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
|
import gzip
import inspect
import warnings
from cStringIO import StringIO
from scrapy.utils.trackref import object_ref
from twisted.trial import unittest
from scrapy.spider import Spider, BaseSpider
from scrapy.http import Request, Response, TextResponse, XmlResponse, HtmlResponse
from scrapy.contrib.spiders.init import InitSpider
from scrapy.contrib.spiders import CrawlSpider, Rule, XMLFeedSpider, \
CSVFeedSpider, SitemapSpider
from scrapy.contrib.linkextractors import LinkExtractor
from scrapy.exceptions import ScrapyDeprecationWarning
class SpiderTest(unittest.TestCase):
spider_class = Spider
def setUp(self):
warnings.simplefilter("always")
def tearDown(self):
warnings.resetwarnings()
def test_base_spider(self):
spider = self.spider_class("example.com")
self.assertEqual(spider.name, 'example.com')
self.assertEqual(spider.start_urls, [])
def test_start_requests(self):
spider = self.spider_class('example.com')
start_requests = spider.start_requests()
self.assertTrue(inspect.isgenerator(start_requests))
self.assertEqual(list(start_requests), [])
def test_spider_args(self):
"""Constructor arguments are assigned to spider attributes"""
spider = self.spider_class('example.com', foo='bar')
self.assertEqual(spider.foo, 'bar')
def test_spider_without_name(self):
"""Constructor arguments are assigned to spider attributes"""
self.assertRaises(ValueError, self.spider_class)
self.assertRaises(ValueError, self.spider_class, somearg='foo')
class InitSpiderTest(SpiderTest):
spider_class = InitSpider
class XMLFeedSpiderTest(SpiderTest):
spider_class = XMLFeedSpider
def test_register_namespace(self):
body = """<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns:x="http://www.google.com/schemas/sitemap/0.84"
xmlns:y="http://www.example.com/schemas/extras/1.0">
<url><x:loc>http://www.example.com/Special-Offers.html</loc><y:updated>2009-08-16</updated><other value="bar" y:custom="fuu"/></url>
<url><loc>http://www.example.com/</loc><y:updated>2009-08-16</updated><other value="foo"/></url>
</urlset>"""
response = XmlResponse(url='http://example.com/sitemap.xml', body=body)
class _XMLSpider(self.spider_class):
itertag = 'url'
namespaces = (
('a', 'http://www.google.com/schemas/sitemap/0.84'),
('b', 'http://www.example.com/schemas/extras/1.0'),
)
def parse_node(self, response, selector):
yield {
'loc': selector.xpath('a:loc/text()').extract(),
'updated': selector.xpath('b:updated/text()').extract(),
'other': selector.xpath('other/@value').extract(),
'custom': selector.xpath('other/@b:custom').extract(),
}
for iterator in ('iternodes', 'xml'):
spider = _XMLSpider('example', iterator=iterator)
output = list(spider.parse(response))
self.assertEqual(len(output), 2, iterator)
self.assertEqual(output, [
{'loc': [u'http://www.example.com/Special-Offers.html'],
'updated': [u'2009-08-16'],
'custom': [u'fuu'],
'other': [u'bar']},
{'loc': [],
'updated': [u'2009-08-16'],
'other': [u'foo'],
'custom': []},
], iterator)
class CSVFeedSpiderTest(SpiderTest):
spider_class = CSVFeedSpider
class CrawlSpiderTest(SpiderTest):
test_body = """<html><head><title>Page title<title>
<body>
<p><a href="item/12.html">Item 12</a></p>
<div class='links'>
<p><a href="/about.html">About us</a></p>
</div>
<div>
<p><a href="/nofollow.html">This shouldn't be followed</a></p>
</div>
</body></html>"""
spider_class = CrawlSpider
def test_process_links(self):
response = HtmlResponse("http://example.org/somepage/index.html",
body=self.test_body)
class _CrawlSpider(self.spider_class):
name="test"
allowed_domains=['example.org']
rules = (
Rule(LinkExtractor(), process_links="dummy_process_links"),
)
def dummy_process_links(self, links):
return links
spider = _CrawlSpider()
output = list(spider._requests_to_follow(response))
self.assertEqual(len(output), 3)
self.assertTrue(all(map(lambda r: isinstance(r, Request), output)))
self.assertEquals([r.url for r in output],
['http://example.org/somepage/item/12.html',
'http://example.org/about.html',
'http://example.org/nofollow.html'])
def test_process_links_filter(self):
response = HtmlResponse("http://example.org/somepage/index.html",
body=self.test_body)
class _CrawlSpider(self.spider_class):
import re
name="test"
allowed_domains=['example.org']
rules = (
Rule(LinkExtractor(), process_links="filter_process_links"),
)
_test_regex = re.compile('nofollow')
def filter_process_links(self, links):
return [link for link in links
if not self._test_regex.search(link.url)]
spider = _CrawlSpider()
output = list(spider._requests_to_follow(response))
self.assertEqual(len(output), 2)
self.assertTrue(all(map(lambda r: isinstance(r, Request), output)))
self.assertEquals([r.url for r in output],
['http://example.org/somepage/item/12.html',
'http://example.org/about.html'])
def test_process_links_generator(self):
response = HtmlResponse("http://example.org/somepage/index.html",
body=self.test_body)
class _CrawlSpider(self.spider_class):
name="test"
allowed_domains=['example.org']
rules = (
Rule(LinkExtractor(), process_links="dummy_process_links"),
)
def dummy_process_links(self, links):
for link in links:
yield link
spider = _CrawlSpider()
output = list(spider._requests_to_follow(response))
self.assertEqual(len(output), 3)
self.assertTrue(all(map(lambda r: isinstance(r, Request), output)))
self.assertEquals([r.url for r in output],
['http://example.org/somepage/item/12.html',
'http://example.org/about.html',
'http://example.org/nofollow.html'])
class SitemapSpiderTest(SpiderTest):
spider_class = SitemapSpider
BODY = "SITEMAP"
f = StringIO()
g = gzip.GzipFile(fileobj=f, mode='w+b')
g.write(BODY)
g.close()
GZBODY = f.getvalue()
def test_get_sitemap_body(self):
spider = self.spider_class("example.com")
r = XmlResponse(url="http://www.example.com/", body=self.BODY)
self.assertEqual(spider._get_sitemap_body(r), self.BODY)
r = HtmlResponse(url="http://www.example.com/", body=self.BODY)
self.assertEqual(spider._get_sitemap_body(r), None)
r = Response(url="http://www.example.com/favicon.ico", body=self.BODY)
self.assertEqual(spider._get_sitemap_body(r), None)
r = Response(url="http://www.example.com/sitemap", body=self.GZBODY, headers={"content-type": "application/gzip"})
self.assertEqual(spider._get_sitemap_body(r), self.BODY)
r = TextResponse(url="http://www.example.com/sitemap.xml", body=self.BODY)
self.assertEqual(spider._get_sitemap_body(r), self.BODY)
r = Response(url="http://www.example.com/sitemap.xml.gz", body=self.GZBODY)
self.assertEqual(spider._get_sitemap_body(r), self.BODY)
class BaseSpiderDeprecationTest(unittest.TestCase):
def test_basespider_is_deprecated(self):
with warnings.catch_warnings(record=True) as w:
class MySpider1(BaseSpider):
pass
self.assertEqual(len(w), 1)
self.assertEqual(w[0].category, ScrapyDeprecationWarning)
self.assertEqual(w[0].lineno, inspect.getsourcelines(MySpider1)[1])
def test_basespider_issubclass(self):
class MySpider2(Spider):
pass
class MySpider2a(MySpider2):
pass
class Foo(object):
pass
class Foo2(object_ref):
pass
assert issubclass(MySpider2, BaseSpider)
assert issubclass(MySpider2a, BaseSpider)
assert not issubclass(Foo, BaseSpider)
assert not issubclass(Foo2, BaseSpider)
def test_basespider_isinstance(self):
class MySpider3(Spider):
name = 'myspider3'
class MySpider3a(MySpider3):
pass
class Foo(object):
pass
class Foo2(object_ref):
pass
assert isinstance(MySpider3(), BaseSpider)
assert isinstance(MySpider3a(), BaseSpider)
assert not isinstance(Foo(), BaseSpider)
assert not isinstance(Foo2(), BaseSpider)
def test_crawl_spider(self):
assert issubclass(CrawlSpider, Spider)
assert issubclass(CrawlSpider, BaseSpider)
assert isinstance(CrawlSpider(name='foo'), Spider)
assert isinstance(CrawlSpider(name='foo'), BaseSpider)
if __name__ == '__main__':
unittest.main()
|
