python自动生成采集规则_【仅供学习参考】Python多线程池采集小说，超简单！

[Python] 纯文本查看 复制代码#采集小说lingdiankanshu.co

import requests

from lxml import etree

from multiprocessing.dummy import Pool as ThreadPool #多线程

import os

global xsmz

xsmz=''

def cljj(sm):

global xsmz

#url="https://www.lingdiankanshu.co/338379/"

url="https://www.lingdiankanshu.co/{}/".format(sm)

html=requests.get(url,timeout=20).text

#print(html)

ljnr=etree.HTML(html)

#获取小说名

xsm=ljnr.xpath('//*[@id="info"]/h1/text()')

xsmz=xsm[0]

ljs=[]

ljj=ljnr.xpath('//*[@id="list"]/dl/dd/a/@href')

for lj in ljj:

lj=url+lj

ljs.append(lj)

return(ljs)

def cxsnr(url):

global xsmz

#url="https://www.lingdiankanshu.co/338379/20