def tosrt(sub):
for file in sub:
with open(file, 'r') as f:
srtfile = asstosrt.convert(f)
new_name = '.'.join(file.split('.')[:-1]) + '.srt'
with open(new_name, 'w') as f:
f.write(srtfile)
os.remove(file)
def duplicate_srt_sub(ass_filename):
srt_filename = ass_filename.replace(".ass", ".srt")
with open(srt_filename, "w+", encoding="utf8") as srt_file:
try:
with open(ass_filename, encoding="utf8") as ass_file:
srt_file.write(asstosrt.convert(ass_file))
print("duplicate srt {}".format(srt_filename))
except Exception as e:
print(e)
def _convert_files(files, args):
if args.encoding:
in_codec = codecs.lookup(args.encoding)
else:
in_codec = None
if args.srt_encoding:
out_codec = codecs.lookup(args.srt_encoding)
else:
out_codec = in_codec
sum = len(files)
done = 0
fail = 0
ignore = 0
print("Found {} file(s), converting...".format(sum))
for in_path, out_path in _combine_output_file_path(files, args.output_dir):
print("\t({:02d}/{:02d}) is converting... " \
.format(done + fail + ignore + 1, sum), end='')
if not args.force and os.path.exists(out_path):
print('[ignore] (SRT exists)')
ignore += 1
continue
try:
with open(in_path, 'rb') as in_file:
if args.encoding is None: # Detect file charset.
in_codec = codecs.lookup(_detect_charset(in_file))
if args.srt_encoding is None:
out_codec = in_codec
out_str = asstosrt.convert(in_codec.streamreader(in_file),
args.translator, args.no_effact,
args.only_first_line)
with open(out_path, 'wb') as out_file:
out_file.write(get_bom(out_codec))
out_file.write(out_codec.encode(out_str)[0])
done += 1
print('[done]')
except (UnicodeDecodeError, UnicodeEncodeError, LookupError) as e:
print('[fail] (codec error)')
print(e, file=sys.stderr)
fail += 1
except ValueError as e:
print('[fail] (irregular format)')
print(e, file=sys.stderr)
fail += 1
except IOError as e:
print('[fail] (IO error)')
print(e, file=sys.stderr)
fail += 1
print("All done:\n\t{} success, {} ignore, {} fail." \
.format(done, ignore, sum - done - ignore))
def _convert_files(files, args):
if args.encoding:
in_codec = codecs.lookup(args.encoding)
else:
in_codec = None
if args.srt_encoding:
out_codec = codecs.lookup(args.srt_encoding)
else:
out_codec = in_codec
sum = len(files)
done = 0
fail = 0
ignore = 0
print("Found {} file(s), converting...".format(sum))
for in_path, out_path in _combine_output_file_path(files, args.output_dir):
print("\t({:02d}/{:02d}) is converting... " \
.format(done + fail + ignore + 1, sum), end='')
if not args.force and os.path.exists(out_path):
print('[ignore] (SRT exists)')
ignore += 1
continue
try:
with open(in_path, 'rb') as in_file:
if args.encoding is None: # Detect file charset.
in_codec = codecs.lookup(_detect_charset(in_file))
if args.srt_encoding is None:
out_codec = in_codec
out_str = asstosrt.convert(in_codec.streamreader(in_file),
args.translator, args.no_effact, args.only_first_line)
with open(out_path, 'wb') as out_file:
out_file.write(get_bom(out_codec))
out_file.write(out_codec.encode(out_str)[0])
done += 1
print('[done]')
except (UnicodeDecodeError, UnicodeEncodeError, LookupError) as e:
print('[fail] (codec error)')
print(e, file=sys.stderr)
fail += 1
except ValueError as e:
print('[fail] (irregular format)')
print(e, file=sys.stderr)
fail += 1
except IOError as e:
print('[fail] (IO error)')
print(e, file=sys.stderr)
fail += 1
print("All done:\n\t{} success, {} ignore, {} fail." \
.format(done, ignore, sum - done - ignore))
def convert_ass_to_srt(file_string):
file_name, file_extension = os.path.splitext(file_string)
if file_extension.endswith('ass') and os.path.isfile(file_string):
# https://www.zhihu.com/question/36368902
with open(file_string, 'r', encoding='utf-8',
errors='ignore') as ass_file:
srt_str = asstosrt.convert(ass_file, no_effect=True)
srt_file_name = file_name + '_converted_ass.srt'
if os.path.isfile(srt_file_name):
os.remove(srt_file_name)
with open(srt_file_name, "w", encoding='utf-8',
newline='\n') as srt_file:
srt_file.write(srt_str)
def main(path):
subs = []
# 如果是目录
if os.path.isdir(path):
for root, _, files in os.walk(path):
for ass_file in files:
if re.match("(?i).*(ass)$", ass_file):
subs.append(os.path.join(root, ass_file))
# 如果是文件
else:
subs = {path}
path = os.path.split(path)[0]
for sub_file in subs:
with open(sub_file, "rb") as ass_file:
charset = chardet.detect(ass_file.read())["encoding"].lower()
ass_file_name = '.'.join(sub_file.split('.')[:-1]) + '.srt'
with open(sub_file, "r", encoding=charset) as ass_file:
with open(ass_file_name, "wb") as srt_file:
srt_file.write(convert(asstosrt.convert(ass_file), 'zh-cn').encode('utf8'))
print(ass_file_name, "done")
def run(self, fold):
"""
主要逻辑控制
:param fold: 输入文件夹
:return:
"""
if os.path.isdir(fold):
files = list_file(folder=fold)
elif os.path.isfile(fold):
files = [fold]
else:
print("不是文件夹不是文件, 你到底是啥")
files = []
for file in files:
coding_msg = self.check_char(file)
encoding_format = coding_msg.get("encoding")
if encoding_format == "Windows-1254":
encoding_format = "utf8"
with open(file, 'r', encoding=encoding_format) as f:
# if file.endswith("srt") or file.endswith('txt'):
# subtitle_content = self.parse_srt(f)
# elif file.endswith("ass"):
# srt_str = asstosrt.convert(f)
# srt = srt_str.split('\n')
# 如果是ass文件将ass文件转化为 srt格式，这次的txt内容上是srt文件所以不做区分
if file.endswith("ass"):
srt_str = asstosrt.convert(f)
f = srt_str.split('\n')
subtitle_content = self.parse_srt(f)
with open(r'C:\Users\Administrator\Desktop\vietnam_speaking.txt',
'a',
encoding='utf8') as f:
f.write(subtitle_content + "\n")
# -*- coding: utf-8 -*-
import glob
import chardet
import asstosrt
for ass_fn in glob.iglob('*.ass'):
with open(ass_fn, 'rb') as f:
ass_bytes = f.read()
encoding = chardet.detect(ass_bytes)['encoding']
with open(ass_fn, 'r', encoding=encoding) as f:
srt_str = asstosrt.convert(f)
srt_fn = ass_fn[:-4] + '.srt'
with open(srt_fn, 'w', encoding='utf-8') as f:
f.write(srt_str)
def baks_mkv(self):
failedfiles = []
print("------------")
print('get srt.bak file from vedio!')
for postfix in self.vediotypes:
if postfix in self.files:
for fi, f in enumerate(self.files[postfix]):
mkvfile = os.path.join(f[0], f[1])
print("------------")
print(fi, mkvfile)
srtbak_path = os.path.splitext(mkvfile)[0] + ".srt.bak"
if os.path.exists(srtbak_path):
print(srtbak_path, "exists")
print("------------")
continue
print("1. Check streams in mkv!")
res = subprocess.run(["ffmpeg",
"-i", mkvfile],
stderr=subprocess.PIPE)
"""
print(res)
print("------------")
print(res.stderr)
print(res.stdout)
print(res.args)
print("------------over")
"""
beg = False
streams = []
stream = None
for i, v in enumerate(res.stderr.decode("utf-8").split("\n")):
if "Stream" in v:
beg = True
m = re.match(r" *Stream #(\d+):(\d+)(\(\w+\))?: (\w+): (\w+)", v)
if m:
# print(m.groups()[1:]) # c
if stream is not None:
streams.append(stream)
stream = {"id": m.group(2), "type": m.group(4), "filetype": m.group(5)}
if m.group(3) is not None:
# subhead 副标题
stream['subhead'] = m.group(3)
continue
else:
print("err: reg not work on this sentence")
print(v)
sys.exit(2)
elif not beg:
continue
else:
m = re.match(r" *title *: (.*)", v)
if m:
stream['title'] = m.group(1)
pass
pass
streams_df = pd.DataFrame(streams)
print("streams_df:\n", streams_df) # c
# print(streams_df.dtypes) # c
if len(streams_df) < 2 or len(streams_df[streams_df["type"] == "Subtitle"]) <= 0:
print("not have enough stream")
failedfiles.append(mkvfile)
continue
print("2. get srt.bak file from mkv!")
engchs = []
if 'title' in streams_df:
criterion = streams_df['title']. \
map(lambda t: re.match(r"(英.中)|(英中)|(中英字幕)", str(t)) is not None)
engchs = streams_df[criterion]
if len(engchs) > 0:
# todo: deal engchs
print("engchs:\n", engchs)
# print( os.path.splitext(mkvfile)[0] + ".srt.bak") # c
base = os.path.splitext(mkvfile)[0]
srt = base + ".srt"
if 'ass' == str(engchs.iloc[0].filetype):
ass = base + ".ass"
ass_file = open(ass)
srt_str = asstosrt.convert(ass_file)
f = open(srt, "w")
f.write(srt_str)
f.close()
"""
subprocess.run(
["mkvextract", "tracks",
mkvfile,
"{0}:{1}".format(
str(engchs.iloc[0].id),
ass
)
])
time.sleep(2)
res = subprocess.run(["ffmpeg", "-i", ass, srt])
if os.path.getsize(srt) <= 10:
print(res)
print("------------")
print(res.stderr)
print(res.stdout)
print(res.args)
print("------------over")
sys.exit(8)
"""
if os.path.exists(srt):
shutil.move(srt, srtbak_path)
else:
# todo: log err
print("error: {} failed to create!".format(srt))
failedfiles.append(mkvfile)
pass
elif 'subrip' == str(engchs.iloc[0].filetype):
print("filetype:", str(engchs.iloc[0].filetype))
subprocess.run(
["mkvextract", "tracks",
mkvfile,
"{0}:{1}".format(
str(engchs.iloc[0].id),
srtbak_path
)
])
pass
else:
criterion = streams_df['subhead']. \
map(lambda t: re.match(r"eng", str(t)) is not None)
eng = streams_df[
criterion &
(streams_df.type == "Subtitle")
]
if len(eng) > 0:
# todo: deal eng
print("eng:\n", eng)
pass
else:
print('-------------')
print(f[1], "has no suitable subtitle stream!")
print(streams_df[streams_df.type == "Subtitle"])
failedfiles.append(mkvfile)
print('-------------')
pass
print("files failed to create .srt.bak:\n")
for f in failedfiles:
print(f)
print('-------------')
pass