<?php $ch= curl_init(); curl_setopt($ch, CURLOPT_URL,"http://localhost/mytest/phpinfo.php"); curl_setopt($ch, CURLOPT_HEADER, false); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);//若是把这行注释掉的话,就会直接输出 $result=curl_exec($ch); curl_close($ch); ?>
为何要使用代理进行抓取呢?以google为例吧,若是去抓google的数据,短期内抓的很频繁的话,你就抓取不到了。google对你的ip地址作限制这个时候,你能够换代理从新抓。php
<?php $ch= curl_init(); curl_setopt($ch, CURLOPT_URL,"http://blog.51yip.com"); curl_setopt($ch, CURLOPT_HEADER, false); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); curl_setopt($ch, CURLOPT_HTTPPROXYTUNNEL, TRUE); curl_setopt($ch, CURLOPT_PROXY, 125.21.23.6:8080); //url_setopt($ch, CURLOPT_PROXYUSERPWD, 'user:password');若是要密码的话,加上这个 $result=curl_exec($ch); curl_close($ch); ?>
单独说一下数据提交数据,由于用 curl的时候,不少时候会有数据交互的,因此比较重要的。html
<?php $ch= curl_init(); /*在这里须要注意的是,要提交的数据不能是二维数组或者更高 *例如array('name'=>serialize(array('tank','zhang')),'sex'=>1,'birth'=>'20101010') *例如array('name'=>array('tank','zhang'),'sex'=>1,'birth'=>'20101010')这样会报错的*/ $data=array('name'=>'test','sex'=>1,'birth'=>'20101010'); curl_setopt($ch, CURLOPT_URL,'http://localhost/mytest/curl/upload.php'); curl_setopt($ch, CURLOPT_POST, 1); curl_setopt($ch, CURLOPT_POSTFIELDS,$data); curl_exec($ch); ?>
在 upload.php文件中,print_r($_POST);利用curl就能抓取出upload.php输出的内容Array ( [name] => test [sex] => 1 [birth] => 20101010 )数组
之前写过一篇,页面访问控制的3种方法有兴趣的能够看一下。cookie
若是用上面提到的方法抓的话,会报如下错误curl
You are not authorized to view this pagepost
Youdonot have permission to view this directoryorpage using the credentials that you supplied because your Web browser is sending a WWW-Authenticate header field that the Web server is not configured to accept.ui
这个时候,咱们就要用CURLOPT_USERPWD来进行验证了this
<?php $ch= curl_init(); curl_setopt($ch, CURLOPT_URL,"http://club-china"); /*CURLOPT_USERPWD主要用来破解页面访问控制的 *例如平时咱们因此htpasswd产生页面控制等。*/ //curl_setopt($ch, CURLOPT_USERPWD, '231144:2091XTAjmd='); curl_setopt($ch, CURLOPT_HTTPGET, 1); curl_setopt($ch, CURLOPT_REFERER,"http://club-china"); curl_setopt($ch, CURLOPT_HEADER, 0); $result=curl_exec($ch); curl_close($ch); ?>
咱们要抓取数据,多是登陆之后的内容,这个时候咱们就要用到curl的模拟登陆功能了。google
<?php functionchecklogin($user,$password) { if( emptyempty($user) || emptyempty($password) ) { return0; } $ch= curl_init( ); curl_setopt($ch, CURLOPT_REFERER,"http://mail.sina.com.cn/index.html"); curl_setopt($ch, CURLOPT_HEADER, true ); curl_setopt($ch, CURLOPT_RETURNTRANSFER, true ); curl_setopt($ch, CURLOPT_USERAGENT, USERAGENT ); curl_setopt($ch, CURLOPT_COOKIEJAR, COOKIEJAR ); curl_setopt($ch, CURLOPT_TIMEOUT, TIMEOUT ); curl_setopt($ch, CURLOPT_URL,"http://mail.sina.com.cn/cgi-bin/login.cgi"); curl_setopt($ch, CURLOPT_POST, true ); curl_setopt($ch, CURLOPT_POSTFIELDS,"&logintype=uid&u=".urlencode($user)."&psw=".$password); $contents= curl_exec($ch); curl_close($ch); if( !preg_match("/Location: (.*)\\/cgi\\/index\\.php\\?check_time=(.*)\n/",$contents,$matches) ) { return0; }else{ return1; } } define("USERAGENT",$_SERVER['HTTP_USER_AGENT'] ); define("COOKIEJAR", tempnam("/tmp","cookie") ); define("TIMEOUT", 500 ); echochecklogin("zhangying215","xtaj227"); ?> 打开/tmp下面的cookie文件看一下 # Netscape HTTP Cookie File # http://curl.haxx.se/rfc/cookie_spec.html # This file was generated by libcurl! Edit at your own risk. mail.sina.com.cn FALSE / FALSE 0 SINAMAIL-WEBFACE-SESSID 65223c4bd8900284ed463d2a3e1ac182 #HttpOnly_.sina.com.cn TRUE / FALSE 0 SUE es%3D8d96db0820c6c79922ad57d422f575e8%26ev%3Dv0%26es2%3Dcddfb8400dc5ca95902367ddcd7f57dd .sina.com.cn TRUE / FALSE 0 SUP cv%3D1%26bt%3D1286900433%26et%3D1286986833%26lt%3D1%26uid%3D1445632344%26user%3D%25E5%25BC%25A0%25E6%2598%25A02001%26ag%3D2%26name%3Dzhangying20015%2540sina.com%26nick%3D%25E5%25BC%25A0%25E6%2598%25A02001%26sex%3D1%26ps%3D0%26email%3Dzhangying20015%2540sina.com%26dob%3D1982-07-18 #HttpOnly_.sina.com.cn TRUE / FALSE 0 SID BihcallomxMx-QZxzGrOlcSQx%2F0B%2F0cmr.NyQ%2F0B%2FcmGGalmarlmcHrcGlSmrmxmfxal_CBZ%2F_afugCmmGirBYHm0Bc%40fr5ciZiGG5i #HttpOnly_.sina.com.cn TRUE / FALSE 0 SPRIAL bfb4102951fd5892a3fd5b42d442cd26 #HttpOnly_.sina.com.cn TRUE / FALSE 0 SINA_USER %D5%C5%D2001