xlsx2csv.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-


import argparse
import csv
import sys
import codecs
import pprint
from openpyxl import load_workbook
import cStringIO

class UnicodeWriter:
    """
    A CSV writer which will write rows to CSV file "f",
    which is encoded in the given encoding.
    """

    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
        # Redirect output to a queue
        self.queue = cStringIO.StringIO()
        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
        self.stream = f
        self.encoder = codecs.getincrementalencoder(encoding)()

    def writerow(self, row):
        self.writer.writerow([s.encode("utf-8") for s in row])
        # Fetch UTF-8 output from the queue ...
        data = self.queue.getvalue()
        data = data.decode("utf-8")
        # ... and reencode it into the target encoding
        data = self.encoder.encode(data)
        # write to the target stream
        self.stream.write(data)
        # empty queue
        self.queue.truncate(0)

    def writerows(self, rows):
        for row in rows:
            self.writerow(row)

pp = pprint.PrettyPrinter(indent=4)

parser = argparse.ArgumentParser()
parser.add_argument("input_file")
args = parser.parse_args()

if not ".xlsx" in args.input_file:
    sys.stderr.write("Error: File does not have the ending \".xlsx\".\n")
    sys.exit(2)

input_fh = open(args.input_file)
wb = load_workbook(filename = args.input_file)
ws = wb.active
csvFilename = args.input_file.replace(".xlsx", ".csv")
csvFile = open(csvFilename, "w")
csvFile.write(codecs.BOM_UTF8)

csvWriter = UnicodeWriter(csvFile)

for row in enumerate(ws.rows):
    cells = []
    rowNumber = row[0]
    for col in enumerate(row[1]):
        colNumber = col[0]
        cell = col[1]
        value = unicode(cell.value)
        cells.append(value)
    csvWriter.writerow(cells)