File: test_downloader_handlers.py

package info (click to toggle)
python-scrapy 2.14.2-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 6,332 kB
  • sloc: python: 55,629; xml: 199; makefile: 25; sh: 7
file content (384 lines) | stat: -rw-r--r-- 14,148 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
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
"""Tests for DownloadHandlers and for specific non-HTTP download handlers."""

from __future__ import annotations

import contextlib
import os
from pathlib import Path
from tempfile import mkdtemp, mkstemp
from unittest import mock

import pytest
from w3lib.url import path_to_file_uri

from scrapy.core.downloader.handlers import DownloadHandlers
from scrapy.core.downloader.handlers.datauri import DataURIDownloadHandler
from scrapy.core.downloader.handlers.file import FileDownloadHandler
from scrapy.core.downloader.handlers.s3 import S3DownloadHandler
from scrapy.exceptions import NotConfigured, ScrapyDeprecationWarning
from scrapy.http import Request
from scrapy.responsetypes import responsetypes
from scrapy.utils.boto import is_botocore_available
from scrapy.utils.defer import deferred_f_from_coro_f
from scrapy.utils.misc import build_from_crawler
from scrapy.utils.test import get_crawler


class DummyDH:
    lazy = False

    async def download_request(self, request):
        pass


class DummyLazyDH:
    # Default (but deprecated) is lazy for backward compatibility
    async def download_request(self, request):
        pass


class OffDH:
    lazy = False

    def __init__(self, crawler):
        raise NotConfigured

    @classmethod
    def from_crawler(cls, crawler):
        return cls(crawler)


class BuggyDH:
    lazy = False

    def __init__(self, crawler):
        raise ValueError

    @classmethod
    def from_crawler(cls, crawler):
        return cls(crawler)


class TestLoad:
    def test_enabled_handler(self):
        handlers = {"scheme": DummyDH}
        crawler = get_crawler(settings_dict={"DOWNLOAD_HANDLERS": handlers})
        dh = DownloadHandlers(crawler)
        assert "scheme" in dh._schemes
        assert "scheme" in dh._handlers
        assert "scheme" not in dh._notconfigured

    def test_not_configured_handler(self):
        handlers = {"scheme": OffDH}
        crawler = get_crawler(settings_dict={"DOWNLOAD_HANDLERS": handlers})
        dh = DownloadHandlers(crawler)
        assert "scheme" in dh._schemes
        assert "scheme" not in dh._handlers
        assert "scheme" in dh._notconfigured

    def test_buggy_handler(self, caplog: pytest.LogCaptureFixture) -> None:
        handlers = {"scheme": BuggyDH}
        crawler = get_crawler(settings_dict={"DOWNLOAD_HANDLERS": handlers})
        dh = DownloadHandlers(crawler)
        assert "scheme" in dh._schemes
        assert "scheme" not in dh._handlers
        assert "scheme" in dh._notconfigured
        assert (
            'Loading "<class \'tests.test_downloader_handlers.BuggyDH\'>" for scheme "scheme"'
            in caplog.text
        )

    def test_disabled_handler(self):
        handlers = {"scheme": None}
        crawler = get_crawler(settings_dict={"DOWNLOAD_HANDLERS": handlers})
        dh = DownloadHandlers(crawler)
        assert "scheme" not in dh._schemes
        for scheme in handlers:  # force load handlers
            dh._get_handler(scheme)
        assert "scheme" not in dh._handlers
        assert "scheme" in dh._notconfigured

    def test_lazy_handlers(self):
        handlers = {"scheme": DummyLazyDH}
        crawler = get_crawler(settings_dict={"DOWNLOAD_HANDLERS": handlers})
        with pytest.warns(
            ScrapyDeprecationWarning,
            match="DummyLazyDH doesn't define a 'lazy' attribute",
        ):
            dh = DownloadHandlers(crawler)
        assert "scheme" in dh._schemes
        assert "scheme" not in dh._handlers
        for scheme in handlers:  # force load lazy handler
            dh._get_handler(scheme)
        assert "scheme" in dh._handlers
        assert "scheme" not in dh._notconfigured


class TestFile:
    def setup_method(self):
        # add a special char to check that they are handled correctly
        self.fd, self.tmpname = mkstemp(suffix="^")
        Path(self.tmpname).write_text("0123456789", encoding="utf-8")
        download_handler = build_from_crawler(FileDownloadHandler, get_crawler())
        self.download_request = download_handler.download_request

    def teardown_method(self):
        os.close(self.fd)
        Path(self.tmpname).unlink()

    @deferred_f_from_coro_f
    async def test_download(self):
        request = Request(path_to_file_uri(self.tmpname))
        assert request.url.upper().endswith("%5E")
        response = await self.download_request(request)
        assert response.url == request.url
        assert response.status == 200
        assert response.body == b"0123456789"
        assert response.protocol is None

    @deferred_f_from_coro_f
    async def test_non_existent(self):
        request = Request(path_to_file_uri(mkdtemp()))
        # the specific exception differs between platforms
        with pytest.raises(OSError):  # noqa: PT011
            await self.download_request(request)


class HttpDownloadHandlerMock:
    def __init__(self, *args, **kwargs):
        pass

    async def download_request(self, request):
        return request


@pytest.mark.requires_botocore
class TestS3Anon:
    def setup_method(self):
        crawler = get_crawler()
        with mock.patch(
            "scrapy.core.downloader.handlers.s3.HTTP11DownloadHandler",
            HttpDownloadHandlerMock,
        ):
            self.s3reqh = build_from_crawler(S3DownloadHandler, crawler)
        self.download_request = self.s3reqh.download_request

    @deferred_f_from_coro_f
    async def test_anon_request(self):
        req = Request("s3://aws-publicdatasets/")
        httpreq = await self.download_request(req)
        assert hasattr(self.s3reqh, "anon")
        assert self.s3reqh.anon
        assert httpreq.url == "http://aws-publicdatasets.s3.amazonaws.com/"


@pytest.mark.requires_botocore
class TestS3:
    def setup_method(self):
        # test use same example keys than amazon developer guide
        # http://s3.amazonaws.com/awsdocs/S3/20060301/s3-dg-20060301.pdf
        # and the tests described here are the examples from that manual
        crawler = get_crawler(
            settings_dict={
                "AWS_ACCESS_KEY_ID": "0PN5J17HBGZHT7JJ3X82",
                "AWS_SECRET_ACCESS_KEY": "uV3F3YluFJax1cknvbcGwgjvx4QpvB+leU8dUj2o",
            }
        )
        with mock.patch(
            "scrapy.core.downloader.handlers.s3.HTTP11DownloadHandler",
            HttpDownloadHandlerMock,
        ):
            s3reqh = build_from_crawler(S3DownloadHandler, crawler)
        self.download_request = s3reqh.download_request

    @contextlib.contextmanager
    def _mocked_date(self, date):
        try:
            import botocore.auth  # noqa: F401,PLC0415
        except ImportError:
            yield
        else:
            # We need to mock botocore.auth.formatdate, because otherwise
            # botocore overrides Date header with current date and time
            # and Authorization header is different each time
            with mock.patch("botocore.auth.formatdate") as mock_formatdate:
                mock_formatdate.return_value = date
                yield

    @deferred_f_from_coro_f
    async def test_request_signing1(self):
        # gets an object from the johnsmith bucket.
        date = "Tue, 27 Mar 2007 19:36:42 +0000"
        req = Request("s3://johnsmith/photos/puppy.jpg", headers={"Date": date})
        with self._mocked_date(date):
            httpreq = await self.download_request(req)
        assert (
            httpreq.headers["Authorization"]
            == b"AWS 0PN5J17HBGZHT7JJ3X82:xXjDGYUmKxnwqr5KXNPGldn5LbA="
        )

    @deferred_f_from_coro_f
    async def test_request_signing2(self):
        # puts an object into the johnsmith bucket.
        date = "Tue, 27 Mar 2007 21:15:45 +0000"
        req = Request(
            "s3://johnsmith/photos/puppy.jpg",
            method="PUT",
            headers={
                "Content-Type": "image/jpeg",
                "Date": date,
                "Content-Length": "94328",
            },
        )
        with self._mocked_date(date):
            httpreq = await self.download_request(req)
        assert (
            httpreq.headers["Authorization"]
            == b"AWS 0PN5J17HBGZHT7JJ3X82:hcicpDDvL9SsO6AkvxqmIWkmOuQ="
        )

    @deferred_f_from_coro_f
    async def test_request_signing3(self):
        # lists the content of the johnsmith bucket.
        date = "Tue, 27 Mar 2007 19:42:41 +0000"
        req = Request(
            "s3://johnsmith/?prefix=photos&max-keys=50&marker=puppy",
            method="GET",
            headers={
                "User-Agent": "Mozilla/5.0",
                "Date": date,
            },
        )
        with self._mocked_date(date):
            httpreq = await self.download_request(req)
        assert (
            httpreq.headers["Authorization"]
            == b"AWS 0PN5J17HBGZHT7JJ3X82:jsRt/rhG+Vtp88HrYL706QhE4w4="
        )

    @deferred_f_from_coro_f
    async def test_request_signing4(self):
        # fetches the access control policy sub-resource for the 'johnsmith' bucket.
        date = "Tue, 27 Mar 2007 19:44:46 +0000"
        req = Request("s3://johnsmith/?acl", method="GET", headers={"Date": date})
        with self._mocked_date(date):
            httpreq = await self.download_request(req)
        assert (
            httpreq.headers["Authorization"]
            == b"AWS 0PN5J17HBGZHT7JJ3X82:thdUi9VAkzhkniLj96JIrOPGi0g="
        )

    @deferred_f_from_coro_f
    async def test_request_signing6(self):
        # uploads an object to a CNAME style virtual hosted bucket with metadata.
        date = "Tue, 27 Mar 2007 21:06:08 +0000"
        req = Request(
            "s3://static.johnsmith.net:8080/db-backup.dat.gz",
            method="PUT",
            headers={
                "User-Agent": "curl/7.15.5",
                "Host": "static.johnsmith.net:8080",
                "Date": date,
                "x-amz-acl": "public-read",
                "content-type": "application/x-download",
                "Content-MD5": "4gJE4saaMU4BqNR0kLY+lw==",
                "X-Amz-Meta-ReviewedBy": "joe@johnsmith.net,jane@johnsmith.net",
                "X-Amz-Meta-FileChecksum": "0x02661779",
                "X-Amz-Meta-ChecksumAlgorithm": "crc32",
                "Content-Disposition": "attachment; filename=database.dat",
                "Content-Encoding": "gzip",
                "Content-Length": "5913339",
            },
        )
        with self._mocked_date(date):
            httpreq = await self.download_request(req)
        assert (
            httpreq.headers["Authorization"]
            == b"AWS 0PN5J17HBGZHT7JJ3X82:C0FlOtU8Ylb9KDTpZqYkZPX91iI="
        )

    @deferred_f_from_coro_f
    async def test_request_signing7(self):
        # ensure that spaces are quoted properly before signing
        date = "Tue, 27 Mar 2007 19:42:41 +0000"
        req = Request(
            "s3://johnsmith/photos/my puppy.jpg?response-content-disposition=my puppy.jpg",
            method="GET",
            headers={"Date": date},
        )
        with self._mocked_date(date):
            httpreq = await self.download_request(req)
        assert (
            httpreq.headers["Authorization"]
            == b"AWS 0PN5J17HBGZHT7JJ3X82:+CfvG8EZ3YccOrRVMXNaK2eKZmM="
        )


@pytest.mark.skipif(is_botocore_available(), reason="Requires not having botocore")
def test_s3_no_botocore() -> None:
    crawler = get_crawler()
    with pytest.raises(NotConfigured, match="missing botocore library"):
        build_from_crawler(S3DownloadHandler, crawler)


class TestDataURI:
    def setup_method(self):
        crawler = get_crawler()
        download_handler = build_from_crawler(DataURIDownloadHandler, crawler)
        self.download_request = download_handler.download_request

    @deferred_f_from_coro_f
    async def test_response_attrs(self):
        uri = "data:,A%20brief%20note"
        request = Request(uri)
        response = await self.download_request(request)
        assert response.url == uri
        assert not response.headers

    @deferred_f_from_coro_f
    async def test_default_mediatype_encoding(self):
        request = Request("data:,A%20brief%20note")
        response = await self.download_request(request)
        assert response.text == "A brief note"
        assert type(response) is responsetypes.from_mimetype("text/plain")  # pylint: disable=unidiomatic-typecheck
        assert response.encoding == "US-ASCII"

    @deferred_f_from_coro_f
    async def test_default_mediatype(self):
        request = Request("data:;charset=iso-8859-7,%be%d3%be")
        response = await self.download_request(request)
        assert response.text == "\u038e\u03a3\u038e"
        assert type(response) is responsetypes.from_mimetype("text/plain")  # pylint: disable=unidiomatic-typecheck
        assert response.encoding == "iso-8859-7"

    @deferred_f_from_coro_f
    async def test_text_charset(self):
        request = Request("data:text/plain;charset=iso-8859-7,%be%d3%be")
        response = await self.download_request(request)
        assert response.text == "\u038e\u03a3\u038e"
        assert response.body == b"\xbe\xd3\xbe"
        assert response.encoding == "iso-8859-7"

    @deferred_f_from_coro_f
    async def test_mediatype_parameters(self):
        request = Request(
            "data:text/plain;foo=%22foo;bar%5C%22%22;"
            "charset=utf-8;bar=%22foo;%5C%22 foo ;/,%22"
            ",%CE%8E%CE%A3%CE%8E"
        )
        response = await self.download_request(request)
        assert response.text == "\u038e\u03a3\u038e"
        assert type(response) is responsetypes.from_mimetype("text/plain")  # pylint: disable=unidiomatic-typecheck
        assert response.encoding == "utf-8"

    @deferred_f_from_coro_f
    async def test_base64(self):
        request = Request("data:text/plain;base64,SGVsbG8sIHdvcmxkLg%3D%3D")
        response = await self.download_request(request)
        assert response.text == "Hello, world."

    @deferred_f_from_coro_f
    async def test_protocol(self):
        request = Request("data:,")
        response = await self.download_request(request)
        assert response.protocol is None