before claude

pricewatch/app/stores/cdiscount/store.py

@@ -112,7 +112,7 @@ class CdiscountStore(BaseStore):
         currency = self._extract_currency(soup, debug_info)
         stock_status = self._extract_stock(soup, debug_info)
         images = self._extract_images(soup, debug_info)
-        category = self._extract_category(soup, debug_info)
+        category = self._extract_category(soup, debug_info, url)
         specs = self._extract_specs(soup, debug_info)
         description = self._extract_description(soup, debug_info)
         msrp = self._extract_msrp(soup, debug_info)
@@ -180,7 +180,7 @@ class CdiscountStore(BaseStore):
         return None
 
     def _extract_price(self, soup: BeautifulSoup, debug: DebugInfo) -> Optional[float]:
-        """Extrait le prix."""
+        """Extrait le prix (DOM puis JSON-LD)."""
         selectors = self.get_selector("price", [])
         if isinstance(selectors, str):
             selectors = [selectors]
@@ -188,16 +188,33 @@ class CdiscountStore(BaseStore):
         for selector in selectors:
             elements = soup.select(selector)
             for element in elements:
-                # Attribut content (schema.org) ou texte
                 price_text = element.get("content") or element.get_text(strip=True)
-
                 price = parse_price_text(price_text)
                 if price is not None:
                     return price
 
+        price = self._extract_price_from_json_ld(soup)
+        if price is not None:
+            return price
+
         debug.errors.append("Prix non trouvé")
         return None
 
+    def _extract_price_from_json_ld(self, soup: BeautifulSoup) -> Optional[float]:
+        """Extrait le prix depuis les scripts JSON-LD."""
+        product_ld = self._find_product_ld(soup)
+        offers = product_ld.get("offers")
+        if isinstance(offers, list):
+            offers = offers[0] if offers else None
+        if isinstance(offers, dict):
+            price = offers.get("price")
+            if isinstance(price, str):
+                return parse_price_text(price)
+            if isinstance(price, (int, float)):
+                # convert to float but maintain decimals
+                return float(price)
+        return None
+
     def _extract_msrp(self, soup: BeautifulSoup, debug: DebugInfo) -> Optional[float]:
         """Extrait le prix conseille."""
         selectors = [
@@ -205,6 +222,8 @@ class CdiscountStore(BaseStore):
             ".price__old",
             ".c-price__strike",
             ".price-strike",
+            "div[data-e2e='strikedPrice']",
+            "div.SecondaryPrice-price",
         ]
         for selector in selectors:
             element = soup.select_one(selector)
@@ -212,6 +231,19 @@ class CdiscountStore(BaseStore):
                 price = parse_price_text(element.get_text(strip=True))
                 if price is not None:
                     return price
+        # Fallback: JSON-LD (offers price + promotions)
+        product_ld = self._find_product_ld(soup)
+        offer = product_ld.get("offers")
+        if isinstance(offer, dict):
+            price = offer.get("price")
+            if isinstance(price, str):
+                candidate = parse_price_text(price)
+            elif isinstance(price, (int, float)):
+                candidate = float(price)
+            else:
+                candidate = None
+            if candidate is not None:
+                return candidate
         return None
 
     def _extract_currency(self, soup: BeautifulSoup, debug: DebugInfo) -> Optional[str]:
@@ -288,7 +320,7 @@ class CdiscountStore(BaseStore):
 
         return list(dict.fromkeys(images))  # Préserver l’ordre
 
-    def _extract_category(self, soup: BeautifulSoup, debug: DebugInfo) -> Optional[str]:
+    def _extract_category(self, soup: BeautifulSoup, debug: DebugInfo, url: str) -> Optional[str]:
         """Extrait la catégorie depuis les breadcrumbs."""
         selectors = self.get_selector("category", [])
         if isinstance(selectors, str):
@@ -310,6 +342,54 @@ class CdiscountStore(BaseStore):
                     if parts:
                         return parts[-1]
 
+        if title := self._extract_category_from_breadcrumbs(soup):
+            return title
+        return self._extract_category_from_url(url)
+
+    def _extract_category_from_breadcrumbs(self, soup: BeautifulSoup) -> Optional[str]:
+        """Cherche un breadcrumb via JSON-LD (BreadcrumbList) et retourne l'avant-dernier item."""
+        entries = self._extract_json_ld_entries(soup)
+        for entry in entries:
+            if not isinstance(entry, dict):
+                continue
+            if entry.get("@type") != "BreadcrumbList":
+                continue
+            items = entry.get("itemListElement", [])
+            if not isinstance(items, list):
+                continue
+            positions = [
+                element.get("position")
+                for element in items
+                if isinstance(element, dict) and isinstance(element.get("position"), int)
+            ]
+            max_pos = max(positions) if positions else None
+            for element in reversed(items):
+                if not isinstance(element, dict):
+                    continue
+                position = element.get("position")
+                if max_pos is not None and position == max_pos:
+                    continue
+                item = element.get("item", {})
+                name = item.get("name")
+                if name and isinstance(name, str):
+                    title = name.strip()
+                    if title:
+                        return title
+        return None
+
+    def _extract_category_from_url(self, url: str) -> Optional[str]:
+        """Déduit la catégorie via l'URL /informatique/.../f-..."""
+        if not url:
+            return None
+        parsed = urlparse(url)
+        segments = [seg for seg in parsed.path.split("/") if seg]
+        breadcrumb = []
+        for segment in segments:
+            if segment.startswith("f-") or segment.startswith("p-"):
+                break
+            breadcrumb.append(segment)
+        if breadcrumb:
+            return breadcrumb[-1].replace("-", " ").title()
         return None
 
     def _extract_json_ld_entries(self, soup: BeautifulSoup) -> list[dict]:

pricewatch/app/stores/price_parser.py

@@ -17,6 +17,18 @@ def parse_price_text(text: str) -> Optional[float]:
     if not text:
         return None
 
+    euro_suffix = re.search(r"([0-9 .,]+)\s*€\s*(\d{2})\b", text)
+    if euro_suffix:
+        integer_part = euro_suffix.group(1)
+        decimal_part = euro_suffix.group(2)
+        integer_clean = re.sub(r"[^\d]", "", integer_part)
+        if integer_clean:
+            cleaned_decimal = f"{integer_clean}.{decimal_part}"
+            try:
+                return float(cleaned_decimal)
+            except ValueError:
+                pass
+        # Fallback to original replacement if suffix logic fails
     text = re.sub(r"(\d)\s*€\s*(\d)", r"\1,\2", text)
     cleaned = text.replace("\u00a0", " ").replace("\u202f", " ").replace("\u2009", " ")
     cleaned = "".join(ch for ch in cleaned if ch.isdigit() or ch in ".,")