junte/survey-extraction
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/survey-extraction.git synced 2026-06-08 11:17:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

save

Browse source
This commit is contained in:
Jun-te Kim 2025-03-05 18:30:36 +00:00
parent 67bdd6b259
commit 65e9b415fd
2 changed files with 10 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
etl/src/etl/main.py
View file

@ -15,14 +15,14 @@ logger = Logger(name="main.py", level=logging.DEBUG).get_logger()
def main():
# POC PDF Reader
#list_ = pdfReaderToText(INTERESTING_FILE_LOC).get_list_of_test()
#pprint(list_)
list_ = pdfReaderToText(INTERESTING_FILE_LOC).get_list_of_test()
pprint(list_)
# POC Scraper from sharepoint and get useful data
south_coast_scraper = SharePointScraper(SharePointInstaller.SOUTH_COAST_INSULATION_SERVICE)
list_of_names = south_coast_scraper.list_of_names_that_has_the_wrong_date_format()
logger.info(pformat(list_of_names))
# south_coast_scraper = SharePointScraper(SharePointInstaller.SOUTH_COAST_INSULATION_SERVICE)
# list_of_names = south_coast_scraper.list_of_names_that_has_the_wrong_date_format()
# logger.info(pformat(list_of_names))
@ -37,3 +37,7 @@ def main():
if __name__ == "__main__":
main()
# Khalim would like these metrics from the pdf
# address, uprn, assessor's name validation, current sap rating, current annual emissions. DImension
#

1
etl/src/etl/validator/validator.py
View file

@ -12,6 +12,7 @@ class DomnaSharePointValidator():
def valid_dates(list_of_dates_to_check):
# Patten Nic wants: W.C. DD.MM.YYYY
# TODO: Ideally split the date and W.C. and use a datatime library so its more standardised
pattern = r"^W\.C\. (0[1-9]|[12][0-9]|3[01])\.(0[1-9]|1[0-2])\.(\d{4})$"