🕷️ 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
Python aiai-scrapingautomationcrawlercrawlingcrawling-pythondatadata-extractionmcpmcp-serverplaywrightpythonscrapingselectorsstealthweb-scraperweb-scrapingweb-scraping-pythonwebscrapingxpath
fix: prevent duplicate ID segments in full-path selector generation
sjhddh1ac26733d80e
diff --git a/scrapling/core/mixins.py b/scrapling/core/mixins.pyindex c2e7420..5cbcba4 100644--- a/scrapling/core/mixins.py+++ b/scrapling/core/mixins.py@@ -47,7 +47,7 @@ class SelectorsGeneration:if counter[target.tag] > 1:part += f":nth-of-type({counter[target.tag]})" if css else f"[{counter[target.tag]}]"- selectorPath.append(part)+ selectorPath.append(part)target = target.parentif target is None or target.tag == "html":return " > ".join(reversed(selectorPath)) if css else "//" + "/".join(reversed(selectorPath))diff --git a/tests/parser/test_general.py b/tests/parser/test_general.pyindex 26f6e6c..3961660 100644--- a/tests/parser/test_general.py+++ b/tests/parser/test_general.py@@ -321,6 +321,45 @@ def test_selectors_generation(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 Testsdef test_getting_all_text(page):"""Test getting all text from the page"""