survey-extraction/etl/daily_script.py

41 lines
1.3 KiB
Python

import os
from pdfReader.pdfReaderToText import pdfReaderToText
from etl.scraper.scraper import SharePointScraper, SharePointInstaller
from pprint import pprint, pformat
import logging
from etl.utils.logger import Logger
from etl.validator.validator import DomnaSharePointValidator
logger = Logger(name="main.py", level=logging.INFO).get_logger()
def main():
"""
This script returns a list of names that is misformatted in the sharepoint
"""
# Correct dates format checker
south_coast_scraper = SharePointScraper(SharePointInstaller.SOUTH_COAST_INSULATION)
south_coast_names = south_coast_scraper.list_of_names_that_has_the_wrong_date_format()
jjc_scraper = SharePointScraper(SharePointInstaller.JJC)
jjc_names = jjc_scraper.list_of_names_that_has_the_wrong_date_format()
logger.info("Good morning Cyrus")
if south_coast_names:
logger.info("South Coast with wrong date format:")
logger.info(pformat(south_coast_names))
if jjc_names:
logger.info("JJC with wrong date format")
logger.info(pformat(jjc_names))
# Make a quick script that checks if the Pictures folder exists in a certain fail directory
# Make a cron job in github runner for Cyrus for this
logger.info("Hope this helps! <3")
if __name__ == "__main__":
main()