import unittest
import io
import sys


def _dynamic(test, cond, ok, fail):
    if cond:
        test._testMethodName = ok
        test.assertTrue(True)
    else:
        test._testMethodName = fail
        test.fail(fail)


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

    def test_soup_exists(self):
        import user_code
        cond = hasattr(user_code, "soup")
        _dynamic(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(self, cond, "`soup` ok.", "`soup` invalid.")

    def test_html_valid(self):
        import user_code
        try:
            cond = isinstance(user_code.html, str)
        except:
            cond = False
        _dynamic(self, cond, "`html` ok.", "`html` invalid.")

    def test_output(self):
        import user_code
        import importlib
        from bs4 import BeautifulSoup

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

        lines = [ln for ln in buf.getvalue().splitlines() if ln.strip()]

        # expected <a> attributes
        expected_a = [str(a.attrs) for a in user_code.soup.find_all("a")]
        # expected <p> text
        expected_p = [p.get_text() for p in user_code.soup.find_all("p")]

        expected_all = expected_a + expected_p

        if len(lines) != len(expected_all):
            _dynamic(
                self,
                False,
                "",
                "Wrong number of printed lines."
            )
            return

        for printed, expected in zip(lines, expected_all):
            if printed.strip() != expected.strip():
                _dynamic(
                    self,
                    False,
                    "",
                    "Printed content mismatch."
                )
                return

        _dynamic(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: Text from HTML Elements

解答