1 def process_file(path):  # 读文件到缓冲区
 2     try:   # 打开文件
 3         f = open(path, 'r')   # path为文件路径
 4     except IOError as s:
 5         print(s)
 6         return None
 7     try:  # 读文件到缓冲区
 8         bvffer = f.read()
 9     except:
10         print('Read File Error!')
11         return None
12     f.close()
13     return bvffer

def process_buffer(bvffer):  # 处理缓冲区，返回存放每个单词频率的字典word_freqif bvffer:# 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_freqword_freq = {}# 将文本内容都改为小写且去除文本中的中英文标点符号for ch in '“‘!;:,.?”':bvffer = bvffer.lower().replace(ch, " ")# strip()删除空白符（包括'/n', '/r','/t'）；split()以空格分割字符串words = bvffer.strip().split()for word in words:word_freq[word] = word_freq.get(word, 0) + 1return 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("单词:%s 频数:%d " % (item[0], item[1]))

if __name__ == "__main__":path = "Gone_with_the_wind.txt"  # 《飘》文件的路径bvffer = process_file(path)word_freq = process_buffer(bvffer)output_result(word_freq)

def main():  # main函数封装词频运行path = "Gone_with_the_wind.txt"bvffer = process_file(path)word_freq = process_buffer(bvffer)output_result(word_freq)if __name__ == "__main__":import cProfileimport pstatscProfile.run("main()", filename="word_freq.out")# 创建Stats对象p = pstats.Stats('word_freq.out')# 输出调用此处排前十的函数# sort_stats(): 排序# print_stats(): 打印分析结果，指定打印前几行p.sort_stats('calls').print_stats(10)# 输出按照运行时间排名前十的函数# strip_dirs(): 去掉无关的路径信息p.strip_dirs().sort_stats("cumulative", "name").print_stats(10)# 根据上面的运行结果发现函数process_buffer()最耗时间# 查看process_buffer()函数中调用了哪些函数p.print_callees("process_buffer")

for ch in '“‘!;:,.?”':bvffer = bvffer.lower().replace(ch, " ")

for word in words:word_freq[word] = word_freq.get(word, 0) + 1

bvffer = bvffer.lower()# 将文本内容都改为小写且去除文本中的中英文标点符号for ch in '“‘!;:,.?”':bvffer = bvffer.replace(ch, " ")# strip()删除空白符（包括'/n', '/r','/t'）；split()以空格分割字符串