使用Python从xlsm文件的文件夹中获取相同的工作表

Question

我是pandas / python的新手，我想出了以下代码来从工作表的特定部分提取数据。

import openpyxl as xl
import pandas as pd

rows_with_data = [34,37,38,39,44,45,46,47,48,49, 50,54,55,57,58,59,60,62,63,64,65,66,70,71,72,76,77, 78,79,80,81,82,83,84,88,89,90,91,92]

path = r'XXX'
xpath = input('XXX') 
file = r'**.xlsm'
xfile = input('Change file name, current is ' + file + ' :')
sheetname = r'Summary'

wb = xl.load_workbook(filename = xpath + '\\' +file, data_only = True)
sheet = wb.get_sheet_by_name(sheetname)

rows = len(rows_with_data)
line_items = []
for i in range(rows) :
    line_items.append(sheet.cell(row = rows_with_data[i], column = 13).value)

period = []
for col in range(17,35):
    period.append(sheet.cell(row = 20, column = col).value)

print(line_items)

vals = []
x = []
for i in range(rows):
    if i != 0:
        vals.append(x)
        x = []
    for col in range(17,35):

        x.append(sheet.cell(row = rows_with_data[i], column = col).value)


vals.append(x)      
all_values = {}
all_values['Period'] = period
for i in range(rows):
    print(line_items[i])   
    all_values[line_items[i]] = vals[i]

print(all_values)

period_review = input('Enter a period (i.e. 2002): ')
item = input('Enter a period (i.e. XXX): ') 

time = period.index(period_review)
display_item = str(all_values[item][time])
print(item + ' for ' + period_review + " is " + display_item)

Summary_Dataframe = pd.DataFrame(all_values)

writer = pd.ExcelWriter(xpath + '\\' + 'values.xlsx')
Summary_Dataframe.to_excel(writer,'Sheet1')
writer.save()
writer.close()

我在60个xlsm文件的库中有相同的工作表（摘要结果），我很难弄清楚如何在整个文件夹中迭代这个。我还希望将此更改从提取特定行到获取整个“摘要”工作表，将其粘贴到新文件并在粘贴到新excel文件时按文件名（“Experiment_A”）命名工作表。有什么建议？

Answer 1

我很难阅读您的代码，以了解您最终想要做什么。所以这只是一个建议而不是解决方案。您可以使用os遍历文件夹中的所有文件，然后将文件读入一个数据帧，然后将单个大数据帧保存到csv中。我通常避免使用excel，但我猜你需要excel转换。在下面的例子中，我已经从一个目录中读取了所有txt文件，将它们放入数据帧列表，然后将大数据帧存储为json。您也可以将其存储为excel / csv。

import os
import pandas as pd

def process_data():
    # input file path in 2 part in case it is very long
    input_path_1 = r'\\path\to\the\folder'
    input_path_2 = r'\second\part\of\the\path'
    # adding the all file path
    file_path = input_path_1 + input_path_2
    # listing all file in the file folder
    file_list = os.listdir(os.path.join(file_path))
    # selecting only the .txt files in to a list object
    file_list = [file_name for file_name in file_list if '.txt' in file_name]
    # selecting the fields we need
    field_names = ['country', 'ticket_id']
    # defining a list to put all the datafremes in one list
    pd_list = []
    inserted_files = []
    # looping over txt files and storing in to database
    for file_name in file_list:
      # creating the file path to read the file
      file_path_ = file_path + '\\' + file_name
      df_ = pd.read_csv(os.path.join(file_path_), sep='\t', usecols=field_names)
      # converting the datetime to date
      # few internal data transformation example before writting
      df_['sent_date'] = pd.to_datetime(df_['sent_date'])
      df_['sent_date'] = df_['sent_date'].values.astype('datetime64[M]')
      # adding each dataframe to the list
      pd_list.append(df_)
      # adding file name to the inserted list to print later
      inserted_files.append(file_name)
    print(inserted_files)
    # sql like union all dataframes and create a single data source
    df_ = pd.concat(pd_list)

    output_path_1 = r'\\path\to\output'
    output_path_2 = r'\path\to\output'
    output_path = output_path_1 + output_path_2
    # put the file name
    file_name = 'xyz.json'
    # adding the day the file processed
    df_['etl_run_time'] = pd.to_datetime('today').strftime('%Y-%m-%d')
    # write file to json
    df_.to_json(os.path.join(output_path, file_name), orient='records')
    return print('Data Stored as json successfully')

process_data()