Karim shoair commited on
Commit ·
a7cc20d
1
Parent(s): d391239
fix: remove forgotten unused code
Browse files
scrapling/core/translator.py
CHANGED
|
@@ -130,5 +130,5 @@ translator = HTMLTranslator()
|
|
| 130 |
|
| 131 |
@lru_cache(maxsize=256)
|
| 132 |
def css_to_xpath(query: str) -> str:
|
| 133 |
-
"""Return translated XPath version of a given CSS query"""
|
| 134 |
return translator.css_to_xpath(query)
|
|
|
|
| 130 |
|
| 131 |
@lru_cache(maxsize=256)
|
| 132 |
def css_to_xpath(query: str) -> str:
|
| 133 |
+
"""Return the translated XPath version of a given CSS query"""
|
| 134 |
return translator.css_to_xpath(query)
|
scrapling/engines/_browsers/_config_tools.py
CHANGED
|
@@ -1,11 +1,5 @@
|
|
| 1 |
from functools import lru_cache
|
| 2 |
|
| 3 |
-
from scrapling.core._types import Tuple
|
| 4 |
-
from scrapling.engines.constants import (
|
| 5 |
-
DEFAULT_STEALTH_FLAGS,
|
| 6 |
-
HARMFUL_DEFAULT_ARGS,
|
| 7 |
-
DEFAULT_FLAGS,
|
| 8 |
-
)
|
| 9 |
from scrapling.engines.toolbelt.navigation import js_bypass_path
|
| 10 |
from scrapling.engines.toolbelt.fingerprints import generate_headers
|
| 11 |
|
|
@@ -42,19 +36,3 @@ def _compiled_stealth_scripts():
|
|
| 42 |
with open(script_path, "r") as f:
|
| 43 |
scripts.append(f.read())
|
| 44 |
return tuple(scripts)
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
@lru_cache(2, typed=True)
|
| 48 |
-
def _set_flags(hide_canvas, disable_webgl): # pragma: no cover
|
| 49 |
-
"""Returns the flags that will be used while launching the browser if stealth mode is enabled"""
|
| 50 |
-
flags = DEFAULT_STEALTH_FLAGS
|
| 51 |
-
if hide_canvas:
|
| 52 |
-
flags += ("--fingerprinting-canvas-image-data-noise",)
|
| 53 |
-
if disable_webgl:
|
| 54 |
-
flags += (
|
| 55 |
-
"--disable-webgl",
|
| 56 |
-
"--disable-webgl-image-chromium",
|
| 57 |
-
"--disable-webgl2",
|
| 58 |
-
)
|
| 59 |
-
|
| 60 |
-
return flags
|
|
|
|
| 1 |
from functools import lru_cache
|
| 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
from scrapling.engines.toolbelt.navigation import js_bypass_path
|
| 4 |
from scrapling.engines.toolbelt.fingerprints import generate_headers
|
| 5 |
|
|
|
|
| 36 |
with open(script_path, "r") as f:
|
| 37 |
scripts.append(f.read())
|
| 38 |
return tuple(scripts)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
scrapling/engines/_browsers/_validators.py
CHANGED
|
@@ -13,7 +13,6 @@ from scrapling.core._types import (
|
|
| 13 |
Tuple,
|
| 14 |
Optional,
|
| 15 |
Callable,
|
| 16 |
-
Iterable,
|
| 17 |
Sequence,
|
| 18 |
overload,
|
| 19 |
SetCookieParam,
|
|
@@ -37,15 +36,6 @@ def _is_invalid_file_path(value: str) -> bool | str: # pragma: no cover
|
|
| 37 |
return False
|
| 38 |
|
| 39 |
|
| 40 |
-
def _validate_addon_path(value: str) -> None: # pragma: no cover
|
| 41 |
-
"""Fast addon path validation"""
|
| 42 |
-
path = Path(value)
|
| 43 |
-
if not path.exists():
|
| 44 |
-
raise FileNotFoundError(f"Addon path not found: {value}")
|
| 45 |
-
if not path.is_dir():
|
| 46 |
-
raise ValueError(f"Addon path must be a directory of the extracted addon: {value}")
|
| 47 |
-
|
| 48 |
-
|
| 49 |
@lru_cache(2)
|
| 50 |
def _is_invalid_cdp_url(cdp_url: str) -> bool | str:
|
| 51 |
"""Fast CDP URL validation"""
|
|
|
|
| 13 |
Tuple,
|
| 14 |
Optional,
|
| 15 |
Callable,
|
|
|
|
| 16 |
Sequence,
|
| 17 |
overload,
|
| 18 |
SetCookieParam,
|
|
|
|
| 36 |
return False
|
| 37 |
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
@lru_cache(2)
|
| 40 |
def _is_invalid_cdp_url(cdp_url: str) -> bool | str:
|
| 41 |
"""Fast CDP URL validation"""
|
scrapling/engines/toolbelt/navigation.py
CHANGED
|
@@ -11,7 +11,7 @@ from msgspec import Struct, structs, convert, ValidationError
|
|
| 11 |
from playwright.sync_api import Route
|
| 12 |
|
| 13 |
from scrapling.core.utils import log
|
| 14 |
-
from scrapling.core._types import Dict, Tuple
|
| 15 |
from scrapling.engines.constants import DEFAULT_DISABLED_RESOURCES
|
| 16 |
|
| 17 |
__BYPASSES_DIR__ = Path(__file__).parent / "bypasses"
|
|
|
|
| 11 |
from playwright.sync_api import Route
|
| 12 |
|
| 13 |
from scrapling.core.utils import log
|
| 14 |
+
from scrapling.core._types import Dict, Tuple
|
| 15 |
from scrapling.engines.constants import DEFAULT_DISABLED_RESOURCES
|
| 16 |
|
| 17 |
__BYPASSES_DIR__ = Path(__file__).parent / "bypasses"
|