Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- #!/usr/bin/env python3
- # don't use this crazy code
- import itertools
- import argparse
- import bs4
- def parser(file):
- with open(file) as srt_fd:
- srt = srt_fd.read()
- lines = [line for line in srt.splitlines() if line.strip()]
- html = ''.join(subtitle[2] for subtitle in zip(*[iter(lines)]*3))
- subtitle = ''.join(element.text for element in bs4.BeautifulSoup(html, 'lxml').find_all('p'))
- return subtitle
- if __name__ == '__main__':
- arguments = argparse.ArgumentParser()
- arguments.add_argument('file', help='SRT input file', action='store')
- args = arguments.parse_args()
- text = parser(args.file)
- print(text)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement