Looping through tabs in Excel spreadsheet using regex for tab names

Question

I am trying to loop through some Excel spreadsheets and pull information from certain tabs using regex. I have written the following code so far:

import pandas as pd
import os
import re

root = r"my_dir"

agg_df = pd.DataFrame()

for directory, subdirectory, files in os.walk(root):
    for file in files:
        if file.endswith('.xlsm'):
            filepath = os.path.join(directory, file)
            xls = pd.ExcelFile(filepath)
            for i in xls.sheet_names:
                if re.search(r'Apples', i):
                    df_temp = pd.read_excel(filepath, sheet_names=i)
                    df_temp['Filepath'] = filepath
                    df_temp['Sheet_Name'] = i
                    agg_df = agg_df.append(df_temp)
                elif re.search(r'Oranges', i):
                    df_temp = pd.read_excel(filepath, sheet_names=i)
                    df_temp['Filepath'] = filepath
                    df_temp['Sheet_Name'] = i
                    agg_df = agg_df.append(df_temp)
                elif re.search('Grapes', i):
                    df_temp = pd.read_excel(filepath, sheet_names=i)
                    df_temp['Filepath'] = filepath
                    df_temp['Sheet_Name'] = i
                    agg_df = agg_df.append(df_temp)
                elif re.search(r'Tomatoes', i):
                    df_temp = pd.read_excel(filepath, sheet_names=i)
                    df_temp['Filepath'] = filepath
                    df_temp['Sheet_Name'] = i
                    agg_df = agg_df.append(df_temp)
                elif re.search(r'Peaches', i):
                    df_temp = pd.read_excel(filepath, sheet_names=i)
                    df_temp['Filepath'] = filepath
                    df_temp['Sheet_Name'] = i
                    agg_df = agg_df.append(df_temp)
                elif re.search(r'Pears', i):
                    df_temp = pd.read_excel(filepath, sheet_names=i)
                    df_temp['Filepath'] = filepath
                    df_temp['Sheet_Name'] = i
                    agg_df = agg_df.append(df_temp)
                elif re.search(r'Bananas', i):
                    df_temp = pd.read_excel(filepath, sheet_names=i)
                    df_temp['Filepath'] = filepath
                    df_temp['Sheet_Name'] = i
                    agg_df = agg_df.append(df_temp)
                elif re.search(r'Mangos', i):
                    df_temp = pd.read_excel(filepath, sheet_names=i)
                    df_temp['Filepath'] = filepath
                    df_temp['Sheet_Name'] = i
                    agg_df = agg_df.append(df_temp) 

However, this is pulling the first tab and not the tabs I'm trying to specify.

Answer 1

You are passing parameter sheet_names , but the pandas documentation is mentioning the parameter is sheet_name . See read_excel() function.

I did some changes in your code, try execute:

import os

import pandas as pd


def parse_excel(sheet_name: str, abs_file_path: str):
    df = pd.read_excel(abs_file_path, sheet_name=sheet_name)
    df['Filepath'] = abs_file_path
    df['Sheet_Name'] = sheet_name
    return df


root = "my_dir"
agg_df = pd.DataFrame()
for directory, subdirectory, files in os.walk(root):
    for file in files:
        if file.endswith('.xlsm'):
            file_path = os.path.join(directory, file)
            xls = pd.ExcelFile(file_path)
            sheet_names = ['Apples', 'Oranges', 'Grapes', 'Tomatoes', 'Peaches',
                           'Pears', 'Bananas', 'Mangos']
            available_sheets = [sheet_name for sheet_name in xls.sheet_names if sheet_name in sheet_names]
            for available_sheet in available_sheets:
                agg_df = agg_df.append(parse_excel(available_sheet, file_path))