From password-protected Excel file to pandas DataFrame

Question

I can open a password-protected Excel file with this:

import sys
import win32com.client
xlApp = win32com.client.Dispatch(\"Excel.Application\")
print \"Excel         


        

Answer 1

Based on the suggestion provided by @ikeoddy, this should put the pieces together:

How to open a password protected excel file using python?

# Import modules
import pandas as pd
import win32com.client
import os
import getpass

# Name file variables
file_path = r'your_file_path'
file_name = r'your_file_name.extension'

full_name = os.path.join(file_path, file_name)
# print(full_name)

Getting command-line password input in Python

# You are prompted to provide the password to open the file
xl_app = win32com.client.Dispatch('Excel.Application')
pwd = getpass.getpass('Enter file password: ')

Workbooks.Open Method (Excel)

xl_wb = xl_app.Workbooks.Open(full_name, False, True, None, pwd)
xl_app.Visible = False
xl_sh = xl_wb.Worksheets('your_sheet_name')

# Get last_row
row_num = 0
cell_val = ''
while cell_val != None:
    row_num += 1
    cell_val = xl_sh.Cells(row_num, 1).Value
    # print(row_num, '|', cell_val, type(cell_val))
last_row = row_num - 1
# print(last_row)

# Get last_column
col_num = 0
cell_val = ''
while cell_val != None:
    col_num += 1
    cell_val = xl_sh.Cells(1, col_num).Value
    # print(col_num, '|', cell_val, type(cell_val))
last_col = col_num - 1
# print(last_col)

ikeoddy's answer:

content = xl_sh.Range(xl_sh.Cells(1, 1), xl_sh.Cells(last_row, last_col)).Value
# list(content)
df = pd.DataFrame(list(content[1:]), columns=content[0])
df.head()

python win32 COM closing excel workbook

xl_wb.Close(False)