使用Notepad++及Python脚本批量将老友记的srt字幕文件批量转换为json格式

Z时代
2024-01-10
分类：综合

python

从网上字幕库下载得到的字幕文件压缩包如下图所示：

然后使用7z解压到当前目录，得到的部分文件列表如下（一共有228个字幕文件）：

打开其中一个文件查看格式如下：

字符编码是 ANSI 的，需要先批量转换为 UTF-8的格式，可参考： https://www.cnblogs.com/abc789/p/12148402.html

然后再使用如下Python脚本批量转换为json格式。

 1 # -*- coding: UTF-8 -*-
 2 #coding=utf-8
 3 from os.path import abspath, dirname
 4 import re
 5 import sys
 6 import shutil
 7 import os
 8 def proSrtFile(path,srtFile,pathDest):
 9     result = list()
10     f = open(path + \'\\\' + srtFile,\'r\')
11     lines = f.readlines()
12     new_line=\'\'
13     is_eng = 0 
14     is_chn = 0
15     chn = \'\'
16     eng = \'\' 
17     result.append(\'[\')
18     for line in lines:
19         line = line.strip() 
20         line = line.lstrip() 
21         line = line.replace(\'...\',\' \')
22         line = line.replace(\'\"\',\'\\'\')
23         line = line.replace(\'.\',\'. \')
24         line = line.replace(\',\',\', \')
25         line = line.replace(\'?\',\'? \')
26         line = line.replace(\':\',\': \')
27         line = line.replace(\';\',\'; \')
28         line = line.replace(\'!\',\'! \')
29         line = line.replace(\'. . \',\'. \')
30         if \'-->\' in line:
31             continue
32         line = line.replace(\'-\',\'\')
33         if line == \'\':
34             # 如果中文或英文之一为空则不输出
35             if eng != \'\' and chn != \'\': 
36                 result.append(\'{"eng":"\' + eng + \'","chn":"\' + chn + \'"},\')
37             is_eng = 0 
38             is_chn = 0 
39             eng = \'\'
40             chn = \'\' 
41             continue    
42         
43         # 如果这行是数字则写入上一行并重新开始：
44         if line.isdigit():
45             is_eng = 1 
46             is_chn = 0
47             eng = \'\' 
48             chn = \'\' 
49             continue
50         if is_eng == 1:
51             eng = line 
52             is_eng = 0 
53             is_chn = 1
54             continue
55         if is_chn == 1:
56             chn = line 
57             is_eng = 0 
58             is_chn = 0
59             continue
60  
61     f.close()
62     result.append(\']\')
63     open(pathDest + \'\\\' +  srtFile[0:14] +\'.json\',\'w\').write(\'%s\' % \'\n\'.join(result))
64     
65 pathSrc="D:\\data\\corona_projects\\LearnEnglishSentences_json\\data\\friends\\001\\" 
66 pathDest="D:\\data\\corona_projects\\LearnEnglishSentences_json\\eng"
67 indexList= list()
68 for root, dirs, files in os.walk(pathSrc):
69     for fn in files: 
70         if fn[-4:] == \'.srt\':
71             
72             print fn
73             indexList.append(\'{"title":"\'+fn[0:14]+\'","file":"\' + fn[0:14] +\'.json"},\')
74             proSrtFile(root,fn,pathDest)
75 
76 open(pathDest + \'\\\' +  \'x_temp_index.xml\',\'w\').write(\'%s\' % \'\n\'.join(indexList))
77  
78 print \'--------------------------------------------\'
79 print pathDest 
80 print pathDest + \'\\\' +  \'x_temp_index.xml\'
81