🕷️ 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 IndexError in adaptive relocation with auto_save
Mubashir Rahimcd4cdc69e622
diff --git a/scrapling/parser.py b/scrapling/parser.pyindex 2b88af3..200cb43 100644--- a/scrapling/parser.py+++ b/scrapling/parser.py@@ -671,7 +671,7 @@ class Selector(SelectorsGeneration):element_data = self.retrieve(identifier or selector)if element_data:elements = self.relocate(element_data, percentage)- if elements is not None and auto_save:+ if elements and auto_save:self.save(elements[0], identifier or selector)return self.__handle_elements(elements)diff --git a/tests/parser/test_adaptive.py b/tests/parser/test_adaptive.pyindex 8d40f77..85881d1 100644--- a/tests/parser/test_adaptive.py+++ b/tests/parser/test_adaptive.py@@ -56,6 +56,32 @@ class TestParserAdaptive:assert relocated[0].has_class("new-class")assert relocated[0].css(".new-description")[0].text == "Description 1"+ def test_relocation_auto_save_no_match_above_threshold(self):+ """Adaptive relocation with `auto_save=True` must not crash when no element+ clears the `percentage` threshold (relocate() returns an empty list)."""+ original_html = """+ <div class="container">+ <article class="product" id="target">+ <h3>Widget</h3>+ <p class="desc">A widget</p>+ </article>+ </div>+ """+ # Unrelated structure so nothing can match a high threshold+ changed_html = "<html><body><span>totally unrelated content</span></body></html>"++ old_page = Selector(original_html, url="example.com", adaptive=True)+ new_page = Selector(changed_html, url="example.com", adaptive=True)++ old_page.css("#target", identifier="target", auto_save=True)++ # Before the fix this raised `IndexError: list index out of range` because the+ # guard checked `elements is not None` but relocate() returns [] (never None).+ result = new_page.css(+ "#target", identifier="target", adaptive=True, auto_save=True, percentage=95+ )+ assert list(result) == []+@pytest.mark.asyncioasync def test_element_relocation_async(self):"""Test relocating element after structure change in async mode"""