import unittest
import io
import sys


# Helper from the checklist
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)


class TestUserCode(unittest.TestCase):

    # --------- Test 1: BeautifulSoup imported ---------
    def test_beautifulsoup_imported(self):
        with open("user_code.py", "r") as f:
            src = f.read()

        condition = "from bs4 import BeautifulSoup" in src

        _dynamic_test(
            self,
            condition,
            "The `BeautifulSoup` class is imported correctly.",
            "Expected `BeautifulSoup` to be imported from `bs4`."
        )

    # --------- Test 2: soup variable declared ---------
    def test_soup_variable_declared(self):
        import user_code

        condition = hasattr(user_code, "soup")

        _dynamic_test(
            self,
            condition,
            "The `soup` variable is declared.",
            "Expected `soup` variable to be declared."
        )

    # --------- Test 3: soup is BeautifulSoup instance ---------
    def test_soup_is_beautifulsoup(self):
        import user_code
        from bs4 import BeautifulSoup

        try:
            value = user_code.soup
            condition = isinstance(value, BeautifulSoup)
            fail_msg = "`soup` should be a BeautifulSoup object."
        except Exception:
            condition = False
            fail_msg = "`soup` is not declared or not a BeautifulSoup object."

        _dynamic_test(
            self,
            condition,
            "`soup` is a valid BeautifulSoup instance.",
            fail_msg
        )

    # --------- Test 4: HTML loaded correctly ---------
    def test_html_is_string(self):
        import user_code

        try:
            html_value = user_code.html
            condition = isinstance(html_value, str)
            fail_msg = f"`html` must be a string, got `{type(html_value).__name__}`."
        except:
            condition = False
            fail_msg = "`html` variable is not declared."

        _dynamic_test(
            self,
            condition,
            "`html` contains decoded HTML text.",
            fail_msg
        )

    # --------- Test 5: First h1 printed ---------
    def test_first_h1_printed_correctly(self):
        import user_code
        import importlib
        from bs4 import BeautifulSoup

        # Capture stdout
        captured = io.StringIO()
        sys.stdout = captured

        importlib.reload(user_code)

        sys.stdout = sys.__stdout__

        output = captured.getvalue().strip().splitlines()

        if len(output) == 0:
            _dynamic_test(
                self,
                False,
                "",
                "Expected at least one printed line containing the first <h1> tag."
            )
            return

        printed = output[0].strip()

        # Compute correct h1 from raw html
        expected_h1 = BeautifulSoup(user_code.html, "html.parser").h1

        condition = printed == str(expected_h1)

        _dynamic_test(
            self,
            condition,
            "The first `<h1>` tag is printed correctly.",
            f"Expected printed h1 `{expected_h1}`, but got `{printed}`."
        )


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


test_code.py

Learn to extract valuable data from websites automatically. Master techniques to gather information efficiently, enabling you to perform in-depth analysis, make data-driven decisions, and unlock new insights from the vast ocean of online information.

Explore the structure of an HTML file, learn how to load it efficiently, and gain practical skills in working with the data it contains.

Explore the basics of Beautiful Soup to extract data from HTML documents. Learn how to navigate the structure of HTML, access specific elements, and work with their child elements to build a strong foundation in web scraping.

Master working with element attributes and content using Beautiful Soup. Gain the skills to extract specific information, search elements by attribute values, and use advanced techniques to efficiently parse and analyze HTML data.

Challenge: The BeautifulSoup Object

解答