通過curl_setopt()函數可以方便快捷的抓取網頁(采集很方便),curl_setopt 是php的一個擴展庫
使用條件:需要在php.ini 中配置開啟。(PHP 4 >= 4.0.2)
//取消下面的注釋
extension=php_curl.dll
在Linux下面,需要重新編譯PHP了,編譯時,你需要打開編譯參數——在configure命令上加上“–with-curl” 參數。
1、 一個抓取網頁的簡單案例:
- // 創建一個新cURL資源
- $ch = curl_init();
- // 設置URL和相應的選項
- curl_setopt($ch, CURLOPT_URL, "http://www.baidu.com/");
- curl_setopt($ch, CURLOPT_HEADER, false);
- // 抓取URL並把它傳遞給瀏覽器
- curl_exec($ch);
- //關閉cURL資源,並且釋放系統資源
- curl_close($ch);
2、POST數據案例:
- // 創建一個新cURL資源
- $ch = curl_init();
- $data = 'phone='. urlencode($phone);
- // 設置URL和相應的選項
- curl_setopt($ch, CURLOPT_URL, "http://www.post.com/");
- curl_setopt($ch, CURLOPT_POST, 1);
- curl_setopt($ch, CURLOPT_POSTFIELDS, $data);
- // 抓取URL並把它傳遞給瀏覽器
- curl_exec($ch);
- //關閉cURL資源,並且釋放系統資源
- curl_close($ch);
3、關於SSL和Cookie
關於SSL也就是HTTPS協議,你只需要把CURLOPT_URL連接中的http://變成https://就可以了。當然,還有一個參數叫CURLOPT_SSL_VERIFYHOST可以設置為驗證站點。
關於Cookie,你需要了解下面三個參數:
CURLOPT_COOKIE,在當面的會話中設置一個cookie
CURLOPT_COOKIEJAR,當會話結束的時候保存一個Cookie
CURLOPT_COOKIEFILE,Cookie的文件。
PS:新浪微博登陸API部分截取(部分我增加了點注釋,全當參數翻譯下。哈哈) 有興趣的自己研究,自己挪為己用。嘿嘿
- /**
- * Make an HTTP request
- *
- * @return string API results
- * @ignore
- */
- function http($url, $method, $postfields = NULL, $headers = array()) {
- $this->http_info = array();
- $ci = curl_init();
- /* Curl settings */
- curl_setopt($ci, CURLOPT_HTTP_VERSION, CURL_HTTP_VERSION_1_0);//讓cURL自己判斷使用哪個版本
- curl_setopt($ci, CURLOPT_USERAGENT, $this->useragent);//在HTTP請求中包含一個"User-Agent: "頭的字符串。
- curl_setopt($ci, CURLOPT_CONNECTTIMEOUT, $this->connecttimeout);//在發起連接前等待的時間,如果設置為0,則無限等待
- curl_setopt($ci, CURLOPT_TIMEOUT, $this->timeout);//設置cURL允許執行的最長秒數
- curl_setopt($ci, CURLOPT_RETURNTRANSFER, TRUE);//返回原生的(Raw)輸出
- curl_setopt($ci, CURLOPT_ENCODING, "");//HTTP請求頭中"Accept-Encoding: "的值。支持的編碼有"identity","deflate"和"gzip"。如果為空字符串"",請求頭會發送所有支持的編碼類型。
- curl_setopt($ci, CURLOPT_SSL_VERIFYPEER, $this->ssl_verifypeer);//禁用后cURL將終止從服務端進行驗證
- curl_setopt($ci, CURLOPT_HEADERFUNCTION, array($this, 'getHeader'));//第一個是cURL的資源句柄,第二個是輸出的header數據
- curl_setopt($ci, CURLOPT_HEADER, FALSE);//啟用時會將頭文件的信息作為數據流輸出
- switch ($method) {
- case 'POST':
- curl_setopt($ci, CURLOPT_POST, TRUE);
- if (!empty($postfields)) {
- curl_setopt($ci, CURLOPT_POSTFIELDS, $postfields);
- $this->postdata = $postfields;
- }
- break;
- case 'DELETE':
- curl_setopt($ci, CURLOPT_CUSTOMREQUEST, 'DELETE');
- if (!empty($postfields)) {
- $url = "{$url}?{$postfields}";
- }
- }
- if ( isset($this->access_token) && $this->access_token )
- $headers[] = "Authorization: OAuth2 ".$this->access_token;
- $headers[] = "API-RemoteIP: " . $_SERVER['REMOTE_ADDR'];
- curl_setopt($ci, CURLOPT_URL, $url );
- curl_setopt($ci, CURLOPT_HTTPHEADER, $headers );
- curl_setopt($ci, CURLINFO_HEADER_OUT, TRUE );
- $response = curl_exec($ci);
- $this->http_code = curl_getinfo($ci, CURLINFO_HTTP_CODE);
- $this->http_info = array_merge($this->http_info, curl_getinfo($ci));
- $this->url = $url;
- if ($this->debug) {
- echo "=====post data======\r\n";
- var_dump($postfields);
- echo '=====info====='."\r\n";
- print_r( curl_getinfo($ci) );
- echo '=====$response====='."\r\n";
- print_r( $response );
- }
- curl_close ($ci);
- return $response;
- }
<?php
$user=$_POST["stuno"];
$password=$_POST["stupwd"];
$yzm=$_POST["stuyzm"];
//echo $user;
//echo $password;
//echo $yzm;
$cookie_file = tempnam('./temp','cookie');
$login_url = 'http://xk.shnu.edu.cn:82/index.aspx';
$post_fields = array("cktime"=>"3153600","txtUserID"=>$user,"txtUserPwd"=>$password,"txtValidateCode"=>$yzm);
$ch = curl_init($login_url);
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPTFOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file);
curl_setopt($ch, CURLOPT_POSTFIELDS, $post_fields);
curl_exec($ch);
curl_close($ch);
$url='http://xk.shnu.edu.cn:82/index.aspx';
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 0);
curl_setopt($ch, CURLOPTFOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_file);
$contents = curl_exec($ch);
curl_close($ch);
?>
更詳細的參數說明參考:http://cn2.php.net/curl_setopt