php获取远程网页源码的程序代码

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, &#39;http://www.phprm.com&#39;);
// 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 id="HTTP">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 id="FTP">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 id="Local">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(&#39;http://www.phprm.com/&#39;);
?>

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, &#39;://&#39;);
        $this->_protocol = strtolower(substr($req, 0, $pos));
        $req = substr($req, $pos + 3);
        $pos = strpos($req, &#39;/&#39;);
        if ($pos === false) $pos = strlen($req);
        $host = substr($req, 0, $pos);
        if (strpos($host, &#39;:&#39;) !== false) {
            list($this->_host, $this->_port) = explode(&#39;:&#39;, $host);
        } else {
            $this->_host = $host;
            $this->_port = ($this->_protocol == &#39;https&#39;) ? 443 : 80;
        }
        $this->_uri = substr($req, $pos);
        if ($this->_uri == &#39;&#39;) $this->_uri = &#39;/&#39;;
    }
    // constructor
    function HTTPRequest($url) {
        $this->_url = $url;
        $this->_scan_url();
    }
    // download URL to string
    function DownloadToString() {
        $crlf = "rn";
        // generate request
        $req = &#39;GET &#39; . $this->_uri . &#39; HTTP/1.0&#39; . $crlf . &#39;Host: &#39; . $this->_host . $crlf . $crlf;
        // fetch
        $this->_fp = fsockopen(($this->_protocol == &#39;https&#39; ? &#39;ssl://&#39; : &#39;&#39;) . $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, &#39;:&#39;)) !== false) $headers[strtolower(trim(substr($line, 0, $pos))) ] = trim(substr($line, $pos + 1));
        // redirection?
        if (isset($headers[&#39;location&#39;])) {
            $http = new HTTPRequest($headers[&#39;location&#39;]);
            return ($http->DownloadToString($http));
        } else {
            return ($body);
        }
    }
}
//使用方法
$r = new HTTPRequest(&#39;http://www.phprm.com&#39;);
$str = $r->DownloadToString();
?>