--- /dev/null +++ b/myway_api.json.php @@ -1,1 +1,123 @@ +<?php +function cleanString($subject) +{ + $subject = str_replace(" ", " ", $subject); + $subject = str_replace("&", "&", $subject); + $subject = preg_replace('/[^\r\n\t\x20-\x7E\xA0-\xFF]/', '', $subject); + $subject = str_replace(" ", " ", $subject); + return trim($subject); +} +$return = Array(); +/*if (file_exists("mywayresponse.txt")) { + @$fh = fopen("mywayresponse.txt", 'r'); + if ($fh) { + $pageHTML = fread($fh, filesize("mywayresponse.txt")); + fclose($fh); + } +}*/ +//set POST variables +$url = 'https://www.action.act.gov.au/ARTS/use_Funcs.asp'; +$field_mapping = Array( + "card_number" => "SRNO", + "DOBmonth" => "month", + "DOBday" => "day", + "DOByear" => "year", + "secret_answer" => "pwrd", + "button" => "button" +); +foreach (Array( + "card_number", + "DOBday", + "DOBmonth", + "DOByear" +) as $field_name) { + if (isset($_REQUEST[$field_name])) { + $fields[$field_name] = filter_var($_REQUEST[$field_name], FILTER_SANITIZE_NUMBER_INT); + } + else { + $return["error"][] = $field_name. " parameter invalid or unspecified"; + } +} +if (isset($_REQUEST['secret_answer'])) { + $fields['secret_answer'] = filter_var($_REQUEST['secret_answer'], FILTER_SANITIZE_STRING, Array( + FILTER_FLAG_NO_ENCODE_QUOTES, + FILTER_FLAG_STRIP_HIGH, + FILTER_FLAG_STRIP_LOW + )); +} +else { + $return["error"][] = "secret_answer parameter invalid or unspecified"; +} +$fields['button'] = 'Submit'; +$fields_string = ""; +//url-ify the data for the POST +foreach ($fields as $key => $value) { + if (sizeof($value) === 0) $return['error'][] = $key . " parameter invalid or unspecified"; + $fields_string.= $field_mapping[$key] . '=' . $value . '&'; +} +$fields_string = rtrim($fields_string, '&'); +if (!isset($return['error'])) { + //open connection + $ch = curl_init(); + //set the url, number of POST vars, POST data + curl_setopt($ch, CURLOPT_URL, $url); + curl_setopt($ch, CURLOPT_POST, count($fields)); + curl_setopt($ch, CURLOPT_POSTFIELDS, $fields_string); + curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); + curl_setopt($ch, CURLOPT_HEADER, 0); + curl_setopt($ch, CURLOPT_TIMEOUT, 30); + //execute post + $pageHTML = curl_exec($ch); + if (curl_errno($ch)) $return["error"][] = "Network error " . curl_errno($ch) . " " . curl_error($ch) . " " . $url . $fields_string; + //close connection + curl_close($ch); +} +if (!isset($return['error'])) { + include_once ('simple_html_dom.php'); + $page = str_get_html($pageHTML); + $pageAlerts = $page->find(".smartCardAlert"); + if (sizeof($pageAlerts) > 0) { + $return['error'][] = $pageAlerts[0]->plaintext; + } + if (!isset($return['error'])) { + $tableNum = 0; + $tableName = Array( + 1 => "myway_carddetails", + 2 => "myway_transactions" + ); + foreach ($page->find("table") as $table) { + $tableNum++; + $tableColumns = Array(); + $tableColumnNum = 0; + foreach ($table->find("th") as $th) { + $tableColumns[$tableColumnNum] = cleanString($th->plaintext); + $tableColumnNum++; + } + $tableRowNum = 0; + foreach ($table->find("tr") as $tr) { + $tableColumnNum = 0; + foreach ($tr->find("td") as $td) { + $return[$tableName[$tableNum]][$tableRowNum][$tableColumns[$tableColumnNum]] = cleanString($td->plaintext); + $tableColumnNum++; + } + $tableRowNum++; + } + } + } +} +if (sizeof($return) == 0) { +$return['error'][] = "No data extracted from MyWay website - API may be out of date"; +print $pageHTML; +} +header('Content-Type: text/javascript; charset=utf8'); +// header('Access-Control-Allow-Origin: http://bus.lambdacomplex.org/'); +header('Access-Control-Max-Age: 3628800'); +header('Access-Control-Allow-Methods: GET, POST, PUT, DELETE'); +if (isset($_GET['callback'])) { + $json = '(' . json_encode($return) . ');'; //must wrap in parens and end with semicolon + print_r($_GET['callback'] . $json); //callback is prepended for json-p + +} +else echo json_encode($return); +?>
--- /dev/null +++ b/simple_html_dom.php @@ -1,1 +1,975 @@ - +<?php +/******************************************************************************* +Version: 1.11 ($Rev: 175 $) +Website: http://sourceforge.net/projects/simplehtmldom/ +Author: S.C. Chen <me578022@gmail.com> +Acknowledge: Jose Solorzano (https://sourceforge.net/projects/php-html/) +Contributions by: + Yousuke Kumakura (Attribute filters) + Vadim Voituk (Negative indexes supports of "find" method) + Antcs (Constructor with automatically load contents either text or file/url) +Licensed under The MIT License +Redistributions of files must retain the above copyright notice. +*******************************************************************************/ + +define('HDOM_TYPE_ELEMENT', 1); +define('HDOM_TYPE_COMMENT', 2); +define('HDOM_TYPE_TEXT', 3); +define('HDOM_TYPE_ENDTAG', 4); +define('HDOM_TYPE_ROOT', 5); +define('HDOM_TYPE_UNKNOWN', 6); +define('HDOM_QUOTE_DOUBLE', 0); +define('HDOM_QUOTE_SINGLE', 1); +define('HDOM_QUOTE_NO', 3); +define('HDOM_INFO_BEGIN', 0); +define('HDOM_INFO_END', 1); +define('HDOM_INFO_QUOTE', 2); +define('HDOM_INFO_SPACE', 3); +define('HDOM_INFO_TEXT', 4); +define('HDOM_INFO_INNER', 5); +define('HDOM_INFO_OUTER', 6); +define('HDOM_INFO_ENDSPACE',7); + +// helper functions +// ----------------------------------------------------------------------------- +// get html dom form file +function file_get_html() { + $dom = new simple_html_dom; + $args = func_get_args(); + $dom->load(call_user_func_array('file_get_contents', $args), true); + return $dom; +} + +// get html dom form string +function str_get_html($str, $lowercase=true) { + $dom = new simple_html_dom; + $dom->load($str, $lowercase); + return $dom; +} + +// dump html dom tree +function dump_html_tree($node, $show_attr=true, $deep=0) { + $lead = str_repeat(' ', $deep); + echo $lead.$node->tag; + if ($show_attr && count($node->attr)>0) { + echo '('; + foreach($node->attr as $k=>$v) + echo "[$k]=>\"".$node->$k.'", '; + echo ')'; + } + echo "\n"; + + foreach($node->nodes as $c) + dump_html_tree($c, $show_attr, $deep+1); +} + +// get dom form file (deprecated) +function file_get_dom() { + $dom = new simple_html_dom; + $args = func_get_args(); + $dom->load(call_user_func_array('file_get_contents', $args), true); + return $dom; +} + +// get dom form string (deprecated) +function str_get_dom($str, $lowercase=true) { + $dom = new simple_html_dom; + $dom->load($str, $lowercase); + return $dom; +} + +// simple html dom node +// ----------------------------------------------------------------------------- +class simple_html_dom_node { + public $nodetype = HDOM_TYPE_TEXT; + public $tag = 'text'; + public $attr = array(); + public $children = array(); + public $nodes = array(); + public $parent = null; + public $_ = array(); + private $dom = null; + + function __construct($dom) { + $this->dom = $dom; + $dom->nodes[] = $this; + } + + function __destruct() { + $this->clear(); + } + + function __toString() { + return $this->outertext(); + } + + // clean up memory due to php5 circular references memory leak... + function clear() { + $this->dom = null; + $this->nodes = null; + $this->parent = null; + $this->children = null; + } + + // dump node's tree + function dump($show_attr=true) { + dump_html_tree($this, $show_attr); + } + + // returns the parent of node + function parent() { + return $this->parent; + } + + // returns children of node + function children($idx=-1) { + if ($idx===-1) return $this->children; + if (isset($this->children[$idx])) return $this->children[$idx]; + return null; + } + + // returns the first child of node + function first_child() { + if (count($this->children)>0) return $this->children[0]; + return null; + } + + // returns the last child of node + function last_child() { + if (($count=count($this->children))>0) return $this->children[$count-1]; + return null; + } + + // returns the next sibling of node + function next_sibling() { + if ($this->parent===null) return null; + $idx = 0; + $count = count($this->parent->children); + while ($idx<$count && $this!==$this->parent->children[$idx]) + ++$idx; + if (++$idx>=$count) return null; + return $this->parent->children[$idx]; + } + + // returns the previous sibling of node + function prev_sibling() { + if ($this->parent===null) return null; + $idx = 0; + $count = count($this->parent->children); + while ($idx<$count && $this!==$this->parent->children[$idx]) + ++$idx; + if (--$idx<0) return null; + return $this->parent->children[$idx]; + } + + // get dom node's inner html + function innertext() { + if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER]; + if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + + $ret = ''; + foreach($this->nodes as $n) + $ret .= $n->outertext(); + return $ret; + } + + // get dom node's outer text (with tag) + function outertext() { + if ($this->tag==='root') return $this->innertext(); + + // trigger callback + if ($this->dom->callback!==null) + call_user_func_array($this->dom->callback, array($this)); + + if (isset($this->_[HDOM_INFO_OUTER])) return $this->_[HDOM_INFO_OUTER]; + if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + + // render begin tag + $ret = $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]->makeup(); + + // render inner text + if (isset($this->_[HDOM_INFO_INNER])) + $ret .= $this->_[HDOM_INFO_INNER]; + else { + foreach($this->nodes as $n) + $ret .= $n->outertext(); + } + + // render end tag + if(isset($this->_[HDOM_INFO_END]) && $this->_[HDOM_INFO_END]!=0) + $ret .= '</'.$this->tag.'>'; + return $ret; + } + + // get dom node's plain text + function text() { + if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER]; + switch ($this->nodetype) { + case HDOM_TYPE_TEXT: return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + case HDOM_TYPE_COMMENT: return ''; + case HDOM_TYPE_UNKNOWN: return ''; + } + if (strcasecmp($this->tag, 'script')===0) return ''; + if (strcasecmp($this->tag, 'style')===0) return ''; + + $ret = ''; + foreach($this->nodes as $n) + $ret .= $n->text(); + return $ret; + } + + function xmltext() { + $ret = $this->innertext(); + $ret = str_ireplace('<![CDATA[', '', $ret); + $ret = str_replace(']]>', '', $ret); + return $ret; + } + + // build node's text with tag + function makeup() { + // text, comment, unknown + if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + + $ret = '<'.$this->tag; + $i = -1; + + foreach($this->attr as $key=>$val) { + ++$i; + + // skip removed attribute + if ($val===null || $val===false) + continue; + + $ret .= $this->_[HDOM_INFO_SPACE][$i][0]; + //no value attr: nowrap, checked selected... + if ($val===true) + $ret .= $key; + else { + switch($this->_[HDOM_INFO_QUOTE][$i]) { + case HDOM_QUOTE_DOUBLE: $quote = '"'; break; + case HDOM_QUOTE_SINGLE: $quote = '\''; break; + default: $quote = ''; + } + $ret .= $key.$this->_[HDOM_INFO_SPACE][$i][1].'='.$this->_[HDOM_INFO_SPACE][$i][2].$quote.$val.$quote; + } + } + $ret = $this->dom->restore_noise($ret); + return $ret . $this->_[HDOM_INFO_ENDSPACE] . '>'; + } + + // find elements by css selector + function find($selector, $idx=null) { + $selectors = $this->parse_selector($selector); + if (($count=count($selectors))===0) return array(); + $found_keys = array(); + + // find each selector + for ($c=0; $c<$count; ++$c) { + if (($levle=count($selectors[0]))===0) return array(); + if (!isset($this->_[HDOM_INFO_BEGIN])) return array(); + + $head = array($this->_[HDOM_INFO_BEGIN]=>1); + + // handle descendant selectors, no recursive! + for ($l=0; $l<$levle; ++$l) { + $ret = array(); + foreach($head as $k=>$v) { + $n = ($k===-1) ? $this->dom->root : $this->dom->nodes[$k]; + $n->seek($selectors[$c][$l], $ret); + } + $head = $ret; + } + + foreach($head as $k=>$v) { + if (!isset($found_keys[$k])) + $found_keys[$k] = 1; + } + } + + // sort keys + ksort($found_keys); + + $found = array(); + foreach($found_keys as $k=>$v) + $found[] = $this->dom->nodes[$k]; + + // return nth-element or array + if (is_null($idx)) return $found; + else if ($idx<0) $idx = count($found) + $idx; + return (isset($found[$idx])) ? $found[$idx] : null; + } + + // seek for given conditions + protected function seek($selector, &$ret) { + list($tag, $key, $val, $exp, $no_key) = $selector; + + // xpath index + if ($tag && $key && is_numeric($key)) { + $count = 0; + foreach ($this->children as $c) { + if ($tag==='*' || $tag===$c->tag) { + if (++$count==$key) { + $ret[$c->_[HDOM_INFO_BEGIN]] = 1; + return; + } + } + } + return; + } + + $end = (!empty($this->_[HDOM_INFO_END])) ? $this->_[HDOM_INFO_END] : 0; + if ($end==0) { + $parent = $this->parent; + while (!isset($parent->_[HDOM_INFO_END]) && $parent!==null) { + $end -= 1; + $parent = $parent->parent; + } + $end += $parent->_[HDOM_INFO_END]; + } + + for($i=$this->_[HDOM_INFO_BEGIN]+1; $i<$end; ++$i) { + $node = $this->dom->nodes[$i]; + $pass = true; + + if ($tag==='*' && !$key) { + if (in_array($node, $this->children, true)) + $ret[$i] = 1; + continue; + } + + // compare tag + if ($tag && $tag!=$node->tag && $tag!=='*') {$pass=false;} + // compare key + if ($pass && $key) { + if ($no_key) { + if (isset($node->attr[$key])) $pass=false; + } + else if (!isset($node->attr[$key])) $pass=false; + } + // compare value + if ($pass && $key && $val && $val!=='*') { + $check = $this->match($exp, $val, $node->attr[$key]); + // handle multiple class + if (!$check && strcasecmp($key, 'class')===0) { + foreach(explode(' ',$node->attr[$key]) as $k) { + $check = $this->match($exp, $val, $k); + if ($check) break; + } + } + if (!$check) $pass = false; + } + if ($pass) $ret[$i] = 1; + unset($node); + } + } + + protected function match($exp, $pattern, $value) { + switch ($exp) { + case '=': + return ($value===$pattern); + case '!=': + return ($value!==$pattern); + case '^=': + return preg_match("/^".preg_quote($pattern,'/')."/", $value); + case '$=': + return preg_match("/".preg_quote($pattern,'/')."$/", $value); + case '*=': + if ($pattern[0]=='/') + return preg_match($pattern, $value); + return preg_match("/".$pattern."/i", $value); + } + return false; + } + + protected function parse_selector($selector_string) { + // pattern of CSS selectors, modified from mootools + $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; + preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER); + $selectors = array(); + $result = array(); + //print_r($matches); + + foreach ($matches as $m) { + $m[0] = trim($m[0]); + if ($m[0]==='' || $m[0]==='/' || $m[0]==='//') continue; + // for borwser grnreated xpath + if ($m[1]==='tbody') continue; + + list($tag, $key, $val, $exp, $no_key) = array($m[1], null, null, '=', false); + if(!empty($m[2])) {$key='id'; $val=$m[2];} + if(!empty($m[3])) {$key='class'; $val=$m[3];} + if(!empty($m[4])) {$key=$m[4];} + if(!empty($m[5])) {$exp=$m[5];} + if(!empty($m[6])) {$val=$m[6];} + + // convert to lowercase + if ($this->dom->lowercase) {$tag=strtolower($tag); $key=strtolower($key);} + //elements that do NOT have the specified attribute + if (isset($key[0]) && $key[0]==='!') {$key=substr($key, 1); $no_key=true;} + + $result[] = array($tag, $key, $val, $exp, $no_key); + if (trim($m[7])===',') { + $selectors[] = $result; + $result = array(); + } + } + if (count($result)>0) + $selectors[] = $result; + return $selectors; + } + + function __get($name) { + if (isset($this->attr[$name])) return $this->attr[$name]; + switch($name) { + case 'outertext': return $this->outertext(); + case 'innertext': return $this->innertext(); + case 'plaintext': return $this->text(); + case 'xmltext': return $this->xmltext(); + default: return array_key_exists($name, $this->attr); + } + } + + function __set($name, $value) { + switch($name) { + case 'outertext': return $this->_[HDOM_INFO_OUTER] = $value; + case 'innertext': + if (isset($this->_[HDOM_INFO_TEXT])) return $this->_[HDOM_INFO_TEXT] = $value; + return $this->_[HDOM_INFO_INNER] = $value; + } + if (!isset($this->attr[$name])) { + $this->_[HDOM_INFO_SPACE][] = array(' ', '', ''); + $this->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE; + } + $this->attr[$name] = $value; + } + + function __isset($name) { + switch($name) { + case 'outertext': return true; + case 'innertext': return true; + case 'plaintext': return true; + } + //no value attr: nowrap, checked selected... + return (array_key_exists($name, $this->attr)) ? true : isset($this->attr[$name]); + } + + function __unset($name) { + if (isset($this->attr[$name])) + unset($this->attr[$name]); + } + + // camel naming conventions + function getAllAttributes() {return $this->attr;} + function getAttribute($name) {return $this->__get($name);} + function setAttribute($name, $value) {$this->__set($name, $value);} + function hasAttribute($name) {return $this->__isset($name);} + function removeAttribute($name) {$this->__set($name, null);} + function getElementById($id) {return $this->find("#$id", 0);} + function getElementsById($id, $idx=null) {return $this->find("#$id", $idx);} + function getElementByTagName($name) {return $this->find($name, 0);} + function getElementsByTagName($name, $idx=null) {return $this->find($name, $idx);} + function parentNode() {return $this->parent();} + function childNodes($idx=-1) {return $this->children($idx);} + function firstChild() {return $this->first_child();} + function lastChild() {return $this->last_child();} + function nextSibling() {return $this->next_sibling();} + function previousSibling() {return $this->prev_sibling();} +} + +// simple html dom parser +// ----------------------------------------------------------------------------- +class simple_html_dom { + public $root = null; + public $nodes = array(); + public $callback = null; + public $lowercase = false; + protected $pos; + protected $doc; + protected $char; + protected $size; + protected $cursor; + protected $parent; + protected $noise = array(); + protected $token_blank = " \t\r\n"; + protected $token_equal = ' =/>'; + protected $token_slash = " />\r\n\t"; + protected $token_attr = ' >'; + // use isset instead of in_array, performance boost about 30%... + protected $self_closing_tags = array('img'=>1, 'br'=>1, 'input'=>1, 'meta'=>1, 'link'=>1, 'hr'=>1, 'base'=>1, 'embed'=>1, 'spacer'=>1); + protected $block_tags = array('root'=>1, 'body'=>1, 'form'=>1, 'div'=>1, 'span'=>1, 'table'=>1); + protected $optional_closing_tags = array( + 'tr'=>array('tr'=>1, 'td'=>1, 'th'=>1), + 'th'=>array('th'=>1), + 'td'=>array('td'=>1), + 'li'=>array('li'=>1), + 'dt'=>array('dt'=>1, 'dd'=>1), + 'dd'=>array('dd'=>1, 'dt'=>1), + 'dl'=>array('dd'=>1, 'dt'=>1), + 'p'=>array('p'=>1), + 'nobr'=>array('nobr'=>1), + ); + + function __construct($str=null) { + if ($str) { + if (preg_match("/^http:\/\//i",$str) || is_file($str)) + $this->load_file($str); + else + $this->load($str); + } + } + + function __destruct() { + $this->clear(); + } + + // load html from string + function load($str, $lowercase=true) { + // prepare + $this->prepare($str, $lowercase); + // strip out comments + $this->remove_noise("'<!--(.*?)-->'is"); + // strip out cdata + $this->remove_noise("'<!\[CDATA\[(.*?)\]\]>'is", true); + // strip out <style> tags + $this->remove_noise("'<\s*style[^>]*[^/]>(.*?)<\s*/\s*style\s*>'is"); + $this->remove_noise("'<\s*style\s*>(.*?)<\s*/\s*style\s*>'is"); + // strip out <script> tags + $this->remove_noise("'<\s*script[^>]*[^/]>(.*?)<\s*/\s*script\s*>'is"); + $this->remove_noise("'<\s*script\s*>(.*?)<\s*/\s*script\s*>'is"); + // strip out preformatted tags + $this->remove_noise("'<\s*(?:code)[^>]*>(.*?)<\s*/\s*(?:code)\s*>'is"); + // strip out server side scripts + $this->remove_noise("'(<\?)(.*?)(\?>)'s", true); + // strip smarty scripts + $this->remove_noise("'(\{\w)(.*?)(\})'s", true); + + // parsing + while ($this->parse()); + // end + $this->root->_[HDOM_INFO_END] = $this->cursor; + } + + // load html from file + function load_file() { + $args = func_get_args(); + $this->load(call_user_func_array('file_get_contents', $args), true); + } + + // set callback function + function set_callback($function_name) { + $this->callback = $function_name; + } + + // remove callback function + function remove_callback() { + $this->callback = null; + } + + // save dom as string + function save($filepath='') { + $ret = $this->root->innertext(); + if ($filepath!=='') file_put_contents($filepath, $ret); + return $ret; + } + + // find dom node by css selector + function find($selector, $idx=null) { + return $this->root->find($selector, $idx); + } + + // clean up memory due to php5 circular references memory leak... + function clear() { + foreach($this->nodes as $n) {$n->clear(); $n = null;} + if (isset($this->parent)) {$this->parent->clear(); unset($this->parent);} + if (isset($this->root)) {$this->root->clear(); unset($this->root);} + unset($this->doc); + unset($this->noise); + } + + function dump($show_attr=true) { + $this->root->dump($show_attr); + } + + // prepare HTML data and init everything + protected function prepare($str, $lowercase=true) { + $this->clear(); + $this->doc = $str; + $this->pos = 0; + $this->cursor = 1; + $this->noise = array(); + $this->nodes = array(); + $this->lowercase = $lowercase; + $this->root = new simple_html_dom_node($this); + $this->root->tag = 'root'; + $this->root->_[HDOM_INFO_BEGIN] = -1; + $this->root->nodetype = HDOM_TYPE_ROOT; + $this->parent = $this->root; + // set the length of content + $this->size = strlen($str); + if ($this->size>0) $this->char = $this->doc[0]; + } + + // parse html content + protected function parse() { + if (($s = $this->copy_until_char('<'))==='') + return $this->read_tag(); + + // text + $node = new simple_html_dom_node($this); + ++$this->cursor; + $node->_[HDOM_INFO_TEXT] = $s; + $this->link_nodes($node, false); + return true; + } + + // read tag info + protected function read_tag() { + if ($this->char!=='<') { + $this->root->_[HDOM_INFO_END] = $this->cursor; + return false; + } + $begin_tag_pos = $this->pos; + $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next + + // end tag + if ($this->char==='/') { + $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next + $this->skip($this->token_blank_t); + $tag = $this->copy_until_char('>'); + + // skip attributes in end tag + if (($pos = strpos($tag, ' '))!==false) + $tag = substr($tag, 0, $pos); + + $parent_lower = strtolower($this->parent->tag); + $tag_lower = strtolower($tag); + + if ($parent_lower!==$tag_lower) { + if (isset($this->optional_closing_tags[$parent_lower]) && isset($this->block_tags[$tag_lower])) { + $this->parent->_[HDOM_INFO_END] = 0; + $org_parent = $this->parent; + + while (($this->parent->parent) && strtolower($this->parent->tag)!==$tag_lower) + $this->parent = $this->parent->parent; + + if (strtolower($this->parent->tag)!==$tag_lower) { + $this->parent = $org_parent; // restore origonal parent + if ($this->parent->parent) $this->parent = $this->parent->parent; + $this->parent->_[HDOM_INFO_END] = $this->cursor; + return $this->as_text_node($tag); + } + } + else if (($this->parent->parent) && isset($this->block_tags[$tag_lower])) { + $this->parent->_[HDOM_INFO_END] = 0; + $org_parent = $this->parent; + + while (($this->parent->parent) && strtolower($this->parent->tag)!==$tag_lower) + $this->parent = $this->parent->parent; + + if (strtolower($this->parent->tag)!==$tag_lower) { + $this->parent = $org_parent; // restore origonal parent + $this->parent->_[HDOM_INFO_END] = $this->cursor; + return $this->as_text_node($tag); + } + } + else if (($this->parent->parent) && strtolower($this->parent->parent->tag)===$tag_lower) { + $this->parent->_[HDOM_INFO_END] = 0; + $this->parent = $this->parent->parent; + } + else + return $this->as_text_node($tag); + } + + $this->parent->_[HDOM_INFO_END] = $this->cursor; + if ($this->parent->parent) $this->parent = $this->parent->parent; + + $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next + return true; + } + + $node = new simple_html_dom_node($this); + $node->_[HDOM_INFO_BEGIN] = $this->cursor; + ++$this->cursor; + $tag = $this->copy_until($this->token_slash); + + // doctype, cdata & comments... + if (isset($tag[0]) && $tag[0]==='!') { + $node->_[HDOM_INFO_TEXT] = '<' . $tag . $this->copy_until_char('>'); + + if (isset($tag[2]) && $tag[1]==='-' && $tag[2]==='-') { + $node->nodetype = HDOM_TYPE_COMMENT; + $node->tag = 'comment'; + } else { + $node->nodetype = HDOM_TYPE_UNKNOWN; + $node->tag = 'unknown'; + } + + if ($this->char==='>') $node->_[HDOM_INFO_TEXT].='>'; + $this->link_nodes($node, true); + $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next + return tru