from bs4 import BeautifulSoup
import requests
n=1
url='http://www.5cm.cn/bank/'+str(n)
header={'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.XXXX.XXX Safari/537.36'}
for i in range (1,10000):
html=requests.get(url,headers=header).text
#print (html)
soup=BeautifulSoup(html,'lxml') #用BeautifulSoup来解析获取的子页面html代码
for k in soup.find_all ('tr')[1:]:
print (k)
print ('--')
list1=[]
for j in soup.select('tr td'):
list1.append(j.get_text())
print (list1)
?
cs
