API tools faq
paste
Guest User

Untitled

a guest
Jan 4th, 2025
40
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 7.57 KB | None | 0 0
raw download clone embed print report
  1. import re
  2. import xlsxwriter
  3. from datetime import datetime
  4. import numpy as np
  5. import time
  6. import matplotlib.pyplot as plt
  7. import os
  8.  
  9. def loop_statements(dir,reader_f,act_type,debug=0):
  10.     everything = []
  11.     now_and_then = round(time.time() * 1000)
  12.     count=0
  13.     for f in os.listdir(dir):
  14.         f = f.lower()
  15.         if f.endswith(".pdf"):
  16.             count+=1
  17.             if count >=5 and debug > 0:
  18.                 continue
  19.             y = f[0:4]
  20.             f = dir + f
  21.             everything.append(reader_f(f, debug, y))
  22.  
  23.     everything = filter_list(everything,act_type)
  24.     make_xlsx(everything, act_type+".xlsx")
  25.     print("took",round(time.time() * 1000)-now_and_then, "ms to parse",count,"files")
  26.  
  27. def filter_list(everything, act_type):
  28.     for i in range(len(everything)):
  29.         for j in range(len(everything[i])):
  30.             try:
  31.                 new_amt = float(everything[i][j][4])
  32.             except:
  33.                 new_amt = 0
  34.             if everything[i][j][3] == "NET" and new_amt == 120:
  35.                 everything[i][j][3] = "ANNUAL FEE"
  36.             if re.match(r".*(amz\*amazon|amz\*ware|amazon.ca\*|amazon.*downtown).*", everything[i][j][3], re.IGNORECASE) != None:
  37.                 everything[i][j][3] = "Amazon.ca"
  38.             if re.match(r".*(AMZN Mktp CA|Amazon \*Mark).*", everything[i][j][3], re.IGNORECASE) != None:
  39.                 everything[i][j][3] = "AMZN Mktp CA"
  40.             if re.match(r".*(AMZN Mktp US).*", everything[i][j][3], re.IGNORECASE) != None:
  41.                 everything[i][j][3] = "AMZN Mktp US"    
  42.             if re.match(r".*(audible).*", everything[i][j][3], re.IGNORECASE) != None:
  43.                 everything[i][j][3] = "Audible CA"
  44.             if re.match(r".*(MEC|Mountain Equipment).*", everything[i][j][3], re.IGNORECASE) != None:
  45.                 everything[i][j][3] = "MEC - Mountain Equipment"
  46.             if re.match(r".*(Steamgames|steam.*seattle).*", everything[i][j][3], re.IGNORECASE) != None:
  47.                 everything[i][j][3] = "Steam Games"
  48.             check_groc = re.match(r".*(foods|super a|IGA|Safeway|Buy-low|buy low|freson|nofrills|pc express|superstore|save on|no frills).*", everything[i][j][3], re.IGNORECASE)
  49.             check_ff = re.match(r".*(restaur|kura|pastry|red beard|pho a pho|mr mikes|tandoori|sushi|the shack|bakery|pizza|spicy gre|A&W|subway|dairy queen|wendys|taco de|tim horton|pizzeria|gus' pizza|panago|DQ Grill).*", everything[i][j][3], re.IGNORECASE)
  50.             check_gas = re.match(r".*(chv[0-9]{5}|chevron|mohawk|canco|gti pet|co-op|7-eleven|Shell|esso|husky|petrocan|macs|7 eleven|petro canada).*", everything[i][j][3], re.IGNORECASE)
  51.             check_int = re.match(r".*(Telus comm|tsi).*", everything[i][j][3], re.IGNORECASE)
  52.             check_ful = re.match(r".*(Shell easypay|shell ep).*", everything[i][j][3], re.IGNORECASE)
  53.             check_phn = re.match(r".*(fido mobile|freedom|koodo|virgin|public mob|telus mob).*", everything[i][j][3], re.IGNORECASE)
  54.             check_amz = re.match(r".*(audible|amazon|amzn).*", everything[i][j][3], re.IGNORECASE)
  55.             check_rent = re.match(r".*(cheque withdrawal).*", everything[i][j][3], re.IGNORECASE)
  56.             check_pp = re.match(r".*(paypal).*", everything[i][j][3], re.IGNORECASE)
  57.             check_pwr = re.match(r".*(BC HYDRO).*", everything[i][j][3], re.IGNORECASE)
  58.             check_pay = re.match(r".*(from canada|province of b\.c).*", everything[i][j][3], re.IGNORECASE)
  59.             check_inv2 = re.match(r".*(INTERAC e-Transfer).*", everything[i][j][3], re.IGNORECASE)            
  60.             check_med = re.match(r".*(dental|optometric|audio).*", everything[i][j][3], re.IGNORECASE)
  61.             if check_groc != None:
  62.                 l="grocery"
  63.             elif check_ff != None:
  64.                 l="fast food"
  65.             elif check_ful != None:
  66.                 l="fuel"
  67.             elif check_gas != None and new_amt < 20:
  68.                 l="gas station"
  69.             elif check_gas != None:
  70.                 l="fuel"
  71.             elif check_int != None:
  72.                 l="internet"
  73.             elif check_phn != None:
  74.                 l="cell phone"
  75.             elif check_amz != None:
  76.                 l="amazon"
  77.             elif check_pp != None:
  78.                 l="paypal"
  79.             elif check_pwr != None:
  80.                 l="power"
  81.             elif check_rent != None and new_amt > 470 and new_amt < 600:
  82.                 l="rent"
  83.             elif check_pay != None and new_amt > 1000:
  84.                 l="payroll"
  85.             elif check_pay != None and new_amt < 1000:
  86.                 l="expenses"
  87.             elif check_cc != None:
  88.                 l="credit cards"
  89.                 everything[i][j][4] = str(new_amt * -1)
  90.             elif check_inv2 != None and new_amt > 2800 and new_amt < 3000:
  91.                 l="investing"
  92.             elif act_type == "tngch":
  93.                 l="junk"
  94.             else:
  95.                 l="misc"
  96.             everything[i][j].append(l)
  97.             everything[i][j].append(act_type)
  98.     return everything
  99.    
  100. def make_xlsx(everything, fName): #list of all statements and filename of xlsx
  101.     wb = xlsxwriter.Workbook(fName)
  102.     ws = wb.add_worksheet("statements")
  103.     date_format = wb.add_format({'num_format': 'd mmm yyyy'})
  104.     ws.write(0,0,"year")
  105.     ws.write(0,1,"t_date")
  106.     ws.write(0,2,"p_date")
  107.     ws.write(0,3,"description")
  108.     ws.write(0,4,"amount")
  109.     ws.write(0,5,"label")
  110.     ws.write(0,6,"act type")
  111.     s_row = 1
  112.     s_col = 0
  113.     row=s_row
  114.     col=s_col
  115.     for s in range(0 ,len(everything)):
  116.         for t in range(0, len(everything[s])):
  117.             try:
  118.                 float(everything[s][t][4])
  119.             except Exception as e:
  120.                 print(e)
  121.                 continue
  122.             col=0
  123.             ws.write_number(row,col,int(everything[s][t][0]))
  124.  
  125.             try:
  126.                 if fName == "tngch.xlsx":
  127.                     dte=datetime.strptime(everything[s][t][1], '%d %b %Y').date()
  128.                 elif fName == "td.xlsx":
  129.                     dte=datetime.strptime(everything[s][t][1], '%b %d %Y').date()
  130.                 ws.write_datetime(row,col+1,dte,date_format)
  131.             except Exception as e:
  132.                 print(e)        
  133.                 ws.write(row,col+1,str(everything[s][t][1]))
  134.  
  135.             ws.write(row,col+2,str(everything[s][t][2]))
  136.             ws.write(row,col+3,str(everything[s][t][3]))
  137.             ws.write_number(row,col+4,float(everything[s][t][4]))        
  138.             ws.write(row,col+5,str(everything[s][t][5]))
  139.             ws.write(row,col+6,str(everything[s][t][6]))
  140.             row+=1
  141.         row+=1
  142.  
  143.     ws.set_column(0,0,4.3)
  144.     ws.set_column(1,1,11.45)
  145.     ws.set_column(2,2,11.45)
  146.     ws.set_column(3,3,71.5)
  147.     ws.set_column(4,4,9.7)    
  148.     wb.close()
  149.  
  150.  
  151. def show_image(item, title=""):
  152.     """Display a pixmap.
  153.  
  154.    Just to display Pixmap image of "item" - ignore the man behind the curtain.
  155.  
  156.    Args:
  157.        item: any PyMuPDF object having a "get_pixmap" method.
  158.        title: a string to be used as image title
  159.  
  160.    Generates an RGB Pixmap from item using a constant DPI and using matplotlib
  161.    to show it inline of the notebook.
  162.    """
  163.     DPI = 220  # use this resolution
  164.     pix = item.get_pixmap(dpi=DPI)
  165.     img = np.ndarray([pix.h, pix.w, 3], dtype=np.uint8, buffer=pix.samples_mv)
  166.     plt.figure(dpi=DPI)  # set the figure's DPI
  167.     plt.title(title)  # set title of image
  168.     _ = plt.imshow(img, extent=(0, pix.w * 72 / DPI, pix.h * 72 / DPI, 0))
  169.  
  170. def line_by_line(stuff):
  171.     count = 0
  172.     for line in stuff:
  173.         print(count, line)
  174.         count+=1
Advertisement
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!