Friendfeng
6b7ae8f26e
modified: FFAI/__pycache__/crawlers.cpython-313.pyc new file: FFAI/__pycache__/crawlers_core.cpython-313.pyc new file: 缓存文件 modified: 旧文件 new file: 爬虫文件 modified: 主文件 new file: cache/cache__E4_BA_BA_E5_B7_A5_E6_99_BA_E8_83_BD_json.txt new file: 测试文件 modified: readme.md
49 lines
1.7 KiB
Python
49 lines
1.7 KiB
Python
import os
|
|
import json
|
|
import hashlib
|
|
from datetime import datetime
|
|
|
|
class CacheManager:
|
|
def __init__(self, cache_dir=".cache"):
|
|
self.cache_dir = cache_dir
|
|
os.makedirs(cache_dir, exist_ok=True)
|
|
|
|
def _get_cache_path(self, query: str) -> str:
|
|
"""生成基于查询内容的缓存文件名"""
|
|
query_hash = hashlib.md5(query.encode('utf-8')).hexdigest()
|
|
return os.path.join(self.cache_dir, f"{query_hash}.json")
|
|
|
|
def save_to_cache(self, query: str, data: dict) -> bool:
|
|
"""保存数据到缓存（带时间戳）"""
|
|
cache_data = {
|
|
'timestamp': datetime.now().isoformat(),
|
|
'query': query,
|
|
'data': data
|
|
}
|
|
try:
|
|
with open(self._get_cache_path(query), 'w', encoding='utf-8') as f:
|
|
json.dump(cache_data, f, ensure_ascii=False, indent=2)
|
|
return True
|
|
except Exception as e:
|
|
print(f"缓存保存失败: {e}")
|
|
return False
|
|
|
|
def load_from_cache(self, query: str, max_age_hours=24) -> dict:
|
|
"""从缓存加载数据（可设置最大有效期）"""
|
|
cache_file = self._get_cache_path(query)
|
|
if not os.path.exists(cache_file):
|
|
return None
|
|
|
|
try:
|
|
with open(cache_file, 'r', encoding='utf-8') as f:
|
|
cache_data = json.load(f)
|
|
|
|
# 检查缓存有效期
|
|
cache_time = datetime.fromisoformat(cache_data['timestamp'])
|
|
if (datetime.now() - cache_time).total_seconds() > max_age_hours * 3600:
|
|
return None
|
|
|
|
return cache_data['data']
|
|
except Exception as e:
|
|
print(f"缓存读取失败: {e}")
|
|
return None |