Python 对新浪微博的元素 (Word, Screen Name)的词汇多样性分析

CODE:

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

'''
Created on 2014-7-10
@author: guaguastd
@name: weiboLexicalDiversity.py
'''

if __name__ == '__main__':
    
    # get weibo_api to access sina api
    from sinaWeiboLogin import sinaWeiboLogin
    sinaWeiboApi = sinaWeiboLogin()
    
    # import sinaWeibo
    from sinaWeibo import extractWeiboEntities
    
    # import sinaWeoboStatuses
    from sinaWeiboStatuses import publicTimeline
    
    # import sinaWeiboFrequency
    from sinaWeiboLexicalDiversity import weibo_lexical_diversity, weibo_average_words
    
    # get the new 5 weibo
    weiboNum = 5
    statuses = publicTimeline(sinaWeiboApi, weiboNum)
    status_texts,screen_names,words = extractWeiboEntities(statuses)  

    for token in (words, screen_names):  
        print '\rLexical diversity of %s: ' % token  
        print weibo_lexical_diversity(token)  
  
    for status in (status_texts,):  
        print '\rAverage words of %s: ' % status  
        print weibo_average_words(status)  
            #!/usr/bin/python 
# -*- coding: utf