Filters - Add support for also removing HTML elements using XPath selectors (#2632)

This commit is contained in:
Michael McMillan
2024-09-17 22:43:04 +02:00
committed by GitHub
parent 8c1527c1ad
commit dc936a2e8a
7 changed files with 50 additions and 17 deletions

View File

@@ -87,6 +87,9 @@ def test_element_removal_output():
Some initial text<br>
<p>across multiple lines</p>
<div id="changetext">Some text that changes</div>
<div>Some text should be matched by xPath // selector</div>
<div>Some text should be matched by xPath selector</div>
<div>Some text should be matched by xPath1 selector</div>
</body>
<footer>
<p>Footer</p>
@@ -94,7 +97,16 @@ def test_element_removal_output():
</html>
"""
html_blob = element_removal(
["header", "footer", "nav", "#changetext"], html_content=content
[
"header",
"footer",
"nav",
"#changetext",
"//*[contains(text(), 'xPath // selector')]",
"xpath://*[contains(text(), 'xPath selector')]",
"xpath1://*[contains(text(), 'xPath1 selector')]"
],
html_content=content
)
text = get_text(html_blob)
assert (