Created
June 12, 2015 15:03
-
-
Save leyafo/5cad8e3689c96ef61e61 to your computer and use it in GitHub Desktop.
srt subtitles parse
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os, sys; | |
import distutils.file_util as file_util | |
def iterate_path(source): | |
#list all files | |
files = os.listdir(source) | |
for f in files: | |
if(os.path.isfile(os.path.join(source,f))): | |
#check hide file | |
if(f[0] == "." or f == 'tmp.py'): | |
continue | |
yield f | |
def gbk2utf(s): | |
return s.decode('gb18030').encode('utf-8') | |
def parse(fname): | |
f = open(fname, "r") | |
i = fname.find('.')+1 | |
new_fname = fname[i:fname.find('.', i)] | |
new_f = open(new_fname+".txt", "w+") | |
need_write_file = False | |
need_collect = False | |
results = "" | |
for line in f.readlines(): | |
line = gbk2utf(line.strip()) | |
if need_write_file: | |
new_f.write(results) | |
new_f.write('\n') | |
need_write_file=False | |
results = "" | |
if line.find('-->') != -1: | |
need_collect = True | |
continue | |
if need_collect: | |
if line != "": | |
results += line.replace('\n', '\t') | |
else: | |
need_write_file = True | |
need_collect = False | |
new_f.close | |
if __name__ == "__main__": | |
source = sys.argv[1] | |
for fname in iterate_path(source): | |
parse(fname) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment