import urllib.request
import re
class NeihanSpider:
def __init__(self):
self.baseurl = "https://www.neihan8.com/njjzw/"
self.headers = {"User-Agent":"Mozilla/5.0"}
self.page = 1
# 下载页面
def loadPage(self,url):
req = urllib.request.Request(url,headers=self.headers)
res = urllib.request.urlopen(req)
html = res.read().decode("utf-8")
self.parsePage(html)
# 解析页面
def parsePage(self,html):
p = re.comp
