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
|
from os.path import join, abspath
from twisted.trial import unittest
from twisted.internet import defer
from scrapy.utils.testsite import SiteTest
from scrapy.utils.testproc import ProcessTest
from scrapy.utils.python import to_native_str
from tests.test_commands import CommandTest
class ParseCommandTest(ProcessTest, SiteTest, CommandTest):
command = 'parse'
def setUp(self):
super(ParseCommandTest, self).setUp()
self.spider_name = 'parse_spider'
fname = abspath(join(self.proj_mod_path, 'spiders', 'myspider.py'))
with open(fname, 'w') as f:
f.write("""
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
class MySpider(scrapy.Spider):
name = '{0}'
def parse(self, response):
if getattr(self, 'test_arg', None):
self.logger.debug('It Works!')
return [scrapy.Item(), dict(foo='bar')]
def parse_request_with_meta(self, response):
foo = response.meta.get('foo', 'bar')
if foo == 'bar':
self.logger.debug('It Does Not Work :(')
else:
self.logger.debug('It Works!')
def parse_request_without_meta(self, response):
foo = response.meta.get('foo', 'bar')
if foo == 'bar':
self.logger.debug('It Works!')
else:
self.logger.debug('It Does Not Work :(')
class MyGoodCrawlSpider(CrawlSpider):
name = 'goodcrawl{0}'
rules = (
Rule(LinkExtractor(allow=r'/html'), callback='parse_item', follow=True),
Rule(LinkExtractor(allow=r'/text'), follow=True),
)
def parse_item(self, response):
return [scrapy.Item(), dict(foo='bar')]
def parse(self, response):
return [scrapy.Item(), dict(nomatch='default')]
class MyBadCrawlSpider(CrawlSpider):
'''Spider which doesn't define a parse_item callback while using it in a rule.'''
name = 'badcrawl{0}'
rules = (
Rule(LinkExtractor(allow=r'/html'), callback='parse_item', follow=True),
)
def parse(self, response):
return [scrapy.Item(), dict(foo='bar')]
""".format(self.spider_name))
fname = abspath(join(self.proj_mod_path, 'pipelines.py'))
with open(fname, 'w') as f:
f.write("""
import logging
class MyPipeline(object):
component_name = 'my_pipeline'
def process_item(self, item, spider):
logging.info('It Works!')
return item
""")
fname = abspath(join(self.proj_mod_path, 'settings.py'))
with open(fname, 'a') as f:
f.write("""
ITEM_PIPELINES = {'%s.pipelines.MyPipeline': 1}
""" % self.project_name)
@defer.inlineCallbacks
def test_spider_arguments(self):
_, _, stderr = yield self.execute(['--spider', self.spider_name,
'-a', 'test_arg=1',
'-c', 'parse',
self.url('/html')])
self.assertIn("DEBUG: It Works!", to_native_str(stderr))
@defer.inlineCallbacks
def test_request_with_meta(self):
raw_json_string = '{"foo" : "baz"}'
_, _, stderr = yield self.execute(['--spider', self.spider_name,
'--meta', raw_json_string,
'-c', 'parse_request_with_meta',
self.url('/html')])
self.assertIn("DEBUG: It Works!", to_native_str(stderr))
_, _, stderr = yield self.execute(['--spider', self.spider_name,
'-m', raw_json_string,
'-c', 'parse_request_with_meta',
self.url('/html')])
self.assertIn("DEBUG: It Works!", to_native_str(stderr))
@defer.inlineCallbacks
def test_request_without_meta(self):
_, _, stderr = yield self.execute(['--spider', self.spider_name,
'-c', 'parse_request_without_meta',
self.url('/html')])
self.assertIn("DEBUG: It Works!", to_native_str(stderr))
@defer.inlineCallbacks
def test_pipelines(self):
_, _, stderr = yield self.execute(['--spider', self.spider_name,
'--pipelines',
'-c', 'parse',
self.url('/html')])
self.assertIn("INFO: It Works!", to_native_str(stderr))
@defer.inlineCallbacks
def test_parse_items(self):
status, out, stderr = yield self.execute(
['--spider', self.spider_name, '-c', 'parse', self.url('/html')]
)
self.assertIn("""[{}, {'foo': 'bar'}]""", to_native_str(out))
@defer.inlineCallbacks
def test_parse_items_no_callback_passed(self):
status, out, stderr = yield self.execute(
['--spider', self.spider_name, self.url('/html')]
)
self.assertIn("""[{}, {'foo': 'bar'}]""", to_native_str(out))
@defer.inlineCallbacks
def test_wrong_callback_passed(self):
status, out, stderr = yield self.execute(
['--spider', self.spider_name, '-c', 'dummy', self.url('/html')]
)
self.assertRegexpMatches(to_native_str(out), """# Scraped Items -+\n\[\]""")
self.assertIn("""Cannot find callback""", to_native_str(stderr))
@defer.inlineCallbacks
def test_crawlspider_matching_rule_callback_set(self):
"""If a rule matches the URL, use it's defined callback."""
status, out, stderr = yield self.execute(
['--spider', 'goodcrawl'+self.spider_name, '-r', self.url('/html')]
)
self.assertIn("""[{}, {'foo': 'bar'}]""", to_native_str(out))
@defer.inlineCallbacks
def test_crawlspider_matching_rule_default_callback(self):
"""If a rule match but it has no callback set, use the 'parse' callback."""
status, out, stderr = yield self.execute(
['--spider', 'goodcrawl'+self.spider_name, '-r', self.url('/text')]
)
self.assertIn("""[{}, {'nomatch': 'default'}]""", to_native_str(out))
@defer.inlineCallbacks
def test_spider_with_no_rules_attribute(self):
"""Using -r with a spider with no rule should not produce items."""
status, out, stderr = yield self.execute(
['--spider', self.spider_name, '-r', self.url('/html')]
)
self.assertRegexpMatches(to_native_str(out), """# Scraped Items -+\n\[\]""")
self.assertIn("""No CrawlSpider rules found""", to_native_str(stderr))
@defer.inlineCallbacks
def test_crawlspider_missing_callback(self):
status, out, stderr = yield self.execute(
['--spider', 'badcrawl'+self.spider_name, '-r', self.url('/html')]
)
self.assertRegexpMatches(to_native_str(out), """# Scraped Items -+\n\[\]""")
@defer.inlineCallbacks
def test_crawlspider_no_matching_rule(self):
"""The requested URL has no matching rule, so no items should be scraped"""
status, out, stderr = yield self.execute(
['--spider', 'badcrawl'+self.spider_name, '-r', self.url('/enc-gb18030')]
)
self.assertRegexpMatches(to_native_str(out), """# Scraped Items -+\n\[\]""")
self.assertIn("""Cannot find a rule that matches""", to_native_str(stderr))
|
