多线程爬取小说

例子：
网站：https://www.17k.com/
随便找个小说爬
在这里插入图片描述
代码：
这是用佛如循环一个一个的爬取

import time
from concurrent.futures import ThreadPoolExecutor
from lxml import etree
import requests
url ="https://www.17k.com/list/3379384.html"
resq = requests.get(url)
resq.encoding = "utf-8"
ht = resq.text   
ee= etree.HTML(ht)
nr = ee.xpath("/html/body/div[5]/dl/dd/a/@href")
url1 ="https://www.17k.com"
def getwz(surl):
    resq1 = requests.get(surl)
    resq1.encoding = "utf-8"
    nr1 = resq1.text
    ee1 = etree.HTML(nr1)
    wz = ee1.xpath("//*[@id='readArea']/div[1]/div[2]/p/text()")
    print(wz)
t1= time.time()
for urll in nr:
    surl =url1+urll
    getwz(surl)

t2 = time.time()
print(t2-t1)#这是测试时间

这是上面的运行时间
在这里插入图片描述
可以看到效率是极其低下的

另一种

下面是利用线程池创建多个线程进行爬取

import time
from concurrent.futures import ThreadPoolExecutor   #创建线程池所需的模块
from lxml import etree
import requests
url ="https://www.17k.com/list/3379384.html"
resq = requests.get(url)
resq.encoding = "utf-8"
ht = resq.text

ee= etree.HTML(ht)
nr = ee.xpath("/html/body/div[5]/dl/dd/a/@href")
url1 ="https://www.17k.com"
def getwz(surl):
    resq1 = requests.get(surl)
    resq1.encoding = "utf-8"
    nr1 = resq1.text
    ee1 = etree.HTML(nr1)
    wz = ee1.xpath("//*[@id='readArea']/div[1]/div[2]/p/text()")
    print(wz)
if __name__ == '__main__':
    t1=time.time()
    with ThreadPoolExecutor(50) as t:   #创建线程池的格式，50是代表这个线程池有50个线程

        for urll in nr:      
            surl = url1 + urll
            t.submit(getwz,surl)  #让对象t去调用函数  这样多个函数同时进行效率高
    t2= time.time()
print(t2-t1)

0.9097669124603271
这是程序运行时间，可以看出效率高了很多

用异步操作爬取

并将内容存入文件
代码：

import asyncio
import aiohttp
import requests
from lxml import etree
url ="https://www.17k.com/list/3379384.html"
resq = requests.get(url)
resq.encoding = "utf-8"
ht = resq.text

ee= etree.HTML(ht)
nr = ee.xpath("/html/body/div[5]/dl/dd/a/@href")
url1 ="https://www.17k.com"
async  def getwz(surl):
   async with aiohttp.ClientSession() as session:
       async with session.get(surl) as resq:
           resq.encoding="utf-8"
           nr1 = await resq.text()
           ee1 =etree.HTML(nr1)
           name = ee1.xpath('//*[@id="readArea"]/div[1]/h1/text()')  #文章题目
           name1 = ''.join(name)  #将列表转化成字符串


           nr2 = ee1.xpath("//*[@id='readArea']/div[1]/div[2]/p/text()")
           nr3= ''.join(nr2)   #文章内容

           with open(name1+".txt", mode="w",encoding="utf-8") as f:
               f.write(nr3)  #写入
           

async def main():
    tasks=[]
    for urll in nr:
        surl = url1 + urll
        tasks.append(asyncio.create_task(getwz(surl)))

    await asyncio.wait(tasks)

if __name__ == '__main__':
    asyncio.run(main())
if __name__ == '__main__':
    asyncio.run(main())