freedak/Scrapling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

style: applying the new ruff rules to all files

Browse Source
This commit is contained in:
Karim shoair
2025-09-13 03:22:53 +03:00
parent 60be9dc816
commit 330d03559c
18 changed files with 176 additions and 572 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scrapling/engines/_browsers/_base.py
+7 -25
View File
@@ -80,9 +80,7 @@ class SyncSession:
return self.page_pool.add_page(page)
@staticmethod
def _get_with_precedence(
request_value: Any, session_value: Any, sentinel_value: object
) -> Any:
def _get_with_precedence(request_value: Any, session_value: Any, sentinel_value: object) -> Any:
"""Get value with request-level priority over session-level"""
return request_value if request_value is not sentinel_value else session_value
@@ -169,11 +167,7 @@ class DynamicSessionMixin:
self.wait_selector_state = config.wait_selector_state
self.selector_config = config.selector_config
self.page_action = config.page_action
self._headers_keys = (
set(map(str.lower, self.extra_headers.keys()))
if self.extra_headers
else set()
)
self._headers_keys = set(map(str.lower, self.extra_headers.keys())) if self.extra_headers else set()
self.__initiate_browser_options__()
def __initiate_browser_options__(self):
@@ -184,9 +178,7 @@ class DynamicSessionMixin:
self.headless,
self.proxy,
self.locale,
tuple(self.extra_headers.items())
if self.extra_headers
else tuple(),
tuple(self.extra_headers.items()) if self.extra_headers else tuple(),
self.useragent,
self.real_chrome,
self.stealth,
@@ -194,9 +186,7 @@ class DynamicSessionMixin:
self.disable_webgl,
)
)
self.launch_options["extra_http_headers"] = dict(
self.launch_options["extra_http_headers"]
)
self.launch_options["extra_http_headers"] = dict(self.launch_options["extra_http_headers"])
self.launch_options["proxy"] = dict(self.launch_options["proxy"]) or None
self.context_options = dict()
else:
@@ -206,16 +196,12 @@ class DynamicSessionMixin:
_context_kwargs(
self.proxy,
self.locale,
tuple(self.extra_headers.items())
if self.extra_headers
else tuple(),
tuple(self.extra_headers.items()) if self.extra_headers else tuple(),
self.useragent,
self.stealth,
)
)
self.context_options["extra_http_headers"] = dict(
self.context_options["extra_http_headers"]
)
self.context_options["extra_http_headers"] = dict(self.context_options["extra_http_headers"])
self.context_options["proxy"] = dict(self.context_options["proxy"]) or None
@@ -249,11 +235,7 @@ class StealthySessionMixin:
self.selector_config = config.selector_config
self.additional_args = config.additional_args
self.page_action = config.page_action
self._headers_keys = (
set(map(str.lower, self.extra_headers.keys()))
if self.extra_headers
else set()
)
self._headers_keys = set(map(str.lower, self.extra_headers.keys())) if self.extra_headers else set()
self.__initiate_browser_options__()
def __initiate_browser_options__(self):
scrapling/engines/_browsers/_page.py
+1 -3
View File
@@ -6,9 +6,7 @@ from playwright.async_api import Page as AsyncPage
from scrapling.core._types import Optional, List, Literal
PageState = Literal[
"finished", "ready", "busy", "error"
] # States that a page can be in
PageState = Literal["finished", "ready", "busy", "error"] # States that a page can be in
@dataclass
scrapling/engines/_browsers/_validators.py
+6 -14
View File
@@ -25,9 +25,7 @@ class PlaywrightConfig(Struct, kw_only=True, frozen=False):
stealth: bool = False
wait: int | float = 0
page_action: Optional[Callable] = None
proxy: Optional[str | Dict[str, str]] = (
None # The default value for proxy in Playwright's source is `None`
)
proxy: Optional[str | Dict[str, str]] = None # The default value for proxy in Playwright's source is `None`
locale: str = "en-US"
extra_headers: Optional[Dict[str, str]] = None
useragent: Optional[str] = None
@@ -46,10 +44,8 @@ class PlaywrightConfig(Struct, kw_only=True, frozen=False):
raise ValueError("max_pages must be between 1 and 50")
if self.timeout < 0:
raise ValueError("timeout must be >= 0")
if self.page_action is not None and not callable(self.page_action):
raise TypeError(
f"page_action must be callable, got {type(self.page_action).__name__}"
)
if self.page_action and not callable(self.page_action):
raise TypeError(f"page_action must be callable, got {type(self.page_action).__name__}")
if self.proxy:
self.proxy = construct_proxy_dict(self.proxy, as_tuple=True)
if self.cdp_url:
@@ -108,9 +104,7 @@ class CamoufoxConfig(Struct, kw_only=True, frozen=False):
cookies: Optional[List[Dict]] = None
google_search: bool = True
extra_headers: Optional[Dict[str, str]] = None
proxy: Optional[str | Dict[str, str]] = (
None # The default value for proxy in Playwright's source is `None`
)
proxy: Optional[str | Dict[str, str]] = None # The default value for proxy in Playwright's source is `None`
os_randomize: bool = False
disable_ads: bool = False
geoip: bool = False
@@ -123,10 +117,8 @@ class CamoufoxConfig(Struct, kw_only=True, frozen=False):
raise ValueError("max_pages must be between 1 and 50")
if self.timeout < 0:
raise ValueError("timeout must be >= 0")
if self.page_action is not None and not callable(self.page_action):
raise TypeError(
f"page_action must be callable, got {type(self.page_action).__name__}"
)
if self.page_action and not callable(self.page_action):
raise TypeError(f"page_action must be callable, got {type(self.page_action).__name__}")
if self.proxy:
self.proxy = construct_proxy_dict(self.proxy, as_tuple=True)