A simple script to parse Tmobile's monthly bill and extract billing of individual number line into an xlsx file.

Tmobile_bill_parser.py

'''
Bo Wen
v1: Dec 25, 2019
v2: Nov 21, 2020
v3: Jun, 2021 - updated for tmobile's new summary pdf layout
v4: Dec 2022 - check phone number exists in the summary before processing to avoid error

require:
Python3
pipenv install pdfplumber
pipenv install xlsxwriter
'''

import xlsxwriter
import pdfplumber
import re
import argparse

# the final xlsx report will follow the number order and list bill from left to right
phone_list=['(123)\xa0456-7890',
            '(123)\xa0456-7891',
            '(123)\xa0456-7892',
           ]
# helper functions:
def search_next(lis, word):
    return next((i for i,v in enumerate(lis) if v.startswith(word)), None)

def parse_dollar(word):
    if word == '-':
        return 0
    else:
        v=word.split('$')[-1]
        if ')' in v:
            return -float(v.split(')')[0])
        else:
            return float(v)

# main function:
def Parse_file(filename, phone_list):
    alltext=''
    parsed_dict={}
    ind_dict={}

    if '.pdf' in filename:
        filename = filename.split('.pdf')[0]

    with pdfplumber.open(filename+'.pdf') as pdf:
        for p in pdf.pages:
            temp = p.extract_text(x_tolerance=3, y_tolerance=3)
            if temp is not None:
                alltext=alltext+temp
    lines=re.split(r'\s{2,}|\n', alltext)

    workbook = xlsxwriter.Workbook(filename+'.xlsx')
    worksheet = workbook.add_worksheet()
    
    parsed_dict['Bill period']=lines[1].split(' XXXXXXXXX',1)[0]  # replace "XXXXXXXXX" with your actual tmobile account number, near top right of the pdf
    parsed_dict['Tmobile billed amount']=parse_dollar(lines[search_next(lines, "Here's your bill")-1].split()[0])
    parsed_dict['plan charge']=parse_dollar(lines[search_next(lines, "Account")].split("$")[-1])
    worksheet.write('A1', 'Bill period = '+parsed_dict['Bill period'])
    worksheet.write('B1', parsed_dict['Tmobile billed amount'])
    worksheet.write('A2', 'account + tax (sevice for next month)')
    worksheet.write('C2', parsed_dict['plan charge'])
    
    row=3
    col=0

    pos_ = search_next(lines, "THIS BILL SUMMARY")
    pos_end = search_next(lines, "DETAILED CHARGES")
    
    for phone in phone_list:
        if any(phone in s for s in lines[pos_:pos_end]):
            print(f"processing {phone}")
            phone_line = lines[pos_ + search_next(lines[pos_: pos_ + 20], phone)]
            phone_items = phone_line.split('$', 1)[1].split()
            plans_charge = parse_dollar(phone_items[0])
            eq_charge = parse_dollar(phone_items[1])
            service_charge = parse_dollar(phone_items[2])
            one_time_charge = parse_dollar(phone_items[3])
            if plans_charge > 10:
                plans_charge = plans_charge - 10
            worksheet.write(row, col, plans_charge)
            worksheet.write(row + 1, col, eq_charge)
            worksheet.write(row + 2, col, service_charge)
            worksheet.write(row + 3, col, one_time_charge)

            col = col + 1
        else:
            print(f"{phone} doesn't exist, skip")
        
    workbook.close()


if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='tmobile bill parser')
    parser.add_argument('-f', '--file', required=True, help='bill pdf file')
   # parser.add_argument('-p', '--phone_list', required=False, help='phone number list json')

    args = parser.parse_args()
    Parse_file(args.file, phone_list)