爬虫-有道翻译(requests)

requests模块使用:
1 导包 import requests
2 准备url地址
(请求头: 1 User-Agent 2 Cookie 3 Referer)
3 发送请求获取响应 requests.get(url)
4 提取数据
5 保存

import requests
import time, random, hashlib
from pprint import pprint
from jsonpath import jsonpath

class YouDaoSpider(object):

    def __init__(self,word):
        # 准备url地址
        self.url = "https://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule"
        self.word = word
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36",
            "Cookie": "OUTFOX_SEARCH_USER_ID=1083764993@10.108.160.100; JSESSIONID=aaa9bLvraL5cie3bdE1Px; OUTFOX_SEARCH_USER_ID_NCOO=1222829925.345313; ___rl__test__cookies=1625468463760",
            "Referer": "https://fanyi.youdao.com/"
        }
        self.form_data = {}

    def get_form_data(self):

        # 生成请求字典
        # lts的值 13位的时间戳
        lts = str(int(time.time() * 1000))
        # salt lts随机0-9数字
        random_num = random.randint(0, 9)
        salt = lts +str(random_num)
        # 使用md5生成sign的值
        my_str = "fanyideskweb" + self.word + salt + "Y2FYu%TNSbMCxc3t2u^XT"
        # 创建md5的对象
        md5 = hashlib.md5()
        # 调用md5对象中的 update方法 传入要加密的数据的bytes类型
        md5.update(my_str.encode())
        # 获取加密之后的结果
        sign = md5.hexdigest()

        # 准备请求体
        self.form_data = {
            "i": self.word,
            "from": "AUTO",
            "to": "AUTO",
            "smartresult": "dict",
            "client": "fanyideskweb",
            "salt": salt,
            "sign": sign,
            "lts": lts,
            "bv": "5b3e307b66a6c075d525ed231dcc8dcd",
            "doctype": "json",
            "version": "2.1",
            "keyfrom": "fanyi.web",
            "action": "FY_BY_REALTlME"
        }


        # 发送请求 获取响应
    def send_request(self):
        response = requests.post(self.url, data=self.form_data, headers=self.headers)
        return response.json()

        #解析数据
    def parse_data(self, data):
        # {'errorCode': 0,
        #  'smartResult': {'entries': ['', 'monkey\r\n', 'simian\r\n'], 'type': 1},
        #  'translateResult': [[{'src': '猴子', 'tgt': 'monkey'}]],
        #  'type': 'zh-CHS2en'}
        result = data.get("translateResult")[0][0].get("tgt")
        # result = jsonpath(data, "$..tgt")[0]
        print(f'{self.word} 的翻译结果是{result}')


    def save_data(self):
        pass

    def start(self):
        # 1.生成请求体字典
        self.get_form_data()
        data = self .send_request()
        pprint(data)
        self.parse_data(data)



if __name__ == '__main__':
    word = input('请输入要翻译的内容')
    spider = YouDaoSpider(word)
    spider.start()

有道翻译请求体:

sign 格式:

url:

referer:
cookie: