''''' Created on Dec 21, 2012 處理文件中的每個詞 @author: liury_lab ''' import codecs the_file = codecs.open('d:/text.txt', 'rU', 'UTF-8') for line in the_file:   for word in line.split():     print(word, end = "|") the_file.close() # 若詞的定義有變，可使用正則表達式 # 如詞被定義為數(shù)字字母，連字符或單引號構成的序列 import re the_file = codecs.open('d:/text.txt', 'rU', 'UTF-8') print() print('************************************************************************') re_word = re.compile('[/w/'-]+') for line in the_file:   for word in re_word.finditer(line):     print(word.group(0), end = "|") the_file.close() # 封裝成迭代器 def words_of_file(file_path, line_to_words = str.split):   the_file = codecs.open('d:/text.txt', 'rU', 'UTF-8')   for line in the_file:     for word in line_to_words(line):       yield word   the_file.close() print() print('************************************************************************') for word in words_of_file('d:/text.txt'):   print(word, end = '|') def words_by_re(file_path, repattern = '[/w/'-]+'):   the_file = codecs.open('d:/text.txt', 'rU', 'UTF-8')   re_word = re.compile('[/w/'-]+')    def line_to_words(line):     for mo in re_word.finditer(line):       yield mo.group(0) # 原書為return，發(fā)現(xiàn)結果不對，改為yield   return words_of_file(file_path, line_to_words) print() print('************************************************************************') for word in words_by_re('d:/text.txt'):   print(word, end = '|')