Skip to content

🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev

style: Adjustments to the translator

Karim shoair32cb76604c1e
diff --git a/scrapling/core/translator.py b/scrapling/core/translator.py
index 9c987ff..bdab7a5 100644
--- a/scrapling/core/translator.py
+++ b/scrapling/core/translator.py
@@ -8,7 +8,7 @@ So you don't have to learn a new selectors/api method like what bs4 done with so
If you want to learn about this, head to https://cssselect.readthedocs.io/en/latest/#cssselect.FunctionalPseudoElement
"""
-import re
+from functools import lru_cache
from cssselect import HTMLTranslator as OriginalHTMLTranslator
from cssselect.parser import Element, FunctionalPseudoElement, PseudoElement
@@ -16,11 +16,6 @@ from cssselect.xpath import ExpressionError
from cssselect.xpath import XPathExpr as OriginalXPathExpr
from scrapling.core._types import Any, Optional, Protocol, Self
-from scrapling.core.utils import lru_cache
-
-HTML5_WHITESPACE = " \t\n\r\x0c" # From w3lib.html.HTML5_WHITESPACE
-regex = f"[{HTML5_WHITESPACE}]+"
-replace_html5_whitespaces = re.compile(regex).sub
class XPathExpr(OriginalXPathExpr):
@@ -33,7 +28,7 @@ class XPathExpr(OriginalXPathExpr):
xpath: OriginalXPathExpr,
textnode: bool = False,
attribute: Optional[str] = None,
- ) -> "Self":
+ ) -> Self:
x = cls(path=xpath.path, element=xpath.element, condition=xpath.condition)
x.textnode = textnode
x.attribute = attribute
@@ -57,12 +52,12 @@ class XPathExpr(OriginalXPathExpr):
return path
def join(
- self: "Self",
+ self: Self,
combiner: str,
other: OriginalXPathExpr,
*args: Any,
**kwargs: Any,
- ) -> "Self":
+ ) -> Self:
if not isinstance(other, XPathExpr):
raise ValueError(
f"Expressions of type {__name__}.XPathExpr can ony join expressions"
@@ -90,7 +85,7 @@ class TranslatorMixin:
"""
def xpath_element(self: TranslatorProtocol, selector: Element) -> XPathExpr:
- # https://github.com/python/mypy/issues/12344
+ # https://github.com/python/mypy/issues/14757
xpath = super().xpath_element(selector) # type: ignore[safe-super]
return XPathExpr.from_xpath(xpath)
@@ -98,7 +93,7 @@ class TranslatorMixin:
self, xpath: OriginalXPathExpr, pseudo_element: PseudoElement
) -> OriginalXPathExpr:
"""
- Dispatch method that transforms XPath to support pseudo-elements.
+ Dispatch method that transforms XPath to support the pseudo-element.
"""
if isinstance(pseudo_element, FunctionalPseudoElement):
method_name = f"xpath_{pseudo_element.name.replace('-', '_')}_functional_pseudo_element"
@@ -143,4 +138,4 @@ class HTMLTranslator(TranslatorMixin, OriginalHTMLTranslator):
return super().css_to_xpath(css, prefix)
-translator_instance = HTMLTranslator()
+translator = HTMLTranslator()
diff --git a/scrapling/parser.py b/scrapling/parser.py
index 219181d..7540ba7 100644
--- a/scrapling/parser.py
+++ b/scrapling/parser.py
@@ -36,7 +36,7 @@ from scrapling.core.storage import (
StorageSystemMixin,
_StorageTools,
)
-from scrapling.core.translator import translator_instance
+from scrapling.core.translator import translator as _translator
from scrapling.core.utils import clean_spaces, flatten, html_forbidden, is_jsonable, log
__DEFAULT_DB_FILE__ = str(Path(__file__).parent / "elements_storage.db")
@@ -600,7 +600,7 @@ class Selector(SelectorsGeneration):
try:
if not self.__adaptive_enabled or "," not in selector:
# No need to split selectors in this case, let's save some CPU cycles :)
- xpath_selector = translator_instance.css_to_xpath(selector)
+ xpath_selector = _translator.css_to_xpath(selector)
return self.xpath(
xpath_selector,
identifier or selector,
@@ -614,7 +614,7 @@ class Selector(SelectorsGeneration):
for single_selector in split_selectors(selector):
# I'm doing this only so the `save` function saves data correctly for combined selectors
# Like using the ',' to combine two different selectors that point to different elements.
- xpath_selector = translator_instance.css_to_xpath(
+ xpath_selector = _translator.css_to_xpath(
single_selector.canonical()
)
results += self.xpath(