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
|
# -*- coding: utf-8 -*-
import unittest
from scrapy.downloadermiddlewares.redirect import RedirectMiddleware, MetaRefreshMiddleware
from scrapy.spiders import Spider
from scrapy.exceptions import IgnoreRequest
from scrapy.http import Request, Response, HtmlResponse
from scrapy.utils.test import get_crawler
class RedirectMiddlewareTest(unittest.TestCase):
def setUp(self):
self.crawler = get_crawler(Spider)
self.spider = self.crawler._create_spider('foo')
self.mw = RedirectMiddleware.from_crawler(self.crawler)
def test_priority_adjust(self):
req = Request('http://a.com')
rsp = Response('http://a.com', headers={'Location': 'http://a.com/redirected'}, status=301)
req2 = self.mw.process_response(req, rsp, self.spider)
assert req2.priority > req.priority
def test_redirect_3xx_permanent(self):
def _test(method, status=301):
url = 'http://www.example.com/{}'.format(status)
url2 = 'http://www.example.com/redirected'
req = Request(url, method=method)
rsp = Response(url, headers={'Location': url2}, status=status)
req2 = self.mw.process_response(req, rsp, self.spider)
assert isinstance(req2, Request)
self.assertEqual(req2.url, url2)
self.assertEqual(req2.method, method)
# response without Location header but with status code is 3XX should be ignored
del rsp.headers['Location']
assert self.mw.process_response(req, rsp, self.spider) is rsp
_test('GET')
_test('POST')
_test('HEAD')
_test('GET', status=307)
_test('POST', status=307)
_test('HEAD', status=307)
_test('GET', status=308)
_test('POST', status=308)
_test('HEAD', status=308)
def test_dont_redirect(self):
url = 'http://www.example.com/301'
url2 = 'http://www.example.com/redirected'
req = Request(url, meta={'dont_redirect': True})
rsp = Response(url, headers={'Location': url2}, status=301)
r = self.mw.process_response(req, rsp, self.spider)
assert isinstance(r, Response)
assert r is rsp
# Test that it redirects when dont_redirect is False
req = Request(url, meta={'dont_redirect': False})
rsp = Response(url2, status=200)
r = self.mw.process_response(req, rsp, self.spider)
assert isinstance(r, Response)
assert r is rsp
def test_redirect_302(self):
url = 'http://www.example.com/302'
url2 = 'http://www.example.com/redirected2'
req = Request(url, method='POST', body='test',
headers={'Content-Type': 'text/plain', 'Content-length': '4'})
rsp = Response(url, headers={'Location': url2}, status=302)
req2 = self.mw.process_response(req, rsp, self.spider)
assert isinstance(req2, Request)
self.assertEqual(req2.url, url2)
self.assertEqual(req2.method, 'GET')
assert 'Content-Type' not in req2.headers, \
"Content-Type header must not be present in redirected request"
assert 'Content-Length' not in req2.headers, \
"Content-Length header must not be present in redirected request"
assert not req2.body, \
"Redirected body must be empty, not '%s'" % req2.body
# response without Location header but with status code is 3XX should be ignored
del rsp.headers['Location']
assert self.mw.process_response(req, rsp, self.spider) is rsp
def test_redirect_302_head(self):
url = 'http://www.example.com/302'
url2 = 'http://www.example.com/redirected2'
req = Request(url, method='HEAD')
rsp = Response(url, headers={'Location': url2}, status=302)
req2 = self.mw.process_response(req, rsp, self.spider)
assert isinstance(req2, Request)
self.assertEqual(req2.url, url2)
self.assertEqual(req2.method, 'HEAD')
# response without Location header but with status code is 3XX should be ignored
del rsp.headers['Location']
assert self.mw.process_response(req, rsp, self.spider) is rsp
def test_max_redirect_times(self):
self.mw.max_redirect_times = 1
req = Request('http://scrapytest.org/302')
rsp = Response('http://scrapytest.org/302', headers={'Location': '/redirected'}, status=302)
req = self.mw.process_response(req, rsp, self.spider)
assert isinstance(req, Request)
assert 'redirect_times' in req.meta
self.assertEqual(req.meta['redirect_times'], 1)
self.assertRaises(IgnoreRequest, self.mw.process_response, req, rsp, self.spider)
def test_ttl(self):
self.mw.max_redirect_times = 100
req = Request('http://scrapytest.org/302', meta={'redirect_ttl': 1})
rsp = Response('http://www.scrapytest.org/302', headers={'Location': '/redirected'}, status=302)
req = self.mw.process_response(req, rsp, self.spider)
assert isinstance(req, Request)
self.assertRaises(IgnoreRequest, self.mw.process_response, req, rsp, self.spider)
def test_redirect_urls(self):
req1 = Request('http://scrapytest.org/first')
rsp1 = Response('http://scrapytest.org/first', headers={'Location': '/redirected'}, status=302)
req2 = self.mw.process_response(req1, rsp1, self.spider)
rsp2 = Response('http://scrapytest.org/redirected', headers={'Location': '/redirected2'}, status=302)
req3 = self.mw.process_response(req2, rsp2, self.spider)
self.assertEqual(req2.url, 'http://scrapytest.org/redirected')
self.assertEqual(req2.meta['redirect_urls'], ['http://scrapytest.org/first'])
self.assertEqual(req3.url, 'http://scrapytest.org/redirected2')
self.assertEqual(req3.meta['redirect_urls'], ['http://scrapytest.org/first', 'http://scrapytest.org/redirected'])
def test_spider_handling(self):
smartspider = self.crawler._create_spider('smarty')
smartspider.handle_httpstatus_list = [404, 301, 302]
url = 'http://www.example.com/301'
url2 = 'http://www.example.com/redirected'
req = Request(url)
rsp = Response(url, headers={'Location': url2}, status=301)
r = self.mw.process_response(req, rsp, smartspider)
self.assertIs(r, rsp)
def test_request_meta_handling(self):
url = 'http://www.example.com/301'
url2 = 'http://www.example.com/redirected'
def _test_passthrough(req):
rsp = Response(url, headers={'Location': url2}, status=301, request=req)
r = self.mw.process_response(req, rsp, self.spider)
self.assertIs(r, rsp)
_test_passthrough(Request(url, meta={'handle_httpstatus_list':
[404, 301, 302]}))
_test_passthrough(Request(url, meta={'handle_httpstatus_all': True}))
def test_latin1_location(self):
req = Request('http://scrapytest.org/first')
latin1_location = u'/ação'.encode('latin1') # HTTP historically supports latin1
resp = Response('http://scrapytest.org/first', headers={'Location': latin1_location}, status=302)
req_result = self.mw.process_response(req, resp, self.spider)
perc_encoded_utf8_url = 'http://scrapytest.org/a%E7%E3o'
self.assertEqual(perc_encoded_utf8_url, req_result.url)
def test_utf8_location(self):
req = Request('http://scrapytest.org/first')
utf8_location = u'/ação'.encode('utf-8') # header using UTF-8 encoding
resp = Response('http://scrapytest.org/first', headers={'Location': utf8_location}, status=302)
req_result = self.mw.process_response(req, resp, self.spider)
perc_encoded_utf8_url = 'http://scrapytest.org/a%C3%A7%C3%A3o'
self.assertEqual(perc_encoded_utf8_url, req_result.url)
class MetaRefreshMiddlewareTest(unittest.TestCase):
def setUp(self):
crawler = get_crawler(Spider)
self.spider = crawler._create_spider('foo')
self.mw = MetaRefreshMiddleware.from_crawler(crawler)
def _body(self, interval=5, url='http://example.org/newpage'):
html = u"""<html><head><meta http-equiv="refresh" content="{0};url={1}"/></head></html>"""
return html.format(interval, url).encode('utf-8')
def test_priority_adjust(self):
req = Request('http://a.com')
rsp = HtmlResponse(req.url, body=self._body())
req2 = self.mw.process_response(req, rsp, self.spider)
assert req2.priority > req.priority
def test_meta_refresh(self):
req = Request(url='http://example.org')
rsp = HtmlResponse(req.url, body=self._body())
req2 = self.mw.process_response(req, rsp, self.spider)
assert isinstance(req2, Request)
self.assertEqual(req2.url, 'http://example.org/newpage')
def test_meta_refresh_with_high_interval(self):
# meta-refresh with high intervals don't trigger redirects
req = Request(url='http://example.org')
rsp = HtmlResponse(url='http://example.org',
body=self._body(interval=1000),
encoding='utf-8')
rsp2 = self.mw.process_response(req, rsp, self.spider)
assert rsp is rsp2
def test_meta_refresh_trough_posted_request(self):
req = Request(url='http://example.org', method='POST', body='test',
headers={'Content-Type': 'text/plain', 'Content-length': '4'})
rsp = HtmlResponse(req.url, body=self._body())
req2 = self.mw.process_response(req, rsp, self.spider)
assert isinstance(req2, Request)
self.assertEqual(req2.url, 'http://example.org/newpage')
self.assertEqual(req2.method, 'GET')
assert 'Content-Type' not in req2.headers, \
"Content-Type header must not be present in redirected request"
assert 'Content-Length' not in req2.headers, \
"Content-Length header must not be present in redirected request"
assert not req2.body, \
"Redirected body must be empty, not '%s'" % req2.body
def test_max_redirect_times(self):
self.mw.max_redirect_times = 1
req = Request('http://scrapytest.org/max')
rsp = HtmlResponse(req.url, body=self._body())
req = self.mw.process_response(req, rsp, self.spider)
assert isinstance(req, Request)
assert 'redirect_times' in req.meta
self.assertEqual(req.meta['redirect_times'], 1)
self.assertRaises(IgnoreRequest, self.mw.process_response, req, rsp, self.spider)
def test_ttl(self):
self.mw.max_redirect_times = 100
req = Request('http://scrapytest.org/302', meta={'redirect_ttl': 1})
rsp = HtmlResponse(req.url, body=self._body())
req = self.mw.process_response(req, rsp, self.spider)
assert isinstance(req, Request)
self.assertRaises(IgnoreRequest, self.mw.process_response, req, rsp, self.spider)
def test_redirect_urls(self):
req1 = Request('http://scrapytest.org/first')
rsp1 = HtmlResponse(req1.url, body=self._body(url='/redirected'))
req2 = self.mw.process_response(req1, rsp1, self.spider)
assert isinstance(req2, Request), req2
rsp2 = HtmlResponse(req2.url, body=self._body(url='/redirected2'))
req3 = self.mw.process_response(req2, rsp2, self.spider)
assert isinstance(req3, Request), req3
self.assertEqual(req2.url, 'http://scrapytest.org/redirected')
self.assertEqual(req2.meta['redirect_urls'], ['http://scrapytest.org/first'])
self.assertEqual(req3.url, 'http://scrapytest.org/redirected2')
self.assertEqual(req3.meta['redirect_urls'], ['http://scrapytest.org/first', 'http://scrapytest.org/redirected'])
if __name__ == "__main__":
unittest.main()
|
