爬取有道翻译

url：http://fanyi.youdao.com/

f12抓包

 

 

 

 有4个加密参数

ctrl + shift +f，搜索salt，找到他的加密过程

 

 可以看到r代表当前时间，i为当前时间 +上一个随机整数

t为版本信息，所以t这个参数其实是一直不变的，直接复制上就行

sign:明显是将 两端字符串和 e，i共同进行md5加密得到

在这里设置断点，单步调试

 

 e的值就等于我输入翻译的内容，接下来写代码模拟它这个加密过程就可以了

import requests
import hashlib
import time
import random
import math
def main():
    r = math.floor(time.time()*1000)
    i = r + int(random.random()*10)
    salt = i
    e = input('翻译内容:\n')
    sign =hashlib.md5(("fanyideskweb" + e + str(i) + "Nw(nmmbP%A-r6U3EUn]Aj").encode('utf-8')).hexdigest()
    url = 'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
    headers = {
    'Accept': 'application/json, text/javascript, */*; q=0.01',
    'Accept-Encoding': 'gzip, deflate',
    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
    'Connection': 'keep-alive',
    'Content-Length': '251',
    'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
    'Cookie': 'OUTFOX_SEARCH_USER_ID=-446566454@10.108.160.18; JSESSIONID=aaahlBDeJ38SEg_0B8gbx; OUTFOX_SEARCH_USER_ID_NCOO=668509478.1310366; DICT_UGC=be3af0da19b5c5e6aa4e17bd8d90b28a|; JSESSIONID=abcEY-8G7W-aseXSei_ex; _ntes_nnid=7705a1ceb59666b8545bc121466fe1ed,1586915641487; ___rl__test__cookies=1587197444202',
    'Host': 'fanyi.youdao.com',
    'Referer': 'http://fanyi.youdao.com/',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.113 Safari/537.36 Edg/81.0.416.58',
    'X-Requested-With': 'XMLHttpRequest'
    }
    data = {
    'i': e,
    'client': 'fanyideskweb',
    'salt': salt,
    'sign': sign,
    'version': '2.1',
    'keyfrom': 'fanyi.web',
    }
    html = requests.post(url,headers=headers,data=data).json()
    print(html['translateResult'][0][0]['tgt'])
    translated = html['translateResult'][0][0]['tgt']

#请求音频文件
words = translated.replace(" ",'%20')
url = 'http://tts.youdao.com/fanyivoice?word={}&le=eng&keyfrom=speaker-target'.format(words)
html =requests.get(url).content
with open('{}.mp3'.format(words),'wb') as f:
    f.write(html)

if __name__ == '__main__':
    while(1):
        main()

测试，成功