[foods] Add recipe website parsing

2026-03-06 10:46:34 -05:00
parent 210ff0a4aa
commit 770a51b9c0
12 changed files with 1493 additions and 29 deletions
--- a/tests/foods_tests/init.py
+++ b/tests/foods_tests/init.py
--- a/tests/foods_tests/test_recipe_scraper.py
+++ b/tests/foods_tests/test_recipe_scraper.py
@ -0,0 +1,198 @@
+import pytest
+from foods.sources.rscraper import (
+    RecipeScraperService,
+)
+
+
+RECIPE_HTML_WITH_SCHEMA = """
+<!DOCTYPE html>
+<html>
+<head>
+    <script type="application/ld+json">
+    {
+        "@context": "https://schema.org/",
+        "@type": "Recipe",
+        "name": "Test Recipe",
+        "author": {
+            "@type": "Person",
+            "name": "Test Author"
+        },
+        "recipeIngredient": ["1 cup flour", "2 eggs", "1/2 cup sugar"],
+        "recipeInstructions": [
+            {
+                "@type": "HowToStep",
+                "text": "Mix ingredients together"
+            }
+        ],
+        "totalTime": "PT30M",
+        "recipeYield": "4 servings"
+    }
+    </script>
+</head>
+<body>
+    <h1>Test Recipe</h1>
+</body>
+</html>
+"""
+
+RECIPE_HTML_WITHOUT_SCHEMA = """
+<!DOCTYPE html>
+<html>
+<head>
+    <title>Not a Recipe Page</title>
+</head>
+<body>
+    <h1>Welcome to My Blog</h1>
+    <p>This is just a regular blog post about cooking.</p>
+</body>
+</html>
+"""
+
+RECIPE_HTML_WITH_MICRODATA = """
+<!DOCTYPE html>
+<html>
+<head>
+    <title>Test Recipe</title>
+</head>
+<body itemscope itemtype="http://schema.org/Recipe">
+    <h1 itemprop="name">Microdata Recipe</h1>
+    <div itemprop="author" itemscope itemtype="http://schema.org/Person">
+        <span itemprop="name">Test Author</span>
+    </div>
+    <div itemprop="recipeIngredient">1 cup flour</div>
+    <div itemprop="recipeIngredient">2 eggs</div>
+    <div itemprop="recipeInstructions">
+        <div itemprop="text">Mix all ingredients</div>
+    </div>
+</body>
+</html>
+"""
+
+
+class TestRecipeScraperService:
+    @pytest.fixture
+    def scraper(self):
+        return RecipeScraperService()
+
+    def test_is_recipe_with_valid_schema(self, scraper):
+        result = scraper.is_recipe(
+            RECIPE_HTML_WITH_SCHEMA, "https://example.com/recipe"
+        )
+        assert result is True
+
+    def test_is_recipe_without_schema(self, scraper):
+        result = scraper.is_recipe(
+            RECIPE_HTML_WITHOUT_SCHEMA, "https://example.com/blog"
+        )
+        assert result is False
+
+    def test_is_recipe_with_microdata(self, scraper):
+        result = scraper.is_recipe(
+            RECIPE_HTML_WITH_MICRODATA, "https://example.com/recipe"
+        )
+        assert result is True
+
+    def test_scrape_returns_title(self, scraper):
+        result = scraper.scrape(
+            RECIPE_HTML_WITH_SCHEMA, "https://example.com/recipe"
+        )
+        assert result["title"] == "Test Recipe"
+
+    def test_scrape_returns_ingredients(self, scraper):
+        result = scraper.scrape(
+            RECIPE_HTML_WITH_SCHEMA, "https://example.com/recipe"
+        )
+        assert len(result["ingredients"]) == 3
+        assert "1 cup flour" in result["ingredients"]
+
+    def test_scrape_returns_instructions(self, scraper):
+        result = scraper.scrape(
+            RECIPE_HTML_WITH_SCHEMA, "https://example.com/recipe"
+        )
+        assert len(result["instructions"]) > 0
+        assert "Mix ingredients together" in result["instructions"]
+
+    def test_scrape_returns_yields(self, scraper):
+        result = scraper.scrape(
+            RECIPE_HTML_WITH_SCHEMA, "https://example.com/recipe"
+        )
+        assert result["yields"] == "4 servings"
+
+    def test_scrape_returns_total_time(self, scraper):
+        result = scraper.scrape(
+            RECIPE_HTML_WITH_SCHEMA, "https://example.com/recipe"
+        )
+        assert result["total_time"] == 30
+
+    def test_scrape_returns_url(self, scraper):
+        result = scraper.scrape(
+            RECIPE_HTML_WITH_SCHEMA, "https://example.com/recipe"
+        )
+        assert result["url"] == "https://example.com/recipe"
+
+    def test_scrape_raises_on_invalid_html(self, scraper):
+        with pytest.raises(ValueError):
+            scraper.scrape("", "https://example.com/recipe")
+
+    def test_scrape_handles_missing_optional_fields(self, scraper):
+        minimal_html = """
+        <!DOCTYPE html>
+        <html>
+        <head>
+            <script type="application/ld+json">
+            {
+                "@context": "https://schema.org/",
+                "@type": "Recipe",
+                "name": "Minimal Recipe"
+            }
+            </script>
+        </head>
+        <body></body>
+        </html>
+        """
+        result = scraper.scrape(minimal_html, "https://example.com/minimal")
+        assert result["title"] == "Minimal Recipe"
+        assert result["ingredients"] == []
+        assert result["instructions"] == []
+
+    def test_parse_servings(self, scraper):
+        assert scraper.parse_servings("4 servings") == 4
+        assert scraper.parse_servings("6 people") == 6
+        assert scraper.parse_servings("2") == 2
+        assert scraper.parse_servings("serves 8") == 8
+        assert scraper.parse_servings(None) is None
+        assert scraper.parse_servings("") is None
+
+    def test_extract_tags_from_cuisine(self, scraper):
+        recipe_data = {"cuisine": "Italian"}
+        tags = scraper.extract_tags(recipe_data)
+        assert "Italian" in tags
+
+    def test_extract_tags_from_cuisine_list(self, scraper):
+        recipe_data = {"cuisine": ["Italian", "Mexican"]}
+        tags = scraper.extract_tags(recipe_data)
+        assert "Italian" in tags
+        assert "Mexican" in tags
+
+    def test_extract_tags_from_dietary(self, scraper):
+        recipe_data = {"dietary": "Gluten-Free"}
+        tags = scraper.extract_tags(recipe_data)
+        assert "Gluten-Free" in tags
+
+    def test_extract_tags_from_course(self, scraper):
+        recipe_data = {"course": "Dessert"}
+        tags = scraper.extract_tags(recipe_data)
+        assert "Dessert" in tags
+
+    def test_extract_tags_from_keywords(self, scraper):
+        recipe_data = {"keywords": "easy, quick, healthy"}
+        tags = scraper.extract_tags(recipe_data)
+        assert "easy" in tags
+        assert "quick" in tags
+        assert "healthy" in tags
+
+    def test_extract_tags_from_keywords_list(self, scraper):
+        recipe_data = {"keywords": ["comfort food", "winter"]}
+        tags = scraper.extract_tags(recipe_data)
+        assert "comfort food" in tags
+        assert "winter" in tags
--- a/tests/foods_tests/test_usda.py
+++ b/tests/foods_tests/test_usda.py
@ -0,0 +1,135 @@
+import pytest
+from unittest.mock import patch
+from foods.sources.usda import (
+    USDAFoodAPI,
+    NutritionCalculator,
+)
+
+
+class TestUSDAFoodAPI:
+    @pytest.fixture
+    def usda_api(self):
+        with patch(
+            "vrobbler.apps.foods.sources.usda.settings"
+        ) as mock_settings:
+            mock_settings.USDA_API_KEY = "test_api_key"
+            return USDAFoodAPI(api_key="test_api_key")
+
+    def test_extract_nutrients_with_nutrient_number(self, usda_api):
+        food_data = {
+            "description": "Test Food",
+            "foodNutrients": [
+                {
+                    "nutrientNumber": "203",
+                    "nutrientName": "Protein",
+                    "value": 10.0,
+                },
+                {
+                    "nutrientNumber": "204",
+                    "nutrientName": "Total lipid (fat)",
+                    "value": 5.0,
+                },
+                {
+                    "nutrientNumber": "205",
+                    "nutrientName": "Carbohydrate, by difference",
+                    "value": 20.0,
+                },
+                {
+                    "nutrientNumber": "208",
+                    "nutrientName": "Energy",
+                    "value": 150.0,
+                },
+                {
+                    "nutrientNumber": "269",
+                    "nutrientName": "Sugars, total",
+                    "value": 5.0,
+                },
+            ],
+        }
+        result = usda_api.extract_nutrients(food_data)
+        assert result["protein"] == 10.0
+        assert result["fat"] == 5.0
+        assert result["carbohydrates"] == 20.0
+        assert result["calories"] == 150.0
+        assert result["sugar"] == 5.0
+
+    def test_extract_nutrients_with_nested_nutrient(self, usda_api):
+        food_data = {
+            "description": "Test Food",
+            "foodNutrients": [
+                {
+                    "nutrient": {"id": 203, "name": "Protein"},
+                    "value": 10.0,
+                },
+            ],
+        }
+        result = usda_api.extract_nutrients(food_data)
+        assert result["protein"] == 10.0
+
+    def test_extract_nutrients_with_empty_nutrients(self, usda_api):
+        food_data = {"description": "Test Food", "foodNutrients": []}
+        result = usda_api.extract_nutrients(food_data)
+        assert result["protein"] == 0
+        assert result["calories"] == 0
+
+    def test_extract_nutrients_with_no_nutrients_key(self, usda_api):
+        food_data = {"description": "Test Food"}
+        result = usda_api.extract_nutrients(food_data)
+        assert result["protein"] == 0
+
+
+class TestNutritionCalculator:
+    @pytest.fixture
+    def calculator(self):
+        with patch("vrobbler.apps.foods.sources.usda.USDAFoodAPI"):
+            return NutritionCalculator()
+
+    def test_parse_ingredient_with_fraction(self, calculator):
+        result = calculator.parse_ingredient("1/2 cup flour")
+        assert result["quantity"] == 0.5
+        assert result["unit"] == "cup"
+        assert result["ingredient"] == "flour"
+
+    def test_parse_ingredient_with_mixed_number(self, calculator):
+        result = calculator.parse_ingredient("1 1/2 cups sugar")
+        assert result["quantity"] == 1.5
+        assert result["unit"] == "cups"
+        assert result["ingredient"] == "sugar"
+
+    def test_parse_ingredient_with_decimal(self, calculator):
+        result = calculator.parse_ingredient("0.5 tsp salt")
+        assert result["quantity"] == 0.5
+        assert result["unit"] == "tsp"
+        assert result["ingredient"] == "salt"
+
+    def test_parse_ingredient_with_whole_number(self, calculator):
+        result = calculator.parse_ingredient("3 eggs")
+        assert result["quantity"] == 3
+        assert result["unit"] is None
+        assert result["ingredient"] == "eggs"
+
+    def test_parse_ingredient_with_no_quantity(self, calculator):
+        result = calculator.parse_ingredient("salt to taste")
+        assert result["quantity"] == 1
+
+    def test_clean_ingredient_name_removes_modifiers(self, calculator):
+        result = calculator._clean_ingredient_name("fresh chopped onions")
+        assert "fresh" not in result.lower()
+        assert "chopped" not in result.lower()
+
+    def test_clean_ingredient_name_removes_parentheses(self, calculator):
+        result = calculator._clean_ingredient_name("flour (sifted)")
+        assert "(" not in result
+        assert ")" not in result
+
+    def test_convert_to_grams_cup(self, calculator):
+        result = calculator._convert_to_grams(2, "cups", "flour")
+        assert result == 480
+
+    def test_convert_to_grams_tablespoon(self, calculator):
+        result = calculator._convert_to_grams(3, "tbsp", "olive oil")
+        assert result == 45
+
+    def test_convert_to_grams_unknown_unit(self, calculator):
+        result = calculator._convert_to_grams(1, "unknown", "something")
+        assert result == 100