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
|
"""
Some spiders used for testing and benchmarking
"""
import time
from six.moves.urllib.parse import urlencode
from scrapy.spiders import Spider
from scrapy.http import Request
from scrapy.item import Item
from scrapy.linkextractors import LinkExtractor
class MetaSpider(Spider):
name = 'meta'
def __init__(self, *args, **kwargs):
super(MetaSpider, self).__init__(*args, **kwargs)
self.meta = {}
def closed(self, reason):
self.meta['close_reason'] = reason
class FollowAllSpider(MetaSpider):
name = 'follow'
link_extractor = LinkExtractor()
def __init__(self, total=10, show=20, order="rand", maxlatency=0.0, *args, **kwargs):
super(FollowAllSpider, self).__init__(*args, **kwargs)
self.urls_visited = []
self.times = []
qargs = {'total': total, 'show': show, 'order': order, 'maxlatency': maxlatency}
url = "http://localhost:8998/follow?%s" % urlencode(qargs, doseq=1)
self.start_urls = [url]
def parse(self, response):
self.urls_visited.append(response.url)
self.times.append(time.time())
for link in self.link_extractor.extract_links(response):
yield Request(link.url, callback=self.parse)
class DelaySpider(MetaSpider):
name = 'delay'
def __init__(self, n=1, b=0, *args, **kwargs):
super(DelaySpider, self).__init__(*args, **kwargs)
self.n = n
self.b = b
self.t1 = self.t2 = self.t2_err = 0
def start_requests(self):
self.t1 = time.time()
url = "http://localhost:8998/delay?n=%s&b=%s" % (self.n, self.b)
yield Request(url, callback=self.parse, errback=self.errback)
def parse(self, response):
self.t2 = time.time()
def errback(self, failure):
self.t2_err = time.time()
class SimpleSpider(MetaSpider):
name = 'simple'
def __init__(self, url="http://localhost:8998", *args, **kwargs):
super(SimpleSpider, self).__init__(*args, **kwargs)
self.start_urls = [url]
def parse(self, response):
self.logger.info("Got response %d" % response.status)
class ItemSpider(FollowAllSpider):
name = 'item'
def parse(self, response):
for request in super(ItemSpider, self).parse(response):
yield request
yield Item()
yield {}
class DefaultError(Exception):
pass
class ErrorSpider(FollowAllSpider):
name = 'error'
exception_cls = DefaultError
def raise_exception(self):
raise self.exception_cls('Expected exception')
def parse(self, response):
for request in super(ErrorSpider, self).parse(response):
yield request
self.raise_exception()
class BrokenStartRequestsSpider(FollowAllSpider):
fail_before_yield = False
fail_yielding = False
def __init__(self, *a, **kw):
super(BrokenStartRequestsSpider, self).__init__(*a, **kw)
self.seedsseen = []
def start_requests(self):
if self.fail_before_yield:
1 / 0
for s in range(100):
qargs = {'total': 10, 'seed': s}
url = "http://localhost:8998/follow?%s" % urlencode(qargs, doseq=1)
yield Request(url, meta={'seed': s})
if self.fail_yielding:
2 / 0
assert self.seedsseen, \
'All start requests consumed before any download happened'
def parse(self, response):
self.seedsseen.append(response.meta.get('seed'))
for req in super(BrokenStartRequestsSpider, self).parse(response):
yield req
class SingleRequestSpider(MetaSpider):
seed = None
callback_func = None
errback_func = None
def start_requests(self):
if isinstance(self.seed, Request):
yield self.seed.replace(callback=self.parse, errback=self.on_error)
else:
yield Request(self.seed, callback=self.parse, errback=self.on_error)
def parse(self, response):
self.meta.setdefault('responses', []).append(response)
if callable(self.callback_func):
return self.callback_func(response)
if 'next' in response.meta:
return response.meta['next']
def on_error(self, failure):
self.meta['failure'] = failure
if callable(self.errback_func):
return self.errback_func(failure)
class DuplicateStartRequestsSpider(Spider):
dont_filter = True
name = 'duplicatestartrequests'
distinct_urls = 2
dupe_factor = 3
def start_requests(self):
for i in range(0, self.distinct_urls):
for j in range(0, self.dupe_factor):
url = "http://localhost:8998/echo?headers=1&body=test%d" % i
yield Request(url, dont_filter=self.dont_filter)
def __init__(self, url="http://localhost:8998", *args, **kwargs):
super(DuplicateStartRequestsSpider, self).__init__(*args, **kwargs)
self.visited = 0
def parse(self, response):
self.visited += 1
|
