import unittest
import io
import sys


def _dynamic_test(test_case, cond, ok, fail):
    if cond:
        test_case._testMethodName = ok
        test_case.assertTrue(True)
    else:
        test_case._testMethodName = fail
        test_case.fail(fail)


def normalize(text):
    return " ".join(text.split())


class TestUserCode(unittest.TestCase):

    def test_import(self):
        with open("user_code.py") as f:
            src = f.read()

        cond = "from bs4 import BeautifulSoup" in src

        _dynamic_test(
            self,
            cond,
            "Imported BeautifulSoup.",
            "BeautifulSoup not imported."
        )

    def test_soup_exists(self):
        import user_code
        cond = hasattr(user_code, "soup")

        _dynamic_test(self, cond, "`soup` exists.", "`soup` missing.")

    def test_soup_valid(self):
        import user_code
        from bs4 import BeautifulSoup

        try:
            cond = isinstance(user_code.soup, BeautifulSoup)
        except:
            cond = False

        _dynamic_test(self, cond, "`soup` ok.", "`soup` invalid.")

    def test_html_string(self):
        import user_code

        try:
            cond = isinstance(user_code.html, str)
        except:
            cond = False

        _dynamic_test(self, cond, "`html` ok.", "`html` invalid.")

    def test_output(self):
        import user_code
        import importlib

        buf = io.StringIO()
        sys.stdout = buf
        importlib.reload(user_code)
        sys.stdout = sys.__stdout__

        lines = buf.getvalue().splitlines()

        if len(lines) < 2:
            _dynamic_test(self, False, "", "Not enough output.")
            return

        # First line: p attributes
        printed_attrs = lines[0].strip()
        expected_attrs = str(user_code.soup.p.attrs)

        if printed_attrs != expected_attrs:
            _dynamic_test(self, False, "", "Wrong p attrs.")
            return

        # Remaining lines: UL text
        printed_ul_block = " ".join([ln.strip() for ln in lines[1:] if ln.strip()])
        printed_ul_norm = normalize(printed_ul_block)

        expected_ul_norm = normalize(user_code.soup.ul.get_text())

        if printed_ul_norm != expected_ul_norm:
            _dynamic_test(self, False, "", "Wrong UL text.")
            return

        _dynamic_test(self, True, "Correct output.", "")


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: Attributes

解答