python 30行代码爬取豆瓣top250电影排名保存到Execl中

最新推荐文章于 2021-07-23 16:50:15 发布

一转眼又不见

最新推荐文章于 2021-07-23 16:50:15 发布

阅读量374

点赞数 1

分类专栏： python 文章标签： python 正则表达式 xml url html

本文链接：https://blog.csdn.net/no_do/article/details/115799037

版权

python 专栏收录该内容

3 篇文章 0 订阅

订阅专栏

import requests
import xlwt
from bs4 import BeautifulSoup


def analyse(url,datelist):
    header ={
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"
    }
    resp = requests.get(url,headers=header)
    soup = BeautifulSoup(resp.text,"html.parser")
    for item in soup.find_all('div',class_='item'):
        datelist.append(item.em.string)
        datelist.append(item.a.attrs["href"])
        datelist.append(item.span.string)

def save(datelist):
    k = -1
    book = xlwt.Workbook(encoding='utf8')
    sheet = book.add_sheet('豆瓣250')

    for i in range(0,250):
        for j in range(0,3):
            k =k+1
            sheet.write(i,j,datelist[k])

    book.save('豆瓣.xls')


def main():
    datelist =[]
    for i in range(0,10):
        url ="https://movie.douban.com/top250?start=" +str(i*25)
        analyse(url,datelist)

    save(datelist)

main()