Codewars题解：返回出现频次Top3单词的Python实现

题目要求 #

编写功能函数，输入为一段文本，输出为文本中出现次数排名前三的单词组成的数组。

对应Python实现 #

代码导入re正则模块处理单词匹配规则，通过递归逻辑逐轮筛选当前剩余单词列表里的最高频词，最后清理结果中的空值后返回：

import re


def find_top_word(top, word_list, word_set):
    top_word = ''
    top_count = 0

    for word in word_set:
        counter = 0
        for char in word_list:
            if word == char:
                counter += 1
        if counter > top_count:
            top_word = word
            top_count = counter

    top.append(top_word)

    while top_word in word_list:
        word_list.remove(top_word)

    if len(top) < 3:
        find_top_word(top, word_list, word_set)


def top_3_words(word):
    top = []
    word_list = [str(re.findall(r'\b(\w+.\w+)\b', char.lower()))[2:-2] if "'" in char
                 else str(re.findall(r'\b\w+\b', char.lower()))[2:-2]
                 for char in word.split()]
    word_set = set(word_list)
    find_top_word(top, word_list, word_set)
    for word in top:
        if word == '':
            del top[top.index(word)]
    if top[0] == '':
        del top[0]
    print(top)
    return top

内容的提问来源于stack exchange，提问作者Дима Онуфриенко