前言
我开始学爬虫的一个小愿望就是能实现自动打卡健康防疫系统（每天熬夜，早起打卡让我变得不健康了。。。。），昨天学了一下模拟登陆，但还是没成功，今天继续
一、定义时间戳
今天的目标是有道翻译，先重复老步骤
指定url，headers，这里headers里要包括cookie，user-agent,referer。具体什么时候要加入referer和cookie后续我会添加进来。可以看到，请求的方式不再是get了，而变成了post。因为翻译不同于图片的下载，存在一个动态的请求，所以可以去XHR来搜索我么要的东西。
从这张图可以看到，返回类型是json，这里我们将表单数据用data{}括起来。注意！除了变量之外都要用单引号引起来！
‘salt’: ‘16077564766152’ #是时间戳乘以1000然后再取整然（lts）后再加一个随机数 时间戳的概念在我昨天的文章里有介绍
‘i’ 就是我们要查的那个，也是变量
data={
'i': i,
'from': 'AUTO',
'to': 'AUTO',
'smartresult': 'dict',
'client': 'fanyideskweb',
'salt': d,
'sign': sign, #sign为加密内容
'lts': str(b),
'bv': 'cb2ef3d3d7314f7dee099d6b7353a673',
'doctype': 'json', #文档类型
'version': '2.1',
'keyfrom': 'fanyi.web',
'action': 'FY_BY_REALTlME' #对应的值除了变量也加单引号
}
那么根据往前推我们要定义时间戳和i
i=input("要翻译的内容 ")
# 获取时间戳
a=time.time()
b=int(a*1000) #lts
c=int(random.random()*10)
d=str(b)+str(c) #salt 根据网页上的数据分析，salt是lts的基础上加一个随机数获得的
二、加密
1.引入库
直接抓包工具按Ctrl+Shift+F，后搜索sign
可以看到这个图，找到有可能是加密方式的那句话点过去加上断点再输入一个单词翻译验证，可以发现加密是这句话：sign: n.md5(“fanyideskweb” + e + i + “Tbh5E8=q6U3EXe+&L[4c@”)
我的是在8376行，然后早找到前面的一部分
var n = function(e, t) {
return e << t | e >>> 32 - t
}
, r = function(e, t) {
var n, r, i, a, o;
return i = 2147483648 & e,
a = 2147483648 & t,
n = 1073741824 & e,
r = 1073741824 & t,
o = (1073741823 & e) + (1073741823 & t),
n & r ? 2147483648 ^ o ^ i ^ a : n | r ? 1073741824 & o ? 3221225472 ^ o ^ i ^ a : 1073741824 ^ o ^ i ^ a : o ^ i ^ a
}
, i = function(e, t, n) {
return e & t | ~e & n
}
, a = function(e, t, n) {
return e & n | t & ~n
}
, o = function(e, t, n) {
return e ^ t ^ n
}
, s = function(e, t, n) {
return t ^ (e | ~n)
}
, l = function(e, t, a, o, s, l, c) {
return e = r(e, r(r(i(t, a, o), s), c)),
r(n(e, l), t)
}
, c = function(e, t, i, o, s, l, c) {
return e = r(e, r(r(a(t, i, o), s), c)),
r(n(e, l), t)
}
, u = function(e, t, i, a, s, l, c) {
return e = r(e, r(r(o(t, i, a), s), c)),
r(n(e, l), t)
}
, d = function(e, t, i, a, o, l, c) {
return e = r(e, r(r(s(t, i, a), o), c)),
r(n(e, l), t)
}
, f = function(e) {
for (var t, n = e.length, r = n + 8, i = 16 * ((r - r % 64) / 64 + 1), a = Array(i - 1), o = 0, s = 0; s < n; )
o = s % 4 * 8,
a[t = (s - s % 4) / 4] = a[t] | e.charCodeAt(s) << o,
s++;
return t = (s - s % 4) / 4,
o = s % 4 * 8,
a[t] = a[t] | 128 << o,
a[i - 2] = n << 3,
a[i - 1] = n >>> 29,
a
}
, p = function(e) {
var t, n = "", r = "";
for (t = 0; t <= 3; t++)
n += (r = "0" + (e >>> 8 * t & 255).toString(16)).substr(r.length - 2, 2);
return n
}
, h = function(e) {
e = e.replace(/\x0d\x0a/g, "\n");
for (var t = "", n = 0; n < e.length; n++) {
var r = e.charCodeAt(n);
if (r < 128)
t += String.fromCharCode(r);
else if (r > 127 && r < 2048)
t += String.fromCharCode(r >> 6 | 192),
t += String.fromCharCode(63 & r | 128);
else if (r >= 55296 && r <= 56319) {
if (n + 1 < e.length) {
var i = e.charCodeAt(n + 1);
if (i >= 56320 && i <= 57343) {
var a = 1024 * (r - 55296) + (i - 56320) + 65536;
t += String.fromCharCode(240 | a >> 18 & 7),
t += String.fromCharCode(128 | a >> 12 & 63),
t += String.fromCharCode(128 | a >> 6 & 63),
t += String.fromCharCode(128 | 63 & a),
n++
}
}
} else
t += String.fromCharCode(r >> 12 | 224),
t += String.fromCharCode(r >> 6 & 63 | 128),
t += String.fromCharCode(63 & r | 128)
}
return t
};
md5=function(e) {
var t, n, i, a, o, s, m, g, v, y = Array();
for (e = h(e),
y = f(e),
s = 1732584193,
m = 4023233417,
g = 2562383102,
v = 271733878,
t = 0; t < y.length; t += 16)
n = s,
i = m,
a = g,
o = v,
s = l(s, m, g, v, y[t + 0], 7, 3614090360),
v = l(v, s, m, g, y[t + 1], 12, 3905402710),
g = l(g, v, s, m, y[t + 2], 17, 606105819),
m = l(m, g, v, s, y[t + 3], 22, 3250441966),
s = l(s, m, g, v, y[t + 4], 7, 4118548399),
v = l(v, s, m, g, y[t + 5], 12, 1200080426),
g = l(g, v, s, m, y[t + 6], 17, 2821735955),
m = l(m, g, v, s, y[t + 7], 22, 4249261313),
s = l(s, m, g, v, y[t + 8], 7, 1770035416),
v = l(v, s, m, g, y[t + 9], 12, 2336552879),
g = l(g, v, s, m, y[t + 10], 17, 4294925233),
m = l(m, g, v, s, y[t + 11], 22, 2304563134),
s = l(s, m, g, v, y[t + 12], 7, 1804603682),
v = l(v, s, m, g, y[t + 13], 12, 4254626195),
g = l(g, v, s, m, y[t + 14], 17, 2792965006),
m = l(m, g, v, s, y[t + 15], 22, 1236535329),
s = c(s, m, g, v, y[t + 1], 5, 4129170786),
v = c(v, s, m, g, y[t + 6], 9, 3225465664),
g = c(g, v, s, m, y[t + 11], 14, 643717713),
m = c(m, g, v, s, y[t + 0], 20, 3921069994),
s = c(s, m, g, v, y[t + 5], 5, 3593408605),
v = c(v, s, m, g, y[t + 10], 9, 38016083),
g = c(g, v, s, m, y[t + 15], 14, 3634488961),
m = c(m, g, v, s, y[t + 4], 20, 3889429448),
s = c(s, m, g, v, y[t + 9], 5, 568446438),
v = c(v, s, m, g, y[t + 14], 9, 3275163606),
g = c(g, v, s, m, y[t + 3], 14, 4107603335),
m = c(m, g, v, s, y[t + 8], 20, 1163531501),
s = c(s, m, g, v, y[t + 13], 5, 2850285829),
v = c(v, s, m, g, y[t + 2], 9, 4243563512),
g = c(g, v, s, m, y[t + 7], 14, 1735328473),
m = c(m, g, v, s, y[t + 12], 20, 2368359562),
s = u(s, m, g, v, y[t + 5], 4, 4294588738),
v = u(v, s, m, g, y[t + 8], 11, 2272392833),
g = u(g, v, s, m, y[t + 11], 16, 1839030562),
m = u(m, g, v, s, y[t + 14], 23, 4259657740),
s = u(s, m, g, v, y[t + 1], 4, 2763975236),
v = u(v, s, m, g, y[t + 4], 11, 1272893353),
g = u(g, v, s, m, y[t + 7], 16, 4139469664),
m = u(m, g, v, s, y[t + 10], 23, 3200236656),
s = u(s, m, g, v, y[t + 13], 4, 681279174),
v = u(v, s, m, g, y[t + 0], 11, 3936430074),
g = u(g, v, s, m, y[t + 3], 16, 3572445317),
m = u(m, g, v, s, y[t + 6], 23, 76029189),
s = u(s, m, g, v, y[t + 9], 4, 3654602809),
v = u(v, s, m, g, y[t + 12], 11, 3873151461),
g = u(g, v, s, m, y[t + 15], 16, 530742520),
m = u(m, g, v, s, y[t + 2], 23, 3299628645),
s = d(s, m, g, v, y[t + 0], 6, 4096336452),
v = d(v, s, m, g, y[t + 7], 10, 1126891415),
g = d(g, v, s, m, y[t + 14], 15, 2878612391),
m = d(m, g, v, s, y[t + 5], 21, 4237533241),
s = d(s, m, g, v, y[t + 12], 6, 1700485571),
v = d(v, s, m, g, y[t + 3], 10, 2399980690),
g = d(g, v, s, m, y[t + 10], 15, 4293915773),
m = d(m, g, v, s, y[t + 1], 21, 2240044497),
s = d(s, m, g, v, y[t + 8], 6, 1873313359),
v = d(v, s, m, g, y[t + 15], 10, 4264355552),
g = d(g, v, s, m, y[t + 6], 15, 2734768916),
m = d(m, g, v, s, y[t + 13], 21, 1309151649),
s = d(s, m, g, v, y[t + 4], 6, 4149444226),
v = d(v, s, m, g, y[t + 11], 10, 3174756917),
g = d(g, v, s, m, y[t + 2], 15, 718787259),
m = d(m, g, v, s, y[t + 9], 21, 3951481745),
s = r(s, n),
m = r(m, i),
g = r(g, a),
v = r(v, o);
return (p(s) + p(m) + p(g) + p(v)).toLowerCase()
}
我们刚刚找到的那句代码到这个代码块的最后一句就是md5的加密方式，而前面的段是它的对象，把这段代码命名为get_sign.js，这段代码要放的应用明天我放在评论区。
import requests
import time
import random
import execjs
url='http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule' #使用网页所提供的请求URL
headers={
'Cookie': 'OUTFOX_SEARCH_USER_ID=2006217193@10.108.160.18; OUTFOX_SEARCH_USER_ID_NCOO=302812442.2493042; JSESSIONID=aaadiUSBQLdhe5_m5Rvzx; ___rl__test__cookies=1607756476599',
'Referer': 'http://fanyi.youdao.com/',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'
}
i=input("要翻译的内容 ")
# 获取时间戳
a=time.time()
b=int(a*1000) #lts
c=int(random.random()*10)
d=str(b)+str(c) #salt 根据网页上的数据分析，salt是lts的基础上加一个随机数获得的
# 没被md5加密前的sign
sign_md5="fanyideskweb" + i + d + "Tbh5E8=q6U3EXe+&L[4c@" #IndentationError: unexpected indent 缩进错误
#初始化execjs板块
node=execjs.get()
#打开文件
ctx=node.compile(open('./get_sign.js',encoding='utf-8').read())
#
funcName = "md5('{0}')".format(sign_md5)
sign=ctx.eval(funcName)
data={
'i': i,
'from': 'AUTO',
'to': 'AUTO',
'smartresult': 'dict',
'client': 'fanyideskweb',
'salt': d,
'sign': sign, #sign为加密内容
'lts': str(b),
'bv': 'cb2ef3d3d7314f7dee099d6b7353a673',
'doctype': 'json', #文档类型
'version': '2.1',
'keyfrom': 'fanyi.web',
'action': 'FY_BY_REALTlME' #对应的值除了变量也加单引号
}
res = requests.post(url=url,headers=headers,data=data).json()
translateResult = res['translateResult'][0][0]['tgt']
print("翻译完成"+translateResult)
print(res)
这是总的代码
总结
越学到后面发现东西越多，不会的越多，不知者无畏，坚持下去！加油！
1691
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
