fix: ci ruff

.gitignore

@@ -3,6 +3,7 @@
 __pycache__
 .pytest_cache
 venv/
+.venv/
 *.pyc
 *.pyo
 *.egg-info/

pyproject.toml

@@ -49,6 +49,9 @@ Issues = "https://github.com/smeltery/webgrab/issues"
 [tool.hatch.build.targets.wheel]
 packages = ["src/webgrab"]
 
+[tool.ruff.lint.flake8-bugbear]
+extend-immutable-calls = ["typer.Argument", "typer.Option"]
+
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 python_files = ["test_*.py"]

src/webgrab/capture/browser.py

@@ -1,9 +1,16 @@
 """Low-level Playwright browser operations."""
 
 import asyncio
-from typing import Callable
+from collections.abc import Callable
+from typing import Self
 
-from playwright.async_api import Browser, BrowserContext, Page, Response, async_playwright
+from playwright.async_api import (
+    Browser,
+    BrowserContext,
+    Page,
+    Response,
+    async_playwright,
+)
 
 from ..errors import BrowserError, NavigationError
 from ..models import CaptureConfig
@@ -23,7 +30,7 @@ def __init__(self, config: CaptureConfig) -> None:
         self.context: BrowserContext | None = None
         self.page: Page | None = None
 
-    async def __aenter__(self) -> "BrowserManager":
+    async def __aenter__(self) -> Self:
         """Launch browser and create context."""
         try:
             self.playwright = await async_playwright().start()

src/webgrab/capture/engine.py

@@ -2,7 +2,7 @@
 
 import asyncio
 import time
-from typing import Callable
+from collections.abc import Callable
 
 from playwright.async_api import Response
 

src/webgrab/capture/filters.py

@@ -41,10 +41,7 @@ def should_capture(self, url: str, content_type: str, status_code: int) -> bool:
             return False
 
         # Skip data URLs, blob URLs, etc.
-        if should_skip_url(url):
-            return False
-
-        return True
+        return not should_skip_url(url)
 
 
 class CompositeFilter:

src/webgrab/capture/processor.py

@@ -1,8 +1,9 @@
 """Resource processing with streaming architecture."""
 
 import asyncio
-from typing import AsyncIterator, Callable
+from collections.abc import AsyncIterator, Callable
 
+from playwright.async_api import Error as PlaywrightError
 from playwright.async_api import Response
 
 from ..models import CaptureStats, Resource
@@ -62,7 +63,7 @@ async def process_response(self, response: Response) -> Resource | None:
                 headers=headers,
                 status_code=status,
             )
-        except Exception as e:
+        except PlaywrightError as e:
             self.stats.failed_captures += 1
             if self.on_progress:
                 self.on_progress(f"Failed to capture {url}: {e}")

src/webgrab/cli.py

@@ -2,7 +2,6 @@
 
 import asyncio
 from pathlib import Path
-from typing import Optional
 
 import typer
 from rich.console import Console
@@ -34,7 +33,7 @@ def capture(
         ...,
         help="URL of the webpage to capture resources from.",
     ),
-    output: Optional[Path] = typer.Option(
+    output: Path | None = typer.Option(
         None,
         "--output", "-o",
         help="Output directory for saved resources. Defaults to ./webgrab_output",

src/webgrab/errors.py

@@ -4,26 +4,18 @@
 class WebGrabError(Exception):
     """Base exception for all webgrab errors."""
 
-    pass
-
 
 class CaptureError(WebGrabError):
     """Base exception for capture-related errors."""
 
-    pass
-
 
 class BrowserError(CaptureError):
     """Exception raised for browser-related errors."""
 
-    pass
-
 
 class NavigationError(BrowserError):
     """Exception raised when page navigation fails."""
 
-    pass
-
 
 class ResourceError(CaptureError):
     """Exception raised when capturing a resource fails."""
@@ -44,14 +36,10 @@ def __init__(self, url: str, message: str, original_error: Exception | None = No
 class StorageError(WebGrabError):
     """Base exception for storage-related errors."""
 
-    pass
-
 
 class PathResolutionError(StorageError):
     """Exception raised when URL to path resolution fails."""
 
-    pass
-
 
 class FileWriteError(StorageError):
     """Exception raised when writing a file fails."""
@@ -71,5 +59,3 @@ def __init__(self, path: str, message: str, original_error: Exception | None = N
 
 class ConfigurationError(WebGrabError):
     """Exception raised for configuration errors."""
-
-    pass

src/webgrab/models.py

@@ -2,7 +2,6 @@
 
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Optional
 
 
 @dataclass(frozen=True)
@@ -28,7 +27,7 @@ class CaptureConfig:
     url: str
     wait_time: int = 0
     timeout: int = 60000
-    user_agent: Optional[str] = None
+    user_agent: str | None = None
     include_external: bool = False
     headless: bool = True
     bypass_csp: bool = True

src/webgrab/storage/saver.py

@@ -2,6 +2,7 @@
 
 from pathlib import Path
 
+from ..errors import StorageError
 from ..mime.detector import infer_extension
 from ..models import Resource, SaveConfig, SaveResult
 from ..url.parser import is_same_origin
@@ -30,6 +31,11 @@ def save_resource(self, resource: Resource) -> Path | None:
 
         Returns:
             Path where resource was saved, or None if skipped.
+
+        Raises:
+            StorageError: If writing the resource fails.
+            OSError: If path resolution or filesystem operations fail.
+            ValueError: If URL or path inputs are invalid.
         """
         # Filter external resources if not included
         if not self.config.include_external and not is_same_origin(
@@ -48,13 +54,8 @@ def save_resource(self, resource: Resource) -> Path | None:
         # Deduplicate if path already used
         local_path = self.deduplicator.get_unique_path(local_path)
 
-        # Write content
-        try:
-            write_file(local_path, resource.body)
-            return local_path
-        except Exception:
-            # Return None to indicate failure (caller will track this)
-            return None
+        write_file(local_path, resource.body)
+        return local_path
 
     def save_resources(self, resources: list[Resource]) -> SaveResult:
         """Save all resources to disk.
@@ -74,7 +75,7 @@ def save_resources(self, resources: list[Resource]) -> SaveResult:
                     result.saved_paths.append(saved_path)
                 else:
                     result.skipped_count += 1
-            except Exception as e:
+            except (StorageError, OSError, ValueError) as e:
                 result.failed_saves.append((resource.url, e))
 
         return result