#coding=utf-8 #import linecache; #data_keys = ('bid', 'uid', 'username', 'v_class', 'content', 'img', 'created_at', 'source', 'rt_num', 'cm_num', 'rt_uid', 'rt_username', 'rt_v_class', 'rt_content', 'rt_img', 'src_rt_num', 'src_cm_num', 'gender', 'rt_bid', 'location', 'rt_mid', 'mid', 'lat', 'lon', 'lbs_type', 'lbs_title', 'poiid', 'links', 'hashtags', 'ats', 'rt_links', 'rt_hashtags', 'rt_ats', 'v_url', 'rt_v_url') #keys = {data_keys[k]:k for k in xrange(0,len(data_keys))} # keys={}; # for k in xrange(0,len(data_keys)): # keys[data_keys[k]]=k; # f=linecache.getlines("t.txt"); # data_lists=[]; # for item in f: # lines = item.split(","); # tmp={"bid":lines[keys['bid']], # "uid":lines[keys['uid']], # "username":lines[keys['username']], # "created_at": lines[keys['created_at']] # }; # data_lists.append(tmp); #print data_lists; #输出有多少个用户 # num=set( item["username"] for item in data_lists); #print len(num); #用户名list # name_lists=[]; # for item in data_lists: # name_lists.append(item['username']); #================================================================ #取出是2012-11的时间有多少 # data_lists=[]; # keys = {data_keys[k]:k for k in xrange(0,len(data_keys))} # f = linecache.getlines("./t.txt"); # for lines in f: # line = lines.split(",")[6].replace('"',''); # if len(line) > 0 : # bol = line.startswith("2012-11"); # if bol == True: # data_lists.append(line); # print data_lists; # #================================================================ # keys = {data_keys[k]:k for k in xrange(0,len(data_keys))} # f = linecache.getlines("./t.txt"); # times=[]; # for lines in f: # line = lines.split(",")[6].replace('"',''); # if len(line) >0 and line.startswith("2012"): # times.append(line.split(" ")[0]); # news_list = list(set(times)); # print len(news_list); # #================================================================