Adding canonical_url for all scrapers & associated updates: batch four (

#921)

README.rst

@@ -339,7 +339,6 @@ Scrapers available for:
 - `https://thekitchn.com/ <https://thekitchn.com/>`_
 - `https://www.themagicalslowcooker.com/ <https://www.themagicalslowcooker.com/>`_
 - `https://themodernproper.com/ <https://themodernproper.com/>`_
-- `https://thenutritiouskitchen.co/ <https://thenutritiouskitchen.co/>`_
 - `https://thepioneerwoman.com/ <https://thepioneerwoman.com>`_
 - `https://therecipecritic.com/ <https://therecipecritic.com>`_
 - `https://thespruceeats.com/ <https://thespruceeats.com/>`_

recipe_scrapers/__init__.py

@@ -252,7 +252,6 @@
 from .thekitchn import TheKitchn
 from .themagicalslowcooker import TheMagicalSlowCooker
 from .themodernproper import TheModernProper
-from .thenutritiouskitchen import TheNutritiousKitchen
 from .thepioneerwoman import ThePioneerWoman
 from .therecipecritic import Therecipecritic
 from .thespruceeats import TheSpruceEats
@@ -564,7 +563,6 @@
     TheKitchn.host(): TheKitchn,
     TheMagicalSlowCooker.host(): TheMagicalSlowCooker,
     TheModernProper.host(): TheModernProper,
-    TheNutritiousKitchen.host(): TheNutritiousKitchen,
     ThePioneerWoman.host(): ThePioneerWoman,
     TheSpruceEats.host(): TheSpruceEats,
     TheVintageMixer.host(): TheVintageMixer,

recipe_scrapers/southernliving.py

@@ -1,6 +1,9 @@
 # mypy: disallow_untyped_defs=False
 
+from recipe_scrapers._exceptions import SchemaOrgException
+
 from ._abstract import AbstractScraper
+from ._utils import get_yields
 
 
 class SouthernLiving(AbstractScraper):
@@ -15,7 +18,24 @@ def total_time(self):
         return self.schema.total_time()
 
     def yields(self):
-        return self.schema.yields()
+        try:
+            schema_yield = self.schema.yields()
+            if schema_yield:
+                return schema_yield
+        except SchemaOrgException:
+            pass
+
+        for servings_div in self.soup.find_all(
+            "div", class_="mntl-recipe-details__item"
+        ):
+            label_text = servings_div.find(
+                "div", class_="mntl-recipe-details__label"
+            ).get_text(strip=True)
+            if label_text in ["Servings:", "Yield:"]:
+                servings_element = servings_div.find(
+                    "div", class_="mntl-recipe-details__value"
+                )
+                return get_yields(servings_element)
 
     def image(self):
         return self.schema.image()

recipe_scrapers/sweetpeasandsaffron.py

@@ -1,6 +1,6 @@
 # mypy: disallow_untyped_defs=False
 from ._abstract import AbstractScraper
-from ._utils import normalize_string
+from ._utils import get_minutes, get_yields, normalize_string
 
 
 class SweetPeasAndSaffron(AbstractScraper):
@@ -16,10 +16,12 @@ def title(self):
         return self.soup.find("h2", {"class": "wprm-recipe-name"}).text
 
     def total_time(self):
-        return self.soup.find("span", {"class": "wprm-recipe-total_time"}).text
+        time = self.soup.find("span", {"class": "wprm-recipe-total_time"}).text
+        return get_minutes(time)
 
     def yields(self):
-        return self.soup.find("span", {"class": "wprm-recipe-servings"}).text
+        servings = self.soup.find("span", {"class": "wprm-recipe-servings"}).text
+        return get_yields(servings)
 
     def image(self):
         return self.soup.find(

recipe_scrapers/zeitwochenmarkt.py

@@ -36,12 +36,20 @@ def image(self):
         return self.schema.image()
 
     def ingredients(self):
-        class_name = "recipe-list-collection__special-ingredient"
-        special_ingredients = [
-            normalize_string(item.text)
-            for item in self.soup.find_all("p", {"class": class_name})
-        ]
-        return special_ingredients + self.schema.ingredients()
+        ingredients = []
+        for div_element in self.soup.select(".recipe-list-collection"):
+            special_ingredients = div_element.select(
+                ".recipe-list-collection__special-ingredient"
+            )
+            ingredients.extend(normalize_string(p.text) for p in special_ingredients)
+
+            list_items = div_element.select(".recipe-list-collection__list li")
+            ingredients.extend(
+                normalize_string(li.get_text(strip=True, separator=" "))
+                for li in list_items
+            )
+
+        return ingredients
 
     def instructions(self):
         class_name = "article__subheading article__subheading--recipe article__item"