Add format_as to extract() methods

parsel/selector.py

@@ -16,6 +16,7 @@ def __init__(self, *args, **kwargs):
         kwargs.setdefault('resolve_entities', False)
         super(SafeXMLParser, self).__init__(*args, **kwargs)
 
+
 _ctgroup = {
     'html': {'_parser': html.HTMLParser,
              '_csstranslator': HTMLTranslator(),
@@ -118,23 +119,29 @@ def re_first(self, regex, default=None, replace_entities=True):
         else:
             return default
 
-    def extract(self):
+    def extract(self, format_as=None):
         """
         Call the ``.extract()`` method for each element is this list and return
         their results flattened, as a list of unicode strings.
+
+        ``format_as`` can take either ``xml`` or ``html`` values to pretty format the output. 
         """
-        return [x.extract() for x in self]
+        return [x.extract(format_as=format_as) for x in self]
+
     getall = extract
 
-    def extract_first(self, default=None):
+    def extract_first(self, default=None, format_as=None):
         """
         Return the result of ``.extract()`` for the first element in this list.
         If the list is empty, return the default value.
+
+        ``format_as`` can take either ``xml`` or ``html`` values to pretty format the output. 
         """
         for x in self:
-            return x.extract()
+            return x.extract(format_as=format_as)
         else:
             return default
+
     get = extract_first
 
 
@@ -276,23 +283,29 @@ def re_first(self, regex, default=None, replace_entities=True):
         """
         return next(iflatten(self.re(regex, replace_entities=replace_entities)), default)
 
-    def extract(self):
+    def extract(self, format_as=None):
         """
         Serialize and return the matched nodes in a single unicode string.
         Percent encoded content is unquoted.
+
+        ``format_as`` can take either ``xml`` or ``html`` values to pretty format the output. 
         """
         try:
-            return etree.tostring(self.root,
-                                  method=self._tostring_method,
-                                  encoding='unicode',
-                                  with_tail=False)
+            return etree.tostring(
+                self.root,
+                method=format_as or self._tostring_method,
+                encoding='unicode',
+                with_tail=False,
+                pretty_print=bool(format_as),
+            )
         except (AttributeError, TypeError):
             if self.root is True:
                 return u'1'
             elif self.root is False:
                 return u'0'
             else:
                 return six.text_type(self.root)
+
     get = extract
 
     def getall(self):
@@ -331,9 +344,11 @@ def __bool__(self):
         given by the contents it selects.
         """
         return bool(self.extract())
+
     __nonzero__ = __bool__
 
     def __str__(self):
         data = repr(self.extract()[:40])
         return "<%s xpath=%r data=%s>" % (type(self).__name__, self._expr, data)
+
     __repr__ = __str__