diff --git a/docs/topics/selectors.rst b/docs/topics/selectors.rst
index 3872736ae..c64ebad62 100644
--- a/docs/topics/selectors.rst
+++ b/docs/topics/selectors.rst
@@ -240,6 +240,149 @@ XPath specification.
 
 .. _Location Paths: http://www.w3.org/TR/xpath#location-paths
 
+Using EXSLT extensions
+----------------------
+
+Being built atop `lxml`_, Scrapy selectors also support some `EXSLT`_ extensions
+and come with these pre-registered namespaces to use in XPath expressions:
+
+
+======  ====================================    =======================
+prefix  namespace                               usage
+======  ====================================    =======================
+re      http://exslt.org/regular-expressions    `regular expressions`_
+set     http://exslt.org/sets                   `set manipulation`_
+======  ====================================    =======================
+
+Regular expressions
+~~~~~~~~~~~~~~~~~~~
+
+The ``test()`` function for example can prove quite useful when XPath's
+``starts-with()`` or ``contains()`` are not sufficient.
+
+Example selecting links in list item with a "class" attribute ending with a digit::
+
+    >>> doc = """
+    ... <div>
+    ...     <ul>
+    ...         <li class="item-0"><a href="link1.html">first item</a></li>
+    ...         <li class="item-1"><a href="link2.html">second item</a></li>
+    ...         <li class="item-inactive"><a href="link3.html">third item</a></li>
+    ...         <li class="item-1"><a href="link4.html">fourth item</a></li>
+    ...         <li class="item-0"><a href="link5.html">fifth item</a></li>
+    ...     </ul>
+    ... </div>
+    ... """
+    >>> sel = Selector(text=doc, type="html")
+    >>> sel.xpath('//li//@href').extract()
+    [u'link1.html', u'link2.html', u'link3.html', u'link4.html', u'link5.html']
+    >>> sel.xpath('//li[re:test(@class, "item-\d$")]//@href').extract()
+    [u'link1.html', u'link2.html', u'link4.html', u'link5.html']
+    >>>
+
+.. warning:: C library ``libxslt`` doesn't natively support EXSLT regular
+    expressions so `lxml`_'s implementation uses hooks to Python's ``re`` module.
+    Thus, using regexp functions in your XPath expressions may add a small
+    performance penalty.
+
+Set operations
+~~~~~~~~~~~~~~
+
+These can be handy for excluding parts of a document tree before
+extracting text elements for example.
+
+Example extracting microdata (sample content taken from http://schema.org/Product)
+with groups of itemscopes and corresponding itemprops::
+
+    >>> doc = """
+    ... <div itemscope itemtype="http://schema.org/Product">
+    ...   <span itemprop="name">Kenmore White 17" Microwave</span>
+    ...   <img src="kenmore-microwave-17in.jpg" alt='Kenmore 17" Microwave' />
+    ...   <div itemprop="aggregateRating"
+    ...     itemscope itemtype="http://schema.org/AggregateRating">
+    ...    Rated <span itemprop="ratingValue">3.5</span>/5
+    ...    based on <span itemprop="reviewCount">11</span> customer reviews
+    ...   </div>
+    ...
+    ...   <div itemprop="offers" itemscope itemtype="http://schema.org/Offer">
+    ...     <span itemprop="price">$55.00</span>
+    ...     <link itemprop="availability" href="http://schema.org/InStock" />In stock
+    ...   </div>
+    ...
+    ...   Product description:
+    ...   <span itemprop="description">0.7 cubic feet countertop microwave.
+    ...   Has six preset cooking categories and convenience features like
+    ...   Add-A-Minute and Child Lock.</span>
+    ...
+    ...   Customer reviews:
+    ...
+    ...   <div itemprop="review" itemscope itemtype="http://schema.org/Review">
+    ...     <span itemprop="name">Not a happy camper</span> -
+    ...     by <span itemprop="author">Ellie</span>,
+    ...     <meta itemprop="datePublished" content="2011-04-01">April 1, 2011
+    ...     <div itemprop="reviewRating" itemscope itemtype="http://schema.org/Rating">
+    ...       <meta itemprop="worstRating" content = "1">
+    ...       <span itemprop="ratingValue">1</span>/
+    ...       <span itemprop="bestRating">5</span>stars
+    ...     </div>
+    ...     <span itemprop="description">The lamp burned out and now I have to replace
+    ...     it. </span>
+    ...   </div>
+    ...
+    ...   <div itemprop="review" itemscope itemtype="http://schema.org/Review">
+    ...     <span itemprop="name">Value purchase</span> -
+    ...     by <span itemprop="author">Lucas</span>,
+    ...     <meta itemprop="datePublished" content="2011-03-25">March 25, 2011
+    ...     <div itemprop="reviewRating" itemscope itemtype="http://schema.org/Rating">
+    ...       <meta itemprop="worstRating" content = "1"/>
+    ...       <span itemprop="ratingValue">4</span>/
+    ...       <span itemprop="bestRating">5</span>stars
+    ...     </div>
+    ...     <span itemprop="description">Great microwave for the price. It is small and
+    ...     fits in my apartment.</span>
+    ...   </div>
+    ...   ...
+    ... </div>
+    ... """
+    >>>
+    >>> for scope in sel.xpath('//div[@itemscope]'):
+    ...     print "current scope:", scope.xpath('@itemtype').extract()
+    ...     props = scope.xpath('''
+    ...                 set:difference(./descendant::*/@itemprop,
+    ...                                .//*[@itemscope]/*/@itemprop)''')
+    ...     print "    properties:", props.extract()
+    ...     print
+    ...
+    current scope: [u'http://schema.org/Product']
+        properties: [u'name', u'aggregateRating', u'offers', u'description', u'review', u'review']
+
+    current scope: [u'http://schema.org/AggregateRating']
+        properties: [u'ratingValue', u'reviewCount']
+
+    current scope: [u'http://schema.org/Offer']
+        properties: [u'price', u'availability']
+
+    current scope: [u'http://schema.org/Review']
+        properties: [u'name', u'author', u'datePublished', u'reviewRating', u'description']
+
+    current scope: [u'http://schema.org/Rating']
+        properties: [u'worstRating', u'ratingValue', u'bestRating']
+
+    current scope: [u'http://schema.org/Review']
+        properties: [u'name', u'author', u'datePublished', u'reviewRating', u'description']
+
+    current scope: [u'http://schema.org/Rating']
+        properties: [u'worstRating', u'ratingValue', u'bestRating']
+
+    >>>
+
+Here we first iterate over ``itemscope`` elements, and for each one,
+we look for all ``itemprops`` elements and exclude those that are themselves
+inside another ``itemscope``.
+
+.. _EXSLT: http://www.exslt.org/
+.. _regular expressions: http://www.exslt.org/regexp/index.html
+.. _set manipulation: http://www.exslt.org/set/index.html
 
 .. _topics-selectors-ref:
 
diff --git a/scrapy/selector/unified.py b/scrapy/selector/unified.py
index a316c20cf..790937af5 100644
--- a/scrapy/selector/unified.py
+++ b/scrapy/selector/unified.py
@@ -46,6 +46,17 @@ class Selector(object_ref):
                  '__weakref__', '_parser', '_csstranslator', '_tostring_method']
 
     _default_type = None
+    _default_namespaces = {
+        "re": "http://exslt.org/regular-expressions",
+
+        # supported in libxslt:
+        # set:difference
+        # set:has-same-node
+        # set:intersection
+        # set:leading
+        # set:trailing
+        "set": "http://exslt.org/sets"
+    }
 
     def __init__(self, response=None, text=None, type=None, namespaces=None,
                  _root=None, _expr=None):
@@ -61,7 +72,9 @@ class Selector(object_ref):
             _root = LxmlDocument(response, self._parser)
 
         self.response = response
-        self.namespaces = namespaces
+        self.namespaces = dict(self._default_namespaces)
+        if namespaces is not None:
+            self.namespaces.update(namespaces)
         self._root = _root
         self._expr = _expr
 
diff --git a/scrapy/tests/test_selector.py b/scrapy/tests/test_selector.py
index 72f5ebdd5..d84e4bd47 100644
--- a/scrapy/tests/test_selector.py
+++ b/scrapy/tests/test_selector.py
@@ -400,3 +400,122 @@ class DeprecatedXpathSelectorTest(unittest.TestCase):
             self.assertEqual(xs.select("//div").extract(),
                              [u'<div><img src="a.jpg"><p>Hello</p></img></div>'])
             self.assertRaises(RuntimeError, xs.css, 'div')
+
+
+class ExsltTestCase(unittest.TestCase):
+
+    sscls = Selector
+
+    def test_regexp(self):
+        """EXSLT regular expression tests"""
+        body = """
+        <p><input name='a' value='1'/><input name='b' value='2'/></p>
+        <div class="links">
+        <a href="/first.html">first link</a>
+        <a href="/second.html">second link</a>
+        <a href="http://www.bayes.co.uk/xml/index.xml?/xml/utils/rechecker.xml">EXSLT match example</a>
+        </div>
+        """
+        response = TextResponse(url="http://example.com", body=body)
+        sel = self.sscls(response)
+
+        # re:test()
+        self.assertEqual(
+            sel.xpath(
+                '//input[re:test(@name, "[A-Z]+", "i")]').extract(),
+            [x.extract() for x in sel.xpath('//input[re:test(@name, "[A-Z]+", "i")]')])
+        self.assertEqual(
+            [x.extract()
+             for x in sel.xpath(
+                 '//a[re:test(@href, "\.html$")]/text()')],
+            [u'first link', u'second link'])
+        self.assertEqual(
+            [x.extract()
+             for x in sel.xpath(
+                 '//a[re:test(@href, "first")]/text()')],
+            [u'first link'])
+        self.assertEqual(
+            [x.extract()
+             for x in sel.xpath(
+                 '//a[re:test(@href, "second")]/text()')],
+            [u'second link'])
+
+
+        # re:match() is rather special: it returns a node-set of <match> nodes
+        #[u'<match>http://www.bayes.co.uk/xml/index.xml?/xml/utils/rechecker.xml</match>',
+        #u'<match>http</match>',
+        #u'<match>www.bayes.co.uk</match>',
+        #u'<match></match>',
+        #u'<match>/xml/index.xml?/xml/utils/rechecker.xml</match>']
+        self.assertEqual(
+            sel.xpath('re:match(//a[re:test(@href, "\.xml$")]/@href,'
+                      '"(\w+):\/\/([^/:]+)(:\d*)?([^# ]*)")/text()').extract(),
+            [u'http://www.bayes.co.uk/xml/index.xml?/xml/utils/rechecker.xml',
+             u'http',
+             u'www.bayes.co.uk',
+             u'',
+             u'/xml/index.xml?/xml/utils/rechecker.xml'])
+
+
+
+        # re:replace()
+        self.assertEqual(
+            sel.xpath('re:replace(//a[re:test(@href, "\.xml$")]/@href,'
+                      '"(\w+)://(.+)(\.xml)", "","https://\\2.html")').extract(),
+            [u'https://www.bayes.co.uk/xml/index.xml?/xml/utils/rechecker.html'])
+
+    def test_set(self):
+        """EXSLT set manipulation tests"""
+        # microdata example from http://schema.org/Event
+        body="""
+        <div itemscope itemtype="http://schema.org/Event">
+          <a itemprop="url" href="nba-miami-philidelphia-game3.html">
+          NBA Eastern Conference First Round Playoff Tickets:
+          <span itemprop="name"> Miami Heat at Philadelphia 76ers - Game 3 (Home Game 1) </span>
+          </a>
+
+          <meta itemprop="startDate" content="2016-04-21T20:00">
+            Thu, 04/21/16
+            8:00 p.m.
+
+          <div itemprop="location" itemscope itemtype="http://schema.org/Place">
+            <a itemprop="url" href="wells-fargo-center.html">
+            Wells Fargo Center
+            </a>
+            <div itemprop="address" itemscope itemtype="http://schema.org/PostalAddress">
+              <span itemprop="addressLocality">Philadelphia</span>,
+              <span itemprop="addressRegion">PA</span>
+            </div>
+          </div>
+
+          <div itemprop="offers" itemscope itemtype="http://schema.org/AggregateOffer">
+            Priced from: <span itemprop="lowPrice">$35</span>
+            <span itemprop="offerCount">1938</span> tickets left
+          </div>
+        </div>
+        """
+        response = TextResponse(url="http://example.com", body=body)
+        sel = self.sscls(response)
+
+        self.assertEqual(
+            sel.xpath('''//div[@itemtype="http://schema.org/Event"]
+                            //@itemprop''').extract(),
+            [u'url',
+             u'name',
+             u'startDate',
+             u'location',
+             u'url',
+             u'address',
+             u'addressLocality',
+             u'addressRegion',
+             u'offers',
+             u'lowPrice',
+             u'offerCount']
+        )
+
+        self.assertEqual(sel.xpath('''
+                set:difference(//div[@itemtype="http://schema.org/Event"]
+                                    //@itemprop,
+                               //div[@itemtype="http://schema.org/Event"]
+                                    //*[@itemscope]/*/@itemprop)''').extract(),
+                         [u'url', u'name', u'startDate', u'location', u'offers'])