Using python to rename multiple files
import os
rootdir = r'target'
str = "08"
for filename in os.listdir(rootdir):
if str in filename:
filepath = os.path.join(rootdir, filename)
newfilepath = os.path.join(rootdir, filename.replace(str, "09"))
os.rename(filepath, newfilepath)
Rename a file using Python pathlib module
from pathlib import Path
path = Path("target file")
target = path.with_name(path.name.replace("08",'09'))
path.rename(target)
# Convert PDF file to CSV file
# Reference : https://www.youtube.com/watch?v=wJwXThPSBE8 ( From 3:48 )
import tabula
tabula.io.convert_into('A_PDF_file.pdf','A_CSV_file.csv', output_format='csv', pages='all')
# Convert CSV file to xlsx file
# https://www.youtube.com/watch?v=JFAn-aownHE ( From 3:45 )
import csv
import openpyxl
csv_data = []
with open('A_CSV_file.csv') as file_obj:
reader = csv.reader(file_obj)
for row in reader:
csv_data.append(row)
wb = openpyxl.Workbook()
sheet = wb.active
for row in csv_data:
sheet.append(row)
wb.save('A_.xlsx')
Use python tabula module to convert PDF to csv file
import tabula
tabula.io.convert_into('A_PDF_file.pdf', 'A_CSV_file.csv', output_format='csv', pages='all')
Combine multiple Excel files using python pandas module
from operator import index
import pandas as pd
import datetime as dt
files = ['1_data.xlsx','2_data.xlsx','3_data.xlsx','4_data.xlsx','5_data.xlsx','6_data.xlsx','7_data.xlsx','8_data.xlsx']
combined = pd.DataFrame()
for file in files:
df=pd.read_excel(file)
combined=combined.append(df,ignore_index=True)
combined.to_excel('combine.xlsx',index=False,sheet_name='data')
