#-*- coding=utf-8 -*-
import urllib2
import codecs
import re
csdn_url = "http://blog.csdn.net/walegahaha"
blog_url = ["http://blog.csdn.net/walegahaha/article/details/51945421",
"http://blog.csdn.net/walegahaha/article/details/51867904",
"http://blog.csdn.net/walegahaha/article/details/51603040",
"http://blog.csdn.net/walegahaha/article/details/50938260",
"http://blog.csdn.net/walegahaha/article/details/50884627",
"http://blog.csdn.net/walegahaha/article/details/50877906",
"http://blog.csdn.net/walegahaha/article/details/50868049",
"http://blog.csdn.net/walegahaha/article/details/50533424",
"http://blog.csdn.net/walegahaha/article/details/50504522",
"http://blog.csdn.net/walegahaha/article/details/50489053",
"http://blog.csdn.net/walegahaha/article/details/50471417",
"http://blog.csdn.net/walegahaha/article/details/50464531",
"http://blog.csdn.net/walegahaha/article/details/50452959",
"http://blog.csdn.net/walegahaha/article/details/50435986",
]
class CSDN(object):
def __init__(self):
self.csdn_url = csdn_url
self.blog_url = blog_url
self.headers = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6',}
def openCsdn(self):
req = urllib2.Request(self.csdn_url, headers = self.headers)
response = urllib2.urlopen(req)
thePage = response.read()
response.close()
pattern = "访问：<span>(\d+)次</span>"
number = ''.join(re.findall(pattern, thePage))
print number
def openBlog(self):
for i in range(len(self.blog_url)):
req = urllib2.Request(self.blog_url[i], headers = self.headers)
response = urllib2.urlopen(req)
response.close()
for i in range(500):
print i
csdn = CSDN()
csdn.openCsdn()
csdn.openBlog()
csdn.openCsdn()
