fix: remove network calls from tests (#2055)

* abstracted scraper get_html method

* applied mock to all scrapers

* fixed incorrect var reference

mealie/services/scraper/recipe_scraper.py

@@ -3,6 +3,8 @@ from mealie.services.scraper.scraped_extras import ScrapedExtras
 
 from .scraper_strategies import ABCScraperStrategy, RecipeScraperOpenGraph, RecipeScraperPackage
 
+DEFAULT_SCRAPER_STRATEGIES: list[type[ABCScraperStrategy]] = [RecipeScraperPackage, RecipeScraperOpenGraph]
+
 
 class RecipeScraper:
     """
@@ -14,10 +16,7 @@ class RecipeScraper:
 
     def __init__(self, scrapers: list[type[ABCScraperStrategy]] | None = None) -> None:
         if scrapers is None:
-            scrapers = [
-                RecipeScraperPackage,
-                RecipeScraperOpenGraph,
-            ]
+            scrapers = DEFAULT_SCRAPER_STRATEGIES
 
         self.scrapers = scrapers
 

mealie/services/scraper/scraper_strategies.py

@@ -81,6 +81,10 @@ class ABCScraperStrategy(ABC):
         self.logger = get_logger()
         self.url = url
 
+    @abstractmethod
+    async def get_html(self, url: str) -> str:
+        ...
+
     @abstractmethod
     async def parse(self) -> tuple[Recipe, ScrapedExtras] | tuple[None, None]:
         """Parse a recipe from a web URL.
@@ -95,6 +99,9 @@ class ABCScraperStrategy(ABC):
 
 
 class RecipeScraperPackage(ABCScraperStrategy):
+    async def get_html(self, url: str) -> str:
+        return await safe_scrape_html(url)
+
     def clean_scraper(self, scraped_data: SchemaScraperFactory.SchemaScraper, url: str) -> tuple[Recipe, ScrapedExtras]:
         def try_get_default(func_call: Callable | None, get_attr: str, default: Any, clean_func=None):
             value = default
@@ -160,7 +167,8 @@ class RecipeScraperPackage(ABCScraperStrategy):
         return recipe, extras
 
     async def scrape_url(self) -> SchemaScraperFactory.SchemaScraper | Any | None:
-        recipe_html = await safe_scrape_html(self.url)
+        recipe_html = await self.get_html(self.url)
+
         try:
             scraped_schema = scrape_html(recipe_html, org_url=self.url)
         except (NoSchemaFoundInWildMode, AttributeError):
@@ -204,8 +212,8 @@ class RecipeScraperOpenGraph(ABCScraperStrategy):
     Abstract class for all recipe parsers.
     """
 
-    async def get_html(self) -> str:
-        return await safe_scrape_html(self.url)
+    async def get_html(self, url: str) -> str:
+        return await safe_scrape_html(url)
 
     def get_recipe_fields(self, html) -> dict | None:
         """
@@ -245,7 +253,7 @@ class RecipeScraperOpenGraph(ABCScraperStrategy):
         """
         Parse a recipe from a given url.
         """
-        html = await self.get_html()
+        html = await self.get_html(self.url)
 
         og_data = self.get_recipe_fields(html)
 

tests/integration_tests/user_recipe_tests/test_recipe_crud.py

@@ -1,6 +1,5 @@
 import json
 from pathlib import Path
-from typing import Optional, Union
 
 import pytest
 from bs4 import BeautifulSoup
@@ -12,7 +11,7 @@ from slugify import slugify
 
 from mealie.schema.recipe.recipe import RecipeCategory
 from mealie.services.recipe.recipe_data_service import RecipeDataService
-from mealie.services.scraper.scraper_strategies import RecipeScraperOpenGraph
+from mealie.services.scraper.recipe_scraper import DEFAULT_SCRAPER_STRATEGIES
 from tests import data, utils
 from tests.utils import api_routes
 from tests.utils.factories import random_string
@@ -31,9 +30,9 @@ def get_init(html_path: Path):
     def init_override(
         self,
         url,
-        proxies: Optional[str] = None,
-        timeout: Optional[Union[float, tuple, None]] = None,
-        wild_mode: Optional[bool] = False,
+        proxies: str | None = None,
+        timeout: float | tuple | None = None,
+        wild_mode: bool | None = False,
         **_,
     ):
         page_data = html_path.read_bytes()
@@ -48,7 +47,7 @@ def get_init(html_path: Path):
 
 
 def open_graph_override(html: str):
-    def get_html(self) -> str:
+    async def get_html(self, url: str) -> str:
         return html
 
     return get_html
@@ -68,11 +67,12 @@ def test_create_by_url(
         get_init(recipe_data.html_file),
     )
     # Override the get_html method of the RecipeScraperOpenGraph to return the test html
-    monkeypatch.setattr(
-        RecipeScraperOpenGraph,
-        "get_html",
-        open_graph_override(recipe_data.html_file.read_text()),
-    )
+    for scraper_cls in DEFAULT_SCRAPER_STRATEGIES:
+        monkeypatch.setattr(
+            scraper_cls,
+            "get_html",
+            open_graph_override(recipe_data.html_file.read_text()),
+        )
     # Skip image downloader
     monkeypatch.setattr(
         RecipeDataService,
@@ -113,12 +113,13 @@ def test_create_by_url_with_tags(
         "__init__",
         get_init(html_file),
     )
-    # Override the get_html method of the RecipeScraperOpenGraph to return the test html
-    monkeypatch.setattr(
-        RecipeScraperOpenGraph,
-        "get_html",
-        open_graph_override(html_file.read_text()),
-    )
+    # Override the get_html method of all scraper strategies to return the test html
+    for scraper_cls in DEFAULT_SCRAPER_STRATEGIES:
+        monkeypatch.setattr(
+            scraper_cls,
+            "get_html",
+            open_graph_override(html_file.read_text()),
+        )
     # Skip image downloader
     monkeypatch.setattr(
         RecipeDataService,
@@ -198,7 +199,7 @@ def test_read_update(
     assert len(recipe["recipeCategory"]) == len(recipe_categories)
 
     test_name = [x.name for x in recipe_categories]
-    for cats in zip(recipe["recipeCategory"], recipe_categories):
+    for cats in zip(recipe["recipeCategory"], recipe_categories, strict=False):
         assert cats[0]["name"] in test_name