#coding=utf-8
import urllib.request
from bs4 import BeautifulSoup
def IntoPage(p_href):
indata = urllib.request.urlopen(p_href).read() #这里老出错,报错是'ascii' codec can't encode character u'\u2013' in position 3 2: ordinal not in range(128)
return
data = urllib.request.urlopen(url).read()
soup = BeautifulSoup(data, "html.parser")
for sgdiv in soup.find_all('div',class_='des'):
IntoPage(sgdiv.a.get('href'))