Files
usa/crawler/config.py
2026-03-02 11:28:13 +08:00

50 lines
1.6 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# -*- coding: utf-8 -*-
"""爬虫配置"""
import os
from pathlib import Path
# 数据库路径(与 server 共用 SQLite
PROJECT_ROOT = Path(__file__).resolve().parent.parent
DB_PATH = os.environ.get("DB_PATH", str(PROJECT_ROOT / "server" / "data.db"))
# Node API 地址(用于通知推送)
API_BASE = os.environ.get("API_BASE", "http://localhost:3001")
# 抓取间隔(秒)
CRAWL_INTERVAL = int(os.environ.get("CRAWL_INTERVAL", "300"))
# RSS 源:世界主流媒体,覆盖美伊/中东多视角
RSS_FEEDS = [
# 美国
"https://feeds.reuters.com/reuters/topNews",
"https://rss.nytimes.com/services/xml/rss/nyt/World.xml",
# 英国
"https://feeds.bbci.co.uk/news/world/rss.xml",
"https://feeds.bbci.co.uk/news/world/middle_east/rss.xml",
"https://www.theguardian.com/world/rss",
# 法国
"https://www.france24.com/en/rss",
# 德国
"https://rss.dw.com/xml/rss-en-world",
# 俄罗斯
"https://tass.com/rss/v2.xml",
"https://www.rt.com/rss/",
# 中国
"https://english.news.cn/rss/world.xml",
"https://www.cgtn.com/rss/world",
# 伊朗
"https://www.presstv.ir/rss",
# 卡塔尔(中东)
"https://www.aljazeera.com/xml/rss/all.xml",
"https://www.aljazeera.com/xml/rss/middleeast.xml",
]
# 关键词过滤:至少匹配一个才会入库
KEYWORDS = [
"iran", "iranian", "tehran", "以色列", "israel",
"usa", "us ", "american", "美军", "美国",
"middle east", "中东", "persian gulf", "波斯湾",
"strike", "attack", "military", "missile", "", "nuclear",
"carrier", "航母", "houthi", "胡塞", "hamas",
]