saret/supermarket-scraping
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Fixed the bug with cerberus_web_client.py by working with Selenium. To login each chain working with it must have a username for login with Selenium. in this mechanism, a path to a gz file is returned instead of url

Browse Source 
Added the option to output a prices json file in main.py under --prices-with-promos, where the prices are updated by the latest promotions (under the 'final_price' key, where 'price' represents the price before promotions).

Fixed small bug of BinaWebCleint by checking that filename does not contain 'null'.

Changed Hierarchy of chains such that it includes the webclients.

Added the date to the output filenames to start storing the data over time.

Black formatting (according to pip 8 guidelines).

Changed the chains_dict in main to a constant one.
This commit is contained in:
korenlazar
2022-10-04 11:42:36 +03:00
parent b5db721a3d
commit ceff48dbd9
28 changed files with 796 additions and 406 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
chains/mahsaneiHashook.py
View File

@@ -1,5 +1,6 @@
import re
from typing import Dict, List
import requests
from bs4 import BeautifulSoup
from bs4.element import Tag
@@ -9,33 +10,46 @@ from supermarket_chain import SupermarketChain
class MahsaneiHashook(SupermarketChain):
_promotion_tag_name = 'Sale'
_promotion_update_tag_name = 'PriceUpdateDate'
_date_format = '%Y/%m/%d'
_date_hour_format = '%Y/%m/%d %H:%M:%S'
_update_date_format = '%Y/%m/%d %H:%M:%S'
_item_tag_name = 'Product'
_promotion_tag_name = "Sale"
_promotion_update_tag_name = "PriceUpdateDate"
_date_format = "%Y/%m/%d"
_date_hour_format = "%Y/%m/%d %H:%M:%S"
_update_date_format = "%Y/%m/%d %H:%M:%S"
_item_tag_name = "Product"
@staticmethod
def get_download_url(store_id: int, category: SupermarketChain.XMLFilesCategory, session: requests.Session) -> str:
def get_download_url_or_path(
store_id: int,
category: SupermarketChain.XMLFilesCategory,
session: requests.Session,
) -> str:
prefix = "http://matrixcatalog.co.il/"
url = prefix + "NBCompetitionRegulations.aspx"
req_res: requests.Response = requests.get(url)
soup = BeautifulSoup(req_res.text, features='lxml')
if category in [SupermarketChain.XMLFilesCategory.Promos, SupermarketChain.XMLFilesCategory.Prices]:
fname_filter_func = lambda fname: fname and category.name.replace('s', '') in fname \
and f'-{store_id:03d}-20' in fname \
and not re.search('full', fname, re.IGNORECASE)
if soup.find('a', href=fname_filter_func) is None:
soup = BeautifulSoup(req_res.text, features="lxml")
if category in [
SupermarketChain.XMLFilesCategory.Promos,
SupermarketChain.XMLFilesCategory.Prices,
]:
fname_filter_func = (
lambda fname: fname
and category.name.replace("s", "") in fname
and f"-{store_id:03d}-20" in fname
and not re.search("full", fname, re.IGNORECASE)
)
if soup.find("a", href=fname_filter_func) is None:
return "" # Could not find non-full Promos/Prices file
else:
fname_filter_func = lambda fname: fname and category.name.replace('s', '') in fname \
and f'-{store_id:03d}-20' in fname
suffix: str = soup.find('a', href=fname_filter_func).attrs['href']
fname_filter_func = (
lambda fname: fname
and category.name.replace("s", "") in fname
and f"-{store_id:03d}-20" in fname
)
suffix: str = soup.find("a", href=fname_filter_func).attrs["href"]
down_url: str = prefix + suffix
return down_url
@staticmethod
def get_items(promo: Tag, items_dict: Dict[str, Item]) -> List[Item]:
promo_item = items_dict.get(promo.find('ItemCode').text)
promo_item = items_dict.get(promo.find("ItemCode").text)
return [promo_item] if promo_item else []