diff --git a/tests/test_parsers.py b/tests/test_parsers.py
index 5d289d7..51bccc5 100644
--- a/tests/test_parsers.py
+++ b/tests/test_parsers.py
@@ -2,9 +2,11 @@
from urllib.parse import urlparse
import copy
import unittest
+from unittest.mock import patch
from lxml import etree
+from xextract.extractors import HtmlXPathExtractor, XmlXPathExtractor
from xextract.parsers import (
ParserError, ParsingError, BaseParser, BaseNamedParser,
Prefix, Group, Element, String, Url, DateTime, Date)
@@ -276,6 +278,135 @@ def test_text_extract(self):
self.assertEqual(val, 'nice')
+class TestElementAsExtractor(unittest.TestCase):
+ def test_element_as_parser(self):
+ """
+ we can pass an Element as the extractor to parse_*()
+ """
+ html = '''
+ Hello world!
+
+ Hello mars!
+ '''
+
+ # take only the first containers so we can verify that the correct descendant is chosen
+ container = Element(css='div', count=3).parse(html)[2]
+
+ val = Element(css='span', count=1).parse_html(container)
+ self.assertEqual(val.tag, 'span')
+ self.assertEqual(val.text, 'Hello mars!')
+
+ def test_element_as_parser_html(self):
+ """
+ passing Element as extractor for parse_html should use the correct parser
+ """
+
+ html = '''
+
+
+
+ a<a‘
+
+
+ '''
+
+ original_tostring = etree.tostring
+ original_parser = HtmlXPathExtractor._parser
+
+ # etree.HtmlParser is immutable so we can't patch it
+ # instead we patch HtmlXPathExtractor._parser which references it
+ with patch.object(HtmlXPathExtractor, attribute='_parser', autospec=True) as mock_parser:
+ mock_parser.side_effect = original_parser
+ with patch('lxml.etree.tostring', autospec=True) as mock_tostring:
+ mock_tostring.side_effect = original_tostring
+
+ ancestor = Element(css='div', count=1).parse_html(html)
+ mock_parser.assert_called_once()
+ mock_parser.reset_mock()
+ mock_tostring.assert_not_called()
+
+ script_val = String(css='script', count=1).parse_html(ancestor)
+ mock_parser.assert_not_called()
+ mock_tostring.assert_called_once()
+ self.assertEqual(mock_tostring.call_args.kwargs['method'], 'html')
+ mock_tostring.reset_mock()
+
+ span_val = String(css='span', count=1).parse_html(ancestor)
+ mock_parser.assert_not_called()
+ mock_tostring.assert_called_once()
+ self.assertEqual(mock_tostring.call_args.kwargs['method'], 'html')
+ mock_tostring.reset_mock()
+
+ # HTML has different entity processing from XML:
+ #
+ a<a‘
+
+
+
+ '''
+ namespaces = {'a': 'http://test.com/', 'b': 'http://www.w3.org/2001/XMLSchema-instance'}
+
+ original_tostring = etree.tostring
+ original_parser = XmlXPathExtractor._parser
+
+ # etree.XMLParser is immutable so we can't patch it
+ # instead we patch XmlXPathExtractor._parser which references it
+ with patch.object(XmlXPathExtractor, attribute='_parser', autospec=True) as mock_parser:
+
+ mock_parser.side_effect = original_parser
+ with patch('lxml.etree.tostring', autospec=True) as mock_tostring:
+ mock_tostring.side_effect = original_tostring
+
+ ancestor = Element(xpath='//a:body', count=1, namespaces=namespaces).parse_xml(xml)
+ mock_parser.assert_called_once()
+ mock_parser.reset_mock()
+ mock_tostring.assert_not_called()
+
+ script_val = String(xpath='//a:script', count=1, namespaces=namespaces).parse_xml(ancestor)
+ mock_parser.assert_not_called()
+ mock_tostring.assert_called_once()
+ self.assertEqual(mock_tostring.call_args.kwargs['method'], 'xml')
+ mock_tostring.reset_mock()
+
+ span_val = String(xpath='//a:span', count=1, namespaces=namespaces).parse_xml(ancestor)
+ mock_parser.assert_not_called()
+ mock_tostring.assert_called_once()
+ self.assertEqual(mock_tostring.call_args.kwargs['method'], 'xml')
+ mock_tostring.reset_mock()
+
+
+ # XML has different entity processing from HTML:
+ #