最帅爬虫_破解有道翻译CSS加密文件

一、爬取逻辑

基础路径：http://fanyi.youdao.com/

基于XHR文件判断这是ajax请求方式

二、代码实现

import random
import time,hashlib

import requests


def get_md5(value):
    return hashlib.md5(bytes(value,encoding='utf-8')).hexdigest()


def fanyi(kw):
    '''
    翻译单词
    :param kw: 翻译的单词内容
    :return: str
    '''
    base_url = 'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'

    ts = str(int(time.time() * 1000))
    salt = ts + str(random.randint(0,9))
    sign = get_md5("fanyideskweb" + kw + salt + "Nw(nmmbP%A-r6U3EUn]Aj")
    # print(salt)
    # print(ts)
    # print(sign)

    data = {
        'i': kw,
        'from': 'AUTO',
        'to': 'AUTO',
        'smartresult': 'dict',
        'client': 'fanyideskweb',
        'salt': salt,
        'sign': sign,
        'ts': ts,
        #324a37ffcab402e0b2c0d6b645f8543b
        'bv': '324a37ffcab402e0b2c0d6b645f8543b',
        'doctype': 'json',
        'version': '2.1',
        'keyfrom':'fanyi.web',
        'action': 'FY_BY_REALTlME',
    }
    # print(data)
    headers = {
        'Accept': 'application/json, text/javascript, */*; q=0.01',
        'Accept-Encoding': 'gzip, deflate',
        'Accept-Language': 'zh-CN,zh;q=0.9',
        #客户端
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36',
        #表单类型
        'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
        #ajax请求
        'X-Requested-With': 'XMLHttpRequest',
        #表单长度
        'Content-Length': '242',
        # 请求来自于哪里--->防盗链
        #<a href="网站B这篇新闻的内容">某明星深夜。。。。。（新闻）<>----网站a
        'Referer': 'http://fanyi.youdao.com/',#爬虫很重要的头
        'Host': 'fanyi.youdao.com',
        'Origin': 'http://fanyi.youdao.com',
        'Cookie': 'OUTFOX_SEARCH_USER_ID=299610334@10.169.0.83; OUTFOX_SEARCH_USER_ID_NCOO=1705126783.3297095; _ga=GA1.2.834458747.1587627882; JSESSIONID=aaaBwJH4pSvsj4Samx6ix; ___rl__test__cookies=1590118618294',
    }
    response = requests.post(base_url,headers=headers,data=data)

    result = ''
    # print(response.json())
    # print(response)
    json_data = response.json()
    if json_data['errorCode'] == 0:
        for data in json_data['smartResult']['entries']:
            # print(data)
            result += data
        return result
    else:
        print('请求有误！')


if __name__ == '__main__':
    kw = input('请输入你要查询的单词：')
    result = fanyi(kw)
    print(result)