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
|
from scrapy.utils.sitemap import Sitemap, sitemap_urls_from_robots
class TestSitemap:
def test_sitemap(self):
s = Sitemap(
b"""<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.google.com/schemas/sitemap/0.84">
<url>
<loc>http://www.example.com/</loc>
<lastmod>2009-08-16</lastmod>
<changefreq>daily</changefreq>
<priority>1</priority>
</url>
<url>
<loc>http://www.example.com/Special-Offers.html</loc>
<lastmod>2009-08-16</lastmod>
<changefreq>weekly</changefreq>
<priority>0.8</priority>
</url>
</urlset>"""
)
assert s.type == "urlset"
assert list(s) == [
{
"priority": "1",
"loc": "http://www.example.com/",
"lastmod": "2009-08-16",
"changefreq": "daily",
},
{
"priority": "0.8",
"loc": "http://www.example.com/Special-Offers.html",
"lastmod": "2009-08-16",
"changefreq": "weekly",
},
]
def test_sitemap_index(self):
s = Sitemap(
b"""<?xml version="1.0" encoding="UTF-8"?>
<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
<sitemap>
<loc>http://www.example.com/sitemap1.xml.gz</loc>
<lastmod>2004-10-01T18:23:17+00:00</lastmod>
</sitemap>
<sitemap>
<loc>http://www.example.com/sitemap2.xml.gz</loc>
<lastmod>2005-01-01</lastmod>
</sitemap>
</sitemapindex>"""
)
assert s.type == "sitemapindex"
assert list(s) == [
{
"loc": "http://www.example.com/sitemap1.xml.gz",
"lastmod": "2004-10-01T18:23:17+00:00",
},
{
"loc": "http://www.example.com/sitemap2.xml.gz",
"lastmod": "2005-01-01",
},
]
def test_sitemap_strip(self):
"""Assert we can deal with trailing spaces inside <loc> tags - we've
seen those
"""
s = Sitemap(
b"""<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.google.com/schemas/sitemap/0.84">
<url>
<loc> http://www.example.com/</loc>
<lastmod>2009-08-16</lastmod>
<changefreq>daily</changefreq>
<priority>1</priority>
</url>
<url>
<loc> http://www.example.com/2</loc>
<lastmod />
</url>
</urlset>
"""
)
assert list(s) == [
{
"priority": "1",
"loc": "http://www.example.com/",
"lastmod": "2009-08-16",
"changefreq": "daily",
},
{"loc": "http://www.example.com/2", "lastmod": ""},
]
def test_sitemap_wrong_ns(self):
"""We have seen sitemaps with wrongs ns. Presumably, Google still works
with these, though is not 100% confirmed"""
s = Sitemap(
b"""<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.google.com/schemas/sitemap/0.84">
<url xmlns="">
<loc> http://www.example.com/</loc>
<lastmod>2009-08-16</lastmod>
<changefreq>daily</changefreq>
<priority>1</priority>
</url>
<url xmlns="">
<loc> http://www.example.com/2</loc>
<lastmod />
</url>
</urlset>
"""
)
assert list(s) == [
{
"priority": "1",
"loc": "http://www.example.com/",
"lastmod": "2009-08-16",
"changefreq": "daily",
},
{"loc": "http://www.example.com/2", "lastmod": ""},
]
def test_sitemap_wrong_ns2(self):
"""We have seen sitemaps with wrongs ns. Presumably, Google still works
with these, though is not 100% confirmed"""
s = Sitemap(
b"""<?xml version="1.0" encoding="UTF-8"?>
<urlset>
<url xmlns="">
<loc> http://www.example.com/</loc>
<lastmod>2009-08-16</lastmod>
<changefreq>daily</changefreq>
<priority>1</priority>
</url>
<url xmlns="">
<loc> http://www.example.com/2</loc>
<lastmod />
</url>
</urlset>
"""
)
assert s.type == "urlset"
assert list(s) == [
{
"priority": "1",
"loc": "http://www.example.com/",
"lastmod": "2009-08-16",
"changefreq": "daily",
},
{"loc": "http://www.example.com/2", "lastmod": ""},
]
def test_sitemap_urls_from_robots(self):
robots = """User-agent: *
Disallow: /aff/
Disallow: /wl/
# Search and shopping refining
Disallow: /s*/*facet
Disallow: /s*/*tags
# Sitemap files
Sitemap: http://example.com/sitemap.xml
Sitemap: http://example.com/sitemap-product-index.xml
Sitemap: HTTP://example.com/sitemap-uppercase.xml
Sitemap: /sitemap-relative-url.xml
# Forums
Disallow: /forum/search/
Disallow: /forum/active/
"""
assert list(
sitemap_urls_from_robots(robots, base_url="http://example.com")
) == [
"http://example.com/sitemap.xml",
"http://example.com/sitemap-product-index.xml",
"http://example.com/sitemap-uppercase.xml",
"http://example.com/sitemap-relative-url.xml",
]
def test_sitemap_blanklines(self):
"""Assert we can deal with starting blank lines before <xml> tag"""
s = Sitemap(
b"""
<?xml version="1.0" encoding="UTF-8"?>
<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
<!-- cache: cached = yes name = sitemap_jspCache key = sitemap -->
<sitemap>
<loc>http://www.example.com/sitemap1.xml</loc>
<lastmod>2013-07-15</lastmod>
</sitemap>
<sitemap>
<loc>http://www.example.com/sitemap2.xml</loc>
<lastmod>2013-07-15</lastmod>
</sitemap>
<sitemap>
<loc>http://www.example.com/sitemap3.xml</loc>
<lastmod>2013-07-15</lastmod>
</sitemap>
<!-- end cache -->
</sitemapindex>
"""
)
assert list(s) == [
{"lastmod": "2013-07-15", "loc": "http://www.example.com/sitemap1.xml"},
{"lastmod": "2013-07-15", "loc": "http://www.example.com/sitemap2.xml"},
{"lastmod": "2013-07-15", "loc": "http://www.example.com/sitemap3.xml"},
]
def test_comment(self):
s = Sitemap(
b"""<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
xmlns:xhtml="http://www.w3.org/1999/xhtml">
<url>
<loc>http://www.example.com/</loc>
<!-- this is a comment on which the parser might raise an exception if implemented incorrectly -->
</url>
</urlset>"""
)
assert list(s) == [{"loc": "http://www.example.com/"}]
def test_alternate(self):
s = Sitemap(
b"""<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
xmlns:xhtml="http://www.w3.org/1999/xhtml">
<url>
<loc>http://www.example.com/english/</loc>
<xhtml:link rel="alternate" hreflang="de"
href="http://www.example.com/deutsch/"/>
<xhtml:link rel="alternate" hreflang="de-ch"
href="http://www.example.com/schweiz-deutsch/"/>
<xhtml:link rel="alternate" hreflang="en"
href="http://www.example.com/english/"/>
<xhtml:link rel="alternate" hreflang="en"/><!-- wrong tag without href -->
</url>
</urlset>"""
)
assert list(s) == [
{
"loc": "http://www.example.com/english/",
"alternate": [
"http://www.example.com/deutsch/",
"http://www.example.com/schweiz-deutsch/",
"http://www.example.com/english/",
],
}
]
def test_xml_entity_expansion(self):
s = Sitemap(
b"""<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE foo [
<!ELEMENT foo ANY >
<!ENTITY xxe SYSTEM "file:///etc/passwd" >
]>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
<url>
<loc>http://127.0.0.1:8000/&xxe;</loc>
</url>
</urlset>
"""
)
assert list(s) == [{"loc": "http://127.0.0.1:8000/"}]
|
