python爬取豆瓣top250电影数据 并分析电影类型的代码

好的，以下是相应的Python代码：

import requests
from bs4 import BeautifulSoup
import pandas as pd

url = 'https://movie.douban.com/top250'
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'}

def get_movie_type(movie_url: str) -> str:
    """获取电影类型"""
    r = requests.get(movie_url, headers=headers)
    soup = BeautifulSoup(r.text, 'lxml')
    annotations = soup.select('div#info > span[property="v:genre"]')
    return [a.string for a in annotations]

def parse_movie_page(movie_url: str) -> dict:
    """解析电影页面信息"""
    r = requests.get(movie_url, headers=headers)
    soup = BeautifulSoup(r.text, 'lxml')
    name = soup.select('span[property="v:itemreviewed"]')[0].string
    rating_num = soup.select('strong[property="v:average"]')[0].string
    director = soup.select('a[rel="v:directedBy"]')[0].string
    actors = [a.string for a in soup.select('a[rel="v:starring"]')]
    genres = get_movie_type(movie_url)
    return {'电影名称': name, '评分': rating_num, '导演': director, '主演': actors, '类型': genres}

def get_movies(pages=10):
    """获取多个页面的电影信息"""
    movie_list = []
    for i in range(pages):
        url_index = f'{url}?start={i * 25}&filter='
        r = requests.get(url_index, headers=headers)
        soup = BeautifulSoup(r.text, 'lxml')
        movies = soup.select('.grid_view li div.item > a')
        for movie in movies:
            movie_url = movie.get('href')
            movie_info = parse_movie_page(movie_url)
            movie_list.append(movie_info)
    return movie_list

def analyze_movie_type(movie_list: list):
    """分析所以电影类型"""
    result = {}
    for movie in movie_list:
        types = movie.get('类型')
        for t in types:
            if t in result:
                result[t] += 1
            else:
                result[t] = 1
    return result

if __name__ == '__main__':
    # 获取豆瓣前10页的电影信息
    movies = get_movies(10)
    # 分析电影类型
    types = analyze_movie_type(movies)
    # 转化为DataFrame
    types_df = pd.DataFrame({'类型': list(types.keys()), '数量': list(types.values())})
    # 按照数量从大到小排序
    types_df = types_df.sort_values(by='数量', ascending=False)
    print(types_df)

这段代码会爬取豆瓣电影TOP250中前10页的所有电影，然后分析电影的类型，并按照数量从大到小排序，最后输出结果。