asyncio/aiohttp 未返回响应

Question

我正在尝试从 https://www.officialcharts.com/ by parallelising web requests using asyncio/aiohttp. I implemented the code given at the link here 抓取一些数据。

我遵循了两种不同的程序。第一个是这样的。

from bs4 import BeautifulSoup
from urllib.request import urlopen
from selenium import webdriver
import time
import pandas as pd
import numpy as np
import re
import json

import requests
from bs4 import BeautifulSoup
from datetime import date, timedelta
from IPython.display import clear_output
import memory_profiler

import spotipy
import spotipy.util as util
import pandas as pd
from  more_itertools import unique_everseen

weeks = []
d = date(1970, 1, 1) 
d += timedelta(days = 6 - d.weekday())

for i in range(2500):    
    weeks.append(d.strftime('%Y%m%d'))
    d += timedelta(days = 7)

import asyncio
from aiohttp import ClientSession
import nest_asyncio
nest_asyncio.apply()

result = []
async def fetch(url, session):
    async with session.get(url) as response:
        return await response.read()

async def run(r):  
    tasks = []

    # Fetch all responses within one Client session,
    # keep connection alive for all requests.
    async with ClientSession() as session:
        for i in range(r):
            url = 'https://www.officialcharts.com/charts/singles-chart/' + weeks[i] + '/'
            task = asyncio.ensure_future(fetch(url, session))
            tasks.append(task)

        responses = await asyncio.gather(*tasks)
        result.append(responses)


loop = asyncio.get_event_loop()
future = asyncio.ensure_future(run(5))
loop.run_until_complete(future)

print('Done')
print(result[0][0] == None)

上面代码的问题是，当我同时发出超过 1000 个请求时，它会失败。

post 的作者实施了一个不同的过程来解决这个问题，他声称我们可以处理多达 10K 的请求。我遵循了他的第二个程序，这是我的代码。

import random
import asyncio
from aiohttp import ClientSession
import nest_asyncio
nest_asyncio.apply()

result = []
async def fetch(url, session):
    async with session.get(url) as response:
        delay = response.headers.get("DELAY")
        date = response.headers.get("DATE")
        print("{}:{} with delay {}".format(date, response.url, delay))
        return await response.read()


async def bound_fetch(sem, url, session):
    # Getter function with semaphore.
    async with sem:
        await fetch(url, session)


async def run(r):
    tasks = []
    # create instance of Semaphore
    sem = asyncio.Semaphore(1000)

    # Create client session that will ensure we dont open new connection
    # per each request.
    async with ClientSession() as session:
        for i in range(r):         
            url = 'https://www.officialcharts.com/charts/singles-chart/' + weeks[i] + '/'
            task = asyncio.ensure_future(bound_fetch(sem, url, session))
            tasks.append(task)

        responses = await asyncio.gather(*tasks)
        result.append(responses)

number = 5

loop = asyncio.get_event_loop()
future = asyncio.ensure_future(run(number))
loop.run_until_complete(future)

print('Done')
print(result[0][0] == None)

出于某种原因，这 return 没有任何回应。

PS:我不是CS出身，编程只是为了好玩。我不知道 asyncio 代码内部发生了什么。

Answer 1

尽量使用最新版本。

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

from aiohttp import ClientSession, client_exceptions
from asyncio import Semaphore, ensure_future, gather, run
from json import dumps, loads

limit = 10
http_ok = [200]


async def scrape(url_list):
    tasks = list()
    sem = Semaphore(limit)

    async with ClientSession() as session:
        for url in url_list:
            task = ensure_future(scrape_bounded(url, sem, session))
            tasks.append(task)

        result = await gather(*tasks)

    return result


async def scrape_bounded(url, sem, session):
    async with sem:
        return await scrape_one(url, session)


async def scrape_one(url, session):
    try:
        async with session.get(url) as response:
            content = await response.read()
    except client_exceptions.ClientConnectorError:
        print('Scraping %s failed due to the connection problem', url)
        return False

    if response.status not in http_ok:
        print('Scraping%s failed due to the return code %s', url, response.status)
        return False

    content = loads(content.decode('UTF-8'))

    return content

if __name__ == '__main__':
    urls = ['http://demin.co/echo1/', 'http://demin.co/echo2/']
    res = run(scrape(urls))

    print(dumps(res, indent=4))

这是一个真实的模板project，与预测的一样。

你可以找到这个源代码here

asyncio/aiohttp 未返回响应

asyncio/aiohttp not returning response

python

web-scraping

python-requests

aiohttp