[foods] Add catch for common domain exclusions

vrobbler/apps/foods/constants.py

@@ -0,0 +1,3 @@
+#!/usr/bin/env python3
+
+EXCLUDED_FOOD_DOMAINS = ["bbc.co.uk", "bbc.com", "www.bbc.com"]

vrobbler/apps/foods/sources/rscraper.py

@@ -1,11 +1,17 @@
+import logging
+from typing import Dict, List, Optional
+from urllib.parse import urlparse
+
+import requests
+from django.core.files.base import ContentFile
+from foods.constants import EXCLUDED_FOOD_DOMAINS
 from recipe_scrapers import scrape_html
 from recipe_scrapers._exceptions import (
     NoSchemaFoundInWildMode,
     SchemaOrgException,
 )
-import requests
-from typing import Dict, Optional, List
-from django.core.files.base import ContentFile
+
+logger = logging.getLogger(__name__)
 
 
 class RecipeScraperService:
@@ -73,6 +79,10 @@ class RecipeScraperService:
     @classmethod
     def is_recipe_url(cls, url: str) -> bool:
         """Check if a URL points to a recipe by fetching and checking the HTML."""
+        domain = urlparse(url).netloc
+        if domain in EXCLUDED_FOOD_DOMAINS and "food" not in url:
+            logger.info("[food] domain found in EXCLUDED_FOOD_DOMAINS")
+            return False
         try:
             response = requests.get(
                 url,
@@ -86,7 +96,6 @@ class RecipeScraperService:
                 return False
             return cls.is_recipe(response.text, url)
         except Exception as e:
-            print(e)
             return False
 
     def _safe_call(self, scraper, method, default=None):