def getHTMLText(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except:
        return" "

    
>>> def getStockList(lst,stockURL):
    html=getHTMLText(stockURL)
    soup=BeautifulSoup(html,'html.parser')
    StockList=soup.find('div',attrs={'class':'title'})
    a=StockList.find_all('a')
    for i in a:
        try:
            href=i.attrs['href']
            lst.append(href)[0]
        except:
            continue

        
>>> def getStockInfo(lst,fpath):
    for stock in lst:

        html=getHTMLText(stock)
        try:
            if stock=="":
                continue
            infoDict={}
            soup=BeautifulSoup(stock,'html.parser')
            stockInfo=soup.find('div' ,attrs={'class’:’house-title'})
            name=stockInfo.find_all('div',attrs={'class’:’wrapper'})[0]
            infoDict.update({'房源名稱':name.text.split()[0]})
            with open(fpath,'a',encoding='utf-8')as f:
                f.write(str(infoDict)+'\n')
        except:
            traceback.print_exc()
            continue

        
>>> import requests
>>> from bs4 import BeautifulSoup
>>> import re
>>> import traceback
>>> def main():
    stock_list_url='https://sz.lianjia.com/chengjiao/pg100/'
    output_file='C://Users/Thinkpad/Desktop'
    slist=[]
    getStockList(slist,stock_list_url)
    getStockInfo(slist,output_file)

    
>>> main()