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
|
import warnings
import pytest
from scrapy import Request, Spider
from scrapy.downloadermiddlewares.offsite import OffsiteMiddleware
from scrapy.exceptions import IgnoreRequest
from scrapy.utils.test import get_crawler
UNSET = object()
@pytest.mark.parametrize(
("allowed_domain", "url", "allowed"),
[
("example.com", "http://example.com/1", True),
("example.com", "http://example.org/1", False),
("example.com", "http://sub.example.com/1", True),
("sub.example.com", "http://sub.example.com/1", True),
("sub.example.com", "http://example.com/1", False),
("example.com", "http://example.com:8000/1", True),
("example.com", "http://example.org/example.com", False),
("example.com", "http://example.org/foo.example.com", False),
("example.com", "http://example.com.example", False),
("a.example", "http://nota.example", False),
("b.a.example", "http://notb.a.example", False),
],
)
def test_process_request_domain_filtering(allowed_domain, url, allowed):
crawler = get_crawler(Spider)
spider = crawler._create_spider(name="a", allowed_domains=[allowed_domain])
mw = OffsiteMiddleware.from_crawler(crawler)
mw.spider_opened(spider)
request = Request(url)
if allowed:
assert mw.process_request(request, spider) is None
else:
with pytest.raises(IgnoreRequest):
mw.process_request(request, spider)
@pytest.mark.parametrize(
("value", "filtered"),
[
(UNSET, True),
(None, True),
(False, True),
(True, False),
],
)
def test_process_request_dont_filter(value, filtered):
crawler = get_crawler(Spider)
spider = crawler._create_spider(name="a", allowed_domains=["a.example"])
mw = OffsiteMiddleware.from_crawler(crawler)
mw.spider_opened(spider)
kwargs = {}
if value is not UNSET:
kwargs["dont_filter"] = value
request = Request("https://b.example", **kwargs)
if filtered:
with pytest.raises(IgnoreRequest):
mw.process_request(request, spider)
else:
assert mw.process_request(request, spider) is None
@pytest.mark.parametrize(
("allow_offsite", "dont_filter", "filtered"),
[
(True, UNSET, False),
(True, None, False),
(True, False, False),
(True, True, False),
(False, UNSET, True),
(False, None, True),
(False, False, True),
(False, True, False),
],
)
def test_process_request_allow_offsite(allow_offsite, dont_filter, filtered):
crawler = get_crawler(Spider)
spider = crawler._create_spider(name="a", allowed_domains=["a.example"])
mw = OffsiteMiddleware.from_crawler(crawler)
mw.spider_opened(spider)
kwargs = {"meta": {}}
if allow_offsite is not UNSET:
kwargs["meta"]["allow_offsite"] = allow_offsite
if dont_filter is not UNSET:
kwargs["dont_filter"] = dont_filter
request = Request("https://b.example", **kwargs)
if filtered:
with pytest.raises(IgnoreRequest):
mw.process_request(request, spider)
else:
assert mw.process_request(request, spider) is None
@pytest.mark.parametrize(
"value",
[
UNSET,
None,
[],
],
)
def test_process_request_no_allowed_domains(value):
crawler = get_crawler(Spider)
kwargs = {}
if value is not UNSET:
kwargs["allowed_domains"] = value
spider = crawler._create_spider(name="a", **kwargs)
mw = OffsiteMiddleware.from_crawler(crawler)
mw.spider_opened(spider)
request = Request("https://example.com")
assert mw.process_request(request, spider) is None
def test_process_request_invalid_domains():
crawler = get_crawler(Spider)
allowed_domains = ["a.example", None, "http:////b.example", "//c.example"]
spider = crawler._create_spider(name="a", allowed_domains=allowed_domains)
mw = OffsiteMiddleware.from_crawler(crawler)
with warnings.catch_warnings():
warnings.simplefilter("ignore", UserWarning)
mw.spider_opened(spider)
request = Request("https://a.example")
assert mw.process_request(request, spider) is None
for letter in ("b", "c"):
request = Request(f"https://{letter}.example")
with pytest.raises(IgnoreRequest):
mw.process_request(request, spider)
@pytest.mark.parametrize(
("allowed_domain", "url", "allowed"),
[
("example.com", "http://example.com/1", True),
("example.com", "http://example.org/1", False),
("example.com", "http://sub.example.com/1", True),
("sub.example.com", "http://sub.example.com/1", True),
("sub.example.com", "http://example.com/1", False),
("example.com", "http://example.com:8000/1", True),
("example.com", "http://example.org/example.com", False),
("example.com", "http://example.org/foo.example.com", False),
("example.com", "http://example.com.example", False),
("a.example", "http://nota.example", False),
("b.a.example", "http://notb.a.example", False),
],
)
def test_request_scheduled_domain_filtering(allowed_domain, url, allowed):
crawler = get_crawler(Spider)
spider = crawler._create_spider(name="a", allowed_domains=[allowed_domain])
mw = OffsiteMiddleware.from_crawler(crawler)
mw.spider_opened(spider)
request = Request(url)
if allowed:
assert mw.request_scheduled(request, spider) is None
else:
with pytest.raises(IgnoreRequest):
mw.request_scheduled(request, spider)
@pytest.mark.parametrize(
("value", "filtered"),
[
(UNSET, True),
(None, True),
(False, True),
(True, False),
],
)
def test_request_scheduled_dont_filter(value, filtered):
crawler = get_crawler(Spider)
spider = crawler._create_spider(name="a", allowed_domains=["a.example"])
mw = OffsiteMiddleware.from_crawler(crawler)
mw.spider_opened(spider)
kwargs = {}
if value is not UNSET:
kwargs["dont_filter"] = value
request = Request("https://b.example", **kwargs)
if filtered:
with pytest.raises(IgnoreRequest):
mw.request_scheduled(request, spider)
else:
assert mw.request_scheduled(request, spider) is None
@pytest.mark.parametrize(
"value",
[
UNSET,
None,
[],
],
)
def test_request_scheduled_no_allowed_domains(value):
crawler = get_crawler(Spider)
kwargs = {}
if value is not UNSET:
kwargs["allowed_domains"] = value
spider = crawler._create_spider(name="a", **kwargs)
mw = OffsiteMiddleware.from_crawler(crawler)
mw.spider_opened(spider)
request = Request("https://example.com")
assert mw.request_scheduled(request, spider) is None
def test_request_scheduled_invalid_domains():
crawler = get_crawler(Spider)
allowed_domains = ["a.example", None, "http:////b.example", "//c.example"]
spider = crawler._create_spider(name="a", allowed_domains=allowed_domains)
mw = OffsiteMiddleware.from_crawler(crawler)
with warnings.catch_warnings():
warnings.simplefilter("ignore", UserWarning)
mw.spider_opened(spider)
request = Request("https://a.example")
assert mw.request_scheduled(request, spider) is None
for letter in ("b", "c"):
request = Request(f"https://{letter}.example")
with pytest.raises(IgnoreRequest):
mw.request_scheduled(request, spider)
|
