Created
June 26, 2015 13:48
-
-
Save robsmith1776/efac554de78203ed92fc to your computer and use it in GitHub Desktop.
chunk
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
"""splits a large text file into smaller ones, based on line count | |
Original is left unmodified. | |
Resulting text files are stored in the same directory as the original file. | |
Useful for breaking up text-based logs or blocks of login credentials. | |
""" | |
import os | |
def split_file(filepath, lines_per_file=100): | |
"""splits file at `filepath` into sub-files of length `lines_per_file` | |
""" | |
lpf = lines_per_file | |
path, filename = os.path.split(filepath) | |
with open(filepath, 'r') as r: | |
name, ext = os.path.splitext(filename) | |
try: | |
w = open(os.path.join(path, '{}_{}{}'.format(name, 0, ext)), 'w') | |
for i, line in enumerate(r): | |
if not i % lpf: | |
#possible enhancement: don't check modulo lpf on each pass | |
#keep a counter variable, and reset on each checkpoint lpf. | |
w.close() | |
filename = os.path.join(path, | |
'{}_{}{}'.format(name, i, ext)) | |
w = open(filename, 'w') | |
w.write(line) | |
finally: | |
w.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment