无为清净楼资源网 Design By www.qnjia.com
复制代码 代码如下:
<?php
$oldSetting = libxml_use_internal_errors( true );
libxml_clear_errors();
/**
*
* -+-----------------------------------
* |PHP5 Framework - 2011
* |Web Site: www.iblue.cc
* |E-mail: mejinke@gmail.com
* |Date: 2012-10-12
* -+-----------------------------------
*
* @desc HTML解析器
* @author jingke
*/
class XF_HtmlDom
{
private $_xpath = null;
private $_nodePath = '';
public function __construct($xpath = null, $nodePath = '')
{
$this->_xpath = $xpath;
$this->_nodePath = $nodePath;
}
public function loadHtml($url)
{
ini_set('user_agent', 'Mozilla/5.0 (Linux; U; Android 2.1; en-us; Nexus One Build/ERD62) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17 –Nexus');
$content = '';
if(strpos(strtolower($url), 'http')===false)
{
$content = file_get_contents($url);
}
else
{
$ch = curl_init();
$user_agent = "Baiduspider+(+http://www.baidu.com/search/spider.htm)";
$user_agent1='Mozilla/5.0 (Windows NT 5.1; rv:6.0) Gecko/20100101 Firefox/6.0';
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_HEADER, false);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_REFERER, $url);
curl_setopt($ch, CURLOPT_USERAGENT, $user_agent1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION,1);
$content =curl_exec($ch);
curl_close($ch);
}
$html = new DOMDocument();
$html->loadHtml($content);
$this->_xpath = new DOMXPath( $html );
//return $this;
}
public function find($query, $index = null)
{
if($this->_nodePath == '')
$this->_nodePath = '//';
else
$this->_nodePath .= '/';
$nodes = $this->_xpath->query($this->_nodePath.$query);
//echo $nodes->item(0)->getNodePath();exit;
if ($index == null && !is_numeric($index))
{
$tmp = array();
foreach ($nodes as $node)
{
$tmp[] = new XF_HtmlDom($this->_xpath, $node->getNodePath());
}
return $tmp;
}
return new XF_HtmlDom($this->_xpath,$this->_xpath->query($this->_nodePath.$query)->item($index)->getNodePath());
}
/**
* 获取内容
*/
public function text()
{
if ($this->_nodePath != '' && $this->_xpath != null )
return $this->_xpath->query($this->_nodePath)->item(0)->textContent;
else
return false;
}
/**
* 获取属性值
*/
public function getAttribute($name)
{
if ($this->_nodePath != '' && $this->_xpath != null )
return $this->_xpath->query($this->_nodePath)->item(0)->getAttribute($name);
else
return false;
}
public function __get($name)
{
if($name == 'innertext')
return $this->text();
else
return $this->getAttribute($name);
}
}
$xp = new xf_HtmlDom();
$xp->loadHtml('http://www.aizhan.com/siteall/www.opendir.cn/');
$rows = $xp->find("td[@id='baidu']/a", 0)->innertext;
print_r($rows);
<?php
$oldSetting = libxml_use_internal_errors( true );
libxml_clear_errors();
/**
*
* -+-----------------------------------
* |PHP5 Framework - 2011
* |Web Site: www.iblue.cc
* |E-mail: mejinke@gmail.com
* |Date: 2012-10-12
* -+-----------------------------------
*
* @desc HTML解析器
* @author jingke
*/
class XF_HtmlDom
{
private $_xpath = null;
private $_nodePath = '';
public function __construct($xpath = null, $nodePath = '')
{
$this->_xpath = $xpath;
$this->_nodePath = $nodePath;
}
public function loadHtml($url)
{
ini_set('user_agent', 'Mozilla/5.0 (Linux; U; Android 2.1; en-us; Nexus One Build/ERD62) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17 –Nexus');
$content = '';
if(strpos(strtolower($url), 'http')===false)
{
$content = file_get_contents($url);
}
else
{
$ch = curl_init();
$user_agent = "Baiduspider+(+http://www.baidu.com/search/spider.htm)";
$user_agent1='Mozilla/5.0 (Windows NT 5.1; rv:6.0) Gecko/20100101 Firefox/6.0';
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_HEADER, false);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_REFERER, $url);
curl_setopt($ch, CURLOPT_USERAGENT, $user_agent1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION,1);
$content =curl_exec($ch);
curl_close($ch);
}
$html = new DOMDocument();
$html->loadHtml($content);
$this->_xpath = new DOMXPath( $html );
//return $this;
}
public function find($query, $index = null)
{
if($this->_nodePath == '')
$this->_nodePath = '//';
else
$this->_nodePath .= '/';
$nodes = $this->_xpath->query($this->_nodePath.$query);
//echo $nodes->item(0)->getNodePath();exit;
if ($index == null && !is_numeric($index))
{
$tmp = array();
foreach ($nodes as $node)
{
$tmp[] = new XF_HtmlDom($this->_xpath, $node->getNodePath());
}
return $tmp;
}
return new XF_HtmlDom($this->_xpath,$this->_xpath->query($this->_nodePath.$query)->item($index)->getNodePath());
}
/**
* 获取内容
*/
public function text()
{
if ($this->_nodePath != '' && $this->_xpath != null )
return $this->_xpath->query($this->_nodePath)->item(0)->textContent;
else
return false;
}
/**
* 获取属性值
*/
public function getAttribute($name)
{
if ($this->_nodePath != '' && $this->_xpath != null )
return $this->_xpath->query($this->_nodePath)->item(0)->getAttribute($name);
else
return false;
}
public function __get($name)
{
if($name == 'innertext')
return $this->text();
else
return $this->getAttribute($name);
}
}
$xp = new xf_HtmlDom();
$xp->loadHtml('http://www.aizhan.com/siteall/www.opendir.cn/');
$rows = $xp->find("td[@id='baidu']/a", 0)->innertext;
print_r($rows);
标签:
HTML解析器
无为清净楼资源网 Design By www.qnjia.com
广告合作:本站广告合作请联系QQ:858582 申请时备注:广告合作(否则不回)
免责声明:本站文章均来自网站采集或用户投稿,网站不提供任何软件下载或自行开发的软件! 如有用户或公司发现本站内容信息存在侵权行为,请邮件告知! 858582#qq.com
免责声明:本站文章均来自网站采集或用户投稿,网站不提供任何软件下载或自行开发的软件! 如有用户或公司发现本站内容信息存在侵权行为,请邮件告知! 858582#qq.com
无为清净楼资源网 Design By www.qnjia.com
暂无评论...
更新日志
2024年10月02日
2024年10月02日
- 纪钧瀚《钢琴阅读时光 雨中书店聆听轻音乐》[FLAC/分轨][399.62MB]
- 证声音乐图书馆《走向自然 疗心爵士乐》[320K/MP3][87.4MB]
- 证声音乐图书馆《走向自然 疗心爵士乐》[FLAC/分轨][184.94MB]
- 陈慧娴.2018-Priscilla-Ism演唱会3CD(2024环球红馆40复刻系列)【环球】【WAV+CUE】
- 郑秀文.1999-我应该得到(国)【华纳】【WAV+CUE】
- 陈家慧.2011-钢琴酒吧2CD【龙吟唱片】【WAV+CUE】
- 证声音乐图书馆《雨季 蓝调吉他 Rainy Blues》[320K/MP3][45.01MB]
- 证声音乐图书馆《雨季 蓝调吉他 Rainy Blues》[FLAC/分轨][109.13MB]
- 赞多《序章》[320K/MP3][45.54MB]
- 许巍.2004-每一刻都是崭新的【步升大风】【WAV+CUE】
- 群星.2024-四方馆影视原声带【韶愔音乐】【FLAC分轨】
- 陈雷.1997-安锁咧【金圆唱片】【WAV+CUE】
- 关淑怡.2013-MY.FAVORITE.SK.3CD【环球】【WAV+CUE】
- Sweety.2006-花言乔语【丰华】【WAV+CUE】
- 李恕权.2003-回·20年全精选2CD【SONY】【WAV+CUE】