def main(argv=None, log_ger=None):
if log_ger is None:
log_ger = create_log(log_name="subtitle", level=logging.INFO)
fname = None
start_dtime = datetime.now()
# print("Start time: "+str(start_dtime))#.strftime("%Y-%m-%d %H:%M:%S"))
print()
# sub=Subtitle(logging.getLogger())
sub = Subtitle(log_ger)
try:
opts, args = getopt.getopt(
argv,
"hvf:w:t:d:e:p:s:b:?lm:WDc",
["help", "version", "parse",
"checkup" "file=", "word=",
"type=", "dir=", "pickle=",
"limit=", "section=", "bigger="])
# print opts, args
log_ger.info("opts:{0};args:{1}".format(opts, args))
except getopt.GetoptError as msg:
print("error happened when get options!!! error:{0}".format(msg))
usage()
log_ger.error("getopt.GetoptError:{0}, exit!".format(msg))
sys.exit(2)
except Exception as msg:
log_ger.error("error:{0}, exit!".format(msg))
sys.exit(2)
_is_lines_show = False
_is_words_show = False
sub_type = ""
words_limit = None
for opt, arg in opts:
if opt in ("-?", "-h", "--help"):
usage()
sys.exit()
pass
elif opt in ("-v", "--version"):
version()
sys.exit()
pass
elif opt in ("-b", "--bigger"):
sub.set_times_bigger(int(arg))
pass
elif opt in ("-c", "--checkup"):
sub.checkup = True
pass
elif opt in ("-d", "--dir"):
print("Sorry, -d --dir option still not offer")
sys.exit()
pass
elif opt in ("-e", "--excel"):
pkl = arg
sub.set_lexicon_file(pkl)
pass
elif opt in ("-s", "--section"):
if ',' in arg:
section = arg.split(',')
if len(section) == 2:
# print(section)
start, end = section
if len(start) != 0:
sub.set_start(int(start))
if len(end) != 0:
sub.set_end(int(end))
# print(start, end)
else:
print("something wrong, with option -s --section:", arg)
sys.exit()
else:
print("something wrong, with option -s --section:", arg)
sys.exit()
pass
elif opt in ('-f', "--file"):
fname = arg
sub.add_file(fname)
pass
elif opt in ('-p', "--parse"):
sub.set_parse(True)
pass
elif opt == '-D':
log_ger.setLevel(logging.DEBUG)
sub.set_logger(log_ger)
sub.set_debug(True)
pass
elif opt in ("-w", "--word"):
word = arg
sub.add_word(word)
# 多用于测试，放弃写入
sub.set_output(False)
pass
elif opt in ("-t", "--type"):
sub_type = arg
if sub_type not in ('save', 'scan', 'cloud'):
usage()
sys.exit()
pass
pass
elif opt in ("-m", "--limit"):
words_limit = int(arg)
# print words_limit
_is_words_show = True
pass
elif opt == '-l':
# show lines
_is_lines_show = True
pass
elif opt == '-W':
# show words
_is_words_show = True
pass
"""
if(len(sys.argv)<2):
print "need args!!"
log_ger.error("need args!!sys.argv:{0}".format(sys.argv))
return None
pass
"""
# print sys.argv
# sub.add_punctuation([',','!',';','.',':','>','<'])
# sub.addLexicon(["hello", "world"])
if sub.lexicon_path is None:
sub.set_lexicon_file("lexicon/lexicon.xlsx")
sub.load_old_data()
sub.add_files(args)
# sub.add_strings("hello world, I'm wang. Please call me wang.")
sub.check_all(encode='utf-8')
if _is_lines_show:
sub.lines_show(words_limit)
pass
if _is_words_show:
# print words_limit
sub.words_show(words_limit)
pass
sub.show()
if sub_type == 'save':
sub.dump_data()
elif sub_type == 'cloud':
sub.cloud()
print()
end_dtime = datetime.now()
# print("End time: "+str(end_dtime))
timedelta = end_dtime - start_dtime
print("Cost time: " + str(timedelta))
# getChecksum(sys.argv[1])
pass
class TransferBak(object):
"""
# save srt to srt.bak
# transfer all srt.bak files
# mv wordch.srt to srt
# create m3u from sub srt
# create and cat word.txt
"""
def __init__(self, logger=None, log_level=logging.INFO):
classname = type(self).__name__
# print("classname: ", classname)
if logger is None:
self.logger = create_log(log_name=classname, level=log_level)
else:
self.logger = logger
self.logger.info("\n-----------------")
self.logger.info("Begin to init")
self.logger.info("\n-----------------")
self.sub = Subtitle(self.logger)
self.sub.set_parse(True)
self.files = dict()
self.filetypes = ['srt', 'bak', 'm3u']
self.vediotypes = ['mkv', 'mp4', 'avi']
self.rmsrt = False
self.is_m3u_only = False
if self.sub.lexicon_path is None:
self.sub.set_lexicon_file("lexicon/lexicon.xlsx")
pass
def setrm(self):
self.rmsrt = True
def set_debug(self):
self.logger.setLevel(logging.DEBUG)
self.sub.set_logger(self.logger)
self.sub.set_debug(True)
def set_m3u_only(self):
self.is_m3u_only = True
def set_logger(self, logger):
self.logger = logger
pass
# save srt to srt.bak
def srt_to_baks(self):
for i in self.files["srt"]:
# mv srt to srt.bak
srt = os.path.join(i[0], i[1])
bak = srt + ".bak"
base = os.path.splitext(srt)[0]
if self.get_vedio_num() <= 0 :
# 无视频的情况
print("move " + srt + " to " + bak)
shutil.move(srt, bak)
pass
else:
for postfix in self.vediotypes:
vedio = ''
if base.endswith(".en"):
vedio = base[0:-3] + "." + postfix
bak = base[0:-3] + ".srt.bak"
else:
vedio = base + "." + postfix
if os.path.exists(vedio) and not os.path.exists(bak):
print("move " + srt + " to " + bak)
shutil.move(srt, bak)
pass
# get srt.bak file from mkv!
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
# create and cat word.txt
def words(self):
pass
def show_files(self):
for k, v in self.files.items():
print(k + ": {}".format(len(v)))
pass
def check_types(self, path):
self.files = dict()
for root, dirs, files in os.walk(path):
for file in files:
for postfix in (self.filetypes + self.vediotypes):
if file.endswith("." + postfix):
if postfix not in self.files:
self.files[postfix] = set()
self.files[postfix].add((root, file))
break
self.show_files()
pass
def rm_m3u(self, path):
if 'm3u' in self.files:
for f in self.files['m3u']:
p = os.path.join(f[0], f[1])
os.remove(p)
print(p + " was removed!")
def rm_srt(self, path):
if 'srt' in self.files:
for f in self.files['srt']:
p = os.path.join(f[0], f[1])
# 没有bak的情况下不要删除原始srt, 悲剧过了
if os.path.exists(p+".bak"):
os.remove(p)
print(p + " was removed!")
self.rm_m3u(path)
out = path+"/output.xlsx"
if os.path.exists(out):
os.remove(out)
print(out + " was removed!")
def get_vedio_num(self):
num = 0
for postfix in self.vediotypes:
if postfix in self.files:
num += len(self.files[postfix])
return num
def transfer_dir(self, path):
self.logger.info("path: {}".format(path))
self.check_types(path)
if self.rmsrt:
self.rm_srt(path)
print("\nafter remove str and m3u files:")
self.check_types(path)
old_bak = set()
if 'bak' in self.files:
old_bak = copy.deepcopy(self.files["bak"])
if self.get_vedio_num() > 0 and self.get_vedio_num() != len(old_bak):
if "srt" in self.files and \
len(self.files["srt"]) > 0:
self.srt_to_baks()
pass
print("------------")
print("after move srt to bak")
self.check_types(path)
if "bak" in self.files:
if self.get_vedio_num() > len(self.files["bak"]):
print("There is more vedio than bak!")
print("There is no enough .srt.bak!")
self.baks_mkv()
elif self.get_vedio_num() > 0:
print("There is more vedio than bak(0)!")
print("There is no enough .srt.bak!")
self.baks_mkv()
self.check_types(path)
if "bak" in self.files and len(self.files["bak"]) == len(old_bak):
print("baks num get no increase!")
if 'bak' in self.files:
old_bak = copy.deepcopy(self.files["bak"])
elif len(old_bak) > 0:
print(".srt.bak exists!")
pass
elif self.get_vedio_num() <= 0 :
# 有字幕，无视频的情况, 继续执行，背背单词
print("no .srt.bak at all!")
if "srt" in self.files and \
len(self.files["srt"]) > 0:
self.srt_to_baks()
pass
print("------------")
print("after move srt to bak")
self.check_types(path)
if len(self.files["bak"]) == len(old_bak):
print("baks num get no increase!")
if 'bak' in self.files:
old_bak = copy.deepcopy(self.files["bak"])
else:
print("no .srt.bak at all!")
pass
srt_cre = []
if "srt" in self.files:
srt_set = set([os.path.join(x[0], x[1]) for x in self.files["srt"]])
else:
srt_set = set()
if len(old_bak) > 0:
for f in self.files["bak"]:
bak = os.path.join(f[0], f[1])
bak_base = os.path.splitext(bak)[0] # will get *.srt
# print(bak_base)
if bak_base not in srt_set:
srt_cre.append(bak)
self.sub.load_old_data()
self.sub.add_files(srt_cre)
self.sub.check_all(encode='utf-8')
# 在目标文件夹也放一份单词excel
output_dir = "output/output.xlsx"
if self.sub.words_len() > 0 and os.path.exists(output_dir):
shutil.copy(output_dir, path)
print("output.xlsx was copy to " + path)
self.sub.show()
failedfiles = []
srt_files = []
for f in srt_cre:
base = os.path.splitext(f)[0] # will get *.srt
print("base:", base)
wordsrt = base + "_word.srt"
srt = base
print(wordsrt)
if os.path.exists(wordsrt):
shutil.move(wordsrt, srt)
srt_files.append(srt)
else:
failedfiles.append(srt_cre)
print("files failed to create .srt_word.srt:\n")
for f in failedfiles:
print(f)
print('-------------')
print("srt files created:\n")
for f in srt_files:
print(f)
print('-------------')
self.get_m3u(path)
def get_m3u(self, path):
self.check_types(path)
old_m3u = set()
if 'm3u' in self.files:
old_m3u = copy.deepcopy(self.files['m3u'])
else:
old_m3u = []
for postfix in self.vediotypes:
if postfix in self.files:
for f in self.files[postfix]:
vedio = os.path.join(f[0], f[1])
base = os.path.splitext(vedio)[0] # will get * without .mkv
m3u = base + ".m3u"
srt = base + ".srt"
if not os.path.exists(m3u) and os.path.exists(srt):
print(vedio, "is getting m3u...")
set_m3u(vedio, self.logger)
self.check_types(path)
if 'm3u' in self.files and len(old_m3u) >= len(self.files['m3u']):
print("old_m3u:\n", old_m3u)
print("new_m3u:\n", self.files['m3u'])
pass
def transfer_paths(self, paths):
self.logger.info("paths:{}".format(paths))
# print(paths) # for debug
for p in paths:
if os.path.isfile(p):
print(
"should be dir, don't input file:" +
p)
elif os.path.isdir(p):
print("transfer dir:" + p)
if self.is_m3u_only is True:
self.check_types(p)
self.rm_m3u(p)
self.get_m3u(p)
else:
self.transfer_dir(p)
else:
print(p, "not exists!")
pass