php網頁爬蟲

來源:互聯網
上載者:User

標籤:phpcurl

<?php

/*網頁爬蟲*/

#最簡單的使用,屬性都採用預設值

/*

$curl=curl_init(‘http://www.baidu.com‘);

$output=curl_exec($curl);

curl_close($curl);

echo $output;

*/


#稍微複雜一點的,對頁面進行操作

/*

$curl=curl_init();

curl_setopt($curl, CURLOPT_URL, ‘http://www.baidu.com‘);//可以動態改變網址

curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);//不直接列印在瀏覽器上

$output=curl_exec($curl);//執行

curl_close($curl);//關閉

echo str_replace(‘百度‘, ‘虎哥‘, $output);

*/


#更複雜一點的,類比POST請求

/*

$data=‘theCityName=北京‘;

$curl=curl_init();

curl_setopt($curl, CURLOPT_URL,‘http://www.webxml.com.cn/WebServices/WeatherWebService.asmx/getWeatherbyCityName‘);

curl_setopt($curl,CURLOPT_HEADER, 0);

curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);

curl_setopt($curl,CURLOPT_POST, 1);

curl_setopt($curl,CURLOPT_POSTFIELDS,$data);

curl_setopt($curl,CURLOPT_HTTPHEADER,array(‘application/x-www-form-rulencode;charset=utf-8‘,‘Content-length‘.strlen($data)));

$output=curl_exec($curl);

if(!curl_errno($curl)){

//$info=curl_getinfo($curl);

//print_r($info);

header(‘Content-type:text/html;charset=utf-8;‘);

echo $output;

}else{

echo ‘Curl Error:‘.curl_error($curl);

}

curl_close($curl);

*/


#抓取需要登入的頁面

/*

$data=‘[email protected]&password=19900417&remember=1‘;

$curl=curl_init();

curl_setopt($curl,CURLOPT_URL,‘http://www.imooc.com/user/login‘);

curl_setopt($curl,CURLOPT_RETURNTRANSFER, true);//執行之後不直接列印出來

//Cookie相關設定,這部分設定需要在所有回話開始之前設定

date_default_timezone_set(‘PRC‘);//使用cookie時必須設定時區

curl_setopt($curl,CURLOPT_COOKIESESSION, true);

curl_setopt($curl,CURLOPT_COOKIEFILE,‘cookiefile‘);

curl_setopt($curl,CURLOPT_COOKIEJAR,‘cookiefile‘);

curl_setopt($curl,CURLOPT_COOKIE, session_name().‘=‘.session_id());

curl_setopt($curl,CURLOPT_HEADER,0);//禁止輸出頭資訊

curl_setopt($curl,CURLOPT_FOLLOWLOCATION, 1);

curl_setopt($curl,CURLOPT_POST, 1);

curl_setopt($curl,CURLOPT_POSTFIELDS, $data);

curl_setopt($curl,CURLOPT_HTTPHEADER,array(‘application/x-www-form-rulencode;charset=utf-8‘,‘Content-length:‘.strlen($data)));

curl_exec($curl);//執行

curl_setopt($curl,CURLOPT_URL,‘http://www.imooc.com/space/index‘);

curl_setopt($curl,CURLOPT_POST,0);//下載頁面不是post請求,故置0

curl_setopt($curl,CURLOPT_HTTPHEADER,array(‘Content-type:text/xml‘));

$output=curl_exec($curl);

echo $output;

*/


#從ftp伺服器上下載一個檔案

/*

$curl=curl_init();

curl_setopt($curl,CURLOPT_URL,‘ftp://10.14.12.22:21/test.txt‘);

curl_setopt($curl,CURLOPT_HEADER,0);//禁止輸出頭資訊,調試時,可以輸出

curl_setopt($curl,CURLOPT_RETURNTRANSFER, 1);

curl_setopt($curl,CURLOPT_TIMEOUT,300);//設定逾時時間,單位秒

curl_setopt($curl,CURLOPT_USERPWD,"admin:123");//ftp使用者名稱,密碼

$outfile=fopen(‘mytest.txt‘, ‘wb‘);//儲存到本地的檔案名稱

curl_setopt($curl,CURLOPT_FILE,$outfile);

$output=curl_exec($curl);

fclose($outfile);

if(!curl_errno($curl)){

//$info=curl_getinfo($curl);

//print_r($info);

echo "RETURN:".$output;

}else{

echo ‘Curl error:‘.curl_error($curl);

}

curl_close($curl);

*/


#ftp檔案上傳

/*

$curl=curl_init();

$uploadfile=‘demo1.php‘;

$fp=fopen($uploadfile,‘r‘);

curl_setopt($curl, CURLOPT_URL, ‘ftp://10.14.12.22:21/uploadfile.php‘);

curl_setopt($curl, CURLOPT_HEADER,0);

curl_setopt($curl,CURLOPT_RETURNTRANSFER,1);

curl_setopt($curl, CURLOPT_TIMEOUT,300);

curl_setopt($curl,CURLOPT_USERPWD,‘admin:123‘);

curl_setopt($curl,CURLOPT_UPLOAD,1);

curl_setopt($curl, CURLOPT_INFILE, $fp);

curl_setopt($curl,CURLOPT_INFILESIZE,filesize($uploadfile));

$output=curl_exec($curl);

fclose($fp);

if(!curl_errno($curl)){

echo ‘uploadfile successfully‘;

}else{

echo ‘uploadfile error:‘.curl_error($curl);

}

curl_close($curl);

*/


#curl訪問https上的資源

/*

$curl=curl_init();

curl_setopt($curl,CURLOPT_URL,‘https://ajax.aspnetcdn.com/ajax/jquery.validate/1.12.0/jquery.validate.js‘);

curl_setopt($curl,CURLOPT_RETURNTRANSFER,true);

date_default_timezone_set(‘PRC‘);

curl_setopt($curl,CURLOPT_SSL_VERIFYPEER,0);//終止從服務端進行驗證

$output=curl_exec($curl);

curl_close($curl);

echo $output;

*/



$data=‘{

    "button": [

        {

            "name": "我要淘書", 

            "sub_button": [

   {

                    "type": "click", 

                    "name": "註冊帳號", 

                    "key": "zcyh"

                },

                {

                    "type": "click", 

                    "name": "帳號綁定", 

                    "key": "bd"

                }, 

                {

                    "type": "click", 

                    "name": "圖書搜尋", 

                    "key": "tsss"

                }, 

                {

                    "type": "click", 

                    "name": "賣書訂單", 

                    "key": "[email protected]"

                }, 

                {

                    "type": "click", 

                    "name": "買書訂單", 

                    "key": "[email protected]"

                }

            ]

        }, 

        {

            "name": "努力學習", 

            "sub_button": [

                {

                    "type": "click", 

                    "name": "成績查詢", 

                    "key": "cjcx"

                }, 

                {

                    "type": "click", 

                    "name": "考場查詢", 

                    "key": "kccx"

                }, 

                {

                    "type": "click", 

                    "name": "課表查詢", 

                    "key": "kbcx"

                }

            ]

        }, 

        {

            "name": "多彩生活", 

            "sub_button": [

   {

                    "type": "click", 

                    "name": "學霸工具",

"key":"xbtool"

                },

                {

                    "type": "view", 

                    "name": "校園周邊",

"url":"http://weixuebar.duapp.com/View/surround/schoolSurround.html"

                },

                {

                    "type": "click", 

                    "name": "線上翻譯", 

                    "key": "zxfy"

                },

{

                    "type": "click", 

                    "name": "學霸社區", 

                    "key": "xbsq"

                },

{

                    "type": "view", 

                    "name": "聯絡我們", 

                    "url": "http://weixuebar.duapp.com/View/help.html"

                }

            ]

        }

    ]

}‘;

$url=‘https://api.weixin.qq.com/cgi-bin/menu/create?access_token=4__FZWKzO1gP2_PhvUE9F9_1rpWy2whbQUfKIuvRNBQHnfDrfANGRogi0RXYSwxUW2CYkrfGlKtB5I5wTOOLoA‘;

$curl=curl_init();

curl_setopt($curl,CURLOPT_URL,$url);

curl_setopt($curl,CURLOPT_RETURNTRANSFER,true);

curl_setopt($curl,CURLOPT_POST, 1);

curl_setopt($curl,CURLOPT_POSTFIELDS,$data);

date_default_timezone_set(‘PRC‘);

curl_setopt($curl,CURLOPT_SSL_VERIFYPEER,0);//終止從服務端進行驗證

curl_setopt($curl,CURLOPT_HTTPHEADER,array(‘application/x-www-form-rulencode;charset=utf-8‘,‘Content-length‘.strlen($data)));

$output=curl_exec($curl);

curl_close($curl);

echo $output;




/*curl_setopt($curl, CURLOPT_URL,‘http://www.webxml.com.cn/WebServices/WeatherWebService.asmx/getWeatherbyCityName‘);

curl_setopt($curl,CURLOPT_HEADER, 0);

curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);

curl_setopt($curl,CURLOPT_POST, 1);

curl_setopt($curl,CURLOPT_POSTFIELDS,$data);

curl_setopt($curl,CURLOPT_HTTPHEADER,array(‘application/x-www-form-rulencode;charset=utf-8‘,‘Content-length‘.strlen($data)));

*/


//php官方文檔網址:http://php.net/manual/zh/book.curl.php

?>


本文出自 “虎哥的部落格” 部落格,請務必保留此出處http://7613577.blog.51cto.com/7603577/1531692

聯繫我們

該頁面正文內容均來源於網絡整理,並不代表阿里雲官方的觀點,該頁面所提到的產品和服務也與阿里云無關,如果該頁面內容對您造成了困擾,歡迎寫郵件給我們,收到郵件我們將在5個工作日內處理。

如果您發現本社區中有涉嫌抄襲的內容,歡迎發送郵件至: info-contact@alibabacloud.com 進行舉報並提供相關證據,工作人員會在 5 個工作天內聯絡您,一經查實,本站將立刻刪除涉嫌侵權內容。

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.