- removed contrib/adaptors.py

- display adaptor name when an exception raises inside the adaptor
pipeline
- add debug parameter to item attribute method to display input/output
of each adaptor

--HG--
extra : convert_revision : svn%3Ab85faa78-f9eb-468e-a121-7cced6da292c%40206

scrapy/trunk/scrapy/contrib/adaptors.py

@@ -1,67 +0,0 @@
-"""
-Generic Adaptors for item adaptation pipe. Performs tasks
-usually needed by most cases
-"""
-
-import re
-
-from scrapy.item.models import BaseAdaptor
-from scrapy.utils.python import flatten, unique
-from scrapy.xpath import XPathSelector
-from scrapy.utils.misc import unquote_html, location_str
-from scrapy.conf import settings
-
-class ExtendedAdaptor(BaseAdaptor):
-
-    def do(self, function, a, *args, **kwargs):
-        """Executes an adaptor printing a lot of useful debugging info."""
-    
-        debug = kwargs.get('debug')
-        fname = function.__name__
-    
-        if debug:
-            print repr(kwargs)
-            print "  %07s | input >" % fname, location_str(a)
-        a = function(a, *args, **kwargs)
-        if debug:
-            print "  %07s | output>" % fname, a
-    
-        return a
-        
-class ExtractAdaptor(ExtendedAdaptor):
-
-    def function(self, location, **pipeargs):
-        return self.do(self.extract, location, **pipeargs)
-    
-    def extract(self, location, **kwargs):
-        """Extract a list of strings from the location passed.
-        Receives a list of XPathSelectors or an XPathSelector,
-        or a list of strings or a string.
-        
-        Return a list of strings extracted.
-
-        This function *always* returns a list.
-        """
-        if not location:
-            return []
-        if isinstance(location, (list, tuple)):
-            strings = flatten([self.extract(o, **kwargs) for o in location])
-            if kwargs.get('remove_dupes', False):
-                strings = unique(strings)
-            if kwargs.get('first', False):
-                return strings[:1]
-            else:
-                return strings
-        # XPathSelector
-        elif isinstance(location, XPathSelector):
-            strings = [location.extract()]
-        # Strings
-        elif isinstance(location, unicode):
-            strings = [unquote_html(location, keep_reserved=True)]
-        elif isinstance(location, str):
-            encoding = kwargs.get("encoding", settings.get('DEFAULT_DATA_ENCODING'))
-            strings = [unquote_html(unicode(location, encoding), keep_reserved=True)]
-        else:
-            raise TypeError, "unsupported location type: %s" % type(location)
-
-        return strings

scrapy/trunk/scrapy/item/adaptors.py

@@ -1,4 +1,6 @@
 import re
+from traceback import format_exc
+from scrapy.core import log
 
 class DuplicatedAdaptorName(Exception): pass
 
@@ -67,7 +69,7 @@ class AdaptorPipe:
             self.__adaptorspipe.insert(pos, adaptor)
             return pos
 
-    def execute(self, attrname, value, **pipeargs):
+    def execute(self, attrname, value, debug=False, **pipeargs):
         """
         Execute pipeline for attribute name "attrname" and value "value".
         Pass the given pipeargs to each adaptor function in the pipe.
@@ -85,6 +87,17 @@ class AdaptorPipe:
             else:
                 adapt = True
             if adapt:
-                value = adaptor.function(value, **pipeargs)
+                try:
+                    if debug:
+                        print "pipeargs: %s" % repr(pipeargs)
+                        print "  %07s | input >" % adaptor.name, repr(value)
+                    value = adaptor.function(value, **pipeargs)
+                    if debug:
+                        print "  %07s | output>" % adaptor.name, repr(value)
 
+                except Exception, e:
+                    print "Error in '%s' adaptor. Traceback text:" % adaptor.name
+                    print format_exc()
+                    return
+                    
         return value