docx2csv.py 文件源码

def extract(filename, format='csv', sizefilter=0, singlefile=False):
    tables = extract_docx_table(filename)
    name = filename.rsplit('.', 1)[0]
    format = format.lower()
    n = 0
    lfilter = int(sizefilter)
    if singlefile:
        workbook = xlwt.Workbook()
        for t in tables:
            if lfilter >= len(t):
                print 'Table length %d instead of %d. Skipped' % (len(t), lfilter)
                continue
            n += 1
            sheet = workbook.add_sheet(str(n))
            rn = 0
            for row in t:
                cn = 0
                for c in row:
                    sheet.write(rn, cn, c.decode('utf8'))
                    cn += 1
                rn += 1
        destname = name + '.%s' % (format)
        workbook.save(destname)
        print destname, 'saved'
    else:
        for t in tables:
            if lfilter >= len(t):
                print 'Table length %d instead of %d. Skipped' % (len(t), lfilter)
                continue
            n += 1
            destname = name + '_%d.%s' % (n, format)
            store_table(t, destname, format)
            print destname, 'saved'