Merge branch 'mealie-next' into fix/translation-issues-when-scraping

mealie/services/scraper/cleaner.py

@@ -90,10 +90,10 @@ def clean_image(image: str | list | dict | None = None, default: str = "no image
     image attempts to parse the image field from a recipe and return a string. Currenty
 
     Supported Structures:
-        - `https://exmaple.com` - A string
-        - `{ "url": "https://exmaple.com" }` - A dictionary with a `url` key
-        - `["https://exmaple.com"]` - A list of strings
-        - `[{ "url": "https://exmaple.com" }]` - A list of dictionaries with a `url` key
+        - `https://example.com` - A string
+        - `{ "url": "https://example.com" }` - A dictionary with a `url` key
+        - `["https://example.com"]` - A list of strings
+        - `[{ "url": "https://example.com" }]` - A list of dictionaries with a `url` key
 
     Raises:
         TypeError: If the image field is not a supported type a TypeError is raised.
@@ -113,8 +113,11 @@ def clean_image(image: str | list | dict | None = None, default: str = "no image
             return [x["url"] for x in image]
         case {"url": str(image)}:
             return [image]
+        case [{"@id": str(_)}, *_]:
+            return [x["@id"] for x in image]
         case _:
-            raise TypeError(f"Unexpected type for image: {type(image)}, {image}")
+            logger.exception(f"Unexpected type for image: {type(image)}, {image}")
+            return [default]
 
 
 def clean_instructions(steps_object: list | dict | str, default: list | None = None) -> list[dict]:

mealie/services/scraper/scraper_strategies.py

@@ -212,10 +212,6 @@ class RecipeScraperPackage(ABCScraperStrategy):
 
 
 class RecipeScraperOpenGraph(ABCScraperStrategy):
-    """
-    Abstract class for all recipe parsers.
-    """
-
     async def get_html(self, url: str) -> str:
         return await safe_scrape_html(url)
 
@@ -245,7 +241,7 @@ class RecipeScraperOpenGraph(ABCScraperStrategy):
             "recipeIngredient": ["Could not detect ingredients"],
             "recipeInstructions": [{"text": "Could not detect instructions"}],
             "slug": slugify(og_field(properties, "og:title")),
-            "orgURL": og_field(properties, "og:url"),
+            "orgURL": self.url,
             "categories": [],
             "tags": og_fields(properties, "og:article:tag"),
             "dateAdded": None,