python爬虫-爬取四级词汇

仅供参考！！！

def requ(n):
   i=str(n+1)
   if n!=0:
       url='https://cet4.koolearn.com/20131106/783888_'+i+'.html'
   else:
       url='https://cet4.koolearn.com/20131106/783888'+'.html'
   headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                        'Chrome/100.0.4896.127 Safari/537.36'}
   reponse = r.get(url=url, headers=headers)
   time.sleep(0.001)
   reponse.encoding = "utf-8"
   cihui = reponse.text
   ex='

\\u3000(.*?)

'
   ci=re.findall(ex,cihui,re.S)
   if i=='15':
       ci=ci[:-1]
   if i=='1':
       ci=ci[1:]
   with open('./text2.txt','a+',encoding='utf-8') as fp:
       for i in range(len(ci)):
           fp.write(ci[i]+'\n')
           print("\r{}\tDownload Progress{:-4.1f}%".format('▮'* (int(i/10)), ((i/(len(ci)-1))*100)), end="")
           time.sleep(0.0001)
       fp.close()
       print("\t\t第{}个任务完成！！！".format(n+1))

print("任务开始".center(50//2,"-"))
for i in range(15):
   requ(i)
print("任务结束".center(50//2,"-"))