5-js反爬有道翻译

1.重要过程

2.完整代码

import requests as req
import time
import random
import hashlib

class YDSpider():
    """有道翻译"""
    
    def crawl(self, src_text):
        # 翻译的ajax接口
        url = "https://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule"
        
        headers={
            "Accept": "application/json, text/javascript, */*; q=0.01"
            , "Accept-Encoding": "gzip, deflate, br"
            , "Accept-Language": "zh,zh-CN;q=0.9,zh-TW;q=0.8,en-US;q=0.7,en;q=0.6"
            , "Connection": "keep-alive"
            , "Content-Length": "245"
            , "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8"
            , "Cookie": "OUTFOX_SEARCH_USER_ID=-1464289522@10.108.160.105; JSESSIONID=aaaopIy3ZYGbL-2a-hyPx; OUTFOX_SEARCH_USER_ID_NCOO=1343267741.5045633; fanyi-ad-id=112781; fanyi-ad-closed=1; ___rl__test__cookies=1624977496478"
            , "Host": "fanyi.youdao.com"
            , "Origin": "https://fanyi.youdao.com"
            , "Referer": "https://fanyi.youdao.com/"
            , "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
            , "X-Requested-With": "XMLHttpRequest"
            
        }
        
        """
        # 网页中的js生成规则
        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 + "Tbh5E8=q6U3EXe+&L[4c@")
        }
        """
        
        # python 模仿js生成规则
        ts = str(time.time()*1000)        
        salt = ts + str(random.randint(0, 10))
        # md5信息摘要算法
        md5 = hashlib.md5()
        enc_str = "fanyideskweb" + src_text + salt + "Tbh5E8=q6U3EXe+&L[4c@"
        md5.update(enc_str.encode( 'utf-8' ))
        sign = md5.hexdigest()

        
        data = {
            'i' : src_text,
            'from' : 'AUTO',
            'to': 'AUTO',
            'smartresult': 'dict',
            'client': 'fanyideskweb',
            ##### 以下3个是由自定义js生成规则动态生成的
            'salt': salt,
            'sign' : sign,
            'ts' : ts,
            #####
            'bv' : '6ba427a653365049d202e4d218cbb811',
            'doctype' : 'json',
            'version' : '2.1',
            'keyfrom' : 'fanyi.web',
            'action' : 'FY_BY_REALT1ME'

            
        }
        
        resp = req.post(url, headers=headers, data=data)
#        print(resp)
        content = resp.content.decode("utf-8")
        print(content)
        

if __name__ == "__main__":
    spider = YDSpider()
    spider.crawl("hi there")
    spider.crawl("the moon won't come for you")

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值