X卢小说登录(包括验证码处理)
地址:aHR0cHM6Ly91LmZhbG9vLmNvbS9yZWdpc3QvbG9naW4uYXNweA==
打开页面直接进行分析
任意输入用户名密码及验证码之后可以看到抓到的包中传输的数据明显需要的是txtPwd
进行加密分析。按ctrl+shift+f
进行搜索。
定位来到源代码中断点进行调试。
然后直接跟login_md5
函数,其中pwd
为输入的密码明文,time_stamp
为时间戳精确到秒。跟到login_md5
之后如下图
此时就可以先将js
的入口函数先进行编辑了。
var time_stamp = 1692516644, pwd = '123456';
function getpwd() {
pwd = login_md5(pwd, time_stamp)
}
接下来就是去执行然后补充缺少的函数或者变量了,这里我们一边跟栈一边补充(步骤重复,不全部演示),此处跟到login_md5
函数之后,本地执行代码报错login_md5 is not defined
,所以我们从浏览器中将这个函数抠下来放在本地。然后执行如下:
接下来抠hex_md5
函数
后续步骤重复,就不再展示图片了。代码抠完后执行如下:
与浏览器中所见一致
但是,多请求几次之后会发现ts的值是在发生变化的,也就是time_stamp
的值在变化,所以在实际代码请求的时候不能够将这个值写成一个固定值,而是要动态生成。
然后是关于验证码的识别,验证码识别推荐使用开源库进行识别,钞能力可选择百度或腾讯的AI接口。这里我们选择使用ddddocr
库进行识别,安装直接pip install ddddocr
即可,识别代码如下:
ocr = ddddocr.DdddOcr()
res = ocr.classification(img) # 识别结果
注意,并不是百分百成功,所以代码完全实现之后可能需要多运行几次。完整代码如下:
python
import time
import ddddocr
import requests
import execjs
index_url = 'https://u.faloo.com/regist/Login.aspx'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36'
}
params = {
"txtUserID": "asd854200524",
"txtPwd": "d9a04c33ecf1546446ee5f37fa34064d",
"txtPwd4temp": "",
"verifyCode": "",
"ts": "1692513466",
"t": "2",
"wx171155": "0820",
"backurl": "http://www.faloo.com/",
"mobileVerifyCode": "",
}
session = requests.session()
session.headers = headers
def validateCode():
"""识别验证码图片并保存session状态"""
img_url = 'https://uimg.faloo.com/Common/ValidateImage.aspx?vt=login_code&lc=true&u=asd854200524&height=60&width=260&m=0.22130327238038894'
img = session.get(img_url).content
with open('1.jpg', 'wb') as f:
f.write(img)
ocr = ddddocr.DdddOcr()
res = ocr.classification(img) # 识别结果
params['verifyCode'] = res
print(res)
return res
validateCode()
js_code = open('jscode.js', 'r', encoding='utf-8').read()
ts = int(time.time())
txtPwd = execjs.compile(js_code).call('getpwd', ts)
params['ts'] = ts
params['txtPwd'] = txtPwd
response = session.get(index_url, params=params)
html_text = response.content
with open('1.html', 'wb')as f:
f.write(html_text)
js代码
var hexcase = 0;
var b64pad = "";
var chrsz = 8;
function hex_md5(s) {
return binl2hex(core_md5(str2binl(s), s.length * chrsz));
}
function core_md5(x, len) {
x[len >> 5] |= 0x80 << ((len) % 32);
x[(((len + 64) >>> 9) << 4) + 14] = len;
var a = 1732584193;
var b = -271733879;
var c = -1732584194;
var d = 271733878;
for (var i = 0; i < x.length; i += 16) {
var olda = a;
var oldb = b;
var oldc = c;
var oldd = d;
a = md5_ff(a, b, c, d, x[i + 0], 7, -680876936);
d = md5_ff(d, a, b, c, x[i + 1], 12, -389564586);
c = md5_ff(c, d, a, b, x[i + 2], 17, 606105819);
b = md5_ff(b, c, d, a, x[i + 3], 22, -1044525330);
a = md5_ff(a, b, c, d, x[i + 4], 7, -176418897);
d = md5_ff(d, a, b, c, x[i + 5], 12, 1200080426);
c = md5_ff(c, d, a, b, x[i + 6], 17, -1473231341);
b = md5_ff(b, c, d, a, x[i + 7], 22, -45705983);
a = md5_ff(a, b, c, d, x[i + 8], 7, 1770035416);
d = md5_ff(d, a, b, c, x[i + 9], 12, -1958414417);
c = md5_ff(c, d, a, b, x[i + 10], 17, -42063);
b = md5_ff(b, c, d, a, x[i + 11], 22, -1990404162);
a = md5_ff(a, b, c, d, x[i + 12], 7, 1804603682);
d = md5_ff(d, a, b, c, x[i + 13], 12, -40341101);
c = md5_ff(c, d, a, b, x[i + 14], 17, -1502002290);
b = md5_ff(b, c, d, a, x[i + 15], 22, 1236535329);
a = md5_gg(a, b, c, d, x[i + 1], 5, -165796510);
d = md5_gg(d, a, b, c, x[i + 6], 9, -1069501632);
c = md5_gg(c, d, a, b, x[i + 11], 14, 643717713);
b = md5_gg(b, c, d, a, x[i + 0], 20, -373897302);
a = md5_gg(a, b, c, d, x[i + 5], 5, -701558691);
d = md5_gg(d, a, b, c, x[i + 10], 9, 38016083);
c = md5_gg(c, d, a, b, x[i + 15], 14, -660478335);
b = md5_gg(b, c, d, a, x[i + 4], 20, -405537848);
a = md5_gg(a, b, c, d, x[i + 9], 5, 568446438);
d = md5_gg(d, a, b, c, x[i + 14], 9, -1019803690);
c = md5_gg(c, d, a, b, x[i + 3], 14, -187363961);
b = md5_gg(b, c, d, a, x[i + 8], 20, 1163531501);
a = md5_gg(a, b, c, d, x[i + 13], 5, -1444681467);
d = md5_gg(d, a, b, c, x[i + 2], 9, -51403784);
c = md5_gg(c, d, a, b, x[i + 7], 14, 1735328473);
b = md5_gg(b, c, d, a, x[i + 12], 20, -1926607734);
a = md5_hh(a, b, c, d, x[i + 5], 4, -378558);
d = md5_hh(d, a, b, c, x[i + 8], 11, -2022574463);
c = md5_hh(c, d, a, b, x[i + 11], 16, 1839030562);
b = md5_hh(b, c, d, a, x[i + 14], 23, -35309556);
a = md5_hh(a, b, c, d, x[i + 1], 4, -1530992060);
d = md5_hh(d, a, b, c, x[i + 4], 11, 1272893353);
c = md5_hh(c, d, a, b, x[i + 7], 16, -155497632);
b = md5_hh(b, c, d, a, x[i + 10], 23, -1094730640);
a = md5_hh(a, b, c, d, x[i + 13], 4, 681279174);
d = md5_hh(d, a, b, c, x[i + 0], 11, -358537222);
c = md5_hh(c, d, a, b, x[i + 3], 16, -722521979);
b = md5_hh(b, c, d, a, x[i + 6], 23, 76029189);
a = md5_hh(a, b, c, d, x[i + 9], 4, -640364487);
d = md5_hh(d, a, b, c, x[i + 12], 11, -421815835);
c = md5_hh(c, d, a, b, x[i + 15], 16, 530742520);
b = md5_hh(b, c, d, a, x[i + 2], 23, -995338651);
a = md5_ii(a, b, c, d, x[i + 0], 6, -198630844);
d = md5_ii(d, a, b, c, x[i + 7], 10, 1126891415);
c = md5_ii(c, d, a, b, x[i + 14], 15, -1416354905);
b = md5_ii(b, c, d, a, x[i + 5], 21, -57434055);
a = md5_ii(a, b, c, d, x[i + 12], 6, 1700485571);
d = md5_ii(d, a, b, c, x[i + 3], 10, -1894986606);
c = md5_ii(c, d, a, b, x[i + 10], 15, -1051523);
b = md5_ii(b, c, d, a, x[i + 1], 21, -2054922799);
a = md5_ii(a, b, c, d, x[i + 8], 6, 1873313359);
d = md5_ii(d, a, b, c, x[i + 15], 10, -30611744);
c = md5_ii(c, d, a, b, x[i + 6], 15, -1560198380);
b = md5_ii(b, c, d, a, x[i + 13], 21, 1309151649);
a = md5_ii(a, b, c, d, x[i + 4], 6, -145523070);
d = md5_ii(d, a, b, c, x[i + 11], 10, -1120210379);
c = md5_ii(c, d, a, b, x[i + 2], 15, 718787259);
b = md5_ii(b, c, d, a, x[i + 9], 21, -343485551);
a = safe_add(a, olda);
b = safe_add(b, oldb);
c = safe_add(c, oldc);
d = safe_add(d, oldd);
}
return Array(a, b, c, d);
}
function md5_cmn(q, a, b, x, s, t) {
return safe_add(bit_rol(safe_add(safe_add(a, q), safe_add(x, t)), s), b);
}
function md5_ff(a, b, c, d, x, s, t) {
return md5_cmn((b & c) | ((~b) & d), a, b, x, s, t);
}
function md5_gg(a, b, c, d, x, s, t) {
return md5_cmn((b & d) | (c & (~d)), a, b, x, s, t);
}
function md5_hh(a, b, c, d, x, s, t) {
return md5_cmn(b ^ c ^ d, a, b, x, s, t);
}
function md5_ii(a, b, c, d, x, s, t) {
return md5_cmn(c ^ (b | (~d)), a, b, x, s, t);
}
function safe_add(x, y) {
var lsw = (x & 0xFFFF) + (y & 0xFFFF);
var msw = (x >> 16) + (y >> 16) + (lsw >> 16);
return (msw << 16) | (lsw & 0xFFFF);
}
function bit_rol(num, cnt) {
return (num << cnt) | (num >>> (32 - cnt));
}
function str2binl(str) {
var bin = Array();
var mask = (1 << chrsz) - 1;
for (var i = 0; i < str.length * chrsz; i += chrsz)
bin[i >> 5] |= (str.charCodeAt(i / chrsz) & mask) << (i % 32);
return bin;
}
function binl2hex(binarray) {
var hex_tab = hexcase ? "0123456789ABCDEF" : "0123456789abcdef";
var str = "";
for (var i = 0; i < binarray.length * 4; i++) {
str += hex_tab.charAt((binarray[i >> 2] >> ((i % 4) * 8 + 4)) & 0xF) + hex_tab.charAt((binarray[i >> 2] >> ((i % 4) * 8)) & 0xF);
}
return str;
}
function login_md5(pwd, datetime_num) {
return hex_md5("@345Kie(873_dfbKe>d3<.d23432=" + hex_md5("EW234@![#$&]*{,OP}Kd^w349Op+-32_" + pwd + datetime_num));
}
var pwd = 'asd2523059';
function getpwd(time_stamp) {
pwd = login_md5(pwd, time_stamp)
return pwd
}
执行后打开本地保存的页面如果呈现下方形式则证明登录成功,可以进一步请求登录后的页面。
文章来源:https://www.toymoban.com/news/detail-663501.html
如果失败的话打开本地页面会出现跳转,跳转到原登录页面,并且会出现弹窗提示用户名或密码错误或者验证码错误。请自行验证,若有任何疑惑请联系本人。文章来源地址https://www.toymoban.com/news/detail-663501.html
到了这里,关于Python爬虫实战案例——第一例的文章就介绍完了。如果您还想了解更多内容,请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章,希望大家以后多多支持TOY模板网!