Remove Strikeouts from Excel in Python

removestrikeouts.py

# given excel file removes strikeout
# Emanuele Ruffaldi MMI 2025
# requires openpyxl
# Tested with 3.10.12 and openpyxl 3.1.4
#
import sys
from openpyxl import load_workbook
from openpyxl.styles import Font
from openpyxl.cell.rich_text import Text, CellRichText
import shutil

def remove_strikeout_text(wb):
    """Removes strikeout from all sheets. Return true if any found"""
    changed = False
    for sheet in wb.worksheets:
        for row in sheet.iter_rows():
            for cell in row:
                cellstrike = cell.font and cell.font.strike
                if isinstance(cell.value, CellRichText):
                    l = list(cell.value) # .as_list() will return str
                    if cellstrike:
                        # remove all the str and preserve the correct TextBlocks
                        nl = [t for t in l if not isinstance(t,str) and (not t.font or not t.font.strike)]
                    else:
                        nl = [t for t in l if isinstance(t,str) or not t.font or not t.font.strike]
                        
                    if len(nl) != len(l):
                        # Changed to: empty, simple string, CellRichText
                        if len(nl) == 0:
                            cell.value = ""
                        elif all((isinstance(t,str) for t in nl)):
                            cell.value = "".join(nl)
                        else:
                            cell.value = CellRichText(nl)
                        changed = True
                elif cell.value and cellstrike:
                    # Make it empty string for string, None for other types
                    if isinstance(cell.value,str):
                        cell.value = ""
                    else:
                        cell.value = None
                    changed = True                    
                # remove strike from font anyway
                if cellstrike:
                    cell.font = Font(**{**cell.font.__dict__, "strike": False})
                    changed = True
    return changed

def main():
    if len(sys.argv) == 1:
        print("Expected: inputfile [outputfile]",file=sys.stderr)
    else:
        infile = sys.argv[1]
        outfile = sys.argv[1]+".cleaned.xlsx" if len(sys.argv) < 3 else sys.argv[2]
        wb = load_workbook(infile,rich_text=True)    
        if remove_strikeout_text(wb):
            wb.save(outfile)
        else:
            #copy2 does full metadata
            print("Full copy no strike",file=sys.stderr)
            shutil.copy2(infile,outfile)
            
if __name__ == "__main__":
    main()