xls2tsv

#!/usr/bin/env python2.7
# adapted from http://stackoverflow.com/questions/9884353/xls-to-csv-convertor
import xlrd
# import csv
import sys

warning_count=0
warning_max = 20
def warning(s):
  global warning_count
  warning_count += 1
  if warning_count > warning_max: return
  print>>sys.stderr, "WARNING: %s" % s

def cell_text_clean(text):
  s = text
  if "\t" in s: warning("Clobbering embedded tab")
  if "\n" in s: warning("Clobbering embedded newline")
  if "\r" in s: warning("Clobbering embedded carriage return")
  s = s.replace("\t"," ").replace("\n"," ").replace("\r"," ")
  return s

def tsv_from_excel(excel_file, sheetnum):
    workbook = xlrd.open_workbook(excel_file)
    all_worksheets = workbook.sheet_names()
    worksheet_name = all_worksheets[ sheetnum-1 ]
    worksheet = workbook.sheet_by_name(worksheet_name)
    # wr = csv.writer(your_csv_file, quoting=csv.QUOTE_ALL)

    for rownum in xrange(worksheet.nrows):
        row = [unicode(entry).encode("utf-8") for entry in worksheet.row_values(rownum)]
        row = [cell_text_clean(x) for x in row]
        print '\t'.join(row)

def usage():
    print>>sys.stderr, """
USAGE:
xls2tsv filename.xls [sheetnum]
sheetnum >= 1, defaults to 1
""".strip()
    sys.exit(1)

def main(args):
    if len(args)<2: usage()
    if len(args)>4: usage()
    excel_file = args[1]
    sheet_num = int(args[2]) if len(args)>2 else 1
    if sheet_num < 1:
        assert False, "need sheet number to be >= 1"
    tsv_from_excel(excel_file, sheet_num)

if __name__ == "__main__":
    main(sys.argv)