update notes

notes.md

@@ -8,16 +8,9 @@
   * ~~ignore any links which aren't to pages~~
   * better url checking to get bare domain
   * remove trailing slash from any discovered url
-  * investigate lxml parser
+  * ~~investigate lxml parser~~
   * ~~remove base url from initial urls with and without trailing slash~~
   * investigate using [tldextract](https://github.com/john-kurkowski/tldextract) to match urls
   * ~~implement parsing of [robots.txt](http://docs.w3cub.com/python~3.6/library/urllib.robotparser/)~~
   * investigate [gzip encoding](https://stackoverflow.com/questions/36383227/avoid-downloading-images-using-beautifulsoup-and-urllib-request)
-
-
-```
-text/html; charset=utf-8
-application/xhtml+xml
-'WebPage' object has no attribute 'source'
-'WebPage' object has no attribute 'discovered_hrefs'
-```
+  * implement some kind of progress display

utils/helpers.py

@@ -53,6 +53,8 @@ class WebPage(object):
         self.url = url
         self.base_url = base_url
         self.robots = robots
+        self.source = None
+        self.urls_to_crawl = set()
 
 
     def get_source(self):
@@ -75,7 +77,7 @@ class WebPage(object):
         '''
         hrefs = set()
 
-        soup = BeautifulSoup(self.source, 'lxml') # handle no source
+        soup = BeautifulSoup(self.source, 'lxml')
         links = soup.find_all('a', href=True)
 
         for link in links:
@@ -92,7 +94,6 @@ class WebPage(object):
         Iterate through the list of discovered URLs and add them to the
         pool if they start with the base URL.
         '''
-        self.urls_to_crawl = set()
 
         for url in self.discovered_hrefs: #handle no hrefs found
             if url.startswith(self.url):
@@ -112,8 +113,8 @@ class WebPage(object):
     def run(self):
         try:
             self.get_source()
-        except Exception as e:
-            print(e)
+        except Exception:
+            pass
 
         if self.source:
             self.find_links()