├── README.md
├── demo.py
└── linkedin.py
/README.md:
--------------------------------------------------------------------------------
1 | # LinkedIn Email Scraper
2 | A python class that can scrape LinkedIn profiles for emails. Developed by Tufayel_LUS
3 |
4 | # Prerequisites
5 | 1. Python any version
6 | 2. Installation of below module using command
7 | pip install requests
8 | 3. Account in LinkedIn for accessing private profiles
9 |
10 | # Usage
11 | Refer to demo.py for usage reference. You can modify it as you like. You can import the linkedin.py class file or modify it as per your needs.
12 |
13 | # Example Code For Guest Access
14 | client = LinkedIn()
15 | client.singleScan(url_to_profile)
16 |
--------------------------------------------------------------------------------
/demo.py:
--------------------------------------------------------------------------------
1 | from linkedin import LinkedIn
2 | email = "someone@example.com" #set username
3 | password = "example_password" #set password
4 | target_profile = "https://www.linkedin.com/in/tufayel-ahmed-cse/" #set target profile url
5 | client = LinkedIn()
6 | if client.login(email, password):
7 |
8 | #for single profile
9 | print(client.singleScan(target_profile))
10 |
11 | #for bulk list
12 | #profiles = ["PROFILE_URL_1","PROFILE_URL_2"]
13 | #print(client.bulkScan(target_profile))
14 | else:
15 | print("Login Failed, please recheck login credentials")
16 |
--------------------------------------------------------------------------------
/linkedin.py:
--------------------------------------------------------------------------------
1 | import requests
2 | import re
3 |
4 | class LinkedIn:
5 |
6 | def __init__(self):
7 | self.s = requests.Session()
8 | self.headers = {
9 | "user-agent": "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36 OPR/67.0.3575.97"
10 | }
11 | def login(self,email,password):
12 | try:
13 | sc = self.s.get("https://www.linkedin.com/login", headers=self.headers).text
14 | except:
15 | return False
16 | csrfToken = sc.split('csrfToken" value="')[1].split('"')[0]
17 | sid = sc.split('sIdString" value="')[1].split('"')[0]
18 | pins = sc.split('pageInstance" value="')[1].split('"')[0]
19 | lcsrf = sc.split('loginCsrfParam" value="')[1].split('"')[0]
20 | data = {
21 | 'csrfToken': csrfToken,
22 | 'session_key': email,
23 | 'ac': '2',
24 | 'sIdString': sid,
25 | 'parentPageKey': 'd_checkpoint_lg_consumerLogin',
26 | 'pageInstance': pins,
27 | 'trk': 'public_profile_nav-header-signin',
28 | 'authUUID': '',
29 | 'session_redirect': 'https://www.linkedin.com/feed/',
30 | 'loginCsrfParam': lcsrf,
31 | 'fp_data': 'default',
32 | '_d': 'd',
33 | 'showGoogleOneTapLogin': 'true',
34 | 'controlId': 'd_checkpoint_lg_consumerLogin-login_submit_button',
35 | 'session_password': password,
36 | 'loginFlow': 'REMEMBER_ME_OPTIN'
37 | }
38 | try:
39 | after_login = self.s.post("https://www.linkedin.com/checkpoint/lg/login-submit",headers=self.headers,data=data).text
40 | except:
41 | return False
42 | is_logged_in = after_login.split('')[1].split('')[0]
43 | if is_logged_in == "LinkedIn":
44 | return True
45 | else:
46 | return False
47 |
48 | def bulkScan(self, profiles):
49 | all_emails = []
50 | for profile in profiles:
51 | profile = profile + "/detail/contact-info/"
52 | sc = self.s.get(profile, headers=self.headers, allow_redirects=True).text
53 | emails_found = re.findall('[a-zA-Z0-9\.\-\_i]+@[\w.]+',sc)
54 | all_emails.extend(emails_found)
55 | return all_emails
56 |
57 | def singleScan(self, profile):
58 | profile = profile + "/detail/contact-info/"
59 | sc = self.s.get(profile, headers=self.headers, allow_redirects=True).text
60 | emails_found = re.findall('[a-zA-Z0-9\.\-\_i]+@[\w.]+',sc)
61 | return emails_found
62 |
--------------------------------------------------------------------------------