ajout: nouvelle classe pour données et testes

main.py

@@ -1,5 +1,5 @@
 from sys import stderr
-from typing import cast
+from typing import Any, cast
 from requests import Response, Session
 from bs4 import BeautifulSoup, Tag
 from json import JSONDecodeError, loads
@@ -22,6 +22,7 @@ class Scraper:
         self._session: Session = Session()
         # Système de cache pour éviter de solliciter le serveur inutilement
         self._latest_request: tuple[(str, Response | None)] = ("", None)
+        self._latest_soup: tuple[(str, BeautifulSoup | None)] = ("", None)
 
     def _request(self, subdir: str) -> Response:
         """
@@ -56,12 +57,12 @@ class Scraper:
         """
         rq_subdir, rq_response = self._latest_request
 
-        if rq_response is None or subdir != rq_subdir:
+        if rq_response is not None and subdir == rq_subdir:
-            request: Response = self._request(subdir)
+            return rq_response
-            self._latest_request = (subdir, request)
-            return request
 
-        return rq_response
+        request: Response = self._request(subdir)
+        self._latest_request = (subdir, request)
+        return request
 
     def getsoup(self, subdir: str = "") -> BeautifulSoup:
         """
@@ -76,12 +77,19 @@ class Scraper:
         Raise:
             HTTPError: Si le serveur renvoie un code d'erreur (4xx, 5xx).
         """
-        markup: str = self.getresponse(subdir).text
+        rq_subdir, rq_soup = self._latest_soup
-        return BeautifulSoup(markup, features="html.parser")
 
-    def getjsondata(
+        if rq_soup is not None and subdir == rq_subdir:
-        self, subdir: str = "", id: str = "__NEXT_DATA__"
+            return rq_soup
-    ) -> dict[str, object]:
+
+        soup: BeautifulSoup = BeautifulSoup(
+            markup=self.getresponse(subdir).text, features="html.parser"
+        )
+
+        self._latest_soup = (subdir, soup)
+        return soup
+
+    def getjsondata(self, subdir: str = "", id: str = "__NEXT_DATA__") -> ScraperData:
         """
         Extrait les données JSON contenues dans la balise __NEXT_DATA__ du site.
         Beaucoup de sites modernes (Next.js) stockent leur état initial dans
@@ -120,13 +128,39 @@ class Scraper:
                     # si current_data est bien un dictionnaire et que la clé
                     # est bien dedans
                     if isinstance(current_data, dict) and key in current_data:
-                        current_data = current_data[key]
+                        current_data: object = current_data[key]
                     else:
                         raise ValueError(f"Clé manquante dans le JSON : {key}")
 
                 if isinstance(current_data, dict):
-                    return cast(dict[str, object], current_data)
+                    return ScraperData(data=cast(dict[str, object], current_data))
 
             except (JSONDecodeError, ValueError) as e:
                 print(f"Erreur lors de l'extraction JSON : {e}", file=stderr)
-        return {}
+        return ScraperData({})
+
+
+class ScraperData:
+    def __init__(self, data: dict[str, object]) -> None:
+        if not data:
+            raise ValueError("Données insuffisantes pour créer un ScraperData.")
+        self._data: dict[str, object] = data
+
+    def _getattributes(self) -> dict[str, object] | None:
+        current_data: object = self._data.get("attributes")
+        if isinstance(current_data, dict):
+            return cast(dict[str, object], current_data)
+        return None
+
+    def appellation(self) -> str | None:
+        current_value: dict[str, object] | None = self._getattributes()
+        if current_value is not None:
+            app_dict: dict[str, object] = cast(
+                dict[str, object], current_value.get("appellation")
+            )
+            if app_dict:
+                return cast(str, app_dict.get("value"))
+        return None
+
+    def getdata(self) -> dict[str, object]:
+        return self._data

test_main.py

@@ -2,7 +2,7 @@ from json import dumps
 from bs4 import Tag
 import pytest
 from requests_mock import Mocker
-from main import Scraper
+from main import Scraper, ScraperData
 
 
 @pytest.fixture(autouse=True)
@@ -67,6 +67,16 @@ def mock_site():
                                         "isPrevSale": False,
                                     }
                                 ],
+                                "attributes": {
+                                    "appellation": {
+                                        "valueId": "433",
+                                        "name": "Appellation",
+                                        "value": "Sforzato di Valtellina",
+                                        "url": "sforzato-di-valtellina.html",
+                                        "isSpirit": False,
+                                        "groupIdentifier": "appellation_433",
+                                    },
+                                },
                             }
                         }
                     }
@@ -82,7 +92,10 @@ def mock_site():
         </body>
         </html>
         """
-        m.get("https://www.millesima.fr/nino-negri-5-stelle-sfursat-2022.html", text=html_product)
+        m.get(
+            "https://www.millesima.fr/nino-negri-5-stelle-sfursat-2022.html",
+            text=html_product,
+        )
 
         # on return m sans fermer le server qui simule la page
         yield m
@@ -100,9 +113,16 @@ def test_soup(scraper: Scraper):
     assert h1.text == "MILLESIMA"
 
 
-def test_getProductName(scraper: Scraper):
+# def test_getProductName(scraper: Scraper):
-    jsondata = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
+#     jsondata = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
-    assert jsondata["productName"] == "Nino Negri : 5 Stelle Sfursat 2022"
+#     assert jsondata["productName"] == "Nino Negri : 5 Stelle Sfursat 2022"
-    assert isinstance(jsondata["items"], list)
+#     assert isinstance(jsondata["items"], list)
-    assert len(jsondata["items"]) > 0
+#     assert len(jsondata["items"]) > 0
-    assert jsondata["items"][0]["offerPrice"] == 390
+#     assert jsondata["items"][0]["offerPrice"] == 390
+
+
+def test_appellation(scraper: Scraper):
+    appellation: ScraperData = scraper.getjsondata(
+        "nino-negri-5-stelle-sfursat-2022.html"
+    )
+    assert appellation.appellation() == "Sforzato di Valtellina"