
$args = func_get_args();
$dom->load(call_user_func_array('file_get_contents', $args), true);
return $dom;
}
// get dom form string (deprecated)
function str_get_dom($str, $lowercase=true) {
$dom = new simple_html_dom;
$dom->load($str, $lowercase);
return $dom;
}
// simple html dom node
// ---------------
class simple_html_dom_node {
public $nodetype = HDOM_TYPE_TEXT;
public $tag = 'text';
public $attr = array();
public $children = array();
public $nodes = array();
public $parent = null;
public $_ = array();
private $dom = null;
function __construct($dom) {
$this->dom = $dom;
$dom->nodes[] = $this;
}
function __destruct() {
$this->clear();
}
function __toString() {
return $this->outertext();
}
// clean up memory due to php5 circular references memory leak...
function clear() {
$this->dom = null;
$this->nodes = null;
$this->parent = null;
$this->children = null;
}
// dump node's tree
function dump($show_attr=true) {
dump_html_tree($this, $show_attr);
}
// returns the parent of node
function parent() {
return $this->parent;
}
// returns children of node
function children($idx=-1) {
if ($idx===-1) return $this->children;
if (isset()($this->children[$idx])) return $this->children[$idx];
return null;
}
// returns the first child of node
function first_child() {
if (count($this->children)>0) return $this->children[0];
return null;
}
// returns the last child of node
function last_child() {
if (($count=count($this->children))>0) return $this->children[$count-1];
return null;
}
// returns the next sibling of node
function next_sibling() {
if ($this->parent===null) return null;
$idx = 0;
$count = count($this->parent->children);
while ($idx<$count && $this!==$this->parent->children[$idx])
++$idx;
if (++$idx>=$count) return null;
return $this->parent->children[$idx];
}
// returns the previous sibling of node
function prev_sibling() {
if ($this->parent===null) return null;
$idx = 0;
$count = count($this->parent->children);
while ($idx<$count && $this!==$this->parent->children[$idx])
++$idx;
if (--$idx<0) return null;
return $this->parent->children[$idx];
}
// get dom node's inner html
function innertext() {
if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER];
if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
$ret = '';
foreach($this->nodes as $n)
$ret .= $n->outertext();
return $ret;
}
// get dom node's outer text (with tag)
function outertext() {
if ($this->tag==='root') return $this->innertext();
// trigger callback
if ($this->dom->callback!==null)
call_user_func_array($this->dom->callback, array($this));
if (isset($this->_[HDOM_INFO_OUTER])) return $this->_[HDOM_INFO_OUTER];
if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
// render begin tag
$ret = $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]->makeup();
// render inner text
if (isset($this->_[HDOM_INFO_INNER]))
$ret .= $this->_[HDOM_INFO_INNER];
else {
foreach($this->nodes as $n)
$ret .= $n->outertext();
}
// render end tag
if(isset($this->_[HDOM_INFO_END]) && $this->_[HDOM_INFO_END]!=0)
$ret .= '</'.$this->tag.'>';
return $ret;
}
// get dom node's plain text
function text() {
if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER];
switch ($this->nodetype) {
case HDOM_TYPE_TEXT: return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
case HDOM_TYPE_COMMENT: return '';
case HDOM_TYPE_UNKNOWN: return '';
}
if (strcasecmp($this->tag, 'script')===0) return '';
if (strcasecmp($this->tag, 'style')===0) return '';
$ret = '';
foreach($this->nodes as $n)
$ret .= $n->text();
return $ret;
}
function xmltext() {
$ret = $this->innertext();
$ret = str_ireplace('<![CDATA[', '', $ret);
$ret = str_replace()(']]>', '', $ret);
return $ret;
}
// build node's text with tag
function makeup() {
// text, comment, unknown
if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
$ret = '<'.$this->tag;
$i = -1;
foreach($this->attr as $key=>$val) {
++$i;
// skip removed attribute
if ($val===null || $val===false)
continue;
$ret .= $this->_[HDOM_INFO_SPACE][$i][0];
//no value attr: nowrap, checked selected...
if ($val===true)
$ret .= $key;
else {
switch($this->_[HDOM_INFO_QUOTE][$i]) {
case HDOM_QUOTE_DOUBLE: $quote = '"'; break;
case HDOM_QUOTE_SINGLE: $quote = '\''; break;
default: $quote = '';
}
$ret .= $key.$this->_[HDOM_INFO_SPACE][$i][1].'='.$this->_[HDOM_INFO_SPACE][$i][2].$quote.$val.$quote;
}
}
$ret = $this->dom->restore_noise($ret);
return $ret . $this->_[HDOM_INFO_ENDSPACE] . '>';
}
// find elements by CSS selector
function find($selector, $idx=null) {
$selectors = $this->parse_selector($selector);
if (($count=count($selectors))===0) return array();
$found_keys = array();
// find each selector
for ($c=0; $c<$count; ++$c) {
if (($levle=count($selectors[0]))===0) return array();
if (!isset($this->_[HDOM_INFO_BEGIN])) return array();
$head = array($this->_[HDOM_INFO_BEGIN]=>1);
// handle descendant selectors, no recursive!
for ($l=0; $l<$levle; ++$l) {
$ret = array();
foreach($head as $k=>$v) {
$n = ($k===-1) ? $this->dom->root : $this->dom->nodes[$k];
$n->seek($selectors[$c][$l], $ret);
}
$head = $ret;
}
foreach($head as $k=>$v) {
if (!isset($found_keys[$k]))
$found_keys[$k] = 1;
}
}
// sort keys
ksort($found_keys);
$found = array();
foreach($found_keys as $k=>$v)
$found[] = $this->dom->nodes[$k];
// return nth-element or array
if (is_null($idx)) return $found;
else if ($idx<0) $idx = count($found) + $idx;
return (isset($found[$idx])) ? $found[$idx] : null;
}
// seek for given conditions
protected function seek($selector, &$ret) {
list($tag, $key, $val, $exp, $no_key) = $selector;
// xpath index
if ($tag && $key && is_numeric($key)) {
$count = 0;
foreach ($this->children as $c) {
if ($tag==='*' || $tag===$c->tag) {
if (++$count==$key) {
$ret[$c->_[HDOM_INFO_BEGIN]] = 1;
return;
}
}
}
return;
}
$end = (!empty($this->_[HDOM_INFO_END])) ? $this->_[HDOM_INFO_END] : 0;
if ($end==0) {
$parent = $this->parent;
while (!isset($parent->_[HDOM_INFO_END]) && $parent!==null) {
$end -= 1;
$parent = $parent->parent;
}
$end += $parent->_[HDOM_INFO_END];
}
for($i=$this->_[HDOM_INFO_BEGIN]+1; $i<$end; ++$i) {
$node = $this->dom->nodes[$i];
$pass = true;
if ($tag==='*' && !$key) {
if (in_array($node, $this->children, true))
$ret[$i] = 1;
continue;
}
// compare tag
if ($tag && $tag!=$node->tag && $tag!=='*') {$pass=false;}
// compare key
if ($pass && $key) {
if ($no_key) {
if (isset($node->attr[$key])) $pass=false;
}
else if (!isset($node->attr[$key])) $pass=false;
}
// compare value
if ($pass && $key && $val && $val!=='*') {
$check = $this->match($exp, $val, $node->attr[$key]);
// handle multiple class
if (!$check && strcasecmp($key, 'class')===0) {
foreach(explode()(' ',$node->attr[$key]) as $k) {
$check = $this->match($exp, $val, $k);
if ($check) break;
}
}
if (!$check) $pass = false;
}
if ($pass) $ret[$i] = 1;
unset($node);
}
}
protected function match($exp, $pattern, $value) {
switch ($exp) {
case '=':
return ($value===$pattern);
case '!=':
return ($value!==$pattern);
case '^=':
return preg_match("/^".preg_quote($pattern,'/')."/", $value);
case '$=':
return preg_match("/".preg_quote($pattern,'/')."$/", $value);
case '*=':
if ($pattern[0]=='/')
return preg_match($pattern, $value);
return preg_match("/".$pattern."/i", $value);
}
return false;
}
protected function parse_selector($selector_string) {
// pattern of CSS selectors, modified from mootools
$pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is";
preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER);
$selectors = array();
$result = array();
//print_r($matches);
foreach ($matches as $m) {
$m[0] = trim($m[0]);
if ($m[0]==='' || $m[0]==='/' || $m[0]==='//') continue;
// for borwser grnreated xpath
if ($m[1]==='tbody') continue;
list($tag, $key, $val, $exp, $no_key) = array($m[1], null, null, '=', false);
if(!empty($m[2])) {$key='id'; $val=$m[2];}
if(!empty($m[3])) {$key='class'; $val=$m[3];}
if(!empty($m[4])) {$key=$m[4];}
if(!empty($m[5])) {$exp=$m[5];}
if(!empty($m[6])) {$val=$m[6];}
// convert to lowercase
if ($this->dom->lowercase) {$tag=strtolower()($tag); $key=strtolower($key);}
//elements that do NOT have the specified attribute
if (isset($key[0]) && $key[0]==='!') {$key=substr($key, 1); $no_key=true;}
$result[] = array($tag, $key, $val, $exp, $no_key);
if (trim($m[7])===',') {
$selectors[] = $result;
$result = array();
}
}
if (count($result)>0)
$selectors[] = $result;
return $selectors;
}
function __get($name) {
if (isset($this->attr[$name])) return $this->attr[$name];
switch($name) {
case 'outertext': return $this->outertext();
case 'innertext': return $this->innertext();
case 'plaintext': return $this->text();
case 'xmltext': return $this->xmltext();
default: return array_key_exists($name, $this->attr);
}
}
function __set($name, $value) {
switch($name) {
case 'outertext': return $this->_[HDOM_INFO_OUTER] = $value;
case 'innertext':
if (isset($this->_[HDOM_INFO_TEXT])) return $this->_[HDOM_INFO_TEXT] = $value;
return $this->_[HDOM_INFO_INNER] = $value;
}
if (!isset($this->attr[$name])) {
$this->_[HDOM_INFO_SPACE][] = array(' ', '', '');
$this->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE;
}
$this->attr[$name] = $value;
}
function __isset($name) {
switch($name) {
case 'outertext': return true;
case 'innertext': return true;
case 'plaintext': return true;
}
//no value attr: nowrap, checked selected...
return (array_key_exists($name, $this->attr)) ? true : isset($this->attr[$name]);
}
function __unset($name) {
if (isset($this->attr[$name]))
unset($this->attr[$name]);
}
// camel naming conventions
function getAllAttributes() {return $this->attr;}
function getAttribute($name) {return $this->__get($name);}
function setAttribute($name, $value) {$this->__set($name, $value);}
function hasAttribute($name) {return $this->__isset($name);}
function removeAttribute($name) {$this->__set($name, null);}
function getElementById($id) {return $this->find("#$id", 0);}
function getElementsById($id, $idx=null) {return $this->find("#$id", $idx);}
function getElementByTagName($name) {return $this->find($name, 0);}
function getElementsByTagName($name, $idx=null) {return $this->find($name, $idx);}
function parentNode() {return $this->parent();}
function childNodes($idx=-1) {return $this->children($idx);}
function firstChild() {return $this->first_child();}
function lastChild() {return $this->last_child();}
function nextSibling() {return $this->next_sibling();}
function previousSibling() {return $this->prev_sibling();}
}
// simple html dom parser
// -----------------------------------------------------------------------------
class simple_html_dom {
public $root = null;
public $nodes = array();
public $callback = null;
public $lowercase = false;
protected $pos;
protected $doc;
protected $char;
protected $size;
protected $cursor;
protected $parent;
protected $noise = array();
protected $token_blank = " \t\r\n";
protected $token_equal = ' =/>';
protected $token_slash = " />\r\n\t";
protected $token_attr = ' >';
// use isset instead of in_array, performance boost about 30%...
protected $self_closing_tags = array('img'=>1, 'br'=>1, 'input'=>1, 'meta'=>1, 'link'=>1, 'hr'=>1, 'base'=>1, 'embed'=>1, 'spacer'=>1);
protected $block_tags = array('root'=>1, 'body'=>1, 'form'=>1, 'div'=>1, 'span'=>1, 'table'=>1);
protected $optional_closing_tags = array(
'tr'=>array('tr'=>1, 'td'=>1, 'th'=>1),
'th'=>array('th'=>1),
'td'=>array('td'=>1),
'li'=>array('li'=>1),
'dt'=>array('dt'=>1, 'dd'=>1),
'dd'=>array('dd'=>1, 'dt'=>1),
'dl'=>array('dd'=>1, 'dt'=>1),
'p'=>array('p'=>1),
'nobr'=>array('nobr'=>1),
);
function __construct($str=null) {
if ($str) {
if (preg_match("/^http:\/\//i",$str) || is_file($str))
$this->load_file($str);
else
$this->load($str);
}
}
http://www.devdao.com/
function __destruct() {
$this->clear();
}
// load html from string
function load($str, $lowercase=true) {
// prepare
$this->prepare($str, $lowercase);
// strip out comments
$this->remove_noise("'<!--(.*?)-->'is");
// strip out cdata
$this->remove_noise("'<!\[CDATA\[(.*?)\]\]>'is", true);
// strip out <style> tags
$this->remove_noise("'<\s*style[^>]*[^/]>(.*?)<\s*/\s*style\s*>'is");
$this->remove_noise("'<\s*style\s*>(.*?)<\s*/\s*style\s*>'is");
// strip out <script> tags
$this->remove_noise("'<\s*script[^>]*[^/]>(.*?)<\s*/\s*script\s*>'is");
$this->remove_noise("'<\s*script\s*>(.*?)<\s*/\s*script\s*>'is");
// strip out preformatted tags
$this->remove_noise("'<\s*(?:code)[^>]*>(.*?)<\s*/\s*(?:code)\s*>'is");
// strip out server side scripts
$this->remove_noise("'(<\?)(.*?)(\?>)'s", true);
// strip smarty scripts
$this->remove_noise("'(\{\w)(.*?)(\})'s", true);
// parsing
while ($this->parse());
// end
$this->root->_[HDOM_INFO_END] = $this->cursor;
}
// load html from file
function load_file() {
$args = func_get_args();
$this->load(call_user_func_array('file_get_contents', $args), true);
}
// set callback function
function set_callback($function_name) {
$this->callback = $function_name;
}
// remove callback function
function remove_callback() {
$this->callback = null;
}
// save dom as string
function save($filepath='') {
$ret = $this->root->innertext();
if ($filepath!=='') file_put_contents($filepath, $ret);
return $ret;
}
// find dom node by css selector
function find($selector, $idx=null) {
return $this->root->find($selector, $idx);
}
// clean up memory due to php5 circular references memory leak...
function clear() {
foreach($this->nodes as $n) {$n->clear(); $n = null;}
if (isset($this->parent)) {$this->parent->clear(); unset($this->parent);}
if (isset($this->root)) {$this->root->clear(); unset($this->root);}
unset($this->doc);
unset($this->noise);
}
function dump($show_attr=true) {
$this->root->dump($show_attr);
}
// prepare HTML data and init everything
protected function prepare($str, $lowercase=true) {
$this->clear();
$this->doc = $str;
$this->pos = 0;
$this->cursor = 1;
$this->noise = array();
$this->nodes = array();
$this->lowercase = $lowercase;
$this->root = new simple_html_dom_node($this);
$this->root->tag = 'root';
$this->root->_[HDOM_INFO_BEGIN] = -1;
$this->root->nodetype = HDOM_TYPE_ROOT;
$this->parent = $this->root;
// set the length of content
$this->size = strlen($str);
if ($this->size>0) $this->char = $this->doc[0];
}
// parse html content
protected function parse() {
if (($s = $this->copy_until_char('<'))==='')
return $this->read_tag();
// text
$node = new simple_html_dom_node($this);
++$this->cursor;
$node->_[HDOM_INFO_TEXT] = $s;
$this->link_nodes($node, false);
return true;
}
// read tag info
protected function read_tag() {
if ($this->char!=='<') {
$this->root->_[HDOM_INFO_END] = $this->cursor;
return false;
}
$begin_tag_pos = $this->pos;
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
// end tag
if ($this->char==='/') {
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
$this->skip($this->token_blank_t);
$tag = $this->copy_until_char('>');
// skip attributes in end tag
if (($pos = strpos($tag, ' '))!==false)
$tag = substr($tag, 0, $pos);
$parent_lower = strtolower($this->parent->tag);
$tag_lower = strtolower($tag);
if ($parent_lower!==$tag_lower) {
if (isset($this->optional_closing_tags[$parent_lower]) && isset($this->block_tags[$tag_lower])) {
$this->parent->_[HDOM_INFO_END] = 0;
$org_parent = $this->parent;
while (($this->parent->parent) && strtolower($this->parent->tag)!==$tag_lower)
$this->parent = $this->parent->parent;
if (strtolower($this->parent->tag)!==$tag_lower) {
$this->parent = $org_parent; // restore origonal parent
if ($this->parent->parent) $this->parent = $this->parent->parent;
$this->parent->_[HDOM_INFO_END] = $this->cursor;
return $this->as_text_node($tag);
}
}
else if (($this->parent->parent) && isset($this->block_tags[$tag_lower])) {
$this->parent->_[HDOM_INFO_END] = 0;
$org_parent = $this->parent;
while (($this->parent->parent) && strtolower($this->parent->tag)!==$tag_lower)
$this->parent = $this->parent->parent;
if (strtolower($this->parent->tag)!==$tag_lower) {
$this->parent = $org_parent; // restore origonal parent
$this->parent->_[HDOM_INFO_END] = $this->cursor;
return $this->as_text_node($tag);
}
}
else if (($this->parent->parent) && strtolower($this->parent->parent->tag)===$tag_lower) {
$this->parent->_[HDOM_INFO_END] = 0;
$this->parent = $this->parent->parent;
}
else
return $this->as_text_node($tag);
}
$this->parent->_[HDOM_INFO_END] = $this->cursor;
if ($this->parent->parent) $this->parent = $this->parent->parent;
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
return true;
}
$node = new simple_html_dom_node($this);
$node->_[HDOM_INFO_BEGIN] = $this->cursor;
++$this->cursor;
$tag = $this->copy_until($this->token_slash);
// doctype, cdata & comments...
if (isset($tag[0]) && $tag[0]==='!') {
$node->_[HDOM_INFO_TEXT] = '<' . $tag . $this->copy_until_char('>');
if (isset($tag[2]) && $tag[1]==='-' && $tag[2]==='-') {
$node->nodetype = HDOM_TYPE_COMMENT;
$node->tag = 'comment';
} else {
$node->nodetype = HDOM_TYPE_UNKNOWN;
$node->tag = 'unknown';
}
if ($this->char==='>') $node->_[HDOM_INFO_TEXT].='>';
$this->link_nodes($node, true);
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
return true;
}
// text
if ($pos=strpos($tag, '<')!==false) {
$tag = '<' . substr($tag, 0, -1);
$node->_[HDOM_INFO_TEXT] = $tag;
$this->link_nodes($node, false);
$this->char = $this->doc[--$this->pos]; // prev
return true;
}
if (!preg_match("/^[\w-:]+$/", $tag)) {
$node->_[HDOM_INFO_TEXT] = '<' . $tag . $this->copy_until('<>');
if ($this->char==='<') {
$this->link_nodes($node, false);
return true;
}
if ($this->char==='>') $node->_[HDOM_INFO_TEXT].='>';
$this->link_nodes($node, false);
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
return true;
}
// begin tag
$node->nodetype = HDOM_TYPE_ELEMENT;
$tag_lower = strtolower($tag);
$node->tag = ($this->lowercase) ? $tag_lower : $tag;
// handle optional closing tags
if (isset($this->optional_closing_tags[$tag_lower]) ) {
while (isset($this->optional_closing_tags[$tag_lower][strtolower($this->parent->tag)])) {
$this->parent->_[HDOM_INFO_END] = 0;
$this->parent = $this->parent->parent;
}
$node->parent = $this->parent;
}
$guard = 0; // prevent infinity loop
$space = array($this->copy_skip($this->token_blank), '', '');
// attributes
do {
if ($this->char!==null && $space[0]==='') break;
$name = $this->copy_until($this->token_equal);
if($guard===$this->pos) {
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
continue;
}
$guard = $this->pos;
// handle endless '<'
if($this->pos>=$this->size-1 && $this->char!=='>') {
$node->nodetype = HDOM_TYPE_TEXT;
$node->_[HDOM_INFO_END] = 0;
$node->_[HDOM_INFO_TEXT] = '<'.$tag . $space[0] . $name;
$node->tag = 'text';
$this->link_nodes($node, false);
return true;
}
// handle mismatch '<'
if($this->doc[$this->pos-1]=='<') {
$node->nodetype = HDOM_TYPE_TEXT;
$node->tag = 'text';
$node->attr = array();
$node->_[HDOM_INFO_END] = 0;
$node->_[HDOM_INFO_TEXT] = substr($this->doc, $begin_tag_pos, $this->pos-$begin_tag_pos-1);
$this->pos -= 2;
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
$this->link_nodes($node, false);
return true;
}
if ($name!=='/' && $name!=='') {
$space[1] = $this->copy_skip($this->token_blank);
$name = $this->restore_noise($name);
if ($this->lowercase) $name = strtolower($name);
if ($this->char==='=') {
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
$this->parse_attr($node, $name, $space);
}
else {
//no value attr: nowrap, checked selected...
$node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_NO;
$node->attr[$name] = true;
if ($this->char!='>') $this->char = $this->doc[--$this->pos]; // prev
}
$node->_[HDOM_INFO_SPACE][] = $space;
$space = array($this->copy_skip($this->token_blank), '', '');
}
else
break;
} while($this->char!=='>' && $this->char!=='/');
$this->link_nodes($node, true);
$node->_[HDOM_INFO_ENDSPACE] = $space[0];
// check self closing
if ($this->copy_until_char_escape('>')==='/') {
$node->_[HDOM_INFO_ENDSPACE] .= '/';
$node->_[HDOM_INFO_END] = 0;
}
else {
// reset parent
if (!isset($this->self_closing_tags[strtolower($node->tag)])) $this->parent = $node;
}
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
return true;
}
// parse attributes
protected function parse_attr($node, $name, &$space) {
$space[2] = $this->copy_skip($this->token_blank);
switch($this->char) {
case '"':
$node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE;
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
$node->attr[$name] = $this->restore_noise($this->copy_until_char_escape('"'));
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
break;
case '\'':
$node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_SINGLE;
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
$node->attr[$name] = $this->restore_noise($this->copy_until_char_escape('\''));
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
break;
default:
$node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_NO;
$node->attr[$name] = $this->restore_noise($this->copy_until($this->token_attr));
}
}
// link node's parent
protected function link_nodes(&$node, $is_child) {
$node->parent = $this->parent;
$this->parent->nodes[] = $node;
if ($is_child)
$this->parent->children[] = $node;
}
// as a text node
protected function as_text_node($tag) {
$node = new simple_html_dom_node($this);
++$this->cursor;
$node->_[HDOM_INFO_TEXT] = '</' . $tag . '>';
$this->link_nodes($node, false);
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
return true;
}
protected function skip($chars) {
$this->pos += strspn($this->doc, $chars, $this->pos);
$this->char = ($this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
}
protected function copy_skip($chars) {
$pos = $this->pos;
$len = strspn($this->doc, $chars, $pos);
$this->pos += $len;
$this->char = ($this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
if ($len===0) return '';
return substr($this->doc, $pos, $len);
}
protected function copy_until($chars) {
$pos = $this->pos;
$len = strcspn($this->doc, $chars, $pos);
$this->pos += $len;
$this->char = ($this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
return substr($this->doc, $pos, $len);
}
protected function copy_until_char($char) {
if ($this->char===null) return '';
if (($pos = strpos($this->doc, $char, $this->pos))===false) {
$ret = substr($this->doc, $this->pos, $this->size-$this->pos);
$this->char = null;
$this->pos = $this->size;
return $ret;
}
if ($pos===$this->pos) return '';
$pos_old = $this->pos;
$this->char = $this->doc[$pos];
$this->pos = $pos;
return substr($this->doc, $pos_old, $pos-$pos_old);
}
protected function copy_until_char_escape($char) {
if ($this->char===null) return '';
$start = $this->pos;
while(1) {
if (($pos = strpos($this->doc, $char, $start))===false) {
$ret = substr($this->doc, $this->pos, $this->size-$this->pos);
$this->char = null;
$this->pos = $this->size;
return $ret;
}
if ($pos===$this->pos) return '';
if ($this->doc[$pos-1]==='\\') {
$start = $pos+1;
continue;
}
$pos_old = $this->pos;
$this->char = $this->doc[$pos];
$this->pos = $pos;
return substr($this->doc, $pos_old, $pos-$pos_old);
}
}
// remove noise from html content
protected function remove_noise($pattern, $remove_tag=false) {
$count = preg_match_all($pattern, $this->doc, $matches, PREG_SET_ORDER|PREG_OFFSET_CAPTURE);
for ($i=$count-1; $i>-1; --$i) {
$key = '___noise___'.sprintf()('% 3d', count($this->noise)+100);
$idx = ($remove_tag) ? 0 : 1;
$this->noise[$key] = $matches[$i][$idx][0];
$this->doc = substr_replace($this->doc, $key, $matches[$i][$idx][1], strlen($matches[$i][$idx][0]));
}
// reset the length of content
$this->size = strlen($this->doc);
if ($this->size>0) $this->char = $this->doc[0];
}
// restore noise to html content
function restore_noise($text) {
while(($pos=strpos($text, '___noise___'))!==false) {
$key = '___noise___'.$text[$pos+11].$text[$pos+12].$text[$pos+13];
if (isset($this->noise[$key]))
$text = substr($text, 0, $pos).$this->noise[$key].substr($text, $pos+14);
}
return $text;
}
function __toString() {
return $this->root->innertext();
}
function __get($name) {
switch($name) {
case 'outertext': return $this->root->innertext();
case 'innertext': return $this->root->innertext();
case 'plaintext': return $this->root->text();
}
}
// camel naming conventions
function childNodes($idx=-1) {return $this->root->childNodes($idx);}
function firstChild() {return $this->root->first_child();}
function lastChild() {return $this->root->last_child();}
function getElementById($id) {return $this->find("#$id", 0);}
function getElementsById($id, $idx=null) {return $this->find("#$id", $idx);}
function getElementByTagName($name) {return $this->find($name, 0);}
function getElementsByTagName($name, $idx=-1) {return $this->find($name, $idx);}
function loadFile() {$args = func_get_args();$this->load(call_user_func_array('file_get_contents', $args), true);}
}
?>
tqq.php
<?php
/**
Version: 1.11 ($Rev: 175 $)
*/
//缓存时间,单位:秒
$t = 360;
if(!is_file('index.html')||(time()-filemtime('index.html'))>$t){
//微博帐号
$qq = 'kuaisubeian';
//经过腾讯那个md5_3()加密后的密码
$pwd = '624D3274815F2237817A7C62F42DD26A';
$verifyURL = 'http://ptlogin2.qq.com/check?uin=@'.$qq.'&appid=46000101';
$loginURL = 'http://ptlogin2.qq.com/login?';
//获取验证码及第一次cookie
$curl = curl_init($verifyURL);
$cookie_jar = tempnam('.', 'cookie');
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
$verifyCode = curl_exec($curl);
curl_close($curl);
$verifyCode = strtoupper()(substr($verifyCode, 18, 4));
//echo '验证码:'.$verifyCode;
//echo '<hr />';
// echo 'Cookies:'.$cookie_jar;
// echo '<hr />';
//发送登录请求并获取第二次cookie
$loginURL .= 'u=@'.$qq.'&p='.md5($pwd.$verifyCode).'&verifycode='.$verifyCode.'&aid=46000101&u1=http%3A%2F%2Ft.qq.com&h=1&from_ui=1&fp=loginerroralert';
//echo '登录地址:'.$loginURL;
//echo '<hr />';
$curl = curl_init($loginURL);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_jar);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
$loginResult = curl_exec($curl);
curl_close($curl);
//echo '登录验证结果:'.$loginResult;
//echo '<hr />';
http://www.
//获取第三次cookie
$curl = curl_init('http://t.qq.com');
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_jar);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
$loginResult = curl_exec($curl);
curl_close($curl);
//第四次
$curl = curl_init('http://t.qq.com/'.$qq.'/mine');
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_jar);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
$loginResult = curl_exec($curl);
curl_close($curl);
unlink($cookie_jar);
file_put_contents('index.html',$loginResult);
}
include('cnz.php');
$html = file_get_html('index.html');
$talkList = $html->find('#talkList');
$lastTalk = $talkList[0];
$userName = $lastTalk->children(0)->children(1)->find('.userName');
$msgCnt = $lastTalk->children(0)->children(1)->find('.msgCnt');
$pubInfo = $lastTalk->children(0)->children(1)->find('.pubInfo');
$userName = $userName[0]->plaintext;
$result = '';
//大于二则是转播
if(count($msgCnt) < 10){
$pi = $pubInfo[0]->find('.left');
$result = $userName.$msgCnt[0]->plaintext.'<p > <span ></span></p>
<title>QQweiboQQ|www.beiantuan.com</title><meta http-equiv="content-type" content="text/html; charset=UTF-8" /><span >'.$pi[0]->children(0)->plaintext.' '.$pi[0]->children(1)->plaintext.'</span>';
}else{
$pi = $pubInfo[1]->find('.left');
$result = $userName.$msgCnt[0]->plaintext.'['.$msgCnt[1]->plaintext.'] <span >'.$pi[0]->plaintext.'</span>';
}
echo $result;
?>