直接看代码吧。
<?php
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);
}
}
http://www.devdao.com/
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 true;
}
// text
if ($pos=strpos($tag, '<')!==false) {
$tag = '<' . substr($tag, 0, -1);
$node->_[HDOM_INFO_TEXT] = $tag;
$this->link_nodes($node, false);
$this->char = $this->doc[--$this->pos]; // prev
return true;
}
if (!preg_match("/^[\w-:]+$/", $tag)) {
$node->_[HDOM_INFO_TEXT] = '<' . $tag . $this->copy_until('<>');
if ($this->char==='<') {
$this->link_nodes($node, false);
return true;
}
if ($this->char==='>') $node->_[HDOM_INFO_TEXT].='>';
$this->link_nodes($node, false);
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
return true;
}
// begin tag
$node->nodetype = HDOM_TYPE_ELEMENT;
$tag_lower = strtolower($tag);
$node->tag = ($this->lowercase) ? $tag_lower : $tag;
// handle optional closing tags
if (isset($this->optional_closing_tags[$tag_lower]) ) {
while (isset($this->optional_closing_tags[$tag_lower][strtolower($this->parent->tag)])) {
$this->parent->_[HDOM_INFO_END] = 0;
$this->parent = $this->parent->parent;
}
$node->parent = $this->parent;
}
$guard = 0; // prevent infinity loop
$space = array($this->copy_skip($this->token_blank), '', '');
// attributes
do {
if ($this->char!==null && $space[0]==='') break;
$name = $this->copy_until($this->token_equal);
if($guard===$this->pos) {
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
continue;
}
$guard = $this->pos;
// handle endless '<'
if($this->pos>=$this->size-1 && $this->char!=='>') {
$node->nodetype = HDOM_TYPE_TEXT;
$node->_[HDOM_INFO_END] = 0;
$node->_[HDOM_INFO_TEXT] = '<'.$tag . $space[0] . $name;
$node->tag = 'text';
$this->link_nodes($node, false);
return true;
}
// handle mismatch '<'
if($this->doc[$this->pos-1]=='<') {
$node->nodetype = HDOM_TYPE_TEXT;
$node->tag = 'text';
$node->attr = array();
$node->_[HDOM_INFO_END] = 0;
$node->_[HDOM_INFO_TEXT] = substr($this->doc, $begin_tag_pos, $this->pos-$begin_tag_pos-1);
$this->pos -= 2;
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
$this->link_nodes($node, false);
return true;
}
if ($name!=='/' && $name!=='') {
$space[1] = $this->copy_skip($this->token_blank);
$name = $this->restore_noise($name);
if ($this->lowercase) $name = strtolower($name);
if ($this->char==='=') {
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
$this->parse_attr($node, $name, $space);
}
else {
//no value attr: nowrap, checked selected...
$node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_NO;
$node->attr[$name] = true;
if ($this->char!='>') $this->char = $this->doc[--$this->pos]; // prev
}
$node->_[HDOM_INFO_SPACE][] = $space;
$space = array($this->copy_skip($this->token_blank), '', '');
}
else
break;
} while($this->char!=='>' && $this->char!=='/');
$this->link_nodes($node, true);
$node->_[HDOM_INFO_ENDSPACE] = $space[0];
// check self closing
if ($this->copy_until_char_escape('>')==='/') {
$node->_[HDOM_INFO_ENDSPACE] .= '/';
$node->_[HDOM_INFO_END] = 0;
}
else {
// reset parent
if (!isset($this->self_closing_tags[strtolower($node->tag)])) $this->parent = $node;
}
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
return true;
}
// parse attributes
protected function parse_attr($node, $name, &$space) {
$space[2] = $this->copy_skip($this->token_blank);
switch($this->char) {
case '"':
$node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE;
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
$node->attr[$name] = $this->restore_noise($this->copy_until_char_escape('"'));
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
break;
case '\'':
$node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_SINGLE;
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
$node->attr[$name] = $this->restore_noise($this->copy_until_char_escape('\''));
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
break;
default:
$node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_NO;
$node->attr[$name] = $this->restore_noise($this->copy_until($this->token_attr));
}
}
// link node's parent
protected function link_nodes(&$node, $is_child) {
$node->parent = $this->parent;
$this->parent->nodes[] = $node;
if ($is_child)
$this->parent->children[] = $node;
}
// as a text node
protected function as_text_node($tag) {
$node = new simple_html_dom_node($this);
++$this->cursor;
$node->_[HDOM_INFO_TEXT] = '</' . $tag . '>';
$this->link_nodes($node, false);
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
return true;
}
protected function skip($chars) {
$this->pos += strspn($this->doc, $chars, $this->pos);
$this->char = ($this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
}
protected function copy_skip($chars) {
$pos = $this->pos;
$len = strspn($this->doc, $chars, $pos);
$this->pos += $len;
$this->char = ($this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
if ($len===0) return '';
return substr($this->doc, $pos, $len);
}
protected function copy_until($chars) {
$pos = $this->pos;
$len = strcspn($this->doc, $chars, $pos);
$this->pos += $len;
$this->char = ($this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
return substr($this->doc, $pos, $len);
}
protected function copy_until_char($char) {
if ($this->char===null) return '';
if (($pos = strpos($this->doc, $char, $this->pos))===false) {
$ret = substr($this->doc, $this->pos, $this->size-$this->pos);
$this->char = null;
$this->pos = $this->size;
return $ret;
}
if ($pos===$this->pos) return '';
$pos_old = $this->pos;
$this->char = $this->doc[$pos];
$this->pos = $pos;
return substr($this->doc, $pos_old, $pos-$pos_old);
}
protected function copy_until_char_escape($char) {
if ($this->char===null) return '';
$start = $this->pos;
while(1) {
if (($pos = strpos($this->doc, $char, $start))===false) {
$ret = substr($this->doc, $this->pos, $this->size-$this->pos);
$this->char = null;
$this->pos = $this->size;
return $ret;
}
if ($pos===$this->pos) return '';
if ($this->doc[$pos-1]==='\\') {
$start = $pos+1;
continue;
}
$pos_old = $this->pos;
$this->char = $this->doc[$pos];
$this->pos = $pos;
return substr($this->doc, $pos_old, $pos-$pos_old);
}
}
// remove noise from html content
protected function remove_noise($pattern, $remove_tag=false) {
$count = preg_match_all($pattern, $this->doc, $matches, PREG_SET_ORDER|PREG_OFFSET_CAPTURE);
for ($i=$count-1; $i>-1; --$i) {
$key = '___noise___'.sprintf('% 3d', count($this->noise)+100);
$idx = ($remove_tag) ? 0 : 1;
$this->noise[$key] = $matches[$i][$idx][0];
$this->doc = substr_replace($this->doc, $key, $matches[$i][$idx][1], strlen($matches[$i][$idx][0]));
}
// reset the length of content
$this->size = strlen($this->doc);
if ($this->size>0) $this->char = $this->doc[0];
}
// restore noise to html content
function restore_noise($text) {
while(($pos=strpos($text, '___noise___'))!==false) {
$key = '___noise___'.$text[$pos+11].$text[$pos+12].$text[$pos+13];
if (isset($this->noise[$key]))
$text = substr($text, 0, $pos).$this->noise[$key].substr($text, $pos+14);
}
return $text;
}
function __toString() {
return $this->root->innertext();
}
function __get($name) {
switch($name) {
case 'outertext': return $this->root->innertext();
case 'innertext': return $this->root->innertext();
case 'plaintext': return $this->root->text();
}
}
// camel naming conventions
function childNodes($idx=-1) {return $this->root->childNodes($idx);}
function firstChild() {return $this->root->first_child();}
function lastChild() {return $this->root->last_child();}
function getElementById($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=-1) {return $this->find($name, $idx);}
function loadFile() {$args = func_get_args();$this->load(call_user_func_array('file_get_contents', $args), true);}
}
?>
tqq.php
<?php
/*******************************************************************************
Version: 1.11 ($Rev: 175 $)
Website: http://www.115.co
Author: S.C. Chen <[email protected]>
Acknowledge: Jose Solorzano (http://www.115.co/)
Contributions by:QQ交流群：89097023
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.
*******************************************************************************/
//缓存时间，单位：秒
$t = 360;
if(!is_file('index.html')||(time()-filemtime('index.html'))>$t){
//微博帐号
$qq = 'kuaisubeian';
//经过腾讯那个md5_3()加密后的密码
$pwd = '624D3274815F2237817A7C62F42DD26A';
$verifyURL = 'http://ptlogin2.qq.com/check?uin=@'.$qq.'&appid=46000101';
$loginURL = 'http://ptlogin2.qq.com/login?';
//获取验证码及第一次cookie
$curl = curl_init($verifyURL);
$cookie_jar = tempnam('.', 'cookie');
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
$verifyCode = curl_exec($curl);
curl_close($curl);
$verifyCode = strtoupper(substr($verifyCode, 18, 4));
//echo '验证码：'.$verifyCode;
//echo '<hr />';
// echo 'Cookies：'.$cookie_jar;
// echo '<hr />';
//发送登录请求并获取第二次cookie
$loginURL .= 'u=@'.$qq.'&p='.md5($pwd.$verifyCode).'&verifycode='.$verifyCode.'&aid=46000101&u1=http%3A%2F%2Ft.qq.com&h=1&from_ui=1&fp=loginerroralert';
//echo '登录地址：'.$loginURL;
//echo '<hr />';
$curl = curl_init($loginURL);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_jar);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
$loginResult = curl_exec($curl);
curl_close($curl);
//echo '登录验证结果：'.$loginResult;
//echo '<hr />';
http://www.knowsky.com
//获取第三次cookie
$curl = curl_init('http://t.qq.com');
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_jar);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
$loginResult = curl_exec($curl);
curl_close($curl);
//第四次
$curl = curl_init('http://t.qq.com/'.$qq.'/mine');
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_jar);
curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
$loginResult = curl_exec($curl);
curl_close($curl);
unlink($cookie_jar);
file_put_contents('index.html',$loginResult);
}
include('cnz.php');
$html = file_get_html('index.html');
$talkList = $html->find('#talkList');
$lastTalk = $talkList[0];
$userName = $lastTalk->children(0)->children(1)->find('.userName');
$msgCnt = $lastTalk->children(0)->children(1)->find('.msgCnt');
$pubInfo = $lastTalk->children(0)->children(1)->find('.pubInfo');
$userName = $userName[0]->plaintext;
$result = '';
//大于二则是转播
if(count($msgCnt) < 10){
$pi = $pubInfo[0]->find('.left');
$result = $userName.$msgCnt[0]->plaintext.'<p style="text-align:center;"> <span style="display:none"></span></p>
<title>QQweiboQQ|www.beiantuan.com</title><meta http-equiv="content-type" content="text/html; charset=UTF-8" /><span style="font-style: italic; color: rgb(238, 29, 36);">'.$pi[0]->children(0)->plaintext.' '.$pi[0]->children(1)->plaintext.'</span>';
}else{
$pi = $pubInfo[1]->find('.left');
$result = $userName.$msgCnt[0]->plaintext.'['.$msgCnt[1]->plaintext.'] <span style="font-style: italic; color: rgb(149, 158, 135);">'.$pi[0]->plaintext.'</span>';
}
echo $result;
?>