Merge branch 'hhursev:main' into grouping-simplyquinoa

.github/workflows/coverage.yaml

@@ -12,7 +12,7 @@ on:
 
 jobs:
   coverage:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     steps:
       - uses: actions/checkout@v3
       - name: Set up Python

.github/workflows/linters.yaml

@@ -12,7 +12,7 @@ on:
 
 jobs:
   linters:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     steps:
       - uses: actions/checkout@v3
       - name: Set up Python

.github/workflows/publish.yaml

@@ -9,6 +9,8 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
+      - name: Check that the release commit can be found in a release branch
+        run: git branch main v14 --contains ${{ github.sha }} | egrep '.+'
       - name: Set up Python
         uses: actions/setup-python@v4
         with:

.github/workflows/test_publish.yaml

@@ -11,9 +11,11 @@ on: workflow_dispatch
 
 jobs:
   test_publish:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     steps:
       - uses: actions/checkout@v3
+      - name: Check that the release commit can be found in a release branch
+        run: git branch main v14 --contains ${{ github.sha }} | egrep '.+'
       - name: Set up Python
         uses: actions/setup-python@v4
         with:

.github/workflows/unittests.yaml

@@ -15,12 +15,12 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-latest, macos-13, windows-latest]
+        os: [ubuntu-24.04, macos-latest, windows-latest]
         python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
         include:
           # set toxenv to workaround-darwin on macos (check tox.ini)
           - toxenv: py
-          - os: macos-13
+          - os: macos-latest
             toxenv: workaround-darwin
     runs-on: ${{ matrix.os }}
     steps:
@@ -29,6 +29,7 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
+          cache: pip
       - name: Run Tests
         run: |
           pip install tox

README.rst

@@ -265,6 +265,7 @@ Scrapers available for:
 - `https://kochbucher.com/ <https://kochbucher.com/>`_
 - `http://koket.se/ <http://koket.se>`_
 - `https://kristineskitchenblog.com/ <https://kristineskitchenblog.com>`_
+- `https://krollskorner.com/ <https://krollskorner.com/>`_
 - `https://kuchnia-domowa.pl/ <https://www.kuchnia-domowa.pl/>`_
 - `https://kuchynalidla.sk/ <https://www.kuchynalidla.sk/>`_
 - `https://www.kwestiasmaku.com/ <https://www.kwestiasmaku.com/>`_

recipe_scrapers/__init__.py

@@ -216,6 +216,7 @@
 from .kochbucher import Kochbucher
 from .koket import Koket
 from .kristineskitchenblog import KristinesKitchenBlog
+from .krollskorner import KrollsKorner
 from .kuchniadomowa import KuchniaDomowa
 from .kuchynalidla import KuchynaLidla
 from .kwestiasmaku import KwestiaSmaku
@@ -521,6 +522,7 @@
     KitchenAidAustralia.host(): KitchenAidAustralia,
     KitchenDreaming.host(): KitchenDreaming,
     KristinesKitchenBlog.host(): KristinesKitchenBlog,
+    KrollsKorner.host(): KrollsKorner,
     KuchynaLidla.host(): KuchynaLidla,
     LittleSunnyKitchen.host(): LittleSunnyKitchen,
     LeitesCulinaria.host(): LeitesCulinaria,

recipe_scrapers/_schemaorg.py

@@ -184,8 +184,8 @@ def yields(self):
         yield_data = self.data.get("recipeYield") or self.data.get("yield")
         if yield_data and isinstance(yield_data, list):
             yield_data = yield_data[0]
-        recipe_yield = str(yield_data)
-        return get_yields(recipe_yield)
+        if yield_data:
+            return get_yields(str(yield_data))
 
     def image(self):
         image = self.data.get("image")

recipe_scrapers/_utils.py

@@ -199,6 +199,8 @@ def get_yields(element):
         serve_text = element
     else:
         serve_text = element.get_text()
+    if not serve_text:
+        raise ValueError("Cannot extract yield information from empty string")
 
     if SERVE_REGEX_TO.search(serve_text):
         serve_text = serve_text.split(SERVE_REGEX_TO.split(serve_text, 2)[1], 2)[1]

recipe_scrapers/krollskorner.py

@@ -0,0 +1,35 @@
+from ._abstract import AbstractScraper
+from ._grouping_utils import group_ingredients
+from ._utils import get_equipment
+
+
+class KrollsKorner(AbstractScraper):
+    @classmethod
+    def host(cls):
+        return "krollskorner.com"
+
+    def author(self):
+        author_tag = self.soup.select_one(
+            ".wprm-recipe-details.wprm-recipe-author.wprm-block-text-normal a"
+        )
+        return author_tag.get_text(strip=True)
+
+    def ingredient_groups(self):
+        return group_ingredients(
+            self.ingredients(),
+            self.soup,
+            ".wprm-recipe-ingredient-group h4",
+            ".wprm-recipe-ingredient",
+        )
+
+    def equipment(self):
+        equipment_container = self.soup.select_one(".wprm-recipe-equipment-container")
+        if not equipment_container:
+            return None
+
+        equipment_items = [
+            item.select_one(".wprm-recipe-equipment-name").get_text(strip=True)
+            for item in equipment_container.select(".wprm-recipe-equipment-item")
+            if item.select_one(".wprm-recipe-equipment-name")
+        ]
+        return get_equipment(equipment_items)

recipe_scrapers/maangchi.py

@@ -1,3 +1,5 @@
+import re
+
 from ._abstract import AbstractScraper
 from ._utils import normalize_string
 
@@ -8,7 +10,9 @@ def host(cls):
         return "maangchi.com"
 
     def ingredients(self):
-        before = self.soup.find("h2", string="Ingredients").find_all_next("li")
+        before = self.soup.find("h2", string=re.compile(r"Ingredients")).find_all_next(
+            "li"
+        )
         after = self.soup.find("h2", string="Directions").find_all_previous("li")
         list_before = [normalize_string(b.get_text()) for b in before]
         list_after = [normalize_string(a.get_text()) for a in after]

recipe_scrapers/thehappyfoodie.py

@@ -1,4 +1,5 @@
 from ._abstract import AbstractScraper
+from ._grouping_utils import group_ingredients
 from ._utils import normalize_string
 
 
@@ -27,3 +28,11 @@ def ingredients(self):
             )
 
         return [normalize_string(f"{amount} {name}") for amount, name in ingredients]
+
+    def ingredient_groups(self):
+        return group_ingredients(
+            self.ingredients(),
+            self.soup,
+            ".heading th",
+            ".hf-ingredients__single-group tr:not(.heading, .spacer)",
+        )

recipe_scrapers/thekitchenmagpie.py

@@ -1,7 +1,27 @@
 from ._abstract import AbstractScraper
+from ._grouping_utils import group_ingredients
+from ._utils import csv_to_tags, get_equipment
 
 
 class TheKitchenMagPie(AbstractScraper):
     @classmethod
     def host(cls):
         return "thekitchenmagpie.com"
+
+    def ingredient_groups(self):
+        return group_ingredients(
+            self.ingredients(),
+            self.soup,
+            ".wprm-recipe-ingredient-group h4",
+            ".wprm-recipe-ingredient",
+        )
+
+    def equipment(self):
+        equipment_container = self.soup.select_one(".wprm-recipe-details-container")
+        if equipment_container:
+            equipment_text = equipment_container.find("dt", string="Equipment")
+            if equipment_text:
+                equipment_list = equipment_text.find_next_sibling("dd")
+                if equipment_list:
+                    return get_equipment(csv_to_tags(equipment_list.text))
+        return None

recipe_scrapers/thekitchn.py

@@ -1,7 +1,20 @@
 from ._abstract import AbstractScraper
+from ._exceptions import StaticValueException
+from ._grouping_utils import group_ingredients
 
 
 class TheKitchn(AbstractScraper):
     @classmethod
     def host(cls):
         return "thekitchn.com"
+
+    def ingredient_groups(self):
+        return group_ingredients(
+            self.ingredients(),
+            self.soup,
+            ".Recipe__ingredientsGroupName",
+            ".Recipe__ingredient",
+        )
+
+    def site_name(self):
+        raise StaticValueException(return_value="The Kitchn")

recipe_scrapers/themodernproper.py

@@ -1,12 +1,21 @@
 from ._abstract import AbstractScraper
 from ._exceptions import ElementNotFoundInHtml
+from ._grouping_utils import group_ingredients
 
 
 class TheModernProper(AbstractScraper):
     @classmethod
     def host(cls):
         return "themodernproper.com"
 
+    def ingredient_groups(self):
+        return group_ingredients(
+            self.ingredients(),
+            self.soup,
+            ".recipe-ingredients__list-title",
+            ".recipe-ingredients__item",
+        )
+
     def nutrients(self):
         container = self.schema.nutrients()
         if not container:

recipe_scrapers/therecipecritic.py

@@ -1,4 +1,5 @@
 from ._abstract import AbstractScraper
+from ._grouping_utils import group_ingredients
 
 
 class Therecipecritic(AbstractScraper):
@@ -8,3 +9,11 @@ def host(cls):
 
     def author(self):
         return "The Recipe Critic"
+
+    def ingredient_groups(self):
+        return group_ingredients(
+            self.ingredients(),
+            self.soup,
+            ".wprm-recipe-ingredient-group h4",
+            ".wprm-recipe-ingredient",
+        )

recipe_scrapers/thevintagemixer.py

@@ -1,5 +1,6 @@
 from ._abstract import AbstractScraper
 from ._exceptions import StaticValueException
+from ._grouping_utils import group_ingredients
 
 
 class TheVintageMixer(AbstractScraper):
@@ -9,3 +10,11 @@ def host(cls):
 
     def site_name(self):
         raise StaticValueException(return_value="Vintage Mixer")
+
+    def ingredient_groups(self):
+        return group_ingredients(
+            self.ingredients(),
+            self.soup,
+            ".wprm-recipe-ingredient-group h4",
+            ".wprm-recipe-ingredient",
+        )

recipe_scrapers/thewoksoflife.py

@@ -1,7 +1,16 @@
 from ._abstract import AbstractScraper
+from ._grouping_utils import group_ingredients
 
 
 class Thewoksoflife(AbstractScraper):
     @classmethod
     def host(cls):
         return "thewoksoflife.com"
+
+    def ingredient_groups(self):
+        return group_ingredients(
+            self.ingredients(),
+            self.soup,
+            ".wprm-recipe-ingredient-group h4",
+            ".wprm-recipe-ingredient",
+        )

recipe_scrapers/thinlicious.py

@@ -1,7 +1,21 @@
 from ._abstract import AbstractScraper
+from ._grouping_utils import group_ingredients
+from ._utils import get_equipment
 
 
 class Thinlicious(AbstractScraper):
     @classmethod
     def host(cls):
         return "thinlicious.com"
+
+    def ingredient_groups(self):
+        return group_ingredients(
+            self.ingredients(),
+            self.soup,
+            ".wprm-recipe-group-name",
+            ".wprm-recipe-ingredient",
+        )
+
+    def equipment(self):
+        equipment_list = self.soup.select(".wprm-recipe-equipment-name")
+        return get_equipment(item.get_text() for item in equipment_list)

recipe_scrapers/usapears.py

@@ -11,6 +11,16 @@ class USAPears(AbstractScraper):
     def host(cls):
         return "usapears.org"
 
+    def author(self):
+        author = self.schema.author()
+        if author:
+            return author
+
+        d1 = self.soup.find("meta", {"name": "twitter:data1", "content": True})
+        l1 = self.soup.find("meta", {"name": "twitter:label1", "content": "Written by"})
+        if d1 and l1:
+            return d1["content"]
+
     def total_time(self):
         total_time = 0
         recipe_legends = self.soup.find_all("div", {"class": "recipe-legend"})
@@ -65,10 +75,19 @@ def nutrients(self):
         return results
 
     def ratings(self):
-        try:
-            ratings = self.schema.ratings()
-            if ratings > 0:
-                return ratings
-        except Exception:
-            pass
+        rating_elements = self.soup.find_all("p", {"class": "comment-rating"})
+        if not rating_elements:
+            return None
+
+        total_rating = 0
+        for element in rating_elements:
+            img = element.find("img", {"src": True})
+            if not img:
+                continue
+            match = re.search(r"(\d+)-star\.svg", img["src"])
+            if match:
+                total_rating += int(match.group(1))
+
+        if len(rating_elements) > 0:
+            return round(total_rating / len(rating_elements), 2)
         return None

tests/library/test_utils.py

@@ -6,6 +6,7 @@
     get_minutes,
     get_nutrition_keys,
     get_url_slug,
+    get_yields,
     url_path_to_dict,
 )
 
@@ -168,3 +169,10 @@ def test_get_nutrition_keys(self):
             "cholesterolContent",
         ]
         self.assertEqual((expected_order), (nutrition_keys))
+
+    def test_get_yields(self):
+        self.assertEqual("5 servings", get_yields("5"))
+
+    def test_get_yields_empty_string(self):
+        with self.assertRaises(ValueError):
+            get_yields("")