python web scraper urllib.requests

web_scrape.py

# -*- coding: utf-8 -*-
"""
Created on Mon Mar 15 16:36:30 2021

@author: dsuser
"""

import os
print(os.getcwd())
os.chdir("C:/Users/Public/Desktop/TraceData/hscni-analytics-data/R/risk_assess")
print(os.getcwd())
import urllib.request
import datetime

x=datetime.date.today()
x_d=datetime.timedelta(-1)
x1=x+x_d

def formatDate(x):
    print(x.day)
    print(x.month)
    print(x.year)
    
    if len(str(x.day))!=2:
        xd='0'+str(x.day)
        xd
        
    if len(str(x.month))!=2:
        xm='0'+str(x.month)
        xm
        
    xy=str(x.year)[2:]
    xy    
    
    date=str(x.day)+str(xm)+str(xy)
    return date

todayFormated=formatDate(x)
print('today (ddmmyy): ',todayFormated)
yesterdayFormated=formatDate(x1)
print('yesterday: '+ yesterdayFormated)

newfileName="https://www.health-ni.gov.uk/sites/default/files/publications/health/doh-dd-"+todayFormated+".xlsx"
dls = "https://www.health-ni.gov.uk/sites/default/files/publications/health/doh-dd-"+yesterdayFormated+".xlsx"

try:
    urllib.request.urlretrieve(newfileName, "DoH_latest.xlsx")
    print('todays file is released and loaded from doH')
except:
    urllib.request.urlretrieve(dls, "DoH_latest.xlsx")
    print('todays file not available yet, defaulting to yesterdays')