class HunterioManager:
def __init__(self):
self.hunter = PyHunter('72ebe102b85923275c17d6b374551edb56dbb898')
def get_mails(self, domain, company):
"""
Wrapper around domain_search
"""
results_file = domain + ".txt"
try:
if company != "":
print(company)
x = self.hunter.domain_search(company=company)
else:
print(domain)
x = self.hunter.domain_search(domain)
#json.dumps(json_data["data"])
with open(results_file, 'w') as file:
#x="{'domain': 'instagram.com', 'disposable': False, 'webmail': False, 'pattern': '{first}{last}', 'organization': 'Instagram', 'emails': [{'value': '*****@*****.**'}]}"
#file.write(x) ==> not working
for i in x['emails']:
print(i['value'])
except Exception as e:
raise e
print("Go to hunter.io/<domain> and explore the results manually")
def domain_search_hunter(self):
if len(self.hunter_io_mails) > 0:
self.email_list.update(self.hunter_io_mails)
print(
"Email list is expanded using hunter.io results from the file."
)
return
hunter = PyHunter(self.hunter_api_key)
i = 0
search = hunter.domain_search(self.domain_name,
limit=100,
offset=100 * i)
while search['emails']:
search = hunter.domain_search(self.domain_name,
limit=100,
offset=100 * i)
for item in search['emails']:
user_mail = item['value']
self.email_list.add(user_mail)
self.hunter_io_mails.append(user_mail)
i += 1
print("{} emails have been found via hunter.io".format(
len(self.hunter_io_mails)))
with open("email_hunter.em", "w", encoding="UTF-8") as ff:
ff.write("\n".join(self.hunter_io_mails))
def search(self):
hunter = PyHunter(self.apikey)
result = hunter.domain_search(company=self.domain,
limit=self.limit,
emails_type='personal')
return result
def hunter_domain_search(domain):
api = "44ac9d0fcf060465933c1591d75c2ace4b1692d8"
hunter = PyHunter(api)
info = (hunter.account_information())
print("Kalan API Hakkı : ",info["calls"]["left"])
print("hunter domain search..")
while(True):
if (info["calls"]["left"] != 0):
result = hunter.domain_search(domain)
result = result["emails"]
for i in range(len(result)):
email.append(result[i]["value"])
break
else:
print("\nMevcut Api Arama Hakkı Bitti")
print("""
1 - Yeni API Ekle
0 - Çıkış Yap
""")
choise = input("Yapmak İstediğiniz İşlemi Seçiniz = ")
if (choise == "1"):
api = input("\nYeni Api Değerini Giriniz = ")
elif (choise == "0"):
break
else:
print("Hatalı Bir Seçim Yaptınız, Tekrar Deneyiniz..")
def domain_search_hunter(self):
hunter = PyHunter(self.hunter_api_key)
i = 0
search = hunter.domain_search(self.domain_name,
limit=100,
offset=100 * i)
while search['emails']:
search = hunter.domain_search(self.domain_name,
limit=100,
offset=100 * i)
for item in search['emails']:
user_mail = item['value']
self.email_list.add(user_mail)
self.hunter_io_mails.append(user_mail)
i += 1
print("{} emails have been found via hunter.io".format(
len(self.hunter_io_mails)))
def domain_search(company, qualified):
if company is not None:
hunter = PyHunter('a890302fd13f718af83604989dbd3213772a0d07')
json_load = json.loads(hunter.domain_search(company=company, limit=1000, raw = True).text)
positions = []
emails = []
last_names = []
first_names = []
scores = []
companies = []
for i in range(len(json_load['data']['emails'])):
if emailVerifier(json_load['data']['emails'][i]['value']) == True:
if qualified is False:
positions.append(json_load['data']['emails'][i]['position'])
emails.append(json_load['data']['emails'][i]['value'])
scores.append(json_load['data']['emails'][i]['confidence'])
last_names.append(json_load['data']['emails'][i]['last_name'])
first_names.append(json_load['data']['emails'][i]['first_name'])
companies.append(company)
if qualified is True:
if json_load['data']['emails'][i]['last_name'] is not None:
positions.append(json_load['data']['emails'][i]['position'])
emails.append(json_load['data']['emails'][i]['value'])
scores.append(json_load['data']['emails'][i]['confidence'])
last_names.append(json_load['data']['emails'][i]['last_name'])
first_names.append(json_load['data']['emails'][i]['first_name'])
companies.append(company)
if qualified is 'ultra':
if json_load['data']['emails'][i]['position'] is not None:
positions.append(json_load['data']['emails'][i]['position'])
emails.append(json_load['data']['emails'][i]['value'])
scores.append(json_load['data']['emails'][i]['confidence'])
last_names.append(json_load['data']['emails'][i]['last_name'])
first_names.append(json_load['data']['emails'][i]['first_name'])
companies.append(company)
print('company name terminée: ', company)
companies = pd.DataFrame({ 'last_name': last_names,
'email': emails,
'company': companies,
'position': positions,
'first_name': first_names,
'score': scores
})
if emails != []:
if qualified is False:
companies.to_csv('/home/francois/Téléchargements/allCompanies/' + company + '.csv')
if qualified is True:
companies.to_csv('/home/francois/Téléchargements/allCompanies/' + company + '.csv')
if qualified is 'ultra':
companies.to_csv('/home/francois/Téléchargements/allCompanies/' + company + '.csv')
def Text(self):
textboxValue = self.textbox.text()
hunter=PyHunter('Enter key here')
Temp=hunter.domain_search(textboxValue)
Temp1=Temp['emails']
for i in range (0,len(Temp1)):
temp2=Temp1[i]
Dom_em=temp2['value']
file = open(textboxValue + ".txt",'w')
for i in range (0,len(Temp1)):
temp2=Temp1[i]
file.write(temp2['value'])
file.write('\n')
QMessageBox.question(self, 'Emails', "The Emails are saved in a text file " , QMessageBox.Ok, QMessageBox.Ok)
file.close()
def spreadsheet(self):
textboxValue = self.textbox.text()
hunter=PyHunter('Enter key here')
Temp=hunter.domain_search(textboxValue)
Temp1=Temp['emails']
for i in range (0,len(Temp1)):
temp2=Temp1[i]
Dom_em=temp2['value']
csv = open(textboxValue + ".csv",'w')
Column_Title = "S.No.,Email\n"
csv.write(Column_Title)
for i in range (0,len(Temp1)):
Sno = str(i+1)
temp2=Temp1[i]
email = temp2['value']
row = Sno + "," + email + "\n"
csv.write(row)
QMessageBox.question(self, 'Emails', "The Emails are saved in a spreadsheet" , QMessageBox.Ok, QMessageBox.Ok)
csv.close()
def run(self, conf, args, plugins):
if 'subcommand' in args:
hunter = PyHunter(conf['Hunter']['key'])
if args.subcommand == 'email':
if ' ' not in args.NAME:
print('Name should contains first and last name')
print('(Yes this API is useless)')
sys.exit(1)
res = hunter.email_finder(
domain=args.DOMAIN,
full_name=args.NAME,
raw=True
)
print(json.dumps(res, sort_keys=True, indent=4))
elif args.subcommand == 'domain':
res = hunter.domain_search(args.DOMAIN)
print(json.dumps(res, sort_keys=True, indent=4))
else:
self.parser.print_help()
else:
self.parser.print_help()
def get_hunterio_emails(company, API_KEY):
hunter = PyHunter(API_KEY)
account_info = hunter.account_information()
calls_remaining = account_info['calls']['left']
calls_allowed = account_info['calls']['available']
print_success("[+] Checking hunter.io ({0}/{1} queries remaining)".format(
calls_remaining, calls_allowed))
results = hunter.domain_search(company, limit=1000, emails_type="personal")
company_records = results['emails']
hunterio_emails = []
counter = 0
for record in company_records:
email = str(record['value'])
fname = str(record['first_name'])
lname = str(record['last_name'])
position = str(record['position'])
hunterio_emails.append(fname + "," + lname + "," + email + "," +
position)
counter = counter + 1
return hunterio_emails
dic_dnsreconrecords['tipo'] = y.attrib['type']
dic_dnsreconrecords['name'] = y.attrib['name']
saida = '\nTipo :' + dic_dnsreconrecords[
'tipo'] + ' Registro:' + dic_dnsreconrecords['name']
log_osint.write(saida)
except:
pass
#Execucao do SCAN EMAILS
saida = '\n\n########### E M A I L S ###########\n'
log_osint.write(saida)
print("\033[32m" + "[+] SCAN EMAILS Execution" + "\033[0;0m" + "\n")
##Conexao com o Hunter e buscas de informacoes
hunter = PyHunter('40719a5bd9a907b3c9b204b652a9a1a770b95348')
hunter_search = hunter.domain_search(dominio)
#Parse do HUNTER
for x in hunter_search.keys():
if (x == 'domain'):
dic_hunter['domain'] = hunter_search.get('domain')
if (x == 'emails'):
emails = hunter_search.get('emails')
for y in emails:
e_mail = y.get('value')
dic_hunter['email'] = e_mail
dic_email[e_mail] = e_mail
dic_hunter['tipo'] = y.get('type')
if (dic_hunter['tipo'] == None):
dic_hunter['tipo'] = ''
dic_hunter['confianca'] = y.get('confidence')
if (dic_hunter['confianca'] == None):
def Search(Query_List, Task_ID, Type, Limit=10):
try:
Data_to_Cache = []
Directory = General.Make_Directory(Plugin_Name.lower())
logger = logging.getLogger()
logger.setLevel(logging.INFO)
Log_File = General.Logging(Directory, Plugin_Name.lower())
handler = logging.FileHandler(os.path.join(Directory, Log_File), "w")
handler.setLevel(logging.DEBUG)
formatter = logging.Formatter("%(levelname)s - %(message)s")
handler.setFormatter(formatter)
logger.addHandler(handler)
Shodan_API_Key = Load_Configuration()
API_Session = PyHunter(Shodan_API_Key)
Cached_Data_Object = General.Cache(Directory, Plugin_Name)
Cached_Data = Cached_Data_Object.Get_Cache()
Query_List = General.Convert_to_List(Query_List)
Limit = General.Get_Limit(Limit)
for Query in Query_List:
try:
if Type == "Domain":
if Common.Regex_Handler(Query, Type="Domain"):
Local_Plugin_Name = Plugin_Name + "-Domain"
API_Response = API_Session.domain_search(Query)
JSON_Object = Common.JSON_Handler(API_Response)
JSON_Output_Response = JSON_Object.Dump_JSON()
if API_Response["domain"] and API_Response['emails']:
Main_File = General.Main_File_Create(
Directory, Local_Plugin_Name,
JSON_Output_Response, Query,
The_File_Extensions["Main"])
Output_Connections = General.Connections(
Query, Local_Plugin_Name, Domain, "Account",
Task_ID, Plugin_Name.lower())
Current_Step = 0
for Hunter_Item in API_Response["emails"]:
Current_Email_Address = Hunter_Item["value"]
Current_Hunter_Item_Host = f"https://{Domain}/verify/{Current_Email_Address}"
Current_Hunter_Item_Responses = Common.Request_Handler(
Current_Hunter_Item_Host,
Filter=True,
Host=f"https://{Domain}")
Filtered_Response = Current_Hunter_Item_Responses[
"Filtered"]
Title = "Hunter | " + Current_Email_Address
if Current_Email_Address not in Cached_Data and Current_Email_Address not in Data_to_Cache and Current_Step < int(
Limit):
Output_file = General.Create_Query_Results_Output_File(
Directory, Query, Local_Plugin_Name,
Filtered_Response,
Current_Hunter_Item_Host,
The_File_Extensions["Query"])
if Output_file:
Output_Connections.Output(
[Main_File, Output_file],
Current_Hunter_Item_Host, Title,
Plugin_Name.lower())
Data_to_Cache.append(
Current_Email_Address)
else:
logging.warning(
f"{Common.Date()} - {__name__.strip('plugins.')} - Failed to create output file. File may already exist."
)
Current_Step += 1
elif Type == "Email":
if Common.Regex_Handler(Query, Type="Email"):
Local_Plugin_Name = Plugin_Name + "-Email"
API_Response = API_Session.email_verifier(Query)
JSON_Object = Common.JSON_Handler(API_Response)
JSON_Output_Response = JSON_Object.Dump_JSON()
if API_Response["email"] and API_Response['sources']:
Main_File = General.Main_File_Create(
Directory, Local_Plugin_Name,
JSON_Output_Response, Query,
The_File_Extensions["Main"])
Output_Connections = General.Connections(
Query, Local_Plugin_Name, Domain,
"Account Source", Task_ID, Plugin_Name.lower())
Current_Step = 0
for Hunter_Item in API_Response["sources"]:
Current_Hunter_Item_Host = Hunter_Item["uri"]
Current_Hunter_Item_Domain = Hunter_Item[
"domain"]
if 'http://' in Current_Hunter_Item_Host:
Current_Hunter_Item_Responses = Common.Request_Handler(
Current_Hunter_Item_Host,
Filter=True,
Host=
f"http://{Current_Hunter_Item_Domain}")
Filtered_Response = Current_Hunter_Item_Responses[
"Filtered"]
elif 'https://' in Current_Hunter_Item_Host:
Current_Hunter_Item_Responses = Common.Request_Handler(
Current_Hunter_Item_Host,
Filter=True,
Host=
f"https://{Current_Hunter_Item_Domain}"
)
Filtered_Response = Current_Hunter_Item_Responses[
"Filtered"]
else:
Filtered_Response = Common.Request_Handler(
Current_Hunter_Item_Host)
Title = "Hunter | " + Current_Hunter_Item_Host
if Current_Hunter_Item_Host not in Cached_Data and Current_Hunter_Item_Host not in Data_to_Cache and Current_Step < int(
Limit):
Output_file = General.Create_Query_Results_Output_File(
Directory, Query, Local_Plugin_Name,
Filtered_Response,
Current_Hunter_Item_Host,
The_File_Extensions["Query"])
if Output_file:
Output_Connections.Output(
[Main_File, Output_file],
Current_Hunter_Item_Host, Title,
Plugin_Name.lower())
Data_to_Cache.append(
Current_Hunter_Item_Host)
else:
logging.warning(
f"{Common.Date()} - {__name__.strip('plugins.')} - Failed to create output file. File may already exist."
)
Current_Step += 1
except Exception as e:
logging.warning(
f"{Common.Date()} - {__name__.strip('plugins.')} - Failed to complete task - {str(e)}"
)
Cached_Data_Object.Write_Cache(Data_to_Cache)
except Exception as e:
logging.warning(
f"{Common.Date()} - {__name__.strip('plugins.')} - {str(e)}")
def scrape(domain,api_key):
hunter = PyHunter(api_key)
data = hunter.domain_search(domain)
domain = data['domain']
organization = data['organization']
df = json_normalize(data['emails'])
from pyhunter import PyHunter
import json
import pprint
hunter = PyHunter('a6498ae6a4371fd85d51cbfd9d8f8892b1b6f402')
domain_search = hunter.domain_search('cokodive.com')
domain_search_o = hunter.domain_search(company='Instagram',
limit=5,
offset=2,
emails_type='personal')
pprint.pprint(domain_search)
# -*- coding: utf-8 -*-
"""
Created on Thu Aug 1 11:25:24 2019
@author: ikhwan
"""
import pandas as pd
from pyhunter import PyHunter
hunter = PyHunter('c4d2eab17b086e9bbd65531c7b81a0b5e6e4beb7')
web_list = pd.read_csv('pet_care.csv')
for index, url in web_list.iterrows():
df_profile = pd.DataFrame()
mailList = hunter.domain_search(url['web_url'])
#print(email)
for key, value in mailList.items():
if key == 'emails':
email = value
for mail in email:
del mail['sources']
if df_profile.empty:
df_profile = pd.DataFrame.from_dict(mail, orient='index')
else :
temp = pd.DataFrame.from_dict(mail, orient='index')
df_profile = pd.concat([df_profile, temp], axis=1, join='inner')
df_save = df_profile.transpose()
webpage = webpage.decode("utf8")
# On récupere tout les urls qui se trouvent dans la reponse
urls = re.findall('https?://(?:[-\w.]|(?:%[\da-fA-F]{2}))+', webpage)
# On enleve tous les urls du moteur de recherche : ici google
urls = [x for x in urls if "google" not in x]
# On supprime les doublons
urls = list(dict.fromkeys(urls))
# Ici j'ai eu le choix entre 2 strategies.
# 1er solution : Utiliser Hunter.io | Problème : C'est trop chère pour un étudiant
# 2eme solution : Trouvez les emails moi-même à l'aide de des nom de domaine | Problème : C'est galére et les adresses emails scrapper ne sont pas forcément les bonnes
# je vous presente ici la 1er solution mais je ne ferais que une requete car c'est juste un petit projet (Je suis limité à 50 requete par mois en gratuit, sinon il faut payer).
domaineInformation = hunter.domain_search(
urls[0]
) # Je prend seulement le premier resulat, si on voudrait obtenir tous les informations il suffirait de faire une boucle for sur ces informations et de les enregistrer
print("Voici les informations obtenue :")
# ICI ON PEUT FAIRE LA BOUCLE
print("Pour le nom de domaine : " + domaineInformation["domain"])
print("Voici la liste des adresses emails :")
for info in domaineInformation["emails"]:
print(
"Adresse email : " + info["value"]
) # + " " + info["first_name"] + " " + info["last_name"] + " Role : " + info["position"] + " Tél : " + info["phone_number"] + "Linkedin : " + info["linkedin"])
information = hunter.account_information()
print("Il reste " + str(information["calls"]["left"]) +
" requetes à l'API hunter.io sur le compte. " +
"Le compte hunter.io appartient à " + information["first_name"] + " " +
import requests
from datetime import datetime
from pyhunter import PyHunter
# Checking the params -d and -l
arguments_len = len(sys.argv) - 1
if arguments_len == 4:
if sys.argv[1] == '-d' and sys.argv[3] == '-l':
# Do not forget to put your API-key in PyHunter()!
hunter_api = PyHunter('')
domain = sys.argv[2]
limit = sys.argv[4]
# Trying to connect to Hunter.io and get the list of emails for the given domain
try:
hunter_resp = hunter_api.domain_search(domain, limit=limit)
emails_len = len(hunter_resp['emails'])
filename_output = 'email_results_' + str(
datetime.now().strftime("%H-%M-%S_%d-%m-%y")) + '.txt'
file_output = open(filename_output, "w+")
for x in range(emails_len):
file_output.write(
str(hunter_resp['emails'][x]['value']) + "\r\n")
file_output.close()
# Catching errors into the error log .txt file
except requests.exceptions.HTTPError as e:
filename_output = 'error_log_' + str(
datetime.now().strftime("%H-%M-%S_%d-%m-%y")) + '.txt'
file_output = open(filename_output, "w")
file_output.write(str(e) + "\r\n")
file_output.close()
from pyhunter import PyHunter
import pprint
# https://github.com/VonStruddle/PyHunter
# pip install pyhunter
hunter = PyHunter('SUA-KEY')
hunter.domain_search('businesscorp.com.br')
pp = pprint.PrettyPrinter(indent=4)
pp.pprint(hunter.domain_search('businesscorp.com.br'))
def find_email(self,tld): hunter = PyHunter(self.api_key) response = hunter.domain_search(company=tld) return response
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
"--input-file",
help=
"The input CSV file. Must have the 'Firm' column (and can also have the optional 'Location' column).",
type=str,
default=0)
parser.add_argument("--output-file",
help="The output CSV file.",
type=str,
default=0)
parser.add_argument("--start-row",
help="The row in input file to start on",
type=int,
default=0)
parser.add_argument("--end-row",
help="The row in input file to end on",
type=int,
default=0)
args = parser.parse_args()
if not os.path.isfile(args.input_file):
print("Input file doesn't exist. Exiting.")
sys.exit(1)
if os.path.isfile(
args.output_file) and not (args.end_row or args.start_row):
print("Output file ({}) exists already. Exiting.".format(
args.output_file))
sys.exit(1)
# Make sure we can load the file
df = pd.read_csv(args.input_file)
if args.start_row != 0:
print("Starting on row {}".format(args.start_row))
df = df[args.start_row:]
if args.end_row != 0:
print("Will stop on row {}".format(args.end_row))
df = df[:args.end_row]
if not HUNTER_API_KEY:
print("Hunter API Key missing. Exiting.")
sys.exit(1)
hunter = PyHunter(HUNTER_API_KEY)
tally = len(df)
# Just in case there are duplicate domains we don't want to API call twice
df = df.drop_duplicates(subset=['Domain'])
for index, row in df.iterrows():
domain = row['Domain']
# validators.domain does exactly that - nifty little tool
# also we only want to lookup unique domains
if not validators.domain(
domain) and domain != 'wikipedia.org' and domain != '4icu.org':
print("{} is an invalid domain. Skipping.".format(domain))
break
print("Processing {} ({}/{})".format(domain, index - args.start_row,
tally))
# Had to remove limit=100 as it broke the client
try:
results = hunter.domain_search(domain, emails_type='personal')
except requests.exceptions.HTTPError as e:
print("Received error: {}".format(e))
break
normalized = json_normalize(results['emails'])
normalized['org'] = row['Firm']
normalized.to_csv(args.output_file,
mode='a',
header=1,
encoding='utf-8')
print(normalized.columns)
parser.add_argument(
"-fnm",
help="Find multiple names based on domain and persons name.",
action="store_true")
parser.add_argument(
"-fe",
help="Find all email addresses associated with all domains in a text file",
action="store_true")
parser.add_argument("-v", help="Verify an email address", action="store_true")
parser.add_argument("-c",
help="Check how many calls left",
action="store_true")
args = parser.parse_args()
hunter = PyHunter('CHANGE TO YOUR API KEY FROM HUNTER.IO')
results = hunter.domain_search('YOURDOMAINNAME.com')
if (args.fe):
infile = input("Location of URLs file..")
outfile = input("Location of output text file..")
fopen = open(outfile, 'w')
with open(infile) as f:
for i in f:
x = i.rstrip('\n')
url = x
print(url)
results = hunter.domain_search(url)
printed = json.dumps(results)
fopen.write(printed)
fopen.close()
elif (args.fns):
from pyhunter import PyHunter
from settings import HUNTERIO_API_KEY
hunter = PyHunter(HUNTERIO_API_KEY)
if __name__ == '__main__':
result = hunter.domain_search(domain='mandmpestcontrol.com', limit=10)
from pyhunter import PyHunter
#from reverseip import ReverseIP as rip
import os
import csv
import re
hunter = PyHunter('Enter key here')
Web_Dom = input('Enter The Name of the website: ')
Temp = hunter.domain_search(Web_Dom)
Temp1 = Temp['emails']
for i in range(0, len(Temp1)):
temp2 = Temp1[i]
print(temp2['value'])
Choice = int(
input(
"\n1.Do you want to save in a text file \n2.Do you want to save it in a spreadsheet\n"
))
while Choice > 2 or Choice <= 0:
print('Please Enter either 1 or 2 ')
Choice = int(
input(
"\n1.Do you want to save in a text file \n2. Do you want to save it in a spreadsheet\n"
))
if (Choice == 1):
file = open(str(Web_Dom + ".txt"), 'w')
for i in range(0, len(Temp1)):
temp2 = Temp1[i]
file.write(temp2['value'])