added a replace_str param to remove_escape_chars and added remove_escape adaptor using it

scrapy/contrib_exp/adaptors/__init__.py

@@ -1,5 +1,5 @@
 from scrapy.contrib_exp.adaptors.extraction import extract, ExtractImageLinks
-from scrapy.contrib_exp.adaptors.markup import remove_tags, remove_root, unquote
+from scrapy.contrib_exp.adaptors.markup import remove_tags, remove_root, remove_escape, unquote
 from scrapy.contrib_exp.adaptors.misc import to_unicode, clean_spaces, strip, drop_empty, delist, Regex
 from scrapy.contrib_exp.adaptors.date import to_date
 

scrapy/contrib_exp/adaptors/markup.py

@@ -1,5 +1,5 @@
 import re
-from scrapy.utils.markup import replace_tags, unquote_markup
+from scrapy.utils.markup import replace_tags, remove_escape_chars, unquote_markup
 from scrapy.utils.python import str_to_unicode
 from scrapy.item.adaptors import adaptize
 
@@ -30,6 +30,24 @@ def remove_root(value):
         value = m.group(1)
     return str_to_unicode(value)
 
+
+def remove_escape(which_ones=('\n','\t','\r'), replace_str=u''):
+    """
+    Factory that returns an adaptor for removing/replacing each escape
+    character in the `wich_ones` parameter found in the given value.
+
+    If `replace_str` is given, escape characters are replaced by that
+    string, else they're removed.
+
+    Input: string/unicode
+    Output: unicode
+    
+    """
+    def _remove_escape(value):
+        return remove_escape_chars(value, which_ones, replace_str)
+    return _remove_escape
+
+
 def unquote(keep=None):
     """
     This factory returns an adaptor that

scrapy/utils/markup.py

@@ -105,14 +105,14 @@ def remove_tags_with_content(text, which_ones=()):
     return text
     
 
-def remove_escape_chars(text, which_ones=('\n','\t','\r')):
+def remove_escape_chars(text, which_ones=('\n','\t','\r'), replace_str=u''):
     """ Remove escape chars. Default : \\n, \\t, \\r
 
         which_ones -- is a tuple of which escape chars we want to remove.
                       By default removes \n, \t, \r.
     """
     for ec in which_ones:
-        text = text.replace(ec, u'')
+        text = text.replace(ec, replace_str)
     return str_to_unicode(text)
 
 def unquote_markup(text, keep=(), remove_illegal=True):