Support linkedin url for extracting information

README.rst

@@ -25,6 +25,7 @@ Features
 -  Extract degree
 -  Extract designation
 -  Extract company names
+-  Extract linkedin url
 
 Installation
 ============

pyresparser/resume_parser.py

@@ -62,6 +62,7 @@ def __get_basic_details(self):
                     self.__noun_chunks,
                     self.__skills_file
                 )
+        linkedin = utils.extract_linkedin(self.__text)
         # edu = utils.extract_education(
         #               [sent.string.strip() for sent in self.__nlp.sents]
         #       )
@@ -121,6 +122,8 @@ def __get_basic_details(self):
         self.__details['no_of_pages'] = utils.get_number_of_pages(
                                             self.__resume
                                         )
+
+        self.__details['linkedin'] = linkedin
         return
 
 

pyresparser/utils.py

@@ -494,3 +494,17 @@
         if x and 'experience' in x.lower()
     ]
     return x
+
+
+def extract_linkedin(text):
+    '''
+    Helper function to extract linkedin from text
+
+    :param text: plain text extracted from resume file
+    '''
+    linkedin = re.findall(r'([\s]+linkedin.com[^\s]+)', text)
+    if linkedin:
+        try:
+            return linkedin[0][0]
+        except IndexError:
+            return None

test_name.py

@@ -39,3 +39,8 @@ def test_local_name():
 def test_local_phone_number():
     data = get_local_data()
     assert '8087996634' == data['mobile_number']
+
+def test_linkedin_url():
+    data = get_remote_data()
+    # no valid linkedin url yet
+    assert None == data[0]['linkedin']