Webscrapping using BASH

script.sh

#!/bin/bash
 # This is example of how your can Webscrap using curl , Here i Webscraped my Gas and Electricity and Got all neccessary Information , Just change LINKS to get your corresponding bills to yours.
  
  GASFILE='file:///tmp/gas.html'
  GASLINK="https://www.sngpl.com.pk/web/viewbill?consumer=02613930003&proc=viewbill&contype=NewCon"
  electricityLINK="https://bill.pitc.com.pk/pescobill/general?refno=08262140100430"
  electricityFILE='/tmp/e.txt'

# TOOLS USED HERE: html2text - grep - wget
# Download and Convert ELECTRICTITY to Text  electricity bill for easy extraction 
wget -O /tmp/e.html $electricityLINK
html2text /tmp/e.html > /tmp/e.txt

# Download Gas file to work with offline (Prefered method. Fast processing speed)
wget -O /tmp/gas.html $GASLINK

function g_currentBill(){
  curl -s $GASFILE |
  hxnormalize -x |
  hxselect -c '.txt-bld > td:first-child' 
}
function g_dueDate(){
  curl -s $GASFILE | 
  hxnormalize -x |
  grep -o -P '(?<=<td class="txt-bld">).*(?=</td>)' |
  head -5 |
  tail -n 1
}
function g_billAfterDueDate(){
  curl -s $GASFILE | 
  hxnormalize -x |
  grep -o -P '(?<=<td class="txt-bld">).*(?=</td>)' |
  head -4 |
  tail -n 1
}
function g_accountNumber(){
  curl -s $GASFILE | 
  hxnormalize -x |
  grep -o -P '(?<=<td class="txt-bld">).*(?=</td>)' |
  head -2 |
  tail -n 1
}

function g_dues(){
  curl -s $GASFILE | 
  hxnormalize -x |
  grep -m 1 -o -P '(?<=<td class="txt-rt">).*(?=</td>)'
}

function name(){
  curl -s $GASFILE | 
  hxnormalize -x |
  hxselect -c '.data-td-en.bdr-bt'
}

function g_billingMonth(){
  curl -s $GASFILE |
  grep -o -P '(?<=Billing Month</td><td>).*(?=</td></tr><tr height=)' |
  cut -c 1-8 # Here i Cut because i wasn't able to retrieve only month and year
}


function e_cb(){
cat $electricityFILE | grep "^PAYABLE WITHIN$***"
}

function e_afterDueDate(){
  cat $electricityFILE | grep "^PAYABLE AFTER$***"
}

function e_lastDate(){
  echo Last Date : 
  cat $electricityFILE | grep "[0-9]" |
  head -2 |                             # Trick to access line number 
  awk 'END {print $(NF-2),$(NF-1),$NF}' # Trick to print last few words
}

function e_bmonth(){
  echo Billing Month : 
  cat $electricityFILE | grep "[0-9]" |
  head -2 |                        # Trick to access line number 
  awk 'END {print $(NF-10),$(NF-9)}'
}

function e_name(){
  echo NAME : 
  cat $electricityFILE | grep [A-Z] | 
  head -n 24 |
  tail -n -1 |
  awk '{print $1,$2}'
}

function e_ref(){
  echo Reference No.
  cat $electricityFILE | grep [A-Z] |
  head -n 14 |
  tail -n -1
}

clear
echo --------------------------- ELECTRICITY BILL ------------------
echo $(e_name)
echo $(e_ref)
echo $(e_bmonth)
echo $(e_cb)
echo $(e_afterDueDate)
echo $(e_lastDate)
echo ---------------------------------------------------------------
echo
echo
echo
echo
echo
echo --------------------------- GAS BILL --------------------------
echo $(name) 
echo ACCOUNT NUMBER : $(g_accountNumber)
echo Billing Month  : $(g_billingMonth)
echo CURRENT BILL   : Rs. $(g_currentBill) /-
echo ARREARS        : Rs. $(g_dues) /-
echo LATE BILL      : Rs. $(g_billAfterDueDate) /-
echo DUE DATE       : $(g_dueDate)
echo ----------------------------------------------------------------



#DELETE EVERY FILE IN TMP DIR
rm /tmp/gas.html  /tmp/e.txt /tmp/e.html # Delete After working
sleep 50000