python获取豆瓣top250的电影列表2021年6月4日17:31:26

import urllib.request
from bs4 import BeautifulSoup
import json
from openpyxl import Workbook, load_workbook
import os
import io
import sys

class DouBan:
    sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf8')  # 改变标准输出的默认编码

    #添加参数
    def __init__(self):
        self.URL = "https://movie.douban.com/top250"
        self.startNumber = []
        for start in range(0,251,25):
            self.startNumber.append(start)
        self.header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36"}


    #获取电影名称
    def get_top250(self):
        wb = Workbook()  # create an excel file创建一个excel
        sheet = wb.active  # 获取活跃的sheet
        for start in self.startNumber:
            start = str(start)
            data = {}
            data['start'] = start
            data = urllib.parse.urlencode(data).encode('UTF-8')
            req = urllib.request.Request(self.URL,data,self.header)
            response = urllib.request.urlopen(req)
            html = response.read().decode("UTF-8")
            soup = BeautifulSoup(html,'html.parser')
            name = soup.select("#content > div > div.article > ol > li")
            for item in name:
             item = str(item)
             thisItem = BeautifulSoup(item, 'html.parser')
             data = []
             data.append(thisItem.select("div > div.info > div.hd > a > span:nth-child(1)")[0].get_text())
             data.append(thisItem.select("div > div.info > div.bd > p:nth-child(1)")[0].get_text().lstrip())
             data.append(thisItem.select("div > div.info > div.bd > div > span.rating_num")[0].get_text())
             sheet.append(data)#按行插入
             # print(data)
             print (str(data))
            wb.save('DouBan.xlsx')  # 保存

# 主函数
if __name__ == "__main__":
        print("开始执行....")
        cls = DouBan()
        cls.get_top250()
        print("执行结束...")

结果