将 srt 字幕的台词提取到 txt 中

srt2txt.py

import re

# 注意默认编码是 UTF-8
file = open("input.srt")
lines = file.readlines()
file.close()

text = ""
for line in lines:
    if re.search('^[0-9]+$', line) is None and \
            re.search('^[0-9]{2}:[0-9]{2}:[0-9]{2}', line) is None and \
            re.search('^$', line) is None:
        text += '\n' + line.rstrip('\n')
    text = text.lstrip()
text_file = open("output.txt", 'w')
text_file.write(text)
text_file.close()