HTMLタグを解析し、ノードを素早く見つけてノード情報を取得します。

詳しい導入と使用方法については、ソースコードをクリックしてください。

/**
 * HTML タグ解析パッケージ
 *
 * @category TagParse
 * @package TagParse
 * @author kun
 * @copyright 2014 kun
 * @license http://www.php.net /license/3_01.txt PHP ライセンス 3.01
 * @version 1.0
 * @link http://www.blogkun.com
 * @since 1.0
*/
namespace TagParse;

/**
* TagDomRoot
*
* @category TagParse
* @package TagParse
* @author kun
* @copyright 2014 kun
* @license http://www.php.net/license/ 3_01.txt PHP ライセンス 3.01
* @バージョン 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
*/
 public function initProperty()
 {
 $TagParseError = false;
 $TagSet = array();
 $FoundNode = array();
 $DumpScriptCode = array( );
 $ErrorTag = array();
 }

 /**
 * __construct
 *
 * @param string $str 解析するタグ文字列
 *
 * @access public
 *
 * @return TagDomRoot
*/
 public function __construct($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);
 }
 }
 }

 /**
 * parseTag
 *
 * @parammixed$strDescription.
 *@parammixed&$tagCollectDescription.
 *@parammixed&$attrCollectDescription.
 *@parammixed&$innerContentCollectDescription.
 *
 * @access protected
 *
 * @return boolean Value.
*/
 保護関数 parseTag($str, array &$tagCollect, array &$attrCollect, array &$innerContentCollect)
 {
 $selfClosingTags = array('img' => 1, 'br' => 1、'input' => 1、'link' => 1、'base' => 1, '埋め込み' => 1、'スペーサー' => 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) {//余った終了タグ、破棄
 $error = true;
 $end = $l+strlen($tag);
 self::$ErrorTag[] = substr($str, $l, strpos($str, '>', $l)-$l+1);
 続き;
 }

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

 $countOpen = -1;
 $open = strpos($str, '<'.$tag, $close);
 $close = strpos($str, ' if ($close === false) {//余分な開始タグ
 $innerContentCollect[] = substr($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) {///标签闭合不配对
 $innerContentCollect[] = substr($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 &$str 解析するタグ文字列
 *
 * @access private
 *
 * @return string
*/
プライベート関数 _removeNoise(&$str)
 {
 $str = preg_replace('~~is', '', $str);
 $str = preg_replace('~~is', '', $str);
 $str = preg_replace('~~is', '', $str);
 }

 /**
 * parseSelectors
 *
 * @param string $selectors ユーザーの選択条件
 * @param 配列 &$selectorsTag タグ
 * @param 配列 &$selectorsAttr 属性
 *
 * @access protected
 *
 * @return null
*/
 protected function parseSelectors($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] = $matches[2][$ /**
 * find
 *
 * @param 混合 $selectors ユーザーの選択条件。
 * @param array $selectorsTag タグ。
 * @param array $selectorsAttr 属性。
 *
 * @access public
 *
 * @return array
*/
 public function find($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->gt;child as $key =>$node) {
 $node->find(null, $selectorsTag, $selectorsAttr) );
 }
 }

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

 return $res;
 }
 }

 /**
 * findGlobal
 *
 * @param string $selectors ユーザーの選択条件
 *
 * @access public
 *
 * @return array
*/
 public function findGlobal($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;
 }

 /**
 * シーク
 *
 * @param array $selectorsTag タグ.
 * @param array $selectorsAttr 属性.
 *
 * @access protected
 *
 * @return null
*/
 protected function seen($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]) > preg_match('~^'.$value.' ~', $ノード->attr[$attrName]) > 0
 || preg_match('~ '.$value.'$~', $node->attr[$attrName]) > ;
 } 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 ユーザーの選択条件。
 * @param bool $isReturn 天気の戻り値。
 *
 * @access public
 *
 * @return array
*/
 public function findOneGlobal($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)
 ) {
 続行;
 } 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 2014 kun
* @license http://www .php.net/license/3_01.txt PHP ライセンス 3.01
* @バージョン 1.0
* @link http://www.blogkun.com
* @since 1.0
*/
class TagDomNode extends TagDomRoot
{
 public $attr = array();
 public $parent = null;

 /**
 * __construct
 *
 * @parammixed$tagタグ.
 *@parammixed$parent親ノード.
 *@parammixed$attr属性.
 *@parammixed$innerContentタグのコンテンツ.
 *@parammixed$levelノードレベル
 *
 * @access public
 *
 * @return TagDomNode
*/
 public function __construct($tag 、$parent、$attr、$innerContent、$level)
 {
 $this->tag = $tag;
 $this->gt;parent = $parent;
 $this->gt;_parseAttr($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 $str 属性 string.
 *
 * @access public
 *
 * @return null
*/
プライベート関数 _parseAttr($str)
 {
 preg_match_all('~(?< attrName>[w-]+)="(?.*?)"~s', $str, $matches);
 foreach ($matches['attrName'] as $key => $value ) {
 $this->attr[$value] = $matches['attrValue'][$key];
 }
 }
}