use lxml as the parser and only find links on a page if we've got the source

requirements.txt

@@ -4,4 +4,5 @@ certifi==2018.8.13
 chardet==3.0.4
 idna==2.7
 Jinja2==2.10
+lxml==4.2.4
 MarkupSafe==1.0

utils/helpers.py

@@ -75,7 +75,7 @@ class WebPage(object):
         '''
         hrefs = set()
 
-        soup = BeautifulSoup(self.source, 'html.parser') # handle no source
+        soup = BeautifulSoup(self.source, 'lxml') # handle no source
         links = soup.find_all('a', href=True)
 
         for link in links:
@@ -115,15 +115,9 @@ class WebPage(object):
         except Exception as e:
             print(e)
 
-        try:
+        if self.source:
             self.find_links()
-        except Exception as e:
-            print(e)
-
-        try:
             self.parse_urls()
-        except Exception as e:
-            print(e)
 
 
 class RobotsTxt(object):