有时我们需要做一些采集需要下载远程网页源码到本来了,在这里我们整理了一些php获取远程网页源码代码,希望对各位会有所帮助。
php的curl函数
基本例子
<?php // 初始化一个 cURL 对象 $curl = curl_init(); // 设置你需要抓取的URL curl_setopt($curl, CURLOPT_URL, 'http://www.phprm.com'); // 设置header curl_setopt($curl, CURLOPT_HEADER, 1); // 设置cURL 参数,要求结果保存到字符串中还是输出到屏幕上。 curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); // 运行cURL,请求网页 $data = curl_exec($curl); // 关闭URL请求 curl_close($curl); // 显示获得的数据 var_dump($data); ?>
php fopen函数
<?php print ("<H1>HTTP</H1>n"); // open a file using http protocol if (!($myFile = fopen("http://www.phprm.com/", "r"))) { print ("file could not be opened"); exit; } while (!feof($myFile)) { // read a line from the file $myLine = fgetss($myFile, 255); print ("$myLine <BR>n"); } // close the file fclose($myFile); print ("<H1>FTP</H1>n"); print ("<HR>n"); // open a file using ftp protocol if (!($myFile = fopen("ftp://ftp.php.net/welcome.msg", "r"))) { print ("file could not be opened"); exit; } while (!feof($myFile)) { // read a line from the file $myLine = fgetss($myFile, 255); print ("$myLine <BR>n"); } // close the file fclose($myFile); print ("<H1>Local</H1>n"); print ("<HR>n"); // open a local file if (!($myFile = fopen("data.txt", "r"))) { print ("file could not be opened"); exit; } while (!feof($myFile)) { // read a line from the file $myLine = fgetss($myFile, 255); print ("$myLine <BR>n"); } // close the file fclose($myFile); ?>
file_get_contents函数
<?php file_get_contents('http://www.phprm.com/'); ?>
抓取远程网页源码类
<?php class HTTPRequest { var $_fp; // HTTP socket var $_url; // full URL var $_host; // HTTP host var $_protocol; // protocol (HTTP/HTTPS) var $_uri; // request URI var $_port; // port // scan url function _scan_url() { $req = $this->_url; $pos = strpos($req, '://'); $this->_protocol = strtolower(substr($req, 0, $pos)); $req = substr($req, $pos + 3); $pos = strpos($req, '/'); if ($pos === false) $pos = strlen($req); $host = substr($req, 0, $pos); if (strpos($host, ':') !== false) { list($this->_host, $this->_port) = explode(':', $host); } else { $this->_host = $host; $this->_port = ($this->_protocol == 'https') ? 443 : 80; } $this->_uri = substr($req, $pos); if ($this->_uri == '') $this->_uri = '/'; } // constructor function HTTPRequest($url) { $this->_url = $url; $this->_scan_url(); } // download URL to string function DownloadToString() { $crlf = "rn"; // generate request $req = 'GET ' . $this->_uri . ' HTTP/1.0' . $crlf . 'Host: ' . $this->_host . $crlf . $crlf; // fetch $this->_fp = fsockopen(($this->_protocol == 'https' ? 'ssl://' : '') . $this->_host, $this->_port); fwrite($this->_fp, $req); while (is_resource($this->_fp) && $this->_fp && !feof($this->_fp)) $response.= fread($this->_fp, 1024); fclose($this->_fp); // split header and body $pos = strpos($response, $crlf . $crlf); if ($pos === false) return ($response); $header = substr($response, 0, $pos); $body = substr($response, $pos + 2 * strlen($crlf)); // parse headers $headers = array(); $lines = explode($crlf, $header); foreach ($lines as $line) if (($pos = strpos($line, ':')) !== false) $headers[strtolower(trim(substr($line, 0, $pos))) ] = trim(substr($line, $pos + 1)); // redirection? if (isset($headers['location'])) { $http = new HTTPRequest($headers['location']); return ($http->DownloadToString($http)); } else { return ($body); } } } //使用方法 $r = new HTTPRequest('http://www.phprm.com'); $str = $r->DownloadToString(); ?>