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

perf: optimize get_all_text and adaptive logic by another 10%

Browse Source
This commit is contained in:
Karim shoair
2025-08-02 04:08:14 +03:00
parent 1ec6f0e0f0
commit d1a2ecd341
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scrapling/parser.py
+2 -2
View File
@@ -323,7 +323,7 @@ class Selector(SelectorsGeneration):
ignored_elements.update(set(element.iterchildren())) ignored_elements.update(set(element.iterchildren()))
_all_strings = [] _all_strings = []
for node in self._root.xpath(".//*"): for node in self._root.iter():
if node not in ignored_elements: if node not in ignored_elements:
text = node.text text = node.text
if text and isinstance(text, str): if text and isinstance(text, str):
@@ -496,7 +496,7 @@ class Selector(SelectorsGeneration):
if issubclass(type(element), HtmlElement): if issubclass(type(element), HtmlElement):
element = _StorageTools.element_to_dict(element) element = _StorageTools.element_to_dict(element)
for node in self._root.xpath(".//*"): for node in self._root.iter("*"):
# Collect all elements in the page, then for each element get the matching score of it against the node. # Collect all elements in the page, then for each element get the matching score of it against the node.
# Hence: the code doesn't stop even if the score was 100% # Hence: the code doesn't stop even if the score was 100%
# because there might be another element(s) left in page with the same score # because there might be another element(s) left in page with the same score