PHP web crawler

<?php

/* Web crawler */

#最简单的使用, the properties are in default values

/*

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

$output =curl_exec ($curl);

Curl_close ($curl);

Echo $output;

*/

#稍微复杂一点的, working with the page

/*

$curl =curl_init ();

curl_setopt ($curl, Curlopt_url, ' http://www.baidu.com ');//Can dynamically change the URL

curl_setopt ($curl, Curlopt_returntransfer, true);//Do not print directly on the browser

$output =curl_exec ($curl);//execution

Curl_close ($curl);//Close

Echo str_replace (' Baidu ', ' tiger Brother ', $output);

*/

#更复杂一点的, simulate a POST request

/*

$data = ' thecityname= Beijing ';

$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);

*/

#抓取需要登录的页面

/*

$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);//do not print directly after execution

Cookie-related settings, which need to be set before all calls are started

Date_default_timezone_set (' PRC ');//The time zone must be set when using cookies

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);//Prohibit Output header information

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);//execution

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

curl_setopt ($curl, curlopt_post,0);//download page is not a POST request, so 0

curl_setopt ($curl, Curlopt_httpheader,array (' content-type:text/xml '));

$output =curl_exec ($curl);

Echo $output;

*/

#从ftp服务器上下载一个文件

/*

$curl =curl_init ();

curl_setopt ($curl, Curlopt_url, ' ftp://10.14.12.22:21/test.txt ');

curl_setopt ($curl, curlopt_header,0);//Prohibit output header information, debug, can output

curl_setopt ($curl, Curlopt_returntransfer, 1);

curl_setopt ($curl, curlopt_timeout,300);//Set time-out, units per second

curl_setopt ($curl, Curlopt_userpwd, "admin:123");//ftp user name, password

$outfile =fopen (' Mytest.txt ', ' WB ');//Save to local file name

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文件上传

/*

$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访问https上的资源

/*

$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);//terminating authentication from the service side

$output =curl_exec ($curl);

Curl_close ($curl);

Echo $output;

*/

$data = ' {

"Button": [

{

"Name": "I want to scour the book",

"Sub_button": [

{

"Type": "Click",

"Name": "Registered Account",

"Key": "Zcyh"

},

{

"Type": "Click",

"Name": "Account Binding",

"Key": "BD"

},

{

"Type": "Click",

"Name": "Book Search",

"Key": "TSSs"

},

{

"Type": "Click",

"Name": "Sell book order",

"Key": "[email protected]"

},

{

"Type": "Click",

"Name": "Buy book Order",

"Key": "[email protected]"

}

]

},

{

"Name": "Study Hard",

"Sub_button": [

{

"Type": "Click",

"Name": "Score Query",

"Key": "Cjcx"

},

{

"Type": "Click",

"Name": "Examination Room Enquiry",

"Key": "KCCX"

},

{

"Type": "Click",

"Name": "Timetable Query",

"Key": "Kbcx"

}

]

},

{

"Name": "Colorful Life",

"Sub_button": [

{

"Type": "Click",

"Name": "Genius Tool",

"Key": "Xbtool"

},

{

"Type": "View",

"Name": "Campus Perimeter",

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

},

{

"Type": "Click",

"Name": "Online translator",

"Key": "Zxfy"

},

{

"Type": "Click",

"Name": "Genius Community",

"Key": "XBSQ"

},

{

"Type": "View",

"Name": "Contact Us",

"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);//terminating authentication from the service side

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 Official document URL: http://php.net/manual/zh/book.curl.php

?>

This article is from "Tiger Brother's Blog" blog, please be sure to keep this source http://7613577.blog.51cto.com/7603577/1531692