| 1 |
"""
|
| 2 |
|
| 3 |
Amazon_NameSearches
|
| 4 |
|
| 5 |
Created by:
|
| 6 |
Emanuel Borges
|
| 7 |
12.3.2024
|
| 8 |
|
| 9 |
This program to test searching the MAL.
|
| 10 |
|
| 11 |
"""
|
| 12 |
|
| 13 |
|
| 14 |
|
| 15 |
import os, re
|
| 16 |
import MyCode.Active_prgs.Redgrave.Amazon_PrivLogQC
|
| 17 |
import MyCode.Active_prgs.Redgrave.Amazon_NamesNormQC
|
| 18 |
|
| 19 |
|
| 20 |
|
| 21 |
|
| 22 |
|
| 23 |
if __name__ == '__main__':
|
| 24 |
#cleanedDatExportFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\20241202 - FTC-CID\PLOG All IDs (20241203)\TEST-PLOG.txt"
|
| 25 |
#cleanedDatExportFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\20241202 - FTC-CID\PLOG All IDs (20241203)\PLOG All IDs (20241203)_Converted_SubSetOnly.txt"
|
| 26 |
cleanedDatExportFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\Data Exports\CAAG\CAAG_Log_Data_Export_Converted.txt"
|
| 27 |
masterAttorneyListFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\Amazon_ Master Attorney List 2024.12.12(20241212-1151).xlsx"
|
| 28 |
fullNameOveridesFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\FullNameOverides - Copy.txt"
|
| 29 |
#fullNameOveridesFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\FullNameOverides.txt"
|
| 30 |
allPossibleEmailAddressesRegExPattern = r"[\w.+-]+@[\w-]+\.[\w.-]+"
|
| 31 |
outputFile = open(r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\Data Exports\CAAG\namesSearchResults_new.txt",'w')
|
| 32 |
|
| 33 |
|
| 34 |
|
| 35 |
nv = MyCode.Active_prgs.Redgrave.Amazon_NamesNormQC.NamesVerification(cleanedDatExportFileName, masterAttorneyListFileName, fullNameOveridesFileName)
|
| 36 |
|
| 37 |
|
| 38 |
## This is just some simple searching of email addresses
|
| 39 |
## contents = open(r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\Consilio\VEAS-MasterAttorneyList\2024-12-05_EmailAddressesOnly.txt",encoding='UTF-8').readlines()
|
| 40 |
## contents = contents[1:]
|
| 41 |
## for line in contents:
|
| 42 |
## line = line.replace("\n","")
|
| 43 |
## line = line.split(";")
|
| 44 |
## for i in line:
|
| 45 |
## personMatch = nv.malPeopleList.search_by_email(i.upper())
|
| 46 |
## if personMatch:
|
| 47 |
## if personMatch.is_attorney == 'YES':
|
| 48 |
## pass
|
| 49 |
## #print(f"{i} is an attorney match!")
|
| 50 |
## elif personMatch.is_attorney == 'NO':
|
| 51 |
## print(f"{i} is an downgrade match!")
|
| 52 |
## else:
|
| 53 |
## print(f"{i} is a possible Split Role match!")
|
| 54 |
|
| 55 |
|
| 56 |
## This section was used for comparing the names in legal sources to any email addresses I could locate on that same line.
|
| 57 |
contents = open(cleanedDatExportFileName,encoding='UTF-8').readlines()
|
| 58 |
contents = contents[1:]
|
| 59 |
for line in contents:
|
| 60 |
attorneysInDocumentSet = set()
|
| 61 |
downgradesInSet = set()
|
| 62 |
line = line.replace("\n","")
|
| 63 |
#singleLine = contents[3]
|
| 64 |
resultSet = set()
|
| 65 |
results = re.findall(allPossibleEmailAddressesRegExPattern, line)
|
| 66 |
for result in results:
|
| 67 |
resultSet.add(result)
|
| 68 |
line = line.split("|")
|
| 69 |
legalSources = line[11].upper()
|
| 70 |
if legalSources:
|
| 71 |
legalSources =legalSources.split(";")
|
| 72 |
#print(f"\n\n{legalSources}")
|
| 73 |
for r in list(resultSet):
|
| 74 |
#print(r)
|
| 75 |
personMatch = nv.malPeopleList.search_by_email(r.upper())
|
| 76 |
if personMatch:
|
| 77 |
#print("entry exists")
|
| 78 |
if personMatch.full_name_overide:
|
| 79 |
if f"{personMatch.full_name_overide}*" in legalSources:
|
| 80 |
if personMatch.is_attorney == 'YES':
|
| 81 |
attorneysInDocumentSet.add(f"{personMatch.full_name_overide}* is a match on {r.upper()}. This is an Attorney.")
|
| 82 |
#print (f"{personMatch.full_name_overide}* is a match on {r.upper()}. This is an Attorney.")
|
| 83 |
else:
|
| 84 |
downgradesInSet.add(f"{personMatch.full_name_overide}* is a match on {r.upper()}. This is a DOWNGRADE.")
|
| 85 |
#print (f"{personMatch.full_name_overide}* is a match on {r.upper()}. This is a DOWNGRADE.")
|
| 86 |
if personMatch.full_name_preferred:
|
| 87 |
fullPreferredName = personMatch.full_name_preferred
|
| 88 |
fullPreferredName = fullPreferredName.replace('(LEGAL)','')
|
| 89 |
fullPreferredName = fullPreferredName.replace('(SHE, HER)','')
|
| 90 |
fullPreferredName = fullPreferredName.replace('(SHE HER)','')
|
| 91 |
fullPreferredName = fullPreferredName.replace(',,',',')
|
| 92 |
#print(fullPreferredName)
|
| 93 |
preferedLastName, preferedFirstName = fullPreferredName.split(',')
|
| 94 |
preferedLastName = preferedLastName.strip()
|
| 95 |
preferedFirstName = preferedFirstName.strip()
|
| 96 |
preferedFirstName = preferedFirstName.split(" ")[0]
|
| 97 |
fullName = f"{preferedFirstName} {preferedLastName}"
|
| 98 |
#if f"{preferedLastName}, {preferedFirstName}*" in legalSources:
|
| 99 |
if f"{preferedFirstName} {preferedLastName}*" in legalSources:
|
| 100 |
if personMatch.is_attorney == 'YES':
|
| 101 |
#attorneysInDocumentSet.add(f"{preferedLastName}, {preferedFirstName}* is a match on {r.upper()}. This is an Attorney.")
|
| 102 |
attorneysInDocumentSet.add(f"{preferedFirstName} {preferedLastName}* is a match on {r.upper()}. This is an Attorney.")
|
| 103 |
#print(f"{preferedLastName}, {preferedFirstName}* is a match on {r.upper()}. This is an Attorney.")
|
| 104 |
else:
|
| 105 |
#downgradesInSet.add(f"{preferedLastName}, {preferedFirstName}* is a match on {r.upper()}. This is a DOWNGRADE.")
|
| 106 |
downgradesInSet.add(f"{preferedFirstName} {preferedLastName}* is a match on {r.upper()}. This is a DOWNGRADE.")
|
| 107 |
#print(f"{preferedLastName}, {preferedFirstName}* is a match on {r.upper()}. This is a DOWNGRADE.")
|
| 108 |
#if f"{personMatch.last_name}, {personMatch.first_name}*" in legalSources:
|
| 109 |
if f"{personMatch.first_name} {personMatch.last_name}*" in legalSources:
|
| 110 |
if personMatch.is_attorney == 'YES':
|
| 111 |
#attorneysInDocumentSet.add(f"{personMatch.last_name}, {personMatch.first_name}* is a match on {r.upper()}. This is an Attorney.")
|
| 112 |
attorneysInDocumentSet.add(f"{personMatch.first_name} {personMatch.last_name}* is a match on {r.upper()}. This is an Attorney.")
|
| 113 |
#print(f"{personMatch.last_name}, {personMatch.first_name}* is a match on {r.upper()}. This is an Attorney.")
|
| 114 |
else:
|
| 115 |
#downgradesInSet.add(f"{personMatch.last_name}, {personMatch.first_name}* is a match on {r.upper()}. This is a DOWNGRADE.")
|
| 116 |
downgradesInSet.add(f"{personMatch.first_name} {personMatch.last_name}* is a match on {r.upper()}. This is a DOWNGRADE.")
|
| 117 |
#print(f"{personMatch.last_name}, {personMatch.first_name}* is a match on {r.upper()}. This is a DOWNGRADE.")
|
| 118 |
outputFile.write(f"{line[0]} has {len(attorneysInDocumentSet)} matching attorneys and {len(downgradesInSet)} matching downgrades. ")
|
| 119 |
if len(attorneysInDocumentSet) > 0:
|
| 120 |
outputFile.write("There is at least 1 matching attorney.\n")
|
| 121 |
else:
|
| 122 |
outputFile.write("There are NO matching attorneys!\n")
|
| 123 |
else:
|
| 124 |
pass
|
| 125 |
#print("\n\nEmpty legal sources field")
|
