Retain headers in outfile with python

Question

How do I create headers or keep the first line in my outfiles? Everything else is working great I would just like to keep my first line or "header" in the outfiles.

#!/usr/bin/env python3
import binascii
import csv
import os.path
import sys
from tkinter.filedialog import askopenfilename, askdirectory
from tkinter.simpledialog import askinteger

def split_csv_file(f, dst_dir, keyfunc):
    csv_reader = csv.reader(f)
    csv_writers = {}
    for row in csv_reader:
        k = keyfunc(row)
        if k not in csv_writers:
            csv_writers[k] = csv.writer(open(os.path.join(dst_dir, k),
                                             mode='w', newline=''))
        csv_writers[k].writerow(row)

def get_args_from_cli():
    input_filename = sys.argv[1]
    column = int(sys.argv[2])
    dst_dir = sys.argv[3]
    return (input_filename, column, dst_dir)

def get_args_from_gui():
    input_filename = askopenfilename(
        filetypes=(('CSV', '.csv'),),
        title='Select CSV Input File')
    column = askinteger('Choose Table Column', 'Table column')
    dst_dir = askdirectory(title='Select Destination Directory')
    return (input_filename, column, dst_dir)

if __name__ == '__main__':
    if len(sys.argv) == 1:
        input_filename, column, dst_dir = get_args_from_gui()
    elif len(sys.argv) == 4:
        input_filename, column, dst_dir = get_args_from_cli()
    else:
        raise Exception("Invalid number of arguments")
    with open(input_filename, mode='r', newline='') as f:
        split_csv_file(f, dst_dir, lambda r: r[column-1]+'.csv')
        # if the column has funky values resulting in invalid filenames
        # replace the line from above with:
        # split_csv_file(f, dst_dir, lambda r: binascii.b2a_hex(r[column-1].encode('utf-8')).decode('utf-8')+'.csv')

Here is an example of the begining CSV

"<option value="""">Choose Year</option>",ParentID
"<option value=""Civic1990"">1990</option>",Civic
"<option value=""CRX1990"">1990</option>",CRX
"<option value=""Prelude1990"">1990</option>",Prelude
"<option value=""Accord1990"">1990</option>",Accord
"<option value=""Prelude1991"">1991</option>",Prelude
"<option value=""Civic1991"">1991</option>",Civic
"<option value=""CRX1991"">1991</option>",CRX
"<option value=""Accord1991"">1991</option>",Accord
"<option value=""Prelude1992"">1992</option>",Prelude
"<option value=""Civic1992"">1992</option>",Civic
"<option value=""Accord1992"">1992</option>",Accord
"<option value=""Prelude1993"">1993</option>",Prelude
"<option value=""Civic1993"">1993</option>",Civic
"<option value=""CivicdelSol1993"">1993</option>",CivicdelSol
"<option value=""Accord1993"">1993</option>",Accord
"<option value=""Passport1994"">1994</option>",Passport

OutFile:

<option value="">Choose Year</option>
<option value="Civic1990">1990</option>
<option value="Civic1991">1991</option>
<option value="Civic1992">1992</option>
<option value="Civic1993">1993</option>
<option value="Civic1994">1994</option>
<option value="Civic1995">1995</option>
<option value="Civic1996">1996</option>
<option value="Civic1997">1997</option>
<option value="Civic1998">1998</option

OutFile:

<option value="">Choose Year</option>
<option value="Accord1990">1990</option>
<option value="Accord1991">1991</option>
<option value="Accord1992">1992</option>
<option value="Accord1993">1993</option>
<option value="Accord1994">1994</option>
<option value="Accord1995">1995</option>
<option value="Accord1996">1996</option>
<option value="Accord1997">1997</option>
<option value="Accord1998">1998</option>

Is this really the smallest program that demonstrates your problem? — thebjorn, Feb 04 '16 at 21:16
Check this post:http://stackoverflow.com/questions/20347766/pythonically-add-header-to-a-csv-file — Виталий Стоянов, Feb 04 '16 at 21:20
Your code writes both columns but your example shows one column. That's a bit confusing. Am I right in assuming that `"",ParentID` is the header line and that the shown example outputs are what you want, not what you are currently generating? — tdelaney, Feb 04 '16 at 21:35

score 0 · Accepted Answer · answered Feb 04 '16 at 21:38

If I understand the problem properly, you want to take the header from a single csv file you are reading and make it the header for all of the csv files you are writing. Just grab the header and apply it to each file you write.

def split_csv_file(f, dst_dir, keyfunc):
    csv_reader = csv.reader(f)
    header = next(csv_reader)
    csv_writers = {}
    for row in csv_reader:
        k = keyfunc(row)
        if k not in csv_writers:
            writer = csv.writer(open(os.path.join(dst_dir, k),
                                             mode='w', newline=''))
            writer.writerow(header)
            csv_writers[k] = writer
        csv_writers[k].writerow(row)

Retain headers in outfile with python

1 Answers1