Pyspider+Phantomjs 遇到一个站点的浏览器检查确实不会过

看了下他的检查代码，好像是定时提交一个隐藏的表单

隐藏表单内容如下：

 <form id="challenge-form" action="/cdn-cgi/l/chk_jschl" method="get">
        <input type="hidden" name="jschl_vc" value="8638db33f4d888e137a518e882e7c8e3">
        <input type="hidden" name="pass" value="1475845385.911-E7QOUU3JrO">
        <input type="hidden" id="jschl-answer" name="jschl_answer">
 </form>

对应的检查代码如下：

<script type="text/javascript">
  //<![CDATA[
  (function(){
    var a = function() {
      try{
        return !!window.addEventListener}
      catch(e) {
        return !1}
    }
    ,
    b = function(b, c) {
    a() ? document.addEventListener("DOMContentLoaded", b, c) : document.attachEvent("onreadystatechange", b)};
    b(function(){
      var a = document.getElementById('yjs-content');
      a.style.display = 'block';
      setTimeout(function(){
        var s,t,o,p,b,r,e,a,k,i,n,g,f, tEGADKc={"UOLHSZfuv":+((!+[]+!![]+[])+(!+[]+!![]))};
        t = document.createElement('div');
        t.innerHTML="<a href='/'>x</a>";
        t = t.firstChild.href;
        r = t.match(/https?:\/\//)[0];
        t = t.substr(r.length);
        t = t.substr(0,t.length-1);
        a = document.getElementById('jschl-answer');
        f = document.getElementById('challenge-form');
        ;
        tEGADKc.UOLHSZfuv+=+((!+[]+!![]+!![]+!![]+!![]+[])+(+[]));
        tEGADKc.UOLHSZfuv+=+((!+[]+!![]+!![]+[])+(+!![]));
        tEGADKc.UOLHSZfuv+=+((!+[]+!![]+!![]+[])+(!+[]+!![]+!![]+!![]+!![]+!![]));
        tEGADKc.UOLHSZfuv*=+((!+[]+!![]+!![]+!![]+[])+(!+[]+!![]+!![]));
        tEGADKc.UOLHSZfuv-=!+[]+!![]+!![]+!![]+!![]+!![]+!![];
        tEGADKc.UOLHSZfuv*=+((!+[]+!![]+!![]+!![]+!![]+[])+(+[]));
        a.value = parseInt(tEGADKc.UOLHSZfuv, 10) + t.length;
        '; 121'
        f.submit();
      }
                 , 4000);
    }
      , false);
  }
  )();
  //]]>
</script>

binux

2016-10-09 18:32:47 +08:00

1. 用浏览器过掉验证，拷贝 cookie ，带 cookie 抓（可能 cookie 包含 ip 信息）
2.

```
class Handler(BaseHandler):
crawl_config = {
}

@every(minutes=24 * 60)
def on_start(self):
self.crawl('http://ips.chacuo.net/', callback=self.chk_jschl , fetch_type='js', js_script=r'''
function() {
var script = document.querySelector('script').textContent;
console.log(script);
script = script.match(new RegExp("setTimeout\\(function\\(\\){([\\s\\S\n]+)f.submit", 'm'))[1] + 'a.value;';
console.log(script);
return eval(script);
}
''')

@catch_status_code_error
@config(age=10 * 24 * 60 * 60)
def chk_jschl (self, response):
print response.cookies
print response.js_script_result
self.crawl('http://ips.chacuo.net/cdn-cgi/l/chk_jschl', params={
'jschl_vc': response.doc('input[name=jschl_vc]').val(),
'pass': response.doc('input[name=pass]').val(),
'jschl-answer': response.js_script_result
}, callback=self.detail_page, cookies=response.cookies, headers={
'Referer': 'http://ips.chacuo.net/'
})
```