更新: 21 个文件 - 2026-03-17 00:00:00

scripts/lab/browser.py

@@ -25,8 +25,12 @@ def capture(url: str, run_dir: Path, prefix: str = "baseline") -> Dict[str, Any]
     dom_path = assets_dir / f"{prefix}-dom.html"
     console_path = run_dir / "logs" / f"{prefix}-console.json"
     network_path = run_dir / "logs" / f"{prefix}-network.json"
+    page_path = run_dir / "logs" / f"{prefix}-page.json"
     console_messages: List[Dict[str, Any]] = []
     requests_seen: List[Dict[str, Any]] = []
+    page_title = ""
+    page_body_excerpt = ""
+    final_url = url
     try:
         with sync_playwright() as p:
             browser = p.chromium.launch(headless=True)
@@ -36,6 +40,9 @@ def capture(url: str, run_dir: Path, prefix: str = "baseline") -> Dict[str, Any]
             page.goto(url, wait_until="networkidle", timeout=20000)
             page.screenshot(path=str(screenshot_path), full_page=True)
             dom_path.write_text(page.content(), encoding="utf-8")
+            final_url = page.url
+            page_title = page.title()
+            page_body_excerpt = (page.text_content("body") or "")[:600]
             browser.close()
     except Exception as exc:
         payload["reason"] = str(exc)
@@ -43,10 +50,20 @@ def capture(url: str, run_dir: Path, prefix: str = "baseline") -> Dict[str, Any]
         return payload
     write_json(console_path, console_messages)
     write_json(network_path, requests_seen)
+    write_json(
+        page_path,
+        {
+            "url": final_url,
+            "title": page_title,
+            "body_excerpt": page_body_excerpt,
+        },
+    )
     payload = {
         "required": True,
         "present": True,
-        "refs": [str(screenshot_path), str(dom_path), str(console_path), str(network_path)],
+        "page_title": page_title,
+        "page_url": final_url,
+        "refs": [str(screenshot_path), str(dom_path), str(console_path), str(network_path), str(page_path)],
     }
     write_json(run_dir / "logs" / f"{prefix}-browser.json", payload)
     return payload