🕷️ 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
Move test for get_all_text to test_parser_advanced.py
Matt Hillebrand7cbe566acdbc
diff --git a/tests/parser/test_general.py b/tests/parser/test_general.pyindex 36241a6..26f6e6c 100644--- a/tests/parser/test_general.py+++ b/tests/parser/test_general.py@@ -327,32 +327,6 @@ def test_getting_all_text(page):assert page.get_all_text() != ""-def test_getting_all_text_from_nested_content():- """Test getting all text preserves interleaved text nodes"""- html = """- <html>- <body>- <main>- string1- <b>string2</b>- string3- <div>- <span>string4</span>- </div>- string5- <script>ignored</script>- <style>ignored</style>- </main>- </body>- </html>- """-- page = Selector(html, adaptive=False)- node = page.css("main")[0]-- assert node.get_all_text("\n", strip=True) == "string1\nstring2\nstring3\nstring4\nstring5"--def test_regex_on_text(page):"""Test regex operations on text"""element = page.css('[data-id="1"] .price')[0]diff --git a/tests/parser/test_parser_advanced.py b/tests/parser/test_parser_advanced.pyindex 57086ba..f34ba5c 100644--- a/tests/parser/test_parser_advanced.py+++ b/tests/parser/test_parser_advanced.py@@ -183,6 +183,33 @@ class TestAdvancedSelectors:text = page.get_all_text(valid_values=False)assert text != ""+ def test_get_all_text_preserves_interleaved_text_nodes(self):+ """Test get_all_text preserves interleaved text nodes"""+ html = """+ <html>+ <body>+ <main>+ string1+ <b>string2</b>+ string3+ <div>+ <span>string4</span>+ </div>+ string5+ <script>ignored</script>+ string6+ <style>ignored</style>+ string7+ </main>+ </body>+ </html>+ """++ page = Selector(html, adaptive=False)+ node = page.css("main")[0]++ assert node.get_all_text("\n", strip=True) == "string1\nstring2\nstring3\nstring4\nstring5\nstring6\nstring7"+class TestTextHandlerAdvanced:"""Test advanced TextHandler functionality"""