Files
dt_audio/srt2txt.ipynb
alsesa b10fd0e112 merge
2024-10-14 17:39:25 +08:00

63 lines
1.6 KiB
Plaintext
Executable File
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"id": "1c256e43",
"metadata": {},
"outputs": [],
"source": [
"a = 1\n",
"b = 2\n",
"c = 3\n",
"state = a\n",
"text = ''\n",
"with open('test.srt', 'r') as f: #打开srt字幕文件并去掉文件开头的\\ufeff\n",
" for line in f.readlines(): #遍历srt字幕文件\n",
" if state == a: #跳过第一行\n",
" state = b\n",
" elif state == b: #跳过第二行\n",
" state = c\n",
" elif state == c: #读取第三行字幕文本\n",
" if len(line.strip()) !=0:\n",
" text += ' ' + line.strip() #将同一时间段的字幕文本拼接\n",
" state = c\n",
" elif len(line.strip()) ==0:\n",
" with open('test1.txt', 'a') as fa: #写入txt文本文件中\n",
" fa.write(text)\n",
" text = '\\n'\n",
" state = a"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fcc101e2",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}