-
-
/**
- * 使用腾讯QQ微博API接口获取微博内容
- * by bbs.it-home.org
- */
- 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 ($idxparent->children[$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 ($idxparent->children[$idx])
- ++$idx;
- if (--$idx 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(' $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 = '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; $c if (($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 $ret = array();
- foreach($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 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 $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
- $this->remove_noise("''is", true);
- // strip out
复制代码
tqq.php
-
-
/**
- Version: 1.11 ($Rev: 175 $)
- */
- //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:'.$verifyCode;
- //echo '
';
- // echo 'Cookies:'.$cookie_jar;
- // echo '
';
//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 '
';
- $curl = curl_init($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 '
';
- http://bbs.it-home.org
- //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) $pi = $pubInfo[0]->find('.left');
- $result = $userName.$msgCnt[0]->plaintext.'
-
QQweiboQQ|www.beiantuan.com
'.$pi[0]->children(0)->plaintext.' '.$pi[0]->children(1)->plaintext.'';
- }else{
- $pi = $pubInfo[1]->find('.left');
- $result = $userName.$msgCnt[0]->plaintext.'['.$msgCnt[1]->plaintext.'] '.$pi[0]->plaintext.'';
- }
- echo $result;
- ?>
-
复制代码
|