style: Fix all mypy errors and add type hints to untyped function bodies
**Resolved all 65 mypy errors across 14 files and added type annotations to all previously untyped function bodies. Final result: 0 errors with --check-untyped-defs enabled, all 454 tests pass.** `scrapling/core/_types.py` - Removed broken Self = object fallback — now requires typing_extensions for Python < 3.11 `scrapling/core/storage.py` - Fixed str/bytes mismatch in _get_hash() — used separate _identifier_bytes variable instead of reassigning from str to bytes `scrapling/core/custom_types.py` - split() return type: Union[List, "TextHandlers"] → list[Any] (avoids LSP violation with parent list[str]) - format() kwargs: **kwargs: str → **kwargs: object (matches parent str.format signature) - AttributesHandler.__init__: Added mapping: Any = None, **kwargs: Any and -> None - json_string property: Added -> bytes return type `scrapling/core/mixins.py` - Changed self: "Selector" to self: Any on all mixin methods (mypy can't handle forward-reference self types on non-subclass mixins) - Added Dict[str, int] annotation for counter variable - Removed unused TYPE_CHECKING / Selector imports `scrapling/parser.py (~30 errors)` - Added body: str | bytes pre-annotation for dual-type if/elif assignment - Used Dict[str, Any] kwargs dict for HTMLParser(...) to bypass incomplete lxml stubs missing default_doctype - Changed base_url=url or None → base_url=url or "" (avoids str | None vs str | bytes) - bool(adaptive) to guarantee bool type for __adaptive_enabled - Declared __text: Optional[TextHandler], __tag: Optional[str], __attributes: Optional[AttributesHandler] at top of __init__ - cast(List, ...) for all XPath() call results (_find_all_elements, _find_all_elements_with_spaces) - Added Dict[float, List[Any]] for score_table, Dict[str, Any] for attributes - Changed score, checks = 0, 0 → score: float = 0; checks: int = 0 (two locations) - Renamed target → target_element in save() to avoid variable redefinition with different types - Wrapped node_text.clean() / .lower() in TextHandler(...) to preserve type `scrapling/engines/_browsers/_page.py` - Added PageInfo[SyncPage] | PageInfo[AsyncPage] union type annotation to page_info variable `scrapling/engines/_browsers/_validators.py` - Convert method_kwargs (TypedDict) to plain Dict[str, Any] before dynamic key access `scrapling/engines/_browsers/_base.py` - Added _config declaration to BaseSessionMixin - Used cast(StealthConfig, self._config) in __generate_stealth_options to access stealth-only attributes - Added Tuple[str, ...] annotation for flags - Removed redundant narrower StealthConfig type annotation on self._config in StealthySessionMixin.__validate__ - Widened SyncSession and AsyncSession fields (playwright, context, browser) to Any to support both playwright and patchright types - Added -> None to both start() methods `scrapling/engines/_browsers/_stealth.py` - Added Optional, ProxyType imports - Annotated proxy: Optional[ProxyType] in both sync/async fetch loops - Annotated outer_box: Any at first declaration, removed duplicate type annotations in subsequent branches - Added -> None to sync and async start() - Added config: Any parameter type to _initialize_context - Removed redundant self.context: AsyncBrowserContext re-annotations in conditional branches `scrapling/engines/_browsers/_controllers.py` - Added Optional, ProxyType imports - Annotated proxy: Optional[ProxyType] in both sync/async fetch loops - Added -> None to async start() - Removed redundant self.context: AsyncBrowserContext re-annotations `scrapling/spiders/request.py` - Added Optional import, typed _fp: Optional[bytes] = None - Removed redundant body: bytes re-annotation `scrapling/spiders/session.py` - Used separate client variable instead of reassigning session = session._client (avoids type incompatibility and fixes a bug where session._make_request was called instead of client._make_request) - Added -> None to SessionManager.__init__ `scrapling/engines/toolbelt/convertor.py` - Added list[Response] annotation for history in both sync/async methods `scrapling/engines/static.py` - FetcherClient.__init__ and AsyncFetcherClient.__init__: Added **kwargs: Any and -> None `scrapling/core/shell.py` - Wrapped re_sub(...) result in TextHandler(...) to maintain correct type - Added -> None to CurlParser.__init__ - Added full type signature to create_wrapper, replaced wrapper.__signature__ = ... with setattr(wrapper, "__signature__", ...) to satisfy mypy - Added Callable to imports
This commit is contained in:
@@ -30,6 +30,7 @@ from scrapling.core.custom_types import TextHandler
|
||||
from scrapling.engines.toolbelt.custom import Response
|
||||
from scrapling.core.utils._shell import _ParseHeaders, _CookieParser
|
||||
from scrapling.core._types import (
|
||||
Callable,
|
||||
Dict,
|
||||
Any,
|
||||
cast,
|
||||
@@ -82,7 +83,7 @@ class NoExitArgumentParser(ArgumentParser): # pragma: no cover
|
||||
class CurlParser:
|
||||
"""Builds the argument parser for relevant curl flags from DevTools."""
|
||||
|
||||
def __init__(self):
|
||||
def __init__(self) -> None:
|
||||
from scrapling.fetchers import Fetcher as __Fetcher
|
||||
|
||||
self.__fetcher = __Fetcher
|
||||
@@ -467,19 +468,21 @@ Type 'exit' or press Ctrl+D to exit.
|
||||
|
||||
return result
|
||||
|
||||
def create_wrapper(self, func, get_signature=True, signature_name=None):
|
||||
def create_wrapper(
|
||||
self, func: Callable, get_signature: bool = True, signature_name: Optional[str] = None
|
||||
) -> Callable:
|
||||
"""Create a wrapper that preserves function signature but updates page"""
|
||||
|
||||
@wraps(func)
|
||||
def wrapper(*args, **kwargs):
|
||||
def wrapper(*args: Any, **kwargs: Any) -> Any:
|
||||
result = func(*args, **kwargs)
|
||||
return self.update_page(result)
|
||||
|
||||
if get_signature:
|
||||
# Explicitly preserve and unpack signature for IPython introspection and autocompletion
|
||||
wrapper.__signature__ = _unpack_signature(func, signature_name) # pyright: ignore
|
||||
setattr(wrapper, "__signature__", _unpack_signature(func, signature_name))
|
||||
else:
|
||||
wrapper.__signature__ = signature(func) # pyright: ignore
|
||||
setattr(wrapper, "__signature__", signature(func))
|
||||
|
||||
return wrapper
|
||||
|
||||
@@ -601,7 +604,7 @@ class Convertor:
|
||||
" ",
|
||||
):
|
||||
# Remove consecutive white-spaces
|
||||
txt_content = re_sub(f"[{s}]+", s, txt_content)
|
||||
txt_content = TextHandler(re_sub(f"[{s}]+", s, txt_content))
|
||||
yield txt_content
|
||||
yield ""
|
||||
|
||||
|
||||
Reference in New Issue
Block a user