php curl获取页面信息,php – 如何使用cURL获取页面内容？

这是怎么回事？

/**

* Get a web file (HTML, XHTML, XML, image, etc.) from a URL. Return an

* array containing the HTTP server response header fields and content.

*/

function get_web_page( $url )

{

$user_agent='Mozilla/5.0 (Windows NT 6.1; rv:8.0) Gecko/20100101 Firefox/8.0';

$options = array(

CURLOPT_CUSTOMREQUEST =>"GET", //set request type post or get

CURLOPT_POST =>false, //set to GET

CURLOPT_USERAGENT => $user_agent, //set user agent

CURLOPT_COOKIEFILE =>"cookie.txt", //set cookie file

CURLOPT_COOKIEJAR =>"cookie.txt", //set cookie jar

CURLOPT_RETURNTRANSFER => true, // return web page

CURLOPT_HEADER => false, // don't return headers

CURLOPT_FOLLOWLOCATION => true, // follow redirects

CURLOPT_ENCODING => "", // handle all encodings

CURLOPT_AUTOREFERER => true, // set referer on redirect

CURLOPT_CONNECTTIMEOUT => 120, // timeout on connect

CURLOPT_TIMEOUT => 120, // timeout on response

CURLOPT_MAXREDIRS => 10, // stop after 10 redirects

);

$ch = curl_init( $url );

curl_setopt_array( $ch, $options );

$content = curl_exec( $ch );

$err = curl_errno( $ch );

$errmsg = curl_error( $ch );

$header = curl_getinfo( $ch );

curl_close( $ch );

$header['errno'] = $err;

$header['errmsg'] = $errmsg;

$header['content'] = $content;

return $header;

}

例

//Read a web page and check for errors:

$result = get_web_page( $url );

if ( $result['errno'] != 0 )

... error: bad url, timeout, redirect loop ...

if ( $result['http_code'] != 200 )

... error: no page, no permissions, no service ...

$page = $result['content'];