python爬虫豆瓣top250详细代码

你好！以下是Python爬虫豆瓣Top250电影的详细代码：

import requests
from bs4 import BeautifulSoup

header = {'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'}

def get_movie_info(url):
    html = requests.get(url, headers=header).text
    soup = BeautifulSoup(html, 'html.parser')
    # 获取电影名称
    movie_name = soup.find('span', attrs={'property': 'v:itemreviewed'}).get_text()
    # 获取电影评分
    movie_score = soup.find('strong', class_='ll rating_num').get_text()
    # 获取电影导演、演员列表
    credits = soup.find('div', class_='subject clearfix').find_all('a')
    directors = []
    actors = []
    for credit in credits:
        if 'rel' in credit.attrs and credit.attrs['rel'][0] == 'v:directedBy':
            directors.append(credit.get_text())
        elif 'rel' in credit.attrs and credit.attrs['rel'][0] == 'v:starring':
            actors.append(credit.get_text())
    # 获取电影简介
    movie_intro = soup.find('div', class_='indent', id='link-report').span.get_text().strip().replace('\n', '')
    # 获取电影其他信息
    movie_infos = soup.find('div', id='info').find_all('span')
    movie_country = ''
    movie_language = ''
    movie_runtime = ''
    for movie_info in movie_infos:
        if '制片国家/地区:' in movie_info.get_text():
            movie_country = movie_info.next_sibling.strip().replace('\n', '')
        elif '语言:' in movie_info.get_text():
            movie_language = movie_info.next_sibling.strip().replace('\n', '')
        elif '上映日期:' in movie_info.get_text():
            movie_runtime = movie_info.next_sibling.strip().replace('\n', '')
    # 输出电影信息
    print('电影名称：', movie_name)
    print('电影评分：', movie_score)
    print('导演：', directors)
    print('演员：', actors)
    print('制片国家/地区：', movie_country)
    print('语言：', movie_language)
    print('上映日期：', movie_runtime)
    print('电影简介：', movie_intro)
    print('\n')

def main():
    start = 0
    urls = ['https://movie.douban.com/top250?start=' + str(start) for start in range(0, 250, 25)]
    for url in urls:
        html = requests.get(url, headers=header).text
        soup = BeautifulSoup(html, 'html.parser')
        movie_hrefs = soup.find_all('div', class_='hd')
        for movie_href in movie_hrefs:
            movie_url = movie_href.a['href']
            get_movie_info(movie_url)

if __name__ == "__main__":
    main()

请注意，这只是简单的代码示例，如果您要爬取豆瓣Top250电影，请了解相关法律法规，遵守爬虫道德规范，尊重网站规则。