Python script to generate a JGAAP-Compatible Corpus CSV from a CSV of authors and their text.

split.py

# Example Usage: python split.py yourInputCSVHere.csv
import csv, sys
incsv = open(sys.argv[1], 'r')
outcsv = open('new-' + sys.argv[1], 'w')
counter = 1
csvreader = csv.reader(incsv, delimiter=',', quotechar='"')
for row in csvreader:
	outcsv.write(str(row[0]) + ',file' + str(counter) + '.txt,file' + str(counter) + '.txt by ' + str(row[0]) + '\n')
	doc = open('file' + str(counter) + '.txt', 'w')
	doc.write(row[1])
	doc.close()
	counter += 1