How to read multiple files and save a single output with pandas use command line arguments - pandas

Question

I have multiple files in TXT format how to get all the values ​​with a single output Merge values ​​into a single file use command line arguments in pandas
like this:
python3 file1.txt file2.txt file3.txt
Code:
import pandas as pd
import socket, struct
import os
import glob
import sys
try:
file = sys.argv[1]
except Exception:
print("Usage: python3 {} [file]".format(sys.argv[0]))
sys.exit()
os.chdir('/Users/roc/Desktop/js/projj')
fileList = glob.glob('*.txt')
appended_data = []
for file in fileList:
pdd = pd.read_csv(file,header=None,sep='|',error_bad_lines=False, warn_bad_lines=False,skiprows=[0],names=['Name','Code','Ipv', 'Ip','Range','Date', 'Category'],low_memory=False)
df = pdd[pdd['Ipv'].str.contains("ipv4") & pdd['Ip'].str.contains('[0-9]')]
appended_data.append(df)
appended_data = pd.concat(appended_data)
df = pd.DataFrame(appended_data)
pd.options.mode.chained_assignment = None
def ip2int(ip):
packedIP = socket.inet_aton(ip)
return struct.unpack("!L", packedIP)[0]
df['Ip'] = df.Ip.apply(ip2int)
df['Range'] = df.groupby(['Code'])['Range'].transform('sum').fillna(0).astype(int)
k = df[['Ip', 'Range', 'Code']].dropna()
df2 = k.drop_duplicates(subset=['Range'])
result_df =df2.sort_values('Range', ascending=True)
print(result_df.to_csv("/Users/roc/Desktop/js/projj/delegated2.txt",sep=' ', index=False, header=False))

Answer 1

Use the below to iterate through a folder and append all files to a single dataframe
import os
import glob
os.chdir('C:\\path_to_folder\\')
Filelist = glob.glob('*.txt')
appended_data = []
for file in FileList:
pdd = pd.read_csv(file,header=None,sep='|',error_bad_lines=False, warn_bad_lines=False,skiprows=[0],names=['Name','Code','Ipv', 'Ip','Range','Date', 'Category'],low_memory=False)
df = pdd[pdd['Ipv'].str.contains("ipv4") & pdd['Ip'].str.contains('[0-9]')]
appended_data.append(df)
appended_data = pd.concat(appended_data)
df = pd.DataFrame(appended_data)
Once you have the df which is combined of all the data from all files, use the next part of the code:
pd.options.mode.chained_assignment = None
def ip2int(ip):
packedIP = socket.inet_aton(ip)
return struct.unpack("!L", packedIP)[0]
df['Ip'] = df.Ip.apply(ip2int) df['Range'] = df.groupby(['Code'])['Range'].transform('sum').fillna(0).astype(int)
k = df[['Ip', 'Range', 'Code']].dropna()
df2 = k.drop_duplicates(subset=['Range'])
result_df =df2.sort_values('Range', ascending=True)
result_df.to_csv("/Users/roc/Desktop/output.txt",sep=' ', index=False, header=False)