aiohttp、异步、协程、爬虫（入门案例）

aiohttp异步请求提高爬虫效率

• aiohttp可以理解为一个异步的requests，使用aiohttp发送请求可大大提高爬虫效率。
• 基本语法可参考 https://www.jianshu.com/p/63d9741b0bee

async定义一个协程

improt async

# 定义该函数为协程
async def test():
    pass

requests发送请求

import requests
html_str = requests.get(url).text
print(html_str)

aiohttp发送请求

import asyncio
import aiohttp
# 对比requests语法

async with aiohttp.ClientSession() as session:
    async with session.get(url=url) as response:
        html_str = await response.read()
        print(html)

使用requests单线程爬取糗事百科12页数据

import time

import requests
import lxml.html
def make_url_list():
    base_url = 'https://www.qiushibaike.com/8hr/page/{}/'
    for i in range(1, 14):
        yield base_url.format(i)

def getHTMLText(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
    }
    html_str = requests.get(url=url,headers=headers).text
    return html_str

def printTitle(html_str):
    html = lxml.html.fromstring(str(html_str))
    title = html.xpath('//a[@class="recmd-content"]/text()')
    return title

def run():
    url_list = make_url_list()
    for url in url_list:
        html_str = getHTMLText(url)
        title = printTitle(html_str)
        print(title)

t1 = time.time()
run()
t2 = time.time()
print('耗时：',t2-t1)

打印结果

使用aiohttp异步爬取糗事百科12页数据

import asyncio
import time

import aiohttp
import lxml.html
from queue import Queue


class QiuBai:
    def __init__(self):
        self.base_url = 'https://www.qiushibaike.com/8hr/page/{}/'
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
        }
        self.html_queue = Queue()

    def make_url_list(self):
        for i in range(1, 14):
            url = self.base_url.format(i)
            yield url

    async def getHTMLText(self, url):
        async with aiohttp.ClientSession() as session:
            async with session.get(url=url, headers=self.headers) as response:
                html_str = await response.read()
                html = lxml.html.fromstring(html_str.decode(u'utf-8', errors='ignore'))
                title = html.xpath('//a[@class="recmd-content"]/text()')
                print(title)


    def run(self):
        loop = asyncio.get_event_loop()
        tasks = [self.getHTMLText(url) for url in self.make_url_list()]
        loop.run_until_complete(asyncio.wait(tasks))


if __name__ == '__main__':
    qiu = QiuBai()
    t1 = time.time()
    qiu.run()
    t2 = time.time()
    print('耗时：', t2 - t1)

打印结果
可以看出使用aiohttp异步爬取速度有明显的提升。