added option to return linkedin links

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)

theHarvester/discovery/constants.py

@@ -4,6 +4,28 @@
 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

theHarvester/discovery/linkedinsearch.py

@@ -4,7 +4,6 @@
 import requests
 import time
 
-
 class SearchLinkedin:
 
     def __init__(self, word, limit):
@@ -34,9 +33,20 @@ def get_people(self):
         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.')
+
+
+
+
+
+

theHarvester/lib/core.py

@@ -77,6 +77,7 @@ def get_supportedengines():
                             'hunter',
                             'intelx',
                             'linkedin',
+                            'linkedin_links',
                             'netcraft',
                             'securityTrails',
                             'threatcrowd',

theHarvester/parsers/myparser.py

@@ -92,11 +92,22 @@ def hostnames_all(self):
         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', '')