"""Dump rows of an .xlsx (stdlib only) as tab-separated text. Usage: xlsx_dump.py file.xlsx""" import sys, zipfile, re import xml.etree.ElementTree as ET NS = {"m": "http://schemas.openxmlformats.org/spreadsheetml/2006/main"} def main(path): z = zipfile.ZipFile(path) shared = [] if "xl/sharedStrings.xml" in z.namelist(): root = ET.fromstring(z.read("xl/sharedStrings.xml")) for si in root.findall("m:si", NS): shared.append("".join(t.text or "" for t in si.iter("{%s}t" % NS["m"]))) wb = ET.fromstring(z.read("xl/workbook.xml")) names = [s.get("name") for s in wb.find("m:sheets", NS)] sheets = sorted(n for n in z.namelist() if re.match(r"xl/worksheets/sheet\d+\.xml", n)) for i, sh in enumerate(sorted(sheets, key=lambda s: int(re.findall(r"\d+", s)[-1]))): print("#### SHEET", names[i] if i < len(names) else sh) root = ET.fromstring(z.read(sh)) for row in root.iter("{%s}row" % NS["m"]): vals = [] for c in row.findall("m:c", NS): v = c.find("m:v", NS) t = c.get("t") if t == "s" and v is not None: vals.append(shared[int(v.text)]) elif t == "inlineStr": vals.append("".join(x.text or "" for x in c.iter("{%s}t" % NS["m"]))) else: vals.append(v.text if v is not None else "") print("\t".join(x.replace("\n", " ") for x in vals)) if __name__ == "__main__": main(sys.argv[1])