06.python aiohttp实现异步爬虫

一.进程池实现异步爬虫

1.代码

#原则：线程池处理的是阻塞且较为耗时的操作

#对下述url发起请求解析出视频详情页的url和视频的名称
url = 'https://www.pearvideo.com/category_5'
page_text = requests.get(url=url,headers=headers).text

tree = etree.HTML(page_text)
li_list = tree.xpath('//ul[@id="listvideoListUl"]/li')
urls = [] #存储所有视频的链接and名字
for li in li_list:
    detail_url = 'https://www.pearvideo.com/'+li.xpath('./div/a/@href')[0]
    name = li.xpath('./div/a/div[2]/text()')[0]+'.mp4'
    #对详情页的url发起请求
    detail_page_text = requests.get(url=detail_url,headers=headers).text
    #从详情页中解析出视频的地址（url）
    ex = 'srcUrl="(.*?)",vdoUrl'
    video_url = re.findall(ex,detail_page_text)[0]
    dic = {
        'name':name,
        'url':video_url
    }
    urls.append(dic)
#对视频链接发起请求获取视频的二进制数据，然后将视频数据进行返回
def get_video_data(dic):
    url = dic['url']
    print(dic['name'],'正在下载......')
    data = requests.get(url=url,headers=headers).content
    #持久化存储操作
    with open(dic['name'],'wb') as fp:
        fp.write(data)
        print(dic['name'],'下载成功！')
#使用线程池对视频数据进行请求（较为耗时的阻塞操作）
pool = Pool(4)
pool.map(get_video_data,urls)

pool.close()
pool.join()

2.弊端

根据CPU核心数决定异步效率且开销过大

二.协程实现异步爬虫

1.python 内置协程模块asyncio

Python协程详解

看最后asyncio介绍

2.代码

异步爬取三个网站并持久化存储

import asyncio
import aiohttp

urls = [
    "http://www.smilenow.top",
    "http://www.baidu.com",
    "http://www.163.com"
]


async def get_cont(url):
    print("准备下载：", url)
    async with aiohttp.ClientSession() as session:
        async with  session.get(url) as response:
            name = url.split(".")[1] + ".html"
            with open(name, "w") as fp:
                text = await response.text()
                fp.write(text)
                print(url, "已经下载完毕")


tasks = map(lambda url: get_cont(url), urls)

asyncio.run(asyncio.wait(tasks))  # done：返回结果，pending:返回未完成的协程函数