Python爬虫：学习啦网站文章内容爬取

免责声明：代码仅作技术交流使用，如有侵权请联系本人删除！

起因就是想白嫖形政作业时这个网站告诉我复制要扫码或者收费
我：？？？

不好意思
流氓会武术
谁也挡不住

import requests
from requests.exceptions import HTTPError
import re

def GetHTML(url,path):       
    try:
        res=requests.get(url)
        res.raise_for_status()
        coding=res.encoding
        with open(path,"w+",encoding=coding) as MyFile:
            MyFile.write(res.text)
        
    except HTTPError:
            print("HTTP Error!")
        
    except ConnectionError:
        print("Failed to connect!")
def DataWash(path):
    mid=[]
    final=[]
    with open(path,"r",encoding="gbk") as ReadFile:           
            MyLines=ReadFile.readlines()                      
            for ML in MyLines:  
                            
                if re.search("img",ML)==None and re.search("</p>",ML)!=None:
                    mid.append(ML)           
            for i in mid:                
                i=re.sub("<.+?>"," ",i)
                i=re.sub("&.+?;"," ",i)               
                final.append(i)
    return final
def SaveFile(final,path):
    with open(path,"w+",encoding="gbk") as FinalFile:
            for i in final:               
                if len(i)!=0:
                    FinalFile.write(i)
                    FinalFile.write("\n")

if __name__=='__main__':
    url=input('输入学习啦url')   
    path=input('输入存放路径')
    GetHTML(url,path)
    final=DataWash(path)
    SaveFile(final,path)
    print('Done')

效果如下