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

perf: speeding up find_by_text and find_by_regex by 3%

Browse Source
This commit is contained in:
Karim shoair
2025-08-02 19:46:18 +03:00
parent 67658f1723
commit 740ae815c3
1 changed files with 5 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scrapling/parser.py
+5 -8
View File
@@ -50,6 +50,9 @@ _whitelisted = {
} }
# Pre-compiled selectors for efficiency # Pre-compiled selectors for efficiency
_find_all_elements = XPath(".//*") _find_all_elements = XPath(".//*")
_find_all_elements_with_spaces = XPath(
".//*[normalize-space(text())]"
) # This selector gets all elements with text content
class Selector(SelectorsGeneration): class Selector(SelectorsGeneration):
@@ -1161,10 +1164,7 @@ class Selector(SelectorsGeneration):
if not case_sensitive: if not case_sensitive:
text = text.lower() text = text.lower()
# This selector gets all elements with text content for node in self.__handle_elements(_find_all_elements_with_spaces(self._root)):
for node in self.__handle_elements(
self._root.xpath(".//*[normalize-space(text())]")
):
"""Check if element matches given text otherwise, traverse the children tree and iterate""" """Check if element matches given text otherwise, traverse the children tree and iterate"""
node_text = node.text node_text = node.text
if clean_match: if clean_match:
@@ -1203,10 +1203,7 @@ class Selector(SelectorsGeneration):
""" """
results = Selectors() results = Selectors()
# This selector gets all elements with text content for node in self.__handle_elements(_find_all_elements_with_spaces(self._root)):
for node in self.__handle_elements(
self._root.xpath(".//*[normalize-space(text())]")
):
"""Check if element matches given regex otherwise, traverse the children tree and iterate""" """Check if element matches given regex otherwise, traverse the children tree and iterate"""
node_text = node.text node_text = node.text
if node_text.re( if node_text.re(