[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/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