You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.
import jieba
#阅读文本文件
txt = open ( r ' C: \ Users \ 86158 \ 爬虫作业 \ ai吧.txt ' , ' r ' , encoding = ' UTF-8 ' ) . read ( )
rp_str = ' ： ， ； ？ ‘ ’ （ ） ！ \n \ufeff '
for i in rp_str :
txt = txt . replace ( i , ' ' )
txt = ' ' . join ( txt . split ( ) )
jieba . load_userdict ( r ' C: \ Users \ 86158 \ 爬虫作业 \ userdict.txt ' )
words = jieba . lcut ( txt )
stopwords = open ( r ' C: \ Users \ 86158 \ 爬虫作业 \ stopwords.txt ' , ' r ' , encoding = ' UTF-8 ' ) . read ( )
stopwords_list = list ( stopwords )
#将无意义的高频词写入remov_words筛掉
remove_words = [ ' 哈哈 ' , ' 可以 ' , ' 紫薯 ' , ' 整齐 ' , ' 开始 ' , ' 以为 ' , ' 这人 ' , ' 我们 ' , ' 好像 ' ]
words_counts = { }
for i in words :
if len ( i ) == 1 :
continue
if i in remove_words :
continue
if i not in stopwords_list :
words_counts [ i ] = words_counts . get ( i , 0 ) + 1
words_list = list ( words_counts . items ( ) )
words_list . sort ( key = lambda x : x [ 1 ] , reverse = True )
ranking8_list = words_list [ : 8 ]
ranking8_dict = dict ( ranking8_list )
print ( ranking8_dict )
#将得到的关键词保存为文本文件
f = open ( r ' C: \ Users \ 86158 \ 爬虫作业 \ ciyuntu.txt ' , ' w ' , encoding = ' UTF-8 ' )
for i in range ( len ( words_list ) ) :
k , v = words_list [ i ]
f . write ( ' {:<8} {:>2} \n ' . format ( k , v ) )
f . close ( )
