Merge branch 'optimisation' into exo7

main.py

@@ -1,32 +1,88 @@
-from sys import stderr
 from typing import cast
 from requests import Response, Session
 from bs4 import BeautifulSoup, Tag
-from json import JSONDecodeError, loads
+from collections import OrderedDict
+from json import loads
 
 
-class 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 _getcontent(self) -> dict[str, object] | None:
+        """_summary_
+
+        Returns:
+            dict[str, object]: _description_
+        """
+        current_data: dict[str, object] = self._data
+        for key in ["initialReduxState", "product", "content"]:
+            new_data: object | None = current_data.get(key)
+            if new_data is None:
+                return None
+            current_data: dict[str, object] = cast(dict[str, object], new_data)
+
+        return current_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
+        """_summary_
+
+        Returns:
+            dict[str, object]: _description_
+        """
+        current_data: object = self._getcontent()
+        if current_data is None:
+            return None
+        return cast(dict[str, object], current_data.get("attributes"))
 
     def appellation(self) -> str | None:
+        """_summary_
+
+        Returns:
+            str: _description_
+        """
+        attrs: dict[str, object] | None = self._getattributes()
+
+        if attrs is not None:
+            app_dict: object | None = attrs.get("appellation")
+            if isinstance(app_dict, dict):
+                return cast(str, app_dict.get("value"))
+        return None
+
+    def _getcritiques(self, name: str) -> str | None:
+        """_summary_
+
+        Args:
+            name (str): _description_
+
+        Returns:
+            str | None: _description_
+        """
+
         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")
+                dict[str, object], current_value.get(name)
             )
-            if app_dict:
-                return cast(str, app_dict.get("value"))
+            if not app_dict:
+                return None
+
+            val = cast(str, app_dict.get("value")).rstrip("+").split("-")
+            if len(val) > 1:
+                val[0] = str((int(val[0]) + int(val[1])) / 2)
+
+            return val[0]
         return None
 
+    def parker(self) -> str | None:
+        return self._getcritiques("note_rp")
+
+    def robinson(self) -> str | None:
+        return self._getcritiques("note_jr")
+
+    def suckling(self) -> str | None:
+        return self._getcritiques("note_js")
+
     def getdata(self) -> dict[str, object]:
         return self._data
 
@@ -47,8 +103,10 @@ class Scraper:
         # TCP et d'avoir toujours une connexion constante avec le server
         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)
+        self._latest_request: tuple[(str, Response)] | None = None
+        self._latest_soups: OrderedDict[str, BeautifulSoup] = OrderedDict[
+            str, BeautifulSoup
+        ]()
 
     def _request(self, subdir: str) -> Response:
         """
@@ -68,12 +126,14 @@ class Scraper:
         response.raise_for_status()
         return response
 
-    def getresponse(self, subdir: str = "") -> Response:
+    def getresponse(self, subdir: str = "", use_cache: bool = True) -> Response:
         """
         Récupère la réponse d'une page, en utilisant le cache si possible.
 
         Args:
             subdir (str, optional): Le chemin de la page.
+            use_cache (bool, optional): Utilise la donnée deja sauvegarder ou
+                                    écrase la donnée utilisé avec la nouvelle
 
         Returns:
             Response: L'objet réponse (cache ou nouvelle requête).
@@ -81,16 +141,24 @@ class Scraper:
         Raise:
             HTTPError: Si le serveur renvoie un code d'erreur (4xx, 5xx).
         """
-        rq_subdir, rq_response = self._latest_request
 
-        if rq_response is not None and subdir == rq_subdir:
-            return rq_response
+        # si dans le cache, latest_request existe
+        if use_cache and self._latest_request is not None:
+            rq_subdir, rq_response = self._latest_request
+
+            # si c'est la meme requete et que use_cache est true,
+            # on renvoie celle enregistrer
+            if subdir == rq_subdir:
+                return rq_response
 
         request: Response = self._request(subdir)
-        self._latest_request = (subdir, request)
+        # on recrée la structure pour le systeme de cache si activer
+        if use_cache:
+            self._latest_request = (subdir, request)
+
         return request
 
-    def getsoup(self, subdir: str = "") -> BeautifulSoup:
+    def getsoup(self, subdir: str, use_cache: bool = True) -> BeautifulSoup:
         """
         Récupère le contenu HTML d'une page et le transforme en objet BeautifulSoup.
 
@@ -103,26 +171,29 @@ class Scraper:
         Raise:
             HTTPError: Si le serveur renvoie un code d'erreur (4xx, 5xx).
         """
-        rq_subdir, rq_soup = self._latest_soup
 
-        if rq_soup is not None and subdir == rq_subdir:
-            return rq_soup
+        if use_cache and subdir in self._latest_soups:
+            return self._latest_soups[subdir]
 
-        soup: BeautifulSoup = BeautifulSoup(
-            markup=self.getresponse(subdir).text, features="html.parser"
-        )
+        markup: str = self.getresponse(subdir).text
+        soup: BeautifulSoup = BeautifulSoup(markup, features="html.parser")
+
+        if use_cache:
+            self._latest_soups[subdir] = soup
+
+            if len(self._latest_soups) > 10:
+                _ = self._latest_soups.popitem(last=False)
 
-        self._latest_soup = (subdir, soup)
         return soup
 
-    def getjsondata(self, subdir: str = "", id: str = "__NEXT_DATA__") -> ScraperData:
+    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
         une balise <script> pour l'hydratation côté client.
 
         Args:
-            subdir (str, optional): Le chemin de la page.
+            subdir (str): Le chemin de la page.
             id (str, optional): L'identifiant de la balise script (par défaut __NEXT_DATA__).
 
         Raises:
@@ -138,29 +209,16 @@ class Scraper:
         soup: BeautifulSoup = self.getsoup(subdir)
         script: Tag | None = soup.find("script", id=id)
 
-        if isinstance(script, Tag) and script.string:
-            try:
-                current_data: object = loads(script.string)
-                # tout le chemin à parcourir pour arriver au données
-                # (plein d'information inutile)
-                keys: list[str] = [
-                    "props",
-                    "pageProps",
-                    "initialReduxState",
-                    "product",
-                    "content",
-                ]
-                for key in keys:
-                    # 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: object = current_data[key]
-                    else:
-                        raise ValueError(f"Clé manquante dans le JSON : {key}")
+        if script is None or not script.string:
+            raise ValueError(f"le script id={id} est introuvable")
 
-                if isinstance(current_data, dict):
-                    return ScraperData(data=cast(dict[str, object], current_data))
+        current_data: object = cast(object, loads(script.string))
+
+        for key in ["props", "pageProps"]:
+            if isinstance(current_data, dict) and key in current_data:
+                current_data = cast(object, current_data[key])
+                continue
+            raise ValueError(f"Clé manquante dans le JSON : {key}")
+
+        return _ScraperData(cast(dict[str, object], current_data))
 
-            except (JSONDecodeError, ValueError) as e:
-                print(f"Erreur lors de l'extraction JSON : {e}", file=stderr)
-        return ScraperData({})

requirements.txt

@@ -1,4 +1,3 @@
 requests>=2.32.5
 requests-mock>=1.12.1
-beautifulsoup4>=4.14.3
-    
+beautifulsoup4>=4.14.3

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, ScraperData
+from main import Scraper
 
 
 @pytest.fixture(autouse=True)
@@ -10,7 +10,47 @@ def mock_site():
     with Mocker() as m:
         m.get(
             "https://www.millesima.fr/",
-            text="<html><body><h1>MILLESIMA</h1></body></html>",
+            text=f"""
+            <html>
+                <body>
+                    <script id="__NEXT_DATA__" type="application/json">
+                    {dumps({
+                        "props": {
+                            "pageProps": {
+                                "initialReduxState": {
+                                    "product": {
+                                        "content": {
+                                            "items": [],
+                                            "attributes": {}
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    })}
+                    </script>
+                </body>
+            </html>
+            """,
+        )
+
+        m.get(
+            "https://www.millesima.fr/poubelle",
+            text=f"""
+            <html>
+                <body>
+                    <h1>POUBELLE</h1>
+                    <script id="__NEXT_DATA__" type="application/json">
+                    {dumps({
+                        "props": {
+                            "pageProps": {
+                            }
+                        }
+                    })}
+                    </script>
+                </body>
+            </html>
+            """,
         )
 
         json_data = {
@@ -41,7 +81,7 @@ def mock_site():
                                                 "name": "En promotion",
                                                 "value": "Non",
                                                 "sequence": 80,
-                                                "displayable": "false",
+                                                "displayable": "False",
                                                 "type": "CHECKBOX",
                                                 "isSpirit": False,
                                             },
@@ -65,6 +105,18 @@ def mock_site():
                                     }
                                 ],
                                 "attributes": {
+                                    "equivbtl": {
+                                        "valueId": "1",
+                                        "name": "equivbtl",
+                                        "value": "1",
+                                        "isSpirit": False,
+                                    },
+                                    "nbunit": {
+                                        "valueId": "6",
+                                        "name": "nbunit",
+                                        "value": "6",
+                                        "isSpirit": False,
+                                    },
                                     "appellation": {
                                         "valueId": "433",
                                         "name": "Appellation",
@@ -73,6 +125,24 @@ def mock_site():
                                         "isSpirit": False,
                                         "groupIdentifier": "appellation_433",
                                     },
+                                    "note_rp": {
+                                        "valueId": "91",
+                                        "name": "Parker",
+                                        "value": "91",
+                                        "isSpirit": False,
+                                    },
+                                    "note_jr": {
+                                        "valueId": "17+",
+                                        "name": "J. Robinson",
+                                        "value": "17+",
+                                        "isSpirit": False,
+                                    },
+                                    "note_js": {
+                                        "valueId": "93-94",
+                                        "name": "J. Suckling",
+                                        "value": "93-94",
+                                        "isSpirit": False,
+                                    },
                                 },
                             }
                         }
@@ -83,10 +153,12 @@ def mock_site():
 
         html_product = f"""
         <html>
-            <script id="__NEXT_DATA__" type="application/json">
-                {dumps(json_data)}
-            </script>
-        </body>
+            <body>    
+                <h1>MILLESIMA</h1>
+                <script id="__NEXT_DATA__" type="application/json">
+                    {dumps(json_data)}
+                </script>
+            </body>
         </html>
         """
         m.get(
@@ -104,22 +176,51 @@ def scraper() -> Scraper:
 
 
 def test_soup(scraper: Scraper):
-    h1: Tag | None = scraper.getsoup().find("h1")
-
-    assert isinstance(h1, Tag)
-    assert h1.text == "MILLESIMA"
-
-
-# def test_getProductName(scraper: Scraper):
-#     jsondata = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
-#     assert jsondata["productName"] == "Nino Negri : 5 Stelle Sfursat 2022"
-#     assert isinstance(jsondata["items"], list)
-#     assert len(jsondata["items"]) > 0
-#     assert jsondata["items"][0]["offerPrice"] == 390
+    vide = scraper.getsoup("")
+    poubelle = scraper.getsoup("poubelle")
+    contenu = scraper.getsoup("nino-negri-5-stelle-sfursat-2022.html")
+    assert vide.find("h1") is None
+    assert str(poubelle.find("h1")) == "<h1>POUBELLE</h1>"
+    assert str(contenu.find("h1")) == "<h1>MILLESIMA</h1>"
 
 
 def test_appellation(scraper: Scraper):
-    appellation: ScraperData = scraper.getjsondata(
-        "nino-negri-5-stelle-sfursat-2022.html"
-    )
-    assert appellation.appellation() == "Sforzato di Valtellina"
+    vide = scraper.getjsondata("")
+    poubelle = scraper.getjsondata("poubelle")
+    contenu = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
+    assert vide.appellation() is None
+    assert poubelle.appellation() is None
+    assert contenu.appellation() == "Sforzato di Valtellina"
+
+
+def test_fonctionprivee(scraper: Scraper):
+    vide = scraper.getjsondata("")
+    poubelle = scraper.getjsondata("poubelle")
+    contenu = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
+    assert vide._getattributes() is not None
+    assert vide._getattributes() == {}
+    assert vide._getcontent() is not None
+    assert vide._getcontent() == {"items": [], "attributes": {}}
+    assert poubelle._getattributes() is None
+    assert poubelle._getcontent() is None
+    assert contenu._getcontent() is not None
+    assert contenu._getattributes() is not None
+
+
+
+def test_critiques(scraper: Scraper):
+    vide = scraper.getjsondata("")
+    poubelle = scraper.getjsondata("poubelle")
+    contenu = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
+    assert vide.parker() is None
+    assert vide.robinson() is None
+    assert vide.suckling() is None
+    assert vide._getcritiques("test_ts") is None
+    assert poubelle.parker() is None
+    assert poubelle.robinson() is None
+    assert poubelle.suckling() is None
+    assert poubelle._getcritiques("test_ts") is None
+    assert contenu.parker() == "91"
+    assert contenu.robinson() == "17"
+    assert contenu.suckling() == "93.5"
+    assert contenu._getcritiques("test_ts") is None