diff --git a/application/libraries/simple_html_dom_lib.php b/application/libraries/simple_html_dom_lib.php new file mode 100644 index 00000000..0e0d7192 --- /dev/null +++ b/application/libraries/simple_html_dom_lib.php @@ -0,0 +1,9 @@ +load->library('simple_html_dom_lib'); + } + + public function index() { + $this->load->view('welcome'); + } + + public function optimize() { + $htmlsource = $this->input->post('htmlsource'); + $websitehost = $this->input->post('websitehost'); + if (empty($htmlsource) || empty($websitehost)) { + $this->output->set_status_header(500); + echo 'error:htmlsource or websitehost is empty!'; + return false; + } + //域名后面不能有/ + if (substr($websitehost, -1, 1) == '/') { + $websitehost = substr($websitehost, 0, -1); + } + + $html_object = str_get_html($htmlsource); + if (!empty($html_object)) { + +//提取和下载所有CSS样式，包括链接文件和页面样式 + $link_css_array = array(); + $css_content = ''; + foreach ($html_object->find('link') as $link_css) { + if ($link_css->rel == 'stylesheet' && !empty($link_css->href)) { + $link_css_array[] = $link_css->href; + $link_css->outertext = ''; //删除链接 + } + } + //print_r($link_css_array); + foreach ($link_css_array as $item) { + $css_content.= GET_HTTP($this->format_url($item, $websitehost)); + } + foreach ($html_object->find('style') as $style_css) { + if ($style_css->type == "text/css") { + $css_content .= $style_css->innertext; + } + } + // echo $css_content; + // echo $html_object;die(); + // +//提取和下载所有JS脚本，包括链接文件和页面脚本 + $link_js_array = array(); + $js_content = ''; + foreach ($html_object->find('script') as $link_script) { + if (!empty($link_script->src)) { + $link_js_array[] = $link_script->src; + $link_script->outertext = ''; //删除链接，移动到页底 + } else { + //网页内的js不需要提取 + //$js_content.= $link_script->innertext;//js的内容 + $js_content.= $link_script; + $link_script->outertext = ''; //删除js，移动到页底 + } + } + + foreach ($link_js_array as $item) { + //$js_content.= GET_HTTP($this->format_url($item, $websitehost)); + } + //echo $js_content; + //把网页内容和css提交到purifycss处理 + $optimize_css = GET_HTTP('http://184.172.113.219:33033/', 'html_source=' . urlencode($htmlsource) . '&html_css=' . urlencode($css_content), 'POST'); + if (empty($optimize_css)) { + $this->output->set_status_header(500); + echo 'css精简错误'; + echo ''; + return FALSE; + } + + //把精简的css添加到head后面 + $html_object = str_replace('', '", $html_object); + +//在最后加载原始css文件和js文件 + $lastload_js = ''; + //把js移动到页面底部 + foreach ($link_js_array as $item) { + $lastload_js.=''; + } + $lastload_js.=$js_content; + + $html_object = str_replace('', $lastload_js . '', $html_object); + } + echo $html_object; + } + +//格式化url，保证请求的URL有域名，//更换为对应的域名路径 + function format_url($url, $host = '') { + if (substr($url, 0, 8) == 'https://' || substr($url, 0, 7) == 'http://') { + return urldecode($url); + } + + if (substr($url, 0, 2) == '//') { //https或http + return urldecode(str_replace('//', 'http://', $url)); + } + + return urldecode($host . $url); + } + +} diff --git a/application/third_party/htmlcompressor/views/welcome.php b/application/third_party/htmlcompressor/views/welcome.php new file mode 100644 index 00000000..e18468fd --- /dev/null +++ b/application/third_party/htmlcompressor/views/welcome.php @@ -0,0 +1,22 @@ + + + + + + + + HTML-Compressor + + + +

页面样式精简

+
+

+ + +
+ + + diff --git a/lib/simple_html_dom.php b/lib/simple_html_dom.php new file mode 100644 index 00000000..ce412794 --- /dev/null +++ b/lib/simple_html_dom.php @@ -0,0 +1,1721 @@ +size is the "real" number of bytes the dom was created from. + * but for most purposes, it's a really good estimation. + * Paperg - Added the forceTagsClosed to the dom constructor. Forcing tags closed is great for malformed html, but it CAN lead to parsing errors. + * Allow the user to tell us how much they trust the html. + * Paperg add the text and plaintext to the selectors for the find syntax. plaintext implies text in the innertext of a node. text implies that the tag is a text node. + * This allows for us to find tags based on the text they contain. + * Create find_ancestor_tag to see if a tag is - at any level - inside of another specific tag. + * Paperg: added parse_charset so that we know about the character set of the source document. + * NOTE: If the user's system has a routine called get_last_retrieve_url_contents_content_type availalbe, we will assume it's returning the content-type header from the + * last transfer or curl_exec, and we will parse that and use it in preference to any other method of charset detection. + * + * Found infinite loop in the case of broken html in restore_noise. Rewrote to protect from that. + * PaperG (John Schlick) Added get_display_size for "IMG" tags. + * + * Licensed under The MIT License + * Redistributions of files must retain the above copyright notice. + * + * @author S.C. Chen + * @author John Schlick + * @author Rus Carroll + * @version 1.5 ($Rev: 196 $) + * @package PlaceLocalInclude + * @subpackage simple_html_dom + */ + +/** + * All of the Defines for the classes below. + * @author S.C. Chen + */ +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); +define('DEFAULT_TARGET_CHARSET', 'UTF-8'); +define('DEFAULT_BR_TEXT', "\r\n"); +define('DEFAULT_SPAN_TEXT', " "); +define('MAX_FILE_SIZE', 600000); +// helper functions +// ----------------------------------------------------------------------------- +// get html dom from file +// $maxlen is defined in the code as PHP_STREAM_COPY_ALL which is defined as -1. +function file_get_html($url, $use_include_path = false, $context=null, $offset = -1, $maxLen=-1, $lowercase = true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) +{ + // We DO force the tags to be terminated. + $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText); + // For sourceforge users: uncomment the next line and comment the retreive_url_contents line 2 lines down if it is not already done. + $contents = file_get_contents($url, $use_include_path, $context, $offset); + // Paperg - use our own mechanism for getting the contents as we want to control the timeout. + //$contents = retrieve_url_contents($url); + if (empty($contents) || strlen($contents) > MAX_FILE_SIZE) + { + return false; + } + // The second parameter can force the selectors to all be lowercase. + $dom->load($contents, $lowercase, $stripRN); + return $dom; +} + +// get html dom from string +function str_get_html($str, $lowercase=true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) +{ + $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText); + if (empty($str) || strlen($str) > MAX_FILE_SIZE) + { + $dom->clear(); + return false; + } + $dom->load($str, $lowercase, $stripRN); + return $dom; +} + +// dump html dom tree +function dump_html_tree($node, $show_attr=true, $deep=0) +{ + $node->dump($node); +} + + +/** + * simple html dom node + * PaperG - added ability for "find" routine to lowercase the value of the selector. + * PaperG - added $tag_start to track the start position of the tag in the total byte index + * + * @package PlaceLocalInclude + */ +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; + // The "info" array - see HDOM_INFO_... for what each element contains. + public $_ = array(); + public $tag_start = 0; + 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, $deep=0) + { + $lead = str_repeat(' ', $deep); + + echo $lead.$this->tag; + if ($show_attr && count($this->attr)>0) + { + echo '('; + foreach ($this->attr as $k=>$v) + echo "[$k]=>\"".$this->$k.'", '; + echo ')'; + } + echo "\n"; + + if ($this->nodes) + { + foreach ($this->nodes as $c) + { + $c->dump($show_attr, $deep+1); + } + } + } + + + // Debugging function to dump a single dom node with a bunch of information about it. + function dump_node($echo=true) + { + + $string = $this->tag; + if (count($this->attr)>0) + { + $string .= '('; + foreach ($this->attr as $k=>$v) + { + $string .= "[$k]=>\"".$this->$k.'", '; + } + $string .= ')'; + } + if (count($this->_)>0) + { + $string .= ' $_ ('; + foreach ($this->_ as $k=>$v) + { + if (is_array($v)) + { + $string .= "[$k]=>("; + foreach ($v as $k2=>$v2) + { + $string .= "[$k2]=>\"".$v2.'", '; + } + $string .= ")"; + } else { + $string .= "[$k]=>\"".$v.'", '; + } + } + $string .= ")"; + } + + if (isset($this->text)) + { + $string .= " text: (" . $this->text . ")"; + } + + $string .= " HDOM_INNER_INFO: '"; + if (isset($node->_[HDOM_INFO_INNER])) + { + $string .= $node->_[HDOM_INFO_INNER] . "'"; + } + else + { + $string .= ' NULL '; + } + + $string .= " children: " . count($this->children); + $string .= " nodes: " . count($this->nodes); + $string .= " tag_start: " . $this->tag_start; + $string .= "\n"; + + if ($echo) + { + echo $string; + return; + } + else + { + return $string; + } + } + + // returns the parent of node + // If a node is passed in, it will reset the parent of the current node to that one. + function parent($parent=null) + { + // I am SURE that this doesn't work properly. + // It fails to unset the current node from it's current parents nodes or children list first. + if ($parent !== null) + { + $this->parent = $parent; + $this->parent->nodes[] = $this; + $this->parent->children[] = $this; + } + + return $this->parent; + } + + // verify that node has children + function has_child() + { + return !empty($this->children); + } + + // 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]; + } + + // function to locate a specific ancestor tag in the path to the root. + function find_ancestor_tag($tag) + { + global $debugObject; + if (is_object($debugObject)) { $debugObject->debugLogEntry(1); } + + // Start by including ourselves in the comparison. + $returnDom = $this; + + while (!is_null($returnDom)) + { + if (is_object($debugObject)) { $debugObject->debugLog(2, "Current tag is: " . $returnDom->tag); } + + if ($returnDom->tag == $tag) + { + break; + } + $returnDom = $returnDom->parent; + } + return $returnDom; + } + + // get dom node's inner html + function innertext() + { + if (isset($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() + { + global $debugObject; + if (is_object($debugObject)) + { + $text = ''; + if ($this->tag == 'text') + { + if (!empty($this->text)) + { + $text = " with text: " . $this->text; + } + } + $debugObject->debugLog(1, 'Innertext of tag: ' . $this->tag . $text); + } + + if ($this->tag==='root') return $this->innertext(); + + // trigger callback + if ($this->dom && $this->dom->callback!==null) + { + call_user_func_array($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 + if ($this->dom && $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]) + { + $ret = $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]->makeup(); + } else { + $ret = ""; + } + + // render inner text + if (isset($this->_[HDOM_INFO_INNER])) + { + // If it's a br tag... don't return the HDOM_INNER_INFO that we may or may not have added. + if ($this->tag != "br") + { + $ret .= $this->_[HDOM_INFO_INNER]; + } + } else { + if ($this->nodes) + { + foreach ($this->nodes as $n) + { + $ret .= $this->convert_text($n->outertext()); + } + } + } + + // render end tag + if (isset($this->_[HDOM_INFO_END]) && $this->_[HDOM_INFO_END]!=0) + $ret .= '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 = ''; + // In rare cases, (always node type 1 or HDOM_TYPE_ELEMENT - observed for some span tags, and some p tags) $this->nodes is set to NULL. + // NOTE: This indicates that there is a problem where it's set to NULL without a clear happening. + // WHY is this happening? + if (!is_null($this->nodes)) + { + foreach ($this->nodes as $n) + { + $ret .= $this->convert_text($n->text()); + } + + // If this node is a span... add a space at the end of it so multiple spans don't run into each other. This is plaintext after all. + if ($this->tag == "span") + { + $ret .= $this->dom->default_span_text; + } + + + } + return $ret; + } + + function xmltext() + { + $ret = $this->innertext(); + $ret = str_ireplace('', '', $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 . $this->_[HDOM_INFO_ENDSPACE] . '>'; + } + + // find elements by css selector + //PaperG - added ability for find to lowercase the value of the selector. + function find($selector, $idx=null, $lowercase=false) + { + $selectors = $this->parse_selector($selector); + if (($count=count($selectors))===0) return array(); + $found_keys = array(); + + // find each selector + for ($c=0; $c<$count; ++$c) + { + // The change on the below line was documented on the sourceforge code tracker id 2788009 + // used to be: if (($levle=count($selectors[0]))===0) return array(); + if (($levle=count($selectors[$c]))===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]; + //PaperG - Pass this optional parameter on to the seek function. + $n->seek($selectors[$c][$l], $ret, $lowercase); + } + $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 + // PaperG - added parameter to allow for case insensitive testing of the value of a selector. + protected function seek($selector, &$ret, $lowercase=false) + { + global $debugObject; + if (is_object($debugObject)) { $debugObject->debugLogEntry(1); } + + list($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])) $pass=false; + } else { + if (($key != "plaintext") && !isset($node->attr[$key])) $pass=false; + } + } + // compare value + if ($pass && $key && $val && $val!=='*') { + // If they have told us that this is a "plaintext" search then we want the plaintext of the node - right? + if ($key == "plaintext") { + // $node->plaintext actually returns $node->text(); + $nodeKeyValue = $node->text(); + } else { + // this is a normal search, we want the value of that attribute of the tag. + $nodeKeyValue = $node->attr[$key]; + } + if (is_object($debugObject)) {$debugObject->debugLog(2, "testing node: " . $node->tag . " for attribute: " . $key . $exp . $val . " where nodes value is: " . $nodeKeyValue);} + + //PaperG - If lowercase is set, do a case insensitive test of the value of the selector. + if ($lowercase) { + $check = $this->match($exp, strtolower($val), strtolower($nodeKeyValue)); + } else { + $check = $this->match($exp, $val, $nodeKeyValue); + } + if (is_object($debugObject)) {$debugObject->debugLog(2, "after match: " . ($check ? "true" : "false"));} + + // handle multiple class + if (!$check && strcasecmp($key, 'class')===0) { + foreach (explode(' ',$node->attr[$key]) as $k) { + // Without this, there were cases where leading, trailing, or double spaces lead to our comparing blanks - bad form. + if (!empty($k)) { + if ($lowercase) { + $check = $this->match($exp, strtolower($val), strtolower($k)); + } else { + $check = $this->match($exp, $val, $k); + } + if ($check) break; + } + } + } + if (!$check) $pass = false; + } + if ($pass) $ret[$i] = 1; + unset($node); + } + // It's passed by reference so this is actually what this function returns. + if (is_object($debugObject)) {$debugObject->debugLog(1, "EXIT - ret: ", $ret);} + } + + protected function match($exp, $pattern, $value) { + global $debugObject; + if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} + + switch ($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) { + global $debugObject; + if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} + + // pattern of CSS selectors, modified from mootools + // Paperg: Add the colon to the attrbute, so that it properly finds like google does. + // Note: if you try to look at this attribute, yo MUST use getAttribute since $dom->x:y will fail the php syntax check. +// Notice the \[ starting the attbute? and the @? following? This implies that an attribute can begin with an @ sign that is not captured. +// This implies that an html attribute specifier may start with an @ sign that is NOT captured by the expression. +// farther study is required to determine of this should be documented or removed. +// $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; + $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-:]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; + preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER); + if (is_object($debugObject)) {$debugObject->debugLog(2, "Matches Array: ", $matches);} + + $selectors = array(); + $result = array(); + //print_r($matches); + + foreach ($matches as $m) { + $m[0] = trim($m[0]); + if ($m[0]==='' || $m[0]==='/' || $m[0]==='//') continue; + // for browser generated xpath + if ($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 $this->convert_text($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]); + } + + // PaperG - Function to convert the text from one character set to another if the two sets are not the same. + function convert_text($text) + { + global $debugObject; + if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} + + $converted_text = $text; + + $sourceCharset = ""; + $targetCharset = ""; + + if ($this->dom) + { + $sourceCharset = strtoupper($this->dom->_charset); + $targetCharset = strtoupper($this->dom->_target_charset); + } + if (is_object($debugObject)) {$debugObject->debugLog(3, "source charset: " . $sourceCharset . " target charaset: " . $targetCharset);} + + if (!empty($sourceCharset) && !empty($targetCharset) && (strcasecmp($sourceCharset, $targetCharset) != 0)) + { + // Check if the reported encoding could have been incorrect and the text is actually already UTF-8 + if ((strcasecmp($targetCharset, 'UTF-8') == 0) && ($this->is_utf8($text))) + { + $converted_text = $text; + } + else + { + $converted_text = iconv($sourceCharset, $targetCharset, $text); + } + } + + // Lets make sure that we don't have that silly BOM issue with any of the utf-8 text we output. + if ($targetCharset == 'UTF-8') + { + if (substr($converted_text, 0, 3) == "\xef\xbb\xbf") + { + $converted_text = substr($converted_text, 3); + } + if (substr($converted_text, -3) == "\xef\xbb\xbf") + { + $converted_text = substr($converted_text, 0, -3); + } + } + + return $converted_text; + } + + /** + * Returns true if $string is valid UTF-8 and false otherwise. + * + * @param mixed $str String to be tested + * @return boolean + */ + static function is_utf8($str) + { + $c=0; $b=0; + $bits=0; + $len=strlen($str); + for($i=0; $i<$len; $i++) + { + $c=ord($str[$i]); + if($c > 128) + { + if(($c >= 254)) return false; + elseif($c >= 252) $bits=6; + elseif($c >= 248) $bits=5; + elseif($c >= 240) $bits=4; + elseif($c >= 224) $bits=3; + elseif($c >= 192) $bits=2; + else return false; + if(($i+$bits) > $len) return false; + while($bits > 1) + { + $i++; + $b=ord($str[$i]); + if($b < 128 || $b > 191) return false; + $bits--; + } + } + } + return true; + } + /* + function is_utf8($string) + { + //this is buggy + return (utf8_encode(utf8_decode($string)) == $string); + } + */ + + /** + * Function to try a few tricks to determine the displayed size of an img on the page. + * NOTE: This will ONLY work on an IMG tag. Returns FALSE on all other tag types. + * + * @author John Schlick + * @version April 19 2012 + * @return array an array containing the 'height' and 'width' of the image on the page or -1 if we can't figure it out. + */ + function get_display_size() + { + global $debugObject; + + $width = -1; + $height = -1; + + if ($this->tag !== 'img') + { + return false; + } + + // See if there is aheight or width attribute in the tag itself. + if (isset($this->attr['width'])) + { + $width = $this->attr['width']; + } + + if (isset($this->attr['height'])) + { + $height = $this->attr['height']; + } + + // Now look for an inline style. + if (isset($this->attr['style'])) + { + // Thanks to user gnarf from stackoverflow for this regular expression. + $attributes = array(); + preg_match_all("/([\w-]+)\s*:\s*([^;]+)\s*;?/", $this->attr['style'], $matches, PREG_SET_ORDER); + foreach ($matches as $match) { + $attributes[$match[1]] = $match[2]; + } + + // If there is a width in the style attributes: + if (isset($attributes['width']) && $width == -1) + { + // check that the last two characters are px (pixels) + if (strtolower(substr($attributes['width'], -2)) == 'px') + { + $proposed_width = substr($attributes['width'], 0, -2); + // Now make sure that it's an integer and not something stupid. + if (filter_var($proposed_width, FILTER_VALIDATE_INT)) + { + $width = $proposed_width; + } + } + } + + // If there is a width in the style attributes: + if (isset($attributes['height']) && $height == -1) + { + // check that the last two characters are px (pixels) + if (strtolower(substr($attributes['height'], -2)) == 'px') + { + $proposed_height = substr($attributes['height'], 0, -2); + // Now make sure that it's an integer and not something stupid. + if (filter_var($proposed_height, FILTER_VALIDATE_INT)) + { + $height = $proposed_height; + } + } + } + + } + + // Future enhancement: + // Look in the tag to see if there is a class or id specified that has a height or width attribute to it. + + // Far future enhancement + // Look at all the parent tags of this image to see if they specify a class or id that has an img selector that specifies a height or width + // Note that in this case, the class or id will have the img subselector for it to apply to the image. + + // ridiculously far future development + // If the class or id is specified in a SEPARATE css file thats not on the page, go get it and do what we were just doing for the ones on the page. + + $result = array('height' => $height, + 'width' => $width); + return $result; + } + + // 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();} + function hasChildNodes() {return $this->has_child();} + function nodeName() {return $this->tag;} + function appendChild($node) {$node->parent($this); return $node;} + +} + +/** + * simple html dom parser + * Paperg - in the find routine: allow us to specify that we want case insensitive testing of the value of the selector. + * Paperg - change $size from protected to public so we can easily access it + * Paperg - added ForceTagsClosed in the constructor which tells us whether we trust the html or not. Default is to NOT trust it. + * + * @package PlaceLocalInclude + */ +class simple_html_dom +{ + public $root = null; + public $nodes = array(); + public $callback = null; + public $lowercase = false; + // Used to keep track of how large the text was when we started. + public $original_size; + public $size; + protected $pos; + protected $doc; + protected $char; + 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 = ' >'; + // Note that this is referenced by a child node, and so it needs to be public for that node to see this information. + public $_charset = ''; + public $_target_charset = ''; + protected $default_br_text = ""; + public $default_span_text = ""; + + // 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); + // Known sourceforge issue #2977341 + // B tags that are not closed cause us to return everything to the end of the document. + protected $optional_closing_tags = array( + 'tr'=>array('tr'=>1, 'td'=>1, 'th'=>1), + 'th'=>array('th'=>1), + 'td'=>array('td'=>1), + 'li'=>array('li'=>1), + 'dt'=>array('dt'=>1, 'dd'=>1), + 'dd'=>array('dd'=>1, 'dt'=>1), + 'dl'=>array('dd'=>1, 'dt'=>1), + 'p'=>array('p'=>1), + 'nobr'=>array('nobr'=>1), + 'b'=>array('b'=>1), + 'option'=>array('option'=>1), + ); + + function __construct($str=null, $lowercase=true, $forceTagsClosed=true, $target_charset=DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) + { + if ($str) + { + if (preg_match("/^http:\/\//i",$str) || is_file($str)) + { + $this->load_file($str); + } + else + { + $this->load($str, $lowercase, $stripRN, $defaultBRText, $defaultSpanText); + } + } + // Forcing tags to be closed implies that we don't trust the html, but it can lead to parsing errors if we SHOULD trust the html. + if (!$forceTagsClosed) { + $this->optional_closing_array=array(); + } + $this->_target_charset = $target_charset; + } + + function __destruct() + { + $this->clear(); + } + + // load html from string + function load($str, $lowercase=true, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) + { + global $debugObject; + + // prepare + $this->prepare($str, $lowercase, $stripRN, $defaultBRText, $defaultSpanText); + // strip out comments + $this->remove_noise("''is"); + // strip out cdata + $this->remove_noise("''is", true); + // Per sourceforge http://sourceforge.net/tracker/?func=detail&aid=2949097&group_id=218559&atid=1044037 + // Script tags removal now preceeds style tag removal. + // strip out