# coding=utf-8
 import re
 import requests
 import sys
 reload(sys)
 sys.setdefaultencoding("utf8")
 
 
 class spider():
   def __init__(self):
     print "开始爬取内容。。。"
 
    def changePage(self, url, total_page):
     nowpage = int(re.search('/0-(\d+)/', url, re.S).group(1))
     pagegroup = []
 
     for i in range(nowpage, total_page + 1):
       link = re.sub('/0-(\d+)/', '/0-%s/' % i, url, re.S)
       pagegroup.append(link)
 
     return pagegroup
 
def getsource(self, url):
  html = requests.get(url)
  return html.text
 
def getclasses(self, source):
  classes = re.search('<ul class="zy_course_list">(.*"(.*"', eachclass, re.S).group(1)
  info['people'] = re.search('<p class="color99">(.*"htmlcode">

import requests

html=requests.get("http://gupowang.baijia.baidu.com/article/283878")
html.encoding='utf-8'
print(html.text)




第一行引入requests库，第二行使用requests的get方法获取网页源代码，第三行设置编码格式，第四行文本输出。 

把获取到的网页源代码保存到文本文件中：


import requests
import os

html=requests.get("http://gupowang.baijia.baidu.com/article/283878")
html_file=open("news.txt","w")
html.encoding='utf-8'
print(html.text,file=html_file)