Crawl CSDN Blog's Page Views

csdn.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import re
import urllib2
import datetime

html = urllib2.urlopen('http://blog.csdn.net/zjerryj').read()
mo = re.search(r'访问：<span>(\d+)次</span>', html)

with open('/home/jizhang/csdn.log', 'a') as f:
    f.write('%s,%s\n' % (datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'), mo.group(1)))