Merge pull request #1533 from Digenis/xml_iter-nodename_with_dot

[MRG+1] xmliter nodename with dot

scrapy/utils/iterators.py

@@ -25,8 +25,10 @@ def xmliter(obj, nodename):
     - a unicode string
     - a string encoded as utf-8
     """
-    HEADER_START_RE = re.compile(r'^(.*?)<\s*%s(?:\s|>)' % nodename, re.S)
-    HEADER_END_RE = re.compile(r'<\s*/%s\s*>' % nodename, re.S)
+    nodename_patt = re.escape(nodename)
+
+    HEADER_START_RE = re.compile(r'^(.*?)<\s*%s(?:\s|>)' % nodename_patt, re.S)
+    HEADER_END_RE = re.compile(r'<\s*/%s\s*>' % nodename_patt, re.S)
     text = _body_or_str(obj)
 
     header_start = re.search(HEADER_START_RE, text)
@@ -34,7 +36,7 @@ def xmliter(obj, nodename):
     header_end = re_rsearch(HEADER_END_RE, text)
     header_end = text[header_end[1]:].strip() if header_end else ''
 
-    r = re.compile(r"<%s[\s>].*?</%s>" % (nodename, nodename), re.DOTALL)
+    r = re.compile(r"<{0}[\s>].*?</{0}>".format(nodename_patt), re.DOTALL)
     for match in r.finditer(text):
         nodetext = header_start + match.group() + header_end
         yield Selector(text=nodetext, type='xml').xpath('//' + nodename)[0]

tests/test_utils_iterators.py

@@ -33,6 +33,19 @@ class XmliterTestCase(unittest.TestCase):
         self.assertEqual(attrs,
                          [(['001'], ['Name 1'], ['Type 1']), (['002'], ['Name 2'], ['Type 2'])])
 
+    def test_xmliter_unusual_node(self):
+        body = b"""<?xml version="1.0" encoding="UTF-8"?>
+            <root>
+                <matchme...></matchme...>
+                <matchmenot></matchmenot>
+            </root>
+        """
+        response = XmlResponse(url="http://example.com", body=body)
+        nodenames = [e.xpath('name()').extract()
+                 for e in self.xmliter(response, 'matchme...')]
+        self.assertEqual(nodenames, [['matchme...']])
+
+
     def test_xmliter_text(self):
         body = u"""<?xml version="1.0" encoding="UTF-8"?><products><product>one</product><product>two</product></products>"""