py15:练习之抓取有道翻译

1. JS代码slat与sign

salt、sign 加密有两种实现方式：

• 一种是通过前端 JS 实现
• 另一种是后台服务器生成加密串，并在返回响应信息时，将加密信息交给接浏览器客户端。(通过预览响应信息可知，并没有涉及 salt、sign 的信息，因此可以排除这种方法。)

1. 获取包括salt的js文件

   
   获取JS

2. 使用 Sources 选项卡将 fanyi.min.js 文件中的 JS 代码格式化输出，并使用 Ctrl+F 找到相应的 "salt" 位置

   
   image.png

---

分析salt

1. 获取所有data
2. 获取r.salt
3.证实第2步中为salt

JS源码：

    var r = function(e) {
        var t = n.md5(navigator.appVersion)
          , r = "" + (new Date).getTime()
          , i = r + parseInt(10 * Math.random(), 10);
        return {
            ts: r,
            bv: t,
            salt: i,
            sign: n.md5("fanyideskweb" + e + i + "Ygy_4c=r#e#4EX^NUGUc5")
        }
    };

2.对应的python脚本实现：

#     var r = function(e) {
#         var t = n.md5(navigator.appVersion)
#           , r = "" + (new Date).getTime()
#           , i = r + parseInt(10 * Math.random(), 10);  # 从0（包括0）往上，但是不包括1（排除1）
#         return {
#             ts: r,
#             bv: t,
#             salt: i,
#             sign: n.md5("fanyideskweb" + e + i + "Ygy_4c=r#e#4EX^NUGUc5")
#         }
#     };
"""
i: 测试12345
salt: 16618249339661 
sign: 6de81b23ff84d559dacd3e336c71c49d
lts: 1661824933966  # 13位时间戳

from: AUTO
to: AUTO
smartresult: dict
client: fanyideskweb
bv: 50b61ff102560ebc7bb0148b22d7715c
doctype: json
version: 2.1
keyfrom: fanyi.web
action: FY_BY_REALTlME
"""
import time
times = time.time()
# lts 即r.ts
lts = '%d' % (times * 1000)
print(lts)

# salt即r.salt
import random
salt = lts + str(int(random.random() * 10))
print(salt)

# sign
from hashlib import md5
word = "测试"  # 待翻译字符串
md5 = md5()
s = "fanyideskweb" + word + salt + "Ygy_4c=r#e#4EX^NUGUc5"
print(s)
md5.update(s.encode(encoding="utf-8"))  # md5加密
sign = md5.hexdigest()  # 获取加密后的值
print(sign)
# utf-8方式-： 8506ed5d39137a95f1ff1d4b907ea25d
# GBK方式-：   e0324fdc80ae27ef54808ad0b26f0b12
# GB2312方式-：ed535761cf57f69b2cfc18f89b1f4fd8
# GB18030方式：e380f52ecfc0c532438375392fbf44f1

3.爬虫

# -*- coding:utf-8 -*-
"""
@author:百草Lily
@file:test_youdao.py
@time:2022/8/30
"""
from hashlib import md5
import time
import random

import requests
from faker import Faker

fake = Faker(locale="zh_CN")
ua = fake.user_agent()


class YouDao:
    def __init__(self, word):
        self.word = word  # 待翻译
        #         # url一定要写抓包时抓到的POST请求的提交地址，但是还需要去掉 url中的“_o”，
        #         # “_o”这是一种url反爬策略，做了页面跳转，若直接访问会返回{"errorCode":50}
        # self.url = "https://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule"
        self.url = "https://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule"
        t = f"{int(time.time()*1000)}"
        self.headers = {
            "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",  # 不是json;所以不能使用json传参
            "User-Agent": ua,
            # "cookie": f"td_cookie=4070516452; OUTFOX_SEARCH_USER_ID=782221499@10.110.96.159; OUTFOX_SEARCH_USER_ID_NCOO=1261010561.9584796; ___rl__test__cookies={t}",
            # "Referer": "https://fanyi.youdao.com/",
            # "Accept-Language": "zh-CN,zh;q=0.9",
            # "Cache-Control": "no-cache",
            # "Host": "fanyi.youdao.com",
            # "Origin": "https://fanyi.youdao.com",
            # "Pragma": "no-cache",
            # "Sec-Fetch-Dest": "empty",
            # "Sec-Fetch-Mode": "cors",
            # "Sec-Fetch-Site": "same-origin",
            # "X-Requested-With": "XMLHttpRequest",
            # "sec-ch-ua": '"Chromium";v="104", " Not A;Brand";v="99", "Google Chrome";v="104"',
            # "sec-ch-ua-mobile": ?0,
            # "sec-ch-ua-platform": "Windows"
        }
        # Cookie中的OUTFOX_SEARCH_USER_ID、Referer和User-Agent三个参数也是必须的

    def get_sign(self):
        """获取请求中变化数值"""
        # lts 即r.ts
        times = time.time()
        lts = '%d' % (times * 1000)
        print(lts)

        # salt
        salt = lts + str(int(random.random() * 10))
        print(salt)

        # sign
        # word = "测试"  # 待翻译字符串
        smd5 = md5()
        s = "fanyideskweb" + self.word + salt + "Ygy_4c=r#e#4EX^NUGUc5"
        smd5.update(s.encode())  # md5加密
        sign = smd5.hexdigest()  # 获取加密后的值
        print(sign)
        return lts, salt, sign

    def get_request(self):
        """
        发起请求
        :return:
        """
        lts, salt, sign = self.get_sign()
        data = {
            "i": self.word,
            "from": "AUTO",  # 待翻译的语言类型 "zh-CHS",  #
            "to": "AUTO",  # 输出的语言类型，结果返回：type='EN2ZH_CN' "en",  # 
            "smartresult": "dict",
            "client": "fanyideskweb",
            "salt": salt,
            "sign": sign,
            "lts": lts,
            "bv": "50b61ff102560ebc7bb0148b22d7715c",
            "doctype": "json",
            "version": "2.1",
            "keyfrom": "fanyi.web",
            "action": "FY_BY_REALTlME"
        }
        # res = requests.post(self.url, json=data, headers=self.headers).json()
        resp = requests.post(self.url, data=data, headers=self.headers)
        res = resp.json()
        print(res)


if __name__ == "__main__":
    a = YouDao("test")
    a.get_request()
    # 中文翻译英文异常？
    # {'type': 'EN2ZH_CN', 'errorCode': 0, 'elapsedTime': 0, 'translateResult': [[{'src': '??', 'tgt': '?？'}]]}
    # 原因，md5加密前s的解码方式=>未解决