Skip to content

🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev

fix: emit valid XPath node test for ID elements in full-path mode

sjhddh273c8c2fa02d
diff --git a/scrapling/core/mixins.py b/scrapling/core/mixins.py
index 5cbcba4..868d620 100644
--- a/scrapling/core/mixins.py
+++ b/scrapling/core/mixins.py
@@ -26,7 +26,12 @@ class SelectorsGeneration:
if target.parent:
if target.attrib.get("id"):
# id is enough
- part = f"#{target.attrib['id']}" if css else f"[@id='{target.attrib['id']}']"
+ if css:
+ part = f"#{target.attrib['id']}"
+ elif full_path:
+ part = f"*[@id='{target.attrib['id']}']"
+ else:
+ part = f"[@id='{target.attrib['id']}']"
selectorPath.append(part)
if not full_path:
return " > ".join(reversed(selectorPath)) if css else "//*" + "/".join(reversed(selectorPath))
diff --git a/tests/parser/test_general.py b/tests/parser/test_general.py
index 3961660..293e93e 100644
--- a/tests/parser/test_general.py
+++ b/tests/parser/test_general.py
@@ -342,6 +342,11 @@ def test_full_path_selector_no_duplicate_ids():
assert len(result) == 1
assert result.first.text == "Hello"
+ # The generated XPath selector should also select the correct element
+ result = page.xpath(xpath_full)
+ assert len(result) == 1, f"XPath '{xpath_full}' selected {len(result)} elements, expected 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"""