python爬虫top250电影数据-CSDN博客

之前看到的我改了一下多了很多东西

import requests
from bs4 import BeautifulSoup
from openpyxl import Workbook
from openpyxl.styles import Font
import re

def extract_movie_info(info):
    # 使用正则表达式提取信息
    pattern = re.compile(r'导演: (.*?)\s*主演: (.*?)\s*(\d{4})\s*/\s*(.*?)\s*/\s*(.*)')
    match = pattern.match(info)
    
    if match:
        director = match.group(1).strip()
        actors = match.group(2).strip()
        year = match.group(3).strip()
        country = match.group(4).strip()
        genre = match.group(5).strip()
        return director, actors, year, country, genre
    else:
        return None

def douban_top250():
    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/114.0.0.0 Safari/537.36 Edg/114.0.1823.79'}

    movies = []

    for start_num in range(0, 250, 25):
        page_url = f'{url}?start={start_num}'
        response = requests.get(page_url, headers=headers)
        soup = BeautifulSoup(response.text, 'html.parser')

        for movie in soup.select('.item'):
            title = movie.select_one('.title').text.strip()
            rating = movie.select_one('.rating_num').text.strip()
            
            # 获取导演、主演和其他信息
            info = movie.select_one('p').text.strip()
            movie_info = extract_movie_info(info)
            
            if movie_info:
                director, actors, year, country, genre = movie_info
                movies.append((title, rating, director, actors, year, country, genre))

    return movies

def create_excel(movies):
    wb = Workbook()
    ws = wb.active

    title_font = Font(color='FF0000', bold=True)
    ws.append(['电影名称', '评分', '导演', '主演', '年份', '国家', '类型'])

    for cell in ws[1]:
        cell.font = title_font

    for movie in movies:
        ws.append(movie)

    wb.save('豆瓣_top250.xlsx')

if __name__ == '__main__':
    movies = douban_top250()
    create_excel(movies)
    print('Excel文件已生成。')