add some basic tests

test_helpers.py

@@ -1,37 +1,35 @@
 #!/usr/bin/env python
 
 import unittest
-from utils.helpers import (clean_base_url)
+from utils.helpers import (sanitise_url)
 
 class TestUrls(unittest.TestCase):
 
-    base_url = "github.com"
-
     base_url_list = (('eu.httpbin.org', 'http://eu.httpbin.org'),
                      ('www.simonweald.com', 'http://www.simonweald.com'),
                      ('http://www.github.com/', 'http://www.github.com'),
                      ('https://www.github.com', 'https://www.github.com'))
 
-    valid_urls = ["https://www.github.com", "http://www.github.com",
-                  "github.com", "/some/url/", "index.html"]
+    urls_to_clean = (('https://www.github.com/', 'https://www.github.com/'),
+                     ('https://github.com/?foo=bar', 'https://github.com/'),
+                     ('https://github.com/#anchor', 'https://github.com/'))
 
 
-    def test_clean_base_url(self):
+    def test_sanitise_base_url(self):
         '''
         Tests whether a URL's protocol can be discovered if not provided.
         '''
         for url, target in self.base_url_list:
-            result = clean_base_url(url)
+            result = sanitise_url(url, base_url=True)
             self.assertEqual(result, target)
 
-    # def test_url_validation(self):
-    #     '''
-    #     Passes when given a valid URL. A valid URL is qualified
-    #     by being local to the domain to be crawled.
-    #     '''
-    #     for url in self.valid_urls:
-    #         result = url_validation(self.base_url, url)
-    #         self.assertTrue(result)
+    def test_sanitise_url(self):
+        '''
+        Tests whether a URL's protocol can be discovered if not provided.
+        '''
+        for url, target in self.urls_to_clean:
+            result = sanitise_url(url)
+            self.assertEqual(result, target)
 
 
 if __name__ == '__main__':

utils/helpers.py

@@ -140,6 +140,9 @@ class RobotsTxt(object):
     '''
 
     def __init__(self, base_url=None):
+        '''
+        Manually retrieve robots.txt to allow us to set the user-agent.
+        '''
         self.base_url = base_url
         self.headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:61.0) Gecko/20100101 Firefox/61.0'}