迁移目录

docker/crawler/_test_fetch.py

@@ -0,0 +1,35 @@
+#!/usr/bin/env python3
+"""调试：查看页面结构"""
+from scrapling.fetchers import Fetcher
+
+url = "https://www.tennessean.com/story/news/local/2026/04/25/tennessee-lottery-results-saturday-april-25-2"
+
+page = Fetcher.get(url, follow_redirects=True, timeout=15, stealthy_headers=True, impersonate="chrome")
+print("status:", page.status)
+print()
+
+selectors_to_test = [
+    "article", "#article_content", ".article-content", ".art_content",
+    ".article_body", "#artibody", "#mp-editor",
+    ".content-article", ".article-text", "#article-container",
+    ".article-content-wrap", ".article", "#content",
+    ".post-content", ".main-content", ".TRS_Editor", ".text",
+    "[id*='article']", "[class*='article']", "[class*='art_']",
+    "[class*='content']", "[id*='content']",
+    "[class*='detail']", "[class*='news']", "[class*='body']",
+    ".rich-text", ".news-content", ".detail-content",
+    "#js_content", ".content_area", ".main-text",
+]
+for sel in selectors_to_test:
+    el = page.css(sel)
+    if el:
+        text = el.css("::text").getall()
+        joined = " ".join(t.strip() for t in text if t.strip())
+        print(f"[FOUND] {sel} -> {len(joined)}字: {joined[:200]}")
+    else:
+        print(f"[MISS]  {sel}")
+
+# 输出 HTML 前8000字符
+print("\n\n--- RAW HTML 前8000字 ---")
+html_text = str(page.html) if hasattr(page, 'html') else page.text
+print(html_text[:8000])