cryptorugmunch
8d25702eca
Squashed from chore/license-relicense. Full message preserved in the original branch commitbb77eb5. See ADR-0002 for the decision rationale. Refs: ADR-0002, commitbb77eb5
52 lines
1.4 KiB
Python
52 lines
1.4 KiB
Python
# SPDX-License-Identifier: MIT
|
|
# Copyright (c) 2026 Rug Munch Media LLC
|
|
#
|
|
# Part of Pry — https://git.rugmunch.io/RugMunchMedia/pryscraper
|
|
# Licensed under MIT. See LICENSE.
|
|
"""Tests for SEO content monitor."""
|
|
|
|
from seo_monitor import (
|
|
_count_words,
|
|
_get_headings,
|
|
_get_meta_from_html,
|
|
_get_title_from_html,
|
|
_has_schema,
|
|
)
|
|
|
|
|
|
def test_get_title_from_html() -> None:
|
|
html = "<html><head><title>My SEO Title</title></head><body></body></html>"
|
|
assert _get_title_from_html(html) == "My SEO Title"
|
|
|
|
|
|
def test_get_meta_from_html() -> None:
|
|
html = '<meta name="description" content="Test description here" />'
|
|
desc = _get_meta_from_html(html, "description")
|
|
assert desc == "Test description here"
|
|
|
|
|
|
def test_count_words() -> None:
|
|
html = "<p>Hello world this is a test</p>"
|
|
assert _count_words(html) == 6
|
|
|
|
|
|
def test_get_headings() -> None:
|
|
from lxml import html as lxml_html
|
|
|
|
tree = lxml_html.fromstring(
|
|
"<html><body><h1>Main Title</h1><h2>Sub One</h2><h2>Sub Two</h2></body></html>"
|
|
)
|
|
h1s = _get_headings(tree, "h1")
|
|
assert h1s == ["Main Title"]
|
|
h2s = _get_headings(tree, "h2")
|
|
assert len(h2s) == 2
|
|
|
|
|
|
def test_has_schema() -> None:
|
|
html = '<script type="application/ld+json">{"@context": "https://schema.org"}</script>'
|
|
assert _has_schema(html) is True
|
|
|
|
|
|
def test_has_no_schema() -> None:
|
|
html = "<html><body><p>No schema here</p></body></html>"
|
|
assert _has_schema(html) is False
|