import re
import pandas as pd
from collections import Counter

# 读取文本
def read_file(file_path):
    with open(file_path, 'r', encoding='utf-8') as file:
        return file.read()


# 将文本拆分为句子
def split_into_sentences(text):
    # 使用正则表达式将文本分割
    sentences = re.split(r'[.!?。！？]', text)
    return [sentence.strip() for sentence in sentences if sentence.strip()]

# 查找包含关键词的句子并统计关键词出现次数
def find_top_sentences_by_keyword(sentences, keyword, top_n=8):
    keyword_counts = []
    for sentence in sentences:
        count = sentence.lower().count(keyword.lower())
        if count > 0:
            keyword_counts.append((sentence, count))

    # 根据关键词出现次数排序，并取前n个
    keyword_counts.sort(key=lambda x: x[1], reverse=True)
    return [sentence for sentence, _ in keyword_counts[:top_n]]


# 将结果保存到TXT文件中
def save_to_file(file_path, keyword, sentences):
    with open(file_path, 'a', encoding='utf-8') as file:
        file.write(f"关键词: {keyword}\n")
        for i, sentence in enumerate(sentences, 1):
            file.write(f"{i}. {sentence}\n")
        file.write("\n")  # 分隔不同关键词的结果


# 主函数
def main():
    # 输入TXT文件路径
    input_file = '3.txt'
    output_file = 'output.txt'
    # 要查找的关键词列表
    keywords = [
    'AI', '人工智能', '机器学习', '深度学习', '神经网络', '自动化', '算法', '数据科学',
    '自然语言处理', '计算机视觉',  '人工智能技术', 'AI技术', 'AI应用', 'AI模型',
    '大数据', '预测分析', '机器视觉', '自动驾驶',
     '智能推荐', '计算机科学', '人工智能应用',
    '数据分析','智能化', '情感计算','ai','字幕','推荐','gpt','机器','直播','机翻','实时','技术'
]

    # 读取文本并拆分为句子
    text = read_file(input_file)
    sentences = split_into_sentences(text)

    # 对每个关键词查找出现次数前八的句子
    for keyword in keywords:
        top_sentences = find_top_sentences_by_keyword(sentences, keyword, top_n=8)
        save_to_file(output_file, keyword, top_sentences)
if __name__ == "__main__":
    main()