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

refactor(parser/find_by_regex): Better implementation for ~60% speed boost

Browse Source
This commit is contained in:
Karim shoair
2025-01-31 01:19:11 +02:00
parent 2c6142d96d
commit 37a31a120e
1 changed files with 6 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scrapling/parser.py
+6 -13
View File
@@ -943,23 +943,16 @@ class Adaptor(SelectorsGeneration):
""" """
results = Adaptors([]) results = Adaptors([])
def _traverse(node: Adaptor) -> None: # This selector gets all elements with text content
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 there's already no text in this node, dodge it to save CPU cycles and time if node_text.re(query, check_match=True, clean_match=clean_match, case_sensitive=case_sensitive):
if node_text: results.append(node)
if node_text.re(query, check_match=True, clean_match=clean_match, case_sensitive=case_sensitive):
results.append(node)
if results and first_match: if first_match and results:
# we got an element so we should stop # we got an element so we should stop
return break
for branch in node.children:
_traverse(branch)
# This will block until we traverse all children/branches
_traverse(self)
if results and first_match: if results and first_match:
return results[0] return results[0]