File: test_webclient.py

package info (click to toggle)
python-scrapy 1.5.1-1%2Bdeb10u1
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 4,404 kB
  • sloc: python: 25,793; xml: 199; makefile: 95; sh: 33
file content (365 lines) | stat: -rw-r--r-- 14,530 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
"""
from twisted.internet import defer
Tests borrowed from the twisted.web.client tests.
"""
import os
import six
import shutil

from twisted.trial import unittest
from twisted.web import server, static, util, resource
from twisted.internet import reactor, defer
from twisted.test.proto_helpers import StringTransport
from twisted.python.filepath import FilePath
from twisted.protocols.policies import WrappingFactory
from twisted.internet.defer import inlineCallbacks

from scrapy.core.downloader import webclient as client
from scrapy.http import Request, Headers
from scrapy.utils.python import to_bytes, to_unicode


def getPage(url, contextFactory=None, response_transform=None, *args, **kwargs):
    """Adapted version of twisted.web.client.getPage"""
    def _clientfactory(url, *args, **kwargs):
        url = to_unicode(url)
        timeout = kwargs.pop('timeout', 0)
        f = client.ScrapyHTTPClientFactory(
            Request(url, *args, **kwargs), timeout=timeout)
        f.deferred.addCallback(response_transform or (lambda r: r.body))
        return f

    from twisted.web.client import _makeGetterFactory
    return _makeGetterFactory(to_bytes(url), _clientfactory,
        contextFactory=contextFactory, *args, **kwargs).deferred


class ParseUrlTestCase(unittest.TestCase):
    """Test URL parsing facility and defaults values."""

    def _parse(self, url):
        f = client.ScrapyHTTPClientFactory(Request(url))
        return (f.scheme, f.netloc, f.host, f.port, f.path)

    def testParse(self):
        lip = '127.0.0.1'
        tests = (
    ("http://127.0.0.1?c=v&c2=v2#fragment",     ('http', lip, lip, 80, '/?c=v&c2=v2')),
    ("http://127.0.0.1/?c=v&c2=v2#fragment",    ('http', lip, lip, 80, '/?c=v&c2=v2')),
    ("http://127.0.0.1/foo?c=v&c2=v2#frag",     ('http', lip, lip, 80, '/foo?c=v&c2=v2')),
    ("http://127.0.0.1:100?c=v&c2=v2#fragment", ('http', lip+':100', lip, 100, '/?c=v&c2=v2')),
    ("http://127.0.0.1:100/?c=v&c2=v2#frag",    ('http', lip+':100', lip, 100, '/?c=v&c2=v2')),
    ("http://127.0.0.1:100/foo?c=v&c2=v2#frag", ('http', lip+':100', lip, 100, '/foo?c=v&c2=v2')),

    ("http://127.0.0.1",              ('http', lip, lip, 80, '/')),
    ("http://127.0.0.1/",             ('http', lip, lip, 80, '/')),
    ("http://127.0.0.1/foo",          ('http', lip, lip, 80, '/foo')),
    ("http://127.0.0.1?param=value",  ('http', lip, lip, 80, '/?param=value')),
    ("http://127.0.0.1/?param=value", ('http', lip, lip, 80, '/?param=value')),
    ("http://127.0.0.1:12345/foo",    ('http', lip+':12345', lip, 12345, '/foo')),
    ("http://spam:12345/foo",         ('http', 'spam:12345', 'spam', 12345, '/foo')),
    ("http://spam.test.org/foo",      ('http', 'spam.test.org', 'spam.test.org', 80, '/foo')),

    ("https://127.0.0.1/foo",         ('https', lip, lip, 443, '/foo')),
    ("https://127.0.0.1/?param=value", ('https', lip, lip, 443, '/?param=value')),
    ("https://127.0.0.1:12345/",      ('https', lip+':12345', lip, 12345, '/')),

    ("http://scrapytest.org/foo ",    ('http', 'scrapytest.org', 'scrapytest.org', 80, '/foo')),
    ("http://egg:7890 ",              ('http', 'egg:7890', 'egg', 7890, '/')),
    )

        for url, test in tests:
            test = tuple(
                to_bytes(x) if not isinstance(x, int) else x for x in test)
            self.assertEqual(client._parse(url), test, url)

    def test_externalUnicodeInterference(self):
        """
        L{client._parse} should return C{str} for the scheme, host, and path
        elements of its return tuple, even when passed an URL which has
        previously been passed to L{urlparse} as a C{unicode} string.
        """
        if not six.PY2:
            raise unittest.SkipTest(
                "Applies only to Py2, as urls can be ONLY unicode on Py3")
        badInput = u'http://example.com/path'
        goodInput = badInput.encode('ascii')
        self._parse(badInput)  # cache badInput in urlparse_cached
        scheme, netloc, host, port, path = self._parse(goodInput)
        self.assertTrue(isinstance(scheme, str))
        self.assertTrue(isinstance(netloc, str))
        self.assertTrue(isinstance(host, str))
        self.assertTrue(isinstance(path, str))
        self.assertTrue(isinstance(port, int))



class ScrapyHTTPPageGetterTests(unittest.TestCase):

    def test_earlyHeaders(self):
        # basic test stolen from twisted HTTPageGetter
        factory = client.ScrapyHTTPClientFactory(Request(
            url='http://foo/bar',
            body="some data",
            headers={
                'Host': 'example.net',
                'User-Agent': 'fooble',
                'Cookie': 'blah blah',
                'Content-Length': '12981',
                'Useful': 'value'}))

        self._test(factory,
            b"GET /bar HTTP/1.0\r\n"
            b"Content-Length: 9\r\n"
            b"Useful: value\r\n"
            b"Connection: close\r\n"
            b"User-Agent: fooble\r\n"
            b"Host: example.net\r\n"
            b"Cookie: blah blah\r\n"
            b"\r\n"
            b"some data")

        # test minimal sent headers
        factory = client.ScrapyHTTPClientFactory(Request('http://foo/bar'))
        self._test(factory,
            b"GET /bar HTTP/1.0\r\n"
            b"Host: foo\r\n"
            b"\r\n")

        # test a simple POST with body and content-type
        factory = client.ScrapyHTTPClientFactory(Request(
            method='POST',
            url='http://foo/bar',
            body='name=value',
            headers={'Content-Type': 'application/x-www-form-urlencoded'}))

        self._test(factory,
            b"POST /bar HTTP/1.0\r\n"
            b"Host: foo\r\n"
            b"Connection: close\r\n"
            b"Content-Type: application/x-www-form-urlencoded\r\n"
            b"Content-Length: 10\r\n"
            b"\r\n"
            b"name=value")

        # test a POST method with no body provided
        factory = client.ScrapyHTTPClientFactory(Request(
            method='POST',
            url='http://foo/bar'
        ))

        self._test(factory,
            b"POST /bar HTTP/1.0\r\n"
            b"Host: foo\r\n"
            b"Content-Length: 0\r\n"
            b"\r\n")

        # test with single and multivalued headers
        factory = client.ScrapyHTTPClientFactory(Request(
            url='http://foo/bar',
            headers={
                'X-Meta-Single': 'single',
                'X-Meta-Multivalued': ['value1', 'value2'],
                }))

        self._test(factory,
            b"GET /bar HTTP/1.0\r\n"
            b"Host: foo\r\n"
            b"X-Meta-Multivalued: value1\r\n"
            b"X-Meta-Multivalued: value2\r\n"
            b"X-Meta-Single: single\r\n"
            b"\r\n")

        # same test with single and multivalued headers but using Headers class
        factory = client.ScrapyHTTPClientFactory(Request(
            url='http://foo/bar',
            headers=Headers({
                'X-Meta-Single': 'single',
                'X-Meta-Multivalued': ['value1', 'value2'],
                })))

        self._test(factory,
            b"GET /bar HTTP/1.0\r\n"
            b"Host: foo\r\n"
            b"X-Meta-Multivalued: value1\r\n"
            b"X-Meta-Multivalued: value2\r\n"
            b"X-Meta-Single: single\r\n"
            b"\r\n")

    def _test(self, factory, testvalue):
        transport = StringTransport()
        protocol = client.ScrapyHTTPPageGetter()
        protocol.factory = factory
        protocol.makeConnection(transport)
        self.assertEqual(
            set(transport.value().splitlines()),
            set(testvalue.splitlines()))
        return testvalue

    def test_non_standard_line_endings(self):
        # regression test for: http://dev.scrapy.org/ticket/258
        factory = client.ScrapyHTTPClientFactory(Request(
            url='http://foo/bar'))
        protocol = client.ScrapyHTTPPageGetter()
        protocol.factory = factory
        protocol.headers = Headers()
        protocol.dataReceived(b"HTTP/1.0 200 OK\n")
        protocol.dataReceived(b"Hello: World\n")
        protocol.dataReceived(b"Foo: Bar\n")
        protocol.dataReceived(b"\n")
        self.assertEqual(protocol.headers,
            Headers({'Hello': ['World'], 'Foo': ['Bar']}))


from twisted.web.test.test_webclient import ForeverTakingResource, \
        ErrorResource, NoLengthResource, HostHeaderResource, \
        PayloadResource, BrokenDownloadResource


class EncodingResource(resource.Resource):
    out_encoding = 'cp1251'

    def render(self, request):
        body = to_unicode(request.content.read())
        request.setHeader(b'content-encoding', self.out_encoding)
        return body.encode(self.out_encoding)


class WebClientTestCase(unittest.TestCase):
    def _listen(self, site):
        return reactor.listenTCP(0, site, interface="127.0.0.1")

    def setUp(self):
        self.tmpname = self.mktemp()
        os.mkdir(self.tmpname)
        FilePath(self.tmpname).child("file").setContent(b"0123456789")
        r = static.File(self.tmpname)
        r.putChild(b"redirect", util.Redirect(b"/file"))
        r.putChild(b"wait", ForeverTakingResource())
        r.putChild(b"error", ErrorResource())
        r.putChild(b"nolength", NoLengthResource())
        r.putChild(b"host", HostHeaderResource())
        r.putChild(b"payload", PayloadResource())
        r.putChild(b"broken", BrokenDownloadResource())
        r.putChild(b"encoding", EncodingResource())
        self.site = server.Site(r, timeout=None)
        self.wrapper = WrappingFactory(self.site)
        self.port = self._listen(self.wrapper)
        self.portno = self.port.getHost().port

    @inlineCallbacks
    def tearDown(self):
        yield self.port.stopListening()
        shutil.rmtree(self.tmpname)

    def getURL(self, path):
        return "http://127.0.0.1:%d/%s" % (self.portno, path)

    def testPayload(self):
        s = "0123456789" * 10
        return getPage(self.getURL("payload"), body=s).addCallback(
            self.assertEqual, to_bytes(s))

    def testHostHeader(self):
        # if we pass Host header explicitly, it should be used, otherwise
        # it should extract from url
        return defer.gatherResults([
            getPage(self.getURL("host")).addCallback(
                self.assertEqual, to_bytes("127.0.0.1:%d" % self.portno)),
            getPage(self.getURL("host"), headers={"Host": "www.example.com"}).addCallback(
                self.assertEqual, to_bytes("www.example.com"))])

    def test_getPage(self):
        """
        L{client.getPage} returns a L{Deferred} which is called back with
        the body of the response if the default method B{GET} is used.
        """
        d = getPage(self.getURL("file"))
        d.addCallback(self.assertEqual, b"0123456789")
        return d

    def test_getPageHead(self):
        """
        L{client.getPage} returns a L{Deferred} which is called back with
        the empty string if the method is C{HEAD} and there is a successful
        response code.
        """
        def _getPage(method):
            return getPage(self.getURL("file"), method=method)
        return defer.gatherResults([
            _getPage("head").addCallback(self.assertEqual, b""),
            _getPage("HEAD").addCallback(self.assertEqual, b"")])

    def test_timeoutNotTriggering(self):
        """
        When a non-zero timeout is passed to L{getPage} and the page is
        retrieved before the timeout period elapses, the L{Deferred} is
        called back with the contents of the page.
        """
        d = getPage(self.getURL("host"), timeout=100)
        d.addCallback(
            self.assertEqual, to_bytes("127.0.0.1:%d" % self.portno))
        return d

    def test_timeoutTriggering(self):
        """
        When a non-zero timeout is passed to L{getPage} and that many
        seconds elapse before the server responds to the request. the
        L{Deferred} is errbacked with a L{error.TimeoutError}.
        """
        finished = self.assertFailure(
            getPage(self.getURL("wait"), timeout=0.000001),
            defer.TimeoutError)
        def cleanup(passthrough):
            # Clean up the server which is hanging around not doing
            # anything.
            connected = list(six.iterkeys(self.wrapper.protocols))
            # There might be nothing here if the server managed to already see
            # that the connection was lost.
            if connected:
                connected[0].transport.loseConnection()
            return passthrough
        finished.addBoth(cleanup)
        return finished

    def testNotFound(self):
        return getPage(self.getURL('notsuchfile')).addCallback(self._cbNoSuchFile)

    def _cbNoSuchFile(self, pageData):
        self.assertIn(b'404 - No Such Resource', pageData)

    def testFactoryInfo(self):
        url = self.getURL('file')
        _, _, host, port, _ = client._parse(url)
        factory = client.ScrapyHTTPClientFactory(Request(url))
        reactor.connectTCP(to_unicode(host), port, factory)
        return factory.deferred.addCallback(self._cbFactoryInfo, factory)

    def _cbFactoryInfo(self, ignoredResult, factory):
        self.assertEqual(factory.status, b'200')
        self.assertTrue(factory.version.startswith(b'HTTP/'))
        self.assertEqual(factory.message, b'OK')
        self.assertEqual(factory.response_headers[b'content-length'], b'10')

    def testRedirect(self):
        return getPage(self.getURL("redirect")).addCallback(self._cbRedirect)

    def _cbRedirect(self, pageData):
        self.assertEqual(pageData,
                b'\n<html>\n    <head>\n        <meta http-equiv="refresh" content="0;URL=/file">\n'
                b'    </head>\n    <body bgcolor="#FFFFFF" text="#000000">\n    '
                b'<a href="/file">click here</a>\n    </body>\n</html>\n')

    def test_encoding(self):
        """ Test that non-standart body encoding matches
        Content-Encoding header """
        body = b'\xd0\x81\xd1\x8e\xd0\xaf'
        return getPage(
            self.getURL('encoding'), body=body, response_transform=lambda r: r)\
            .addCallback(self._check_Encoding, body)

    def _check_Encoding(self, response, original_body):
        content_encoding = to_unicode(response.headers[b'Content-Encoding'])
        self.assertEqual(content_encoding, EncodingResource.out_encoding)
        self.assertEqual(
            response.body.decode(content_encoding), to_unicode(original_body))