Python3——简单获取网页文字的爬虫

# -*- coding: utf-8 -*-

import urllib.request
import re

url='http://s.weibo.com/weibo/%25E9%25BE%2599%25E9%25BA%2592&Refer=STopic_box'

urlfile=urllib.request.urlopen(url).read()
urlfile=urlfile.decode('UTF-8')

r1=re.compile('[\u4e00-\u9fa5]{2,4}') #匹配文字

wordList=re.findall(r1,urlfile)
print (wordList)