live rewrite: catch errors from live rewrite and raise a new LiveResourceError with a 400 error code,

indicating bad request for live resource. Add test for invalid live rewrite requests

Author: ikreymer

CHANGES.rst

@@ -1,9 +1,11 @@
 pywb 0.5.0 changelist
 ~~~~~~~~~~~~~~~~~~~~~
 
+* Catch live rewrite errors and display more friendly pywb error message.
+
 * LiveRewriteHandler and WBHandler refactoring: LiveRewriteHandler now supports a root search page html template.
 
-* Proxy mode option: 'unaltered_replay' to proxy archival data with no modifications (no banner, no server or client side rewriting)
+* Proxy mode option: 'unaltered_replay' to proxy archival data with no modifications (no banner, no server or client side rewriting).
 
 * Fix client side rewriting (wombat.js) for proxy mode: only rewrite https -> http in absolute urls.
 
@@ -13,7 +15,7 @@ pywb 0.5.0 changelist
 
   The handler, specified via the ``fallback`` option, can be the name of any other replay handler. Typically, it can be used with a live rewrite handler to fetch missing content from live instead of showing a 404.
 
-* Live Rewrite can now be included as a 'collection type' in a pywb deployment by setting index path to ``$liveweb``
+* Live Rewrite can now be included as a 'collection type' in a pywb deployment by setting index path to ``$liveweb``.
 
 * ``live-rewrite-server`` has optional ``--proxy host:port`` param to specify a loading live web data through an HTTP/S proxy, such as for use with a recording proxy.
 

pywb/cdx/cdxserver.py

@@ -58,7 +58,7 @@ def _check_cdx_iter(self, cdx_iter, query):
                 return self.load_cdx(**fuzzy_query_params)
 
         msg = 'No Captures found for: ' + query.url
-        raise NotFoundException(msg)
+        raise NotFoundException(msg, url=query.url)
 
     def _calc_search_keys(self, query):
         return calc_search_range(url=query.url,

pywb/webapp/live_rewrite_handler.py

@@ -6,6 +6,14 @@
 
 from replay_views import RewriteLiveView
 
+from pywb.utils.wbexception import WbException
+
+
+#=================================================================
+class LiveResourceException(WbException):
+    def status(self):
+        return '400 Bad Live Resource'
+
 
 #=================================================================
 class RewriteHandler(SearchPageWbUrlHandler):
@@ -17,7 +25,13 @@ def __call__(self, wbrequest):
         if wbrequest.wb_url_str == '/':
             return self.render_search_page(wbrequest)
 
-        return self.rewrite_view(wbrequest)
+        try:
+            return self.rewrite_view(wbrequest)
+
+        except Exception as exc:
+            url = wbrequest.wb_url.url
+            msg = 'Could not load the url from the live web: ' + url
+            raise LiveResourceException(msg=msg, url=url)
 
     def __str__(self):
         return 'Live Web Rewrite Handler'

tests/test_live_rewriter.py

@@ -23,4 +23,12 @@ def test_live_rewrite_frame(self):
         assert '<iframe ' in resp.body
         assert 'src="/rewrite/mp_/http://example.com/"' in resp.body
 
+    def test_live_invalid(self):
+        resp = self.testapp.get('/rewrite/mp_/http://abcdef', status=400)
+        assert resp.status_int == 400
+
+    def test_live_invalid_2(self):
+        resp = self.testapp.get('/rewrite/mp_/@#$@#$', status=400)
+        assert resp.status_int == 400
+