import unittest
import re
import io
import sys


# Helper from the Codefinity 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 import ------------
    def test_urlopen_imported(self):
        with open("user_code.py", "r") as f:
            src = f.read()

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

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

    # ------------ Test declared variables ------------
    def test_variables_declared(self):
        import user_code

        condition = (
            hasattr(user_code, "url") and
            hasattr(user_code, "page") and
            hasattr(user_code, "web_page")
        )

        _dynamic_test(
            self,
            condition,
            "Variables `url`, `page`, and `web_page` are declared.",
            "Expected variables `url`, `page`, and `web_page` to all be declared."
        )

    # ------------ Test read + decode ------------
    def test_read_and_decode_used(self):
        with open("user_code.py", "r") as f:
            src = f.read()

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

        _dynamic_test(
            self,
            condition,
            "The page content is read and decoded correctly.",
            "Expected use of `.read()` and `.decode('utf-8')`."
        )

    # ------------ Test web_page type ------------
    def test_web_page_is_string(self):
        import user_code
        try:
            value = user_code.web_page
            condition = isinstance(value, str)
            fail_msg = f"`web_page` should be a string but is `{type(value).__name__}`."
        except AttributeError:
            condition = False
            fail_msg = "`web_page` is not declared."

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

    # ------------ Test printed output ------------
    def test_printed_counts_are_correct(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().strip().splitlines()

        if len(output) < 2:
            _dynamic_test(
                self,
                False,
                "",
                "Expected two printed lines: number of `<div>` and number of `<img>`."
            )
            return

        # Interpret printed values
        try:
            div_printed = int(output[0])
            img_printed = int(output[1])
        except:
            _dynamic_test(
                self,
                False,
                "",
                "Printed values must be integers."
            )
            return

        # Expected values
        expected_div = user_code.web_page.count("<div")
        expected_img = user_code.web_page.count("<img")

        condition = (div_printed == expected_div and img_printed == expected_img)

        _dynamic_test(
            self,
            condition,
            "Correct counts for `<div>` and `<img>` are printed.",
            f"Expected divs={expected_div}, imgs={expected_img}, "
            f"but got divs={div_printed}, imgs={img_printed}."
        )


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: Count Number of Images

解答