Question

我正在使用aiohttp和limited_as_completed方法来加快抓取速度（大约1亿个静态网站页面）。但是，该代码在几分钟后停止，并返回TimeoutError。我尝试了几件事，但仍然无法防止引发asyncio.TimeoutError。请问如何忽略该错误并继续？

我正在运行的代码是：

N=123
import html
from lxml import etree
import requests
import asyncio 
import aiohttp
from aiohttp import ClientSession, TCPConnector
import pandas as pd
import re 
import csv 
import time
from itertools import islice
import sys
from contextlib import suppress

start = time.time()
data = {}
data['name'] = []
filename = "C:\\Users\\xxxx"+ str(N) + ".csv"

def limited_as_completed(coros, limit):
    futures = [
        asyncio.ensure_future(c)
        for c in islice(coros, 0, limit)
    ]
    async def first_to_finish():
        while True:
            await asyncio.sleep(0)
            for f in futures:
                if f.done():
                    futures.remove(f)
                    try:
                        newf = next(coros)
                        futures.append(
                            asyncio.ensure_future(newf))
                    except StopIteration as e:
                        pass
                    return f.result()
    while len(futures) > 0:
        yield first_to_finish()

async def get_info_byid(i, url, session):
    async with session.get(url,timeout=20) as resp:
        print(url)
        with suppress(asyncio.TimeoutError):
            r = await resp.text()
            name = etree.HTML(r).xpath('//h2[starts-with(text(),"Customer Name")]/text()')
            data['name'].append(name)
            dataframe = pd.DataFrame(data)
            dataframe.to_csv(filename, index=False, sep='|')

limit = 1000
async def print_when_done(tasks):
    for res in limited_as_completed(tasks, limit):
        await res

url = "http://xxx.{}.html"
loop = asyncio.get_event_loop()

async def main():
    connector = TCPConnector(limit=10)
    async with ClientSession(connector=connector,headers=headers,raise_for_status=False) as session:
        coros = (get_info_byid(i, url.format(i), session) for i in range(N,N+1000000))
        await print_when_done(coros)

loop.run_until_complete(main())
loop.close()
print("took", time.time() - start, "seconds.")

错误日志为：

Traceback (most recent call last):
  File "C:\Users\xxx.py", line 111, in <module>
    loop.run_until_complete(main())
  File "C:\Users\xx\AppData\Local\Programs\Python\Python37-32\lib\asyncio\base_events.py", line 573, in run_until_complete
    return future.result()
  File "C:\Users\xxx.py", line 109, in main
    await print_when_done(coros)
  File "C:\Users\xxx.py", line 98, in print_when_done
    await res
  File "C:\Users\xxx.py", line 60, in first_to_finish
    return f.result()
  File "C:\Users\xxx.py", line 65, in get_info_byid
    async with session.get(url,timeout=20) as resp:
  File "C:\Users\xx\AppData\Local\Programs\Python\Python37-32\lib\site-packages\aiohttp\client.py", line 855, in __aenter__
    self._resp = await self._coro
  File "C:\Users\xx\AppData\Local\Programs\Python\Python37-32\lib\site-packages\aiohttp\client.py", line 391, in _request
    await resp.start(conn)
  File "C:\Users\xx\AppData\Local\Programs\Python\Python37-32\lib\site-packages\aiohttp\client_reqrep.py", line 770, in start
    self._continue = None
  File "C:\Users\xx\AppData\Local\Programs\Python\Python37-32\lib\site-packages\aiohttp\helpers.py", line 673, in __exit__
    raise asyncio.TimeoutError from None
concurrent.futures._base.TimeoutError

我尝试过 1）添加期望asyncio.TimeoutError：通过。不起作用

async def get_info_byid(i, url, session):
    async with session.get(url,timeout=20) as resp:
        print(url)
        try:
            r = await resp.text()
            name = etree.HTML(r).xpath('//h2[starts-with(text(),"Customer Name")]/text()')
            data['name'].append(name)
            dataframe = pd.DataFrame(data)
            dataframe.to_csv(filename, index=False, sep='|')
        except asyncio.TimeoutError:
            pass

2）如上所示抑制（asyncio.TimeoutError）。不起作用

我昨天刚刚学习了aiohttp，所以也许我的代码中有其他错误，仅在运行几分钟后才导致超时错误？如果有人知道如何处理，将非常感谢！

Answer 1

@Yurii Kramarenko所做的事情肯定会引起未公开的客户会话例外，因为会话从未被正确关闭。我推荐的是这样的：

import asyncio
import aiohttp

async def main(urls):
    async with aiohttp.ClientSession(timeout=self.timeout) as session:
        tasks=[self.do_something(session,url) for url in urls]
        await asyncio.gather(*tasks)

Answer 2

我喜欢@jbxiaoyu的答案，但是超时kwarg似乎有一个特殊的对象，所以我想我要添加您需要创建一个ClientTimeout对象，然后将其传递给Session，如下所示：

from aiohttp import ClientSession, ClientTimeout
timeout = ClientTimeout(total=600)
async with ClientSession(timeout=timeout) as session:
    tasks=[self.do_something(session,url) for url in urls]
    await asyncio.gather(*tasks)

Answer 3

简单的示例（不是很好，但是效果很好）：

import asyncio
from aiohttp.client import ClientSession


class Wrapper:

    def __init__(self, session):
        self._session = session

    async def get(self, url):
        try:
            async with self._session.get(url, timeout=20) as resp:
                return await resp.text()
        except Exception as e:
            print(e)


loop = asyncio.get_event_loop()
wrapper = Wrapper(ClientSession())

responses = loop.run_until_complete(
    asyncio.gather(
        wrapper.get('http://google.com'),
        wrapper.get('http://google.com'),
        wrapper.get('http://google.com'),
        wrapper.get('http://google.com'),
        wrapper.get('http://google.com')
    )
)

print(responses)

Answer 4

当我收到此错误时，我意识到我没有连接到 vpn。所以我建议你检查你在哪里提出请求。

如何防止引发asyncio.TimeoutError并继续循环

4 个答案: