突破Discuz!的防采集

使用httplib2访问原帖子页面（下面以http://www.dz.net/forum.php?mod=viewthread&tid=768为例），返回的是一段混淆过的js，如：

<script type="text/javascript">RKbW=function(){'RKbW';var _R=function(){return '=76'}; return _R();};function AIV(AIV_){function _A(AIV_){function ph(){return getName();}function AIV_(){}return ph();return AIV_}; return _A(AIV_);}DmZP='iew';_IX161 = 'assign';function zoQ(zoQ_){function ti(){return getName();};return ti();return 'zoQ'}function r2oe(){'return r2oe';return 'ad&'}_eloda = 'replace';F59s=function(){'return F59s';return 'p?m';};HP=function(){'return HP';return 'n';};function getName(){var caller=getName.caller;if(caller.name){return caller.name} var str=caller.toString().replace(/[\s]*/g,"");var name=str.match(/^function([^\(]+?)\(/);if(name && name[1]){return name[1];} else {return '';}}uM=function(){'return uM';return '9';};eG9=function(eG9_){'return eG9';return eG9_;};function kp(kp_){function _k(kp_){function o(){return getName();}function kp_(){}return o();return kp_}; return _k(kp_);}vD='1';BN=function(){'BN';var _B=function(){return 'r'}; return _B();};HALw='rum';_RZnE9 = 'href';o5y=function(o5y_){'return o5y';return o5y_;};function PH(){'return PH';return '.'}_BDkwZ = location;function w2(){'return w2';return '_'}KTI4=function(){'return KTI4';return '910';};_NUuAJ = window;wX=function(){'wX';var _w=function(){return 'd'}; return _w();};iyL=function(iyL_){'return iyL';return iyL_;};location.replace((function(){'return Q8mM';return '/fo'})()+HALw+PH()+AIV('Gs8')+F59s()+kp('nm')+(function(){'return njFH';return (function(){return 'd=v';})();})()+DmZP+eG9('th')+BN()+(function(){'return XD';return 'e'})()+r2oe()+zoQ('yKM')+wX()+RKbW()+'8&'+w2()+o5y('ds')+iyL('ig')+HP()+(function(){'return l26W';return '=6f'})()+uM()+(function(){'return by';return (function(){return '7';})();})()+KTI4()+vD);_NUuAJ['href']=(function(){'return Q8mM';return '/fo'})()+HALw+PH()+AIV('Gs8')+F59s()+kp('nm')+(function(){'return njFH';return (function(){return 'd=v';})();})()+DmZP;</script>

显然这样人类是无法理解的……不过使用notepad++的JSFormat插件格式化后还是能看懂的嗯-v-

实际上这是一个字符串替换然后重定向的脚本，生成原理如下(不完全按照上面的例子)：

• 原始字符串为location.href=forum.php?mod=viewthread&tid=768&_dsign=6f979101
• 随机分割这个这个串，如分成l, oc, a, tio, n., ……
• 对每一个子串替换成一个随机命名的函数，如l替换成_Oc9S()，则在脚本里加一句function _Oc9S(){return ‘l’;}以此类推
• 每个function都可能加入奇怪的例如’return l;’这样毫无意义的混淆
• 最后在末尾加上window.href=yyy，yyy为取forum.php?mod=viewthread&tid=768&_dsign=6f979101的前x个字符后得到一个子串

我大概写得不清楚……就……这么个意思……