A Python CSV splitter

csv_splitter.py

import os

def split(filehandler, delimiter=',', row_limit=10000, 
    output_name_template='output_%s.csv', output_path='.', keep_headers=True):
    """
    Splits a CSV file into multiple pieces.
    
    A quick bastardization of the Python CSV library.

    Arguments:

        `row_limit`: The number of rows you want in each output file. 10,000 by default.
        `output_name_template`: A %s-style template for the numbered output files.
        `output_path`: Where to stick the output files.
        `keep_headers`: Whether or not to print the headers in each output file.

    Example usage:
    
        >> from toolbox import csv_splitter;
        >> csv_splitter.split(open('/home/ben/input.csv', 'r'));
    
    """
    import csv
    reader = csv.reader(filehandler, delimiter=delimiter)
    current_piece = 1
    current_out_path = os.path.join(
         output_path,
         output_name_template  % current_piece
    )
    current_out_writer = csv.writer(open(current_out_path, 'w'), delimiter=delimiter)
    current_limit = row_limit
    if keep_headers:
        headers = reader.next()
        current_out_writer.writerow(headers)
    for i, row in enumerate(reader):
        if i + 1 > current_limit:
            current_piece += 1
            current_limit = row_limit * current_piece
            current_out_path = os.path.join(
               output_path,
               output_name_template  % current_piece
            )
            current_out_writer = csv.writer(open(current_out_path, 'w'), delimiter=delimiter)
            if keep_headers:
                current_out_writer.writerow(headers)
        current_out_writer.writerow(row)

Based on this script, I added one more filter criteria (split based on unique row value of certain columns)

https://github.com/airbob/personal-backup/blob/master/scripts/csvsplit.py

It creates an empty line for each record in the csv file.
Anyone know why ?

To avoid empty lines, you can open the file in binary mode (tested on python 2.7) 'wb' instead of 'w'

Based on this script, I added one more filter criteria (split based on unique row value of certain columns)

https://github.com/airbob/personal-backup/blob/master/scripts/csvsplit.py

Link has expired