getnames/getnames.py at master · rtandr01d/getnames · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
#!/usr/bin/env python3

import bs4
import requests
import argparse
import sys
import re

###python3 getname.py -f file.txt -e <fn>.<ln>@email.com

parser = argparse.ArgumentParser(description='Create emails based on a google search result')
parser.add_argument('-c', '--company', help='Name of target organization', required=True)
parser.add_argument('-e', '--emailformat', help='Format you would like the email in. e.g. <fn>.<ln>@gmail.com', required=True)
parser.add_argument('-o', '--outfile', help='File to write output to')
args = parser.parse_args()

if args.outfile:
  outfile = open(sys.argv[6], "w")


fname = ""
lname = ""

def returnformat(fname, lname):
  format = sys.argv[4]
  format = re.split(r"[<>]", format)
  if format[2] == ".":
    if format[1] == "fn":
      if format[3] == "ln":
        email = fname + format[2] + lname + format[4]
        return email
      if format[3] == "li":
        email = fname + format[2] + lname[0] + format[4]
        return email
    if format[1] == "fi":
      if format[3] == "ln":
        email = fname[0] + format[2] + lname + format[4]
        return email
      if format[3] == "li":
        email = fname[0] + format[2] + lname[0] + format[4]
        return email
    if format[1] == "ln":
      if format[3] == "fn":
        email = lname + format[2] + fname + format[4]
        return email
      if format[3] == "fi":
        email = lname + format[2] + fname[0] + format[4]
        return email
    if format[1] == "li":
      if format[3] == "fn":
        email = lname[0] + format[2] + fname + format[4]
        return email
      if format[3] == "fi":
        email = lname[0] + format[2] + fname[0] + format[4]
        return email
  else:
    if format[1] == "fn":
      if format[3] == "ln":
        email = fname + lname + format[4]
        return email
      if format[3] == "li":
        email = fname + lname[0] + format[4]
        return email
    if format[1] == "fi":
      if format[3] == "ln":
        email = fname[0] + lname + format[4]
        return email
      if format[3] == "li":
        email = fname[0] + lname[0] + format[4]
        return email
    if format[1] == "ln":
      if format[3] == "fn":
        email = lname + fname + format[4]
        return email
      if format[3] == "fi":
        email = lname + fname[0] + format[4]
        return email
    if format[1] == "li":
      if format[3] == "fn":
        email = lname[0] + fname + format[4]
        return email
      if format[3] == "fi":
        email = lname[0] + fname[0] + format[4]
        return email

# need to get rid of common false positives
def prune(email):
  bnames = ['Manager', 'manager', 'Analyst', 'analyst', 'Tax', 'tax', 'Partner', 'partner', 'United', 'united', 'State', 'state', 'Region', 'region', 'Consult', 'consult', 'Officer', 'officer', 'Audit', 'audit', 'Service', 'service']
  for bword in bnames:
    if(bword in email):
      return

  if args.outfile:
    outfile.write(email)
    outfile.write('\n')
  else:
    print(pruned_email)


def main():
  # adding a loop to run throuhg multiple pages of google results
  i=0
  while(i<500):
    url = 'https://google.com/search?q=site:linkedin.com%20"' + sys.argv[2] + '"&num=100&start=' + str(i) + ''
    request_result=requests.get( url )
    soup = bs4.BeautifulSoup(request_result.text, "html.parser")
    output = re.findall(r'[a-zA-Z]{1,7} [a-zA-Z]{1,7} -', soup.prettify())

    for line in output:
      splitline = line.split(" ")
      fname = splitline[0]
      lname = splitline[1]
      email = returnformat(fname, lname)
      prune(email)
    i=i+100


if __name__ == "__main__":
    main()