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

Move test for get_all_text to test_parser_advanced.py

Browse Source
This commit is contained in:
Matt Hillebrand
2026-03-08 08:14:35 -07:00
parent e045d0f73f
commit 7cbe566acd
2 changed files with 27 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/parser/test_general.py
-26
View File
@@ -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]
tests/parser/test_parser_advanced.py
+27
View File
@@ -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"""