爬取豆瓣网站前top250电影名称和评分保存到本地excel中（附效果图和代码）

import requests
from lxml import etree
import xlwt

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36'
}

urls = ['https://movie.douban.com/top250?start={}&filter='.format(str(i * 25)) for i in range(0, 10)]
titles = []
point = []
count = []
remark = []
for url in urls:
    session = requests.Session()
    # 登录后，我们需要获取另一个网页中的内容
    response = session.get(url, headers=headers)
    a = response.text
    # 使用xpath解析从网络上获取的数据
    tree = etree.HTML(a)
    # 解析获取当页所有段子的标题
    title_list = tree.xpath("//ol[@class='grid_view']//div[@class='info']//a/span[text()][1]")
    for a in title_list:
        titles.append(a.text)
    # 解析豆瓣评分
    file_point = tree.xpath("//div[@class='star']//span[text()][1]")
    for b in file_point:
        point.append(b.text)
    # 解析电影名评价数量(解析出数量)
    flie_count = tree.xpath("//div[@class='star']//span[text()][2]")
    for i in flie_count:
        count.append(i.text)
    # 解析电影名备注
    flie_remark = tree.xpath("//p[@class='quote']//span")
    for i in flie_remark:
        remark.append(i.text)

print(len(titles), len(point), len(count), len(remark))
# 创建一个excel
workbook = xlwt.Workbook()
# 创建一个sheet页
worksheet = workbook.add_sheet('Input', 'w+b')
titiless = ['电影名称','豆瓣评分','评价人数']
for i in range(len(titiless)):
    worksheet.write(0, i, titiless[i])
for i in range (len(titles)):
    worksheet.write(1 + i, 0, titles[i])
    worksheet.write(1 + i, 1, point[i])
    worksheet.write(1 + i, 2, count[i])
    # worksheet.write(1 + i, 4, remark[i])
workbook.save(r"E:\PythonExcel\豆瓣top250.xls")