4.8

学号：2017*****7053

姓名：商一凡

代码

 

第一段代码

from string import punctuation

def process_file(dst): # 读文件到缓冲区
try: # 打开文件
files = open(dst,"r")
except IOError as s:
print (s)
return None
try: # 读文件到缓冲区
bvffer = files.read()
except:
print ("Read File Error!")
return None
files.close()
return bvffer

第二段代码

def process_buffer(bvffer):
if bvffer:
word_freq = {}
bvffer = bvffer.lower()
# 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
ls = "''?!,.{}+=-:"
for word in ls:
bvffer = bvffer.replace(i, " ")
words = bvffer.strip().split()
for word in words:
word_freq[word] = word_freq.get(word, 0) + 1
return word_freq

第三段代码

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)

第四段代码

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)

运行截图

总结：学到了如何读写文件以及统计文件单词的个数

 

转载于:https://www.cnblogs.com/N1NGQI/p/10672393.html