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
|
# Basic usage of the Selector, strongly typed to test the typing of parsel's API.
import re
from typing import List
from parsel import Selector
def correct() -> None:
selector = Selector(
text="<html><body><ul><li>1</li><li>2</li><li>3</li></ul></body></html>"
)
li_values: List[str] = selector.css("li").getall()
selector.re_first(re.compile(r"[32]"), "").strip()
xpath_values: List[str] = selector.xpath(
"//somens:a/text()", namespaces={"somens": "http://scrapy.org"}
).extract()
class MySelector(Selector):
def my_own_func(self) -> int:
return 3
my_selector = MySelector()
res: int = my_selector.my_own_func()
sub_res: int = my_selector.xpath("//somens:a/text()")[0].my_own_func()
# Negative checks: all the code lines below have typing errors.
# the "# type: ignore" comment makes sure that mypy identifies them as errors.
def incorrect() -> None:
selector = Selector(
text="<html><body><ul><li>1</li><li>2</li><li>3</li></ul></body></html>"
)
# Wrong query type in css.
selector.css(5).getall() # type: ignore
# Cannot assign a list of str to an int.
li_values: int = selector.css("li").getall() # type: ignore
# Cannot use a string to define namespaces in xpath.
selector.xpath(
"//somens:a/text()", namespaces='{"somens": "http://scrapy.org"}' # type: ignore
).extract()
# Typo in the extract method name.
selector.css("li").extact() # type: ignore
class MySelector(Selector):
def my_own_func(self) -> int:
return 3
my_selector = MySelector()
res: str = my_selector.my_own_func() # type: ignore
sub_res: str = my_selector.xpath("//somens:a/text()")[0].my_own_func() # type: ignore
|
