.gitignore

@@ -0,0 +1,36 @@
+# Secrets: personal tokens are never part of the project
+.env
+.env.*
+
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+build/
+dist/
+.eggs/
+
+# Virtual environments
+.venv/
+venv/
+env/
+
+# Test, type and lint caches
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.coverage
+coverage.xml
+htmlcov/
+
+# Doxygen output
+docs/api/
+
+# Editors and operating systems
+.idea/
+.vscode/
+.DS_Store
+Thumbs.db
+
+# AI prompt log (public repository)
+/docs/ai-prompts/

pyproject.toml

@@ -0,0 +1,48 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "scrape-movies"
+version = "0.1.0"
+description = "Day 45 of 100 Days of Code: web scraping with Requests and BeautifulSoup (Hacker News and the Empire 100 greatest movies)."
+readme = "README.md"
+requires-python = ">=3.13"
+license = { file = "LICENSE" }
+dependencies = [
+    "requests>=2.32",
+    "beautifulsoup4>=4.12",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.3",
+    "pytest-cov>=5.0",
+    "ruff>=0.6",
+    "mypy>=1.11",
+    "types-requests>=2.32",
+]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+
+[tool.ruff]
+line-length = 88
+src = ["src", "tests"]
+extend-exclude = ["framework", ".agents", ".claude"]
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "N", "UP", "B", "D"]
+ignore = ["D203", "D213"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**" = ["D"]
+
+[tool.mypy]
+strict = true
+python_version = "3.13"
+mypy_path = "src"

src/scrape_movies/__init__.py

@@ -0,0 +1 @@
+"""@brief Day 45 scraping exercises: soup basics, Hacker News and 100 movies."""

src/scrape_movies/application/__init__.py

@@ -0,0 +1 @@
+"""@brief Use cases and the ports they need; imports only the domain."""

src/scrape_movies/constants.py

@@ -0,0 +1,34 @@
+"""@brief All constants of the project (URLs, limits, paths, parser name)."""
+
+from pathlib import Path
+
+## Root folder of the repository (two levels above this file's package folder).
+PROJECT_ROOT: Path = Path(__file__).resolve().parents[2]
+## Folder with the saved pages the tests and the lecture steps read.
+FIXTURES_DIR: Path = PROJECT_ROOT / "tests" / "fixtures"
+## The sample page from the "Parsing HTML and Making Soup" lecture.
+WEBSITE_HTML_PATH: Path = FIXTURES_DIR / "website.html"
+
+## Parser handed to BeautifulSoup; it is part of the standard library.
+HTML_PARSER: str = "html.parser"
+
+## Seconds to wait for a web server before giving up.
+REQUEST_TIMEOUT_SECONDS: int = 10
+## Sent with every request so a site owner can see who asks.
+USER_AGENT: str = "scrape-movies/0.1 (Udemy 100 Days of Code, Day 45)"
+
+## The course's static copy of the Hacker News front page.
+HACKER_NEWS_URL: str = "https://appbrewery.github.io/news.ycombinator.com/"
+## The live Hacker News front page (scrape it at most once a minute).
+HACKER_NEWS_LIVE_URL: str = "https://news.ycombinator.com/news"
+
+## Internet Archive snapshot of the Empire list, as the assignment requires.
+EMPIRE_WAYBACK_URL: str = (
+    "https://web.archive.org/web/20200518073855/"
+    "https://www.empireonline.com/movies/features/best-movies-2/"
+)
+## The live Empire page, an alternative that may have changed its markup.
+EMPIRE_LIVE_URL: str = "https://www.empireonline.com/movies/features/best-movies-2/"
+
+## File the movie list is written to.
+MOVIES_OUTPUT_FILE: str = "movies.txt"

src/scrape_movies/domain/__init__.py

@@ -0,0 +1 @@
+"""@brief Business rules and entities; imports nothing from other layers."""

src/scrape_movies/infrastructure/__init__.py

@@ -0,0 +1 @@
+"""@brief Adapters for the web, BeautifulSoup and files; implements the ports."""

src/scrape_movies/presentation/__init__.py

@@ -0,0 +1 @@
+"""@brief Command-line entry point; calls the use cases."""