Tencent QQ Micro-Blog API interface to obtain micro-blog content _php Instance

Just look at the code.

Copy Code code as follows:

<?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 "a" 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 () {
  & nbsp;     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 () {
 & nbsp;      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 () {
    & nbsp;   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. = $this-&gt;_[hdom_info_space][$i][0];


No value attr:nowrap, checked selected ...


if ($val ===true)


$ret. = $key;


else {


Switch ($this-&gt;_[hdom_info_quote][$i]) {


Case hdom_quote_double: $quote = ' "'; Break


Case Hdom_quote_single: $quote = ' \ '; Break


Default: $quote = ';


}


$ret. = $key. $this-&gt;_[hdom_info_space][$i][1]. ' = '. $this-&gt;_[hdom_info_space][$i][2]. $quote. $val. $quote;


}


}


$ret = $this-&gt;dom-&gt;restore_noise ($ret);


Return $ret. $this-&gt;_[hdom_info_endspace]. ' &gt; ';


}

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 &lt; $levle; + + $l) {


$ret = Array ();


foreach ($head as $k =&gt; $v) {


$n = ($k ===-1)? $this-&gt;dom-&gt;root: $this-&gt;dom-&gt;nodes[$k];


$n-&gt;seek ($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 &amp;&amp; $key &amp;&amp; is_numeric ($key)) {


$count = 0;


foreach ($this-&gt;children as $c) {


if ($tag = = = ' * ' | | | $tag = = = $c-&gt;tag) {


if (+ + $count = = $key) {


$ret [$c-&gt;_[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 &amp;&amp; $tag!= $node-&gt;tag &amp;&amp; $tag!== ' * ') {$pass =false;}


Compare key


if ($pass &amp;&amp; $key) {


if ($no _key) {


if (Isset ($node-&gt;attr[$key])) $pass =false;


}


else if (!isset ($node-&gt;attr[$key)) $pass =false;


}


Compare value


if ($pass &amp;&amp; $key &amp;&amp; $val &amp;&amp; $val!== ' * ') {


$check = $this-&gt;match ($exp, $val, $node-&gt;attr[$key]);


Handle Multiple class


if (! $check &amp;&amp; strcasecmp ($key, ' class ') ===0) {


foreach (Explode (', $node-&gt;attr[$key]) as $k) {


$check = $this-&gt;match ($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 does 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-&gt;_[hdom_info_outer] = $value;


Case ' innertext ':


if (Isset ($this-&gt;_[hdom_info_text])) return $this-&gt;_[hdom_info_text] = $value;


return $this-&gt;_[hdom_info_inner] = $value;


}


if (!isset ($this-&gt;attr[$name])) {


$this-&gt;_[hdom_info_space][] = Array (', ', ', ');


$this-&gt;_[hdom_info_quote][] = hdom_quote_double;


}


$this-&gt;attr[$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-&gt;attr;}


function GetAttribute ($name) {return $this-&gt;__get ($name);}


function setattribute ($name, $value) {$this-&gt;__set ($name, $value);


function Hasattribute ($name) {return $this-&gt;__isset ($name);}


function RemoveAttribute ($name) {$this-&gt;__set ($name, null);}


function getElementById ($id) {return $this-&gt;find ("# $id", 0);}


function GetElementsById ($id, $idx =null) {return $this-&gt;find ("# $id", $IDX);}


function Getelementbytagname ($name) {return $this-&gt;find ($name, 0);}


function getElementsByTagName ($name, $idx =null) {return $this-&gt;find ($name, $IDX);


function ParentNode () {return $this-&gt;parent ();}


function ChildNodes ($idx =-1) {return $this-&gt;children ($IDX);}


function FirstChild () {return $this-&gt;first_child ();}


function LastChild () {return $this-&gt;last_child ();}


function nextSibling () {return $this-&gt;next_sibling ();}


function previoussibling () {return $this-&gt;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 = ' =/&gt; ';


protected $token _slash = "/&gt;\r\n\t";


protected $token _attr = ' &gt; ';


Use Isset instead of In_array, performance boost about 30% ...


protected $self _closing_tags = Array (' img ' =&gt;1, ' BR ' =&gt;1, ' input ' =&gt;1, ' meta ' =&gt;1, ' link ' =&gt;1, ' hr ' =&gt;1, ' Base ' =&gt;1, ' embed ' =&gt;1, ' spacer ' =&gt;1);


protected $block _tags = array (' root ' =&gt;1, ' body ' =&gt;1, ' form ' =&gt;1, ' div ' =&gt;1, ' span ' =&gt;1, ' table ' =&gt;1);


protected $optional _closing_tags = Array (


' TR ' =&gt;array (' tr ' =&gt;1, ' TD ' =&gt;1, ' th ' =&gt;1),


' th ' =&gt;array (' th ' =&gt;1),


' TD ' =&gt;array (' TD ' =&gt;1),


' Li ' =&gt;array (' Li ' =&gt;1),


' DT ' =&gt;array (' dt ' =&gt;1, ' DD ' =&gt;1),


' DD ' =&gt;array (' dd ' =&gt;1, ' DT ' =&gt;1),


' DL ' =&gt;array (' dd ' =&gt;1, ' DT ' =&gt;1),


' P ' =&gt;array (' P ' =&gt;1),


' nobr ' =&gt;array (' nobr ' =&gt;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


$this-&gt;prepare ($str, $lowercase);


Strip out comments


$this-&gt;remove_noise ("' &lt;!--(. *?) --&gt; ' is ');


Strip out CDATA


$this-&gt;remove_noise ("' &lt;!\[cdata\[") \]\]&gt; ' is ', true);


Strip out &lt;style&gt; tags


$this-&gt;remove_noise ("' &lt;\s*style[^&gt;]*[^/]&gt;. *?) &lt;\s*/\s*style\s*&gt; ' is ');


$this-&gt;remove_noise ("' &lt;\s*style\s*&gt;. *?) &lt;\s*/\s*style\s*&gt; ' is ');


Strip out &lt;script&gt; tags


$this-&gt;remove_noise ("' &lt;\s*script[^&gt;]*[^/]&gt;. *?) &lt;\s*/\s*script\s*&gt; ' is ');


$this-&gt;remove_noise ("' &lt;\s*script\s*&gt;. *?) &lt;\s*/\s*script\s*&gt; ' is ');


Strip out preformatted tags


$this-&gt;remove_noise ("' &lt;\s* (?: code) [^&gt;]*&gt;" (. *?) &lt;\s*/\s* (?: code) \s*&gt; ' is ');


Strip out server side scripts


$this-&gt;remove_noise ("' (&lt;\?) (.*?) (\?&gt;) ' s ", true);


Strip Smarty Scripts


$this-&gt;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) {
&nb sp;       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-&gt;clear ();


$this-&gt;doc = $str;


$this-&gt;pos = 0;


$this-&gt;cursor = 1;


$this-&gt;noise = Array ();


$this-&gt;nodes = Array ();


$this-&gt;lowercase = $lowercase;


$this-&gt;root = new Simple_html_dom_node ($this);


$this-&gt;root-&gt;tag = ' root ';


$this-&gt;root-&gt;_[hdom_info_begin] =-1;


$this-&gt;root-&gt;nodetype = hdom_type_root;


$this-&gt;parent = $this-&gt;root;


Set the length of content


$this-&gt;size = strlen ($STR);


if ($this-&gt;size&gt;0) $this-&gt;char = $this-&gt;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-&gt;parent-&gt;tag)!== $tag _lower) {


$this-&gt;parent = $org _parent; Restore Origonal Parent


if ($this-&gt;parent-&gt;parent) $this-&gt;parent = $this-&gt;parent-&gt;parent;


$this-&gt;parent-&gt;_[hdom_info_end] = $this-&gt;cursor;


return $this-&gt;as_text_node ($tag);


}


}


else if (($this-&gt;parent-&gt;parent) &amp;&amp; isset ($this-&gt;block_tags[$tag _lower)) {


$this-&gt;parent-&gt;_[hdom_info_end] = 0;


$org _parent = $this-&gt;parent;

while (($this->parent->parent) && strtolower ($this->parent->tag)!== $tag _lower)
$this->parent = $this->parent->parent;

if (Strtolower ($this-&gt;parent-&gt;tag)!== $tag _lower) {


$this-&gt;parent = $org _parent; Restore Origonal Parent


$this-&gt;parent-&gt;_[hdom_info_end] = $this-&gt;cursor;


return $this-&gt;as_text_node ($tag);


}


}


else if (($this-&gt;parent-&gt;parent) &amp;&amp; strtolower ($this-&gt;parent-&gt;parent-&gt;tag) = = = $tag _lower) {


$this-&gt;parent-&gt;_[hdom_info_end] = 0;


$this-&gt;parent = $this-&gt;parent-&gt;parent;


}


Else


return $this-&gt;as_text_node ($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
     & nbsp;  $space = Array ($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 ' &lt; '


if ($this-&gt;pos&gt;= $this-&gt;size-1 &amp;&amp; $this-&gt;char!== ' &gt; ') {


$node-&gt;nodetype = Hdom_type_text;


$node-&gt;_[hdom_info_end] = 0;


$node-&gt;_[hdom_info_text] = ' &lt; '. $tag. $space [0]. $name;


$node-&gt;tag = ' text ';


$this-&gt;link_nodes ($node, false);


return true;


}

Handle mismatch ' &lt; '


if ($this-&gt;doc[$this-&gt;pos-1]== ' &lt; ') {


$node-&gt;nodetype = Hdom_type_text;


$node-&gt;tag = ' text ';


$node-&gt;attr = Array ();


$node-&gt;_[hdom_info_end] = 0;


$node-&gt;_[hdom_info_text] = substr ($this-&gt;doc, $begin _tag_pos, $this-&gt;pos-$begin _tag_pos-1);


$this-&gt;pos-= 2;


$this-&gt;char = (+ + $this-&gt;pos&lt; $this-&gt;size)? $this-&gt;doc[$this-&gt;pos]: null; Next


$this-&gt;link_nodes ($node, false);


return true;


}

if ($name!== '/' &amp;&amp; $name!== ') {


$space [1] = $this-&gt;copy_skip ($this-&gt;token_blank);


$name = $this-&gt;restore_noise ($name);


if ($this-&gt;lowercase) $name = Strtolower ($name);


if ($this-&gt;char=== ' = ') {


$this-&gt;char = (+ + $this-&gt;pos&lt; $this-&gt;size)? $this-&gt;doc[$this-&gt;pos]: null; Next


$this-&gt;parse_attr ($node, $name, $space);


}


else {


No value attr:nowrap, checked selected ...


$node-&gt;_[hdom_info_quote][] = hdom_quote_no;


$node-&gt;attr[$name] = true;


if ($this-&gt;char!= ' &gt; ') $this-&gt;char = $this-&gt;doc[--$this-&gt;pos]; Prev


}


$node-&gt;_[hdom_info_space][] = $space;


$space = Array ($this-&gt;copy_skip ($this-&gt;token_blank), ', ' ";


}


Else


Break


while ($this-&gt;char!== ' &gt; ' &amp;&amp; $this-&gt;char!== '/');

$this->link_nodes ($node, true);
$node->_[hdom_info_endspace] = $space [0];

Check self closing


if ($this-&gt;copy_until_char_escape (' &gt; ') = = = '/') {


$node-&gt;_[hdom_info_endspace]. = '/';


$node-&gt;_[hdom_info_end] = 0;


}


else {


Reset Parent


if (!isset ($this-&gt;self_closing_tags[strtolower ($node-&gt;tag))) $this-&gt;parent = $node;


}


$this-&gt;char = (+ + $this-&gt;pos&lt; $this-&gt;size)? $this-&gt;doc[$this-&gt;pos]: null; Next


return true;


}

Parse attributes


protected function parse_attr ($node, $name, &amp; $space) {


$space [2] = $this-&gt;copy_skip ($this-&gt;token_blank);


Switch ($this-&gt;char) {


Case ' "':


$node-&gt;_[hdom_info_quote][] = hdom_quote_double;


$this-&gt;char = (+ + $this-&gt;pos&lt; $this-&gt;size)? $this-&gt;doc[$this-&gt;pos]: null; Next


$node-&gt;attr[$name] = $this-&gt;restore_noise ($this-&gt;copy_until_char_escape (' "));


$this-&gt;char = (+ + $this-&gt;pos&lt; $this-&gt;size)? $this-&gt;doc[$this-&gt;pos]: null; Next


Break


Case ' \ ':


$node-&gt;_[hdom_info_quote][] = Hdom_quote_single;


$this-&gt;char = (+ + $this-&gt;pos&lt; $this-&gt;size)? $this-&gt;doc[$this-&gt;pos]: null; Next


$node-&gt;attr[$name] = $this-&gt;restore_noise ($this-&gt;copy_until_char_escape (' \ '));


$this-&gt;char = (+ + $this-&gt;pos&lt; $this-&gt;size)? $this-&gt;doc[$this-&gt;pos]: null; Next


Break


Default


$node-&gt;_[hdom_info_quote][] = hdom_quote_no;


$node-&gt;attr[$name] = $this-&gt;restore_noise ($this-&gt;copy_until ($this-&gt;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) {
  & nbsp;     $node = new Simple_html_dom_node ($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

&lt;?php


/*******************************************************************************


version:1.11 ($Rev: 175 $)


Website:http://www.115.co


AUTHOR:S.C Chen &lt;admin@185.cm&gt;


Acknowledge:jose Solorzano (http://www.115.co/)


Contributions BY:QQ Exchange Group: 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.


*******************************************************************************/


Cache time, units: seconds


$t = 360;


if (!is_file (' index.html ') | | (Time ()-filemtime (' index.html ')) &gt; $t) {


Micro Blog Account


$QQ = ' Kuaisubeian ';


After Tencent's Md5_3 () encrypted password


$pwd = ' 624d3274815f2237817a7c62f42dd26a ';


$verifyURL = ' http://ptlogin2.qq.com/check?uin=@ '. $qq. ' &amp;appid=46000101 ';


$loginURL = ' http://ptlogin2.qq.com/login? ';





Get the authentication code and the first 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 ' Verification code: '. $verifyCode;


echo ' &lt;hr/&gt; ';


Echo ' Cookies: '. $cookie _jar;


echo ' &lt;hr/&gt; ';





Send a login request and get a second cookie


$loginURL. = ' u=@ '. $qq. ' &amp;p= '. MD5 ($pwd. $verifyCode). ' &amp;verifycode= '. $verifyCode. ' &amp;aid=46000101&amp;u1=http%3a%2f%2ft.qq.com&amp;h=1&amp;from_ui=1&amp;fp=loginerroralert ';


Echo ' Login address: '. $loginURL;


echo ' &lt;hr/&gt; ';


$curl = Curl_init ($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 ' Login verification Result: '. $loginResult;


echo ' &lt;hr/&gt; ';


Http://www.knowsky.com


Get a third time 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);





four times


$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-&gt;find (' #talkList ');


$lastTalk = $talkList [0];





$userName = $lastTalk-&gt;children (0)-&gt;children (1)-&gt;find ('. UserName ');


$msgCnt = $lastTalk-&gt;children (0)-&gt;children (1)-&gt;find ('. msgcnt ');


$pubInfo = $lastTalk-&gt;children (0)-&gt;children (1)-&gt;find ('. PubInfo ');





$userName = $userName [0]-&gt;plaintext;





$result = ';

More than two are broadcast

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;

?>