[Python知识库]python爬取有道词典进行中英翻译

以下代码仅供学习和参考，如有侵权请联系删除

有道词典的解密说简单也很简单，说难也难。简单是js的解密简单，不像google一样复杂,
难是难在反爬虫上

请求的url要用这个链接进行post http://nmt.youdao.com/translate?smartresult=dict&smartresult=rule

一般新手小白可能就开始在{"errorCode":50}上面了,以下代码可以直接复制粘贴使用，做个记录

import hashlib,time,random
import requests
def hashlibsalt(data):
    e = "5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36"
    t=hashlib.md5(e.encode(encoding='UTF-8')).hexdigest()
    r=str(int(time.time()*1000))
    i = r+str(int(10*random.random()))
    return  {
        "ts":r,
        "bv":t,
        "salt":i,
        "sign":hashlib.md5(("fanyideskweb" + data + i + "Y2FYu%TNSbMCxc3t2u^XT").encode(encoding='UTF-8')).hexdigest()
    }

def translate(sentence):
    try:
        url ="http://nmt.youdao.com/translate?smartresult=dict&smartresult=rule"
        headers = {
        "Cookie": "OUTFOX_SEARCH_USER_ID=1076696971@10.168.8.63;JSESSIONID=aaaZ6s5m9DVmYf8g3QoDw;OUTFOX_SEARCH_USER_ID_NCOO=473292646.5080033;___rl__test__cookies=1543228484656",
        "Host": "fanyi.youdao.com",
        "Origin":"http://fanyi.youdao.com",
        "Referer":"http://fanyi.youdao.com/",
        "User-Agent": "Mozilla/5.0(WindowsNT10.0;Win64;x64)AppleWebKit/537.36(KHTML,likeGecko)Chrome/69.0.3497.100Safari/537.36OPR/56.0.3051.104X-Requested-With:XMLHttpRequest"}
        r = hashlibsalt(sentence)
        data = {
            "i":sentence,
            "from": "AUTO",
            "to": "AUTO",
            "smartresult": "dict",
            "client":"fanyideskweb",
            "salt": r['salt'],
            "sign": r['sign'],
            "lts": r['ts'],
            "bv": r['bv'],
            "doctype": "json",
            "version": "2.1",
            "keyfrom": "fanyi.web",
            "action": "FY_BY_REALTIME"
            }
        res = requests.post(url,headers=headers,data=data).json()
        if res['errorCode'] !=50:
            # re = translate(res['translateResult'][0][0]['tgt'])
            print(res['translateResult'][0][0]['tgt'])
            return res['translateResult'][0][0]['tgt']
        else:
            return ''
    except:
        return 'err'

translate("你好，世界上最好的语言")