python 按照jieba分词后，再根据字典的词频进行排序输出

dict.txt

迅雷不及掩耳盗铃之势 1
掩耳盗铃 2
铃儿响叮当 3
当仁不让 5
让世界充满爱 3
让世界充满爱 5
迅雷不及 0
迅雷 0
掩耳 0
盗铃 0

实现代码

# -*- ecoding: utf-8 -*-
# @ModuleName: test002
# @Function: 
# @Author: darling
# @Time: 2022-05-05 20:01
import jieba
from loguru import logger

jieba.set_dictionary("./dict.txt")  # 指定dict.txt加载路径，为了方便部署，使用相对路径。
jieba.initialize()  # jieba库初始化。


def read_headers(file_name):
    with open(file_name, 'r', encoding='UTF-8') as file:
        lines = file.readlines()
        for line in lines:
            if line == '\n':
                continue
            # 这里用的是[: ]进行拆分，因为value中也会存在冒号
            ll = line.split(' ')
            key = ll[0].strip()
            val = ll[1].strip().replace('\n', '')
            if val == '0':
                continue
            header[key] = int(val)
    return header


# 拆词
def split_words(title):
    split_dic = {}
    words = []
    try:
        logger.info('输入的标题为：{}', title)
        lcuts = jieba.lcut(title, cut_all=True)
        # 排除单个字的，保留两个字以上的词语
        list_lcuts = [x for x in lcuts if len(x) >= 2]
        # 去重复性词语
        list_lcuts = list(set(list_lcuts))
        logger.info('lcuts可拆分为：{}', list_lcuts)
        for list_lcut in list_lcuts:
            # 获得字典的词频 词频不唯一
            val = header.get(list_lcut)
            # 生成新的字典
            split_dic[list_lcut] = val
        new_dic = sorted(split_dic.items(), key=lambda x: -x[1])
        print(new_dic)
        # words = [x for x in new_dic if x[0]]
        for splits in new_dic:
            words.append(splits[0])
        logger.info('词频级排序后：{}', words)
        # return list_words
    except Exception as e:
        logger.info('拆词异常：{}', e)


def sort1(arr):
    return arr.sort()


if __name__ == "__main__":
    header = {}
    read_headers('./dict.txt')
    split_words('迅雷不及掩耳盗铃儿响叮当仁不让世界充满爱之势,迅雷不及掩耳盗铃之势')

拓展

对字典，列表进行排序，升序/降序的方式