初始化

2026-07-18 16:13:52 +08:00
parent c0070f0a5c
commit fe8b417ab6
75 changed files with 12898 additions and 1 deletions
@@ -0,0 +1,141 @@
+# 英文财经新闻源配置
+# 每个源的字段说明见 english-news-plan.md M1 章节
+
+settings:
+  concurrency: 5
+  request_delay_sec: 2
+  user_agent: "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
+
+sources:
+  - id: "reuters"
+    name: "Reuters"
+    enabled: true
+    homepage: "https://www.reuters.com/business/"
+    article_url_pattern: "/[^/]+/[^/]+/"
+    js_render: false
+    max_articles_per_run: 30
+    anti_bot_mode: "stealth"       # DataDome 反爬（Web 回退，大概率失败）
+    rss_url: "https://news.google.com/rss/search?q=site:reuters.com+business&hl=en-US&gl=US&ceid=US:en"  # Google News RSS 代理（标题+摘要，绕过 DataDome）
+    # ⚠️ Google News RSS 链接为 Google 跳转 URL，无法获取 reuters.com 原文 URL
+    # rss_crawler.py 自动识别 Google News RSS 格式，标题去 " - Reuters" 后缀
+
+  - id: "cnbc"
+    name: "CNBC"
+    enabled: true
+    homepage: "https://www.cnbc.com/world/"
+    article_url_pattern: "/\\d{4}/\\d{2}/\\d{2}/"
+    js_render: true
+    max_articles_per_run: 25
+    rss_url: "https://search.cnbc.com/rs/search/combinedcms/view.xml?partnerId=wrss01&id=100003114"  # US Top News and Analysis
+    # 其他可用频道（id 参数切换）：
+    #   id=15837362 → U.S. News
+    #   id=15839135 → Earnings
+    #   id=10000116 → Retail
+
+  - id: "marketwatch"
+    name: "MarketWatch"
+    enabled: true
+    homepage: "https://www.marketwatch.com/latest-news"
+    article_url_pattern: "/story/"
+    js_render: false
+    max_articles_per_run: 25
+    rss_url: "https://feeds.marketwatch.com/marketwatch/topstories"  # RSS 优先，绕过 DataDome
+    anti_bot_mode: "stealth"        # RSS 失败回退（headful 在无头服务器不可用）
+    # 其他可用频道：
+    #   https://feeds.marketwatch.com/marketwatch/marketpulse → MarketPulse
+    #   https://feeds.marketwatch.com/marketwatch/bulletins → Bulletins
+
+  - id: "ft"
+    name: "Financial Times"
+    enabled: true
+    homepage: "https://www.ft.com/world"
+    article_url_pattern: "/content/"
+    js_render: false
+    max_articles_per_run: 20
+    rss_url: "https://www.ft.com/rss/home"  # FT International Homepage RSS
+    # 其他可用频道：
+    #   https://www.ft.com/rss/world
+    #   https://www.ft.com/rss/companies
+    #   https://www.ft.com/rss/markets
+    # ⚠️ RSS 含摘要+缩略图，但全文仍需 Crawl4AI 抓取（FT 付费墙）
+
+  - id: "yahoo_finance"
+    name: "Yahoo Finance"
+    enabled: true
+    homepage: "https://finance.yahoo.com/news/"
+    article_url_pattern: "/(news|articles)/"   # /news/、/economy/.../articles/、/markets/.../articles/
+    js_render: true
+    max_articles_per_run: 30
+    rss_url: "https://news.yahoo.com/rss/finance"  # Yahoo Finance RSS
+
+  - id: "investing"
+    name: "Investing.com"
+    enabled: true
+    homepage: "https://www.investing.com/news/latest-news"
+    article_url_pattern: "/news/"
+    js_render: true
+    max_articles_per_run: 25
+    rss_url: "https://www.investing.com/rss/news_1063.rss"  # RSS 绕过反爬
+
+  - id: "seekingalpha"
+    name: "Seeking Alpha"
+    enabled: true
+    homepage: "https://seekingalpha.com/market-news"
+    article_url_pattern: "/news/"
+    js_render: true
+    max_articles_per_run: 20
+    anti_bot_mode: "stealth"       # 首页 OK，文章页 PerimeterX 拦截 → stealth
+    rss_url: "https://seekingalpha.com/feed.xml"  # 全站文章 RSS（标题+摘要+链接）
+
+  - id: "barrons"
+    name: "Barron's"
+    enabled: true
+    homepage: "https://www.barrons.com/latest-news"
+    article_url_pattern: "/articles/"
+    js_render: false
+    max_articles_per_run: 20
+    anti_bot_mode: "stealth"       # HTTP 403 → stealth 回退
+    # ⚠️ 无 Barron's 专属原生 RSS（2026-06-21 实测：feeds.content.dowjones.io/rss/barrons→404，feeds.a.dj.com/rss/RSSBarrons.xml→403）
+    # 替代：使用 Dow Jones RSS World News 作为兜底
+    rss_url: "https://feeds.a.dj.com/rss/RSSWorldNews.xml"  # Dow Jones World News（非 Barron's 专属）
+
+  - id: "wsj"
+    name: "Wall Street Journal"
+    enabled: true
+    homepage: "https://www.wsj.com/economy"
+    article_url_pattern: "/articles/"
+    js_render: false
+    max_articles_per_run: 20
+    anti_bot_mode: "stealth"       # DataDome → RSS 优先 + stealth 回退
+    rss_url: "https://feeds.a.dj.com/rss/RSSWorldNews.xml"  # WSJ World News
+    # 其他可用频道：
+    #   https://feeds.a.dj.com/rss/RSSMarketsMain.xml → Markets
+    #   https://feeds.a.dj.com/rss/RSSWSJD.xml → WSJ Digital (付费墙内)
+
+  - id: "economist"
+    name: "The Economist"
+    enabled: true                        # ✅ RSS 可用（2026-06-21 验证），RSS 优先；Crawl4AI 回退
+    homepage: "https://www.economist.com/finance-and-economics"
+    article_url_pattern: "/finance-and-economics/\\d{4}/\\d{2}/\\d{2}/"
+    js_render: true
+    max_articles_per_run: 15
+    anti_bot_mode: "stealth"
+    rss_url: "https://www.economist.com/finance-and-economics/rss.xml"  # Finance & economics RSS（含标题+摘要+链接）
+
+  - id: "forexlive"
+    name: "ForexLive"
+    enabled: true
+    homepage: "https://www.forexlive.com/"
+    article_url_pattern: "/(news|technical-analysis|Education)/"
+    js_render: false
+    max_articles_per_run: 20
+    rss_url: "https://www.forexlive.com/feed"  # Breaking News RSS（含正文，~91KB/次）
+
+  - id: "zerohedge"
+    name: "ZeroHedge"
+    enabled: true
+    homepage: "https://www.zerohedge.com/"
+    article_url_pattern: "/(geopolitical|markets|economics|commodities|technology|political|macroeconomics|crypto|energy|health|esg)/"
+    js_render: true
+    max_articles_per_run: 15
+    rss_url: "http://feeds.feedburner.com/zerohedge/feed"  # FeedBurner RSS（含正文，~262KB/次）