（一）显示影片基本信息
访问豆瓣电影Top250（豆瓣电影 Top 250），获取每部电影的中文片名、排名、评分及其对应的链接，按照“排名-中文片名-评分-链接”的格式显示在屏幕上。
（二）存储影片详细信息
访问豆瓣电影Top250（豆瓣电影 Top 250），在问题1的基础上，获取每部电影的导演、编剧、主演、类型、上映时间、片长、评分人数以及剧情简介等信息，并将获取到的信息保存至本地文件中。
import requests
from bs4 import BeautifulSoup
import json
import time# 获取单页的电影信息
def get_movies_info_from_page(url):headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36"}response = requests.get(url, headers=headers)if response.status_code != 200:print(f"Failed to retrieve data from {url}")return []soup = BeautifulSoup(response.text, 'html.parser')movies = soup.find_all('div', class_='item')movies_info = []for movie in movies:rank = movie.find('em').get_text() # 排名title = movie.find('span', class_='title').get_text() # 中文片名rating = movie.find('span', class_='rating_num').get_text() # 评分link = movie.find('a')['href'] # 详情链接# 打印基本信息print(f"{rank} - {title} - {rating} - {link}")# 保存到列表中movies_info.append({'rank': rank,'title': title,'rating': rating,'link': link})return movies_info# 获取电影详情页的详细信息
def get_movie_detail(movie):headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36"}response = requests.get(movie['link'], headers=headers)if response.status_code != 200:print(f"Failed to retrieve details from {movie['link']}")return moviesoup = BeautifulSoup(response.text, 'html.parser')# 获取导演、编剧、主演等信息info = soup.find('div', id='info')if info:movie['director'] = info.find('a', rel='v:directedBy').get_text() if info.find('a', rel='v:directedBy') else ''movie['scriptwriters'] = ','.join([a.get_text() for a in info.find_all('a', rel=False) if '编剧' in str(a)]) # 编剧信息movie['actors'] = ','.join([a.get_text() for a in info.find_all('a', rel='v:starring')]) # 主演movie['genre'] = ','.join([a.get_text() for a in info.find_all('span', property='v:genre')]) # 类型movie['release_date'] = info.find('span', property='v:initialReleaseDate').get_text() if info.find('span', property='v:initialReleaseDate') else '' # 上映时间movie['duration'] = info.find('span', property='v:runtime').get_text() if info.find('span', property='v:runtime') else '' # 片长movie['votes'] = soup.find('span', property='v:votes').get_text() if soup.find('span', property='v:votes') else '' # 评分人数movie['summary'] = soup.find('span', property='v:summary').get_text().strip() if soup.find('span', property='v:summary') else '' # 剧情简介return movie# 爬取所有Top 250的电影信息
def scrape_douban_top_250():base_url = 'https://movie.douban.com/top250?start='all_movies = []for i in range(0, 250, 25):url = base_url + str(i)movies_info = get_movies_info_from_page(url)# 获取每部电影的详细信息for movie in movies_info:movie_detail = get_movie_detail(movie)all_movies.append(movie_detail)# 为了防止被网站封禁，添加一些延时time.sleep(2)# 保存到本地文件with open('douban_top_250_movies.json', 'w', encoding='utf-8') as f:json.dump(all_movies, f, ensure_ascii=False, indent=4)# 运行爬虫
scrape_douban_top_250()
