mirror of
https://github.com/R0m1k3/Priceflow.git
synced 2026-10-16 19:57:55 +02:00
70 lines
2.4 KiB
Python
70 lines
2.4 KiB
Python
from bs4 import BeautifulSoup
|
|
from app.services.parsers.base_parser import BaseParser, ProductResult
|
|
import logging
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
class BoulangerParser(BaseParser):
|
|
def __init__(self):
|
|
super().__init__("boulanger.com", "https://www.boulanger.com")
|
|
|
|
def parse_search_results(self, html: str, query: str, search_url: str) -> list[ProductResult]:
|
|
soup = BeautifulSoup(html, "html.parser")
|
|
results = []
|
|
|
|
# Boulanger products
|
|
# Config: a[href*='/ref/'][href*='_']
|
|
|
|
cards = soup.select(".product-item, .product-list__item, article")
|
|
|
|
for card in cards:
|
|
try:
|
|
# Link
|
|
link_el = card.select_one("a[href*='/ref/'], a[class*='link']")
|
|
if not link_el:
|
|
continue
|
|
|
|
href = link_el.get('href')
|
|
if not href:
|
|
continue
|
|
|
|
url = self.make_absolute_url(href)
|
|
|
|
# Title
|
|
title = None
|
|
title_el = card.select_one("h2, h3, .product-label, [class*='title']")
|
|
if title_el:
|
|
title = title_el.get_text(strip=True)
|
|
else:
|
|
title = link_el.get_text(strip=True)
|
|
|
|
if not title:
|
|
continue
|
|
|
|
# Image
|
|
img_url = self.extract_image_url(card)
|
|
|
|
# Price
|
|
price = None
|
|
price_el = card.select_one(".price, .product-price, [class*='price']")
|
|
if price_el:
|
|
price = self.parse_price_text(price_el.get_text())
|
|
|
|
results.append(ProductResult(
|
|
title=title,
|
|
url=url,
|
|
source="Boulanger",
|
|
price=price,
|
|
currency="EUR",
|
|
in_stock=True,
|
|
image_url=img_url,
|
|
snippet=f"Product from Boulanger"
|
|
))
|
|
|
|
except Exception as e:
|
|
logger.error(f"Error parsing Boulanger product: {e}")
|
|
continue
|
|
|
|
logger.info(f"BoulangerParser found {len(results)} results")
|
|
return results
|