聊斋相关的分词出现次数前20

import jieba
from collections import Counter

def analyze_liaozhai(text_path, top_n=20):
"""
分析聊斋文本的词频

参数:
    text_path: 聊斋文本文件路径
    top_n: 要统计的高频词数量
"""
try:
    # 读取文本文件
    with open(text_path, 'r', encoding='utf-8') as file:
        liaozhai_text = file.read()
    
    # 使用jieba进行分词
    words = jieba.lcut(liaozhai_text)
    
    # 过滤掉标点符号和单字
    filtered_words = [word for word in words if len(word) > 1 and not word.isspace()]
    
    # 统计词频
    word_counts = Counter(filtered_words)
    
    # 获取前N个高频词
    top_words = word_counts.most_common(top_n)
    
    # 打印结果
    print(f"聊斋文本中出现频率最高的{top_n}个词语：")
    for i, (word, count) in enumerate(top_words, 1):
        print(f"{i}. {word}: {count}次")
        
except FileNotFoundError:
    print(f"错误：找不到文件 {text_path}")
except Exception as e:
    print(f"发生错误: {str(e)}")

使用示例

if name == "main":
# 替换为你的聊斋文本实际路径
text_path = "E:\作业spyder\《聊斋志异》.txt" # 可以是相对路径或绝对路径
analyze_liaozhai(text_path, top_n=20)