ajout: restructuration des fichiers et modifications scraper

Exo7 loic

.gitignore

@@ -205,3 +205,5 @@ cython_debug/
 marimo/_static/
 marimo/_lsp/
 __marimo__/
+
+*.csv

pyproject.toml

@@ -0,0 +1,15 @@
+[project]
+name = "projet-millesima-s6"
+version = "0.1.0"
+dependencies = [
+    "requests==2.32.5",
+    "beautifulsoup4==4.14.3",
+    "pandas==2.3.3",
+]
+
+[project.optional-dependencies]
+test = ["pytest==8.4.2", "requests-mock==1.12.1"]
+
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"

requirements.txt

@@ -1,3 +0,0 @@
-requests>=2.32.5
-requests-mock>=1.12.1
-beautifulsoup4>=4.14.3

src/main.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python3
+
+from os import getcwd
+from os.path import normpath, join
+from sys import argv
+from pandas import read_csv, DataFrame
+
+def main() -> None:
+    if len(argv) != 2:
+        raise ValueError(f"{argv[0]} <filename.csv>")
+
+    path: str = normpath(join(getcwd(), argv[1]))
+    db: DataFrame = read_csv(path)
+    print(db.all())
+
+if __name__ == "__main__":
+    try:
+        main()
+    except Exception as e:
+        print(f"ERREUR: {e}")

src/scraper.py

@@ -1,12 +1,22 @@
+#!/usr/bin/env python3
+
+from sys import argv
 from typing import cast
-from requests import Response, Session
+from requests import HTTPError, Response, Session
 from bs4 import BeautifulSoup, Tag
 from collections import OrderedDict
-from json import loads
+from json import JSONDecodeError, loads
 
 
 class _ScraperData:
+    """_summary_"""
+
     def __init__(self, data: dict[str, object]) -> None:
+        """_summary_
+
+        Args:
+            data (dict[str, object]): _description_
+        """
         self._data: dict[str, object] = data
 
     def _getcontent(self) -> dict[str, object] | None:
@@ -55,7 +65,6 @@ class _ScraperData:
         prix_calcule: float | None = None
 
         for item in items:
-
             if not isinstance(item, dict):
                 continue
 
@@ -114,8 +123,8 @@ class _ScraperData:
                 return None
 
             val = cast(str, app_dict.get("value")).rstrip("+").split("-")
-            if len(val) > 1:
+            if len(val) > 1 and val[1] != "":
-                val[0] = str((int(val[0]) + int(val[1])) / 2)
+                val[0] = str(round((float(val[0]) + float(val[1])) / 2, 1))
 
             return val[0]
         return None
@@ -165,6 +174,18 @@ class Scraper:
         # Très utile pour éviter de renvoyer toujours les mêmes handshake
         # TCP et d'avoir toujours une connexion constante avec le server
         self._session: Session = Session()
+        # Crée une "fausse carte d'identité" pour éviter que le site nous
+        # bloque car on serait des robots
+        self._session.headers.update(
+            {
+                "User-Agent": 
+                    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) \
+                     AppleWebKit/537.36 (KHTML, like Gecko) \
+                     Chrome/122.0.0.0 Safari/537.36",
+                "Accept-Language": 
+                    "fr-FR,fr;q=0.9,en;q=0.8",
+            }
+        )
         # Système de cache pour éviter de solliciter le serveur inutilement
         self._latest_request: tuple[(str, Response)] | None = None
         self._latest_soups: OrderedDict[str, BeautifulSoup] = OrderedDict[
@@ -185,7 +206,8 @@ class Scraper:
             HTTPError: Si le serveur renvoie un code d'erreur (4xx, 5xx).
         """
         target_url: str = self._url + subdir.lstrip("/")
-        response: Response = self._session.get(url=target_url, timeout=10)
+        # envoyer une requête GET sur la page si erreur, renvoie un raise
+        response: Response = self._session.get(url=target_url, timeout=30)
         response.raise_for_status()
         return response
 
@@ -285,3 +307,79 @@ class Scraper:
 
         return _ScraperData(cast(dict[str, object], current_data))
 
+    def _geturlproductslist(self, subdir: str) -> list[str] | None:
+        """_summary_
+
+        Args:
+            subdir (str): _description_
+
+        Returns:
+            _type_: _description_
+        """
+        try:
+            data: dict[str, object] = self.getjsondata(subdir).getdata()
+
+            for element in ["initialReduxState", "categ", "content"]:
+                data: dict[str, object] = cast(dict[str, object], data.get(element))
+                if not isinstance(data, dict):
+                    return None
+
+            products: list[str] = cast(list[str], data.get("products"))
+            if isinstance(products, list):
+                return products
+
+        except (JSONDecodeError, HTTPError):
+            return None
+
+    def getvins(self, subdir: str, filename: str) -> None:
+        """_summary_
+
+        Args:
+            subdir (str): _description_
+            filename (str): _description_
+        """
+        with open(filename, "w") as f:
+            cache: set[str] = set[str]()
+            page = 0
+            _ = f.write("Appellation,Robert,Robinson,Suckling,Prix\n")
+
+            while True:
+                page += 1
+                products_list: list[str] | None = \
+                    self._geturlproductslist(f"{subdir}?page={page}")
+
+                if not products_list:
+                    break
+
+                products_list_length = len(products_list)
+                for i, product in enumerate(products_list):
+                    if not isinstance(product, dict):
+                        continue
+
+                    link = product.get("seoKeyword")
+
+                    if link and link not in cache:
+                        try:
+                            infos = self.getjsondata(link).informations()
+                            _ = f.write(infos + "\n")
+                            print(
+                                f"page: {page} | {i + 1}/{products_list_length} {link}"
+                            )
+                            cache.add(link)
+                        except (JSONDecodeError, HTTPError) as e:
+                            print(f"Erreur sur le produit {link}: {e}")
+                f.flush()
+
+
+def main() -> None:
+    if len(argv) != 2:
+        raise ValueError(f"{argv[0]} <sous-url>")
+    scraper: Scraper = Scraper()
+    scraper.getvins(argv[1], "donnee.csv")
+
+
+if __name__ == "__main__":
+    try:
+        main()
+    except Exception as e:
+        print(f"ERREUR: {e}")

tests/test_scraper.py

@@ -1,8 +1,8 @@
 from json import dumps
-from bs4 import Tag
+from unittest.mock import patch, mock_open
 import pytest
 from requests_mock import Mocker
-from main import Scraper
+from scraper import Scraper
 
 
 @pytest.fixture(autouse=True)
@@ -71,10 +71,10 @@ def mock_site():
                                         "_id": "J4131/22/C/CC/6-11652",
                                         "partnumber": "J4131/22/C/CC/6",
                                         "taxRate": "H",
-                                        "listPrice": 390,
+                                        "listPrice": 842,
-                                        "offerPrice": 390,
+                                        "offerPrice": 842,
-                                        "seoKeyword": "nino-negri-5-stelle-sfursat-2022-c-cc-6.html",
+                                        "seoKeyword": "vin-de-charazade1867.html",
-                                        "shortdesc": "Un carton de 6 Bouteilles (75cl)",
+                                        "shortdesc": "Une bouteille du meilleur vin du monde?",
                                         "attributes": {
                                             "promotion_o_n": {
                                                 "valueId": "0",
@@ -101,9 +101,9 @@ def mock_site():
                                                 "isSpirit": False,
                                             },
                                             "nbunit": {
-                                                "valueId": "6",
+                                                "valueId": "1",
                                                 "name": "nbunit",
-                                                "value": "6",
+                                                "value": "1",
                                                 "isSpirit": False,
                                             },
                                         },
@@ -120,14 +120,14 @@ def mock_site():
                                     "appellation": {
                                         "valueId": "433",
                                         "name": "Appellation",
-                                        "value": "Sforzato di Valtellina",
+                                        "value": "Madame-Loïk",
-                                        "url": "sforzato-di-valtellina.html",
+                                        "url": "Madame-loik.html",
                                         "isSpirit": False,
                                         "groupIdentifier": "appellation_433",
                                     },
                                     "note_rp": {
                                         "valueId": "91",
-                                        "name": "Parker",
+                                        "name": "Peter Parker",
                                         "value": "91",
                                         "isSpirit": False,
                                     },
@@ -138,8 +138,8 @@ def mock_site():
                                         "isSpirit": False,
                                     },
                                     "note_js": {
-                                        "valueId": "93-94",
+                                        "valueId": "93-94.5",
-                                        "name": "J. Suckling",
+                                        "name": "J. cherazade",
                                         "value": "93-94",
                                         "isSpirit": False,
                                     },
@@ -166,6 +166,79 @@ def mock_site():
             text=html_product,
         )
 
+        html_product = f"""
+        <html>
+            <body>    
+                <h1>MILLESIMA</h1>
+                <script id="__NEXT_DATA__" type="application/json">
+                    {dumps(json_data)}
+                </script>
+            </body>
+        </html>
+        """
+
+        list_pleine = f"""
+            <html>
+                <body>    
+                    <h1>LE WINE</h1>
+                    <script id="__NEXT_DATA__" type="application/json">
+                        {dumps({
+                            "props": {
+                                "pageProps": {
+                                    "initialReduxState": {
+                                        "categ": {
+                                            "content": {
+                                                "products": [
+                                                    {"seoKeyword": "/nino-negri-5-stelle-sfursat-2022.html",},
+                                                    {"seoKeyword": "/poubelle",},
+                                                    {"seoKeyword": "/",}
+                                                ]
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                        )}
+                    </script>
+                </body>
+            </html>
+            """
+
+        list_vide = f"""
+            <html>
+                <body>    
+                    <h1>LE WINE</h1>
+                    <script id="__NEXT_DATA__" type="application/json">
+                        {dumps({
+                            "props": {
+                                "pageProps": {
+                                    "initialReduxState": {
+                                        "categ": {
+                                            "content": {
+                                                "products": [
+                                                ]
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                        )}
+                    </script>
+                </body>
+            </html>
+            """
+
+        m.get(
+            "https://www.millesima.fr/wine.html",
+            complete_qs=False,
+            response_list=[
+                {"text": list_pleine},
+                {"text": list_vide},
+            ],
+        )
+
         # on return m sans fermer le server qui simule la page
         yield m
 
@@ -190,7 +263,7 @@ def test_appellation(scraper: Scraper):
     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"
+    assert contenu.appellation() == "Madame-Loïk"
 
 
 def test_fonctionprivee(scraper: Scraper):
@@ -207,7 +280,6 @@ def test_fonctionprivee(scraper: Scraper):
     assert contenu._getattributes() is not None
 
 
-
 def test_critiques(scraper: Scraper):
     vide = scraper.getjsondata("")
     poubelle = scraper.getjsondata("poubelle")
@@ -232,13 +304,23 @@ def test_prix(scraper: Scraper):
     contenu = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
     assert vide.prix() is None
     assert poubelle.prix() is None
-    assert contenu.prix() == 65.0
+    assert contenu.prix() == 842.0
 
 
 def test_informations(scraper: Scraper):
     contenu = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
-    assert contenu.informations() == "Sforzato di Valtellina,91,17,93.5,65.0"
+    assert contenu.informations() == "Madame-Loïk,91,17,93.5,842.0"
     vide = scraper.getjsondata("")
     poubelle = scraper.getjsondata("poubelle")
     assert vide.informations() == "None,None,None,None,None"
     assert poubelle.informations() == "None,None,None,None,None"
+
+
+def test_search(scraper: Scraper):
+    m = mock_open()
+    with patch("builtins.open", m):
+        scraper.getvins("wine.html", "fake_file.csv")
+
+    assert m().write.called
+    all_writes = "".join(call.args[0] for call in m().write.call_args_list)
+    assert "Madame-Loïk,91,17,93.5,842.0" in all_writes