python学习3

破解百度翻译

import requests
import json
if __name__ == '__main__':
    #UA伪装:让爬虫对应的请求载体身份标识伪装成某一款浏览器
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36 SLBrowser/9.0.0.10191 SLBChan/103'
    }
    post_url='https://fanyi.baidu.com/sug'
    kw=input('输入字段')
    data = {
        'kw':kw
    }
    response=requests.post(url=post_url,data=data,headers=headers)
    dic_obj =response.json()
    fileName =kw+'.json'
    fp=open(fileName,'w',encoding='utf-8')
    json.dump(dic_obj,fp=fp,ensure_ascii=False)
    print('爬取数据完成')

爬取结果

3、豆瓣电影排行

import requests
import json
if __name__ == '__main__':
  #网页检查
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36 SLBrowser/9.0.0.10191 SLBChan/103'
    }
    url=' https://movie.douban.com/j/chart/top_list'
#运行界面时，进入检查界面中的XHR，找到json数据

    param = {
        'type':'24',
        'interval_id':'100:90',
        'action':'',
        'start':'0',#从库的第几部电影去取
        'limit':'20',#一次取出的个数
    }
    response = requests.get(url=url, params=param, headers=headers)
    list_data =response.json()

    fp=open('./douban.json','w',encoding='utf-8')
    json.dump(list_data,fp=fp,ensure_ascii=False)
    print('爬取数据完成')

爬取结果

json在线转化