Refactor Pydantic model configuration to use ConfigDict for arbitrary types

crawl4ai/async_url_seeder.py

@@ -166,22 +166,6 @@ class AsyncUrlSeeder:
     Async version of UrlSeeder.
     Call pattern is await/async for / async with.
 
-    Parameters
-    ----------
-    ttl : timedelta, default TTL
-        Time-to-live for cached results.
-    client : httpx.AsyncClient, optional
-        HTTP client to use. If None, creates a new one.
-    logger : AsyncLoggerBase, optional
-        Logger instance for logging messages.
-    base_directory : str or pathlib.Path, optional
-        Base directory for cache storage. Defaults to home directory.
-    cache_root : str or pathlib.Path, optional
-        Root directory for URL seeder cache. Defaults to ~/.cache/url_seeder.
-    verify_redirect_targets : bool, default True
-        Whether to verify that redirect targets are alive (2xx status) before returning them.
-        When False, returns redirect targets without verification (legacy behavior).
-
     Public coroutines
     -----------------
     await seed.urls(...)
@@ -219,8 +203,6 @@ class AsyncUrlSeeder:
         # NEW: Add base_directory
         base_directory: Optional[Union[str, pathlib.Path]] = None,
         cache_root: Optional[Union[str, Path]] = None,
-        # NEW: Control redirect target verification
-        verify_redirect_targets: bool = True,
     ):
         self.ttl = ttl
         self._owns_client = client is None  # Track if we created the client
@@ -245,9 +227,6 @@ class AsyncUrlSeeder:
             cache_root or "~/.cache/url_seeder"))
         (self.cache_root / "live").mkdir(parents=True, exist_ok=True)
         (self.cache_root / "head").mkdir(exist_ok=True)
-        
-        # Store redirect verification setting
-        self.verify_redirect_targets = verify_redirect_targets
 
     def _log(self, level: str, message: str, tag: str = "URL_SEED", **kwargs: Any):
         """Helper to log messages using the provided logger, if available."""
@@ -703,47 +682,24 @@ class AsyncUrlSeeder:
 
         Returns:
             * the same URL if it answers 2xx,
-            * the absolute redirect target if it answers 3xx (and if verify_redirect_targets=True, only if target is alive/2xx),
+            * the absolute redirect target if it answers 3xx,
             * None on any other status or network error.
         """
         try:
             r = await self.client.head(url, timeout=10, follow_redirects=False)
-            # direct 2xx hit
+
+            # direct hit
             if 200 <= r.status_code < 300:
                 return str(r.url)
-            # single-level redirect (3xx)
+
+            # single level redirect
             if r.status_code in (301, 302, 303, 307, 308):
                 loc = r.headers.get("location")
                 if loc:
-                    target = urljoin(url, loc)
-                    # Avoid infinite loop on self-redirect
-                    if target == url:
-                        return None
-                    
-                    # If not verifying redirect targets, return immediately (old behavior)
-                    if not self.verify_redirect_targets:
-                        return target
-                    
-                    # Verify redirect target is alive (new behavior)
-                    try:
-                        r2 = await self.client.head(target, timeout=10, follow_redirects=False)
-                        if 200 <= r2.status_code < 300:
-                            return str(r2.url)
-                        # Optionally, could handle another 3xx here for 2-step chains, but spec only says 1
-                        else:
-                            self._log(
-                                "debug",
-                                "HEAD redirect target {target} did not resolve: status {status}",
-                                params={"target": target, "status": r2.status_code},
-                                tag="URL_SEED",
-                            )
-                            return None
-                    except Exception as e2:
-                        self._log("debug", "HEAD {target} failed: {err}",
-                            params={"target": target, "err": str(e2)}, tag="URL_SEED")
-                        return None
-            # all other cases
+                    return urljoin(url, loc)
+
             return None
+
         except Exception as e:
             self._log("debug", "HEAD {url} failed: {err}",
                       params={"url": url, "err": str(e)}, tag="URL_SEED")

crawl4ai/models.py

@@ -1,4 +1,4 @@
-from pydantic import BaseModel, HttpUrl, PrivateAttr, Field
+from pydantic import BaseModel, HttpUrl, PrivateAttr, Field, ConfigDict
 from typing import List, Dict, Optional, Callable, Awaitable, Union, Any
 from typing import AsyncGenerator
 from typing import Generic, TypeVar
@@ -153,8 +153,7 @@ class CrawlResult(BaseModel):
     console_messages: Optional[List[Dict[str, Any]]] = None
     tables: List[Dict] = Field(default_factory=list)  # NEW – [{headers,rows,caption,summary}]
 
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
 # NOTE: The StringCompatibleMarkdown class, custom __init__ method, property getters/setters,
 # and model_dump override all exist to support a smooth transition from markdown as a string
@@ -332,8 +331,7 @@ class AsyncCrawlResponse(BaseModel):
     network_requests: Optional[List[Dict[str, Any]]] = None
     console_messages: Optional[List[Dict[str, Any]]] = None
 
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
 ###############################
 # Scraping Models

tests/test_async_url_seeder.py

@@ -1,29 +0,0 @@
-import pytest
-import asyncio
-from crawl4ai.async_url_seeder import AsyncUrlSeeder
-
-@pytest.mark.asyncio
-async def test_resolve_head_handles_dead_redirects():
-    seeder = AsyncUrlSeeder()
-    # Should return None – redirects to a dead URL
-    assert await seeder._resolve_head("http://youtube.com/sitemap.xml") is None
-    assert await seeder._resolve_head("https://stripe.com/sitemap.xml") is None
-
-@pytest.mark.asyncio
-async def test_resolve_head_direct_hit():
-    seeder = AsyncUrlSeeder()
-    # Test with a known live URL, e.g., httpbin
-    result = await seeder._resolve_head("https://httpbin.org/status/200")
-    assert result == "https://httpbin.org/status/200"
-
-@pytest.mark.asyncio
-async def test_resolve_head_verify_redirect_targets_false():
-    # Test with verification disabled - should return redirect target without checking if alive
-    seeder = AsyncUrlSeeder(verify_redirect_targets=False)
-    # This should return the redirect target even if it's dead (old behavior)
-    result = await seeder._resolve_head("http://youtube.com/sitemap.xml")
-    # The exact redirect target might vary, but it should not be None
-    assert result is not None
-    assert isinstance(result, str)
-    # Should be different from the input URL (indicating redirect was followed)
-    assert result != "http://youtube.com/sitemap.xml"