aiohttp 异步http请求-3.异步批量下载图片

Posted 2022-04-22 上海-悠悠

前言

当我们需要批量下载图片的时候，requests 库会比较慢，如果一个个下载，出现阻塞的时候，后面的都会阻塞卡住，假死状态。当然你用多线程也能提高效率。
这里介绍用aiohttp 异步批量下载图片

异步批量下载图片

话不多说，直接看代码

import aiohttp
import asyncio
from pathlib import Path


async def down_img(session, url):
    """下载图片"""
    name = url.split('/')[-1]  # 获得图片名字
    img = await session.get(url)
    # 触发到await就切换，等待get到数据
    content = await img.read()
    # 读取内容
    with open('./down_img/'+str(name), 'wb') as f:
        # 写入至文件
        f.write(content)
        print(f'name 下载完成！')
    return str(url)


async def main(URL):
    # 建立会话session
    async with aiohttp.ClientSession() as session:
        # 建立所有任务
        tasks = [asyncio.create_task(down_img(session, img_url)) for img_url in URL]
        # 触发await，等待任务完成
        done, pending = await asyncio.wait(tasks)
        all_results = [done_task.result() for done_task in done]
        # 获取所有结果
        print("ALL RESULT:"+str(all_results))


URL = [
    'https://cdn.pixabay.com/photo/2014/10/07/13/48/mountain-477832_960_720.jpg',
    'https://cdn.pixabay.com/photo/2013/07/18/10/56/railroad-163518_960_720.jpg',
    'https://cdn.pixabay.com/photo/2018/03/12/20/07/maldives-3220702_960_720.jpg',
    'https://cdn.pixabay.com/photo/2017/08/04/17/56/dolomites-2580866_960_720.jpg',
    'https://cdn.pixabay.com/photo/2016/06/20/03/15/pier-1467984_960_720.jpg',
    'https://cdn.pixabay.com/photo/2014/07/30/02/00/iceberg-404966_960_720.jpg',
    'https://cdn.pixabay.com/photo/2014/11/02/10/41/plane-513641_960_720.jpg',
    'https://cdn.pixabay.com/photo/2015/10/30/20/13/sea-1014710_960_720.jpg'
]

fp = Path('./down_img')
if not fp.exists():
    fp.mkdir()


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

运行结果

mountain-477832_960_720.jpg 下载完成！
railroad-163518_960_720.jpg 下载完成！
maldives-3220702_960_720.jpg 下载完成！
dolomites-2580866_960_720.jpg 下载完成！
pier-1467984_960_720.jpg 下载完成！
plane-513641_960_720.jpg 下载完成！
iceberg-404966_960_720.jpg 下载完成！
sea-1014710_960_720.jpg 下载完成！
ALL RESULT:['https://cdn.pixabay.com/photo/2014/07/30/02/00/iceberg-404966_960_720.jpg', 'https://cdn.pixabay.com/photo/2018/03/12/20/07/maldives-3220702_960_720.jpg', 'https://cdn.pixabay.com/photo/2014/10/07/13/48/mountain-477832_960_720.jpg', 'https://cdn.pixabay.com/photo/2014/11/02/10/41/plane-513641_960_720.jpg', 'https://cdn.pixabay.com/photo/2017/08/04/17/56/dolomites-2580866_960_720.jpg', 'https://cdn.pixabay.com/photo/2013/07/18/10/56/railroad-163518_960_720.jpg', 'https://cdn.pixabay.com/photo/2015/10/30/20/13/sea-1014710_960_720.jpg', 'https://cdn.pixabay.com/photo/2016/06/20/03/15/pier-1467984_960_720.jpg']

Semaphore控制并发

上面的代码是把8个url一起加入到并发任务，当url数量很多的时候，我们希望可以控制并发量，于是可以用到Semaphore控制并发。

semaphore = asyncio.Semaphore(2)  # 限制并发量为2

优化后的代码

import aiohttp
import asyncio
from pathlib import Path


async def down_img(session, url, semaphore):
    """下载图片"""
    async with semaphore:
        name = url.split('/')[-1]  # 获得图片名字
        img = await session.get(url)
        # 触发到await就切换，等待get到数据
        content = await img.read()
        # 读取内容
        with open('./down_img/'+str(name), 'wb') as f:
            # 写入至文件
            f.write(content)
            print(f'name 下载完成！')
        return str(url)


async def main(URL):
    semaphore = asyncio.Semaphore(2)  # 限制并发量为2
    # 建立会话session
    async with aiohttp.ClientSession() as session:
        # 建立所有任务
        tasks = [asyncio.create_task(down_img(session, img_url, semaphore)) for img_url in URL]
        # 触发await，等待任务完成
        done, pending = await asyncio.wait(tasks)
        all_results = [done_task.result() for done_task in done]
        # 获取所有结果
        print("ALL RESULT:"+str(all_results))


URL = [
    'https://cdn.pixabay.com/photo/2014/10/07/13/48/mountain-477832_960_720.jpg',
    'https://cdn.pixabay.com/photo/2013/07/18/10/56/railroad-163518_960_720.jpg',
    'https://cdn.pixabay.com/photo/2018/03/12/20/07/maldives-3220702_960_720.jpg',
    'https://cdn.pixabay.com/photo/2017/08/04/17/56/dolomites-2580866_960_720.jpg',
    'https://cdn.pixabay.com/photo/2016/06/20/03/15/pier-1467984_960_720.jpg',
    'https://cdn.pixabay.com/photo/2014/07/30/02/00/iceberg-404966_960_720.jpg',
    'https://cdn.pixabay.com/photo/2014/11/02/10/41/plane-513641_960_720.jpg',
    'https://cdn.pixabay.com/photo/2015/10/30/20/13/sea-1014710_960_720.jpg'
]

fp = Path('./down_img')
if not fp.exists():
    fp.mkdir()

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

使用TCPConnector控制并发

TCPConnector 使用 limit 参数控制并发数

    conn = aiohttp.TCPConnector(limit=2)
    # 建立会话session
    async with aiohttp.ClientSession(connector=conn) as session:

完成代码如下

import aiohttp
import asyncio
from pathlib import Path


async def down_img(session, url):
    """下载图片"""
    name = url.split('/')[-1]  # 获得图片名字
    img = await session.get(url)
    # 触发到await就切换，等待get到数据
    content = await img.read()
    # 读取内容
    with open('./down_img/'+str(name), 'wb') as f:
        # 写入至文件
        f.write(content)
        print(f'name 下载完成！')
    return str(url)


async def main(URL):
    conn = aiohttp.TCPConnector(limit=2)
    # 建立会话session
    async with aiohttp.ClientSession(connector=conn) as session:
        # 建立所有任务
        tasks = [asyncio.create_task(down_img(session, img_url)) for img_url in URL]
        # 触发await，等待任务完成
        done, pending = await asyncio.wait(tasks)
        all_results = [done_task.result() for done_task in done]
        # 获取所有结果
        print("ALL RESULT:"+str(all_results))


URL = [
    'https://cdn.pixabay.com/photo/2014/10/07/13/48/mountain-477832_960_720.jpg',
    'https://cdn.pixabay.com/photo/2013/07/18/10/56/railroad-163518_960_720.jpg',
    'https://cdn.pixabay.com/photo/2018/03/12/20/07/maldives-3220702_960_720.jpg',
    'https://cdn.pixabay.com/photo/2017/08/04/17/56/dolomites-2580866_960_720.jpg',
    'https://cdn.pixabay.com/photo/2016/06/20/03/15/pier-1467984_960_720.jpg',
    'https://cdn.pixabay.com/photo/2014/07/30/02/00/iceberg-404966_960_720.jpg',
    'https://cdn.pixabay.com/photo/2014/11/02/10/41/plane-513641_960_720.jpg',
    'https://cdn.pixabay.com/photo/2015/10/30/20/13/sea-1014710_960_720.jpg'
]

fp = Path('./down_img')
if not fp.exists():
    fp.mkdir()

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