2017*********7015，王金羽
def process_file(dst): # 读文件到缓冲区
try: # 打开文件
x = open(dst,"r")
except IOError as s:
print (s)
return None
try: # 读文件到缓冲区
bvffer = x.read()
except:
print ('Read File Error!')
return None
x.close()
return bvffer
def process_buffer(bvffer):
if bvffer:
word_freq = {}
# 下面添加处理缓冲区 bvffer代码，统计每个单词的频率，存放在字典word_freq
for ch in'"!?;,."':
bvffer = bvffer.lower().replace(ch,"")
word = bvffer.strip().split()
for word in word:
word_freq[word] = word_freq.get(word,0)+1
return word_freq
def output_result(word_freq):
if word_freq:
sorted_word_freq = sorted(word_freq.items(), key=lambda v: v[1], reverse=True)
for item in sorted_word_freq[:10]: # 输出 Top 10 的单词
print(item)
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('dst')
args = parser.parse_args()
dst = args.dst
bvffer = process_file(dst)
word_freq = process_buffer(bvffer)
output_result(word_freq)
TOP10的单词
最多最长
学会了查询方法
