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
|
import weakref
import parsel
import pytest
from packaging import version
from scrapy.http import HtmlResponse, TextResponse, XmlResponse
from scrapy.selector import Selector
PARSEL_VERSION = version.parse(getattr(parsel, "__version__", "0.0"))
PARSEL_18_PLUS = PARSEL_VERSION >= version.parse("1.8.0")
class TestSelector:
def test_simple_selection(self):
"""Simple selector tests"""
body = b"<p><input name='a'value='1'/><input name='b'value='2'/></p>"
response = TextResponse(url="http://example.com", body=body, encoding="utf-8")
sel = Selector(response)
xl = sel.xpath("//input")
assert len(xl) == 2
for x in xl:
assert isinstance(x, Selector)
assert sel.xpath("//input").getall() == [x.get() for x in sel.xpath("//input")]
assert [x.get() for x in sel.xpath("//input[@name='a']/@name")] == ["a"]
assert [
x.get()
for x in sel.xpath(
"number(concat(//input[@name='a']/@value, //input[@name='b']/@value))"
)
] == ["12.0"]
assert sel.xpath("concat('xpath', 'rules')").getall() == ["xpathrules"]
assert [
x.get()
for x in sel.xpath(
"concat(//input[@name='a']/@value, //input[@name='b']/@value)"
)
] == ["12"]
def test_root_base_url(self):
body = b'<html><form action="/path"><input name="a" /></form></html>'
url = "http://example.com"
response = TextResponse(url=url, body=body, encoding="utf-8")
sel = Selector(response)
assert url == sel.root.base
def test_flavor_detection(self):
text = b'<div><img src="a.jpg"><p>Hello</div>'
sel = Selector(XmlResponse("http://example.com", body=text, encoding="utf-8"))
assert sel.type == "xml"
assert sel.xpath("//div").getall() == [
'<div><img src="a.jpg"><p>Hello</p></img></div>'
]
sel = Selector(HtmlResponse("http://example.com", body=text, encoding="utf-8"))
assert sel.type == "html"
assert sel.xpath("//div").getall() == [
'<div><img src="a.jpg"><p>Hello</p></div>'
]
def test_http_header_encoding_precedence(self):
# '\xa3' = pound symbol in unicode
# '\xc2\xa3' = pound symbol in utf-8
# '\xa3' = pound symbol in latin-1 (iso-8859-1)
meta = (
'<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">'
)
head = f"<head>{meta}</head>"
body_content = '<span id="blank">\xa3</span>'
body = f"<body>{body_content}</body>"
html = f"<html>{head}{body}</html>"
encoding = "utf-8"
html_utf8 = html.encode(encoding)
headers = {"Content-Type": ["text/html; charset=utf-8"]}
response = HtmlResponse(
url="http://example.com", headers=headers, body=html_utf8
)
x = Selector(response)
assert x.xpath("//span[@id='blank']/text()").getall() == ["\xa3"]
def test_badly_encoded_body(self):
# \xe9 alone isn't valid utf8 sequence
r1 = TextResponse(
"http://www.example.com",
body=b"<html><p>an Jos\xe9 de</p><html>",
encoding="utf-8",
)
Selector(r1).xpath("//text()").getall()
def test_weakref_slots(self):
"""Check that classes are using slots and are weak-referenceable"""
x = Selector(text="")
weakref.ref(x)
assert not hasattr(x, "__dict__"), (
f"{x.__class__.__name__} does not use __slots__"
)
def test_selector_bad_args(self):
with pytest.raises(ValueError, match="received both response and text"):
Selector(TextResponse(url="http://example.com", body=b""), text="")
class TestJMESPath:
@pytest.mark.skipif(
not PARSEL_18_PLUS, reason="parsel < 1.8 doesn't support jmespath"
)
def test_json_has_html(self) -> None:
"""Sometimes the information is returned in a json wrapper"""
body = """
{
"content": [
{
"name": "A",
"value": "a"
},
{
"name": {
"age": 18
},
"value": "b"
},
{
"name": "C",
"value": "c"
},
{
"name": "<a>D</a>",
"value": "<div>d</div>"
}
],
"html": "<div><a>a<br>b</a>c</div><div><a>d</a>e<b>f</b></div>"
}
"""
resp = TextResponse(url="http://example.com", body=body, encoding="utf-8")
assert (
resp.jmespath("html").get()
== "<div><a>a<br>b</a>c</div><div><a>d</a>e<b>f</b></div>"
)
assert resp.jmespath("html").xpath("//div/a/text()").getall() == ["a", "b", "d"]
assert resp.jmespath("html").css("div > b").getall() == ["<b>f</b>"]
assert resp.jmespath("content").jmespath("name.age").get() == "18"
@pytest.mark.skipif(
not PARSEL_18_PLUS, reason="parsel < 1.8 doesn't support jmespath"
)
def test_html_has_json(self) -> None:
body = """
<div>
<h1>Information</h1>
<content>
{
"user": [
{
"name": "A",
"age": 18
},
{
"name": "B",
"age": 32
},
{
"name": "C",
"age": 22
},
{
"name": "D",
"age": 25
}
],
"total": 4,
"status": "ok"
}
</content>
</div>
"""
resp = TextResponse(url="http://example.com", body=body, encoding="utf-8")
assert resp.xpath("//div/content/text()").jmespath("user[*].name").getall() == [
"A",
"B",
"C",
"D",
]
assert resp.xpath("//div/content").jmespath("user[*].name").getall() == [
"A",
"B",
"C",
"D",
]
assert resp.xpath("//div/content").jmespath("total").get() == "4"
@pytest.mark.skipif(
not PARSEL_18_PLUS, reason="parsel < 1.8 doesn't support jmespath"
)
def test_jmestpath_with_re(self) -> None:
body = """
<div>
<h1>Information</h1>
<content>
{
"user": [
{
"name": "A",
"age": 18
},
{
"name": "B",
"age": 32
},
{
"name": "C",
"age": 22
},
{
"name": "D",
"age": 25
}
],
"total": 4,
"status": "ok"
}
</content>
</div>
"""
resp = TextResponse(url="http://example.com", body=body, encoding="utf-8")
assert resp.xpath("//div/content/text()").jmespath("user[*].name").re(
r"(\w+)"
) == ["A", "B", "C", "D"]
assert resp.xpath("//div/content").jmespath("user[*].name").re(r"(\w+)") == [
"A",
"B",
"C",
"D",
]
assert resp.xpath("//div/content").jmespath("unavailable").re(r"(\d+)") == []
assert (
resp.xpath("//div/content").jmespath("unavailable").re_first(r"(\d+)")
is None
)
assert resp.xpath("//div/content").jmespath("user[*].age.to_string(@)").re(
r"(\d+)"
) == ["18", "32", "22", "25"]
@pytest.mark.skipif(PARSEL_18_PLUS, reason="parsel >= 1.8 supports jmespath")
def test_jmespath_not_available(self) -> None:
body = """
{
"website": {"name": "Example"}
}
"""
resp = TextResponse(url="http://example.com", body=body, encoding="utf-8")
with pytest.raises(AttributeError):
resp.jmespath("website.name").get()
|
