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

style(parser): optimize selectors instances creation

Browse Source
This commit is contained in:
Karim shoair
2025-07-30 01:45:26 +03:00
parent e7cdd39695
commit 7300efa77e
1 changed files with 10 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scrapling/parser.py
+10 -12
View File
@@ -253,14 +253,14 @@ class Selector(SelectorsGeneration):
if not len( if not len(
result result
): # Lxml will give a warning if I used something like `not result` ): # Lxml will give a warning if I used something like `not result`
return Selectors([]) return Selectors()
# From within the code, this method will always get a list of the same type, # From within the code, this method will always get a list of the same type,
# so we will continue without checks for a slight performance boost # so we will continue without checks for a slight performance boost
if self._is_text_node(result[0]): if self._is_text_node(result[0]):
return TextHandlers(list(map(self.__content_convertor, result))) return TextHandlers(list(map(self.__content_convertor, result)))
return Selectors(list(map(self.__element_convertor, result))) return Selectors(map(self.__element_convertor, result))
def __getstate__(self) -> Any: def __getstate__(self) -> Any:
# lxml don't like it :) # lxml don't like it :)
@@ -378,11 +378,9 @@ class Selector(SelectorsGeneration):
def children(self) -> "Selectors[Selector]": def children(self) -> "Selectors[Selector]":
"""Return the children elements of the current element or empty list otherwise""" """Return the children elements of the current element or empty list otherwise"""
return Selectors( return Selectors(
[ self.__element_convertor(child)
self.__element_convertor(child) for child in self._root.iterchildren()
for child in self._root.iterchildren() if type(child) not in html_forbidden
if type(child) not in html_forbidden
]
) )
@property @property
@@ -390,9 +388,9 @@ class Selector(SelectorsGeneration):
"""Return other children of the current element's parent or empty list otherwise""" """Return other children of the current element's parent or empty list otherwise"""
if self.parent: if self.parent:
return Selectors( return Selectors(
[child for child in self.parent.children if child._root != self._root] child for child in self.parent.children if child._root != self._root
) )
return Selectors([]) return Selectors()
def iterancestors(self) -> Generator["Selector", None, None]: def iterancestors(self) -> Generator["Selector", None, None]:
"""Return a generator that loops over all ancestors of the element, starting with the element's parent.""" """Return a generator that loops over all ancestors of the element, starting with the element's parent."""
@@ -734,7 +732,7 @@ class Selector(SelectorsGeneration):
attributes = dict() attributes = dict()
tags, patterns = set(), set() tags, patterns = set(), set()
results, functions, selectors = Selectors([]), [], [] results, functions, selectors = Selectors(), [], []
# Brace yourself for a wonderful journey! # Brace yourself for a wonderful journey!
for arg in args: for arg in args:
@@ -1134,7 +1132,7 @@ class Selector(SelectorsGeneration):
:param clean_match: if enabled, this will ignore all whitespaces and consecutive spaces while matching :param clean_match: if enabled, this will ignore all whitespaces and consecutive spaces while matching
""" """
results = Selectors([]) results = Selectors()
if not case_sensitive: if not case_sensitive:
text = text.lower() text = text.lower()
@@ -1178,7 +1176,7 @@ class Selector(SelectorsGeneration):
:param case_sensitive: If enabled, the letters case will be taken into consideration in the regex. :param case_sensitive: If enabled, the letters case will be taken into consideration in the regex.
:param clean_match: If enabled, this will ignore all whitespaces and consecutive spaces while matching. :param clean_match: If enabled, this will ignore all whitespaces and consecutive spaces while matching.
""" """
results = Selectors([]) results = Selectors()
# This selector gets all elements with text content # This selector gets all elements with text content
for node in self.__handle_elements( for node in self.__handle_elements(