Summary  
This chapter covers selecting and manipulating paragraph elements in the DOM, including updating their text content and styling programmatically.

General domain of usage  
Web development (client-side)

import unittest
import io
import sys


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


class TestUserCode(unittest.TestCase):

    # -------- 1. Check import --------
    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.",
            "Expected `from bs4 import BeautifulSoup` import."
        )

    # -------- 2. soup exists --------
    def test_soup_declared(self):
        import user_code

        condition = hasattr(user_code, "soup")

        _dynamic_test(
            self,
            condition,
            "`soup` variable is declared.",
            "`soup` variable is missing."
        )

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

        try:
            s = user_code.soup
            condition = isinstance(s, BeautifulSoup)
            fail_msg = "`soup` must be a BeautifulSoup instance."
        except:
            condition = False
            fail_msg = "`soup` is missing or invalid."

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

    # -------- 4. html is decoded string --------
    def test_html_is_string(self):
        import user_code

        try:
            h = user_code.html
            condition = isinstance(h, str)
            fail_msg = f"`html` must be str, got `{type(h).__name__}`."
        except:
            condition = False
            fail_msg = "`html` variable missing."

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

    # -------- 5. p is correct list of <p> elements --------
    def test_p_is_correct(self):
        import user_code

        try:
            p_val = user_code.p
            is_list = isinstance(p_val, list)
        except:
            is_list = False

        _dynamic_test(
            self,
            is_list,
            "`p` is a list of `<p>` elements.",
            "`p` must be a list returned by `soup.find_all('p')`."
        )

    # -------- 6. printed output matches p and len(p) --------
    def test_printed_output(self):
        import user_code
        import importlib

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

        importlib.reload(user_code)

        sys.stdout = sys.__stdout__

        output = captured.getvalue().splitlines()

        if len(output) < 2:
            _dynamic_test(
                self,
                False,
                "",
                "Expected two printed lines: list of `<p>` elements and its length."
            )
            return

        printed_list = output[0].strip()
        printed_len = output[1].strip()

        # Expected values
        expected_list = str(user_code.p)
        expected_len = str(len(user_code.p))

        cond_list = printed_list == expected_list
        cond_len = printed_len == expected_len

        if not cond_list:
            _dynamic_test(
                self,
                False,
                "",
                f"Expected printed list `{expected_list}`, got `{printed_list}`."
            )
            return

        if not cond_len:
            _dynamic_test(
                self,
                False,
                "",
                f"Expected printed length `{expected_len}`, got `{printed_len}`."
            )
            return

        _dynamic_test(
            self,
            True,
            "The list of `<p>` elements and its length are printed correctly.",
            ""
        )


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


test_code.py

Leer waardevolle gegevens automatisch van websites te extraheren. Beheers technieken om efficiënt informatie te verzamelen, waardoor diepgaande analyses, datagedreven besluitvorming en het ontsluiten van nieuwe inzichten uit de enorme hoeveelheid online informatie mogelijk worden.

Ontdek de structuur van een HTML-bestand, leer hoe u het efficiënt kunt laden en verkrijg praktische vaardigheden in het werken met de gegevens die het bevat.

Verken de basisprincipes van Beautiful Soup voor het extraheren van gegevens uit HTML-documenten. Leer hoe u de structuur van HTML navigeert, specifieke elementen benadert en werkt met hun kindelementen om een solide basis te leggen in webscraping.

Beheers het werken met elementattributen en inhoud met Beautiful Soup. Ontwikkel vaardigheden om specifieke informatie te extraheren, elementen te zoeken op attribuutwaarden en geavanceerde technieken toe te passen voor het efficiënt parseren en analyseren van HTML-data.

Werken met Paragraafelementen

Oplossing