From 4806751470cb186f646335a0c44b4ffdcee1d513 Mon Sep 17 00:00:00 2001
From: csparks <csparksnj@gmail.com>
Date: Fri, 6 Sep 2019 02:57:53 +0000
Subject: [PATCH 01/10] added option to return linkedin links

---
 theHarvester/__main__.py                 | 20 ++++++++++++++++++--
 theHarvester/discovery/constants.py      | 22 ++++++++++++++++++++++
 theHarvester/discovery/linkedinsearch.py | 12 +++++++++++-
 theHarvester/lib/core.py                 |  1 +
 theHarvester/parsers/myparser.py         | 13 ++++++++++++-
 5 files changed, 64 insertions(+), 4 deletions(-)

diff --git a/theHarvester/__main__.py b/theHarvester/__main__.py
index 8d87cf47..ebbcdbb5 100644
--- a/theHarvester/__main__.py
+++ b/theHarvester/__main__.py
@@ -53,9 +53,9 @@ def start():
     parser.add_argument('-c', '--dns-brute', help='perform a DNS brute force on the domain', default=False, action='store_true')
     parser.add_argument('-f', '--filename', help='save the results to an HTML and/or XML file', default='', type=str)
     parser.add_argument('-b', '--source', help='''baidu, bing, bingapi, censys, crtsh, dnsdumpster,
-                        dogpile, duckduckgo, github-code, google, 
+                        dogpile, duckduckgo, github-code, google,
                         hunter, intelx,
-                        linkedin, netcraft, securityTrails, threatcrowd,
+                        linkedin,linkedin_links, netcraft, securityTrails, threatcrowd,
                         trello, twitter, vhost, virustotal, yahoo, all''')
     parser.add_argument('-x', '--exclude', help='exclude options when using all sources', type=str)
     args = parser.parse_args()
@@ -279,6 +279,22 @@ def start():
                         for user in sorted(list(set(people))):
                             print(user)
 
+                elif engineitem == 'linkedin_links':
+                    print('\033[94m[*] Searching Linkedin. \033[0m')
+                    search = linkedinsearch.SearchLinkedin(word, limit)
+                    search.process()
+                    people = search.get_links()
+                    db = stash.stash_manager()
+                    db.store_all(word, people, 'name', 'linkedin')
+
+                    if len(people) == 0:
+                        print('\n[*] No links found Linkedin.\n\n')
+                    else:
+                        print(f'\n[*] Links found: {len(people)}')
+                        print('---------------------')
+                        for user in sorted(list(set(people))):
+                            print(user)
+
                 elif engineitem == 'netcraft':
                     print('\033[94m[*] Searching Netcraft. \033[0m')
                     search = netcraft.SearchNetcraft(word)
diff --git a/theHarvester/discovery/constants.py b/theHarvester/discovery/constants.py
index eeb8dcaf..2be35d84 100644
--- a/theHarvester/discovery/constants.py
+++ b/theHarvester/discovery/constants.py
@@ -4,6 +4,28 @@ import random
 googleUA = 'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36'
 
 
+def splitter(links):
+    """
+    Method that tries to remove duplicates
+    :param links: list of links to remove duplicates from
+    :return: unique-ish list
+    """
+    unique_list = []
+    name_check = []
+    for url in links:
+        tail = url.split("/")[-1]
+        if len(tail) == 2 or tail == "zh-cn":
+            tail = url.split("/")[-2]
+            name = tail.split("-")
+            if len(name) > 1:
+                joined_name = name[0] + name[1]
+            else:
+                joined_name = name[0]
+            if joined_name not in name_check:
+                unique_list.append(url)
+                name_check.append(joined_name)
+    return unique_list
+
 def filter(lst):
     """
     Method that filters list
diff --git a/theHarvester/discovery/linkedinsearch.py b/theHarvester/discovery/linkedinsearch.py
index d59d14fd..7992200d 100644
--- a/theHarvester/discovery/linkedinsearch.py
+++ b/theHarvester/discovery/linkedinsearch.py
@@ -4,7 +4,6 @@ from theHarvester.parsers import myparser
 import requests
 import time
 
-
 class SearchLinkedin:
 
     def __init__(self, word, limit):
@@ -34,9 +33,20 @@ class SearchLinkedin:
         rawres = myparser.Parser(self.totalresults, self.word)
         return rawres.people_linkedin()
 
+    def get_links(self):
+        links = myparser.Parser(self.totalresults, self.word)
+        return splitter(links.links_linkedin())
+
+
     def process(self):
         while self.counter < self.limit:
             self.do_search()
             time.sleep(getDelay())
             self.counter += 100
             print(f'\tSearching {self.counter} results.')
+
+
+
+
+
+
diff --git a/theHarvester/lib/core.py b/theHarvester/lib/core.py
index 66a9ef27..40042bbf 100644
--- a/theHarvester/lib/core.py
+++ b/theHarvester/lib/core.py
@@ -77,6 +77,7 @@ class Core:
                             'hunter',
                             'intelx',
                             'linkedin',
+                            'linkedin_links',
                             'netcraft',
                             'securityTrails',
                             'threatcrowd',
diff --git a/theHarvester/parsers/myparser.py b/theHarvester/parsers/myparser.py
index a63b0612..5958c8d9 100644
--- a/theHarvester/parsers/myparser.py
+++ b/theHarvester/parsers/myparser.py
@@ -92,11 +92,22 @@ class Parser:
         hostnames = self.unique()
         return hostnames
 
+    def links_linkedin(self):
+        reg_links = re.compile("url=https:\/\/www.linkedin.com(.*?)&")
+        self.temp = reg_links.findall(self.results)
+        resul = []
+        for x in self.temp:
+            y = x.replace("url=", "")
+            resul.append("https://www.linkedin.com" + y)
+        return set(resul)
+
     def people_linkedin(self):
         reg_people = re.compile(r'">[a-zA-Z0-9._ -]* \| LinkedIn')
         self.temp = reg_people.findall(self.results)
         resul = []
-        for x in self.temp:
+
+
+        for x in (self.temp):
             y = x.replace(' | LinkedIn', '')
             y = y.replace(' profiles ', '')
             y = y.replace('LinkedIn', '')

From 0e975961f1c01767f6f5fdbb0879ea2756509d4b Mon Sep 17 00:00:00 2001
From: csparks <csparksnj@gmail.com>
Date: Fri, 6 Sep 2019 03:36:22 +0000
Subject: [PATCH 02/10] fixing unintended code overwrite

---
 theHarvester/__main__.py | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/theHarvester/__main__.py b/theHarvester/__main__.py
index 3fc442ac..3093c822 100644
--- a/theHarvester/__main__.py
+++ b/theHarvester/__main__.py
@@ -41,10 +41,6 @@ def start():
                         trello, twitter, vhost, virustotal, yahoo, all''')
     parser.add_argument('-x', '--exclude', help='exclude options when using all sources', type=str)
 
-                        dogpile, duckduckgo, exalead, github-code, google,
-                        hunter, intelx,
-                        linkedin, netcraft, securityTrails, threatcrowd,
-                        trello, twitter, vhost, virustotal, yahoo''')
 
     args = parser.parse_args()
 

From 6740f051fc3db8c34786aaf609a2fb0b5c1cd15a Mon Sep 17 00:00:00 2001
From: csparks <csparksnj@gmail.com>
Date: Fri, 6 Sep 2019 03:46:14 +0000
Subject: [PATCH 03/10] have to remember to fetch, even if its just a week

---
 theHarvester/__main__.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/theHarvester/__main__.py b/theHarvester/__main__.py
index 3093c822..af6df831 100644
--- a/theHarvester/__main__.py
+++ b/theHarvester/__main__.py
@@ -288,6 +288,7 @@ def start():
 
                 elif engineitem == 'linkedin_links':
                     print('\033[94m[*] Searching Linkedin. \033[0m')
+                    from theHarvester.discovery import linkedinsearch
                     search = linkedinsearch.SearchLinkedin(word, limit)
                     search.process()
                     people = search.get_links()

From 06dbea58d021aa804bc613ef5bdd0c7fa82cf248 Mon Sep 17 00:00:00 2001
From: csparks <csparksnj@gmail.com>
Date: Fri, 6 Sep 2019 04:00:05 +0000
Subject: [PATCH 04/10] flake8

---
 theHarvester/__main__.py                 | 3 ---
 theHarvester/discovery/constants.py      | 1 +
 theHarvester/discovery/linkedinsearch.py | 8 +-------
 theHarvester/parsers/myparser.py         | 2 --
 4 files changed, 2 insertions(+), 12 deletions(-)

diff --git a/theHarvester/__main__.py b/theHarvester/__main__.py
index af6df831..a34e5674 100644
--- a/theHarvester/__main__.py
+++ b/theHarvester/__main__.py
@@ -34,16 +34,13 @@ def start():
     parser.add_argument('-c', '--dns-brute', help='perform a DNS brute force on the domain', default=False, action='store_true')
     parser.add_argument('-f', '--filename', help='save the results to an HTML and/or XML file', default='', type=str)
     parser.add_argument('-b', '--source', help='''baidu, bing, bingapi, censys, crtsh, dnsdumpster,
-
                         dogpile, duckduckgo, github-code, google,
                         hunter, intelx,
                         linkedin,linkedin_links, netcraft, securityTrails, threatcrowd,
                         trello, twitter, vhost, virustotal, yahoo, all''')
     parser.add_argument('-x', '--exclude', help='exclude options when using all sources', type=str)
 
-
     args = parser.parse_args()
-
     try:
         db = stash.stash_manager()
         db.do_init()
diff --git a/theHarvester/discovery/constants.py b/theHarvester/discovery/constants.py
index 69510ad2..5f4c55dd 100644
--- a/theHarvester/discovery/constants.py
+++ b/theHarvester/discovery/constants.py
@@ -26,6 +26,7 @@ def splitter(links):
                 name_check.append(joined_name)
     return unique_list
 
+
 def filter(lst):
     """
     Method that filters list
diff --git a/theHarvester/discovery/linkedinsearch.py b/theHarvester/discovery/linkedinsearch.py
index 7992200d..ef774df3 100644
--- a/theHarvester/discovery/linkedinsearch.py
+++ b/theHarvester/discovery/linkedinsearch.py
@@ -4,6 +4,7 @@ from theHarvester.parsers import myparser
 import requests
 import time
 
+
 class SearchLinkedin:
 
     def __init__(self, word, limit):
@@ -37,16 +38,9 @@ class SearchLinkedin:
         links = myparser.Parser(self.totalresults, self.word)
         return splitter(links.links_linkedin())
 
-
     def process(self):
         while self.counter < self.limit:
             self.do_search()
             time.sleep(getDelay())
             self.counter += 100
             print(f'\tSearching {self.counter} results.')
-
-
-
-
-
-
diff --git a/theHarvester/parsers/myparser.py b/theHarvester/parsers/myparser.py
index b7dd7a46..95b3607b 100644
--- a/theHarvester/parsers/myparser.py
+++ b/theHarvester/parsers/myparser.py
@@ -90,8 +90,6 @@ class Parser:
         reg_people = re.compile(r'">[a-zA-Z0-9._ -]* \| LinkedIn')
         self.temp = reg_people.findall(self.results)
         resul = []
-
-
         for x in (self.temp):
             y = x.replace(' | LinkedIn', '')
             y = y.replace(' profiles ', '')

From ef7b2fd1d11d0ab04e18cc19fe63f8b3d784cf18 Mon Sep 17 00:00:00 2001
From: csparks <csparksnj@gmail.com>
Date: Fri, 6 Sep 2019 04:11:55 +0000
Subject: [PATCH 05/10] invalid escape sequence

---
 theHarvester/parsers/myparser.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/theHarvester/parsers/myparser.py b/theHarvester/parsers/myparser.py
index 95b3607b..2fd6f050 100644
--- a/theHarvester/parsers/myparser.py
+++ b/theHarvester/parsers/myparser.py
@@ -78,7 +78,7 @@ class Parser:
         return hostnames
 
     def links_linkedin(self):
-        reg_links = re.compile("url=https:\/\/www.linkedin.com(.*?)&")
+        reg_links = re.compile(r"url=https:\/\/www.linkedin.com(.*?)&")
         self.temp = reg_links.findall(self.results)
         resul = []
         for x in self.temp:

From efa7bf8dab141f28b80cc548f18cde643f6c7bdf Mon Sep 17 00:00:00 2001
From: csparks <csparksnj@gmail.com>
Date: Sat, 7 Sep 2019 00:32:48 +0000
Subject: [PATCH 06/10] fixed unescaped regex, formatted -b options

---
 theHarvester/__main__.py         | 2 +-
 theHarvester/parsers/myparser.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/theHarvester/__main__.py b/theHarvester/__main__.py
index a34e5674..eefeed22 100644
--- a/theHarvester/__main__.py
+++ b/theHarvester/__main__.py
@@ -36,7 +36,7 @@ def start():
     parser.add_argument('-b', '--source', help='''baidu, bing, bingapi, censys, crtsh, dnsdumpster,
                         dogpile, duckduckgo, github-code, google,
                         hunter, intelx,
-                        linkedin,linkedin_links, netcraft, securityTrails, threatcrowd,
+                        linkedin, linkedin_links, netcraft, securityTrails, threatcrowd,
                         trello, twitter, vhost, virustotal, yahoo, all''')
     parser.add_argument('-x', '--exclude', help='exclude options when using all sources', type=str)
 
diff --git a/theHarvester/parsers/myparser.py b/theHarvester/parsers/myparser.py
index 2fd6f050..09c8f825 100644
--- a/theHarvester/parsers/myparser.py
+++ b/theHarvester/parsers/myparser.py
@@ -78,7 +78,7 @@ class Parser:
         return hostnames
 
     def links_linkedin(self):
-        reg_links = re.compile(r"url=https:\/\/www.linkedin.com(.*?)&")
+        reg_links = re.compile(r"url=https:\/\/www\.linkedin.com(.*?)&")
         self.temp = reg_links.findall(self.results)
         resul = []
         for x in self.temp:

From 88e8e88874b91da229bbde3ab76ff9816a2ac3d1 Mon Sep 17 00:00:00 2001
From: csparks <csparksnj@gmail.com>
Date: Sat, 7 Sep 2019 02:58:57 +0000
Subject: [PATCH 07/10] added unit test; removed splitter function since regex
 now handles dupes

---
 tests/discovery/test_linkedin_links.py   | 21 +++++++++++++++++++++
 theHarvester/discovery/constants.py      | 23 -----------------------
 theHarvester/discovery/linkedinsearch.py |  2 +-
 3 files changed, 22 insertions(+), 24 deletions(-)
 create mode 100644 tests/discovery/test_linkedin_links.py

diff --git a/tests/discovery/test_linkedin_links.py b/tests/discovery/test_linkedin_links.py
new file mode 100644
index 00000000..e03f8860
--- /dev/null
+++ b/tests/discovery/test_linkedin_links.py
@@ -0,0 +1,21 @@
+#!/usr/bin/env python3
+# coding=utf-8
+import sys
+sys.path.append("../../")
+from theHarvester.parsers import myparser
+from theHarvester.discovery import linkedinsearch
+import pytest
+from theHarvester.lib import stash
+
+
+class TestGetLinks(object):
+
+    def test_get_links(self):
+        search = linkedinsearch.SearchLinkedin("facebook.com", '100')
+        search.process()
+        links = search.get_links()
+        for link in links:
+            print(link)
+
+if __name__ == '__main__':
+    pytest.main()
diff --git a/theHarvester/discovery/constants.py b/theHarvester/discovery/constants.py
index 5f4c55dd..7549c4c6 100644
--- a/theHarvester/discovery/constants.py
+++ b/theHarvester/discovery/constants.py
@@ -4,29 +4,6 @@ import random
 googleUA = 'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36'
 
 
-def splitter(links):
-    """
-    Method that tries to remove duplicates
-    :param links: list of links to remove duplicates from
-    :return: unique-ish list
-    """
-    unique_list = []
-    name_check = []
-    for url in links:
-        tail = url.split("/")[-1]
-        if len(tail) == 2 or tail == "zh-cn":
-            tail = url.split("/")[-2]
-            name = tail.split("-")
-            if len(name) > 1:
-                joined_name = name[0] + name[1]
-            else:
-                joined_name = name[0]
-            if joined_name not in name_check:
-                unique_list.append(url)
-                name_check.append(joined_name)
-    return unique_list
-
-
 def filter(lst):
     """
     Method that filters list
diff --git a/theHarvester/discovery/linkedinsearch.py b/theHarvester/discovery/linkedinsearch.py
index ef774df3..22a58699 100644
--- a/theHarvester/discovery/linkedinsearch.py
+++ b/theHarvester/discovery/linkedinsearch.py
@@ -36,7 +36,7 @@ class SearchLinkedin:
 
     def get_links(self):
         links = myparser.Parser(self.totalresults, self.word)
-        return splitter(links.links_linkedin())
+        return links.links_linkedin()
 
     def process(self):
         while self.counter < self.limit:

From 7ded50fd95d6cfef2ab4da066cb8eb917ac57041 Mon Sep 17 00:00:00 2001
From: csparks <csparksnj@gmail.com>
Date: Sat, 7 Sep 2019 03:00:22 +0000
Subject: [PATCH 08/10] removed testing imports

---
 tests/discovery/test_linkedin_links.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/tests/discovery/test_linkedin_links.py b/tests/discovery/test_linkedin_links.py
index e03f8860..b748e77b 100644
--- a/tests/discovery/test_linkedin_links.py
+++ b/tests/discovery/test_linkedin_links.py
@@ -1,11 +1,9 @@
 #!/usr/bin/env python3
 # coding=utf-8
-import sys
-sys.path.append("../../")
 from theHarvester.parsers import myparser
 from theHarvester.discovery import linkedinsearch
-import pytest
 from theHarvester.lib import stash
+import pytest
 
 
 class TestGetLinks(object):

From b18983fecb8ade833a714788407d1ace1b3e50cb Mon Sep 17 00:00:00 2001
From: csparks <csparksnj@gmail.com>
Date: Sat, 7 Sep 2019 03:16:56 +0000
Subject: [PATCH 09/10] pylint

---
 tests/discovery/test_linkedin_links.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/discovery/test_linkedin_links.py b/tests/discovery/test_linkedin_links.py
index b748e77b..c1965221 100644
--- a/tests/discovery/test_linkedin_links.py
+++ b/tests/discovery/test_linkedin_links.py
@@ -1,6 +1,5 @@
 #!/usr/bin/env python3
 # coding=utf-8
-from theHarvester.parsers import myparser
 from theHarvester.discovery import linkedinsearch
 from theHarvester.lib import stash
 import pytest
@@ -8,6 +7,7 @@ import pytest
 
 class TestGetLinks(object):
 
+
     def test_get_links(self):
         search = linkedinsearch.SearchLinkedin("facebook.com", '100')
         search.process()

From a2a2e197ecab7f3d1829db1cdbc72801e96d39b7 Mon Sep 17 00:00:00 2001
From: csparks <csparksnj@gmail.com>
Date: Sat, 7 Sep 2019 03:35:59 +0000
Subject: [PATCH 10/10] too many blank lines in test

---
 tests/discovery/test_linkedin_links.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tests/discovery/test_linkedin_links.py b/tests/discovery/test_linkedin_links.py
index c1965221..2dc6f3dc 100644
--- a/tests/discovery/test_linkedin_links.py
+++ b/tests/discovery/test_linkedin_links.py
@@ -1,13 +1,11 @@
 #!/usr/bin/env python3
 # coding=utf-8
 from theHarvester.discovery import linkedinsearch
-from theHarvester.lib import stash
 import pytest
 
 
 class TestGetLinks(object):
 
-
     def test_get_links(self):
         search = linkedinsearch.SearchLinkedin("facebook.com", '100')
         search.process()
@@ -15,5 +13,6 @@ class TestGetLinks(object):
         for link in links:
             print(link)
 
+
 if __name__ == '__main__':
     pytest.main()