splits file returns the files splitted and the number of files(current_piece)

csv_split.py

import csv
import os
import pprint
import datetime
#splits file returns the files splitted and the number of files(current_piece)

import csv
def splits(filehandler, delimiter=',', row_limit=100000, 
    output_name_template='output_%s.csv', output_path='.', keep_headers=True):
    """
    Splits a CSV file into multiple pieces.


    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.

    """
    created_files = []
    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)
        print current_out_path
        created_files.append(current_out_path)
    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)
            print current_out_path
            created_files.append(current_out_path)
            if keep_headers:
                current_out_writer.writerow(headers)
        current_out_writer.writerow(row)
    return created_files,current_piece

'''
This module is a simple utility for working with a single csv file, 
or muttiple csv files in a directory.
You can instantiate a csv file by simply doing 
>>>import csvgoo2
>>> c = CsvFile('sample.csv')    
and then grab the data by doing 
>>>c.fill()

The CsFile object only grabs the data when you explicitly call the fill() method 
in order to save memory.  You can also use the empty() method to clear data once 
its been filled
'''


#CsvFile USAGE
#c = CsvFile('sample.csv')
#print c.columns
#c.fill()


class CsvFile(object):
    def __init__(self, name):
        self.name = name
        self.data = []
        self.columns = []
    def __str__(self):
        return self.name

    def empty(self):
        self.data = []

    def fill(self):
        self.data = [x for x in csv.DictReader(open(self.name, 'rU'))]
        self.columns = self.data[0].keys()


''' 
The Repo class is similar to the csv file object 
but lets you gather all csv files in a directory at once
the get() method just instantiates a CsvFile object. 
'''

class Repo(object):
    def __init__(self, pathdir = '.', fillall = False):
        if not fillall:
            self.items = [CsvFile(f).empty() for f in os.listdir(pathdir) if os.path.isfile(f) and f.lower().endswith('.csv')]
        else:
            self.items = [CsvFile(f) for f in os.listdir(pathdir) if os.path.isfile(f) and f.lower().endswith('.csv')]
    def fill_all(self):
        self.items = [x.fill for x in self.items]
    def get(self, filea):
        return CsvFile(str(filea))