数据是从chrome中的History分析出来的,它用的是sqlite数据库,python有接口
import sqlite3 import thread import time import datetime import re def getHistoryDB(): path=‘C:\Users\Administrator\AppData\Local\Google\Chrome\User Data\Default\History‘ db=sqlite3.connect(path)#将path换自己电脑History的路径 cu=db.cursor() cu.execute("select url,title,(substr(last_visit_time,1,11)-11644473600) from urls") result=cu.fetchall() cu.close() db.close() ‘‘‘ print ‘length:‘+str(len(result)) # print getTime(result[len(result)-1][2]) #print result[len(result)-1][2] for x in range(10): print ‘---------------‘ print getWebsite(result[x][0]) print result[x][1] print getTime(result[x][2]) #print getTime(result[x][5]) ‘‘‘ return result def getWebsite(result): AllWebsite={} for x in result: #处理url url=getUrl(x[0]) #print url website=url.split(‘.‘) #print website if len(website)<=1: key=‘others‘ else: key=url #如果为空 if key in AllWebsite: AllWebsite[key]+=1 else: AllWebsite[key]=1 return AllWebsite def displayWebsite(): result=getHistoryDB() AllWebsite=getWebsite(result) for x in AllWebsite: print x,AllWebsite[x] #从url中提起到关键信息,如http://www.baidu.com/xxxxxxx,得到www.baidu.com def getUrl(urls): reg=re.compile(‘//(.*?)/‘) url=reg.findall(urls) #print url #print len(url) if len(url)>0: return url[0] else: return ‘nothing‘ #获得访问时间的,没有用到 def getTime(vtime): #print vtime #vtime=format(float(vtime)/10000000,‘.3f‘) #print vtime return time.strftime(‘%Y-%m-%d %H:%M:%S‘,time.localtime(float(vtime))) if __name__==‘__main__‘: displayWebsite() #getHistoryDB()
去看看你最近常浏览的网站吧,是否有什么有趣的发现