|
<?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]=='/') |
|