263 lines
8.2 KiB
Python
263 lines
8.2 KiB
Python
|
"""Tests for CSFD.cz scraper module."""
|
||
|
|
|
||
|
|
import pytest
|
||
|
|
from unittest.mock import patch, MagicMock
|
||
|
|
from src.core.csfd import (
|
||
|
|
CSFDMovie,
|
||
|
|
fetch_movie,
|
||
|
|
search_movies,
|
||
|
|
fetch_movie_by_id,
|
||
|
|
_extract_csfd_id,
|
||
|
|
_parse_duration,
|
||
|
|
_extract_json_ld,
|
||
|
|
_extract_rating,
|
||
|
|
_extract_poster,
|
||
|
|
_extract_plot,
|
||
|
|
_extract_genres,
|
||
|
|
_extract_origin_info,
|
||
|
|
_check_dependencies,
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
# Sample HTML for testing
|
||
|
|
SAMPLE_JSON_LD = """
|
||
|
|
{
|
||
|
|
"@type": "Movie",
|
||
|
|
"name": "Test Movie",
|
||
|
|
"director": [{"@type": "Person", "name": "Test Director"}],
|
||
|
|
"actor": [{"@type": "Person", "name": "Actor 1"}, {"@type": "Person", "name": "Actor 2"}],
|
||
|
|
"aggregateRating": {"ratingValue": 85.5, "ratingCount": 1000},
|
||
|
|
"duration": "PT120M",
|
||
|
|
"description": "A test movie description."
|
||
|
|
}
|
||
|
|
"""
|
||
|
|
|
||
|
|
SAMPLE_HTML = """
|
||
|
|
<html>
|
||
|
|
<head>
|
||
|
|
<script type="application/ld+json">%s</script>
|
||
|
|
</head>
|
||
|
|
<body>
|
||
|
|
<div class="film-rating-average">85%%</div>
|
||
|
|
<div class="genres">
|
||
|
|
<a href="/zanry/1/">Drama</a> /
|
||
|
|
<a href="/zanry/2/">Thriller</a>
|
||
|
|
</div>
|
||
|
|
<div class="origin">Česko, 2020, 120 min</div>
|
||
|
|
<div class="film-poster">
|
||
|
|
<img src="//image.example.com/poster.jpg">
|
||
|
|
</div>
|
||
|
|
<div class="plot-full"><p>Full plot description.</p></div>
|
||
|
|
</body>
|
||
|
|
</html>
|
||
|
|
""" % SAMPLE_JSON_LD
|
||
|
|
|
||
|
|
|
||
|
|
class TestCSFDMovie:
|
||
|
|
"""Tests for CSFDMovie dataclass."""
|
||
|
|
|
||
|
|
def test_csfd_movie_basic(self):
|
||
|
|
"""Test basic CSFDMovie creation."""
|
||
|
|
movie = CSFDMovie(title="Test", url="https://csfd.cz/film/123/")
|
||
|
|
assert movie.title == "Test"
|
||
|
|
assert movie.url == "https://csfd.cz/film/123/"
|
||
|
|
assert movie.year is None
|
||
|
|
assert movie.genres == []
|
||
|
|
assert movie.rating is None
|
||
|
|
|
||
|
|
def test_csfd_movie_full(self):
|
||
|
|
"""Test CSFDMovie with all fields."""
|
||
|
|
movie = CSFDMovie(
|
||
|
|
title="Test Movie",
|
||
|
|
url="https://csfd.cz/film/123/",
|
||
|
|
year=2020,
|
||
|
|
genres=["Drama", "Thriller"],
|
||
|
|
directors=["Director 1"],
|
||
|
|
actors=["Actor 1", "Actor 2"],
|
||
|
|
rating=85,
|
||
|
|
rating_count=1000,
|
||
|
|
duration=120,
|
||
|
|
country="Česko",
|
||
|
|
poster_url="https://image.example.com/poster.jpg",
|
||
|
|
plot="A test movie.",
|
||
|
|
csfd_id=123
|
||
|
|
)
|
||
|
|
assert movie.year == 2020
|
||
|
|
assert movie.genres == ["Drama", "Thriller"]
|
||
|
|
assert movie.rating == 85
|
||
|
|
assert movie.duration == 120
|
||
|
|
assert movie.csfd_id == 123
|
||
|
|
|
||
|
|
def test_csfd_movie_str(self):
|
||
|
|
"""Test CSFDMovie string representation."""
|
||
|
|
movie = CSFDMovie(
|
||
|
|
title="Test Movie",
|
||
|
|
url="https://csfd.cz/film/123/",
|
||
|
|
year=2020,
|
||
|
|
genres=["Drama"],
|
||
|
|
directors=["Director 1"],
|
||
|
|
rating=85
|
||
|
|
)
|
||
|
|
s = str(movie)
|
||
|
|
assert "Test Movie (2020)" in s
|
||
|
|
assert "85%" in s
|
||
|
|
assert "Drama" in s
|
||
|
|
assert "Director 1" in s
|
||
|
|
|
||
|
|
def test_csfd_movie_str_minimal(self):
|
||
|
|
"""Test CSFDMovie string with minimal data."""
|
||
|
|
movie = CSFDMovie(title="Test", url="https://csfd.cz/film/123/")
|
||
|
|
s = str(movie)
|
||
|
|
assert "Test" in s
|
||
|
|
|
||
|
|
|
||
|
|
class TestHelperFunctions:
|
||
|
|
"""Tests for helper functions."""
|
||
|
|
|
||
|
|
def test_extract_csfd_id_valid(self):
|
||
|
|
"""Test extracting CSFD ID from valid URL."""
|
||
|
|
assert _extract_csfd_id("https://www.csfd.cz/film/9423-pane-vy-jste-vdova/") == 9423
|
||
|
|
assert _extract_csfd_id("https://www.csfd.cz/film/123456/") == 123456
|
||
|
|
assert _extract_csfd_id("/film/999/prehled/") == 999
|
||
|
|
|
||
|
|
def test_extract_csfd_id_invalid(self):
|
||
|
|
"""Test extracting CSFD ID from invalid URL."""
|
||
|
|
assert _extract_csfd_id("https://www.csfd.cz/") is None
|
||
|
|
assert _extract_csfd_id("not-a-url") is None
|
||
|
|
|
||
|
|
def test_parse_duration_valid(self):
|
||
|
|
"""Test parsing ISO 8601 duration."""
|
||
|
|
assert _parse_duration("PT97M") == 97
|
||
|
|
assert _parse_duration("PT120M") == 120
|
||
|
|
assert _parse_duration("PT60M") == 60
|
||
|
|
|
||
|
|
def test_parse_duration_invalid(self):
|
||
|
|
"""Test parsing invalid duration."""
|
||
|
|
assert _parse_duration("") is None
|
||
|
|
assert _parse_duration("invalid") is None
|
||
|
|
assert _parse_duration("PT") is None
|
||
|
|
|
||
|
|
|
||
|
|
class TestHTMLExtraction:
|
||
|
|
"""Tests for HTML extraction functions."""
|
||
|
|
|
||
|
|
@pytest.fixture
|
||
|
|
def soup(self):
|
||
|
|
"""Create BeautifulSoup object from sample HTML."""
|
||
|
|
from bs4 import BeautifulSoup
|
||
|
|
return BeautifulSoup(SAMPLE_HTML, "html.parser")
|
||
|
|
|
||
|
|
def test_extract_json_ld(self, soup):
|
||
|
|
"""Test extracting data from JSON-LD."""
|
||
|
|
data = _extract_json_ld(soup)
|
||
|
|
assert data["title"] == "Test Movie"
|
||
|
|
assert data["directors"] == ["Test Director"]
|
||
|
|
assert data["actors"] == ["Actor 1", "Actor 2"]
|
||
|
|
assert data["rating"] == 86 # Rounded from 85.5
|
||
|
|
assert data["rating_count"] == 1000
|
||
|
|
assert data["duration"] == 120
|
||
|
|
|
||
|
|
def test_extract_rating(self, soup):
|
||
|
|
"""Test extracting rating from HTML."""
|
||
|
|
rating = _extract_rating(soup)
|
||
|
|
assert rating == 85
|
||
|
|
|
||
|
|
def test_extract_genres(self, soup):
|
||
|
|
"""Test extracting genres from HTML."""
|
||
|
|
genres = _extract_genres(soup)
|
||
|
|
assert "Drama" in genres
|
||
|
|
assert "Thriller" in genres
|
||
|
|
|
||
|
|
def test_extract_poster(self, soup):
|
||
|
|
"""Test extracting poster URL."""
|
||
|
|
poster = _extract_poster(soup)
|
||
|
|
assert poster == "https://image.example.com/poster.jpg"
|
||
|
|
|
||
|
|
def test_extract_plot(self, soup):
|
||
|
|
"""Test extracting plot."""
|
||
|
|
plot = _extract_plot(soup)
|
||
|
|
assert plot == "Full plot description."
|
||
|
|
|
||
|
|
def test_extract_origin_info(self, soup):
|
||
|
|
"""Test extracting origin info."""
|
||
|
|
info = _extract_origin_info(soup)
|
||
|
|
assert info["country"] == "Česko"
|
||
|
|
assert info["year"] == 2020
|
||
|
|
assert info["duration"] == 120
|
||
|
|
|
||
|
|
|
||
|
|
class TestFetchMovie:
|
||
|
|
"""Tests for fetch_movie function."""
|
||
|
|
|
||
|
|
@patch("src.core.csfd.requests")
|
||
|
|
def test_fetch_movie_success(self, mock_requests):
|
||
|
|
"""Test successful movie fetch."""
|
||
|
|
mock_response = MagicMock()
|
||
|
|
mock_response.text = SAMPLE_HTML
|
||
|
|
mock_response.raise_for_status = MagicMock()
|
||
|
|
mock_requests.get.return_value = mock_response
|
||
|
|
|
||
|
|
movie = fetch_movie("https://www.csfd.cz/film/123-test/")
|
||
|
|
|
||
|
|
assert movie.title == "Test Movie"
|
||
|
|
assert movie.csfd_id == 123
|
||
|
|
assert movie.rating == 86
|
||
|
|
assert "Drama" in movie.genres
|
||
|
|
mock_requests.get.assert_called_once()
|
||
|
|
|
||
|
|
@patch("src.core.csfd.requests")
|
||
|
|
def test_fetch_movie_network_error(self, mock_requests):
|
||
|
|
"""Test network error handling."""
|
||
|
|
import requests as real_requests
|
||
|
|
mock_requests.get.side_effect = real_requests.RequestException("Network error")
|
||
|
|
|
||
|
|
with pytest.raises(real_requests.RequestException):
|
||
|
|
fetch_movie("https://www.csfd.cz/film/123/")
|
||
|
|
|
||
|
|
|
||
|
|
class TestSearchMovies:
|
||
|
|
"""Tests for search_movies function."""
|
||
|
|
|
||
|
|
@patch("src.core.csfd.requests")
|
||
|
|
def test_search_movies(self, mock_requests):
|
||
|
|
"""Test movie search."""
|
||
|
|
search_html = """
|
||
|
|
<html><body>
|
||
|
|
<a href="/film/123-test/" class="film-title-name">Test Movie</a>
|
||
|
|
<a href="/film/456-another/" class="film-title-name">Another Movie</a>
|
||
|
|
</body></html>
|
||
|
|
"""
|
||
|
|
mock_response = MagicMock()
|
||
|
|
mock_response.text = search_html
|
||
|
|
mock_response.raise_for_status = MagicMock()
|
||
|
|
mock_requests.get.return_value = mock_response
|
||
|
|
mock_requests.utils.quote = lambda x: x
|
||
|
|
|
||
|
|
results = search_movies("test", limit=10)
|
||
|
|
|
||
|
|
assert len(results) >= 1
|
||
|
|
assert any(m.csfd_id == 123 for m in results)
|
||
|
|
|
||
|
|
|
||
|
|
class TestFetchMovieById:
|
||
|
|
"""Tests for fetch_movie_by_id function."""
|
||
|
|
|
||
|
|
@patch("src.core.csfd.fetch_movie")
|
||
|
|
def test_fetch_by_id(self, mock_fetch):
|
||
|
|
"""Test fetching movie by ID."""
|
||
|
|
mock_fetch.return_value = CSFDMovie(title="Test", url="https://csfd.cz/film/9423/")
|
||
|
|
|
||
|
|
movie = fetch_movie_by_id(9423)
|
||
|
|
|
||
|
|
mock_fetch.assert_called_once_with("https://www.csfd.cz/film/9423/")
|
||
|
|
assert movie.title == "Test"
|
||
|
|
|
||
|
|
|
||
|
|
class TestDependencyCheck:
|
||
|
|
"""Tests for dependency checking."""
|
||
|
|
|
||
|
|
def test_dependencies_available(self):
|
||
|
|
"""Test that dependencies are available (they should be in test env)."""
|
||
|
|
# Should not raise
|
||
|
|
_check_dependencies()
|