Read Merged Cells in Excel With Python

Read merged cells in Excel with Python

I just tried this and it seems to work for your sample data:

all_data = []
excel = xlrd.open_workbook(excel_dir+ excel_file)
sheet_0 = excel.sheet_by_index(0) # Open the first tab

prev_row = [None for i in range(sheet_0.ncols)]
for row_index in range(sheet_0.nrows):
    row= []
    for col_index in range(sheet_0.ncols):
        value = sheet_0.cell(rowx=row_index,colx=col_index).value
        if len(value) == 0:
            value = prev_row[col_index]
        row.append(value)
    prev_row = row
    all_data.append(row)

returning

[['2', '0', '30'], ['2', '1', '20'], ['2', '5', '52']]

It keeps track of the values from the previous row and uses them if the corresponding value from the current row is empty.

Note that the above code does not check if a given cell is actually part of a merged set of cells, so it could possibly duplicate previous values in cases where the cell should really be empty. Still, it might be of some help.

Additional information:

I subsequently found a documentation page that talks about a merged_cells attribute that one can use to determine the cells that are included in various ranges of merged cells. The documentation says that it is "New in version 0.6.1", but when i tried to use it with xlrd-0.9.3 as installed by pip I got the error

NotImplementedError: formatting_info=True not yet implemented

I'm not particularly inclined to start chasing down different versions of xlrd to test the merged_cells feature, but perhaps you might be interested in doing so if the above code is insufficient for your needs and you encounter the same error that I did with formatting_info=True.

How to read merged cells in python using openpyxl?

I amend my code and it's work.

import openpyxl
from openpyxl.utils import range_boundaries
wb = openpyxl.load_workbook('book1.xlsx')
sheet = wb.get_sheet_by_name('info')
all_data=[]
for row_index in range(1,sheet.max_row+1):
    row=[]
    for col_index in range(1,sheet.max_column+1):
        vals = sheet.cell(row_index,col_index).value
        if vals == None:
            for crange in sheet.merged_cells:
                clo,rlo,chi,rhi = crange.bounds
                top_value = sheet.cell(rlo,clo).value
                if rlo<=row_index and row_index<=rhi and clo<=col_index and col_index<=chi:
                vals = top_value
                    print(vals)
                    break
    row.append(vals)
all_data.append(row)
print(all_data)
for row in all_data:
    sheet.append(row)
wb.save('bbbb.xlsx')

Pandas: Parse Excel spreadsheet with merged cells and blank values

Something like this should work assuming you know the starting row of your excel file (or come up with a better way to check that)

import pandas as pd
import numpy as np
import openpyxl
def test():
    filepath = "C:\\Users\\me\\Desktop\\SO nonsense\\PandasMergeCellTest.xlsx"
    df = pd.read_excel(filepath)
    wb = openpyxl.load_workbook(filepath)
    sheet = wb["Sheet1"]
    df["Row"] = np.arange(len(df)) + 2 #My headers were row 1 so adding 2 to get the row numbers
    df["Merged"] = df.apply(lambda x: checkMerged(x, sheet), axis=1)
    df["Day"] = np.where(df["Merged"] == True, df["Day"].ffill(), np.nan)
    df = df.drop(["Row", "Merged"], 1)
    print(df)

def checkMerged(x, sheet):
    cell = sheet.cell(x["Row"], 1)
    for mergedcell in sheet.merged_cells.ranges:
        if(cell.coordinate in mergedcell):
            return True

test()

Pandas merged cell issue when reading from excel

Managed to find a fix

def read_excel(path):
    excel = None
    if path.endswith('xlsx'):
        excel = pd.ExcelFile(xlrd.open_workbook(path), engine='xlrd')
    elif path.endswith('xls'):
        excel = pd.ExcelFile(xlrd.open_workbook(path, formatting_info=True), engine='xlrd')
    else:
        raise ValueError("Could not read this type of data")
    return excel

def parse_excel(excel_file):
    sheet_0 = excel_file.book.sheet_by_index(0)
    df = excel_file.parse(0, header=None)
    return sheet_0, df

def fill_merged_na(sheet, dataframe):
    for e in sheet.merged_cells:
        rl, rh, cl, ch = e
        base_value = sheet.cell_value(rl, cl)
        dataframe.iloc[rl:rh, cl:ch] = base_value
    return dataframe

Some of the important bits are opening the excel file with the formatting_info set to True in order to also read formatting such as merged cells and the fill_merged_na function that fills only the merged nan values but leaves the initial empty cells as they were.

How to read merged excel column in python?

df = pd.read_excel(r'C:/Users/USER1/Desktop/report.xlsx')
df = df.reset_index()
df = df.drop(labels = df.filter(regex = 'Unnamed').columns, axis = 1)
df

---

Related Topics