feat: 增强反爬策略 + forexlive 迁移 investinglive

- crawler.py: 启用 magic/stealth 全自动反检测, --disable-webrtc,
  delay_before_return_html=3s, remove_consent_popups, 过滤列表页URL
- rss_crawler.py: 新增 _make_rss_client() 支持 httpx 代理,
  Google News RSS 跳过 article_url_pattern 域名过滤
- sources.yaml: investing.com 改用 Google News RSS 代理绕过Cloudflare;
  forexlive -> investinglive (域名已301重定向)
- domestic_crawl_8g.sh: HTTP_PROXY/HTTPS_PROXY 在 .env 加载前设置

Co-Authored-By: Claude <noreply@anthropic.com>

crawler/crawler.py

@@ -133,6 +133,7 @@ def _make_browser_config(source: SourceConfig) -> BrowserConfig:
         extra_args += [
             "--disable-blink-features=AutomationControlled",
             "--disable-features=IsolateOrigins,site-per-process",
+            "--disable-webrtc",  # 防止 WebRTC 泄露真实 IP
         ]
 
     # ── SOCKS5 代理 ──────────────────────────────────
@@ -147,6 +148,9 @@ def _make_browser_config(source: SourceConfig) -> BrowserConfig:
             os.environ["DISPLAY"] = _XVFB_DISPLAY
             logger.info("🖥️  headful 模式: DISPLAY=%s", _XVFB_DISPLAY)
 
+    # stealth 反检测
+    enable_stealth = (mode == "stealth") or _HEADFUL
+
     return BrowserConfig(
         browser_type="chromium",
         headless=headless,
@@ -157,18 +161,25 @@ def _make_browser_config(source: SourceConfig) -> BrowserConfig:
         light_mode=headless,
         user_agent=_USER_AGENT,
         extra_args=extra_args,
+        enable_stealth=enable_stealth,  # Playwright stealth 反检测
     )
 
 
 def _make_run_config(source: SourceConfig) -> CrawlerRunConfig:
     """抓取运行时配置"""
+    mode = source.anti_bot_mode or ""
+    is_stealth = (mode in ("stealth", "headful")) or _HEADFUL
+
     return CrawlerRunConfig(
         cache_mode=CacheMode.BYPASS,
         page_timeout=PAGE_TIMEOUT_MS,
-        wait_until="domcontentloaded",
+        wait_until="domcontentloaded",                    # networkidle 会被 Cloudflare 挑战阻塞
         scan_full_page=False,
         simulate_user=True,
         override_navigator=True,
+        magic=is_stealth,                                   # Crawl4AI 全自动反检测
+        delay_before_return_html=3.0 if is_stealth else 0.1,  # 等待 Cloudflare JS 挑战完成
+        remove_consent_popups=True,                 # 自动关闭 Cookie/隐私弹窗
     )
 
 def _extract_domain(url: str) -> str:
@@ -214,7 +225,8 @@ async def _extract_article_urls(
     )
     # 非文章技术路径
     _SKIP_PATH = re.compile(
-        r"/(manifest|robots|sitemap|_next/static|__nextjs_|favicon)"
+        r"/(manifest|robots|sitemap|_next/static|__nextjs_|favicon"
+        r"|most-popular-news|trending|popular-news|latest-news)"
         r"[/.]",
         re.IGNORECASE,
     )