use requests, cope with site timeouts

screenless/bureau/publications/publications.py

@@ -124,13 +124,16 @@ class Publications(Bureau):
         else:
             url = url.decode()
 
-        # download
+        # download page with requests
         headers = {'User-Agent': 'Mozilla/5.0'}
-        req = urllib.request.Request(url, None, headers)
-        urldata = urllib.request.urlopen(req)
+        try:
+            resp = requests.get(url, timeout=20.0, headers=headers)
+        except requests.ReadTimeout:
+            self.log.warning("Timeout reading RSS feed %s", url)
+            return  # TODO: do we need to spit out an error?
 
         # re-render with readability
-        doc = readability.Document(urldata.read(),
+        doc = readability.Document(resp.text,
                                    url=url)
         timestamp = datetime.now().strftime("Sourced %d %B, %Y at %H:%M")
         html = lxml.html.document_fromstring(doc.summary())
@@ -175,7 +178,7 @@ class Publications(Bureau):
             try:
                 resp = requests.get(url, timeout=20.0)
             except requests.ReadTimeout:
-                self.log("Timeout reading RSS feed %s", url)
+                self.log.warning("Timeout reading RSS feed %s", url)
                 continue
 
             feed_data = io.BytesIO(resp.content)