腾讯QQ微博API接口获取微博内容(7)

// 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 = ' =https://www.jb51.net/>';
    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);
        }
    }
   
    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;
    }

内容版权声明:除非注明,否则皆为本站原创文章。

转载注明出处:http://www.heiqu.com/48a71be181fbc92c655ea1d0074b56d8.html