1.添加请求头，防止被拦截

dic = {
    "User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) 
    AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.
    106 Safari/537.36"
}

2.预编译正则表达式，用于过滤无用信息

# cinema_name：电影名；Release_date：上映日期；
# grade：评分 ；Evaluation_number：评价人数；筛选出如下四个数据；
obj = re.compile(r'<li>.*?<div class="item">.*?<span class="title">(?P<cinema_name>.*?)'
                 r'</span>.*?<p class="">.*?<br>(?P<Release_date>.*?)&nbsp.*?'
                 r'<span class="rating_num" property="v:average">(?P<grade>.*?)</span>.*?'
                 r'<span>(?P<Evaluation_number>.*?)</span>', re.S)

3.获取网页内容

250条数据一共有十页，所以需要获取十页网页的内容

# 获取当前页数为page的网页对象并返回，这个对象包含了该网页的所有数据
def get_web_content(page):
    url = 'https://movie.douban.com/top250?start=%d&filter='%(page)
    web_content = requests.get(url, headers=dic)
    return web_content
    
# 合并十页的内容
web_content_all = get_web_content(0).text
for i in range(1,10):
    web_content_all = web_content_all + get_web_content(i*25).text

4.对获取的内容进行过滤

select_information = obj.finditer(web_content_all)

5.保存数据

# 新建一个csv文件用于保存数据
# newline="":csv文件去掉多余换行
Data_file = open("data.csv", mode="w", newline="")
csv_writer = csv.writer(Data_file)

# 将抓取的信息转换为字典存储并且写入csv文件
for i in select_information:
    dic = i.groupdict()
    dic['Release_date'] = dic['Release_date'].strip()
    csv_writer.writerow(dic.values())

Data_file.close()
print("over!")

6.完整代码

import requests
import re
import csv

# 添加请求头，防止被拦截
dic = {
    "User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.106 Safari/537.36"
}

# 获取当前页数为page的网页对象并返回，这个对象包含了该网页的所有数据
def get_web_content(page):
    url = 'https://movie.douban.com/top250?start=%d&filter='%(page)
    web_content = requests.get(url, headers=dic)
    return web_content

# compile:预编译正则表达式，可以重复使用
obj = re.compile(r'<li>.*?<div class="item">.*?<span class="title">(?P<cinema_name>.*?)'
                 r'</span>.*?<p class="">.*?<br>(?P<Release_date>.*?)&nbsp.*?'
                 r'<span class="rating_num" property="v:average">(?P<grade>.*?)</span>.*?'
                 r'<span>(?P<Evaluation_number>.*?)</span>', re.S)

# 获取10页共250数据网页内容text
web_content_all = get_web_content(0).text
for i in range(1,10):
    web_content_all = web_content_all + get_web_content(i*25).text

# 开始匹配
select_information = obj.finditer(web_content_all)

# 新建一个csv文件用于保存数据
# newline="":csv文件去掉多余换行
Data_file = open("data.csv", mode="w", newline="")
csv_writer = csv.writer(Data_file)

# 将抓取的信息转换为字典存储并且写入csv文件
for i in select_information:
    dic = i.groupdict()
    dic['Release_date'] = dic['Release_date'].strip()
    csv_writer.writerow(dic.values())

Data_file.close()
print("over!")