mirror of
https://github.com/R0m1k3/Priceflow.git
synced 2026-10-14 10:46:32 +02:00
Claude
d2c492ff5c
Complete refactoring of the search module for robustness and reliability: **New Architecture:** - Modular parser system with specialized parsers for each major site - Factory pattern for automatic parser selection - Generic fallback parser for sites without specific implementation **Specialized Parsers:** - ✅ Amazon.fr - Robust parser with multiple fallback selectors - Handles sponsored products, Prime eligibility, ratings, reviews - Based on proven amazon_scraper_v2.py implementation - ✅ Cdiscount.com - Optimized for Cdiscount's HTML structure - ✅ Fnac.com - Handles Fnac's picture elements and article structure - ✅ Darty.com - Specialized for electronics retailer - ✅ Boulanger.com - Optimized for Boulanger's product cards **Key Features:** - Multiple fallback selectors for each element (title, price, image) - Proper price parsing for French format (1 234,56 €) - Rating and review count extraction - Stock status detection - Image URL extraction with multiple attribute fallbacks - Query filtering to ensure relevant results **Benefits:** - Much more robust than previous generic parsing - Easier to maintain (one parser per site) - Easily extensible (add new parser for new site) - Better error handling and logging - Higher success rate for product extraction **Updated Services:** - improved_search_service.py now uses ParserFactory - Legacy _parse_results marked as deprecated - Conversion layer between ProductResult and SearchResult This implements the Amazon France model across all major sites for consistent, reliable product search results.
132 lines
4.2 KiB
Python
132 lines
4.2 KiB
Python
"""
|
|
Darty Parser - Specialized parser for Darty.com
|
|
"""
|
|
|
|
from bs4 import BeautifulSoup
|
|
|
|
from .base_parser import BaseParser, ProductResult
|
|
|
|
|
|
class DartyParser(BaseParser):
|
|
"""
|
|
Parser for Darty.com
|
|
|
|
Key selectors:
|
|
- Product links: a[href*='/nav/achat/'][href*='.html']
|
|
- Images: img.product_img
|
|
"""
|
|
|
|
def __init__(self):
|
|
super().__init__(
|
|
site_name="Darty",
|
|
base_url="https://www.darty.com"
|
|
)
|
|
|
|
def parse_search_results(self, html: str, query: str, search_url: str) -> list[ProductResult]:
|
|
"""Parse Darty search results"""
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
products = []
|
|
|
|
# Try multiple selectors
|
|
selectors = [
|
|
"a[href*='/nav/achat/'][href*='.html']",
|
|
".product-card a",
|
|
"[class*='product'] a[href*='/nav/achat/']",
|
|
]
|
|
|
|
links = []
|
|
for selector in selectors:
|
|
links = soup.select(selector)
|
|
if links:
|
|
self.logger.info(f"Found {len(links)} products with selector: {selector}")
|
|
break
|
|
|
|
if not links:
|
|
self.logger.warning("No products found on Darty")
|
|
return []
|
|
|
|
seen_urls = set()
|
|
|
|
for link in links:
|
|
try:
|
|
href = link.get("href")
|
|
if not href:
|
|
continue
|
|
|
|
full_url = self.make_absolute_url(href)
|
|
|
|
if full_url in seen_urls:
|
|
continue
|
|
seen_urls.add(full_url)
|
|
|
|
# Extract title
|
|
title = link.get_text(strip=True)
|
|
if not title:
|
|
title = link.get("title", "")
|
|
|
|
# Try in parent
|
|
if not title or len(title) < 3:
|
|
parent = link.find_parent(["article", "li", "div"])
|
|
if parent:
|
|
title_elem = parent.select_one("h2, h3, .product-title, [class*='title']")
|
|
if title_elem:
|
|
title = title_elem.get_text(strip=True)
|
|
|
|
if not title or len(title) < 3:
|
|
continue
|
|
|
|
# Filter by query
|
|
if not self.filter_by_query(title, query):
|
|
continue
|
|
|
|
# Extract image
|
|
image_url = None
|
|
parent = link.find_parent(["article", "li", "div"])
|
|
if parent:
|
|
img_selectors = [
|
|
"img.product_img",
|
|
"img.product-image",
|
|
"img[class*='product']",
|
|
"img",
|
|
]
|
|
for img_sel in img_selectors:
|
|
img = parent.select_one(img_sel)
|
|
if img:
|
|
image_url = self._get_image_src(img)
|
|
if image_url:
|
|
image_url = self.make_absolute_url(image_url)
|
|
break
|
|
|
|
# Extract price
|
|
price = None
|
|
if parent:
|
|
price_selectors = [
|
|
".price",
|
|
"[class*='price'][class*='current']",
|
|
"[data-testid='price']",
|
|
"span[class*='prix']",
|
|
]
|
|
for price_sel in price_selectors:
|
|
price_elem = parent.select_one(price_sel)
|
|
if price_elem:
|
|
price = self.parse_price_text(price_elem.get_text(strip=True))
|
|
if price:
|
|
break
|
|
|
|
products.append(ProductResult(
|
|
title=title,
|
|
url=full_url,
|
|
source=self.site_name,
|
|
price=price,
|
|
currency="EUR",
|
|
image_url=image_url,
|
|
snippet=f"Product from {self.site_name}"
|
|
))
|
|
|
|
except Exception as e:
|
|
self.logger.error(f"Error parsing Darty product: {e}")
|
|
continue
|
|
|
|
self.logger.info(f"Extracted {len(products)} products from Darty")
|
|
return products
|