def _get_subtitles_from_single_file(self, fn):
sta = self.fix_path(fn)
# The nested try is from the pysubs examples,
# https://github.com/tigr42/pysubs/blob/
# master/examples/chapter_gen.py
try:
return pysubs.load(sta)
except pysubs.exceptions.EncodingDetectionError:
try:
return pysubs.load(sta, self.default_sub_encoding)
except UnicodeDecodeError:
with open(sta) as fp:
subs = pysubs.SSAFile()
subs.from_str(unicode(fp.read(), encoding=self.default_sub_encoding, errors="replace"))
return subs
def _get_subtitles_from_single_file(self, fn):
sta = self.fix_path(fn)
# The nested try is from the pysubs examples,
# https://github.com/tigr42/pysubs/blob/
# master/examples/chapter_gen.py
try:
return pysubs.load(sta)
except pysubs.exceptions.EncodingDetectionError:
try:
return pysubs.load(sta, self.default_sub_encoding)
except UnicodeDecodeError:
with open(sta) as fp:
subs = pysubs.SSAFile()
subs.from_str(
unicode(fp.read(),
encoding=self.default_sub_encoding,
errors="replace"))
return subs
import atexit
atexit.register(exit_handler)
####################################################
#
# 从字幕文件里取一行字幕. 待会我们翻译它.
#
######################################################
subs = pysubs.load(file_full_path, encoding='utf-8')
# 打开字幕文件
e_txt = subs[4].text.replace('\\N', ' ')
# 获取一行字幕. 并且把换行去掉, 因为英文字幕有时会分成几行.
# 这个换行符也拿去翻译的话后面的处理会很麻烦. 所以直接删掉.
# 这里的数字4可任意替换
print (e_txt)
print()
# 把原文输出来.
################################
里的全角符号换成半角
此程序需要和 Translate_Whole_SubtitleFile.py 配合使用.
因为 Translate_Whole_SubtitleFile.py 在翻译完字幕后
会保存到新文件里, 而且新文件的文件名会多一个(done)
'''
# encoding=utf-8
import glob
import pysubs
filename_list = glob.glob("(done)*.srt")
for filename in filename_list:
subs = pysubs.load(filename, encoding='utf-8')
for line in subs:
line.text = line.text.replace('，', ', ')
line.text = line.text.replace('。', '. ')
line.text = line.text.replace('！', '! ')
line.text = line.text.replace('’', "'")
line.text = line.text.replace('：', ': ')
line.text = line.text.replace('？', '? ')
subs.save(filename)
print("done")
input()
return p.sub(r'\1 \2', string)
#== (start) 2. 处理逗号 句号 数字问题(字幕文件) ==
ugly = pysubs.load(need_split_path, encoding="utf-8")
# 打开字幕文件
# 循环每行字幕
for line in ugly:
temp = line.text.split('\\N')
# 有些英文字幕是两行的, 用了杠N隔开, 我们按照换行符号分割成列表.
# temp 现在是个列表
# 循环这个列表, index是索引, one是内容
for index,one in enumerate(temp):
temp[index] = Handle_Number(one)
temp[index] = Handle_Period(temp[index])
##########################
#
# 正式开始处理字幕文件
#
##########################
try:
subs = pysubs.load(filepath, encoding='utf-8')
except:
print('字幕文件打开失败 程序退出')
for line in subs:
try:
whole_Sentence = line.text
l = whole_Sentence.split(r'\N')
l[0] = l[0].replace(',', ' ')
l[0] = l[0].replace('.', ' ')
l[0] = l[0].replace('，', ' ')
l[0] = l[0].replace('。', ' ')
except:
pass
try:
print (sys.argv[1]) # 输出拖入的文件的路径
file_path = sys.argv[1]
except:
print('请拖入需要删除第一行字幕的字幕文件. 不要直接运行. 按[回车键]退出程序')
input()
exit()
# 如果不是拖入字幕文件来运行 就提示需要拖入文件
subs = pysubs.load(file_path, encoding="utf-8")
for line in subs:
text = line.text
try:
text = text.split(r'\N')
if len(text) == 2:
text = str(text[1])
else:
text = str(text[0])
line.text = text
except:
pass
subs.save(file_path)
time_elapsed = ''
if hours > 0:
time_elapsed += str(hours) + ' hrs '
if minutes > 0:
time_elapsed += str(minutes) + ' min '
if seconds > 0:
time_elapsed += str(seconds) + ' sec'
with codecs.open('subtitles.srt', 'a', 'utf-8-sig') as s:
s.write(str(i + 1))
s.write('\n')
s.write(
str(substart)[11:] + ',000 --> ' + str(subend)[11:] + ',000\n')
s.write(time_elapsed + ' skipped \n' + times[i][2] + '\n \n')
s.close()
subs = pysubs.load('subtitles.srt')
subs.save('subtitles.ass')
subtitle = FFmpeg(inputs={args.i: None},
outputs={'subtitled.mp4': '-vf "ass=subtitles.ass"'})
subtitle.run()
for i in range(len(starts)):
name = str(i) + '.mp4'
if i == 0: a = 'w'
else: a = 'a'
with open('videos.txt', a) as v:
v.write("file '" + name + "'\n")
v.close()
def __init__(self, filepath):
"""打开字幕 filepath 准备处理"""
self._filepath = filepath
self._subs = pysubs.load(filepath)
self._timemap = None
self._timedelta = None