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
|
from __future__ import print_function
from testfixtures import LogCapture
from twisted.trial import unittest
from twisted.python.failure import Failure
from twisted.internet import reactor
from twisted.internet.defer import Deferred, inlineCallbacks
from scrapy.http import Request, Response
from scrapy.settings import Settings
from scrapy.spiders import Spider
from scrapy.utils.request import request_fingerprint
from scrapy.pipelines.media import MediaPipeline
from scrapy.utils.log import failure_to_exc_info
from scrapy.utils.signal import disconnect_all
from scrapy import signals
def _mocked_download_func(request, info):
response = request.meta.get('response')
return response() if callable(response) else response
class BaseMediaPipelineTestCase(unittest.TestCase):
pipeline_class = MediaPipeline
settings = None
def setUp(self):
self.spider = Spider('media.com')
self.pipe = self.pipeline_class(download_func=_mocked_download_func,
settings=Settings(self.settings))
self.pipe.open_spider(self.spider)
self.info = self.pipe.spiderinfo
def tearDown(self):
for name, signal in vars(signals).items():
if not name.startswith('_'):
disconnect_all(signal)
def test_default_media_to_download(self):
request = Request('http://url')
assert self.pipe.media_to_download(request, self.info) is None
def test_default_get_media_requests(self):
item = dict(name='name')
assert self.pipe.get_media_requests(item, self.info) is None
def test_default_media_downloaded(self):
request = Request('http://url')
response = Response('http://url', body=b'')
assert self.pipe.media_downloaded(response, request, self.info) is response
def test_default_media_failed(self):
request = Request('http://url')
fail = Failure(Exception())
assert self.pipe.media_failed(fail, request, self.info) is fail
def test_default_item_completed(self):
item = dict(name='name')
assert self.pipe.item_completed([], item, self.info) is item
# Check that failures are logged by default
fail = Failure(Exception())
results = [(True, 1), (False, fail)]
with LogCapture() as l:
new_item = self.pipe.item_completed(results, item, self.info)
assert new_item is item
assert len(l.records) == 1
record = l.records[0]
assert record.levelname == 'ERROR'
self.assertTupleEqual(record.exc_info, failure_to_exc_info(fail))
# disable failure logging and check again
self.pipe.LOG_FAILED_RESULTS = False
with LogCapture() as l:
new_item = self.pipe.item_completed(results, item, self.info)
assert new_item is item
assert len(l.records) == 0
@inlineCallbacks
def test_default_process_item(self):
item = dict(name='name')
new_item = yield self.pipe.process_item(item, self.spider)
assert new_item is item
def test_modify_media_request(self):
request = Request('http://url')
self.pipe._modify_media_request(request)
assert request.meta == {'handle_httpstatus_all': True}
class MockedMediaPipeline(MediaPipeline):
def __init__(self, *args, **kwargs):
super(MockedMediaPipeline, self).__init__(*args, **kwargs)
self._mockcalled = []
def download(self, request, info):
self._mockcalled.append('download')
return super(MockedMediaPipeline, self).download(request, info)
def media_to_download(self, request, info):
self._mockcalled.append('media_to_download')
if 'result' in request.meta:
return request.meta.get('result')
return super(MockedMediaPipeline, self).media_to_download(request, info)
def get_media_requests(self, item, info):
self._mockcalled.append('get_media_requests')
return item.get('requests')
def media_downloaded(self, response, request, info):
self._mockcalled.append('media_downloaded')
return super(MockedMediaPipeline, self).media_downloaded(response, request, info)
def media_failed(self, failure, request, info):
self._mockcalled.append('media_failed')
return super(MockedMediaPipeline, self).media_failed(failure, request, info)
def item_completed(self, results, item, info):
self._mockcalled.append('item_completed')
item = super(MockedMediaPipeline, self).item_completed(results, item, info)
item['results'] = results
return item
class MediaPipelineTestCase(BaseMediaPipelineTestCase):
pipeline_class = MockedMediaPipeline
@inlineCallbacks
def test_result_succeed(self):
cb = lambda _: self.pipe._mockcalled.append('request_callback') or _
eb = lambda _: self.pipe._mockcalled.append('request_errback') or _
rsp = Response('http://url1')
req = Request('http://url1', meta=dict(response=rsp), callback=cb, errback=eb)
item = dict(requests=req)
new_item = yield self.pipe.process_item(item, self.spider)
self.assertEqual(new_item['results'], [(True, rsp)])
self.assertEqual(self.pipe._mockcalled,
['get_media_requests', 'media_to_download',
'media_downloaded', 'request_callback', 'item_completed'])
@inlineCallbacks
def test_result_failure(self):
self.pipe.LOG_FAILED_RESULTS = False
cb = lambda _: self.pipe._mockcalled.append('request_callback') or _
eb = lambda _: self.pipe._mockcalled.append('request_errback') or _
fail = Failure(Exception())
req = Request('http://url1', meta=dict(response=fail), callback=cb, errback=eb)
item = dict(requests=req)
new_item = yield self.pipe.process_item(item, self.spider)
self.assertEqual(new_item['results'], [(False, fail)])
self.assertEqual(self.pipe._mockcalled,
['get_media_requests', 'media_to_download',
'media_failed', 'request_errback', 'item_completed'])
@inlineCallbacks
def test_mix_of_success_and_failure(self):
self.pipe.LOG_FAILED_RESULTS = False
rsp1 = Response('http://url1')
req1 = Request('http://url1', meta=dict(response=rsp1))
fail = Failure(Exception())
req2 = Request('http://url2', meta=dict(response=fail))
item = dict(requests=[req1, req2])
new_item = yield self.pipe.process_item(item, self.spider)
self.assertEqual(new_item['results'], [(True, rsp1), (False, fail)])
m = self.pipe._mockcalled
# only once
self.assertEqual(m[0], 'get_media_requests') # first hook called
self.assertEqual(m.count('get_media_requests'), 1)
self.assertEqual(m.count('item_completed'), 1)
self.assertEqual(m[-1], 'item_completed') # last hook called
# twice, one per request
self.assertEqual(m.count('media_to_download'), 2)
# one to handle success and other for failure
self.assertEqual(m.count('media_downloaded'), 1)
self.assertEqual(m.count('media_failed'), 1)
@inlineCallbacks
def test_get_media_requests(self):
# returns single Request (without callback)
req = Request('http://url')
item = dict(requests=req) # pass a single item
new_item = yield self.pipe.process_item(item, self.spider)
assert new_item is item
assert request_fingerprint(req) in self.info.downloaded
# returns iterable of Requests
req1 = Request('http://url1')
req2 = Request('http://url2')
item = dict(requests=iter([req1, req2]))
new_item = yield self.pipe.process_item(item, self.spider)
assert new_item is item
assert request_fingerprint(req1) in self.info.downloaded
assert request_fingerprint(req2) in self.info.downloaded
@inlineCallbacks
def test_results_are_cached_across_multiple_items(self):
rsp1 = Response('http://url1')
req1 = Request('http://url1', meta=dict(response=rsp1))
item = dict(requests=req1)
new_item = yield self.pipe.process_item(item, self.spider)
self.assertTrue(new_item is item)
self.assertEqual(new_item['results'], [(True, rsp1)])
# rsp2 is ignored, rsp1 must be in results because request fingerprints are the same
req2 = Request(req1.url, meta=dict(response=Response('http://donot.download.me')))
item = dict(requests=req2)
new_item = yield self.pipe.process_item(item, self.spider)
self.assertTrue(new_item is item)
self.assertEqual(request_fingerprint(req1), request_fingerprint(req2))
self.assertEqual(new_item['results'], [(True, rsp1)])
@inlineCallbacks
def test_results_are_cached_for_requests_of_single_item(self):
rsp1 = Response('http://url1')
req1 = Request('http://url1', meta=dict(response=rsp1))
req2 = Request(req1.url, meta=dict(response=Response('http://donot.download.me')))
item = dict(requests=[req1, req2])
new_item = yield self.pipe.process_item(item, self.spider)
self.assertTrue(new_item is item)
self.assertEqual(new_item['results'], [(True, rsp1), (True, rsp1)])
@inlineCallbacks
def test_wait_if_request_is_downloading(self):
def _check_downloading(response):
fp = request_fingerprint(req1)
self.assertTrue(fp in self.info.downloading)
self.assertTrue(fp in self.info.waiting)
self.assertTrue(fp not in self.info.downloaded)
self.assertEqual(len(self.info.waiting[fp]), 2)
return response
rsp1 = Response('http://url')
def rsp1_func():
dfd = Deferred().addCallback(_check_downloading)
reactor.callLater(.1, dfd.callback, rsp1)
return dfd
def rsp2_func():
self.fail('it must cache rsp1 result and must not try to redownload')
req1 = Request('http://url', meta=dict(response=rsp1_func))
req2 = Request(req1.url, meta=dict(response=rsp2_func))
item = dict(requests=[req1, req2])
new_item = yield self.pipe.process_item(item, self.spider)
self.assertEqual(new_item['results'], [(True, rsp1), (True, rsp1)])
@inlineCallbacks
def test_use_media_to_download_result(self):
req = Request('http://url', meta=dict(result='ITSME', response=self.fail))
item = dict(requests=req)
new_item = yield self.pipe.process_item(item, self.spider)
self.assertEqual(new_item['results'], [(True, 'ITSME')])
self.assertEqual(self.pipe._mockcalled, \
['get_media_requests', 'media_to_download', 'item_completed'])
class MediaPipelineAllowRedirectSettingsTestCase(unittest.TestCase):
def _assert_request_no3xx(self, pipeline_class, settings):
pipe = pipeline_class(settings=Settings(settings))
request = Request('http://url')
pipe._modify_media_request(request)
self.assertIn('handle_httpstatus_list', request.meta)
for status, check in [
(200, True),
# These are the status codes we want
# the downloader to handle itself
(301, False),
(302, False),
(302, False),
(307, False),
(308, False),
# we still want to get 4xx and 5xx
(400, True),
(404, True),
(500, True)]:
if check:
self.assertIn(status, request.meta['handle_httpstatus_list'])
else:
self.assertNotIn(status, request.meta['handle_httpstatus_list'])
def test_standard_setting(self):
self._assert_request_no3xx(
MediaPipeline,
{
'MEDIA_ALLOW_REDIRECTS': True
})
def test_subclass_standard_setting(self):
class UserDefinedPipeline(MediaPipeline):
pass
self._assert_request_no3xx(
UserDefinedPipeline,
{
'MEDIA_ALLOW_REDIRECTS': True
})
def test_subclass_specific_setting(self):
class UserDefinedPipeline(MediaPipeline):
pass
self._assert_request_no3xx(
UserDefinedPipeline,
{
'USERDEFINEDPIPELINE_MEDIA_ALLOW_REDIRECTS': True
})
|
