# -*- coding: utf-8 -*-
import jieba

seg_str = "好好學習，天天向上。"

print("/".join(jieba.lcut(seg_str)))    # 精簡模式，返回一個列表類型的結果
print("/".join(jieba.lcut(seg_str, cut_all=True)))      # 全模式，使用 'cut_all=True' 指定 
print("/".join(jieba.lcut_for_search(seg_str)))     # 搜索引擎模式

# -*- coding: utf-8 -*-
import jieba

txt = open("三國演義.txt", "r", encoding='utf-8').read()
words = jieba.lcut(txt)     # 使用精確模式對文本進行分詞
counts = {}     # 通過鍵值對的形式存儲詞語及其出現(xiàn)的次數(shù)

for word in words:
    if len(word) == 1:    # 單個詞語不計算在內
        continue
    else:
        counts[word] = counts.get(word, 0) + 1    # 遍歷所有詞語，每出現(xiàn)一次其對應的值加 1

items = list(counts.items())
items.sort(key=lambda x: x[1], reverse=True)    # 根據(jù)詞語出現(xiàn)的次數(shù)進行從大到小排序

for i in range(3):
    word, count = items[i]
    print("{0:<5}{1:>5}".format(word, count))

# -*- coding: utf-8 -*-

def get_text():
    txt = open("1.txt", "r", encoding='UTF-8').read()
    txt = txt.lower()
    for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':
        txt = txt.replace(ch, " ")      # 將文本中特殊字符替換為空格
    return txt

file_txt = get_text()
words = file_txt.split()    # 對字符串進行分割，獲得單詞列表
counts = {}

for word in words:
    if len(word) == 1:
        continue
    else:
        counts[word] = counts.get(word, 0) + 1 

items = list(counts.items())    
items.sort(key=lambda x: x[1], reverse=True)      

for i in range(5):
    word, count = items[i]
    print("{0:<5}->{1:>5}".format(word, count))