|
|
|
|
|
import re
|
|
|
|
|
|
import pandas as pd
|
|
|
|
|
|
|
|
|
|
|
|
# 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(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(sentences, keyword, top_n=8):
|
|
|
|
|
|
keyword_lower = keyword.lower()
|
|
|
|
|
|
keyword_counts = []
|
|
|
|
|
|
|
|
|
|
|
|
for sentence in sentences:
|
|
|
|
|
|
sentence_lower = sentence.lower()
|
|
|
|
|
|
count = sentence_lower.count(keyword_lower)
|
|
|
|
|
|
if count > 0:
|
|
|
|
|
|
keyword_counts.append((sentence, count))
|
|
|
|
|
|
|
|
|
|
|
|
if not keyword_counts:
|
|
|
|
|
|
return []
|
|
|
|
|
|
|
|
|
|
|
|
# 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Excel文件中
|
|
|
|
|
|
def save(file_path, result_dict):
|
|
|
|
|
|
with pd.ExcelWriter(file_path, engine='openpyxl') as writer:
|
|
|
|
|
|
for keyword, sentences in result_dict.items():
|
|
|
|
|
|
# 如果某个关键词没有找到对应的句子，跳过保存
|
|
|
|
|
|
if sentences:
|
|
|
|
|
|
df = pd.DataFrame(sentences, columns=[f'{keyword}'])
|
|
|
|
|
|
df.to_excel(writer, sheet_name=keyword[:30], index=False)
|
|
|
|
|
|
|
|
|
|
|
|
def main():
|
|
|
|
|
|
input_file = '3.txt'
|
|
|
|
|
|
output_file = 'results.xlsx'
|
|
|
|
|
|
|
|
|
|
|
|
# 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(text)
|
|
|
|
|
|
result_dict = {}
|
|
|
|
|
|
|
|
|
|
|
|
# 对每个关键词查找出现次数前八的句子
|
|
|
|
|
|
for keyword in keywords:
|
|
|
|
|
|
top_sentences = find(sentences, keyword, top_n=8)
|
|
|
|
|
|
result_dict[keyword] = top_sentences
|
|
|
|
|
|
|
|
|
|
|
|
# 将结果保存到Excel文件
|
|
|
|
|
|
save(output_file, result_dict)
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
|
|
main()
|
