Splitting one csv into multiple files

Question

I have a csv file of about 5000 rows in python i want to split it into five files.

I wrote a code for it but it is not working

import codecs import csv NO_OF_LINES_PER_FILE = 1000 def again(count_file_header,count):     f3 = open('write_'+count_file_header+'.csv', 'at')     with open('import_1458922827.csv', 'rb') as csvfile:         candidate_info_reader = csv.reader(csvfile, delimiter=',', quoting=csv.QUOTE_ALL)         co = 0               for row in candidate_info_reader:             co = co + 1             count  = count + 1             if count <= count:                 pass             elif count >= NO_OF_LINES_PER_FILE:                 count_file_header = count + NO_OF_LINES_PER_FILE                 again(count_file_header,count)             else:                 writer = csv.writer(f3,delimiter = ',', lineterminator='\n',quoting=csv.QUOTE_ALL)                 writer.writerow(row)  def read_write():     f3 = open('write_'+NO_OF_LINES_PER_FILE+'.csv', 'at')     with open('import_1458922827.csv', 'rb') as csvfile:           candidate_info_reader = csv.reader(csvfile, delimiter=',', quoting=csv.QUOTE_ALL)          count = 0                for row in candidate_info_reader:             count  = count + 1             if count >= NO_OF_LINES_PER_FILE:                 count_file_header = count + NO_OF_LINES_PER_FILE                 again(count_file_header,count)             else:                 writer = csv.writer(f3,delimiter = ',', lineterminator='\n',quoting=csv.QUOTE_ALL)                 writer.writerow(row)  read_write() 

The above code creates many fileswith empty content.

How to split one files into five csv files?

Answer 1

In Python

Use readlines() and writelines() to do that, here is an example:

>>> csvfile = open('import_1458922827.csv', 'r').readlines() >>> filename = 1 >>> for i in range(len(csvfile)): ...     if i % 1000 == 0: ...         open(str(filename) + '.csv', 'w+').writelines(csvfile[i:i+1000]) ...         filename += 1 

the output file names will be numbered 1.csv, 2.csv, ... etc.

From terminal

FYI, you can do this from the command line using split as follows:

$ split -l 1000 import_1458922827.csv 

Answer 2

I suggest you not inventing a wheel. There is existing solution. Source here

import os   def split(filehandler, delimiter=',', row_limit=1000,           output_name_template='output_%s.csv', output_path='.', keep_headers=True):     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) 

Use it like:

split(open('/your/pat/input.csv', 'r'));