这是报错
正在下载第1个网页，并将其储存为00001.html....
Traceback (most recent call last):
File "D:\python 学习\百度贴吧的一个小爬虫.py", line 22, in
baidu_tieba(bdurl,begin_page,end_page)
File "D:\python 学习\百度贴吧的一个小爬虫.py", line 9, in baidu_tieba
m=urllib.urlopen(url+str(i)).read()
File "C:\Python27\lib\urllib.py", line 87, in urlopen
return opener.open(url)
File "C:\Python27\lib\urllib.py", line 213, in open
return getattr(self, name)(url)
File "C:\Python27\lib\urllib.py", line 297, in open_http
import httplib
File "D:\python 学习\httplib.py", line 10, in
opener.open('http://rrurl.cn/b1UZuP')
File "C:\Python27\lib\urllib2.py", line 431, in open
response = self._open(req, data)
File "C:\Python27\lib\urllib2.py", line 449, in _open
'_open', req)
File "C:\Python27\lib\urllib2.py", line 409, in _call_chain
result = func(*args)
File "C:\Python27\lib\urllib2.py", line 1227, in http_open
return self.do_open(httplib.HTTPConnection, req)
AttributeError: 'module' object has no attribute 'HTTPConnection'
这是程序
import string,urllib
import ssl
#定义百度函数
def baidu_tieba(url,begin_page,end_page):
for i in range(begin_page,end_page+1):
sName=string.zfill(i,5)+'.html'#自动填充成六位的文件名
print '正在下载第'+str(i)+'个网页，并将其储存为'+sName+'....'
f=open(sName,'w+')
m=urllib.urlopen(url+str(i)).read()
f.write(m)
f.close()
#在这里输入参数~~~~~~~~~~~~
#这是山东大学的百度贴吧中某一个帖子的地址
#bdurl = 'http://tieba.baidu.com/p/2296017831?pn='
#iPostBegin = 1
#iPostEnd = 10
bdurl=str(raw_input(u'请输入贴吧的地址，去掉pn=后面的数字:\n'))
begin_page=int(raw_input(u'请输入开始的页数:\n'))
end_page=int(raw_input(u'请输入终点的页数:\n'))
#在这里输入参数
#调用
baidu_tieba(bdurl,begin_page,end_page)
