【发布时间】:2019-03-19 22:37:14
【问题描述】:
给定一个包含 50k 个网站 url 的列表,我的任务是找出其中哪些是可用的/可访问的。这个想法只是向每个 URL 发送一个HEAD 请求并查看状态响应。据我所知,异步方法是可行的方法,现在我使用asyncio 和aiohttp。
我想出了以下代码,但速度非常糟糕。在我的 10mbit 连接上,1000 个 URL 大约需要 200 秒。我不知道期望什么速度,但我是 Python 异步编程的新手,所以我认为我在某个地方走错了。如您所见,我尝试将允许的同时连接数增加到 1000(从默认值 100 增加),并将 DNS 解析的持续时间保留在缓存中;也没有什么大的效果。环境有 Python 3.6 和aiohttp 3.5.4。
也感谢与问题无关的代码审查。
import asyncio
import time
from socket import gaierror
from typing import List, Tuple
import aiohttp
from aiohttp.client_exceptions import TooManyRedirects
# Using a non-default user-agent seems to avoid lots of 403 (Forbidden) errors
HEADERS = {
'user-agent': ('Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/45.0.2454.101 Safari/537.36'),
}
async def get_status_code(session: aiohttp.ClientSession, url: str) -> Tuple[int, str]:
try:
# A HEAD request is quicker than a GET request
resp = await session.head(url, allow_redirects=True, ssl=False, headers=HEADERS)
async with resp:
status = resp.status
reason = resp.reason
if status == 405:
# HEAD request not allowed, fall back on GET
resp = await session.get(
url, allow_redirects=True, ssl=False, headers=HEADERS)
async with resp:
status = resp.status
reason = resp.reason
return (status, reason)
except aiohttp.InvalidURL as e:
return (900, str(e))
except aiohttp.ClientConnectorError:
return (901, "Unreachable")
except gaierror as e:
return (902, str(e))
except aiohttp.ServerDisconnectedError as e:
return (903, str(e))
except aiohttp.ClientOSError as e:
return (904, str(e))
except TooManyRedirects as e:
return (905, str(e))
except aiohttp.ClientResponseError as e:
return (906, str(e))
except aiohttp.ServerTimeoutError:
return (907, "Connection timeout")
except asyncio.TimeoutError:
return (908, "Connection timeout")
async def get_status_codes(loop: asyncio.events.AbstractEventLoop, urls: List[str],
timeout: int) -> List[Tuple[int, str]]:
conn = aiohttp.TCPConnector(limit=1000, ttl_dns_cache=300)
client_timeout = aiohttp.ClientTimeout(connect=timeout)
async with aiohttp.ClientSession(
loop=loop, timeout=client_timeout, connector=conn) as session:
codes = await asyncio.gather(*(get_status_code(session, url) for url in urls))
return codes
def poll_urls(urls: List[str], timeout=20) -> List[Tuple[int, str]]:
"""
:param timeout: in seconds
"""
print("Started polling")
time1 = time.time()
loop = asyncio.get_event_loop()
codes = loop.run_until_complete(get_status_codes(loop, urls, timeout))
time2 = time.time()
dt = time2 - time1
print(f"Polled {len(urls)} websites in {dt:.1f} seconds "
f"at {len(urls)/dt:.3f} URLs/sec")
return codes
【问题讨论】:
标签: python python-3.x python-asyncio aiohttp