import requests
import urllib.request
import bs4
import re
#import urllib3.request
import xlwt
#import sqlite3_to_mysql


def main():
    print("hello")
    baseurl = "https://movie.douban.com/top250?start="
    # 1、爬取数据
    datalist = getData(baseurl)
    savepath = ".\\豆瓣电影Top250.xls"
    # 3、保存数据
    # savedata(savepath)
    askURL("https://movie.douban.com/top250?start=0")

def askURL(url):
    head = {    #模拟浏览器头部信息，向豆瓣服务器请求发送信息
        "User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36"
    }
                #用户代理，表示告诉豆瓣服务器，我们是怎样的机器、浏览器（本质上是告诉豆瓣服务器，我们的浏览器能够接收怎样水平的文件内容
#head = '"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36"'
#url = "https://movie.douban.com/top250?start="
    request = urllib.request.Request(url,headers=head)
    html = ""
try:
    response = urllib.request.urlopen(request)
    html = response.read().decode("utf-8")
    print(html)
except urllib.error.URLError as e:
    if hasattr(e,"code"):
        print(e.code)
    if hasattr(e,"reason"):
       print(e.reason)

#return html

def getData(baseurl):
    datalist = []
    for i in range(0, 10):  # 调用获取信息的函数10次
        url = baseurl + str(i * 25)
        html = askURL(url)  # 保存获取到的网页源码

    # 2、逐一解释数据
    return datalist

    print("baseurl")

def savedata(savepath):


    if __name__ == "__main__":  # 当程序执行是
       # 调用函数
        main()