diff --git a/scrapy/http/request/__init__.py b/scrapy/http/request/__init__.py index ef58deacc..498f1b052 100644 --- a/scrapy/http/request/__init__.py +++ b/scrapy/http/request/__init__.py @@ -65,7 +65,11 @@ class Request(object_ref): s = safe_url_string(url, self.encoding) self._url = escape_ajax(s) - if ('://' not in self._url) and (not self._url.startswith('data:')): + if ( + '://' not in self._url + and not self._url.startswith('about:') + and not self._url.startswith('data:') + ): raise ValueError(f'Missing scheme in request url: {self._url}') url = property(_get_url, obsolete_setter(_set_url, 'url')) diff --git a/tests/test_http_request.py b/tests/test_http_request.py index 0a303dbe2..74579dfc4 100644 --- a/tests/test_http_request.py +++ b/tests/test_http_request.py @@ -43,6 +43,15 @@ class RequestTest(unittest.TestCase): assert r.headers is not headers self.assertEqual(r.headers[b"caca"], b"coco") + def test_url_scheme(self): + # This test passes by not raising any (ValueError) exception + self.request_class('http://example.org') + self.request_class('https://example.org') + self.request_class('s3://example.org') + self.request_class('ftp://example.org') + self.request_class('about:config') + self.request_class('data:,Hello%2C%20World!') + def test_url_no_scheme(self): self.assertRaises(ValueError, self.request_class, 'foo') self.assertRaises(ValueError, self.request_class, '/foo/')