MarleySpoon: add precautionary check for unexpected API URLs. (#1069)

hhursev · May 6, 2024 · 94b2617 · 94b2617
1 parent b4567bf
commit 94b2617
Show file tree

Hide file tree

Showing 4 changed files with 75 additions and 2 deletions.
diff --git a/recipe_scrapers/marleyspoon.py b/recipe_scrapers/marleyspoon.py
@@ -1,12 +1,13 @@
 # mypy: disallow_untyped_defs=False
 import json
 import re
+from urllib.parse import urljoin
 
 import requests
 
 from ._abstract import HEADERS, AbstractScraper
-from ._exceptions import ElementNotFoundInHtml
-from ._utils import normalize_string
+from ._exceptions import ElementNotFoundInHtml, RecipeScrapersExceptions
+from ._utils import get_host_name, normalize_string
 
 ID_PATTERN = re.compile(r"/(\d+)-")
 SCRIPT_PATTERN = re.compile(
@@ -65,6 +66,25 @@ def _get_json_params(self):
         if api_url is None or api_token is None:
             raise ElementNotFoundInHtml("Required script not found.")
 
+        from . import SCRAPERS
+
+        scraper_name = self.__class__.__name__
+        try:
+            next_url = urljoin(self.url, api_url)
+            host_name = get_host_name(next_url)
+            next_scraper = type(None)
+            # check: api.foo.xx.example, foo.xx.example, xx.example
+            while host_name and host_name.count("."):
+                next_scraper = SCRAPERS.get(host_name)
+                if next_scraper:
+                    break
+                _, host_name = host_name.split(".", 1)
+            if not isinstance(self, next_scraper):
+                msg = f"Attempted to scrape using {next_scraper} from {scraper_name}"
+                raise ValueError(msg)
+        except Exception as e:
+            raise RecipeScrapersExceptions(f"Unexpected API URL: {api_url}") from e
+
         return api_url, api_token
 
     @classmethod

diff --git a/tests/legacy/test_data/faulty.testhtml b/tests/legacy/test_data/faulty.testhtml
@@ -0,0 +1,6 @@
+<!DOCTYPE html>
+<html>
+<script>
+gon.current_brand="test_invalid"; gon.current_country="XX"; gon.api_token=" ".trim() || null; gon.api_host="http://api.marlarkey.invalid";
+</script>
+</html>
diff --git a/tests/legacy/test_data/relative_url.testhtml b/tests/legacy/test_data/relative_url.testhtml
@@ -0,0 +1,6 @@
+<!DOCTYPE html>
+<html>
+<script>
+gon.current_brand="test_invalid"; gon.current_country="XX"; gon.api_token=" ".trim() || null; gon.api_host="relative_path/unexpected.js";
+</script>
+</html>
diff --git a/tests/legacy/test_marleyspoon_invalid.py b/tests/legacy/test_marleyspoon_invalid.py
@@ -0,0 +1,41 @@
+import unittest
+
+import responses
+
+from recipe_scrapers._exceptions import RecipeScrapersExceptions
+from recipe_scrapers.marleyspoon import MarleySpoon
+
+
+class TestFaultyAPIURLResponse(unittest.TestCase):
+
+    @responses.activate
+    def test_faulty_response(self):
+        url = "https://marleyspoon.de/menu/113813-glasierte-veggie-burger-mit-roestkartoffeln-und-apfel-gurken-salat"
+        with open("tests/legacy/test_data/faulty.testhtml") as faulty_data:
+            faulty_response = faulty_data.read()
+
+        responses.add(
+            method=responses.GET,
+            url=url,
+            body=faulty_response,
+        )
+
+        with self.assertRaises(RecipeScrapersExceptions):
+            MarleySpoon(url=url)
+
+    @responses.activate
+    def test_relative_api_url(self):
+        url = "https://marleyspoon.de/menu/113813-glasierte-veggie-burger-mit-roestkartoffeln-und-apfel-gurken-salat"
+        with open("tests/legacy/test_data/relative_url.testhtml") as relative_url_data:
+            relative_url_response = relative_url_data.read()
+
+        responses.add(
+            method=responses.GET,
+            url=url,
+            body=relative_url_response,
+        )
+
+        with self.assertRaises(Exception):
+            MarleySpoon(
+                url=url
+            )  # currently this raises an requests.exceptions.MissingSchema exception