def srt_to_txt(srt_path, txt_path):
"""
将srt字幕文件转换成纯文本txt文件
去掉时间码、index等信息
"""
txt_file = codecs.open(txt_path, 'w+', encoding='utf-8')
srt_file = codecs.open(srt_path, encoding='utf-8')
for sub in pysrt.stream(srt_file):
txt_file.write(sub.text + '\n')
srt_file.close()
txt_file.close()
def __attrs_post_init__(self):
self.file = codecs.open(str(self.path), encoding=self.encoding)
self.stream = pysrt.stream(self.file)
def test_blank_lines(self):
items = list(
pysrt.stream(['\n'] * 20, error_handling=SubRipFile.ERROR_RAISE))
self.assertEqual(len(items), 0)
def test_blank_lines(self):
items = list(pysrt.stream([u'\n'] * 20, error_handling=SubRipFile.ERROR_RAISE))
self.assertEquals(len(items), 0)