Added to_dict

TESTING.md

@@ -0,0 +1,6 @@
+# Run the following to run unit tests
+`python -m unittest`
+
+
+# Integration Tests
+`python ./test/scrape_person.py`

linkedin_scraper/person.py

@@ -1,19 +1,24 @@
-import requests
+from typing import Dict, Any
+
 from selenium import webdriver
 from selenium.webdriver.common.by import By
 from selenium.webdriver.support.ui import WebDriverWait
 from selenium.webdriver.support import expected_conditions as EC
 from selenium.common.exceptions import NoSuchElementException
 from .objects import Experience, Education, Scraper, Interest, Accomplishment, Contact
+from .utils import to_dict
 import os
 from linkedin_scraper import selectors
 
-
 class Person(Scraper):
 
     __TOP_CARD = "pv-top-card"
     __WAIT_FOR_ELEMENT_TIMEOUT = 5
 
+
+    linkedin_url: str
+    name: str
+
     def __init__(
         self,
         linkedin_url=None,
@@ -392,3 +397,14 @@ def __repr__(self):
             acc=self.accomplishments,
             conn=self.contacts,
         )
+
+    def to_dict(self) -> Dict[str, Any]:
+        return to_dict({
+            'name': self.name,
+            'about': self.about,
+            'experiences': self.experiences,
+            'educations': self.educations,
+            'interests': self.interests,
+            'accomplishments': self.accomplishments,
+            'contacts': self.contacts,
+        })

linkedin_scraper/utils.py

@@ -0,0 +1,40 @@
+"""
+Utilities
+"""
+import io
+from typing import Dict, Any, List
+from dataclasses import is_dataclass, asdict
+
+
+def custom_asdict(obj):
+    # Custom asdict function that excludes _io.BufferedWriter objects
+    obj_dict = {}
+    for field in obj.__dataclass_fields__.values():
+        value = getattr(obj, field.name)
+        if not isinstance(value, io.BufferedWriter):
+            obj_dict[field.name] = to_dict(value)
+    return obj_dict
+
+def to_dict(obj) -> Dict[str, Any]:    
+    if is_dataclass(obj):
+        # If the object is a data class, use asdict to convert it to a dictionary
+        return to_dict(custom_asdict(obj))
+
+    if isinstance(obj, (int, str, bool, float)):
+        # If the object is a basic type, return it as is
+        return obj
+
+    if isinstance(obj, list):
+        # If the object is a list, recursively call to_dict on its elements
+        return [to_dict(item) for item in obj]
+
+    if isinstance(obj, dict):
+        # If the object is a dictionary, recursively call to_dict on its values
+        return {key: to_dict(value) for key, value in obj.items() if not key.startswith('_')}
+
+    if hasattr(obj, '__dict__'):
+        # If the object has a __dict__ attribute, recursively call to_dict on its attributes
+        return {key: to_dict(value) for key, value in obj.__dict__.items() if not key.startswith('_')}
+
+    # If none of the above conditions match, return None (or handle as needed)
+    return None

test/__init__.py

@@ -0,0 +1,6 @@
+import os
+import sys
+
+current_dir = os.path.dirname(os.path.abspath(__file__))
+root_dir = os.path.dirname(current_dir)
+sys.path.append(root_dir)  # Add the parent directory to sys.path

test/scrape_person.py

@@ -1,5 +1,10 @@
+# Integration test
+import __init__
 from linkedin_scraper import Person
 
 rick_fox = Person("https://www.linkedin.com/in/rifox?trk=pub-pbmap")
+rick_fox.to_dict()
 iggy = Person("https://www.linkedin.com/in/andre-iguodala-65b48ab5")
+iggy.to_dict()
 Anirudra = Person("https://in.linkedin.com/in/anirudra-choudhury-109635b1")
+Anirudra.to_dict()

test/test_utils.py

@@ -0,0 +1,51 @@
+"""
+Test Utils
+"""
+from typing import Dict, Any
+from linkedin_scraper.utils import to_dict
+from linkedin_scraper.objects import Contact, Institution
+from dataclasses import dataclass
+import unittest
+
+@dataclass
+class SampleClass:
+    _test_var: str
+    contact: Contact
+    institution: Institution
+    def to_dict(self) -> Dict[str, Any]:
+        return to_dict(self)
+
+class TestUtils(unittest.TestCase):
+    """
+    Test Utils
+    """
+    def test_to_dict(self):
+        test_class = SampleClass(
+            _test_var = 'test var',
+            contact=Contact(
+                name='test_name'
+            ),
+            institution=Institution(
+                institution_name= 'test_place'
+            )
+        )
+
+        test_class_dict = to_dict(test_class)
+        expected_output = {
+            'contact': {'name':'test_name',
+                        'occupation': None,
+                        'url': None},
+            'institution': {
+                'company_size': None,
+                'founded': None,
+                'headquarters': None,
+                'industry': None,
+                'institution_name': 'test_place',
+                'linkedin_url': None,
+                'type': None,
+                'website': None
+            }
+        }
+        self.assertEqual(test_class_dict, expected_output)
+if __name__ == "__main__":
+    unittest.main()