第三次课后作业-CSDN博客

学号：2017035102048
姓名：张宇，
我的码云贪吃蛇项目仓库：https://gitee.com/zy990104/second_homework

# filename： word_freq.py

from string import punctuation
def process_file(dst): # 读文件到缓冲区
try: # 打开文件
fi = open(dst) ###
except IOError as s:
print (s)
return None
try: # 读文件到缓冲区
bvffer = fi.read() ###
except:
print ("Read File Error!")
return None

fi.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 i in bvffer.strip().split():
word = i.strip(punctuation+' ')
if word in word_freq.keys():
word_freq[word]+=1
else:
word_freq[word]=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