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

Apprenez à extraire automatiquement des données précieuses à partir de sites web. Maîtrisez des techniques pour collecter efficacement des informations, permettant d’effectuer des analyses approfondies, de prendre des décisions fondées sur les données et de découvrir de nouveaux aperçus à partir de l’immense volume d’informations en ligne.

Explorer la structure d’un fichier HTML, apprendre à le charger efficacement et acquérir des compétences pratiques dans la manipulation des données qu’il contient.

Découvrez les principes fondamentaux de Beautiful Soup pour extraire des données à partir de documents HTML. Apprenez à naviguer dans la structure du HTML, à accéder à des éléments spécifiques et à manipuler leurs éléments enfants afin de consolider les bases du web scraping.

Maîtrise de la gestion des attributs d’élément et du contenu avec Beautiful Soup. Acquisition des compétences pour extraire des informations spécifiques, rechercher des éléments par valeurs d’attributs et utiliser des techniques avancées pour analyser et parser efficacement des données HTML.

Travail Avec les Éléments de Paragraphe

Solution