小編給大家分享一下php如何實現HTML解析器類可用于采集數據,相信大部分人都還不怎么了解,因此分享這篇文章給大家參考一下,希望大家閱讀完這篇文章后大有收獲,下面讓我們一起去了解一下吧!
代碼如下:
<?php
$oldSetting = libxml_use_internal_errors( true );
libxml_clear_errors();
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());
}
/**
* 獲取內容
*/
public function text()
{
if ($this->_nodePath != '' && $this->_xpath != null )
return $this->_xpath->query($this->_nodePath)->item(0)->textContent;
else
return false;
}
/**
* 獲取屬性值
*/
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);以上是“php如何實現HTML解析器類可用于采集數據”這篇文章的所有內容,感謝各位的閱讀!相信大家都有了一定的了解,希望分享的內容對大家有所幫助,如果還想學習更多知識,歡迎關注億速云行業資訊頻道!
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。