# Lector mínimo de XLSX (zipfile + ElementTree): hojas → filas de celdas (texto o número). Uso: python3 -I xlsx.py fichero [hoja] import sys, zipfile, re import xml.etree.ElementTree as ET NS = {'m': 'http://schemas.openxmlformats.org/spreadsheetml/2006/main', 'r': 'http://schemas.openxmlformats.org/officeDocument/2006/relationships'} def col(ref): n = 0 for ch in re.match(r'[A-Z]+', ref).group(0): n = n * 26 + ord(ch) - 64 return n - 1 def leer(path): z = zipfile.ZipFile(path) ss = [] if 'xl/sharedStrings.xml' in z.namelist(): for si in ET.fromstring(z.read('xl/sharedStrings.xml')).findall('m:si', NS): ss.append(''.join(t.text or '' for t in si.iter('{%s}t' % NS['m']))) wb = ET.fromstring(z.read('xl/workbook.xml')) rels = ET.fromstring(z.read('xl/_rels/workbook.xml.rels')) rid = {r.get('Id'): r.get('Target') for r in rels} hojas = {} for s in wb.find('m:sheets', NS): tgt = rid[s.get('{%s}id' % NS['r'])] tgt = tgt if tgt.startswith('xl/') else 'xl/' + tgt.lstrip('/') filas = [] for row in ET.fromstring(z.read(tgt)).iter('{%s}row' % NS['m']): f = {} for c in row.findall('m:c', NS): v = c.find('m:v', NS); t = c.get('t') if v is None: is_ = c.find('m:is', NS) val = ''.join(x.text or '' for x in is_.iter('{%s}t' % NS['m'])) if is_ is not None else None else: val = ss[int(v.text)] if t == 's' else (v.text if t in ('str', 'inlineStr') else float(v.text)) f[col(c.get('r'))] = val filas.append([f.get(i) for i in range(max(f) + 1)] if f else []) hojas[s.get('name')] = filas return hojas if __name__ == '__main__': h = leer(sys.argv[1]) if len(sys.argv) > 2: for r in h[sys.argv[2]][:80]: print(r) else: for k, v in h.items(): print(k, len(v), v[:3])