链家网爬虫同步VS异步执行时间对比

异步执行时间

import time

import asyncio

import aiohttp

from lxml import etree

start_time = time.time()

async def get_url(url):

    session = aiohttp.ClientSession()

    response = await session.get(url)

    result = await response.text()

    terr = etree.HTML(result)

    ret = terr.xpath('//*[@id="content"]/div[1]/ul/li')

    for li in ret:

        title = li.xpath('.//div[@class="title"]//text()')

        print(title)

async def get_html():

    result = await get_url(url)

    print(result)

if __name__ == '__main__':

    url = "https://sz.lianjia.com/ershoufang/pg{}"

    tasks = [asyncio.ensure_future(get_url(url.format(rl))) for rl in range(1,30)]  # 创建task对象

    loop = asyncio.get_event_loop() # 创建事件循环对象

    loop.run_until_complete(asyncio.wait(tasks)) # 将所有task对象注册到事件循环对象中

    end_time = time.time()

    print("执行时间{}".format(end_time - start_time))  # 执行时间6.241659641265869

同步执行时间

import time

import requests

from lxml import etree

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36'

}

start_time = time.time()

def get_url():

    url = "https://sz.lianjia.com/ershoufang/pg{}"

    for i in range(1,30):

        urli = url.format(i)

        result = requests.get(urli, headers=headers).text

        terr = etree.HTML(result)

        ret = terr.xpath('//*[@id="content"]/div[1]/ul/li')

        for li in ret:

            title = li.xpath('.//div[@class="title"]//text()')

            print(title)

get_url()

end_time = time.time()

print("执行时间{}".format(end_time - start_time))

# 执行时间82.57950687408447