Sun*_*nse 7 javascript python-3.5
我正在尝试登录我的富国银行帐户并查看我的交易历史记录,以便我可以使用它们来跟踪我的财务状况.如果我可以访问页面的HTML,我可以执行抓取部分.我遇到的问题是到达那里,下面的代码给我带来了很多胡言乱语.
####Bring in BeautifulSoup and urllib.
import bs4
import urllib.request
import requests
####Navigate to the website.
url = 'https://connect.secure.wellsfargo.com/auth/login/do'
payload = {"j_username":"USERNAME", "j_password":"PASSWORD"}
r = requests.post(url, payload)
print(r.text)
Run Code Online (Sandbox Code Playgroud)
此代码输出以下内容:
<html><head><meta http-equiv="Pragma" content="no-cache"/>
<meta http-equiv="Expires" content="-1"/>
<meta http-equiv="CacheControl" content="no-cache"/>
<script>
(function(){
var securemsg;
var dosl7_common;
window["bobcmn"] = "1011200000002200000001300000021application/x-www-form-urlencoded3000000088adfa450300000008TSPD_101300000014%2fauth%2flogin%2fdo300000000300000006/TSPD/300000008TSPD_101300000005https3000000b6#sCmnToken#0BC26lnGAWSD9m6NkEoMZy0dIjA7Os6O4oLerWkImSHetiQqPjvoid03xpkXMNwHZ4wUmjd9+FeNk7M7zEe5ESlixC/1O8E7X61l10gL4ddUAhMNR4LaIYlGkq+hckjmRwTXudNvohk90GvOs8Ea9fFIoAAAAAE=#eCmnToken#200000000";
try{(function(){try{var jS,JS,LS=1,oS=1,OS=1,zS=1,S_=1,__=1,i_=1,I_=1,j_=1;for(var L_=0;L_<JS;++L_)LS+=2,oS+=2,OS+=2,zS+=2,S_+=2,__+=2,i_+=2,I_+=2,j_+=3;jS=LS+oS+OS+zS+S_+__+i_+I_+j_;window.i===jS&&(window.i=++jS)}catch(o_){window.i=jS}var O_=window.sdkljshr489=!0;function z_(S){window.sdkljshr489&&S&&(O_=!1);return O_}function Z_(){}z_(window[Z_.name]===Z_);z_("undefined"===window.vodsS0);window.vodsS0=null;z_(/\x3c/.test(function(){return"\x3c"})&/x3d/.test(function(){return"0";"x3d"}));
var s_=/mobi/i.test(navigator.userAgent),Si=+new Date,_i=s_?3E4:3E3;function ii(){return z_(Si+_i<(Si=+new Date))}
(function Ii(){var J=!1;function l(J){for(var l=0;J--;)l+=L(document.documentElement,null);return l}function L(J,l){var Z="vi";l=l||new z;return _S(J,function(J){J.setAttribute("data-"+Z,l.SS());return L(J,l)},null)}function z(){this.O=1;this.L=0;this._=this.O;this.j=null;this.SS=function(){this.j=this.L+this._;if(!isFinite(this.j))return this.reset(),this.SS();this.L=this._;this._=this.j;this.j=null;return this._};this.reset=function(){this.O++;this.L=0;this._=this.O}}var Z=!1;function s(J,l){var L=
document.createElement(J);l=l||document.body;l.appendChild(L);L&&L.style&&(L.style.display="none")}function iS(l,L){L=L||l;var z="|";function s(J){J=J.split(z);var l=[];for(var L=0;L<J.length;++L){var Z="",lS=J[L].split(",");for(var SS=0;SS<lS.length;++SS)Z+=lS[SS][SS];l.push(Z)}return l}var _S=0,IS="datalist,details,embed,figure,hrimg,strong,article,formaddress|audio,blockquote,area,source,input|canvas,form,link,tbase,option,details,article";IS.split(z);IS=s(IS);IS=new RegExp(IS.join(z),"g");while(IS.exec(l))IS=
new RegExp((""+new Date)[8],"g"),J&&(Z=O_),++_S;return L(_S&&1)}function _S(J,l,L){(L=L||Z)&&s("div",J);J=J.children;var z=0;for(var _S in J){L=J[_S];try{L instanceof HTMLElement&&(l(L),++z)}catch(IS){}}return z}iS(Ii,l)})();window.oi={iI:"08c787b5a40180002943d30328de8438de8cc553d459dcd4fc6c4cb17feaa34f085900356d674a1888119e0ea122f11994fc63fbabf471ce1f60053949777f087711d376633d1c30cd2e2f14295017cd8afeedacf0c4783d8b9ec0abec9808a830fa17d4cc351f649688f2b9c98cc0961ddcaf13fb0e7020486252f76f751366cdb10741f04ad6fd"};function _(S){return 753>S}function I(){var S=arguments.length;for(var J=0;J<S;++J)arguments[J]-=38;return String.fromCharCode.apply(String,arguments)}function O(S){return S.toString(36)}(function ji(J){return J?0:ji(J)*ji(J)})(ii());var v;})();}finally{sdkljshr489=false;ie9rgb4=void(0);};
eval((ie9rgb4=function (){var m='function () {/*fQb f_TcC}-di`U_V YU)bWR$+dbikuVe^SdY_^uvkdbikfQb ZCy:Cy<C-!y_C-!y?C-!+V_bufQb <O-}+<O,:C+xx<Ov<Cx-"y_Cx-"y?Cx-#+ZC-<Cx_Cx?C+gY^T_g{Y---ZCssugY^T_g{Y-xxZCvmSQdSXu_OvkgY^T_g{Y-ZCmfQb ?O-gY^T_g{cT[\\ZcXb$()-n}+Ve^SdY_^ jOuCvkgY^T_g{cT[\\ZcXb$()ssCssu?O-n!v+bUdeb^ ?OmVe^SdY_^ JOuvkmjOugY^T_gKJO{^Q]UM---JOv+jOuoe^TUVY^UTo---gY^T_g{f_TcC}v+gY^T_g{f_TcC}-^e\\\\+jOu|Lh#S|{dUcduVe^SdY_^uvkbUdeb^oLh#Somvs|h#T|{dUcduVe^SdY_^uvkbUdeb^o}o+oh#Tomvv+\r\nfQb cO-|]_RY|Y{dUcdu^QfYWQd_b{ecUb1WU^dvyCY-x^Ug 4QdUyOY-cO/#5$*#5#+Ve^SdY_^ YYuvkbUdeb^ jOuCYxOY,uCY-x^Ug 4QdUvvmuVe^SdY_^uvkfQb C-kTUSbi`d*Ve^SdY_^uCvkdbikbUdeb^ :C?>{`QbcUuVe^SdY_^uCvkC-C{c`\\Yduo\\ov+fQb :-oo+V_bufQb \\-}+\\,C{\\U^WdX+xx\\v:x-CdbY^W{Vb_]3XQb3_TUuCK\\Mv+bUdeb^ :muCvvmSQdSXu\\vkmmm+bUdeb^ C-kS_^VYWebQdY_^*C{TUSbi`duo!"#\\#$\\)\'\\))\\!!&\\!}%\\!!(\\!}!\\#$\\%(\\#$\\!!}\\!!!\\#$\\$$\\#$\\!}}\\!}!\\)(\\!!\'\\!}#\\!}#\\!}%\\!!}\\!}#\\#$\\%(\\#$\\!!}\\!!!\\#$\\$$\\#$\\!})\\!!!\\!}}\\!!\'\\!}(\\!}!\\$)\\#$\\%(\\#$\\!}!\\!!}\\)\'\\)(\\!}(\\!}!\\!}}\\#$\\$$\\#$\\!})\\!!!\\!}}\\!!\'\\!}(\\!}!\\%}\\#$\\%(\\#$\\!}!\\!!}\\)\'\\)(\\!}(\\!}!\\!}}\\#$\\$$\\#$\\!})\\!!!\\!}}\\!!\'\\!}(\\!}!\\%!\\#$\\%(\\#$\\!}!\\!!}\\)\'\\)(\\!}(\\!}!\\!}}\\#$\\$$\\#$\\!})\\!!!\\!}}\\!!\'\\!}(\\!}!\\%"\\#$\\%(\\#$\\!}!\\!!}\\)\'\\)(\\!}(\\!}!\\!}}\\#$\\!"%ovmmvuv+\r\ncUSebU]cW-kcZC*Ve^SdY_^uCvkbUdeb^ cUSebU]cWK?u"(()\'vMucUSebU]cW{jYuuOu!&}vy}vyCyOu)""v/}*!vyVe^SdY_^uvkbUdeb^ CdbY^WK9u!$}y!%"y!$)y!$\'y!}%y!$"y!#%y!%"y!}%y!$)y!#(y!#)vMu=QdXK?u"&"}&}!!vMu=QdXK?u!&%}$\'#\'#$vMuvwuOu))#v/#$"*"%&vxuOu""$v/!*}vvruOu")\'v/"%&*#""vvmvK?u)!("#)vMuoovmyjC*Ve^SdY_^uCvkbUdeb^uuCsuOu"%#v/"%%*""}vv,,uOu)$\'v/"!*"$vluCsuOu$(&v/&%"(}*&&%%%vv,,uOu)}!v/%*(vlC..uOu(()v/)*(vsuOu&&"v/&%"(}*\'##\'\'vlC..uOu%%)v/"$*#"vsuOu!&$v/"%%*#"\'vv...uOu!)"vy}vmy9}*Ve^SdY_^uCy:vkV_bufQb \\-ooy<-uOu%&)vy\r\n}v+<,CK?u!")$#))"}%vM+<xxv\\x-CdbY^WKoLe}}&&b_]3Lh&(Qb3_TUoMuCK9u!#\'y!$"y!#%y!%"y!}%y!$)y!#(y!#)y!}#y!%$vMuu<xCK?u!")$#))"}%vMz:vrCK?u!")$#))"}%vMvv+bUdeb^ \\myYZC*Ve^SdY_^uCy:vkbUdeb^ cUSebU]cW{9}uCyCK?u!")$#))"}%vMz:vmy<O*Ve^SdY_^uCy:vkYVuCK?u!")$#))"}%vMn-:K?u!")$#))"}%vMvdXb_g cUSebU]cW{:CuCvycUSebU]cW{:Cu:vyoo+V_bufQb \\-ooy<-uOu\'&#vy}v+<,CK?u!")$#))"}%vM+<xxv\\x-CdbY^WKoLe}}&&bLh&V]Le}}$#XLh&!bLe}}$#_Lh&$UoMuCK9u!#\'y\r\n!$"y!#%y!%"y!}%y!$)y!#(y!#)y!}#y!%$vMu<vN:KoLe}}&#XQbLh$#_TU1doMu<vv+bUdeb^ \\my<C*Ve^SdY_^uCy:vkbUdeb^uuC...uOu""!vy}vvxu:...uOu"")vy}vvsuOu)$&v/"!$\'$(#&$\'*$")$)&\'")%vv...uOu&$#vy}vmyO:*Ve^SdY_^uCy:vkbUdeb^uuC...uOu()(vy}vvz:suOu!}&v/$")$)&\'")%*"!$\'$(#&$\'vv...uOu#\'}vy}vmy_%*Ve^SdY_^uCy:y\\vkdbikYVuCK?u!")$#))"}%vMn-uOu("#v/""*!&vvdXb_goo+YVu:K?u!")$#))"}%vMn-uOu&}&v/(*&vvdXb_goo+fQb <-cUSebU]cW{c_uCv+<KOu()vy}M-cUSebU]cW{jCu<KOu\'(&vy}Mv+<KOu\'(#v/}*!M-cUSebU]cW{jCu<KOu)!(v/\r\n}*!Mv+<KOu)"(v/!*"M-cUSebU]cW{jCu<KOu&\'}vy"Mv+<KOu\'(%v/"*#M-cUSebU]cW{jCu<KOu!\')vy#Mv+fQb j-cUSebU]cW{c_u:vyJ-cUSebU]cW{jCujKOu\'$}vy}Mvyc-cUSebU]cW{jCujKOu(\'}v/}*!MvyYC-u\\/Ou)"&v/"!$\'$(#&$\'*$"$\'})\'"#}$*uOu)&#vy}vv...uOu$\'#vy}v+YVu\\vV_bufQb OC-Ou""!v/!%*!"+OC.-uOu"%#vy}v+OCzzvfQb CC-cUSebU]cW{<CuJ,,uOu#\'%v/$*#vNJ...uOu$#%v/%*#vyJvy\\C-cUSebU]cW{<CuYCy<KYC...uOu""#v/!!*!}vsuOu"}\'v/#*"vMvyc-cUSebU]cW{O:ucyCCN\\CvyYC-cUSebU]cW{O:uYCyOu"}%v/"&%$$#%\'&)*"!$!&$}&("vycC-cUSebU]cW{<Cuc,,uOu\'\'\'vy$vNc...uOu!\')v/\r\n%*"vycvyJC-
*************************************************************
""}"!&2) %%}%"&"6 3%21#225 2"24}2"( "22$%1)" %32#&1}$ 3"4\'661\' 2%4}36#! "34))5(2 %24515!4 )2&$3"2} 53""& \'%&11#)3 }"&4)#}1 )3})}&1) 52}5# \'"}\'&\'(% }%}}%\'!# )%26$1(" 5"2(\'1!$ \'22!"215 }32&!2#( )"4"(5)2 5%4%25}4 \'343562\' }24246"! (&4#4"4$ 6!4$5"$" &(442#6( !641(#&5 (!25!&34 6&2)"&%2 &62}\'\'5! !(2\'$\'\'\' ((}(%15& 66}6&1\'} &&}ç !!}!}2%3 (6&%)566 6(&"15&) &!&2664# !&&336$% 1}}15"\'( 4\'}44"55 $5}$(#%$ #)}#2#3" 1\'&\'"&&! 4}&}!&6\' $)&)$\'$4 #5&5\'\'42 154!&1$1 4)4&%143 $}46}2&& #\'4(#26} 1)2315%# 4522)53% $\'2"36\'6 #}2%665) 24246"!3 31213"(1 %#2#)##} "$2$1#1& 214}#&}% 344\'}&)# %$45%\'") "#4)&\'26 2#&&\'1"5 3$&!$12( %4&(!2}" "1&6"2)$ 2$}225#\' 3#}3(51! %1}%46!2 "4}"56(4oK?u!\'$#))!)(#vMuuu\\ON\r\n9CK9u!#\'y!$"y!#%y!%"y!}%y!$)y!#(y!#)y!}#y!%$vMu\\vvsuOu$&&v/"%%*#\'!vvwuOu\'!!v/)*&vyOu"}!v/(*!!v+\\ON-uOu$!$vyz!v+\\O-=QdXK?u!##($vMu\\Ov+\\On-`QbcU9^duJv/uJCxxycUdDY]U_eduCyuOu!#}vy}vvv*:uvmU\\cU :uvmVe^SdY_^ :uvkfQb C-cUSebU]cWK?u!#"$()#vMu:Ox9u)&vxcxoLe}}#QoxYCx9u)&vx\\OyoLh#}Le}}##ov+T_c\\\'OS_]]_^{9Ju<yCyooyOu"($v/%5#*$}\'#yYYuvvmV_bufQb \\-cUSebU]cW{?CugY^T_g{_Y{Y9yoLe}}#}Lh#!ovy\\-T_c\\\'OS_]]_^{::u\\yn!vy<-cUSebU]cW{:Cu\\KOu&#"vy}Mvy\r\nj-\\KOu!!#v/!*}MyJ-\\KOu$&v/"*!Myc-\\KOu!)%v/#*"MyYC-\\KOu&&#vy$MyOC-\\KOu(%$vy%MyCC-\\KOu$}\'v/&*#MK9u!#\'y!$"y!#%y!%"y!}%y!$)y!#(y!#)y!}#y!%$vMuuOu$$&vy}vvy\\C-1bbQiujvycC-=QdXK?u##")&vMuCCzOCKoLe}}&#Lh&(Le}}&!Lh\'"Le}}$#Lh&VLe}}&$Lh&%Le}}$!Lh\'$oMuuOu&%$vy}vvxuOu!)"v/!*}vyjvyJC-uOu\'"%vy}v+JC,j+JCxxv\\CKJCM-OC+fQb JC-uOu)"}vy}vy:Oy9Cy\\O+cUdDY]U_eduCyuOu"\'\'vy}vvmv+\r\nVe^SdY_^ OuCvkbUdeb^ \'%#.CmVe^SdY_^ 9uvkfQb C-QbWe]U^dc{\\U^WdX+V_bufQb :-}+:,C+xx:vQbWe]U^dcK:Mz-#(+bUdeb^ CdbY^W{Vb_]3XQb3_TU{Q``\\iuCdbY^WyQbWe]U^dcvmVe^SdY_^ ?uCvkbUdeb^ C{d_CdbY^Wu#&vmuVe^SdY_^ ZYu:vkbUdeb^ :/}*ZYu:vwZYu:vmvuYYuvv+fQb f+mvuv+mVY^Q\\\\ikcT[\\ZcXb$()-VQ\\cU+YU)bWR$-f_YTu}v+m+*/;}'.slice(15,-4);for(var i=0,c=8,j=0,l,r='';l=m.charCodeAt(i);++i)c=String.fromCharCode(l<33||l>=126?l:(93+l-((-76E-3+''+({}).a).slice(7).charCodeAt(j%'1')))%93+33),r+=c,j-=c.indexOf('\x0d');return r;})());
})();
</script>
<noscript>Please enable JavaScript to view the page content.</noscript>
</head><body>
</body></html>
Run Code Online (Sandbox Code Playgroud)
我为可怕的格式道歉,但我不知道如何处理它.另外,为了长度的缘故,我在中间删除了一个用星号代替的大的任意部分.
对我而言,我看到的关键是"请启用JavaScript以查看页面内容." 这个输出实际上是JS吗?我如何处理Python的任何内容?我根本不知道这告诉我什么,我非常感谢你能提供的任何帮助.
谢谢.
Bac*_*mon 19
我知道已经花了很多时间,但我可以在这里给出一些关闭.您所看到的是由F5 Networks,Inc.的优秀人员销售的机器人失败代码,旨在防止天真的网络浏览器和抓取工具访问使用它的网站.
简而言之,这是混淆的Javascript,它通过一系列迭代步骤来计算值,这些步骤执行各种特定于浏览器的Javascript功能,并利用一些相当粗鲁的Javascript语言行为.该值将作为cookie发送回Wells Fargo,并作为导航所需的部分网络表单.只使用无头浏览器不会削减它 - 计算中有一些技巧专门用于对抗无头浏览器和与它们一起使用的Javascript引擎.错过任何技巧都不会导致任何失败; 相反,它会以一种让你难以辨别错过的方式抛弃最终结果.
从理论上讲,它可以破译代码并用您选择的语言模拟所有计算; 我知道数据汇总公司写的一个成功的对策,但该代码不公开供公众阅读.或者,您可以在JS解释器中找出正确执行它所需的内容.我不记得所有的细节,但它比看起来容易.您无需对整个工程进行逆向工程,只需在正确的环境中运行即可.您需要一个虚拟窗口对象和更多的虚拟对象,无论代码正在寻找什么,例如您的环境中的navigator.userAgent,还有其他东西.
出于实际目的,编写对策可能不值得.如果您是一个组织,请要列入白名单.
如果你有兴趣的挑战,这里是一个(也许明显)的起点-乱码的长串eval((ie9rgb4=function (){var m='function ()... .slice...一部分被加密的代码.紧随其后的for循环包含字符转换.您可以复制在该循环中执行的操作以解密第一级混淆.在调试器处于活动状态的情况下,通过普通浏览器登录该站点,观察发送的请求和cookie,以了解您正在寻找的最终目标,并尝试将其与您看到的JS代码相关联.
您可能还会发现以下值的映射在某些方面很有用:
{"$$$", "7"},
{"$$$$", "f"},
{"$$$_", "e"},
{"$$_", "6"},
{"$$_$", "d"},
{"$$__", "c"},
{"$_", "constructor"},
{"$_$", "5"},
{"$_$$", "b"},
{"$_$_", "a"},
{"$__", "4"},
{"$__$", "9"},
{"$___", "8"},
{"_", "u"},
{"_$", "o"},
{"_$$", "3"},
{"_$_", "2"},
{"__", "t"},
{"__$", "1"},
{"___", "0"}
Run Code Online (Sandbox Code Playgroud)
一些使用 javascript 的网站无法仅通过下载 html 并将其传递给 html 解析器来抓取,因为内容根本不存在。通常发生这种情况是因为页面包含一个脚本,该脚本下载真实信息并将其插入到 DOM 树中。
在这种情况下,仅仅下载网站是不够的,您需要一个支持 JavaScript 的 Web 浏览器引擎,并且可以通过 Python 进行控制。
这里有一个可以用于此目的的项目列表: https: //github.com/dhamaniasad/HeadlessBrowsers,支持不同的编程语言。我使用过 Selenium,它工作得很好,但我不确定对 Python 3.5 的支持。