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/rss_crawler.py

@@ -78,14 +78,18 @@ def _is_valid_article_url(url: str, source: SourceConfig) -> bool:
         return False
 
     # 源级 article_url_pattern 校验
-    pattern = getattr(source, "article_url_pattern", "")
-    if pattern:
-        try:
-            if not re.search(pattern, url, re.IGNORECASE):
-                logger.debug("RSS 跳过不匹配 article_url_pattern: %s", url[:80])
-                return False
-        except re.error:
-            pass  # 正则异常不阻塞
+    # Google News RSS 跳过（链接为 news.google.com 格式，不匹配源 pattern）
+    rss_url = getattr(source, "rss_url", "")
+    is_google_news = "news.google.com" in rss_url
+    if not is_google_news:
+        pattern = getattr(source, "article_url_pattern", "")
+        if pattern:
+            try:
+                if not re.search(pattern, url, re.IGNORECASE):
+                    logger.debug("RSS 跳过不匹配 article_url_pattern: %s", url[:80])
+                    return False
+            except re.error:
+                pass  # 正则异常不阻塞
 
     # 域名一致性校验（RSS 跨站污染防护）
     # 例外: Google News RSS 的链接是 news.google.com 跳转 URL，跳过域名校验
@@ -237,6 +241,20 @@ def _attr(element: ElementTree.Element, tag: str, attr: str) -> str:
 # ── 主抓取接口 ───────────────────────────────────────
 
 
+def _make_rss_client() -> httpx.Client:
+    """创建 httpx 客户端，自动配置代理"""
+    try:
+        from crawler.config import load_system_config
+        cfg = load_system_config()
+        p = cfg.get("proxy", {})
+        if p.get("enabled") and p.get("url"):
+            return httpx.Client(proxy=p["url"], follow_redirects=True, timeout=30.0)
+    except Exception:
+        pass
+    return httpx.Client(follow_redirects=True, timeout=30.0)
+
+
+
 def crawl_rss_source(source: SourceConfig) -> CrawlResult:
     """通过 RSS/Atom Feed 抓取单个新闻源。
 
@@ -268,9 +286,9 @@ def crawl_rss_source(source: SourceConfig) -> CrawlResult:
     crawl_time = start_time.isoformat()
 
     try:
-        resp = httpx.get(
+        client = _make_rss_client()
+        resp = client.get(
             rss_url,
-            follow_redirects=True,
             timeout=30.0,
             headers={
                 "User-Agent": (