Active_prgs/Redgrave/NTRS-TopSenderAnalysis.py

"""

NTRS-TopSenderAnalysis

Created by:
Emanuel Borges
09.20.2023

Very simple program that will read multiple CSV files and export a report based on LanID and other general information.
To-Do: Method to QC for any parsing errors.  There should be the same number of fields across all of the CSVs.; 

"""

import csv, os, re

if __name__ == '__main__':
    startDir = r"C:\Users\eborges\Documents\Cases\Northern Trust\20230919 - FileNetTopSenderAnalysis-Req"
    allToLanAddressesSet = set()
    #regExPattern = '[A-Za-z]{2}[0-9]{2,3}@NTRS.COM'
    regExPattern = '[A-Za-z]{1,15}[0-9]{1,3}@NTRS.COM'
    

    for (root,dirs,files) in os.walk(startDir):
        for fl in files:
            fileRowCount = 0
            eightyCharRowCount = 0
            nonEightyCharRowCount = 0
            charsOverEighty = False
            noNtrsDomainBucketCount = 0
            ntrsAndLanBucketCount = 0
            ntrsNoLanBucketCount = 0
            
            with open(os.path.join(root,fl),mode='r',encoding='ANSI') as csv_file:
                csv_reader = csv.DictReader(csv_file)    
                for row in csv_reader:
                    fileRowCount += 1
                    if len(row['To']) == 80:
                        eightyCharRowCount +=1
                    else:
                        nonEightyCharRowCount +=1
                    if len(row['To']) > 80:
                       charsOverEighty = True 
                    toValue = row['To']
                    toValue = toValue.upper()
                    if "@NTRS.COM" in toValue:
                        ## No ntrs addresses found at all, 
                        ntrsLanAddressesList = re.findall(regExPattern, toValue)
                        if ntrsLanAddressesList:
                            ntrsAndLanBucketCount +=1
                            for a in ntrsLanAddressesList:
                                allToLanAddressesSet.add(a)
                        else:
                            ntrsNoLanBucketCount +=1
                    else:
                        noNtrsDomainBucketCount +=1
            print(f"{fl}|{fileRowCount}|{eightyCharRowCount}|{nonEightyCharRowCount}|{charsOverEighty}|{noNtrsDomainBucketCount}|{ntrsAndLanBucketCount}|{ntrsNoLanBucketCount}")
            csv_file.close()
    print(f"There are {len(allToLanAddressesSet)} unique LAN ID addresses.")
    outputFile = open(r"C:\Users\eborges\Documents\Cases\Northern Trust\ExtractedLanAddresses.txt",'w')
    allToLanAddressesList = list(allToLanAddressesSet)
    allToLanAddressesList.sort()
    for i in allToLanAddressesList:
        outputFile.write(f"{i}\n")
    outputFile.close()

    ## Initially gathering some very basic information across the CSV files, not using csv lib
#    for (root,dirs,files) in os.walk(r"C:\Users\eborges\Documents\Cases\Northern Trust"):
#        for fl in files:
#            contents = open(os.path.join(root,fl), encoding='ANSI').readlines()
#            print(f"{fl}|{len(contents)-1}")
Revision:	799
Committed:	Mon Sep 25 15:44:23 2023 UTC (2 years, 6 months ago) by nino.borges
Content type:	text/x-python
File size:	3060 byte(s)
Log Message:	Version of the program before finding many other examples that could also be LAN IDs and plan on adding extra verification.
#	User	Rev	Content
1	nino.borges	797	"""
2
3			NTRS-TopSenderAnalysis
4
5			Created by:
6			Emanuel Borges
7			09.20.2023
8
9			Very simple program that will read multiple CSV files and export a report based on LanID and other general information.
10	nino.borges	798	To-Do: Method to QC for any parsing errors. There should be the same number of fields across all of the CSVs.;
11	nino.borges	797
12			"""
13
14	nino.borges	798	import csv, os, re
15	nino.borges	797
16			if __name__ == '__main__':
17	nino.borges	798	startDir = r"C:\Users\eborges\Documents\Cases\Northern Trust\20230919 - FileNetTopSenderAnalysis-Req"
18			allToLanAddressesSet = set()
19	nino.borges	799	#regExPattern = '[A-Za-z]{2}[0-9]{2,3}@NTRS.COM'
20			regExPattern = '[A-Za-z]{1,15}[0-9]{1,3}@NTRS.COM'
21	nino.borges	798
22	nino.borges	797
23
24			for (root,dirs,files) in os.walk(startDir):
25			for fl in files:
26	nino.borges	798	fileRowCount = 0
27			eightyCharRowCount = 0
28			nonEightyCharRowCount = 0
29			charsOverEighty = False
30	nino.borges	799	noNtrsDomainBucketCount = 0
31			ntrsAndLanBucketCount = 0
32			ntrsNoLanBucketCount = 0
33
34	nino.borges	797	with open(os.path.join(root,fl),mode='r',encoding='ANSI') as csv_file:
35	nino.borges	798	csv_reader = csv.DictReader(csv_file)
36	nino.borges	797	for row in csv_reader:
37	nino.borges	798	fileRowCount += 1
38			if len(row['To']) == 80:
39			eightyCharRowCount +=1
40			else:
41			nonEightyCharRowCount +=1
42			if len(row['To']) > 80:
43			charsOverEighty = True
44			toValue = row['To']
45			toValue = toValue.upper()
46			if "@NTRS.COM" in toValue:
47	nino.borges	799	## No ntrs addresses found at all,
48	nino.borges	798	ntrsLanAddressesList = re.findall(regExPattern, toValue)
49			if ntrsLanAddressesList:
50	nino.borges	799	ntrsAndLanBucketCount +=1
51	nino.borges	798	for a in ntrsLanAddressesList:
52			allToLanAddressesSet.add(a)
53	nino.borges	799	else:
54			ntrsNoLanBucketCount +=1
55			else:
56			noNtrsDomainBucketCount +=1
57			print(f"{fl}\|{fileRowCount}\|{eightyCharRowCount}\|{nonEightyCharRowCount}\|{charsOverEighty}\|{noNtrsDomainBucketCount}\|{ntrsAndLanBucketCount}\|{ntrsNoLanBucketCount}")
58	nino.borges	798	csv_file.close()
59			print(f"There are {len(allToLanAddressesSet)} unique LAN ID addresses.")
60			outputFile = open(r"C:\Users\eborges\Documents\Cases\Northern Trust\ExtractedLanAddresses.txt",'w')
61			allToLanAddressesList = list(allToLanAddressesSet)
62			allToLanAddressesList.sort()
63			for i in allToLanAddressesList:
64			outputFile.write(f"{i}\n")
65			outputFile.close()
66	nino.borges	797
67			## Initially gathering some very basic information across the CSV files, not using csv lib
68			# for (root,dirs,files) in os.walk(r"C:\Users\eborges\Documents\Cases\Northern Trust"):
69			# for fl in files:
70			# contents = open(os.path.join(root,fl), encoding='ANSI').readlines()
71			# print(f"{fl}\|{len(contents)-1}")