[Python知识库]python爬虫---突破JS加密实现桌面翻译器

网页分析

目标网站：https://fanyi.youdao.com/

进入NetWork后，找到对应的Request URL
因为有道是进行了JS加密的，所以这里我们要注意表单，然后分析表单中的一些加密信息。


同样的通过搜索找到相应的js文件，找到对应的值和加密方法。

r:时间戳，注意保留的位数
i:是r加上[0,9]之间的一个随机数
t:浏览器版本的md5加密
sign：对"fanyideskweb" + e + i + "Y2FYu%TNSbMCxc3t2u^XT"这一串数据的md5加密

代码实现

1.引入库

import requests
import time
import random
import hashlib

2.实现翻译

word = input("please input:")
def make_md5(string):
    string = string.encode('utf-8')
    md5 = hashlib.md5(string).hexdigest()
    return md5

lts = str(int(time.time() * 1000))
print(lts)
salt = lts + str(random.randint(0, 9))
print(salt)
sign =make_md5("fanyideskweb" + word + salt + "Y2FYu%TNSbMCxc3t2u^XT")
print(sign)
bv = make_md5('Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36')
data = {
    'i':word,
    'from':'AUTO',
    'to':'AUTO',
    'smartresult':'dict',
    'client':'fanyideskweb',
    'salt':salt,
    'sign':sign,
    'lts':lts,
    'bv':bv,
    'doctype':'json',
    'version':'2.1',
    'keyfrom':'fanyi.web',
    'action':'FY_BY_REALTlME',
}
headers = {
    'Accept':'application/json, text/javascript, */*; q=0.01',
    'Accept-Encoding':'gzip, deflate, br',
    'Accept-Language':'zh-CN,zh;q=0.9',
    'Cache-Control':'no-cache',
    'Connection':'keep-alive',
    'Content-Length':'236',
    'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8',
    'Cookie':'OUTFOX_SEARCH_USER_ID=1461755990@10.108.160.102; JSESSIONID=aaa2DGpVmXzJm8iDcfcUx; OUTFOX_SEARCH_USER_ID_NCOO=1322657966.5601964; fanyi-ad-id=114757; fanyi-ad-closed=1; ___rl__test__cookies=1629977928463',
    'Host':'fanyi.youdao.com',
    'Origin':'https://fanyi.youdao.com',
    'Pragma':'no-cache',
    'Referer':'https://fanyi.youdao.com/',
    'sec-ch-ua':'"Chromium";v="92", " Not A;Brand";v="99", "Google Chrome";v="92"',
    'sec-ch-ua-mobile':'?0',
    'Sec-Fetch-Dest':'empty',
    'Sec-Fetch-Mode':'cors',
    'Sec-Fetch-Site':'same-origin',
    'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36',
    'X-Requested-With':'XMLHttpRequest'
}
response = requests.post('https://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule',data=data,headers=headers).json()
response_trans = response['translateResult'][0][0]['tgt']
print(response)
print(response_trans)

这里一定要注意data和headers。

二、tkinter制作窗口

import tkinter as tk
root = tk.Tk()
root.geometry('600x300')
root.title('桌面翻译器2.0')
b1 = tk.Button(root,text='翻译',width=8,command=traslate)
b1.pack()
t1 = tk.Text(root)
t1.pack()
root.mainloop()

同时注意输入的word要替换成 t1.get(0.0,‘end’)
完整代码如下：

import requests
import time
import random
import hashlib
import tkinter as tk

#word = input("please input:")
def make_md5(string):
    string = string.encode('utf-8')
    md5 = hashlib.md5(string).hexdigest()
    return md5

#print(make_md5('12345'))
def traslate():
    lts = str(int(time.time() * 1000))
    print(lts)
    salt = lts + str(random.randint(0, 9))
    print(salt)
    sign =make_md5("fanyideskweb" + t1.get(0.0,'end') + salt + "Y2FYu%TNSbMCxc3t2u^XT")
    print(sign)
    bv = make_md5('Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36')
    data = {
        'i':t1.get(0.0,'end'),
        'from':'AUTO',
        'to':'AUTO',
        'smartresult':'dict',
        'client':'fanyideskweb',
        'salt':salt,
        'sign':sign,
        'lts':lts,
        'bv':bv,
        'doctype':'json',
        'version':'2.1',
        'keyfrom':'fanyi.web',
        'action':'FY_BY_REALTlME',
    }
    headers = {
        'Accept':'application/json, text/javascript, */*; q=0.01',
        'Accept-Encoding':'gzip, deflate, br',
        'Accept-Language':'zh-CN,zh;q=0.9',
        'Cache-Control':'no-cache',
        'Connection':'keep-alive',
        'Content-Length':'236',
        'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8',
        'Cookie':'OUTFOX_SEARCH_USER_ID=1461755990@10.108.160.102; JSESSIONID=aaa2DGpVmXzJm8iDcfcUx; OUTFOX_SEARCH_USER_ID_NCOO=1322657966.5601964; fanyi-ad-id=114757; fanyi-ad-closed=1; ___rl__test__cookies=1629977928463',
        'Host':'fanyi.youdao.com',
        'Origin':'https://fanyi.youdao.com',
        'Pragma':'no-cache',
        'Referer':'https://fanyi.youdao.com/',
        'sec-ch-ua':'"Chromium";v="92", " Not A;Brand";v="99", "Google Chrome";v="92"',
        'sec-ch-ua-mobile':'?0',
        'Sec-Fetch-Dest':'empty',
        'Sec-Fetch-Mode':'cors',
        'Sec-Fetch-Site':'same-origin',
        'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36',
        'X-Requested-With':'XMLHttpRequest'
    }
    response = requests.post('https://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule',data=data,headers=headers).json()
    response_trans = response['translateResult'][0][0]['tgt']
    print(response)
    #删掉要翻译的内容，然后显示翻译后的内容
    t1.delete(0.0,'end')
    t1.insert(0.0,response_trans)
    #return response_trans

root = tk.Tk()
root.geometry('600x300')
root.title('桌面翻译器2.0')
b1 = tk.Button(root,text='翻译',width=8,command=traslate)
b1.pack()
t1 = tk.Text(root)
t1.pack()
root.mainloop()

关注博主即可阅读全文