"""Tests for NWSL scraper.""" from datetime import datetime from unittest.mock import patch import pytest from sportstime_parser.scrapers.nwsl import NWSLScraper, create_nwsl_scraper from sportstime_parser.scrapers.base import RawGameData from sportstime_parser.tests.fixtures import ( load_json_fixture, NWSL_ESPN_SCOREBOARD_JSON, ) class TestNWSLScraperInit: """Test NWSLScraper initialization.""" def test_creates_scraper_with_season(self): """Test scraper initializes with correct season.""" scraper = NWSLScraper(season=2026) assert scraper.sport == "nwsl" assert scraper.season == 2026 def test_factory_function_creates_scraper(self): """Test factory function creates correct scraper.""" scraper = create_nwsl_scraper(season=2026) assert isinstance(scraper, NWSLScraper) assert scraper.season == 2026 def test_expected_game_count(self): """Test expected game count is correct for NWSL.""" scraper = NWSLScraper(season=2026) assert scraper.expected_game_count == 182 def test_sources_in_priority_order(self): """Test sources are returned in correct priority order.""" scraper = NWSLScraper(season=2026) sources = scraper._get_sources() assert sources == ["espn"] class TestESPNParsing: """Test ESPN API response parsing.""" def test_parses_completed_games(self): """Test parsing completed games from ESPN.""" scraper = NWSLScraper(season=2026) data = load_json_fixture(NWSL_ESPN_SCOREBOARD_JSON) games = scraper._parse_espn_response(data, "http://espn.com/api") completed = [g for g in games if g.status == "final"] assert len(completed) == 2 # Angel City @ Thorns la_por = next(g for g in completed if g.away_team_raw == "Angel City FC") assert la_por.home_team_raw == "Portland Thorns FC" assert la_por.away_score == 1 assert la_por.home_score == 2 assert la_por.stadium_raw == "Providence Park" def test_parses_scheduled_games(self): """Test parsing scheduled games from ESPN.""" scraper = NWSLScraper(season=2026) data = load_json_fixture(NWSL_ESPN_SCOREBOARD_JSON) games = scraper._parse_espn_response(data, "http://espn.com/api") scheduled = [g for g in games if g.status == "scheduled"] assert len(scheduled) == 1 sd_bay = scheduled[0] assert sd_bay.away_team_raw == "San Diego Wave FC" assert sd_bay.home_team_raw == "Bay FC" assert sd_bay.stadium_raw == "PayPal Park" def test_parses_venue_info(self): """Test venue information is extracted.""" scraper = NWSLScraper(season=2026) data = load_json_fixture(NWSL_ESPN_SCOREBOARD_JSON) games = scraper._parse_espn_response(data, "http://espn.com/api") for game in games: assert game.stadium_raw is not None class TestGameNormalization: """Test game normalization and canonical ID generation.""" def test_normalizes_games_with_canonical_ids(self): """Test games are normalized with correct canonical IDs.""" scraper = NWSLScraper(season=2026) raw_games = [ RawGameData( game_date=datetime(2026, 4, 10), home_team_raw="Portland Thorns FC", away_team_raw="Angel City FC", stadium_raw="Providence Park", home_score=2, away_score=1, status="final", source_url="http://example.com", ) ] games, review_items = scraper._normalize_games(raw_games) assert len(games) == 1 game = games[0] # Check canonical ID format assert game.id == "nwsl_2026_anf_por_0410" assert game.sport == "nwsl" assert game.season == 2026 # Check team IDs assert game.home_team_id == "team_nwsl_por" assert game.away_team_id == "team_nwsl_anf" # Check scores preserved assert game.home_score == 2 assert game.away_score == 1 def test_creates_review_items_for_unresolved_teams(self): """Test review items are created for unresolved teams.""" scraper = NWSLScraper(season=2026) raw_games = [ RawGameData( game_date=datetime(2026, 4, 10), home_team_raw="Unknown Team XYZ", away_team_raw="Portland Thorns FC", stadium_raw="Providence Park", status="scheduled", ), ] games, review_items = scraper._normalize_games(raw_games) # Game should not be created due to unresolved team assert len(games) == 0 # But there should be a review item assert len(review_items) >= 1 class TestTeamAndStadiumScraping: """Test team and stadium data scraping.""" def test_scrapes_all_nwsl_teams(self): """Test all NWSL teams are returned.""" scraper = NWSLScraper(season=2026) teams = scraper.scrape_teams() # NWSL has 14 teams assert len(teams) == 14 # Check team IDs are unique team_ids = [t.id for t in teams] assert len(set(team_ids)) == 14 # Check all teams have required fields for team in teams: assert team.id.startswith("team_nwsl_") assert team.sport == "nwsl" assert team.city assert team.name assert team.full_name assert team.abbreviation def test_scrapes_all_nwsl_stadiums(self): """Test all NWSL stadiums are returned.""" scraper = NWSLScraper(season=2026) stadiums = scraper.scrape_stadiums() # Should have stadiums for all teams assert len(stadiums) == 14 # Check stadium IDs are unique stadium_ids = [s.id for s in stadiums] assert len(set(stadium_ids)) == 14 # Check all stadiums have required fields for stadium in stadiums: assert stadium.id.startswith("stadium_nwsl_") assert stadium.sport == "nwsl" assert stadium.name assert stadium.city assert stadium.state assert stadium.country == "USA" assert stadium.latitude != 0 assert stadium.longitude != 0 class TestScrapeFallback: """Test fallback behavior (NWSL only has ESPN).""" def test_returns_failure_when_espn_fails(self): """Test scraper returns failure when ESPN fails.""" scraper = NWSLScraper(season=2026) with patch.object(scraper, '_scrape_espn') as mock_espn: mock_espn.side_effect = Exception("ESPN failed") result = scraper.scrape_games() assert not result.success assert "All sources failed" in result.error_message class TestSeasonMonths: """Test season month calculation.""" def test_gets_correct_season_months(self): """Test correct months are returned for NWSL season.""" scraper = NWSLScraper(season=2026) months = scraper._get_season_months() # NWSL season is March-November assert len(months) == 9 # Mar, Apr, May, Jun, Jul, Aug, Sep, Oct, Nov # Check first month is March of season year assert months[0] == (2026, 3) # Check last month is November assert months[-1] == (2026, 11)