Merge pull request #292 from chrissparksnj/master

added search links linkedin module

tests/discovery/test_linkedin_links.py

@@ -0,0 +1,18 @@
+#!/usr/bin/env python3
+# coding=utf-8
+from theHarvester.discovery import linkedinsearch
+import pytest
+
+
+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()

theHarvester/__main__.py

@@ -34,12 +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, exalead, github-code, google,
+                        dogpile, duckduckgo, github-code, google,
                         hunter, intelx,
-                        linkedin, netcraft, securityTrails, threatcrowd,
-                        trello, twitter, vhost, virustotal, yahoo''')
-    args = parser.parse_args()
+                        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()
@@ -282,6 +283,23 @@ def start():
                         for user in sorted(list(set(people))):
                             print(user)
 
+                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()
+                    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')
                     from theHarvester.discovery import netcraft

theHarvester/discovery/linkedinsearch.py

@@ -34,6 +34,10 @@ 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 links.links_linkedin()
+
     def process(self):
         while self.counter < self.limit:
             self.do_search()

theHarvester/lib/core.py

@@ -77,6 +77,7 @@ class Core:
                             'hunter',
                             'intelx',
                             'linkedin',
+                            'linkedin_links',
                             'netcraft',
                             'securityTrails',
                             'threatcrowd',

theHarvester/parsers/myparser.py

@@ -77,11 +77,20 @@ class Parser:
         hostnames = self.unique()
         return hostnames
 
+    def links_linkedin(self):
+        reg_links = re.compile(r"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', '')