import unittest
import re


# Helper function 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: urlopen import -----------------------------------------------
    def test_urlopen_is_imported(self):
        with open("user_code.py", "r") as file:
            source = file.read()

        condition = "from urllib.request import urlopen" in source

        _dynamic_test(
            self,
            condition,
            "The `urlopen` function is imported from `urllib.request`.",
            "Expected `urlopen` to be imported from `urllib.request`."
        )

    # --- Test 2: url variable exists ------------------------------------------
    def test_url_variable_declared(self):
        import user_code

        condition = hasattr(user_code, "url")

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

    # --- Test 3: page variable exists -----------------------------------------
    def test_page_variable_declared(self):
        import user_code

        condition = hasattr(user_code, "page")

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

    # --- Test 4: urlopen() used ------------------------------------------------
    def test_urlopen_is_used(self):
        with open("user_code.py", "r") as file:
            source = file.read()

        condition = "urlopen(" in source

        _dynamic_test(
            self,
            condition,
            "The `urlopen()` function is used to open the web page.",
            "Expected `urlopen()` to be used to open the web page."
        )

    # --- Test 5: web_page variable exists -------------------------------------
    def test_web_page_declared(self):
        import user_code

        condition = hasattr(user_code, "web_page")

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

    # --- Test 6: read() and decode("utf-8") used ------------------------------
    def test_read_and_decode_used(self):
        with open("user_code.py", "r") as file:
            source = file.read()

        condition = (
            ".read()" in source and
            '.decode("utf-8")' in source or
            ".decode('utf-8')" in source
        )

        _dynamic_test(
            self,
            condition,
            "The `read()` method and `.decode('utf-8')` are used to process the page.",
            "Expected the `read()` method and `.decode('utf-8')` to be used."
        )

    # --- Test 7: web_page is a string -----------------------------------------
    def test_web_page_is_string(self):
        import user_code

        try:
            value = user_code.web_page
            condition = isinstance(value, str)
            failure = (
                f"Expected `web_page` to be a string, "
                f"but got `{type(value).__name__}`."
            )
        except AttributeError:
            condition = False
            failure = "The `web_page` variable is not declared in `user_code`."

        _dynamic_test(
            self,
            condition,
            "The `web_page` variable contains a decoded string.",
            failure
        )


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


test_main.py

Aprenda a extraer datos valiosos de sitios web de forma automática. Domine técnicas para recopilar información de manera eficiente, permitiendo realizar análisis en profundidad, tomar decisiones basadas en datos y descubrir nuevos conocimientos a partir del vasto océano de información en línea.

Explora la estructura de un archivo HTML, aprende a cargarlo de manera eficiente y adquiere habilidades prácticas para trabajar con los datos que contiene.

Explora los conceptos básicos de Beautiful Soup para extraer datos de documentos HTML. Aprende a navegar por la estructura de HTML, acceder a elementos específicos y trabajar con sus elementos secundarios para construir una base sólida en web scraping.

Domine el trabajo con atributos y contenido de elementos utilizando Beautiful Soup. Adquiera las habilidades para extraer información específica, buscar elementos por valores de atributos y emplear técnicas avanzadas para analizar y procesar datos HTML de manera eficiente.

Desafío: Leer el Archivo HTML

Solución

Awesome!

Desafío: Leer el Archivo HTML

Solución