Identifying **orphan pages**—pages on your website that are not linked to by any other page—is a crucial step in improving site structure and SEO. **Orphan pages** are often overlooked by both users and search engines, resulting in poor discoverability and lower rankings. By programmatically detecting these pages, you can ensure your site is fully interconnected and optimized for crawling.


import unittest
import user_code
import ast
import re   
import importlib
import csv
import unittest
import importlib

class TestTask(unittest.TestCase):
    def test_returns_all_orphans(self):
        import user_code
        importlib.reload(user_code)
        site_structure = {
            "home": ["about", "contact"],
            "about": ["home"],
            "contact": [],
            "blog": ["home"],
            "faq": []
        }
        result = user_code.find_orphan_pages(site_structure)
        expected = ["blog", "faq"]
        _dynamic_test(
            self,
            isinstance(result, list) and set(result) == set(expected),
            "Correctly returns all orphan pages.",
            f"Expected {expected}, got {result}.",
        )

    def test_excludes_linked_pages(self):
        import user_code
        importlib.reload(user_code)
        site_structure = {
            "a": ["b"],
            "b": ["c"],
            "c": ["a"],
            "d": [],
            "e": []
        }
        result = user_code.find_orphan_pages(site_structure)
        expected = ["d", "e"]
        _dynamic_test(
            self,
            isinstance(result, list) and set(result) == set(expected),
            f"Correctly excludes any page that is linked.",
            f"Expected {expected}, got {result}.",
        )

    def test_all_pages_linked(self):
        import user_code
        importlib.reload(user_code)
        site_structure = {
            "a": ["b"],
            "b": ["c"],
            "c": ["a"]
        }
        result = user_code.find_orphan_pages(site_structure)
        expected = []
        _dynamic_test(
            self,
            isinstance(result, list) and result == expected,
            "Returns empty list when all pages are linked.",
            f"Expected {expected}, got {result}.",
        )

    def test_all_pages_orphans(self):
        import user_code
        importlib.reload(user_code)
        site_structure = {
            "a": [],
            "b": [],
            "c": []
        }
        result = user_code.find_orphan_pages(site_structure)
        expected = ["a", "b", "c"]
        _dynamic_test(
            self,
            isinstance(result, list) and set(result) == set(expected),
            "Returns all pages if none are linked.",
            f"Expected {expected}, got {result}.",
        )

    def test_empty_structure(self):
        import user_code
        importlib.reload(user_code)
        site_structure = {}
        result = user_code.find_orphan_pages(site_structure)
        expected = []
        _dynamic_test(
            self,
            isinstance(result, list) and result == expected,
            "Returns empty list for empty site structure.",
            f"Expected {expected}, got {result}.",
        )

def _dynamic_test(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
        test_case.assertTrue(True, success_message)
    else:
        test_case._testMethodName = failure_message
        test_case.fail(failure_message)

def normalize_text(text):
    text = text.lower()
    text = re.sub(r"\\s{2,}", " ", text)
    text = re.sub(r"\\s*([,:?])\\s*", r"\\1 ", text)
    return text.strip()

def change_var(code: str, var_name: str, value: str) -> str:
    tree = ast.parse(code)
    lines = code.splitlines()
    changed = False
    # Collect all assignment nodes to modify
    assign_nodes = [
        (i, node)
        for i, node in enumerate(tree.body)
        if isinstance(node, ast.Assign)
        and any(isinstance(target, ast.Name) and target.id == var_name for target in node.targets)
    ]

    # If nothing to change, return unmodified code
    if not assign_nodes:
        return code

    # Perform replacements for all matching assignments (from last to first to not break line offsets)
    for i, node in reversed(assign_nodes):
        start_line = node.lineno - 1
        line = lines[start_line]
        indent = ' ' * (len(line) - len(line.lstrip()))
        lines[start_line] = f"{indent}{var_name} = {value}"
        next_line = len(lines)
        for next_node in tree.body[i+1:]:
            if hasattr(next_node, 'lineno'):
                next_line = next_node.lineno - 1
                break
        if next_line > start_line + 1:
            lines[start_line+1:next_line] = []
        changed = True

    return '\\n'.join(lines) if changed else code

if __name__ == "__main__":
    unittest.main()


test_main.py

Master the use of Python to automate, analyze, and optimize SEO workflows. This course guides SEO professionals through practical Python applications for keyword research, on-page analysis, and technical SEO, using real-world scenarios and hands-on coding tasks.

Learn how Python can automate repetitive SEO tasks, from scraping search results to generating meta tags, making your SEO workflow more efficient.

Explore how Python can be used to analyze keyword data, identify opportunities, and visualize keyword trends for SEO campaigns.

Apply Python to analyze on-page SEO elements and perform technical audits, including content checks, tag analysis, and site structure evaluation.

Challenge: Find Orphan Pages

Ratkaisu