Added formname parameter for FormRequest.from_response

docs/topics/request-response.rst

@@ -254,7 +254,7 @@ objects.
     The :class:`FormRequest` objects support the following class method in
     addition to the standard :class:`Request` methods:
 
-    .. classmethod:: FormRequest.from_response(response, [formnumber=0, formdata=None, clickdata=None, dont_click=False, ...])
+    .. classmethod:: FormRequest.from_response(response, [formname=None, formnumber=0, formdata=None, clickdata=None, dont_click=False, ...])
 
        Returns a new :class:`FormRequest` object with its form field values
        pre-populated with those found in the HTML ``<form>`` element contained
@@ -277,6 +277,11 @@ objects.
           to pre-populate the form fields
        :type response: :class:`Response` object
 
+       :param formname: if given, the form with name attribute set to this value
+          will be used. Otherwise, ``formnumber`` will be used for selecting
+          the form.
+       :type formname: string
+
        :param formnumber: the number of form to use, when the response contains
           multiple forms. The first one (and also the default) is ``0``.
        :type formnumber: integer
@@ -298,6 +303,9 @@ objects.
        The other parameters of this class method are passed directly to the
        :class:`FormRequest` constructor.
 
+       .. versionadded:: 0.10.3
+          The ``formname`` parameter.
+
 Request usage examples
 ----------------------
 

scrapy/http/request/form.py

@@ -37,17 +37,27 @@ class FormRequest(Request):
             self.headers['Content-Type'] = 'application/x-www-form-urlencoded'
 
     @classmethod
-    def from_response(cls, response, formnumber=0, formdata=None, 
+    def from_response(cls, response, formname=None, formnumber=0, formdata=None, 
                       clickdata=None, dont_click=False, **kwargs):
         encoding = getattr(response, 'encoding', 'utf-8')
         forms = ParseFile(StringIO(response.body), response.url,
                           encoding=encoding, backwards_compat=False)
         if not forms:
             raise ValueError("No <form> element found in %s" % response)
-        try:
-            form = forms[formnumber]
-        except IndexError:
-            raise IndexError("Form number %d not found in %s" % (formnumber, response))
+        
+        form = None
+
+        if formname:
+            for f in forms:
+                if f.name == formname:
+                    form = f
+                    break
+
+        if not form:
+            try:
+                form = forms[formnumber]
+            except IndexError:
+                raise IndexError("Form number %d not found in %s" % (formnumber, response))
         if formdata:
             # remove all existing fields with the same name before, so that
             # formdata fields properly can properly override existing ones,

scrapy/tests/test_http_request.py

@@ -330,6 +330,67 @@ class FormRequestTest(RequestTest):
         response = Response("http://www.example.com/lala.html", body=respbody)
         self.assertRaises(IndexError, self.request_class.from_response, response, formnumber=1)
 
+    def test_from_response_noformname(self):
+        respbody = """
+<form action="post.php" method="POST">
+<input type="hidden" name="one" value="1">
+<input type="hidden" name="two" value="2">
+</form>
+        """
+        response = Response("http://www.example.com/formname.html", body=respbody)
+        r1 = self.request_class.from_response(response, formdata={'two':'3'}, callback=lambda x: x)
+        self.assertEqual(r1.method, 'POST')
+        self.assertEqual(r1.headers['Content-type'], 'application/x-www-form-urlencoded')
+        fs = cgi.FieldStorage(StringIO(r1.body), r1.headers, environ={"REQUEST_METHOD": "POST"})
+        self.assertEqual(fs['one'].value, '1')
+        self.assertEqual(fs['two'].value, '3')
+
+
+    def test_from_response_formname_exists(self):
+        respbody = """
+<form action="post.php" method="POST">
+<input type="hidden" name="one" value="1">
+<input type="hidden" name="two" value="2">
+</form>
+<form name="form2" action="post.php" method="POST">
+<input type="hidden" name="three" value="3">
+<input type="hidden" name="four" value="4">
+</form>
+        """
+        response = Response("http://www.example.com/formname.html", body=respbody)
+        r1 = self.request_class.from_response(response, formname="form2", callback=lambda x: x)
+        self.assertEqual(r1.method, 'POST')
+        fs = cgi.FieldStorage(StringIO(r1.body), r1.headers, environ={"REQUEST_METHOD": "POST"})
+        self.assertEqual(fs['three'].value, "3")
+        self.assertEqual(fs['four'].value, "4")
+
+    def test_from_response_formname_notexist(self):
+        respbody = """
+<form name="form1" action="post.php" method="POST">
+<input type="hidden" name="one" value="1">
+</form>
+<form name="form2" action="post.php" method="POST">
+<input type="hidden" name="two" value="2">
+</form>
+        """
+        response = Response("http://www.example.com/formname.html", body=respbody)
+        r1 = self.request_class.from_response(response, formname="form3", callback=lambda x: x)
+        self.assertEqual(r1.method, 'POST')
+        fs = cgi.FieldStorage(StringIO(r1.body), r1.headers, environ={"REQUEST_METHOD": "POST"})
+        self.assertEqual(fs['one'].value, "1")
+
+    def test_from_response_formname_errors_formnumber(self):
+        respbody = """
+<form name="form1" action="post.php" method="POST">
+<input type="hidden" name="one" value="1">
+</form>
+<form name="form2" action="post.php" method="POST">
+<input type="hidden" name="two" value="2">
+</form>
+        """
+        response = Response("http://www.example.com/formname.html", body=respbody)
+        self.assertRaises(IndexError, self.request_class.from_response, response, formname="form3", formnumber=2)
+
 
 class XmlRpcRequestTest(RequestTest):