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
|
import scrapy
from scrapy.crawler import CrawlerProcess
from scrapy.utils.reactor import (
install_reactor,
is_asyncio_reactor_installed,
is_reactor_installed,
)
if is_reactor_installed():
raise RuntimeError(
"Reactor already installed before is_asyncio_reactor_installed()."
)
try:
is_asyncio_reactor_installed()
except RuntimeError:
pass
else:
raise RuntimeError("is_asyncio_reactor_installed() did not raise RuntimeError.")
if is_reactor_installed():
raise RuntimeError(
"Reactor already installed after is_asyncio_reactor_installed()."
)
install_reactor("twisted.internet.asyncioreactor.AsyncioSelectorReactor")
if not is_asyncio_reactor_installed():
raise RuntimeError("Wrong reactor installed after install_reactor().")
class ReactorCheckExtension:
def __init__(self):
if not is_asyncio_reactor_installed():
raise RuntimeError("ReactorCheckExtension requires the asyncio reactor.")
class NoRequestsSpider(scrapy.Spider):
name = "no_request"
async def start(self):
return
yield
process = CrawlerProcess(
settings={
"TWISTED_REACTOR": "twisted.internet.asyncioreactor.AsyncioSelectorReactor",
"EXTENSIONS": {ReactorCheckExtension: 0},
}
)
process.crawl(NoRequestsSpider)
process.start()
|
