最近在学习curl的抓取实践, 在里面也学到了一些东西。

有一些网站需要cookie才可以抓取成功。这个时候我们就可以通过fiddle4 去抓包实现。然后通过构建头部信息 ,绕过网站端的验证。

以下是实现代码:

<?php
$stime=microtime(true);

$ch = curl_init();
$ckw = urlencode("圆形折叠麻将机全自动餐桌两用带椅子机麻家用欧式实木电动麻将桌PHP");
curl_setopt($ch, CURLOPT_URL, " http://www.meegoe.com/sou_Y3sl/ ?keywords=".$ckw);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);//https请求 不验证证书
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false);//https请求 不验证HOST
curl_setopt($ch, CURLOPT_TIMEOUT, 10); // 3秒超时
curl_setopt($ch, CURLOPT_HEADER, 0); // 不需要页面的HTTP头
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); // 抓取结果直接返回(如果为0,则直接输出内容到页面)
curl_setopt($ch, CURLOPT_ENCODING, 'gzip,deflate');//这个是解释gzip内容
curl_setopt($ch, CURLOPT_HTTPHEADER, array(
'Connection: keep-alive',
'Upgrade-Insecure-Requests: 1',
'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36',
'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Referer: http://www.meegoe.com/ ',
'Accept-Encoding: gzip, deflate, br',
'Accept-Language: zh-CN,zh;q=0.9',
));
curl_setopt($ch,CURLOPT_COOKIE,'cna=3kDtFId2QkgCAbaBNczxpp/X; hng=CN%7Czh-CN%7CCNY%7C156; UM_distinctid=1694cacf99e377-0508f14d59d804-b781636-100200-1694cacf99f503; lid=haosweet; ali_ab=139.207.69.183.1552121532339.7; ali_apache_id=11.23.78.17.1552121946782.441191.7; h_keys="%u714e%u997c#%u4ebf%u5065%u8702%u80f6#arrl#%u8702%u871c"; ad_prefer="2019/03/10 16:12:09"; alicnweb=touch_tb_at%3D1552399125776%7Clastlogonid%3Dlweizwer1%7Cshow_inter_tips%3Dfalse%7ChomeIdttS%3D00964423784623518415084922041883626898%7ChomeIdttSAction%3Dtrue; l=bBEVjusVvczbe9OxBOCiVQhfhO_t7IRxMuSJcRVMi_5ZNsY1VUQOl_0dEUv6Vj5RsLYB4z6vzNp9-etlw; XSRF-TOKEN=2f40c7b9-d618-4a87-929c-6ec68e187b2c; CNZZDATA1261998348=973403025-1552118420-%7C1552486140; _m_h5_tk=4727e399320af3a5455fcd4219c72fab_1552498204613; _m_h5_tk_enc=12f885140e5402698a7e5018ae67b361; cookie2=58efdb753105b686ecef55419f454629; t=dbb53d6a3987478e0c4062af14864a21; _tb_token_=5376f111de15e; __wapcsf__=1; CNZZDATA1000231236=1647319684-1552120971-https%253A%252F%252Fm.1688.com%252F%7C1552488361; cookie1=AC0hYCJXlFdQ3RN7W3VKzBxzzaCSgNA0AcLxtMnL0LY%3D; cookie17=UUwZ%2FIsa2fE%3D; sg=t49; csg=1d0e7cb7; unb=24919014; cn_tmp=Z28mC+GqtZ3c/avrs/YMFPZ2bd/61p+3miHRxh1Ln3dRZyI6Ty99coP9r4fXQg5HeFCbmBGfCoM0uJ5S4hKyp8d/dCaXlrTBFg1H7FJYAmCE010I4N7w+Jg7Vhr/kazJ; cn_m_s=f45iaMZwweUupgX4WQ4KM4ETJYv3kX2cqWhNxyCgwpVdxe/jMOVBC3dCOcy+zuVVQ8hOf3FxKpA=; ali_apache_track="c_mid=b2b-24919014|c_lid=haosweet"; tbsnid=L/wTnzRvkMphMdhmdLmpLeGySwk1OIyE25mgNN62TSI6sOlEpJKl9g==; __cn_logon__=true; __cn_logon_id__=haosweet; ali-ss=bG9naW5JZD1oYW9zd2VldCZsb2dpbk1lc3NhZ2VFcnJvcj0mbG9naW5TdGF0dXNSZXRNc2c9JnVzZXJJZD0yNDkxOTAxNCZsb2dpbkVycm9yVXNlck5hbWU9JmNoZWNrY29kZT0mbWVtYmVySWQ9YjJiLTI0OTE5MDE0JnNpZD01OGVmZGI3NTMxMDViNjg2ZWNlZjU1NDE5ZjQ1NDYyOSZlY29kZT1pZVNtSw==; isg=BGxsuluhHLbc1gh-fAzC2pEuPUpejRHMGizBBMatWZe60Q3b7jeYXvJz9dlM2Ugn');
$output = curl_exec($ch);
curl_close($ch);

$contents = preg_replace("/([\r\n|\n|\t| ]+)/",'',$output);
$contents = mb_convert_encoding($contents, 'gbk', 'UTF-8');
print_r($contents);
preg_match_all("/(<divclass=\"container-tag\"><ahref=\"(.*)\">)(.*)(<\/a><\/div>)/iUs",$contents,$matchrelated);

print_r($matchrelated[3]);

$etime=microtime(true);//获取程序执行结束的时间
$total=$etime-$stime; //计算差值

echo "<br />当前页面执行时间为:{$total} 秒";
?>

04-14 03:08