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

fix: prevent duplicate ID segments in full-path selector generation

Browse Source 
When generating full-path CSS/XPath selectors, elements with id
attributes had their selector appended twice — once in the id branch
(line 30) and again unconditionally (line 50).

This produced selectors like 'body > #main > #main > #target > #target'
instead of the correct 'body > #main > #target'.

Move the append into the else branch so it only fires for elements
without an id (elements with id already append in the if branch).

Includes 2 regression tests.
This commit is contained in:
sjhddh
2026-04-12 01:25:45 +02:00
parent 2046527575
commit 1ac26733d8
2 changed files with 40 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scrapling/core/mixins.py
+1 -1
View File
@@ -47,7 +47,7 @@ class SelectorsGeneration:
if counter[target.tag] > 1: if counter[target.tag] > 1:
part += f":nth-of-type({counter[target.tag]})" if css else f"[{counter[target.tag]}]" part += f":nth-of-type({counter[target.tag]})" if css else f"[{counter[target.tag]}]"
selectorPath.append(part) selectorPath.append(part)
target = target.parent target = target.parent
if target is None or target.tag == "html": if target is None or target.tag == "html":
return " > ".join(reversed(selectorPath)) if css else "//" + "/".join(reversed(selectorPath)) return " > ".join(reversed(selectorPath)) if css else "//" + "/".join(reversed(selectorPath))
tests/parser/test_general.py
+39
View File
@@ -321,6 +321,45 @@ def test_selectors_generation(page):
_traverse(page) _traverse(page)
def test_full_path_selector_no_duplicate_ids():
"""Test that full path selectors don't duplicate id segments (regression test)"""
html = '<html><body><div id="main"><p id="target">Hello</p></div></body></html>'
page = Selector(html)
target = page.css("#target").first
# CSS full path should not duplicate id selectors
css_full = target.generate_full_css_selector
assert css_full.count("#target") == 1, f"Duplicate #target in CSS full path: {css_full}"
assert css_full.count("#main") == 1, f"Duplicate #main in CSS full path: {css_full}"
# XPath full path should not duplicate id selectors
xpath_full = target.generate_full_xpath_selector
assert xpath_full.count("@id='target'") == 1, f"Duplicate @id='target' in XPath full path: {xpath_full}"
assert xpath_full.count("@id='main'") == 1, f"Duplicate @id='main' in XPath full path: {xpath_full}"
# The generated CSS selector should actually select the correct element
result = page.css(css_full)
assert len(result) == 1
assert result.first.text == "Hello"
def test_full_path_selector_mixed_id_and_no_id():
"""Test full path selectors with a mix of elements with and without ids"""
html = '<html><body><div id="wrapper"><section><p>Text</p></section></div></body></html>'
page = Selector(html)
target = page.css("p").first
css_full = target.generate_full_css_selector
# p has no id, so it should appear as a tag name; div has id
assert "#wrapper" in css_full
assert css_full.count("#wrapper") == 1
# Verify the selector works
result = page.css(css_full)
assert len(result) == 1
assert result.first.text == "Text"
# Miscellaneous Tests # Miscellaneous Tests
def test_getting_all_text(page): def test_getting_all_text(page):
"""Test getting all text from the page""" """Test getting all text from the page"""