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
|
import hashlib
import shutil
import sys
import tempfile
from pathlib import Path
from warnings import catch_warnings
from testfixtures import LogCapture
from scrapy.core.scheduler import Scheduler
from scrapy.dupefilters import BaseDupeFilter, RFPDupeFilter
from scrapy.exceptions import ScrapyDeprecationWarning
from scrapy.http import Request
from scrapy.utils.python import to_bytes
from scrapy.utils.test import get_crawler
from tests.spiders import SimpleSpider
def _get_dupefilter(*, crawler=None, settings=None, open=True):
if crawler is None:
crawler = get_crawler(settings_dict=settings)
scheduler = Scheduler.from_crawler(crawler)
dupefilter = scheduler.df
if open:
dupefilter.open()
return dupefilter
class FromCrawlerRFPDupeFilter(RFPDupeFilter):
@classmethod
def from_crawler(cls, crawler):
df = super().from_crawler(crawler)
df.method = "from_crawler"
return df
class DirectDupeFilter:
method = "n/a"
class TestRFPDupeFilter:
def test_df_from_crawler_scheduler(self):
settings = {
"DUPEFILTER_DEBUG": True,
"DUPEFILTER_CLASS": FromCrawlerRFPDupeFilter,
}
crawler = get_crawler(settings_dict=settings)
scheduler = Scheduler.from_crawler(crawler)
assert scheduler.df.debug
assert scheduler.df.method == "from_crawler"
def test_df_direct_scheduler(self):
settings = {
"DUPEFILTER_CLASS": DirectDupeFilter,
}
crawler = get_crawler(settings_dict=settings)
scheduler = Scheduler.from_crawler(crawler)
assert scheduler.df.method == "n/a"
def test_filter(self):
dupefilter = _get_dupefilter()
r1 = Request("http://scrapytest.org/1")
r2 = Request("http://scrapytest.org/2")
r3 = Request("http://scrapytest.org/2")
assert not dupefilter.request_seen(r1)
assert dupefilter.request_seen(r1)
assert not dupefilter.request_seen(r2)
assert dupefilter.request_seen(r3)
dupefilter.close("finished")
def test_dupefilter_path(self):
r1 = Request("http://scrapytest.org/1")
r2 = Request("http://scrapytest.org/2")
path = tempfile.mkdtemp()
try:
df = _get_dupefilter(settings={"JOBDIR": path}, open=False)
try:
df.open()
assert not df.request_seen(r1)
assert df.request_seen(r1)
finally:
df.close("finished")
df2 = _get_dupefilter(settings={"JOBDIR": path}, open=False)
assert df != df2
try:
df2.open()
assert df2.request_seen(r1)
assert not df2.request_seen(r2)
assert df2.request_seen(r2)
finally:
df2.close("finished")
finally:
shutil.rmtree(path)
def test_request_fingerprint(self):
"""Test if customization of request_fingerprint method will change
output of request_seen.
"""
dupefilter = _get_dupefilter()
r1 = Request("http://scrapytest.org/index.html")
r2 = Request("http://scrapytest.org/INDEX.html")
assert not dupefilter.request_seen(r1)
assert not dupefilter.request_seen(r2)
dupefilter.close("finished")
class RequestFingerprinter:
def fingerprint(self, request):
fp = hashlib.sha1()
fp.update(to_bytes(request.url.lower()))
return fp.digest()
settings = {"REQUEST_FINGERPRINTER_CLASS": RequestFingerprinter}
case_insensitive_dupefilter = _get_dupefilter(settings=settings)
assert not case_insensitive_dupefilter.request_seen(r1)
assert case_insensitive_dupefilter.request_seen(r2)
case_insensitive_dupefilter.close("finished")
def test_seenreq_newlines(self):
r"""Checks against adding duplicate \r to
line endings on Windows platforms."""
r1 = Request("http://scrapytest.org/1")
path = tempfile.mkdtemp()
crawler = get_crawler(settings_dict={"JOBDIR": path})
try:
scheduler = Scheduler.from_crawler(crawler)
df = scheduler.df
df.open()
df.request_seen(r1)
df.close("finished")
with Path(path, "requests.seen").open("rb") as seen_file:
line = next(seen_file).decode()
assert not line.endswith("\r\r\n")
if sys.platform == "win32":
assert line.endswith("\r\n")
else:
assert line.endswith("\n")
finally:
shutil.rmtree(path)
def test_log(self):
with LogCapture() as log:
settings = {
"DUPEFILTER_DEBUG": False,
"DUPEFILTER_CLASS": FromCrawlerRFPDupeFilter,
}
crawler = get_crawler(SimpleSpider, settings_dict=settings)
spider = SimpleSpider.from_crawler(crawler)
dupefilter = _get_dupefilter(crawler=crawler)
r1 = Request("http://scrapytest.org/index.html")
r2 = Request("http://scrapytest.org/index.html")
dupefilter.log(r1, spider)
dupefilter.log(r2, spider)
assert crawler.stats.get_value("dupefilter/filtered") == 2
log.check_present(
(
"scrapy.dupefilters",
"DEBUG",
"Filtered duplicate request: <GET http://scrapytest.org/index.html> - no more"
" duplicates will be shown (see DUPEFILTER_DEBUG to show all duplicates)",
)
)
dupefilter.close("finished")
def test_log_debug(self):
with LogCapture() as log:
settings = {
"DUPEFILTER_DEBUG": True,
"DUPEFILTER_CLASS": FromCrawlerRFPDupeFilter,
}
crawler = get_crawler(SimpleSpider, settings_dict=settings)
spider = SimpleSpider.from_crawler(crawler)
dupefilter = _get_dupefilter(crawler=crawler)
r1 = Request("http://scrapytest.org/index.html")
r2 = Request(
"http://scrapytest.org/index.html",
headers={"Referer": "http://scrapytest.org/INDEX.html"},
)
dupefilter.log(r1, spider)
dupefilter.log(r2, spider)
assert crawler.stats.get_value("dupefilter/filtered") == 2
log.check_present(
(
"scrapy.dupefilters",
"DEBUG",
"Filtered duplicate request: <GET http://scrapytest.org/index.html> (referer: None)",
)
)
log.check_present(
(
"scrapy.dupefilters",
"DEBUG",
"Filtered duplicate request: <GET http://scrapytest.org/index.html>"
" (referer: http://scrapytest.org/INDEX.html)",
)
)
dupefilter.close("finished")
def test_log_debug_default_dupefilter(self):
with LogCapture() as log:
settings = {
"DUPEFILTER_DEBUG": True,
}
crawler = get_crawler(SimpleSpider, settings_dict=settings)
spider = SimpleSpider.from_crawler(crawler)
dupefilter = _get_dupefilter(crawler=crawler)
r1 = Request("http://scrapytest.org/index.html")
r2 = Request(
"http://scrapytest.org/index.html",
headers={"Referer": "http://scrapytest.org/INDEX.html"},
)
dupefilter.log(r1, spider)
dupefilter.log(r2, spider)
assert crawler.stats.get_value("dupefilter/filtered") == 2
log.check_present(
(
"scrapy.dupefilters",
"DEBUG",
"Filtered duplicate request: <GET http://scrapytest.org/index.html> (referer: None)",
)
)
log.check_present(
(
"scrapy.dupefilters",
"DEBUG",
"Filtered duplicate request: <GET http://scrapytest.org/index.html>"
" (referer: http://scrapytest.org/INDEX.html)",
)
)
dupefilter.close("finished")
class TestBaseDupeFilter:
def test_log_deprecation(self):
dupefilter = _get_dupefilter(
settings={"DUPEFILTER_CLASS": BaseDupeFilter},
)
with catch_warnings(record=True) as warning_list:
dupefilter.log(None, None)
assert len(warning_list) == 1
assert (
str(warning_list[0].message)
== "Calling BaseDupeFilter.log() is deprecated."
)
assert warning_list[0].category == ScrapyDeprecationWarning
|
