解析HTML標籤，並實現快速查找節點，取得節點信息

詳細介紹使用請點選來源碼出處。

/**
 * htmlmap 解析器
 *
 * @category TagParse
 * @package TagParse
 * @author 這個
 * @copyright 2014 * @version 1.0
 * @link http://www.blogkun.com
 * @since 1.0
*/
命名空間 TagParse;

/**
* TagDomRoot
*
* @category TagParse
* @package TagParse
* @author kun
* @copyright 2014 kun; license http://www.php.net/license/3_01.txt PHP 許可證3.01
* @版本1.0
* @link http://www.blogkun.com
* @since 1.0
*/
 class TagDomRoot
{
 public $tag = 'root';
 public $plaintext;
 public $child = array();
 public $level = 0;
 public static $ TagParseError = false;
 protected static $TagSet = array();
 protected static $FoundNode = array();
 public static $ErrorTag = array();

 🎝>*/
 public function initProperty()
 {
 $TagParseError = false;
 $TagSet = array();
 $FoundNode = array(); $ErrorTag = array();
 }

 /**
 * initProperty
 *
 * @access public
 *
 * @return null
*/
 public function __construct($str)
 {
 $
 $ this->_removeNoise($str);
 if ($str === null) {
 self::$TagParseError = true;
 } else {
 $l = strpos($str ,> } else {
 $l = strpos($str , ' if ($l !== false) {
 $this->plaintext = substr($str, 0, $l);
 }
 $res = preg_match_all( '~>(.*?) if ($res !== false && $res >; 0) {
 $this->plaintext .= 內爆($matches[1]);
 }
 $r = strrpos($str, '>');
 if ($ r !== false) {
 $this->plaintext 。 🎜 >
 if ($this->parseTag($str, $tagCollect, $attrCollect, $innerContentCollect) === false) {
 self::$TagParseError = true;
 }
 self::$TagParseError = true;
 }


 foreach ($tagCollect as $index => $tag) {
 $this->child[] = new TagDomNode($tag , $this, $attrCollect[$index], $innerContentCollect[$index], $ this ->level 1);
 }
 }
 }

 /**
 * __construct
 *
 * @param string $str 要解析的標籤字串。
 *
 * @access public
 *
 * @return TagDomRoot
*/
 受保護的函數parseTag($str, array &$taglect, array &$attrCollect, array &$innerContentCollect)
 {
 $selfClosingTags = array('img' => 1, 'br ' => 1, '輸入' => 1, '元' => 1、 '連結'=> 1、'小時'=> 1、'基礎'=> 1、'嵌入'=> 1、'間隔'=> 1);
 $end = -2;
 $close = 0;
 $error = false;
 $tag = '';
 while (true) {
 $l = strpos($str, ' if ($l === false) {//解析結束
 break;
 }
 if (strpos(substr($str, $l, 2), '/' ) !== false) {//多餘的結束標記，丟棄
 $error = true;
 $end = $l strlen( $tag);
 self::$ErrorTag[] = substr( $ str, $l, strpos($str, '>', $l)-$l 1);
 繼續;
 }

 $r = strpos($str, '>' , $l);
 $tag = substr($str, $l 1, $r-$l-1);
 if (!ctype_alpha($tag[0]) || strpos($tag, ' $end = $r 1;
 繼續;
 }
 $tag = preg_replace("~n ~", ' ', $tag);
 $space = strpos($tag, ' ');
 if ($space !== false) {
 $attrCollect[] = substr($tag, $space 1);
 $tag = substr($tag, 0, $space);
 } else {
 $attrCollect[] = '' ;
 }
 $tagCollect[] = $tag;
 if (isset($selfClosingTags[$tag])) {
 $innerContentCollect[] = '';
 $end = $> $innerContentCollect[] = '';
 $end = $ r-strlen($tag)-2;
 $close = $r 1;
 繼續;
 }

 $countOpen = -1;
 $open = strpos($ str, ' $close = strpos($str, ''.$tag.'>', $open);
 if ($close === false) {//告白的開始標記
 $innerContentCollect[] = substr($str, $r 1);
 $error = true;
 self::$ErrorTag[] = '';
 規則;
 }
 $start = $open;
 while ($open
 $close && $open !== false) {
 $countOpen ;
 $open = strpos($str, ' }

 while ($countOpen > 0 && $close ! == false) {
 $open = strpos($str, ' $close = strpos($str, ''.$tag.'>', $close strlen($tag) 3);
 if ($close === false) {
break ;
 }
 $countOpen--;
 while ($open  $open = strpos($str, ' $countOpen ;
 }
 }
 if ($close === false) {//標籤閉合不佈局
 $innerContentCollect[] = substr($str, $r 1);
 $error = true;
 中斷;
 }
 $end = $close;
 $r = strpos($ str, '> ', $start);
 $innerContentCollect[] = substr($str, $r 1, $end - $r - 1);
 }

 return !$錯誤;
 }

 /**
 * _removeNoise
 *
 * @param string &$str 要解析的標籤字串。
 *
 * @access private
 *
 * @return string
*/
 私有函數_removeNoise(&$str)
 {
 $str = preg_replace('~~is', '', $str);
 $str = preg_replace('~~is', ' ', $str);
 $str = preg_replace('~*?>~is', '', $str);
 }

 /**
 * parseSelectors
 *
 * @param string $selectors 使用者的選擇條件。
 * @param array &$selectorsTag 標籤
 * @param array &$selectorsAttr 屬性
 *
 * @access protected
 *
 * @return null *
 * @return null
*/
 protected function parseSelectors ( $selectors, 陣列&$selectorsTag, 陣列&$selectorsAttr)
 {
 preg_match_all('~([wd] )([[wd -="._/ ] ])?~', $selectors, $ matches);
 $selectorsTag = $matches[1];
 foreach ($matches[2] as $key =>; $value) {
 $selectorsAttr[$key] = array();
 if ($value !== '') {
 preg_match_all('~([wd-] )="([wd -._/] )"~', $value, $matches);
 foreach ($matches[1] as $index => $attr) {
 $selectorsAttr[$key][$attr] = $matches[2][$index];
 }
 }
 }
 }

 /**
 * find
 *
 * @param mix $selectors 使用者的選擇條件。
 * @param array $selectorsTag 標籤。
 * @param array $selectorsAttr 屬性。
 *
 * @access public
 *
 * @return array
*/
 public function find($selectors , $selectorsTag = array(), $selectorsAttr = array())
 {
 if ($selectors !== null) {
 $this->parseSelectors($selectors, $selectorsTag, $selectorsAttr );
 }
 var_dump($selectorsTag, $selectorsAttr);exit();
 if (!empty($selectorsTag)) {
 $this->seek($selectorsTag, $selectorsAttr) );
 foreach ($this->child as $key => $node) {
 $node->find(null, $selectorsTag, $selectorsAttr);
 }
 }

 if ($selectors !== null) {
 $res = self::$FoundNode;
 self::$FoundNode = array(); return $res ; } }

 /**
 * findGlobal
 *
 * @param string $selectors 使用者的選擇條件。
 *
 * @access public
 *
 * @return array
*/
 public function findGlobal($selectors)
 {
 $space = strpos($selectors, ' ', strpos($selectors, ']' ));
 if ($space === false) {
 return $this->findOneGlobal($selectors);
 } else {
 $selectorsAttr = array();
 $
 $selectorsAttr = array();
 $ selectorsTag = array();
 $this->findOneGlobal(substr($selectors, 0, $space), false);
 $this->parseSelectors(substr($selectors, $space 1) , $selectorsTag , $selectorsAttr);
 if (!empty(self::$FoundNode) && !empty($selectorsTag)) {
 $nodes = self::$FoundNode;
 self::$ FoundNode = 陣列();
 foreach ($nodes as $key => $node) {
 $node->seek($selectorsTag, $selectorsAttr);
 }
 }


 }

 $res = self::$FoundNode;
 self::$FoundNode = array();

 return $res;
 }

 /**
 * 尋找
 *
 * @param 陣列 $selectorsTag 標籤。
 * @param 陣列 $selectorsAttr 屬性。
 *
 * @access protected
 *
 * @return null
*/
 protected functioneek($selectorsTag, $selectorsAttr)
 {
 foreach ($this->child as $key =>; $node) {
 $isFind = true;
 if ($node->tag === $selectorsTag[0]) {
 foreach ($selectorsAttr[0] as $attrName => $ value) {

 if ( isset($node->attr[$attrName])
 && (preg_match('~.*? '.$價值。 .*?~', $node ->attr[$attrName]) > 0
 || preg_match('~^'.$value.'$~', $node->attr[$attrName]) > 0
 | | preg_match('~^'.$value.' ~', $node->attr[$attrName]) > 0
 || preg_match('~ '.$value.'$~', $node ->attr[$attrName]) > 0)
 ) {
 續;
 } else {
 $isFind = false ;
 中斷;
 }
 }
 } else {
 $isFind = false;
 }
 if ($isFind) {
 if (count($selectorsTag ) ) === 1) {
 self::$ FoundNode[] = $node;
 } else {
 $node->seek(
 array_slice($selectorsTag, 1),
 array_slice($selectorsAttr, 1)
 );
 }
 }
 }
 }

 /***/ $選擇器, $isReturn = true)
 {
 preg_match('~([wd] )([[wd -="._/] ])?~', $selector, $matches);
 $tag = $matches[1];
 $ attr = array();
 if (isset($matches[2])) {
 preg_match_all('~([wd-] )= "( [wd-._/] )"~', $matches[2], $matches);
 foreach ($matches[1] as $key => $value) {
 $attr[$ value] = $matches [2][$key];
 }
 }
 if (isset(self::$TagSet[$tag])) {
 foreach (self::$TagSet [$ tag] as $attrValue => $nodeArray) {
 $isFind = true;
 foreach ($attr as $attrName => $value) {
 if (preg_match('~'.$attrName .' = ".*? '.$value.' .*?"~', $attrValue)
 || preg_match('~'.$attrName.'="'.$value.' .*?" ~' , $attrValue)
 || preg_match('~'.$attrName.'=".*? '.$value.'"~', $attrValue)
 || preg_match('~'.$attrName. '="'.$value.'"~', $attrValue)
 ) {
 繼續;
 } else {
 $isFind = false;
 中斷;
 }
 }
 if ($isFind) {
 foreach ($nodeArray as $key =>; $node) {
 self::$FoundNode[] = $key =>; $node) {
 是 $節點;
 }
 }
 }
 }
 if ($isReturn) {
 $res = self ::$FoundNode;
 self::$FoundNode = array( );

 回傳$res;
 }
 }
}

/**
* TagDomNode
*
* @uses TagDomRoot
*
* @category TagParse
* @package TagParse
* @author kun
* @package TagParse
* @author kun * @copyright 2014 kun
* @license http://www.php.net/license/3_01.txt PHP 許可證3.01
* @version 1.0
* @link http://www. php.net/license/3_01.txt php.net/license/3_01.txt blogkun.com
* @since 1.0
*/
class TagDomNode 擴充 TagDomRoot
{
 public $attr = array();
 public $parent = null;

 /**
 * __construct
 *
 * @param Mixed $tag 標籤。
 * @param Mixed $parent 父節點。
 * @param Mixed $attr 屬性。
 * @param Mixed $innerContent 標記內容。
 * @param 混合 $level 節點層級。
 *
 * @access public
 *
 * @return TagDomNode
*/
 公用函數__construct($tag, $parent, $attr, $innerContent, $level)
 {
 $this->tag = $tag;
 $this->parent = $parent;
 $this->_parseAttr($attr);
 $this->level = $level;

 $l = strpos($ insideContent, '  if ($l !== false) {
 $this->plaintext = substr($innerContent, 0, $l);
 }
 $ res = preg_match_all(' ~ >(.*?) if ($res !== false && $res > 0) {
 $this ->plaintext .= implode($ matches [1]);
 } else {
 $this->plaintext .= $innerContent;
 }
 $r = strrpos($innerContent, '>');
 if ( $ r !== false) {
 $this->plaintext .= substr($innerContent, $r 1);
 }

 $tagCollect = array();
 $attrlect = array();
 $innerContentCollect = array();

 if ($this->parseTag($innerContent, $tagCollect, $attrCollect) , $innerContentCollect) === false) {
 self::$TagParseError = true;
 }

 foreach ($tagCollect as $index =>; $tag) {
 $this->child[] = new TagDomNode($tag, $this, $attrCollect[$index], $innerContentCollect[$index], $this->level 1);
 }

 if (!isset(self::$TagSet[$this->tag])) {
 self::$TagSet[$this->tag] = array();
 }
 if (!isset(self::$TagSet[$this->tag][$attr])) {
 self::$TagSet[$this->tag][$attr] = array();
 }
 self::$TagSet[$this->tag][$attr][] = &$this;
 }

 /* *
 * _parseAttr
 *
 * @param string $str 屬性字串。
 *
 * @access public
 *
 * @return null
*/
 解剖函數_parseAttr($str)
 {
 preg_match_all('~(?[w-] )="(?.*?) "~s' , $str, $matches);
 foreach ($matches['attrName'] as $key => $value) {
 $this->attr[$value] = $matches ['attrValue'][ $ key];
 }
 }
}