python爬取豆瓣电影top250数据可视化并存入csv

好的，我可以为您提供代码参考。首先需要安装相关的库：requests、BeautifulSoup、pandas、matplotlib。

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

# 获取电影信息
def get_movie_info(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/537.3'}
    response = requests.get(url, headers=headers)
    soup = BeautifulSoup(response.text, 'html.parser')
    movie_list = soup.find_all('div', class_='hd')
    info_list = []
    for movie in movie_list:
        title = movie.a.span.text.strip()  # 电影名称
        link = movie.a['href']  # 电影链接
        rating = movie.parent.find('span', class_='rating_num').text  # 评分
        rating_num = movie.parent.find('div', class_='star').find_all('span')[-1].text[:-3]  # 评分人数
        info_list.append([title, link, float(rating), int(rating_num)])
    return info_list

# 获取所有电影信息
def get_all_movie_info():
    url = 'https://movie.douban.com/top250'
    info_list = []
    for i in range(10):
        page_url = url + f'?start={i*25}'
        info_list += get_movie_info(page_url)
    return info_list

# 可视化电影评分分布
def plot_rating_distribution(data):
    plt.hist(data, bins=10, range=(0, 10), color='b', alpha=0.5)
    plt.xlabel('Rating')
    plt.ylabel('Number of Movies')
    plt.title('Distribution of Movie Ratings')
    plt.savefig('rating_distribution.png')
    plt.show()

# 存储电影信息到csv文件
def save_to_csv(data):
    df = pd.DataFrame(data, columns=['Title', 'Link', 'Rating', 'RatingNum'])
    df.to_csv('movie_info.csv', index=False)

if __name__ == '__main__':
    movie_info = get_all_movie_info()
    save_to_csv(movie_info)
    ratings = [info[2] for info in movie_info]
    plot_rating_distribution(ratings)

以上代码中，`get_movie_info(url)`函数用于获取单页电影信息，`get_all_movie_info()`函数用于获取所有电影信息，`save_to_csv(data)`函数用于将数据存储到csv文件中，`plot_rating_distribution(data)`函数用于绘制电影评分分布直方图。最后在主函数中调用这些函数即可。