# import scrapy
# import json
# import requests
# from datetime import datetime
# from urllib.parse import urljoin
#
#
# class DoubanTVSpider(scrapy.Spider):
#     name = 'douban_tv'
#     allowed_domains = ['movie.douban.com']
#
#     # 使用start()替代已弃用的start_requests()
#     def start_requests(self):
#         headers = {
#             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 Chrome/112.0.0.0 Safari/537.36'
#         }
#         # 同时爬取电影和电视剧
#         urls = [
#             "https://movie.douban.com/j/new_search_subjects?sort=U&tag=电视剧&start=0",
#             "https://movie.douban.com/j/new_search_subjects?sort=U&tag=电影&start=0"
#         ]
#
#         for url in urls:
#             yield scrapy.Request(url, headers=headers, callback=self.parse)
#
#     def parse(self, response):
#         try:
#             data = json.loads(response.text)
#         except json.JSONDecodeError:
#             self.logger.error("JSON解析失败: %s", response.url)
#             return
#
#         for item in data.get('data', []):
#             detail_url = item.get('url')
#             if detail_url:
#                 yield scrapy.Request(
#                     detail_url,
#                     callback=self.parse_detail,
#                     meta={'item': item}
#                 )
#
#         # 分页逻辑
#         current_start = int(response.url.split('start=')[-1])
#         next_start = current_start + 20
#         if next_start < 60:
#             next_url = response.url.replace(f'start={current_start}', f'start={next_start}')
#             yield response.follow(next_url, callback=self.parse)
#
#     def parse_detail(self, response):
#         item = response.meta['item']
#
#         # 获取详细信息
#         title = item.get('title', '').strip()
#         rate = item.get('rate', '')
#         year = item.get('date', '')[:4] if item.get('date') else ''
#
#         # 从详情页获取更多信息
#         info = response.css('#info').get('')
#
#         # 获取导演
#         director = ','.join(response.css('#info .attrs a::text').getall()[:1])
#
#         # 获取演员
#         actors = ','.join(response.css('#info .actor .attrs a::text').getall())
#
#         # 获取类型
#         type_text = ','.join(response.css('#info span[property="v:genre"]::text').getall())
#
#         # 获取制片方
#         producer = response.css('#info span:contains("制片国家/地区:") + ::text').get('').strip()
#
#         # 获取剧情简介
#         synopsis = response.css('#link-report span[property="v:summary"]::text').get('').strip()
#
#         # 获取封面图片
#         cover_url = response.css('#mainpic img::attr(src)').get('')
#         cover_alt = response.css('#mainpic img::attr(alt)').get('')
#
#         # 构建API请求数据
#         api_data = {
#             'nameCn': title,
#             'nameEn': '',  # 豆瓣API没有提供英文名
#             'type': '电视剧' if '电视剧' in response.url else '电影',
#             'releaseYear': f"{year}-01-01T00:00:00" if year else None,
#             'director': director,
#             'producer': producer,
#             'actors': actors,
#             'keywords': type_text,
#             'synopsis': synopsis,
#             'coverUrl': cover_url,
#             'coverAlt': cover_alt
#         }
#
#         # 发送数据到API
#         try:
#             response = requests.post(
#                 'http://192.168.1.213:8080/flower/api/filmWorks/new',
#                 json=api_data,
#                 headers={'Content-Type': 'application/json'}
#             )
#             if response.status_code == 200:
#                 self.logger.info(f"成功保存作品: {title}")
#             else:
#                 self.logger.error(f"保存失败: {title}, 状态码: {response.status_code}")
#         except Exception as e:
#             self.logger.error(f"API请求失败: {str(e)}")
#
#     # 添加设置（可选）
#     custom_settings = {
#         'DOWNLOAD_DELAY': 2,  # 增加延迟，避免被封
#         'CONCURRENT_REQUESTS': 1,  # 限制并发请求
#         'ROBOTSTXT_OBEY': False
#     }