added more tests

async_crawler.py

@@ -24,6 +24,15 @@ from utils.helpers import RobotsTxt, AsyncCrawler, standardise_url
 def sanity_checks(url=None):
     '''
     Runs some basic sanity checks before the crawler is initialised.
+
+    Accepts:
+      url: the root URL to be crawled.
+
+    Returns:
+      baseurl: a validated and cleaned version of the initial URL.
+              (type=string)
+      robots: an object which allows us to query whether a site may be crawled.
+              (type=RobotsTxt)
     '''
     # ensure we have a sensible URL to work with
     baseurl = standardise_url(url=url)
@@ -41,6 +50,11 @@ def sanity_checks(url=None):
 def render_sitemap(base_url=None, crawled_urls=None, runtime=None):
     '''
     Renders the sitemap to an HTML file.
+
+    Accepts:
+        base_url:
+        crawled_urls:
+        runtime:
     '''
     urlcount = len(crawled_urls)
     sorted_urls = sorted(crawled_urls)

test_helpers.py

@@ -1,34 +1,54 @@
 #!/usr/bin/env python
 
 import unittest
-from utils.helpers import (sanitise_url)
+from utils.helpers import (RobotsTxt, standardise_url)
+
+class TestRobots(unittest.TestCase):
+
+    base_url = 'http://eu.httpbin.org'
+
+    test_paths = (('/', True), ('/deny', False))
+
+    robots = RobotsTxt(base_url=base_url)
+
+    def test_robots_txt_deny(self):
+        '''
+        Asserts result is True or False.
+        '''
+        for path, allowed in self.test_paths:
+            result = self.robots.check(url=path)
+            self.assertIs(result, allowed)
+
 
 class TestUrls(unittest.TestCase):
 
+    base_url = 'http://eu.httpbin.org'
+
     base_url_list = (('eu.httpbin.org', 'http://eu.httpbin.org'),
-                     ('www.simonweald.com', 'http://www.simonweald.com'),
+                     ('http://eu.httpbin.org/', 'http://eu.httpbin.org'),
-                     ('http://www.github.com/', 'http://www.github.com'),
+                     ('https://eu.httpbin.org', 'https://eu.httpbin.org'))
-                     ('https://www.github.com', 'https://www.github.com'))
 
-    urls_to_clean = (('https://www.github.com/', 'https://www.github.com/'),
+    urls_to_clean = (('http://eu.httpbin.org', 'http://eu.httpbin.org'),
-                     ('https://github.com/?foo=bar', 'https://github.com/'),
+                     ('http://eu.httpbin.org/some/path/', 'http://eu.httpbin.org/some/path/'),
-                     ('https://github.com/#anchor', 'https://github.com/'))
+                     ('http://eu.httpbin.org/index.html','http://eu.httpbin.org/index.html'),
+                     ('http://eu.httpbin.org/index.html?foo=bar', 'http://eu.httpbin.org/index.html'),
+                     ('http://eu.httpbin.org/index.html#anchor', 'http://eu.httpbin.org/index.html'))
 
-
+    def test_standardise_base_url(self):
-    def test_sanitise_base_url(self):
         '''
-        Tests whether a URL's protocol can be discovered if not provided.
+        Tests whether a base URL can be standardised to the format
+        proto://[sub].domain.tld.
         '''
         for url, target in self.base_url_list:
-            result = sanitise_url(url, base_url=True)
+            result = standardise_url(url)
             self.assertEqual(result, target)
 
-    def test_sanitise_url(self):
+    def test_standardise_url(self):
         '''
-        Tests whether a URL's protocol can be discovered if not provided.
+        Ensure that fragments/anchors etc are stripped.
         '''
         for url, target in self.urls_to_clean:
-            result = sanitise_url(url)
+            result = standardise_url(url, base_url=self.base_url)
             self.assertEqual(result, target)
 
 

utils/helpers.py

@@ -58,7 +58,7 @@ class AsyncCrawler(object):
         async with self.semaphore:
             async with self.client_session.head(url, timeout=5) as head:
                 try:
-                    data = await head.read()
+                    _ = await head.read()
                 except Exception as e:
                     print(e)
             if 'text/html' in head.headers['Content-Type']:
@@ -130,7 +130,7 @@ class AsyncCrawler(object):
         print('Crawling: {0}'.format(self.baseurl))
         while len(to_crawl) > 0:
             discovered_urls = await self.run(urls=to_crawl)
-            # empty toe crawl list and then add all newly discovered URLs for
+            # empty to_crawl list and then add all newly discovered URLs for
             # the next iteration.
             to_crawl.clear()
             to_crawl.extend(discovered_urls)