Files
supermarket-scraping/shufersal.py
2020-12-26 17:18:21 +02:00

41 lines
1.4 KiB
Python

from typing import Dict, List
import requests
from bs4 import BeautifulSoup
from bs4.element import Tag
from supermarket_chain import SupermarketChain
class ShuferSal(SupermarketChain):
promotion_tag_name = 'Promotion'
promotion_update_tag_name = 'PromotionUpdateDate'
date_format = '%Y-%m-%d'
date_hour_format = '%Y-%m-%d %H:%M'
item_tag_name = 'Item'
@staticmethod
def get_download_url(store_id: int, category: SupermarketChain.XMLFilesCategory) -> str:
url = f"http://prices.shufersal.co.il/FileObject/UpdateCategory?catID={category.value}"
if SupermarketChain.is_valid_store_id(int(store_id)):
url += f"&storeId={store_id}"
req_res: requests.Response = requests.get(url)
soup = BeautifulSoup(req_res.text, features='lxml')
down_url = soup.find('a', text="לחץ להורדה")['href']
print(down_url)
return down_url
class XMLFilesCategory(SupermarketChain.XMLFilesCategory):
All, Prices, PricesFull, Promos, PromosFull, Stores = range(6)
def __repr__(self):
return 'Shufersal'
@staticmethod
def get_items(promo: Tag, items_dict: Dict[str, str]) -> List[str]:
items = list()
for item in promo.find_all('Item'):
item_code = item.find('ItemCode').text
full_item_info = items_dict.get(item_code)
if full_item_info:
items.append(full_item_info)
return items