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
284
285
286
287
288
289
290
|
import re
import unittest
from scrapy.http import HtmlResponse
from scrapy.link import Link
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor, BaseSgmlLinkExtractor
from scrapy.contrib.linkextractors.image import HTMLImageLinkExtractor
from scrapy.tests import get_testdata
class LinkExtractorTestCase(unittest.TestCase):
def test_basic(self):
html = """<html><head><title>Page title<title>
<body><p><a href="item/12.html">Item 12</a></p>
<p><a href="/about.html">About us</a></p>
<img src="/logo.png" alt="Company logo (not a link)" />
<p><a href="../othercat.html">Other category</a></p>
<p><a href="/">>></a></p>
<p><a href="/" /></p>
</body></html>"""
response = HtmlResponse("http://example.org/somepage/index.html", body=html)
lx = BaseSgmlLinkExtractor() # default: tag=a, attr=href
self.assertEqual(lx.extract_links(response),
[Link(url='http://example.org/somepage/item/12.html', text='Item 12'),
Link(url='http://example.org/about.html', text='About us'),
Link(url='http://example.org/othercat.html', text='Other category'),
Link(url='http://example.org/', text='>>'),
Link(url='http://example.org/', text='')])
def test_base_url(self):
html = """<html><head><title>Page title<title><base href="http://otherdomain.com/base/" />
<body><p><a href="item/12.html">Item 12</a></p>
</body></html>"""
response = HtmlResponse("http://example.org/somepage/index.html", body=html)
lx = BaseSgmlLinkExtractor() # default: tag=a, attr=href
self.assertEqual(lx.extract_links(response),
[Link(url='http://otherdomain.com/base/item/12.html', text='Item 12')])
# base url is an absolute path and relative to host
html = """<html><head><title>Page title<title><base href="/" />
<body><p><a href="item/12.html">Item 12</a></p></body></html>"""
response = HtmlResponse("https://example.org/somepage/index.html", body=html)
self.assertEqual(lx.extract_links(response),
[Link(url='https://example.org/item/12.html', text='Item 12')])
# base url has no scheme
html = """<html><head><title>Page title<title><base href="//noschemedomain.com/path/to/" />
<body><p><a href="item/12.html">Item 12</a></p></body></html>"""
response = HtmlResponse("https://example.org/somepage/index.html", body=html)
self.assertEqual(lx.extract_links(response),
[Link(url='https://noschemedomain.com/path/to/item/12.html', text='Item 12')])
def test_link_text_wrong_encoding(self):
html = """<body><p><a href="item/12.html">Wrong: \xed</a></p></body></html>"""
response = HtmlResponse("http://www.example.com", body=html, encoding='utf-8')
lx = BaseSgmlLinkExtractor()
self.assertEqual(lx.extract_links(response),
[Link(url='http://www.example.com/item/12.html', text=u'Wrong: \ufffd')])
def test_extraction_encoding(self):
body = get_testdata('link_extractor', 'linkextractor_noenc.html')
response_utf8 = HtmlResponse(url='http://example.com/utf8', body=body, headers={'Content-Type': ['text/html; charset=utf-8']})
response_noenc = HtmlResponse(url='http://example.com/noenc', body=body)
body = get_testdata('link_extractor', 'linkextractor_latin1.html')
response_latin1 = HtmlResponse(url='http://example.com/latin1', body=body)
lx = BaseSgmlLinkExtractor()
self.assertEqual(lx.extract_links(response_utf8),
[ Link(url='http://example.com/sample_%C3%B1.html', text=''),
Link(url='http://example.com/sample_%E2%82%AC.html', text='sample \xe2\x82\xac text'.decode('utf-8')) ])
self.assertEqual(lx.extract_links(response_noenc),
[ Link(url='http://example.com/sample_%C3%B1.html', text=''),
Link(url='http://example.com/sample_%E2%82%AC.html', text='sample \xe2\x82\xac text'.decode('utf-8')) ])
self.assertEqual(lx.extract_links(response_latin1),
[ Link(url='http://example.com/sample_%F1.html', text=''),
Link(url='http://example.com/sample_%E1.html', text='sample \xe1 text'.decode('latin1')) ])
def test_matches(self):
url1 = 'http://lotsofstuff.com/stuff1/index'
url2 = 'http://evenmorestuff.com/uglystuff/index'
lx = BaseSgmlLinkExtractor()
self.assertEqual(lx.matches(url1), True)
self.assertEqual(lx.matches(url2), True)
class SgmlLinkExtractorTestCase(unittest.TestCase):
def setUp(self):
body = get_testdata('link_extractor', 'sgml_linkextractor.html')
self.response = HtmlResponse(url='http://example.com/index', body=body)
def test_urls_type(self):
'''Test that the resulting urls are regular strings and not a unicode objects'''
lx = SgmlLinkExtractor()
self.assertTrue(all(isinstance(link.url, str) for link in lx.extract_links(self.response)))
def test_extraction(self):
'''Test the extractor's behaviour among different situations'''
lx = SgmlLinkExtractor()
self.assertEqual([link for link in lx.extract_links(self.response)],
[ Link(url='http://example.com/sample1.html', text=u''),
Link(url='http://example.com/sample2.html', text=u'sample 2'),
Link(url='http://example.com/sample3.html', text=u'sample 3 text'),
Link(url='http://www.google.com/something', text=u'') ])
lx = SgmlLinkExtractor(allow=('sample', ))
self.assertEqual([link for link in lx.extract_links(self.response)],
[ Link(url='http://example.com/sample1.html', text=u''),
Link(url='http://example.com/sample2.html', text=u'sample 2'),
Link(url='http://example.com/sample3.html', text=u'sample 3 text') ])
lx = SgmlLinkExtractor(allow=('sample', ), unique=False)
self.assertEqual([link for link in lx.extract_links(self.response)],
[ Link(url='http://example.com/sample1.html', text=u''),
Link(url='http://example.com/sample2.html', text=u'sample 2'),
Link(url='http://example.com/sample3.html', text=u'sample 3 text'),
Link(url='http://example.com/sample3.html', text=u'sample 3 repetition') ])
lx = SgmlLinkExtractor(allow=('sample', ))
self.assertEqual([link for link in lx.extract_links(self.response)],
[ Link(url='http://example.com/sample1.html', text=u''),
Link(url='http://example.com/sample2.html', text=u'sample 2'),
Link(url='http://example.com/sample3.html', text=u'sample 3 text'),
])
lx = SgmlLinkExtractor(allow=('sample', ), deny=('3', ))
self.assertEqual([link for link in lx.extract_links(self.response)],
[ Link(url='http://example.com/sample1.html', text=u''),
Link(url='http://example.com/sample2.html', text=u'sample 2') ])
lx = SgmlLinkExtractor(allow_domains=('google.com', ))
self.assertEqual([link for link in lx.extract_links(self.response)],
[ Link(url='http://www.google.com/something', text=u'') ])
def test_extraction_using_single_values(self):
'''Test the extractor's behaviour among different situations'''
lx = SgmlLinkExtractor(allow='sample')
self.assertEqual([link for link in lx.extract_links(self.response)],
[ Link(url='http://example.com/sample1.html', text=u''),
Link(url='http://example.com/sample2.html', text=u'sample 2'),
Link(url='http://example.com/sample3.html', text=u'sample 3 text') ])
lx = SgmlLinkExtractor(allow='sample', deny='3')
self.assertEqual([link for link in lx.extract_links(self.response)],
[ Link(url='http://example.com/sample1.html', text=u''),
Link(url='http://example.com/sample2.html', text=u'sample 2') ])
lx = SgmlLinkExtractor(allow_domains='google.com')
self.assertEqual([link for link in lx.extract_links(self.response)],
[ Link(url='http://www.google.com/something', text=u'') ])
lx = SgmlLinkExtractor(deny_domains='example.com')
self.assertEqual([link for link in lx.extract_links(self.response)],
[ Link(url='http://www.google.com/something', text=u'') ])
def test_matches(self):
url1 = 'http://lotsofstuff.com/stuff1/index'
url2 = 'http://evenmorestuff.com/uglystuff/index'
lx = SgmlLinkExtractor(allow=(r'stuff1', ))
self.assertEqual(lx.matches(url1), True)
self.assertEqual(lx.matches(url2), False)
lx = SgmlLinkExtractor(deny=(r'uglystuff', ))
self.assertEqual(lx.matches(url1), True)
self.assertEqual(lx.matches(url2), False)
lx = SgmlLinkExtractor(allow_domains=('evenmorestuff.com', ))
self.assertEqual(lx.matches(url1), False)
self.assertEqual(lx.matches(url2), True)
lx = SgmlLinkExtractor(deny_domains=('lotsofstuff.com', ))
self.assertEqual(lx.matches(url1), False)
self.assertEqual(lx.matches(url2), True)
lx = SgmlLinkExtractor(allow=('blah1', ), deny=('blah2', ),
allow_domains=('blah1.com', ), deny_domains=('blah2.com', ))
self.assertEqual(lx.matches('http://blah1.com/blah1'), True)
self.assertEqual(lx.matches('http://blah1.com/blah2'), False)
self.assertEqual(lx.matches('http://blah2.com/blah1'), False)
self.assertEqual(lx.matches('http://blah2.com/blah2'), False)
def test_restrict_xpaths(self):
lx = SgmlLinkExtractor(restrict_xpaths=('//div[@id="subwrapper"]', ))
self.assertEqual([link for link in lx.extract_links(self.response)],
[ Link(url='http://example.com/sample1.html', text=u''),
Link(url='http://example.com/sample2.html', text=u'sample 2') ])
def test_restrict_xpaths_encoding(self):
"""Test restrict_xpaths with encodings"""
html = """<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\xa3</a></p>
</div>
<div>
<p><a href="/nofollow.html">This shouldn't be followed</a></p>
</div>
</body></html>"""
response = HtmlResponse("http://example.org/somepage/index.html", body=html, encoding='windows-1252')
lx = SgmlLinkExtractor(restrict_xpaths="//div[@class='links']")
self.assertEqual(lx.extract_links(response),
[Link(url='http://example.org/about.html', text=u'About us\xa3')])
def test_deny_extensions(self):
html = """<a href="page.html">asd</a> and <a href="photo.jpg">"""
response = HtmlResponse("http://example.org/", body=html)
lx = SgmlLinkExtractor()
self.assertEqual(lx.extract_links(response),
[Link(url='http://example.org/page.html', text=u'asd')])
def test_process_value(self):
"""Test restrict_xpaths with encodings"""
html = """
<a href="javascript:goToPage('../other/page.html','photo','width=600,height=540,scrollbars'); return false">Link text</a>
<a href="/about.html">About us</a>
"""
response = HtmlResponse("http://example.org/somepage/index.html", body=html, encoding='windows-1252')
def process_value(value):
m = re.search("javascript:goToPage\('(.*?)'", value)
if m:
return m.group(1)
lx = SgmlLinkExtractor(process_value=process_value)
self.assertEqual(lx.extract_links(response),
[Link(url='http://example.org/other/page.html', text='Link text')])
def test_base_url_with_restrict_xpaths(self):
html = """<html><head><title>Page title<title><base href="http://otherdomain.com/base/" />
<body><p><a href="item/12.html">Item 12</a></p>
</body></html>"""
response = HtmlResponse("http://example.org/somepage/index.html", body=html)
lx = SgmlLinkExtractor(restrict_xpaths="//p")
self.assertEqual(lx.extract_links(response),
[Link(url='http://otherdomain.com/base/item/12.html', text='Item 12')])
class HTMLImageLinkExtractorTestCase(unittest.TestCase):
def setUp(self):
body = get_testdata('link_extractor', 'image_linkextractor.html')
self.response = HtmlResponse(url='http://example.com/index', body=body)
def tearDown(self):
del self.response
def test_urls_type(self):
'''Test that the resulting urls are regular strings and not a unicode objects'''
lx = HTMLImageLinkExtractor()
links = lx.extract_links(self.response)
self.assertTrue(all(isinstance(link.url, str) for link in links))
def test_extraction(self):
'''Test the extractor's behaviour among different situations'''
lx = HTMLImageLinkExtractor(locations=('//img', ))
links_1 = lx.extract_links(self.response)
self.assertEqual(links_1,
[ Link(url='http://example.com/sample1.jpg', text=u'sample 1'),
Link(url='http://example.com/sample2.jpg', text=u'sample 2'),
Link(url='http://example.com/sample4.jpg', text=u'sample 4') ])
lx = HTMLImageLinkExtractor(locations=('//img', ), unique=False)
links_2 = lx.extract_links(self.response)
self.assertEqual(links_2,
[ Link(url='http://example.com/sample1.jpg', text=u'sample 1'),
Link(url='http://example.com/sample2.jpg', text=u'sample 2'),
Link(url='http://example.com/sample4.jpg', text=u'sample 4'),
Link(url='http://example.com/sample4.jpg', text=u'sample 4 repetition') ])
lx = HTMLImageLinkExtractor(locations=('//div[@id="wrapper"]', ))
links_3 = lx.extract_links(self.response)
self.assertEqual(links_3,
[ Link(url='http://example.com/sample1.jpg', text=u'sample 1'),
Link(url='http://example.com/sample2.jpg', text=u'sample 2'),
Link(url='http://example.com/sample4.jpg', text=u'sample 4') ])
lx = HTMLImageLinkExtractor(locations=('//a', ))
links_4 = lx.extract_links(self.response)
self.assertEqual(links_4,
[ Link(url='http://example.com/sample2.jpg', text=u'sample 2'),
Link(url='http://example.com/sample3.html', text=u'sample 3') ])
if __name__ == "__main__":
unittest.main()
|
