-
-
/**
- * 使用騰訊QQ微博API介面取得微博內容
- * by bbs.it-home.org
- */
- define('HDOM_TYPE_ELEMENT', 1);
- define('HDOM_TYPE_ELEMENT', 1);
- define('HDOM_TYPE_ELEMENT', 1);
- define('HDOM_TYPE_ELEMENT', 1);
- Define('HDOM_TYPE_COMMENT', 2);
- define('HDOM_TYPE_TEXT', 3);
- define('HDOM_TYPE_ENDTAG', 4);
- define('HDOM_TYPE_ENDTA', 5)RO; 'HDOM_TYPE_UNKNOWN', 6);
- define('HDOM_QUOTE_DOUBLE', 0);
- define('HDOM_QUOTE_SINGLE', 1);
- define('HDOM_QUOTE_NO', . ', 0);
- define('HDOM_INFO_END', 1);
- define('HDOM_INFO_QUOTE', 2);
- define('HDOM_INFO_SPACE', 3);
- define(DOMOM_IN 4);
- define('HDOM_INFO_INNER', 5);
- define('HDOM_INFO_OUTER', 6);
- define('HDOM_INFO_ENDSPACE',7);
- //輔助函數
- / ---------------
- //取得html dom 表單檔案
- 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 $dom;
- }
- //取得html dom表單字串
- function str_get_html($str, $lowercase=true) {
- $dom = new simple_html_dom;
- $dom->load($str, $lowercase);
- return $dom;
- }
- // 轉儲html dom 樹
- function dump_html_tree($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);
- }
- //取得dom表單檔案(已棄用)
- 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 $dom;
- }
- //取得dom 形式字串(已棄用)
- function str_get_dom($str, $lowercase=true) {
- $dom = new simple_html_dom;
- $dom->load($str, $lowercase);
- return $dom;
- }
- //簡單html dom 節點
- // ------ ------ ---
- 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();
- }
- // 由於php5 循環而清理記憶體引用記憶體洩漏...
- function clear () {
- $this->dom = null;
- $this->nodes = null;
- $this->parent = null;
- $this->children = null;
- }
// 轉儲節點的樹
- function dump($show_attr=true) {
- dump_html_tree($ this, $show_attr);
- }
- // 回傳節點
- 的父節點function Parent() {
- return $this->parent;
- }
- // 回傳節點
- 的子節點function child($idx=-1) {
- if ($idx==-1 ) return $this->children;
- if (isset($this->children[$idx] ) )) return $this->children[$idx];
- return null;
- }
- // 傳回節點
- 的第一個子節點function first_child() {
- if ( count ($this->children)>0) return $this->children[0];
- return null;
- }
- // 回傳節點
- 的最後一個子節點function last_child() {
- if (($count=count($this->children))>0) return $this->children[$count-1];
- return null;
- }
- //回傳節點
- 的下一個兄弟節點function next_sibling() {
- if ($this ->parent===null) return null;
- $idx = 0;
- $count = count($ this ->父級->子級);
- while ($idx父級->子級[$idx])
- ++$idx;
- if ( ++$idx>=$count) return null;
- return $this->parent->children[$idx];
- }
- // 回傳節點
- 的上一個兄弟節點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];
- }
- // 取得dom節點的內部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 $ret;
- }
- // 取得dom 節點的外部文字(帶標籤)
- 函數externaltext() {
- if ($this ->tag==='root') return $this->innertext();
- // 觸發回呼
- if ($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] );
- // 渲染開始標籤
- $ret = $this->dom-> nodes[$this->_[HDOM_INFO_BEGIN]]->makeup();
- // 渲染內部文字
- if (isset($this->_[HDOM_INFO_INNER]))
- $ret .= $ this->_[HDOM_INFO_INNER];
- else {
- foreach($this- >nodes as $n)
- $ret .= $n->outertext();
- }
- / / 渲染結束標記
- if(isset($this->_[HDOM_INFO_END) ]) && $this->_[HDOM_INFO_END]!=0)
- $ret .= ''.$this-> tag.'>';
- return $ret;
- }
- // 取得dom 節點的純文字
- function text() {
- if (isset($this->_[HDOM_INFO_INNER ])) return $this->_[HDOM_INFO_INNER];
- switch ($this->nodetype) {
- case HDOM_TYPE_TEXT: return $this->dom->restore_noise($this->_[HDOM_TEXT: return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT。 ;
- case HDOM_TYPE_COMMENT: return '' ;
- case HDOM_TYPE_UNKNOWN: return '';
- }
- if (strcasecmp($this->tag, 'script')===0) return ''===0) return '' ;
- if (strcasecmp($ 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 $ret;
- }
- // 使用標籤建立節點文字
- function Makeup() {
- //文字、註解、未知
- if (isset($this->_ [HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
- $ ret = 'tag;
- $i = -1;
- foreach($this->attr as $key=>$val) {
- ++$ i;
- // 跳過已刪除的屬性
- if ($val===null | | $val===false)
- continue;
- $ret .= $this->_[HDOM_INFO_SPACE ][$i][0];
- //無值屬性:nowrap,選取所選...
- if ($val===true)
- $ret .= $key;
- else {
- switch($this->_[HDOM_INFO_QUOTE][$i]) {
- case HDOM_QUOTE_DOUBLE: $quote = '"';break;
- case HDOM_QUOTE_SINGLE: $quote = '''; Break;
- 預設值:$quote = '';
- }
- $ret .= $key.$this->_[HDOM_INFO_SPACE][$i][1].'='.$this ->_[HDOM_INFO_SPACE][$i][2].$quote.$val.$quote;
- }
- }
- $ret = $this->dom->restore_noise($ ret);
- 回傳$ret 。 $this->_[HDOM_INFO_ENDSPACE] 。 '>';
- }
- // 透過CSS 選擇器找出元素
- function find($selector, $idx=null) {
- $selectors = $this->parse_selector($selector);
- if (($count =count($selectors))===0) return array();
- $found_keys = array();
- // 找出每個選擇器
- for ($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);
- // 處理後代選擇器,無遞歸!
- 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;
- }
- }
- // 排序鍵
- ksort($found_keys);
- $found = array();
- foreach($found_keys as $k=>$v)
- $found[] = $this->dom->nodes[$k];
- // 傳回第n 個元素或陣列
- if (is_null($idx)) return $found;
- else if ($idx return (isset($found[ $idx])) ? $found[$idx] : null;
- }
- // 找給定條件
- protected functioneek($selector, &$ret) {
- list($tag, $key, $val , $exp, $no_key) = $selector;
- // xpath 索引
- if ($tag && $key && is_numeric($key)) {
- $count = 0;
- foreach ($ this ->children as $c) {
- if ($tag==='*' || $tag===$c->tag) {
- if (++$count==$鍵) {
- $ret[$c->_[HDOM_INFO_BEGIN]] = 1;
- return;
- }
- }
- }
- return;
- }
- $endend = (!empty($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;
- }
- // 比較標籤
- if ($tag && $tag! =$node->tag && $tag!=='*') {$pass=false;}
- // 比較key
- if ($pass && $key) {
- if ($no_key ) {
- if (isset($node->attr[$key])) $pass=false;
- }
- else if (!isset($node->attr [$key]) ) $pass=false;
- }
- // 比較值
- if ($pass && $key && $val && $val!=='*') {
- $ check = $this- >match($exp, $val, $node->attr[$key]);
- // 處理多個類別
- 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);
- }
- }
- 受保護函數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) {
- // CSS 選擇器的模式,從mootools 修改
- $pattern = "/([w-:*]*)(?:#([w- ]) +)|.([w-]+))?(?:[@?(!?[w-]+)(?:([!*^$]?=)["']?(. *? )["']?)?])?([/, ]+)/is";
- preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER);
- $selectors = array();
- $result = array();
- //print_r($matches);
- foreach ($matches as $m) {
- $m[0] = trimrim ($ m[0]);
- if ($m[0]==='' || $m[0]==='/' || $m[0]==='//' ) 繼續;
- // for borwser grnreated xpath
- if ($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=$m[6];}
- // 轉換成小寫
- if ($this->dom->lowercase) {$tag=strtolower($tag); $key= strtolower($key);}
- //不具有指定屬性的元素
- 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 )
- $選擇器[] = $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();
- 預設值: 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': 回傳true;
- case 'innertext': 回傳true;
- ;
- case 'plaintext': 回傳true;
- }
- //無值attr:nowrap,選取選定...
- return (array_key_exists($name, $this->attr)) ? true : isset ($this->attr[$name]);
- }
- function __unset($name) {
- if (isset($this->attr[$name]))
- unset($ this->attr[$name]);
- }
- // 駱駝命名約定
- function getAllAttributes() {return $this->attr;}
- function getAttribute ($name) {return $attr;}
- function getAttribute ($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, 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();}}
- // 簡單的 html dom 解析器
- // ---------------------------------- -------------------------------------------------- ------
- class simple_html_dom {
- public $root = null;
- public $nodes = array();
- public $callback = null;
- public $lowercase = false;
- 受保護的$pos;
- 受保護的$doc;
- 受保護的$char;
- 受保護的$size;
- 受保護的$cursor;
- 受保護的$parent;
- 受保護的$noise = 陣列();
- protected $token_blank = " trn";
- protected $token_equal = ' =/>';
- protected $token_slash = " / >rnt";
- protected $token_attr = ' >' ;
- // 使用isset 而不是in_array,效能提升約30%...
- protected $self_ending_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_ending_tags = array(
- 'tr'=>array('tr'=>1, 'td'=>1, 'th'=>1),
- 'th'= >array('th'= >1),
- 'td'=>陣列('td'=>1),
- 'li'=>陣列('li'= >; 1),
- 'dt'=>陣列('dt'=>1, 'dd'=>1),
- 'dd'=>陣列('dd'=>1, 'dt' =>1),
- 'dl'=>陣列('dd'=>1, 'dt'=>1),
- 'p'=>陣列('p '=>1),
- 'nobr'=>陣列('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();
- }
- // 從字串載入html
- function load($str, $lowercase=true) {
- // 準備
- $this-> ; prepare($str, $lowercase);
- // 刪除註解
- $this->remove_noise("''is");
- // 刪除cdata
- $this->remove_noise("''is", true);
- // 去掉
- 風格>標籤
- $this- >remove_noise("'
]*[^/]>(.*?)'is") ;- $this->remove_noise("'(.*?)
'is");- // 去掉標籤
- $this->remove_noise("'
]*[^/]>(.*?)'is") ;- $this->remove_noise("'
(.*? )'is");- // 刪除預篩選標籤
- $this->remove_noise("'
]*> ( .*?) ;'is");- // 刪除伺服器端腳本
- $this->remove_noise("'()( . *?)(?>)'s", true);
- // 分割 smarty 腳本
- $this->remove_noise("'({w)(.*?)(})'s", true);
- // 解析
- while ( $ this->parse());
- // 結束
- $this->root->_[HDOM_INFO_END] = $this->cursor;
- }
- // 載入來自檔案的html
- function load_file() {
- $args = func_get_args();
- $this->load(call_user_func_array('file_get_contents', $args), true);
- }
- }
- // 設定回復函數
- function set_callback($function_name) {
- $this->callback = $function_name;
- }
- // 刪除回呼函數
- function remove_callback() { callback = null;
- }
- // 將dom 儲存為字串
- function save($filepath='') {
- $ret = $this->root- >innertext();
- if ($filepath!=='') file_put_contents($filepath, $ret);
- return $ret;
- }
- // 透過css選擇器來尋找🎜> function find($selector, $idx=null) {
- return $this->root->find($selector, $idx);
- }
- // 清理記憶體php5 迴圈引用記憶體浪費.. .
- function clear() {
- foreach($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();取消設定($this->root);}
- 取消設定($this->doc);
- 取消設定($this->雜訊);
- }
function dump($show_attr=true) {
- $this->root->dump($show_attr);
- }
- // 準備 HTML 資料並初始化所有內容
- 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;
- // 設定內容的長度
- $ this->size = strlen($ str);
- if ($this->size>0) $this->char = $this->doc[0];
- }
- // 解析html 內容
- protected function parse( ) {
- if (($s = $this->copy_until_char(' return $this-> ;read_tag();
- // 文字
- $node = new simple_html_dom_node($this);
- ++$this->曼谷;
- $node->_[HDOM_INFO_TEXT] = $ s;
- $this->link_nodes($node, false) ;
- return true;
- }
- // 讀取標籤資訊
- protected function read_tag() {
- if ( $this->char!==' $this->root->_[HDOM_INFO_END] = $this->遊標;
- return false;
- }
- $begin_tag_pos = $this->pos;
- $this->char = ( ++$this->possize) ? $this->doc[$this->pos] : null; // 下一個
- // 結束標記
- if ($this->char==='/') {
- $this->char = (++$this->posdoc[$this->pos] : null; // next
- $this->skip($this->token_blank_t);
- $tag = $this->copy_until_char( '>') ;
- // 跳過結束標記中的屬性
- if (($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->optical_writing_tags[ $parent_lower]) && isset($this->block_tags[$tag_lower])) {
- $this->parent->_[HDOM_INFO_END] = 0
- $this->parent->_[HDOM_INFO_END] = 0
- $🎜> $ org_parent = $this->;父親;
- while (($this->parent->parent) && strtolower($this->parent->tag)!==$tag_lower)
- $ this->parent = $ this->parent->parent;
- if (strtolower($this->parent->tag)!==$tag_lower) {
- $this->parent = $org_parent; / / 恢復原始父級
- if ($this->parent->parent) $this->parent = $this->parent->parent;
- $this->parent-> ;_[HDOM_INFO_END] = $this->曼谷;
- 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 = $this->;父;
- while (($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; // 恢復原始父級
- $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->possize) ? $this->doc[$this->pos] : null; // next
- 回傳 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 與註解...
- if (isset($ tag[0]) && $tag[0]==='!') {
- $node->_[HDOM_INFO_TEXT] = ' $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);
- $this->char = (++$這個->possize) ? $this->doc[$this->pos] : null; // next
- return true;
- }
- // text
- if ($pos=strpos($tag, ' $tag = ' doc[--$this->pos]; // prev
- return true;
- }
- if (!preg_match("/^[w-:]+$/", $tag)) {
- $node->_[HDOM_INFO_TEXT ] = ' return true;
- }
- if ($this->char==='>') $node->_[HDOM_INFO_TEXT].='>';
- $ this- >link_nodes($node, false);
- $this->char = (++$this->possize) ? $this->doc[$this->pos] : null; // next
- return true;
- }
- // 開始標籤
- $node->nodetype = HDOM_TYPE_ELEMENT;
- $tag_lower = strtolower($tag); $no🎜> $node-標籤= ($this->小寫) ? $tag_lower : $tag;
- // 處理任選的結束標籤
- if (isset($this->optical_writing_tags[$tag_lower]) ) {
- while (isset($this->optical_ending_tags[$ tag_lower][strtolower($this->parent->tag)])) {
- $this->parent->_[HDOM_INFO_END] = 0;
- $this->parent = $this->parent- >parent;
- }
- $node->parent = $this->parent;
- }
- $guard = 0; // 防止無限迴圈
- $space = array($this->copy_skip($this->token_blank), '', '');
- // 屬性
- do {
- if ($ this->char!==null && $space[0]==='') break;
- $name = $this->copy_until($this->token_equal);
- if ($guard== =$this->pos) {
- $this->char = (++$this->possize) ? $this->doc[$this->pos] : null; // next
- continue;
- }
- $guard = $this->pos;
- // 處理無限的 ' if($this->pos>=$ this- >size-1 && $this->char!=='>') {
- $node->nodetype = HDOM_TYPE_TEXT;
- $node->_[HDOM_INFO_END] = 0;
- $node->_[HDOM_INFO_TEXT] = ' 回傳true;
- }
- // 處理不符 ' if($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- $this->doc[$this->pos] : null; >possize) ? // 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 ->小寫) $name = strtolower($name);
- if ($this->char==='=') {
- $this->char = (++$this-> ;pos尺寸) ? $this->doc[$this->pos] : null; // next
- $this->parse_attr($node, $name, $space);
- }
- else {
- //無值屬性:nowrap,勾選...
- $node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_NO;
- $node->attr[$name] = true;
- if ($this->char!='>') $這-> char = $這-> doc[--$這-> pos]; // 上一個
- }
- $node->_[HDOM_INFO_SPACE][] = $space;
- $space = array($this->copy_skip($this->token_blank), '' , ' ');
- }
- else
- 規則;
- } while($this->char!=='>' && $this->char!=='/' );
- $this->link_nodes($node, true);
- $node->_[HDOM_INFO_ENDSPACE] = $space[0];
- // 檢查自關閉
- if ( $this->copy_until_char_escape(' >')==='/') {
- $node->_[HDOM_INFO_ENDSPACE] .= '/';
- $node->_[HDOM_INFO_END] = 0;
- }
- else {
- // 重置父級
- if (!isset($this->self_ending_tags[strtolower($node->tag)])) $this-> ;parent = $node;
- }
- $this->char = (++$this->possize) ? $this->doc[$this->pos] : null; // next
- return true;
- }
- // 解析屬性
- 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->possize) ? $this->doc[$this->pos] : null; > $node->attr[$name] = $this- >restore_noise($this->copy_until_char_escape('"'));
- $this->char = (++$this->; possize) ? $this->doc[$this->pos] : null; // next
- break;
- case ''':
- $node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_SINGLE;
- $this->char = (++$this-> ;pos 大小) ? $this->doc[$this->pos] : null; // next
- $node->attr[$name] = $this->restore_noise($this->copy_until_char_escape('''));
- $this->char = (++ $this-> pos大小) ? $this->doc[$this->pos] : null; // next
- break;
- 預設:
- $node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_NO;
- $node->attr[$name] = $this->s_noise (thisrestore_noise ($thisrestore_noise) (thisrestore_noise (thisrestore_noise) ->copy_until($this->token_attr));
- }
- }
- // 連結節點的父節點
- protected function link_nodes(&$node, $is_child) {
- $nonode ->parent = $this->parent;
- $this->parent->nodes[] = $node;
- if ($is_child)
- $this->; Parent->children[] = $node;
- }
- // 作為文字節點
- protected function as_text_node($tag) {
- $node = new simple_html_dom_node($this);
- $node = new simple_html_dom_node($this);
- + +$this-> 曼谷;
- $node->_[HDOM_INFO_TEXT] = '' 。 this->char = (++$this->possize) ? $this->doc[$this->pos] : null; // 下一個
- 回傳 true;
- }
- 受保護的函數skip($chars) {
- $this->pos += strspn($this->doc, $chars, $this->pos);
- $this->; char = ($this->possize) ? $this->doc[$this->pos] : null; // next
- }
- 受保護函數copy_skip($chars) {
- $pos = $this->pos;
- $len = strspn($this->doc, $chars, $ pos ) ;
- $this->pos += $len;
- $this->char = ($this->possize) ? $this->doc[$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->possize) ? $this->doc[$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;
- 繼續;
- }
- $pos_old = $this- >pos;
- $this->char = $this->doc[$ pos];
- $this->pos = $pos;
- return substr($this->doc , $pos_old, $pos-$pos_old);
- }
- }
- //去除html內容中的噪音
- protected function remove_noise($pattern, $remove_tag=false) {
- $count = preg_match_all($pattern, $this->doc, $matches, PREG_SET_ORDER|PREG_OFFSET_CAPd);對於($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]));
- }
- // 重設內容長度
- $ this->size = strlen($this->doc);
- if ($this->size>0) $this->char = $this->doc[0] ;
- }
- / / 將雜訊還原到html 內容
- function restore_noise($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 $this-> root->text();
- }
- }
- // 駱駝起源約定
- function childNodes($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', $args), true);}
- }
- ?>
複製程式碼
複製程式碼
- tqq.php
-
-
-
-
-
-
/**
- 版本:1.11($Rev:175 $)
- */
- //快取時間,單位:秒
- $t = 360;
- if(!is_file('index.html')||(time()-filemtime('index.html'))>$t){
- //微博帳號
- $qq = 'kuaisubeian';
- //經過騰訊那個md5_3()加密後的密碼
- $pwd = '624D3274815F2237817A7C62F42DD26A'; $loginURL = 'http://ptlogin2.qq.com/login?';
/ /取得驗證碼及第一次cookie
- $curl = curl_init($verifyURL);
- $cookie_jar = tempnam('.', 'cookie');
- curl_setopt($curl, CURLOPT_RETURNTRANSFER, 11) ;
- curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
- $verifyCode = curl_exec($curl);
- curl_close($curl);
- $verifyCode = strver. , 4));
- //echo '驗證碼:'.$verifyCode;
- //echo '
';
- // echo 'Cookies:'.$cookie_jar;
- // echo '
';
//發送登入要求並取得第二次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 '
';- $curl = curl_init($loginURL);
- curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); ($curl, CURLOPT_COOKIEJAR, $cookie_jar);
- curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_jar);
- curl_setopt($curl, CURLOPT_CIEJAR, $cookie;
- curl_close($curl);
- //echo '登入驗證結果:'.$loginResult;
- //echo '
';
- http://bbs.it-home .org
- //取得第三次cookie
- $curl = curl_init('http://t.qq.com');
- curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
- curl_setopttopt ($curl, CURLOPT_COOKIEJAR, $cookie_jar);
- curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_jar);
- curl_setopt($curl, CURLOPT_CIEJAR, $cookie;
- curl_close($curl);
//第四次
- $curl = curl_init('http://t.qq.com/'.$qq.'/ mine');
- curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
- curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_jar);
- curl_setop($c), CURL); $curl, CURLOPT_COOKIEJAR, $cookie_jar);
- $loginResult = curl_exec($curl);
- curl_close($curl);
unlink($cookie_jar);}- 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;
$result = '';
//大於二則是轉播
- if(count($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;
- ?>
-
-
複製程式碼
|