Felix's Blog

1
00:01:06,107 --> 00:01:07,483
This is a test
这是一个测试
 
2
00:01:12,906 --> 00:01:16,450
测试!
快测试呀
 
3
00:01:18,703 --> 00:01:19,953
测试好了没有?
我问你好了没有?
Is the test OK?
What's the result?

1
00:01:06,107 --> 00:01:07,483
这是一个测试
This is a test
 
2
00:01:12,906 --> 00:01:16,450
测试! 快测试呀
 
3
00:01:18,703 --> 00:01:19,953
测试好了没有? 我问你好了没有?
Is the test OK? What's the result?

#coding:utf-8
import re
import sys
if len(sys.argv)<2: exit();
filename = sys.argv[1]
 
f=file(filename,'r')
a=f.read()
 
try:
    a=a.decode('utf8')
except:
    pass
 
aa=a.split('\n\n')
f.close()
k=[]
 
for a in aa:
    if len(a.split('\n'))<2:
        for m in a.split('\n'): k.append(m.replace('- ','-'))
        continue
    time = "\n".join(a.split('\n')[:2])
    chi = [x for x in a.split('\n')[2:] if x != x.encode('unicode-escape')]
    eng = [x for x in a.split('\n')[2:] if x == x.encode('unicode-escape')]
 
    k.append(time)
    if len(chi)>0: k.append(" ".join(chi).replace('- ','-'))
    if len(eng)>0: k.append(" ".join(eng).replace('- ','-'))
    k.append('')
 
f=open(filename+"_fixed.srt","w")
for m in k: f.write(m.encode(sys.getfilesystemencoding())+'\n')
f.close()