def get_dist_page_type()

in src/dist.py [0:0]

• 28 lines of code
• 16 McCabe index (conditional complexity)

def get_dist_page_type(url):
    page_type = None

    if url.endswith('/') or url.endswith('.html'):
        page_type = 'Page'

        if url.startswith('community'):
            page_type = 'Page_Community'
        if url.startswith('docs/reference'):
            page_type = 'Page_Reference'
        if url.startswith('docs/tutorials'):
            page_type = 'Page_Tutorial'
        if url.endswith('404.html'):
            page_type = 'Page_NotFound'

        parsed = get_dist_page_xml(url)

        if url.startswith("/api/latest/"):
            page_type = "Page_API_stdlib" if "jvm/stdlib" in url else "Page_API_test"

        if url.startswith("/spec/"):
            page_type = "Page_Spec"

        if parsed.select_one("body[data-article-props]"):
            page_type = 'Page_Documentation'

        if parsed.find("meta", {"http-equiv": "refresh"}):
            page_type = 'Redirect'

        if parsed.find("meta", {"name": "robots", "content": "noindex"}):
            page_type = 'Hidden'

    if url.endswith('pdf'):
        page_type = 'File_Pdf'

    if url.endswith('package-list') or url.endswith('index.yml'):
        page_type = 'File_Text'

    return page_type