[Python知识库]Python 爬取有道翻译 （纯python）

首先要用到hashlib模块来计算遇到的md5加密问题

# coding:utf-8
import hashlib

data = 'python'
# 创建hash对象
md5 = hashlib.md5()

# 向hash对象中添加需要做hash运算的字符串
md5.update(data.encode())

# 获取字符串的hash值 hexdigest 16进制
result = md5.hexdigest()

print(result)

上源码哈

#coding:utf-8
import requests
import hashlib
import time
import random
import json

class Youdao(object):
    def __init__(self,word):
        self.url = 'https://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
        self.headers ={
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36',

            'Cookie': 'OUTFOX_SEARCH_USER_ID=284317034@10.169.0.81; JSESSIONID=aaafNS_X9rEJLgmojgj2x; OUTFOX_SEARCH_USER_ID_NCOO=1207360466.0357785; ___rl__test__cookies=1638682669421',
            
            'Referer': 'https://fanyi.youdao.com/'
        }

        self.formdata = None
        self.word = word

    def generate_formdata(self):
        '''

            ts: r = "" + (new Date).getTime(),
            salt: ts + parseInt(10 * Math.random(), 10);
            sign: n.md5("fanyideskweb" + e + i + "Y2FYu%TNSbMCxc3t2u^XT")
        '''
        ts = str(int(time.time()*1000))
        salt = ts + str(random.randint(0,9))
        tempstr = "fanyideskweb" + self.word + salt + "Y2FYu%TNSbMCxc3t2u^XT"
        md5 = hashlib.md5()
        md5.update(tempstr.encode())
        sign = md5.hexdigest()

        self.formdata = {
            "i": self.word,
            "from": "AUTO",
            "to": "AUTO",
            "smartresult": "dict",
            "client": "fanyideskweb",
            "salt": salt,
            "sign": sign,
            "lts": ts,
            "bv": "36756d23dc251cc14bf9558b9730e3a5",
            "doctype": "json",
            "version": "2.1",
            "keyfrom": "fanyi.web",
            "action": "FY_BY_REALTlME"
        }

    def get_data(self):
        response = requests.post(self.url,data=self.formdata,headers=self.headers)
        return response.content

    def run(self):
        # 爬虫思路
        # url
        # headers
        # formdata
        self.generate_formdata()
        # 发送请求， 获取响应， 解析数据
        data = self.get_data()
        # print(data)
        js = json.loads(data)
        # print(js.get('translateResult'))

        # 遍历字典列表
        # for value in js.values():
        #     print(value)

        for dict in js.get('translateResult'):
            pass
            # print(dict)
        for value in dict[0].values():
            print(value)

        # 来自test.py文件夹的测试
        # dict = {'translateResult': [[{'tgt': 'hello', 'src': '你好'}]], 'errorCode': 0, 'type': 'zh-CHS2en'}
        # a = dict.get('translateResult')
        # for b in a:
        #     pass
        #     # print(b[0])
        # for value in b[0].values():
        #     print(value)

if __name__ == '__main__':
    # youdao = Youdao('力量')
    # youdao.run()
    word = input('输入您想翻译的单词或句子：')
    youdao = Youdao(word)
    youdao.run()