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
|
import shutil
import tempfile
import unittest
import collections
from twisted.internet import defer
from twisted.trial.unittest import TestCase
from scrapy.crawler import Crawler
from scrapy.core.downloader import Downloader
from scrapy.core.scheduler import Scheduler
from scrapy.http import Request
from scrapy.spiders import Spider
from scrapy.utils.httpobj import urlparse_cached
from scrapy.utils.test import get_crawler
from tests.mockserver import MockServer
MockEngine = collections.namedtuple('MockEngine', ['downloader'])
MockSlot = collections.namedtuple('MockSlot', ['active'])
class MockDownloader:
def __init__(self):
self.slots = dict()
def _get_slot_key(self, request, spider):
if Downloader.DOWNLOAD_SLOT in request.meta:
return request.meta[Downloader.DOWNLOAD_SLOT]
return urlparse_cached(request).hostname or ''
def increment(self, slot_key):
slot = self.slots.setdefault(slot_key, MockSlot(active=list()))
slot.active.append(1)
def decrement(self, slot_key):
slot = self.slots.get(slot_key)
slot.active.pop()
def close(self):
pass
class MockCrawler(Crawler):
def __init__(self, priority_queue_cls, jobdir):
settings = dict(
SCHEDULER_DEBUG=False,
SCHEDULER_DISK_QUEUE='scrapy.squeues.PickleLifoDiskQueue',
SCHEDULER_MEMORY_QUEUE='scrapy.squeues.LifoMemoryQueue',
SCHEDULER_PRIORITY_QUEUE=priority_queue_cls,
JOBDIR=jobdir,
DUPEFILTER_CLASS='scrapy.dupefilters.BaseDupeFilter',
)
super().__init__(Spider, settings)
self.engine = MockEngine(downloader=MockDownloader())
class SchedulerHandler:
priority_queue_cls = None
jobdir = None
def create_scheduler(self):
self.mock_crawler = MockCrawler(self.priority_queue_cls, self.jobdir)
self.scheduler = Scheduler.from_crawler(self.mock_crawler)
self.spider = Spider(name='spider')
self.scheduler.open(self.spider)
def close_scheduler(self):
self.scheduler.close('finished')
self.mock_crawler.stop()
self.mock_crawler.engine.downloader.close()
def setUp(self):
self.create_scheduler()
def tearDown(self):
self.close_scheduler()
_PRIORITIES = [("http://foo.com/a", -2),
("http://foo.com/d", 1),
("http://foo.com/b", -1),
("http://foo.com/c", 0),
("http://foo.com/e", 2)]
_URLS = {"http://foo.com/a", "http://foo.com/b", "http://foo.com/c"}
class BaseSchedulerInMemoryTester(SchedulerHandler):
def test_length(self):
self.assertFalse(self.scheduler.has_pending_requests())
self.assertEqual(len(self.scheduler), 0)
for url in _URLS:
self.scheduler.enqueue_request(Request(url))
self.assertTrue(self.scheduler.has_pending_requests())
self.assertEqual(len(self.scheduler), len(_URLS))
def test_dequeue(self):
for url in _URLS:
self.scheduler.enqueue_request(Request(url))
urls = set()
while self.scheduler.has_pending_requests():
urls.add(self.scheduler.next_request().url)
self.assertEqual(urls, _URLS)
def test_dequeue_priorities(self):
for url, priority in _PRIORITIES:
self.scheduler.enqueue_request(Request(url, priority=priority))
priorities = list()
while self.scheduler.has_pending_requests():
priorities.append(self.scheduler.next_request().priority)
self.assertEqual(priorities,
sorted([x[1] for x in _PRIORITIES], key=lambda x: -x))
class BaseSchedulerOnDiskTester(SchedulerHandler):
def setUp(self):
self.jobdir = tempfile.mkdtemp()
self.create_scheduler()
def tearDown(self):
self.close_scheduler()
shutil.rmtree(self.jobdir)
self.jobdir = None
def test_length(self):
self.assertFalse(self.scheduler.has_pending_requests())
self.assertEqual(len(self.scheduler), 0)
for url in _URLS:
self.scheduler.enqueue_request(Request(url))
self.close_scheduler()
self.create_scheduler()
self.assertTrue(self.scheduler.has_pending_requests())
self.assertEqual(len(self.scheduler), len(_URLS))
def test_dequeue(self):
for url in _URLS:
self.scheduler.enqueue_request(Request(url))
self.close_scheduler()
self.create_scheduler()
urls = set()
while self.scheduler.has_pending_requests():
urls.add(self.scheduler.next_request().url)
self.assertEqual(urls, _URLS)
def test_dequeue_priorities(self):
for url, priority in _PRIORITIES:
self.scheduler.enqueue_request(Request(url, priority=priority))
self.close_scheduler()
self.create_scheduler()
priorities = list()
while self.scheduler.has_pending_requests():
priorities.append(self.scheduler.next_request().priority)
self.assertEqual(priorities,
sorted([x[1] for x in _PRIORITIES], key=lambda x: -x))
class TestSchedulerInMemory(BaseSchedulerInMemoryTester, unittest.TestCase):
priority_queue_cls = 'scrapy.pqueues.ScrapyPriorityQueue'
class TestSchedulerOnDisk(BaseSchedulerOnDiskTester, unittest.TestCase):
priority_queue_cls = 'scrapy.pqueues.ScrapyPriorityQueue'
_URLS_WITH_SLOTS = [("http://foo.com/a", 'a'),
("http://foo.com/b", 'a'),
("http://foo.com/c", 'b'),
("http://foo.com/d", 'b'),
("http://foo.com/e", 'c'),
("http://foo.com/f", 'c')]
class TestMigration(unittest.TestCase):
def setUp(self):
self.tmpdir = tempfile.mkdtemp()
def tearDown(self):
shutil.rmtree(self.tmpdir)
def _migration(self, tmp_dir):
prev_scheduler_handler = SchedulerHandler()
prev_scheduler_handler.priority_queue_cls = 'scrapy.pqueues.ScrapyPriorityQueue'
prev_scheduler_handler.jobdir = tmp_dir
prev_scheduler_handler.create_scheduler()
for url in _URLS:
prev_scheduler_handler.scheduler.enqueue_request(Request(url))
prev_scheduler_handler.close_scheduler()
next_scheduler_handler = SchedulerHandler()
next_scheduler_handler.priority_queue_cls = 'scrapy.pqueues.DownloaderAwarePriorityQueue'
next_scheduler_handler.jobdir = tmp_dir
next_scheduler_handler.create_scheduler()
def test_migration(self):
with self.assertRaises(ValueError):
self._migration(self.tmpdir)
def _is_scheduling_fair(enqueued_slots, dequeued_slots):
"""
We enqueued same number of requests for every slot.
Assert correct order, e.g.
>>> enqueued = ['a', 'b', 'c'] * 2
>>> correct = ['a', 'c', 'b', 'b', 'a', 'c']
>>> incorrect = ['a', 'a', 'b', 'c', 'c', 'b']
>>> _is_scheduling_fair(enqueued, correct)
True
>>> _is_scheduling_fair(enqueued, incorrect)
False
"""
if len(dequeued_slots) != len(enqueued_slots):
return False
slots_number = len(set(enqueued_slots))
for i in range(0, len(dequeued_slots), slots_number):
part = dequeued_slots[i:i + slots_number]
if len(part) != len(set(part)):
return False
return True
class DownloaderAwareSchedulerTestMixin:
priority_queue_cls = 'scrapy.pqueues.DownloaderAwarePriorityQueue'
reopen = False
def test_logic(self):
for url, slot in _URLS_WITH_SLOTS:
request = Request(url)
request.meta[Downloader.DOWNLOAD_SLOT] = slot
self.scheduler.enqueue_request(request)
if self.reopen:
self.close_scheduler()
self.create_scheduler()
dequeued_slots = list()
requests = []
downloader = self.mock_crawler.engine.downloader
while self.scheduler.has_pending_requests():
request = self.scheduler.next_request()
# pylint: disable=protected-access
slot = downloader._get_slot_key(request, None)
dequeued_slots.append(slot)
downloader.increment(slot)
requests.append(request)
for request in requests:
# pylint: disable=protected-access
slot = downloader._get_slot_key(request, None)
downloader.decrement(slot)
self.assertTrue(_is_scheduling_fair(list(s for u, s in _URLS_WITH_SLOTS),
dequeued_slots))
self.assertEqual(sum(len(s.active) for s in downloader.slots.values()), 0)
class TestSchedulerWithDownloaderAwareInMemory(DownloaderAwareSchedulerTestMixin,
BaseSchedulerInMemoryTester,
unittest.TestCase):
pass
class TestSchedulerWithDownloaderAwareOnDisk(DownloaderAwareSchedulerTestMixin,
BaseSchedulerOnDiskTester,
unittest.TestCase):
reopen = True
class StartUrlsSpider(Spider):
def __init__(self, start_urls):
self.start_urls = start_urls
super().__init__(name='StartUrlsSpider')
def parse(self, response):
pass
class TestIntegrationWithDownloaderAwareInMemory(TestCase):
def setUp(self):
self.crawler = get_crawler(
spidercls=StartUrlsSpider,
settings_dict={
'SCHEDULER_PRIORITY_QUEUE': 'scrapy.pqueues.DownloaderAwarePriorityQueue',
'DUPEFILTER_CLASS': 'scrapy.dupefilters.BaseDupeFilter',
},
)
@defer.inlineCallbacks
def tearDown(self):
yield self.crawler.stop()
@defer.inlineCallbacks
def test_integration_downloader_aware_priority_queue(self):
with MockServer() as mockserver:
url = mockserver.url("/status?n=200", is_secure=False)
start_urls = [url] * 6
yield self.crawler.crawl(start_urls)
self.assertEqual(self.crawler.stats.get_value('downloader/response_count'),
len(start_urls))
class TestIncompatibility(unittest.TestCase):
def _incompatible(self):
settings = dict(
SCHEDULER_PRIORITY_QUEUE='scrapy.pqueues.DownloaderAwarePriorityQueue',
CONCURRENT_REQUESTS_PER_IP=1,
)
crawler = Crawler(Spider, settings)
scheduler = Scheduler.from_crawler(crawler)
spider = Spider(name='spider')
scheduler.open(spider)
def test_incompatibility(self):
with self.assertRaises(ValueError):
self._incompatible()
|
