XLS

Python XLS parser using standard modules.

Found on stackoverflow. It is announced as very very basic but it works very well.

This routine returns a list of dicts like { <columname> : <cellvalue> [, .. ] }

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'):                                 # <v>84</v>
            value = el.text
        if el.tag.endswith('}c'):                                 # <c r="A3" t="s"><v>84</v></c>
            if el.attrib.get('t') == 's':
                value = strings[int(value)]
            letter = el.attrib['r']                               # AZ22
            while letter[-1].isdigit():
                letter = letter[:-1]
            row[letter] = value
            value = ''
        if el.tag.endswith('}row'):
            rows.append(row)
            row = {}
    return rows