/** * 获取URL内容 */ function get_page_content($url) { $url = eregi_replace('^http://', '', $url); $temp = explode('/', $url); $host = array_shift($temp); $path = '/'.implode('/', $temp); $temp = explode(':', $host); $host = $temp[0]; $port = isset($temp[1]) ? $temp[1] : 80; $fp = @fsockopen($host, $port, &$errno, &$errstr, 30); if ($fp) { @fputs($fp, "GET $path HTTP/1.1\r\nHost: $host\r\nAccept: */*\r\nReferer:$url\r\nUser-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1)\r\nConnection: Close\r\n\r\n"); } $Content = ""; while ($str = @fread($fp, 4096)) { $Content .= $str; } @fclose($fp); //重定向 if(preg_match("/^HTTP\/\d.\d 301 Moved Permanently/is",$Content)) { if(preg_match("/Location:(.*?)\r\n/is",$Content,$murl)) { return get_page_content($murl[1]); } } //读取内容 if(preg_match("/^HTTP\/\d.\d 200 OK/is",$Content)) { preg_match("/Content-Type:(.*?)\r\n/is",$Content,$murl); $contentType=trim($murl[1]); $Content=explode("\r\n\r\n",$Content,2); $Content=$Content[1]; } return $Content; }
|