20250715-66bfff96/代码实现/config.py

# -*- coding: utf-8 -*-
"""
搜索系统配置文件
"""

import os
from pathlib import Path

# 基础配置
BASE_DIR = Path(__file__).parent
DATA_DIR = BASE_DIR / "data"
EXPORT_DIR = BASE_DIR.parent / "新闻"

# 确保目录存在
DATA_DIR.mkdir(exist_ok=True)
EXPORT_DIR.mkdir(exist_ok=True)

# 数据库配置
DATABASE_CONFIG = {
    'type': 'sqlite',  # 'sqlite', 'mysql', 'postgresql'
    'sqlite': {
        'path': DATA_DIR / "search_system.db"
    },
    'mysql': {
        'host': 'localhost',
        'port': 3306,
        'user': 'root',
        'password': '',
        'database': 'search_system'
    }
}

# API配置
API_CONFIG = {
    'newsapi': {
        'key': os.getenv('NEWSAPI_KEY', ''),
        'base_url': 'https://newsapi.org/v2/',
        'rate_limit': 1000  # 每日请求限制
    },
    'twitter': {
        'bearer_token': os.getenv('TWITTER_BEARER_TOKEN', ''),
        'base_url': 'https://api.twitter.com/2/',
        'rate_limit': 300  # 每15分钟请求限制
    },
    'alpha_vantage': {
        'key': os.getenv('ALPHA_VANTAGE_KEY', ''),
        'base_url': 'https://www.alphavantage.co/query',
        'rate_limit': 5  # 每分钟请求限制
    }
}

# RSS源配置
RSS_SOURCES = {
    'finance': [
        {
            'name': 'Federal Reserve',
            'url': 'https://www.federalreserve.gov/feeds/press_all.xml',
            'authority_level': 1,
            'language': 'en'
        },
        {
            'name': 'SEC',
            'url': 'https://www.sec.gov/rss/news/press-release.xml',
            'authority_level': 1,
            'language': 'en'
        },
        {
            'name': 'Bloomberg Markets',
            'url': 'https://feeds.bloomberg.com/markets/news.rss',
            'authority_level': 2,
            'language': 'en'
        },
        {
            'name': 'Reuters Finance',
            'url': 'https://feeds.reuters.com/reuters/businessNews',
            'authority_level': 2,
            'language': 'en'
        },
        {
            'name': 'Financial Times',
            'url': 'https://www.ft.com/rss/home',
            'authority_level': 2,
            'language': 'en'
        },
        {
            'name': 'Wall Street Journal',
            'url': 'https://feeds.a.dj.com/rss/RSSMarketsMain.xml',
            'authority_level': 2,
            'language': 'en'
        }
    ],
    'ai_software': [
        {
            'name': 'arXiv Computer Science',
            'url': 'http://rss.arxiv.org/rss/cs',
            'authority_level': 1,
            'language': 'en'
        },
        {
            'name': 'Google AI Blog',
            'url': 'https://ai.googleblog.com/feeds/posts/default',
            'authority_level': 1,
            'language': 'en'
        },
        {
            'name': 'OpenAI Blog',
            'url': 'https://openai.com/blog/rss.xml',
            'authority_level': 1,
            'language': 'en'
        },
        {
            'name': 'MIT Technology Review',
            'url': 'https://www.technologyreview.com/feed/',
            'authority_level': 2,
            'language': 'en'
        },
        {
            'name': 'TechCrunch',
            'url': 'https://techcrunch.com/feed/',
            'authority_level': 2,
            'language': 'en'
        },
        {
            'name': 'The Verge',
            'url': 'https://www.theverge.com/rss/index.xml',
            'authority_level': 2,
            'language': 'en'
        }
    ],
    'manufacturing': [
        {
            'name': 'ISO News',
            'url': 'https://www.iso.org/rss/news.xml',
            'authority_level': 1,
            'language': 'en'
        },
        {
            'name': 'IEEE Spectrum',
            'url': 'https://spectrum.ieee.org/rss/fulltext',
            'authority_level': 1,
            'language': 'en'
        },
        {
            'name': 'Industry Week',
            'url': 'https://www.industryweek.com/rss.xml',
            'authority_level': 2,
            'language': 'en'
        },
        {
            'name': 'Manufacturing.net',
            'url': 'https://www.manufacturing.net/rss.xml',
            'authority_level': 3,
            'language': 'en'
        }
    ],
    'healthcare_pharma': [
        {
            'name': 'FDA News',
            'url': 'https://www.fda.gov/about-fda/contact-fda/stay-informed/rss-feeds',
            'authority_level': 1,
            'language': 'en'
        },
        {
            'name': 'NIH News',
            'url': 'https://www.nih.gov/news-events/rss',
            'authority_level': 1,
            'language': 'en'
        },
        {
            'name': 'WHO News',
            'url': 'https://www.who.int/rss-feeds',
            'authority_level': 1,
            'language': 'en'
        },
        {
            'name': 'STAT News',
            'url': 'https://www.statnews.com/feed/',
            'authority_level': 2,
            'language': 'en'
        }
    ]
}

# 搜索配置
SEARCH_CONFIG = {
    'max_results_per_source': 50,
    'search_timeout': 30,
    'min_relevance_score': 0.3,
    'default_language': 'en',
    'keywords_for_china': ['中国', '国内', 'A股', '人民币', '央行', '国务院']
}

# 文档导出配置
EXPORT_CONFIG = {
    'default_format': 'docx',
    'template_path': BASE_DIR / 'templates',
    'max_articles_per_doc': 20,
    'include_source_links': True
}

# 日志配置
LOGGING_CONFIG = {
    'level': 'INFO',
    'format': '%(asctime)s - %(name)s - %(levelname)s - %(message)s',
    'file': DATA_DIR / 'search_system.log',
    'max_size': 10 * 1024 * 1024,  # 10MB
    'backup_count': 5
}

# RSS监控配置
RSS_MONITOR_CONFIG = {
    'check_interval': 3600,  # 1小时检查一次
    'max_retries': 3,
    'timeout': 30,
    'user_agent': 'SearchSystem/1.0 (RSS Monitor)'
}