Skip to content

Add HTML lang attribute SEO check #124

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
aouwalitshikkha wants to merge 1 commit into
base: main
Choose a base branch
from
+34 −0
Open

Add HTML lang attribute SEO check #124

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions pyseoanalyzer/page.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -273,6 +273,7 @@ def get_meta_value(key):
self.analyze_a_tags(soup_unmodified)
self.analyze_img_tags(soup_lower)
self.analyze_h1_tags(soup_lower)
self.analyze_html_lang(soup_lower)

if self.analyze_headings:
self.analyze_heading_tags(soup_unmodified)
Expand Down Expand Up @@ -449,6 +450,14 @@ def analyze_h1_tags(self, bs):
if len(htags) == 0:
self.warn("Each page should have at least one h1 tag")

def analyze_html_lang(self, bs):
"""
Make sure the HTML tag has a lang attribute
"""
html_tag = bs.find("html")
if html_tag is not None and not html_tag.get("lang"):
self.warn("Missing lang attribute on <html> tag")

def analyze_a_tags(self, bs):
"""
Add any new links (that we didn't find in the sitemap)
Expand Down
25 changes: 25 additions & 0 deletions tests/test_page.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,31 @@ def test_analyze():
assert "seth" in p.title.lower()


def test_analyze_html_lang_missing():
from bs4 import BeautifulSoup

p = page.Page(url="https://example.com/", base_domain="https://example.com/")
soup = BeautifulSoup(
"<html><head><title>Test</title></head><body><p>Hello</p></body></html>",
"html.parser",
)
p.analyze_html_lang(soup)
assert len(p.warnings) == 1
assert "lang" in p.warnings[0].lower()


def test_analyze_html_lang_present():
from bs4 import BeautifulSoup

p = page.Page(url="https://example.com/", base_domain="https://example.com/")
soup = BeautifulSoup(
'<html lang="en"><head><title>Test</title></head><body><p>Hello</p></body></html>',
"html.parser",
)
p.analyze_html_lang(soup)
assert len(p.warnings) == 0


def test_analyze_with_llm():
p = page.Page(
url="https://www.sethserver.com/",
Expand Down