|
发表于 2021-7-16 10:09:15
|
显示全部楼层
- import re
- RE_WORD = '\w+'
- def DealFile(filename):
- # 读取文件信息
- with open(filename) as f:
- data = f.readlines()
-
- # 单词出现次数统计字典{'word':次数}
- word_dict = {}
- # 处理每一行字符串
- for line in data:
- # 正则表达式获取一行中所有单词
- words = re.findall(RE_WORD, line)
- # 将单词加入到统计字典中
- for w in words:
- # 除空格
- w = w.strip()
- # 出现次数+1
- word_dict[w] = word_dict.get(w,0) + 1
-
- # 按单词次数排序, [(word, count),...]
- word_count_list = sorted(word_dict.items(), key=lambda x: x[1], reverse=True)
- # 打印次数最多的单词
- maxVal = word_count_list[0][1]
- for w, count in word_count_list:
- if count == maxVal:
- print(w)
- else:
- break
-
- DealFile('test.txt')
复制代码 |
|