better exception handling, specific status codes for exceptions,

detect access control and not found exceptions more consistently

pywb/archivalrouter.py

@@ -19,10 +19,4 @@ class ArchivalRequestRouter:
         handler, wbrequest = self.parse_request(env)
         return handler.run(wbrequest)
 
-    def handle_exception(self, env, exc):
-        return WbResponse.text_response('Error: ' + str(exc), status = '400 Bad Request')
-
-    def handle_not_found(self, env):
-        return WbResponse.text_response('Not Found: ' + env['REQUEST_URI'], status = '404 Not Found')
-
 

pywb/indexreader.py

@@ -1,5 +1,6 @@
 import urllib
 import urllib2
+import wbexceptions
 
 class RemoteCDXServer:
     """
@@ -27,17 +28,23 @@ class RemoteCDXServer:
         params.update(**kwvalues)
 
         urlparams = urllib.urlencode(params)
-        request = urllib2.Request(self.serverUrl, urlparams)
-        response = urllib2.urlopen(request)
+
+        try:
+            request = urllib2.Request(self.serverUrl, urlparams)
+            response = urllib2.urlopen(request)
+        except urllib2.HTTPError, e:
+            if e.code == 403:
+                exc_msg = e.read()
+                msg = 'Blocked By Robots' if 'Blocked By Robots' in exc_msg else 'Excluded'
+                raise wbexceptions.AccessException(msg)
+            else:
+                raise e
 
         if parse_cdx:
             return map(CDXCaptureResult, response)
         else:
             return response
 
-class InvalidCDXException(Exception):
-    pass
-
 class CDXCaptureResult:
     CDX_FORMATS = [["urlkey","timestamp","original","mimetype","statuscode","digest","redirect","robotflags","length","offset","filename"],
                    ["urlkey","timestamp","original","mimetype","statuscode","digest","redirect","offset","filename"]]

pywb/utils.py

@@ -0,0 +1,9 @@
+import itertools
+
+def peek_iter(iterable):
+    try:
+        first = next(iterable)
+    except StopIteration:
+        return None
+
+    return itertools.chain([first], iterable)

pywb/wbapp.py

@@ -3,11 +3,14 @@ from archiveurl import archiveurl
 from archivalrouter import ArchivalRequestRouter
 import indexreader
 import json
+import wbexceptions
+import utils
 
 class WBHandler:
     def run(self, wbrequest):
         wburl = archiveurl(wbrequest.wb_url)
-        return WbResponse.text_response(repr(wburl))
+        wbrequest.parsed_url = wburl
+        return WbResponse.text_stream(str(vars(wburl)))
 
 class QueryHandler:
     def __init__(self):
@@ -15,7 +18,6 @@ class QueryHandler:
 
     @staticmethod
     def get_query_params(wburl):
-        print wburl.type
         return {
 
             archiveurl.QUERY:
@@ -37,23 +39,27 @@ class QueryHandler:
 
     def run(self, wbrequest):
         wburl = archiveurl(wbrequest.wb_url)
+        #wburl = wbresponse.body.parsed_url
 
         params = QueryHandler.get_query_params(wburl)
 
-        #parse_cdx = (wburl.mod == 'json')
         cdxlines = self.cdxserver.load(wburl.url, params)
 
-        return WbResponse.text_stream(cdxlines)
+        cdxlines = utils.peek_iter(cdxlines)
+
+        if cdxlines is not None:
+            return WbResponse.text_stream(cdxlines)
+
+        raise wbexceptions.NotFoundException('WB Does Not Have Url: ' + wburl.url)
 
-        #if parse_cdx:
-        #    text = str("\n".join(map(str, cdxlines)))
-        #    text = json.dumps(cdxlines, default=lambda o: o.__dict__)
-        #else:
-        #    text = cdxlines
 
 
 ## ===========
-parser = ArchivalRequestRouter({'/web/': QueryHandler()}, hostpaths = ['http://localhost:9090/'])
+parser = ArchivalRequestRouter(
+    {'/t1/' : WBHandler(),
+     '/t2/' : QueryHandler()
+    },
+    hostpaths = ['http://localhost:9090/'])
 ## ===========
 
 
@@ -63,13 +69,26 @@ def application(env, start_response):
     try:
         response = parser.handle_request(env)
 
+        if not response:
+            raise wbexceptions.NotFoundException(env['REQUEST_URI'] + ' was not found')
+
     except Exception as e:
         last_exc = e
         import traceback
         traceback.print_exc()
-        response = parser.handle_exception(env, e)
-
-    if not response:
-        response = parser.handle_not_found(env)
+        response = handle_exception(env, e)
 
     return response(env, start_response)
+
+def handle_exception(env, exc):
+    if hasattr(exc, 'status'):
+        status = exc.status()
+    else:
+        status = '400 Bad Request'
+
+    return WbResponse.text_response(status + ' Error: ' + str(exc), status = status)
+
+#def handle_not_found(env):
+#    return WbResponse.text_response('Not Found: ' + env['REQUEST_URI'], status = '404 Not Found')
+
+

pywb/wbexceptions.py

@@ -1,8 +1,20 @@
 
 class RequestParseException(Exception):
-    pass
+    def status(_):
+        return '400'
 
 class BadUrlException(Exception):
-    pass
+    def status(_):
+        return '400'
 
+class AccessException(Exception):
+    def status(_):
+        return '403'
 
+class InvalidCDXException(Exception):
+    def status(_):
+        return '500'
+
+class NotFoundException(Exception):
+    def status(_):
+        return '404'

pywb/wbrequestresponse.py

@@ -1,4 +1,3 @@
-
 #WB Request and Response
 
 class WbRequest:
@@ -57,8 +56,8 @@ class WbResponse:
         return WbResponse(status, value = [text], headersList = [('Content-Type', 'text/plain')])
 
     @staticmethod
-    def redir_response(location):
-        return WbResponse('302 Redirect', headersList = [('Location', location)])
+    def redir_response(location, status = '302 Redirect'):
+        return WbResponse(status, headersList = [('Location', location)])
 
     def get_header(self, name):
         name_upp = name.upper()
@@ -72,7 +71,12 @@ class WbResponse:
         #    headersList.append((key, value))
 
         start_response(self.status, self.headersList)
-        return self.body
+
+        if hasattr(self.body, '__iter__'):
+            return self.body
+        else:
+            return [str(self.body)]
+
 
     def __repr__(self):
         return str(vars(self))