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

refactor(parser): Make get_all_text method 40% faster

Browse Source
This commit is contained in:
Karim shoair
2025-07-28 03:29:13 +03:00
parent 7f11b6f59b
commit d220050160
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
@@ -304,7 +304,7 @@ class Adaptor(SelectorsGeneration):
for tag in ignore_tags: for tag in ignore_tags:
for element in self._root.xpath(f".//{tag}"): for element in self._root.xpath(f".//{tag}"):
ignored_elements.add(element) ignored_elements.add(element)
ignored_elements.update(element.xpath(".//*")) ignored_elements.update(set(element.iterchildren()))
_all_strings = [] _all_strings = []
for node in self._root.xpath(".//*"): for node in self._root.xpath(".//*"):
@@ -315,7 +315,7 @@ class Adaptor(SelectorsGeneration):
if not valid_values or processed_text.strip(): if not valid_values or processed_text.strip():
_all_strings.append(processed_text) _all_strings.append(processed_text)
return TextHandler(separator.join(_all_strings)) return TextHandler(separator).join(_all_strings)
def urljoin(self, relative_url: str) -> str: def urljoin(self, relative_url: str) -> str:
"""Join this Adaptor's url with a relative url to form an absolute full URL.""" """Join this Adaptor's url with a relative url to form an absolute full URL."""