Question

我尝试使用aiohttp和asyncio进行请求。但是出现错误

'需要asyncio.Future，协程或可等待的对象'

这是我的代码。我该如何解决。

import requests
from bs4 import BeautifulSoup
import asyncio
import aiohttp

res = requests.get('https://www.rottentomatoes.com/top/')
soup = BeautifulSoup(res.text,'lxml')
movie_list=[]
for link in soup.select('section li a[href]'):
    movie_list.append('https://www.rottentomatoes.com'+link.get('href'))

async def request(url):
    async with aiohttp.ClientSession() as session:
        async with session.get(url) as resp:
            body = await resp.text(encoding='utf-8')
            soup =BeautifulSoup(body,'lxml')
            movie = []
            async for link in soup.select('tbody tr td a '):
                await movie.append(link.get('href'))

        return  movie

async def main():
    results = await asyncio.gather(*[request(url) for url in movie_list])
    print(results)
    return results
print(movie_list)

loop = asyncio.get_event_loop()
results = loop.run_until_complete(main)

Answer 1

您需要调用loop.run_until_complete(main())，而不仅仅是函数main（不带括号）。接下来的事情是您在async中不需要soup.select()关键字。我还更改了选择字符串以解析内容：

import requests
from bs4 import BeautifulSoup
import asyncio
import aiohttp

res = requests.get('https://www.rottentomatoes.com/top/')
soup = BeautifulSoup(res.text,'lxml')
movie_list=[]

for link in soup.select('section li a[href]'):
    movie_list.append('https://www.rottentomatoes.com'+link.get('href'))

async def request(url):
    async with aiohttp.ClientSession() as session:
        async with session.get(url) as resp:
            body = await resp.text(encoding='utf-8')
            soup = BeautifulSoup(body,'lxml')
            movie = []
            # no need to call async for here!
            for link in soup.select('section#top_movies_main table a'):
                movie.append(link['href'])

        return  movie

async def main():
    results = await asyncio.gather(*[request(url) for url in movie_list])
    print(results)
    return results

print(movie_list)

loop = asyncio.get_event_loop()
results = loop.run_until_complete(main())   # you need to create coroutine

打印：

['https://www.rottentomatoes.com/top/bestofrt/top_100_action__adventure_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_animation_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_art_house__international_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_classics_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_comedy_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_documentary_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_drama_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_horror_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_kids__family_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_musical__performing_arts_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_mystery__suspense_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_romance_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_science_fiction__fantasy_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_special_interest_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_sports__fitness_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_television_movies/', 'https://www.rottentomatoes.com/top/bestofrt/top_100_western_movies/']
[['/m/mad_max_fury_road', '/m/1013775-metropolis', '/m/wonder_woman_2017', '/m/logan_2017', '/m/1011615-king_kong', '/m/zootopia', '/m/1000355-adventures_of_robin_hood', '/m/star_wars_episode_vii_the_force_awakens', 

... and so on

对python的异步请求

1 个答案: