style: General type hints fixes and imports optimizing

This commit is contained in:
Karim shoair
2025-07-29 23:43:06 +03:00
parent 3d07a1533e
commit 9bcb9e9d93
7 changed files with 35 additions and 31 deletions
+1
View File
@@ -4,6 +4,7 @@ Type definitions for type checking purposes.
from typing import (
TYPE_CHECKING,
overload,
Any,
Callable,
Dict,
+10 -7
View File
@@ -7,14 +7,15 @@ from orjson import dumps, loads
from scrapling.core._types import (
Dict,
Iterable,
List,
Literal,
Optional,
Pattern,
SupportsIndex,
TypeVar,
Union,
TypeVar,
Literal,
Pattern,
Iterable,
Optional,
Generator,
SupportsIndex,
)
from scrapling.core.utils import _is_iterable, flatten
from scrapling.core._html_utils import _replace_entities
@@ -341,7 +342,9 @@ class AttributesHandler(Mapping[str, _TextHandlerType]):
"""Acts like the standard dictionary `.get()` method"""
return self._data.get(key, default)
def search_values(self, keyword, partial=False):
def search_values(
self, keyword: str, partial: bool = False
) -> Generator["AttributesHandler", None, None]:
"""Search current attributes by values and return a dictionary of each matching item
:param keyword: The keyword to search for in the attribute values
:param partial: If True, the function will search if keyword in each value instead of perfect match
+3 -3
View File
@@ -9,7 +9,7 @@ from orjson import dumps, loads
from tldextract import extract as tld
from scrapling.core.utils import _StorageTools, log
from scrapling.core._types import Dict, Optional, Union
from scrapling.core._types import Dict, Optional, Union, Any
class StorageSystemMixin(ABC):
@@ -106,7 +106,7 @@ class SQLiteStorageSystem(StorageSystemMixin):
""")
self.connection.commit()
def save(self, element: HtmlElement, identifier: str):
def save(self, element: HtmlElement, identifier: str) -> None:
"""Saves the elements unique properties to the storage for retrieval and relocation later
:param element: The element itself which we want to save to storage.
@@ -126,7 +126,7 @@ class SQLiteStorageSystem(StorageSystemMixin):
self.cursor.fetchall()
self.connection.commit()
def retrieve(self, identifier: str) -> Optional[Dict]:
def retrieve(self, identifier: str) -> Optional[Dict[str, Any]]:
"""Using the identifier, we search the storage and return the unique properties of the element
:param identifier: This is the identifier that will be used to retrieve the element from the storage. See
+6 -6
View File
@@ -5,7 +5,7 @@ from itertools import chain
import orjson
from lxml import html
from scrapling.core._types import Any, Dict, Iterable, Union
from scrapling.core._types import Any, Dict, Iterable, Union, List
# Using cache on top of a class is a brilliant way to achieve a Singleton design pattern without much code
from functools import lru_cache # isort:skip
@@ -41,8 +41,8 @@ def setup_logger():
log = setup_logger()
def is_jsonable(content: Union[bytes, str]) -> bool:
if type(content) is bytes:
def is_jsonable(content: bytes | str) -> bool:
if isinstance(content, bytes):
content = content.decode()
try:
@@ -52,14 +52,14 @@ def is_jsonable(content: Union[bytes, str]) -> bool:
return False
def flatten(lst: Iterable):
def flatten(lst: Iterable[Any]) -> List[Any]:
return list(chain.from_iterable(lst))
def _is_iterable(s: Any):
def _is_iterable(obj: Any) -> bool:
# This will be used only in regex functions to make sure it's iterable but not string/bytes
return isinstance(
s,
obj,
(
list,
tuple,