Karim shoair
5ec929435b
**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
88 lines
2.7 KiB
Python
88 lines
2.7 KiB
Python
from threading import RLock
|
|
from dataclasses import dataclass
|
|
|
|
from playwright.sync_api._generated import Page as SyncPage
|
|
from playwright.async_api._generated import Page as AsyncPage
|
|
|
|
from scrapling.core._types import Optional, List, Literal, overload, TypeVar, Generic, cast
|
|
|
|
PageState = Literal["ready", "busy", "error"] # States that a page can be in
|
|
PageType = TypeVar("PageType", SyncPage, AsyncPage)
|
|
|
|
|
|
@dataclass
|
|
class PageInfo(Generic[PageType]):
|
|
"""Information about the page and its current state"""
|
|
|
|
__slots__ = ("page", "state", "url")
|
|
page: PageType
|
|
state: PageState
|
|
url: Optional[str]
|
|
|
|
def mark_busy(self, url: str = ""):
|
|
"""Mark the page as busy"""
|
|
self.state = "busy"
|
|
self.url = url
|
|
|
|
def mark_error(self):
|
|
"""Mark the page as having an error"""
|
|
self.state = "error"
|
|
|
|
def __repr__(self):
|
|
return f'Page(URL="{self.url!r}", state={self.state!r})'
|
|
|
|
def __eq__(self, other_page):
|
|
"""Comparing this page to another page object."""
|
|
if other_page.__class__ is not self.__class__:
|
|
return NotImplemented
|
|
return self.page == other_page.page
|
|
|
|
|
|
class PagePool:
|
|
"""Manages a pool of browser pages/tabs with state tracking"""
|
|
|
|
__slots__ = ("max_pages", "pages", "_lock")
|
|
|
|
def __init__(self, max_pages: int = 5):
|
|
self.max_pages = max_pages
|
|
self.pages: List[PageInfo[SyncPage] | PageInfo[AsyncPage]] = []
|
|
self._lock = RLock()
|
|
|
|
@overload
|
|
def add_page(self, page: SyncPage) -> PageInfo[SyncPage]: ...
|
|
|
|
@overload
|
|
def add_page(self, page: AsyncPage) -> PageInfo[AsyncPage]: ...
|
|
|
|
def add_page(self, page: SyncPage | AsyncPage) -> PageInfo[SyncPage] | PageInfo[AsyncPage]:
|
|
"""Add a new page to the pool"""
|
|
with self._lock:
|
|
if len(self.pages) >= self.max_pages:
|
|
raise RuntimeError(f"Maximum page limit ({self.max_pages}) reached")
|
|
|
|
if isinstance(page, AsyncPage):
|
|
page_info: PageInfo[SyncPage] | PageInfo[AsyncPage] = cast(
|
|
PageInfo[AsyncPage], PageInfo(page, "ready", "")
|
|
)
|
|
else:
|
|
page_info = cast(PageInfo[SyncPage], PageInfo(page, "ready", ""))
|
|
|
|
self.pages.append(page_info)
|
|
return page_info
|
|
|
|
@property
|
|
def pages_count(self) -> int:
|
|
"""Get the total number of pages"""
|
|
return len(self.pages)
|
|
|
|
@property
|
|
def busy_count(self) -> int:
|
|
"""Get the number of busy pages"""
|
|
with self._lock:
|
|
return sum(1 for p in self.pages if p.state == "busy")
|
|
|
|
def cleanup_error_pages(self):
|
|
"""Remove pages in error state"""
|
|
with self._lock:
|
|
self.pages = [p for p in self.pages if p.state != "error"]
|