pycharm爬取豆瓣电影250可视化代码并存入csv

好的，下面是完整的爬取豆瓣电影Top250并可视化的代码，并将数据存入csv文件中：

import requests
from bs4 import BeautifulSoup
import pandas as pd
import matplotlib.pyplot as plt

# 请求URL
url = 'https://movie.douban.com/top250'

# 得到页面的内容
def get_page_content(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'}
    page = requests.get(url, headers=headers).content
    return page

# 解析页面内容，获取电影信息
def parse_page_content(page):
    soup = BeautifulSoup(page, 'html.parser')
    movie_list_soup = soup.find('ol', attrs={'class': 'grid_view'})
    movie_name_list = []
    movie_rating_list = []
    movie_info_list = []

    for movie_li in movie_list_soup.find_all('li'):
        detail = movie_li.find('div', attrs={'class': 'hd'})
        movie_name = detail.find('span', attrs={'class': 'title'}).getText()
        movie_rating = movie_li.find('span', attrs={'class': 'rating_num'}).getText()
        movie_info = detail.find('span', attrs={'class': 'inq'}).getText() if detail.find('span', attrs={'class': 'inq'}) else ''
        movie_name_list.append(movie_name)
        movie_rating_list.append(movie_rating)
        movie_info_list.append(movie_info)

    return movie_name_list, movie_rating_list, movie_info_list

# 爬取豆瓣电影Top250
def get_movie_top250(url):
    movie_name_list = []
    movie_rating_list = []
    movie_info_list = []

    for i in range(0, 10):
        page = get_page_content(url + '?start=' + str(i * 25))
        movie_name, movie_rating, movie_info = parse_page_content(page)
        movie_name_list += movie_name
        movie_rating_list += movie_rating
        movie_info_list += movie_info

    # 将数据存入csv文件
    data = {'电影名称': movie_name_list, '电影评分': movie_rating_list, '电影简介': movie_info_list}
    df = pd.DataFrame(data)
    df.to_csv('douban_movie_top250.csv', index=False, encoding='utf-8-sig')

    # 数据可视化
    plt.rcParams['font.sans-serif'] = ['SimHei']
    plt.rcParams['axes.unicode_minus'] = False

    plt.figure(figsize=(10, 10))
    plt.scatter(movie_rating_list, movie_name_list, s=100)
    plt.xlabel('电影评分')
    plt.ylabel('电影名称')
    plt.title('豆瓣电影Top250')
    plt.savefig('douban_movie_top250.png', dpi=300)

    print('豆瓣电影Top250数据已保存到douban_movie_top250.csv，图片已保存到douban_movie_top250.png')

if __name__ == '__main__':
    get_movie_top250(url)

如果想要运行代码，需要安装以下库：

- requests
- BeautifulSoup
- pandas
- matplotlib

可使用以下命令安装：

pip install requests
pip install beautifulsoup4
pip install pandas
pip install matplotlib

代码执行完毕后，会在当前目录下生成douban_movie_top250.csv和douban_movie_top250.png文件，分别是豆瓣电影Top250的数据和数据可视化结果。