excel_to_csv.py

#!/usr/bin/env python
import cStringIO
import codecs
import csv
import sys
import xlrd

# Taken verbatim from https://docs.python.org/2/library/csv.html#examples
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)

if __name__ == "__main__":
    if len(sys.argv) not in (2, 3):
        print "usage:", sys.argv[0], "file.xls [sheet_name]"

    book = xlrd.open_workbook(sys.argv[1])
    if book.nsheets != 1 and len(sys.argv) == 2:
        print "Sheet name required:", ", ".join(book.sheet_names())
        sys.exit(1)

    if book.nsheets == 1:
        sheet = book.sheet_by_index(0)
    else:
        sheet = book.sheet_by_name(sys.argv[2])

    output =  UnicodeWriter(sys.stdout)
    for i in range(sheet.nrows):
        output.writerow([unicode(x) for x in sheet.row_values(i)])