在我的代码触发此警告消息后，我在 Google 上搜索如何重用 aiohttp ClientSession 实例后发现了这个问题：UserWarning: Creating a client session outside of coroutine is a very dangerous idea
此代码虽然相关，但可能无法解决上述问题。我是 asyncio 和 aiohttp 的新手，所以这可能不是最佳实践。这是我在阅读了很多看似矛盾的信息后能想到的最好的方法。
我从打开上下文的 Python 文档中创建了一个类 ResourceManager。
ResourceManager 实例通过魔术方法 __aenter__ 和 __aexit__ 以及 BaseScraper.set_session 和 BaseScraper.close_session 包装方法来处理 aiohttp ClientSession 实例的打开和关闭。
我能够使用以下代码重用 ClientSession 实例。
BaseScraper 类也有验证方法。依赖lxml第三方包。
import asyncio
from time import time
from contextlib import contextmanager, AbstractContextManager, ExitStack
import aiohttp
import lxml.html
class ResourceManager(AbstractContextManager):
# Code taken from Python docs: 29.6.2.4. of https://docs.python.org/3.6/library/contextlib.html
def __init__(self, scraper, check_resource_ok=None):
self.acquire_resource = scraper.acquire_resource
self.release_resource = scraper.release_resource
if check_resource_ok is None:
def check_resource_ok(resource):
return True
self.check_resource_ok = check_resource_ok
@contextmanager
def _cleanup_on_error(self):
with ExitStack() as stack:
stack.push(self)
yield
# The validation check passed and didn't raise an exception
# Accordingly, we want to keep the resource, and pass it
# back to our caller
stack.pop_all()
def __enter__(self):
resource = self.acquire_resource()
with self._cleanup_on_error():
if not self.check_resource_ok(resource):
msg = "Failed validation for {!r}"
raise RuntimeError(msg.format(resource))
return resource
def __exit__(self, *exc_details):
# We don't need to duplicate any of our resource release logic
self.release_resource()
class BaseScraper:
login_url = ""
login_data = dict() # dict of key, value pairs to fill the login form
loop = asyncio.get_event_loop()
def __init__(self, urls):
self.urls = urls
self.acquire_resource = self.set_session
self.release_resource = self.close_session
async def _set_session(self):
self.session = await aiohttp.ClientSession().__aenter__()
def set_session(self):
set_session_attr = self.loop.create_task(self._set_session())
self.loop.run_until_complete(set_session_attr)
return self # variable after "as" becomes instance of BaseScraper
async def _close_session(self):
await self.session.__aexit__(None, None, None)
def close_session(self):
close_session = self.loop.create_task(self._close_session())
self.loop.run_until_complete(close_session)
def __call__(self):
fetch_urls = self.loop.create_task(self._fetch())
return self.loop.run_until_complete(fetch_urls)
async def _get(self, url):
async with self.session.get(url) as response:
result = await response.read()
return url, result
async def _fetch(self):
tasks = (self.loop.create_task(self._get(url)) for url in self.urls)
start = time()
results = await asyncio.gather(*tasks)
print(
"time elapsed: {} seconds \nurls count: {}".format(
time() - start, len(urls)
)
)
return results
@property
def form(self):
"""Create and return form for authentication."""
form = aiohttp.FormData(self.login_data)
get_login_page = self.loop.create_task(self._get(self.login_url))
url, login_page = self.loop.run_until_complete(get_login_page)
login_html = lxml.html.fromstring(login_page)
hidden_inputs = login_html.xpath(r'//form//input[@type="hidden"]')
login_form = {x.attrib["name"]: x.attrib["value"] for x in hidden_inputs}
for key, value in login_form.items():
form.add_field(key, value)
return form
async def _login(self, form):
async with self.session.post(self.login_url, data=form) as response:
if response.status != 200:
response.raise_for_status()
print("logged into {}".format(url))
await response.release()
def login(self):
post_login_form = self.loop.create_task(self._login(self.form))
self.loop.run_until_complete(post_login_form)
if __name__ == "__main__":
urls = ("http://example.com",) * 10
base_scraper = BaseScraper(urls)
with ResourceManager(base_scraper) as scraper:
for url, html in scraper():
print(url, len(html))