Advertisement
DeaD_EyE

srt_parser

Nov 27th, 2016
211
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 0.65 KB | None | 0 0
  1. #!/usr/bin/env python3
  2. # don't use this crazy code
  3.  
  4. import itertools
  5. import argparse
  6. import bs4
  7.  
  8. def parser(file):
  9.     with open(file) as srt_fd:
  10.         srt = srt_fd.read()
  11.     lines = [line for line in srt.splitlines() if line.strip()]
  12.     html = ''.join(subtitle[2] for subtitle in zip(*[iter(lines)]*3))
  13.     subtitle = ''.join(element.text for element in bs4.BeautifulSoup(html, 'lxml').find_all('p'))
  14.     return subtitle
  15.  
  16. if __name__ == '__main__':
  17.     arguments = argparse.ArgumentParser()
  18.     arguments.add_argument('file', help='SRT input file', action='store')
  19.     args = arguments.parse_args()
  20.     text = parser(args.file)
  21.     print(text)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement