First optional check to be implemented. - See https://github.com/kapt-labs/django-check-seo/wiki/Custom-Checks

__init__.py

# optional file, see https://github.com/kapt-labs/django-check-seo/wiki/How-to-add-a-check%3F

# Standard Library
import glob
from os.path import basename, dirname, isfile, join
import sys, json

from django.conf import settings

# list files
modules = glob.glob(join(dirname(__file__), "*.py"))

__all__ = []

# add them to __all__ so they can be imported
for module in modules:
    if (
        isfile(module)
        and not module.endswith("__init__.py")
    ):
        __all__.append(basename(module)[:-3])

check_broken_links.py

# Standard Library
import os
import importlib

# Third party
import bs4
from django.utils.translation import gettext as _, pgettext
import requests

# Local application / specific library imports
from django_check_seo.checks import custom_list

def importance():
    """Scripts with higher importance will be executed in first.

    Returns:
        int -- Importance of the script.
    """
    return 1


def run(site):
    """Counts the number of internal and external links in the extracted content.

    Arguments:
        site {Site} -- Structure containing a good amount of resources from the targeted webpage.
    """

    broken_internal = custom_list.CustomList(
        name=_("Found broken internal links"),
        settings=pgettext("masculin", "none"),
        description=_(
            "Neither Google nor users like broken links. Consider setting up redirections rather than deleting content on your site."
        ),
    )

    working_internal = custom_list.CustomList(
        name=_("No broken internal link found"),
        settings=pgettext("masculin", "none"),
        found=pgettext("masculin", "none"),
        description=broken_internal.description,
    )



    links = bs4.element.ResultSet(None)

    # only get links with href
    for c in site.content:
        links += c.find_all("a", href=True)

    internal_links = 0
    internal_links_list = []
    external_links = 0

    for link in links:
        # internal links = absolute links that contains domain name or relative links
        if os.environ["DOMAIN_NAME"] in link["href"] or not link["href"].startswith(
            "http"
        ):
            internal_links += 1
            internal_links_list.append(link)
        else:
            external_links += 1


    # prevent using domain name for loading internal links when testing another website's page
    if os.environ["DOMAIN_NAME"] not in site.full_url:
        domain = site.full_url
        if site.full_url.endswith("/"):
            domain = domain[:-1]
    else:
        domain = "http://" + os.environ["DOMAIN_NAME"]

    # broken internal links
    broken_links = []
    link_text = _("link")
    for link in internal_links_list:

        # prevent bugs if link is absolute and not relative
        if link["href"].startswith("/"):
            link["href"] = domain + link["href"]

        r = requests.get(link["href"]).status_code

        # status is not success or redirect
        if r != 200 and r != 301 and r != 302:
            broken_links.append(
                '<a target="_blank" title="broken link" href="'
                + link["href"]
                + '">'
                + link_text
                + "</a>"
            )

    if len(broken_links) > 0:
        broken_internal.found = str(len(broken_links)) + " - " + ", ".join(broken_links)
        broken_internal.searched_in = [link.text for link in internal_links_list]
        site.problems.append(broken_internal)

    else:
        working_internal.searched_in = [link.text for link in internal_links_list]
        site.success.append(working_internal)