'
]
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 = (
''
)
head = f"{meta}"
body_content = '\xa3'
body = f"{body_content}"
html = f"{head}{body}"
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"
an Jos\xe9 de
",
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="")
@pytest.mark.skipif(not PARSEL_18_PLUS, reason="parsel < 1.8 doesn't support jmespath")
class TestJMESPath:
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": "D",
"value": "
