求助！关于字节码无法解码成中文的问题

来源：13-12 案例总结

simon_wyk

2018-01-18

<html><script>
var arg1='D4CBD40860C10B69DA0344EF3AA5575FEEA97B6B';
var _0x4818=['\x63\x73\x4b\x48\x77\x71\x4d\x49','\x5a\x73\x4b\x4a\x77\x72\x38\x56\x65\x41\x73\x79','\x55\x63\x4b\x69\x4e\x38\x4f\x2f\x77\x70\x6c\x77\x4d\x41\x3d\x3d','\x4a\x52\x38\x43\x54\x67\x3d\x3d','\x59\x73\x4f\x6e\x62\x53\x45\x51\x77\x37\x6f\x7a\x77\x71\x5a\x4b\x65\x73\x4b\x55\x77\x37\x6b\x77\x58\x38\x4f\x52\x49\x51\x3d\x3d','\x77\x37\x6f\x56\x53\x38\x4f\x53\x77\x6f\x50\x43\x6c\x33\x6a\x43\x68\x4d\x4b\x68\x77\x36\x48\x44\x6c\x73\x4b\x58\x77\x34\x73\x2f\x59\x73\x4f\x47','\x66\xx58\x73\x4b\x5a\x50\x33\x44\x43\x6c\x63\x4b\x79\x77\x36\x48\x44\x72\x51\x3d\x3d','\x77\x6f\x77\x2b\x77\x36\x76\x44\x6d\x48\x70\x73\x77\x37\x52\x74\x77\x6f\x39\x38\x4c\x43\x37\x43\x69\x47\x37\x43\x6b\x73\x4f\x52\x54\x38\x4b\x6c\x57\x38\x4f\x35\x77\x72\x33\x44\x69\x38\x4f\x54\x48\x73\x4f\x44\x65\x48\x6a\x44\x6d\x63\x4b\x6c\x4a\x73\x4b\x71\x56\x41\x3d\x3d','\x4e\x77\x56\x2b','\x77\x37\x48\x44\x72\x63\x4b\x74\x77\x70\x4a\x61\x77\x70\x5a\x62','\x77\x70\x51\x73\x77\x71\x76\x44\x69\x48\x70\x75\x77\x36\x49\x3d','\x59\x4d\x4b\x55\x77\x71\x4d\x4a\x5a\x51\x3d\x3d','\x4b\x48\x31\x56\x4b\x63\x4f\x71\x4b\x73\x4b\x31','\x66\x51\x35\x73\x46\x55\x6b\x6b\x77\x70\x49\x3d','\x77\x72\x76\x43\x72\x63\x4f\x42\x52\x38\x4b\x6b','\x4d\x33\x77\x30\x66\x51\x3d\x3d','\x77\x36\x78\x58\x77\x71\x50\x44\x76\x4d\x4f\x46\x77\x6f\x35\x64'];(function(_0x4c97f0,_0x1742fd){var _0x4db1c=function(_0x48181e){while(--_0x48181e){_0x4c97f0['\x70\x75\x73\x68'](_0x4c97f0['\x73\x68\x69\x66\x74']());}};var _0x3cd6c6=function(){var _0xb8360b={'\x64\x61\x74\x61':{'\x6b\x65\x79':'\x63\x6f\x6f\x6b\x69\x65','\x76\x61\x6c\x75\x65':'\x74\x69\x6d\x65\x6f\x75\x74'},'\x73\x65\x74\x43\x6f\x6f\x6b\x69\x65':function(_0x20bf34,_0x3e840e,_0x5693d3,_0x5e8b26){_0x5e8b26=_0x5e8b26||{};var _0xba82f0=_0x3e840e+'\x3d'+_0x5693d3;var _0x5afe31=0x0;for(var _0x5afe31=0x0,_0x178627=_0x20bf34['\x6c\x65\x6e\x67\x74\x68'];_0x5afe31<_0x178627;_0x5afe31++){var _0x41b2ff=_0x20bf34[_0x5afe31];_0xba82f0+='\x3b\x20'+_0x41b2ff;var _0xd79219=_0x20bf34[_0x41b2ff];_0x20bf34['\x70\x75\x73\x68'](_0xd79219);_0x178627=_0x20bf34['\x6c\x65\x6e\x67\x74\x68'];if(_0xd79219!==!![]){_0xba82f0+='\x3d'+_0xd79219;}}_0x5e8b26['\x63\x6f\x6f\x6b\x69\x65']=_0xba82f0;},'\x72\x65\x6d\x6f\x76\x65\x43\x6f\x6f\x6b\x69\x65':function(){return'\x64\x65\x76';},'\x67\x65\x74\x43\x6f\x6f\x6b\x69\x65':function(_0x4a11fe,_0x189946){_0x4a11fe=_0x4a11fe||function(_0x6259a2){return _0x6259a2;};var _0x25af93=_0x4a11fe(new RegExp('\x28\xx450614){if((''+_0x450614/_0x450614)[_0x55f3('0x1c', '\x56\x32\x4b\x45')]!==0x1||_0x450614%0x14===0x0){(function(){}[_0x55f3('0x1d', '\x43\x4e\x55\x59')]((undefined+'')[0x2]+(!![]+'')[0x3]+([][_0x55f3('0x1e', '\x77\x38\x50\x52')]()+'')[0x2]+(undefined+'')[0x0]+(![]+[0x0]+String)[0x14]+(![]+[0x0]+String)[0x14]+(!![]+'')[0x3]+(!![]+'')[0x1])());}else{(function(){}['\x63\x6f\x6e\x73\x74\x72\x75\x63\x74\x6f\x72']((undefined+'')[0x2]+(!![]+'')[0x3]+([][_0x55f3('0x1f', '\x4c\x24\x28\x44')]()+'')[0x2]+(undefined+'')[0x0]+(![]+[0x0]+String)[0x14]+(![]+[0x0]+String)[0x\x50\x5e\x45\x71')]=_0x1766ff;_0x9b5e29[_0x55f3('0x2c', '\x6c\x67\x4d\x30')][_0x55f3('0x2d', '\x4c\x24\x28\x44')]=_0x1766ff;_0x9b5e29[_0x55f3('0x2f', '\x43\x5a\x63\x38')][_0x55f3('0x30', '\x57\x75\x36\x25')]=_0x1766ff;});_0x5b6351();try{return!!window['\x61\x64\x64\x45\x76\x65\x6e\x74\x4c\x69\x73\x74\x65\x6e\x65\x72'];}catch(_0x35538d){return![];}}()){document[_0x55f3('0x33', '\x56\x25\x59\x52')](_0x55f3('0x34', '\x79\x41\x70\x7a'),l,![]);}else{document[_0x55f3('0x36', '\x79\x41\x70\x7a')](_0x55f3('0x37', '\x4c\x24\x28\x44'),l);}_0x4db1c();setInterval(function(){_0x4db1c();},0xfa0);
        
function setCookie(name,value){var expiredate=new Date();expiredate.setTime(expiredate.getTime()+(600*1000));document.cookie=name+"="+value+";expires="+expiredate.toGMTString()+";max-age=600;path=/";}
function reload(x) {setCookie("acw_sc__", x);document.location.reload();}
</script></html>

上面是我爬取后的数据，已经做了解压并且已经decode解码了。中文内容还是显示的是字节码

下面是我的代码

#!/usr/bin/env Python
# coding=utf-8


import urllib.request as request
import gzip

url='https://www.itjuzi.com'
head={
     'User-Agent':'Mozilla/5.0 (Windows NT 6.2; rv:16.0) Gecko/20100101 Firefox/16.0',
     'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
     'Connection':'keep-alive','Accept-Encoding': 'utf-8'
    }
req=request.Request(url,headers=head)
response=request.urlopen(req)
data=gzip.GzipFile(fileobj=response)
html=data.read().decode('utf-8')
print(html)

写回答

1回答