ajout : moyennes des notes par appellation

cleaning.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+from pandas import DataFrame, to_numeric
+
+
+def display_info(df: DataFrame) -> None:
+    print(df.all())
+    print(df.info())
+    print("\nNombre de valeurs manquantes par colonne :")
+    print(df.isna().sum())
+
+
+def drop_empty_appellation(df: DataFrame) -> DataFrame:
+
+    return df.dropna(subset=["Appellation"])
+
+
+def mean_score(df: DataFrame, col: str) -> DataFrame:
+    """
+    Calcule la moyenne d'une colonne de score par appellation.
+        - Convertit les valeurs en numériques, en remplaçant les non-convertibles par NaN
+        - Calcule la moyenne par appellation
+        - Remplace les NaN résultants par 0 
+
+    """
+    tmp = df[["Appellation", col]].copy()
+
+    tmp[col] = to_numeric(tmp[col], errors="coerce")
+
+    # moyenne par appellation
+    means = tmp.groupby("Appellation", as_index=False)[col].mean()
+    
+    means[col] = means[col].fillna(0)
+    
+    means = means.rename(columns={col: f"mean_{col}"})
+    
+    return means
+
+
+def mean_robert(df: DataFrame) -> DataFrame:
+    return mean_score(df, "Robert")
+
+
+def mean_robinson(df: DataFrame) -> DataFrame:
+    return mean_score(df, "Robinson")
+
+
+def mean_suckling(df: DataFrame) -> DataFrame:
+    return mean_score(df, "Suckling")

main.py

@@ -5,13 +5,53 @@ from os.path import normpath, join
 from sys import argv
 from pandas import read_csv, DataFrame
 
+from cleaning import (display_info,
+                      drop_empty_appellation,
+                      mean_robert,
+                      mean_robinson,
+                      mean_suckling)
+
+
+def load_csv(filename: str) -> DataFrame:
+    path: str = normpath(join(getcwd(), filename))
+    return read_csv(path)
+
+
+def save_csv(df: DataFrame, out_filename: str) -> None:
+    df.to_csv(out_filename, index=False)
+
+
 def main() -> None:
     if len(argv) != 2:
-        raise ValueError(f"{argv[0]} <filename.csv>")
+        raise ValueError(f"Usage: {argv[0]} <filename.csv>")
+
+    df = load_csv(argv[1])
+
+    print("=== Avant nettoyage ===")
+    display_info(df)
+
+    df = drop_empty_appellation(df)
+    save_csv(df, "donnee_clean.csv")
+
+    print("\n=== Après nettoyage d'appellations manquantes ===")
+    display_info(df)
+    
+    #la moyenne des notes des vins pour chaque appellation
+    robert_means = mean_robert(df)
+    save_csv(robert_means, "mean_robert_by_appellation.csv")
+    print("\n=== moyenne Robert par appellation ===")
+    print(robert_means.head(10))
+
+    robinson_means = mean_robinson(df)
+    save_csv(robinson_means, "mean_robinson_by_appellation.csv")
+    print("\n===: moyennes Robinson par appellation ===")
+    print(robinson_means.head(10))
+    
+    suckling_means = mean_suckling(df)
+    save_csv(suckling_means, "mean_suckling_by_appellation.csv")
+    print("\n===: moyennes Suckling par appellation ===")
+    print(suckling_means.head(10))
 
-    path: str = normpath(join(getcwd(), argv[1]))
-    db: DataFrame = read_csv(path)
-    print(db.all())
 
 if __name__ == "__main__":
     try:

scraper.py

@@ -3,9 +3,12 @@
 from sys import argv
 from typing import cast
 from requests import HTTPError, Response, Session
+from requests.exceptions import Timeout, ConnectionError
+import time
 from bs4 import BeautifulSoup, Tag
 from collections import OrderedDict
 from json import JSONDecodeError, loads
+from pathlib import Path
 
 
 class _ScraperData:
@@ -151,10 +154,7 @@ class _ScraperData:
         parker = self.parker()
         robinson = self.robinson()
         suckling = self.suckling()
-        try:
+        prix = self.prix()
-            prix = self.prix()
-        except ValueError:
-            prix = None
 
         return f"{appellation},{parker},{robinson},{suckling},{prix}"
 
@@ -174,6 +174,12 @@ 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()
+        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[
@@ -194,9 +200,20 @@ 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)
+        
-        response.raise_for_status()
+        last_exc: Exception | None = None
-        return response
+        for attempt in range(1, 4):
+            try:
+                response: Response = self._session.get(url=target_url, timeout=30)
+                response.raise_for_status()
+                return response
+            except (Timeout, ConnectionError) as e:
+                last_exc = e
+                print(f"Timeout/ConnectionError ({attempt}/3) sur {target_url}: {e}")
+                time.sleep(2 * attempt)  # 2s, 4s, 6s
+
+        # après 3 essais, on abandonne
+        raise last_exc if last_exc else RuntimeError("Request failed")
 
     def getresponse(self, subdir: str = "", use_cache: bool = True) -> Response:
         """
@@ -318,6 +335,27 @@ class Scraper:
         except (JSONDecodeError, HTTPError):
             return None
 
+    def _save_progress(self, page: int, i: int, last_link: str) -> None:
+        Path("progress.txt").write_text(f"{page},{i},{last_link}", encoding="utf-8")
+
+
+    def _load_progress(self) -> tuple[int, int, str | None]:
+        p = Path("progress.txt")
+        if not p.exists():
+            return (1, 0, None)
+
+        try:
+            parts = p.read_text(encoding="utf-8").strip().split(",", 2)
+
+            page = int(parts[0])
+            i = int(parts[1])
+
+            last_link = parts[2] if len(parts) == 3 and parts[2] != "" else None
+            return (page, i, last_link)
+
+        except Exception:
+            return (1, 0, None)
+        
     def getvins(self, subdir: str, filename: str):
         """_summary_
 
@@ -325,10 +363,16 @@ class Scraper:
             subdir (str): _description_
             filename (str): _description_
         """
-        with open(filename, "a") as f:
+        start_page, start_i, last_link = self._load_progress()
+        print(f"__INFO__ Reprise à page={start_page}, index={start_i}, last_link={last_link}")
+        
+        with open(filename, "a", encoding="utf-8") as f:
             cache: set[str] = set[str]()
-            page = 0
+            
-            _ = f.write("Appellation,Robert,Robinson,Suckling,Prix\n")
+            if f.tell() == 0:
+                _ = f.write("Appellation,Robert,Robinson,Suckling,Prix\n")
+                
+            page = start_page - 1
             
             while True:
                 page += 1
@@ -338,24 +382,40 @@ class Scraper:
                     break
 
                 products_list_length = len(products_list)
-                for i, product in enumerate(products_list):
+                start_at = start_i if page == start_page else 0
+
+                for i in range(start_at, products_list_length):
+                    product = products_list[i]
                     if not isinstance(product, dict):
                         continue
 
                     link = product.get("seoKeyword")
+                    if not link:
+                        continue
+
+                    # pour eviter les doublons :
+                    if (page == start_page) and (last_link is not None) and (link == last_link):
+                        self._save_progress(page, + 1, link)
+                        continue
+
+                    self._save_progress(page, i + 1, link)
+
+                    if link in cache:
+                        continue
+
+                    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}")
 
-                    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()
 
+        Path("progress.txt").unlink(missing_ok=True)
+
 
 def main() -> None:
     if len(argv) != 2: