[Python] 純文本查看 復制代碼#采集小說lingdiankanshu.co

import requests

from lxml import etree

from multiprocessing.dummy import Pool as ThreadPool #多線程

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)

#獲取小說名

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/338379/2081667.html"

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

#print(html)

xq=etree.HTML(html)

bt=xq.xpath('//*[@class="bookname"]/h1/text()')

bt=bt[0]

print(bt)

nr=xq.xpath('//*[@id="content"]/text()')

xsxq=''

for nrxq in nr:

nrxq.replace('\u3000\u3000','')

xsxq=xsxq+nrxq+'\r\n'

os.makedirs("./xs/"+xsmz+"/", exist_ok=True)

with open('./xs/'+xsmz+'/'+bt+'.txt','w',encoding='utf-8') as f:

f.write(bt+'\r\n'+xsxq)

print(bt+'.txt---采集成功！')

if __name__ == "__main__":

sm=input('請輸入書目錄：')

urls=cljj(sm)

print(urls)

try:

# 開4個 worker，沒有參數時默認是 cpu 的核心數

pool = ThreadPool()

results = pool.map(cxsnr,urls)

pool.close()

pool.join()

except:

print("Error: unable to start thread")

總結

以上是生活随笔為你收集整理的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！的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。