1.读文件,通过正则匹配
def statisticWord():
line_number = 0
words_dict = {}
with open (r'D:\test\test.txt',encoding='utf-8') as a_file:
for line in a_file:
words = re.findall(r'\d+;|&#\d+;|&\w+;',line)
for word in words:
words_dict[word] = words_dict.get(word,0) + 1 #get the value of word, default is 0
sort_words_dict = OrderedDict(sorted(words_dict.items(),key = lambda x : x[1], reverse = True))
# sort_words_dict = sorted(words_dict, key = operator.itemgetter(1))
with open(r'D:\test\output.txt',encoding = 'utf-8', mode='w') as b_file:
for k,v in sort_words_dict.items():
b_file.write("%-15s:%15s" % (k,v))
b_file.write('\n')
2. 通过命令行参数
def statisticWord2():
if len(sys.argv) == 1 or sys.argv[1] in {"-h",