HTML 태그를 구문 분석하고, 빠르게 노드를 찾고, 노드 정보를 얻습니다.

자세한 소개와 사용법을 보시려면 소스코드를 클릭해주세요.

/**
 * htmlmap 파서
 *
 * @category TagParse
 * @package TagParse
 * @author this
 * @copyright 2014 this * @version 1.0
 * @link http://www.blogkun.com
 * @ 1.0
 이후*/
네임스페이스 TagParse;

/**
* TagDomRoot
*
* @category TagParse
* @package TagParse
* @author kun
* @copyright 2014 kun
* @license http://www.php.net/license/3_01.txt PHP 라이센스 3.01
* @version 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();

 /**
 * initProperty
 *
 * @access public
 *
 * @return null
*/
 공용 함수 initProperty()
 {
 $TagParseError = false;
 $TagSet = array();
 $FoundNode = array();
 $DumpScriptCode = array();
 $ErrorTag = array();
 }

 /**
 * __construct
 *
 * @param string $str 구문 분석할 태그 문자열.
 *
 * @access public
 *
 * @return TagDomRoot
*/
 공개 함수 __construct($str)
 {
 $ this->_removeNoise($str);
 if ($str === null) {
 self::$TagParseError = true;
 } else {
 $l = strpos($str , '<');
 if ($l !== false) {
 $this->plaintext = substr($str, 0, $l);
 }
 $res = preg_match_all('~>(.*?)<~s', $str, $matches);
 if ($res !== false && $res > 0) {
 $this->plaintext .= implode($matches[1]);
 }
 $r = strrpos($str, '>');
 if ($ r !== false) {
 $this->plaintext .= substr($str, $r 1);
 }

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

 if ($this->parseTag($str, $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);
 }
 }
 }

 /**
 * parsTag
 *
 * @param 혼합 $str 설명.
 * @param 혼합 &$tagCollect 설명.
 * @param 혼합 &$attrCollect 설명.
 * @param 혼합 &$innerContentCollect 설명.
 *
 * @access protected
 *
 * @return 부울 값.
*/
 보호된 함수 parseTag($str, 배열 &$tagCollect, 배열 &$attrCollect, 배열 &$innerContentCollect)
 {
 $selfClosingTags = array('img' => 1, 'br ' => 1, '입력' => 1, '메타' => 1, '링크' => 1, '시간' => 1, '베이스' => 1, '삽입' => 1, '스페이서' => 1);
 $end = -2;
 $close = 0;
 $error = false;
 $tag = '';
 while(true) {
 $l = strpos($str, '<', $end strlen($tag) 2);
 if ($l === false) {//parse end
 break;
 }
 if (strpos(substr($str, $l, 2), '/') !== false) {//잉여 닫는 태그, 버리기
 $error = true;
 $end = $l strlen( $tag);
 self::$ErrorTag[] = substr($str, $l, strpos($str, '>', $l)-$l 1);
 계속;
 }

 $r = strpos($str, '>', $l);
 $tag = substr($str, $l 1, $r-$l-1);
 if (!ctype_alpha($tag[0]) || strpos($tag, '<') !== false) {
 $end = $r 1;
 계속;
 }
 $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 = $ r-strlen($tag)-2;
 $close = $r 1;
 계속;
 }

 $countOpen = -1;
 $open = strpos($ str, '<'.$tag, $close);
 $close = strpos($str, '', $open);
 if ($close === false) {//여분 여는 태그
 $innerContentCollect[] = substr($str, $r 1);
 $error = true;
 self::$ErrorTag[] = '< ;'.$tag.'>';
 break;
 }
 $start = $open;
 while ($open < $close && $open !== false) {
 $countOpen ;
 $open = strpos($str, '<'.$tag, $open strlen($tag));
 }

 while ($countOpen > 0 && $close !== false) {
 $open = strpos($str, '<'.$tag, $close strlen($tag) 3);
 $close = strpos($str, '', $close strlen($tag) 3);
 if ($close === false) {
 break;
 }
 $countOpen--;
 while ($open < $close && $open !== false) {
 $open = strpos($str, '<' .$tag, $open strlen($tag) 3);
 $countOpen ;
 }
 }
 if ($close === false) {//标签闭합불配对
 $innerContentCollect[] = substr($str, $r 1);
 $error = true;
 break;
 }
 $end = $close;
 $r = strpos($ str, '>', $start);
 $innerContentCollect[] = substr($str, $r 1, $end - $r - 1);
 }

 return !$ error;
 }

 /**
 * _removeNoise
 *
 * @param string &$str 구문 분석할 태그 문자열.
 *
 * @access private
 *
 * @return string
*/
 비공개 함수 _removeNoise(&$str)
 {
 $str = preg_replace('~~is', '', $str);
 $str = preg_replace('~~is', ' ', $str);
 $str = preg_replace('~~is', '', $str);
 }

 /**
 * parseSelectors
 *
 * @param string $selectors 사용자 선택 조건
 * @param array &$selectorsTag 태그
 * @param array &$selectorsAttr 속성
 *
 * @액세스 보호됨
 *
 * @return null
*/
 보호 함수 parseSelectors($selectors, array &$selectorsTag, array &$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 혼합 $selectors 사용자 선택 조건.
 * @param array $selectorsTag 태그.
 * @param array $selectorsAttr 속성.
 *
 * @access public
 *
 * @return 배열
*/
 공개 함수 find($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 $selectors 사용자 선택 조건
 *
 * @access public
 *
 * @return 배열
*/
 공개 함수 findGlobal($selectors)
 {
 $space = strpos($selectors, ' ', strpos($selectors, ']' ));
 if ($space === false) {
 return $this->findOneGlobal($selectors);
 } else {
 $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 = array();
 foreach ($nodes as $key => $node) {
 $node->seek($selectorsTag, $selectorsAttr);
 }
 }


 }

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

 return $res;
 }

 /**
 * 탐색
 *
 * @param 배열 $selectorsTag 태그.
 * @param 배열 $selectorsAttr 속성.
 *
 * @access protected
 *
 * @return null
*/
 보호된 함수 탐색($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('~.*? '.$value.' .*?~', $node ->attr[$attrName]) > 0
 || preg_match('~^'.$value.'$~', $node->attr[$attrName]) > 0
 | | preg_match('~^'.$value.' ~', $node->attr[$attrName]) > 0
 || preg_match('~ '.$value.'$~', $node ->attr[$attrName]) > 0)
 ) {
 계속;
 } else {
 $isFind = false;
 break;
 }
 }
 } else {
 $isFind = false;
 }
 if ($isFind) {
 if (count($selectorsTag) === 1) {
 self::$ FoundNode[] = $node;
 } else {
 $node->seek(
 array_slice($selectorsTag, 1),
 array_slice($selectorsAttr, 1)
 );
 }
 }
 }
 }

 /**
 * findOneGlobal
 *
 * @param string $selector 사용자의 선택 조건.
 * @param bool $isReturn 날씨 반환 값.
 *
 * @access public
 *
 * @return 배열
*/
 공개 함수 findOneGlobal($selector, $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)
 ) {
 계속;
 } else {
 $isFind = false;
 break;
 }
 }
 if ($isFind) {
 foreach ($nodeArray as $key => $node) {
 self::$FoundNode[] = $node;
 }
 }
 }
 }
 if ($isReturn) {
 $res = self ::$FoundNode;
 self::$FoundNode = array();

 return $res;
 }
 }
}

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

 /**
 * __construct
 *
 * @param 혼합 $tag 태그.
 * @param 혼합 $parent 상위 노드.
 * @param 혼합 $attr 속성.
 * @param 혼합 $innerContent 태그 콘텐츠.
 * @param 혼합 $level 노드 수준.
 *
 * @access public
 *
 * @return TagDomNode
*/
 공개 함수 __construct($tag, $parent, $attr, $innerContent, $level)
 {
 $this->tag = $tag;
 $this->parent = $parent;
 $this->_parseAttr($attr);
 $this->level = $level;

 $l = strpos($ innerContent, '<');
 if ($l !== false) {
 $this->plaintext = substr($innerContent, 0, $l);
 }
 $ res = preg_match_all('~>(.*?)<~s', $innerContent, $matches);
 if ($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();
 $attrCollect = 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 $str 속성 문자열.
 *
 * @access public
 *
 * @return null
*/
 비공개 함수 _parseAttr($str)
 {
 preg_match_all('~(?[w-] )="(?.*?) "~s', $str, $matches);
 foreach ($matches['attrName'] as $key => $value) {
 $this->attr[$value] = $matches ['attrValue'][$key];
 }
 }
}