[python] Reading/parsing Excel (xls) files with Python

For xlsx I like the solution posted earlier as https://web.archive.org/web/20180216070531/https://stackoverflow.com/questions/4371163/reading-xlsx-files-using-python. I uses modules from the standard library only.

def xlsx(fname):
    import zipfile
    from xml.etree.ElementTree import iterparse
    z = zipfile.ZipFile(fname)
    strings = [el.text for e, el in iterparse(z.open('xl/sharedStrings.xml')) if el.tag.endswith('}t')]
    rows = []
    row = {}
    value = ''
    for e, el in iterparse(z.open('xl/worksheets/sheet1.xml')):
        if el.tag.endswith('}v'):  # Example: <v>84</v>                            
            value = el.text
        if el.tag.endswith('}c'):  # Example: <c r="A3" t="s"><v>84</v></c>                                 
            if el.attrib.get('t') == 's':
                value = strings[int(value)]
            letter = el.attrib['r']  # Example: AZ22                         
            while letter[-1].isdigit():
                letter = letter[:-1]
            row[letter] = value
            value = ''
        if el.tag.endswith('}row'):
            rows.append(row)
            row = {}
    return rows

Improvements added are fetching content by sheet name, using re to get the column and checking if sharedstrings are used.

def xlsx(fname,sheet):
    import zipfile
    from xml.etree.ElementTree import iterparse
    import re
    z = zipfile.ZipFile(fname)
    if 'xl/sharedStrings.xml' in z.namelist():
        # Get shared strings
        strings = [element.text for event, element
                   in iterparse(z.open('xl/sharedStrings.xml')) 
                   if element.tag.endswith('}t')]
    sheetdict = { element.attrib['name']:element.attrib['sheetId'] for event,element in iterparse(z.open('xl/workbook.xml'))
                                      if element.tag.endswith('}sheet') }
    rows = []
    row = {}
    value = ''

    if sheet in sheets:
    sheetfile = 'xl/worksheets/sheet'+sheets[sheet]+'.xml'
    #print(sheet,sheetfile)
    for event, element in iterparse(z.open(sheetfile)):
        # get value or index to shared strings
        if element.tag.endswith('}v') or element.tag.endswith('}t'):
            value = element.text
        # If value is a shared string, use value as an index
        if element.tag.endswith('}c'):
            if element.attrib.get('t') == 's':
                value = strings[int(value)]
            # split the row/col information so that the row leter(s) can be separate
            letter = re.sub('\d','',element.attrib['r'])
            row[letter] = value
            value = ''
        if element.tag.endswith('}row'):
            rows.append(row)
            row = {}

    return rows