def search_subtitles(self):
"""
search subtitles for a given file
:return: Opensubtitles search data or None
"""
try:
movie_file = File(self.path)
except:
print "Error Calculating File Size"
return False
file_hash = movie_file.get_hash()
if "Error" in file_hash:
print "Error Calculating File Hash"
return False
if not self.is_auth:
print "Error Connecting to OpenSubtitles"
return False
# search function
searchdata = self.opensubtitles.search_subtitles([{
'sublanguageid':
self.language,
'moviehash':
file_hash,
'moviebytesize':
movie_file.size
}])
return searchdata
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
"file",
help="Path to the file you want to download subtitles for",
type=str)
args = parser.parse_args()
if os.path.exists(args.file):
f = File(os.path.abspath(args.file))
path, file = os.path.split(args.file)
path_full_nofile = os.path.abspath(path)
path_file = file
path_file_noext = os.path.splitext(args.file)[0]
else:
sys.exit("File does not exist")
ost = OpenSubtitles()
username = input("Please input your OpenSubtitles.org username: "******"Please input your OpenSubtitles.org password: "******"Logging in, please wait...")
ost.login(username, password)
print("Successfully logged in!")
hash = f.get_hash()
size = f.size
print("Scouring the web for subtitles, please wait...")
data = ost.search_subtitles([{
'sublanguageid': 'eng',
'moviehash': hash,
'moviebytesize': size
}])
bestdic = None
highestdownloadcount = 0
for dict in data:
downloadcount = int(dict.get('SubDownloadsCnt'))
if downloadcount > highestdownloadcount:
downloadcount = highestdownloadcount
bestdic = dict
print("Subtitle found in", bestdic.get('SubLanguageID'), "with",
bestdic.get('SubDownloadsCnt'), "downloads.")
print("Downloading subtitles, please wait...")
urllib.request.urlretrieve(
bestdic.get('SubDownloadLink'),
path_full_nofile + "/" + path_file_noext + ".srt.gz")
print("Subtitle downloaded!")
print("Unzipping subtitle, please wait...")
inF = gzip.open(path_full_nofile + "/" + path_file_noext + ".srt.gz", "rb")
outF = open(path_full_nofile + "/" + path_file_noext + ".srt", "wb")
outF.write(inF.read())
inF.close()
outF.close()
os.remove(path_full_nofile + "/" + path_file_noext + ".srt.gz")
print("Done!")
def downloader(file_list, search):
for file_path in file_list:
if search == 'hash':
fname = os.path.split(file_path) # fname stores file name and root directory path in a tuple
#print('fname', ' ', fname)
file_root = fname[0]
print('some more bs', file_root, '\n', file_path)
f = File(file_path) # File class has methods to get hash and size of file
data = ost.search_subtitles([{'sublanguageid': 'all', 'moviehash': f.get_hash(), 'moviebytesize': f.size}]) # this method stores multiple subtitle's data in a list in multiple dictionaries using file hash and size.
# data stores hash, size ,imdbrating, and much more
elif search == 'query':
fname = os.path.split(nfdict[file_path])
#print('fname', ' ', fname)
file_root = fname[0]
print('some more bs', file_root, '\n', file_path)
print('file root: ', file_root)
data = ost.search_subtitles([{'sublanguageid': 'all', 'query': file_path}]) # uses file name to search for subs and stores sub data in a list.
if data == []:
print('Could not find sub in opensubtitles.org') # if sub not found data will be empty
# file path and name will be adden to a dict as values and keys
if search == 'query': # respectively for hash search, and only name to a list for name search
newlist.append(fname[1])
elif search == 'hash':
nfdict[fname[1]] = file_path
continue
else:
#print("\n\n\n\n check check \n\n ")
#print(data)
id_subtitle_file = data[0].get('IDSubtitleFile') # gets sub id (a 6 digit num)
#print(data)
imdb_rating(goodmv1, avgmv1, tmv1, data, fname)
newsub = file_root + s + fname[1][:-4] + '.srt' # a string with the name of the final sub file
# used below to check if file already exists.
if os.path.exists(newsub):
print("sub for this exists so i don't think downloading it again will do shit....")
continue
else: # downloads subtitles using sub id from data and stores sub in output dir.
ost.download_subtitles([id_subtitle_file], output_directory=file_root, extension='srt')
sub = file_root + s + str(id_subtitle_file) + '.srt'
if os.path.exists(sub) == False: # debugging to check if download failed
print("Probably subtitle downloading limit reached(for the account).")
try:
rename_file(file_root, id_subtitle_file, fname)
except FileExistsError:
print('file exists so deleting the newly made file')
os.remove(sub)
def main():
pathList = []
downloadList = []
#if len(sys.argv) < 1 :
# print "Missing Arguments"
# quit()
folder = "/home/Downloads/torrents"
#print sys.argv[1]
for root, dirs, files in os.walk(folder):
path = root.split('/')
#print root
for file in files:
if(file.endswith(".mp4") or file.endswith(".avi") or file.endswith(".mkv") ):
print os.path.join(root,file)
pathList.append(os.path.join(root,file))
print "Found %d files" % len(pathList)
if len(pathList) >= 1:
ops = OpenSubtitles()
token = ops.login("","")
print token
for subToFind in pathList:
f = File(subToFind)
dirname = os.path.normpath(subToFind)
subData = ops.search_subtitles([{'sublanguageid': 'pob','moviehash': f.get_hash() , 'moviebytesize': f.size }])
if not subData:
print "Sub not found for %s " % f.path
else:
filename = ''
if f.path.endswith(".mp4"):
filename = dirname.replace('.mp4', '.srt')
elif f.path.endswith('.mkv'):
filename = dirname.replace('.mkv', '.srt')
elif f.path.endswith('.avi'):
filename = dirname.replace('.avi', '.srt')
response = urllib2.urlopen(subData[0]['SubDownloadLink'])
compressedFile = StringIO.StringIO()
compressedFile.write(response.read())
response.close()
compressedFile.seek(0)
decompressedFile = gzip.GzipFile(fileobj=compressedFile,mode='rb')
with open(filename ,'w') as outfile:
outfile.write(decompressedFile.read())
time.sleep(1)
ops.logout()
def download_all_subtitles(filepath):
dirname = os.path.dirname(filepath)
basename = os.path.basename(filepath)
basename_without_ext = os.path.splitext(basename)[0]
ost = OpenSubtitles()
ost.login(None, None)
f = File(filepath)
h = f.get_hash()
results_from_hash = (ost.search_subtitles([{
"sublanguageid": "all",
"moviehash": h
}]) or [])
languages_in_results_from_hash = [
lang_id
for lang_id in [r.get("SubLanguageID") for r in results_from_hash]
]
results_from_filename = [
r for r in ost.search_subtitles([{
"sublanguageid": "all",
"query": basename_without_ext
}])
]
results_from_filename_but_not_from_hash = [
r for r in results_from_filename if r.get("SubLanguageID")
and r.get("SubLanguageID") not in languages_in_results_from_hash
]
results = results_from_hash + results_from_filename_but_not_from_hash
wait_before_next_chunk = False
for chunk in _chunks(results, 10):
sub_ids = {
r["IDSubtitleFile"]: f'{basename_without_ext}.{r["ISO639"]}.srt'
for r in chunk
}
def _download_subtitle_chunk(retries=5):
nonlocal ost
try:
ost.download_subtitles(
[_id for _id in sub_ids.keys()],
override_filenames=sub_ids,
output_directory=dirname,
extension="srt",
)
except ProtocolError as e:
if retries == 0:
raise e
time.sleep(10)
ost = OpenSubtitles()
ost.login(None, None)
_download_subtitle_chunk(retries=retries - 1)
if wait_before_next_chunk:
time.sleep(10)
_download_subtitle_chunk()
wait_before_next_chunk = True
def main(video):
log("info", "Loaded module subtitles")
# Logging in to OST
log("info", "Logging in to OpenSubtitles")
ost = OpenSubtitles()
token = ost.login(opensubtitles_username, opensubtitles_password)
if isinstance(token, str):
log("success", "Logged in to OpenSubtitles")
else:
log("critical", "Invalid username / password entered")
return
# Opening File
file_path = video_path + video
if not path.exists(file_path):
log("critical", "Could not find specified video file '" + file_path + "'")
return
# Hashing file
log("info", "Generating video hash...")
f = File(file_path)
hash = f.get_hash()
log("success", "File hash generated: " + hash)
# Searching OST
log("info", "Querying OpenSubtitles for subtitles...")
data = ost.search_subtitles([{'sublanguageid': 'all', 'moviehash': hash}])
if len(data) > 0:
log("success", f"Found {len(data)} results.")
else:
log("warning", "No results found.")
# TODO: Implement series and episode-based downloading
return
subtitle_id = data[0]["IDSubtitleFile"]
log("info", "Attempting download of subtitles with ID " + str(subtitle_id))
try:
if isinstance(ost.download_subtitles([subtitle_id], override_filenames={subtitle_id: video + '.srt'}, output_directory=video_path, extension='srt'), dict):
log("success", "Subtitles successfully downloaded. Enjoy your video!")
else:
log("critical", "Subtitle download failed.")
return
except:
#TODO: Make neater
log("error", "Something went wrong. Trying second option in list(?)")
subtitle_id = data[1]["IDSubtitleFile"]
log("info", "Attempting download of subtitles with ID " + str(subtitle_id))
try:
if isinstance(ost.download_subtitles([subtitle_id], override_filenames={subtitle_id: video + '.srt'}, output_directory=video_path, extension='srt'), dict):
log("success", "Subtitles successfully downloaded. Enjoy your video!")
else:
log("critical", "Subtitle download failed.")
return
except:
log("critical", "giving up after too many tries")
return
def find_subtitles(path, langid='all'):
''' Get a list of subtitles for a given file '''
f = File(path)
hash = f.get_hash()
assert type(hash) == str
size = f.size
assert isinstance(size, Number)
data = osmgr.search_subtitles([{'sublanguageid': langid,
'moviehash': hash,
'moviebytesize': size}])
assert type(data) == list
return data
def find_subtitles(path, langid='all'):
''' Get a list of subtitles for a given file '''
f = File(path)
hash = f.get_hash()
assert type(hash) == str
size = f.size
assert isinstance(size, Number)
data = osmgr.search_subtitles([{
'sublanguageid': langid,
'moviehash': hash,
'moviebytesize': size
}])
assert type(data) == list
return data
def downloadSub():
names = os.listdir()
for name in names:
if (name.endswith(tuple(ext))):
file_name, file_ext = splitext(name)
class Test(object):
usename = 'ermisss'
password = '******'
video = name
path = currdir
# Test.video=file_name
fullPath = currdir + '/' + file_name
token = ost.login('ermisss', '258456++')
assert type(token) == str
f = File(path.join(Test.path, Test.video))
hash = f.get_hash()
assert type(hash) == str
log.write("hash:" + hash + "\n")
size = f.size
assert type(size) == str
log.write("size:" + size + "\n")
dataid = ost.search_subtitles([{
'sublanguageid': 'tur',
'moviehash': hash,
'moviebytesize': size
}])
log.write("id:" + dataid + "\n")
id_subtitle = dataid[0].get('IDSubtitle')
id_sub_movie_file = dataid[0].get('IDSubMovieFile')
subURL = dataid[0].get('SubDownloadLink')
assert type(dataid) == list
urllib.request.urlretrieve(subURL, fullPath + ".srt.gz")
with gzip.open(fullPath + '.srt.gz', 'rb') as f_in:
with open(fullPath + '.srt', 'wb') as f_out:
shutil.copyfileobj(f_in, f_out)
if os.path.exists(fullPath + '.srt.gz'):
os.remove(fullPath + '.srt.gz')
log.write(name + "\n")
def download_subtitle(self):
"""
Downloads subtitles from opensubtitles.org, in the defined language
and stores them in a tempfile.
Search is trying to match movie by hash and if it is unsuccessful,
it searches by movie name.
Only first match is considered.
"""
ost = OpenSubtitles()
logged_in = ost.login(self.os_username, self.os_password)
if not logged_in:
raise Error("Wrong opensubtitles credentials")
# TODO refactor to consume path on event, potentially from queue
mkv_files = [mkv for mkv in self.watch_path.glob("*.mkv")]
subs = list()
for movie in mkv_files:
movie_file = File(movie.absolute())
# search by hash, if not, by name
ost_data = ost.search_subtitles([
{
"sublanguageid":
self.os_language
if len(self.os_language) == 3 else self.os_language,
"moviehash":
movie_file.get_hash(),
},
{
"sublanguageid":
self.os_language
if len(self.os_language) == 3 else self.os_language,
"query":
movie.name,
},
])
if ost_data:
# # downloading first subtitle
plain_link = ost_data[0]["SubDownloadLink"]
sub_link_parts = plain_link.split("/download/")
# rebuilding link to get utf-8 subtitle
sub_link = (sub_link_parts[0] + "/download/subencoding-utf8/" +
sub_link_parts[1])
response = requests.get(sub_link)
tmp, tmp_name = tempfile.mkstemp()
with open(tmp, "wb") as srt_out:
srt_out.write(gzip.decompress(response.content))
subs.append({"file_path": movie, "sub": tmp_name})
else:
subs.append({"file_path": movie, "sub": None})
return subs
def get_subtitle(filename):
os_sub = OpenSubtitles()
try:
token = os_sub.login('thegyro','idontlikepasswords')
if os.path.exists(os.path.join(source_dir,filename)):
video_file = File(os.path.join(source_dir,filename))
video_hash = video_file.get_hash()
video_size = video_file.size
sub_param = {'sublanguageid':'English','moviehash':video_hash,'moviebytesize': video_size}
subtitles = os_sub.search_subtitles([sub_param])
print subtitles
else:
raise Exception("File doesn't exist")
except Exception as ex:
print str(ex)
def downloadSubs(Parameters):
#Assign/allocate object and get token after logging in with credentials from the Parameters object
opensubs = OpenSubtitles()
token = opensubs.login(Parameters.username, Parameters.password)
if token is None:
print '\n*** Login failed! ***\n'
sys.exit()
#Get hash and size of file from Parameters object
f = File(os.path.join(Parameters.path, Parameters.video))
print '\tPath: %s' % Parameters.path
print '\tFile: %s' % Parameters.video
hash = f.get_hash()
size = f.get_size()
#Search subtitles DB using file hash and size. Looks like the first result is the best matching result
data = opensubs.search_subtitles([{'sublanguageid': 'eng', 'moviehash': hash, 'moviebytesize': size}])
if data:
#Download first result, decode it from BASE64, add gz extension, save file
download = opensubs.download_subtitles([data[0]['IDSubtitleFile']])
data_decoded = base64.b64decode(unicode(download[0]['data']))
gz_file = os.path.join(Parameters.path, Parameters.subtitle) + '.gz'
print '\nCreating gz file: %s' % gz_file
download_file = open(gz_file,'w')
download_file.write(data_decoded)
download_file.close()
print 'Created gz file: %s' % gz_file
#Extract SRT file from gz file and place it in the same folder
print 'Opening gz file: %s' % gz_file
srt_file_buffer = gzip.open(gz_file, 'r')
srt_file_name = os.path.join(Parameters.path, Parameters.subtitle)
print 'Creating SRT file: %s' % srt_file_name
srt_file = open(srt_file_name,'w')
srt_file.write(srt_file_buffer.read())
srt_file.close()
print 'Created SRT file: %s' % srt_file_name
#Delete .gz file
print 'Deleting %s' % gz_file
os.remove(gz_file)
else:
print '*** No match found for file! ***'
def download_all_subtitles(filepath):
dirname = os.path.dirname(filepath)
basename = os.path.basename(filepath)
basename_without_ext = os.path.splitext(basename)[0]
ost = OpenSubtitles()
ost.login(None, None)
f = File(filepath)
h = f.get_hash()
results = ost.search_subtitles([{"sublanguageid": "all", "moviehash": h}])
for chunk in _chunks(results, 20):
sub_ids = {
r["IDSubtitleFile"]:
f'{basename_without_ext}.{r["SubLanguageID"]}.srt'
for r in chunk
}
ost.download_subtitles(
[_id for _id in sub_ids.keys()],
override_filenames=sub_ids,
output_directory=dirname,
extension="srt",
)
def find_subtitles_by_hash(self, source):
f = File(source)
return self.find_subtitles(moviehash=f.get_hash(), moviebytesize=f.size)
video = 'Trance.2013 WEBRip XViD juggs.avi'
#title = 'Dark.City.1998.Directors.Cut.BRRip.H264.AAC.5.1ch.Gopo.srt'
#subtitle = 'Dark.City.1998.Directors.Cut.BRRip.H264.AAC.5.1ch.Gopo.srt'
token = fd.login(Data.username, Data.password)
if not token:
print("Chyba prihlaseni")
sys.exit(1)
print(token)
from pythonopensubtitles.utils import File
f = File(os.path.join(Data.path, Data.video))
h = f.get_hash()
print("Hash: %s" % h)
print("Size: %f" % f.size)
data = fd.search_subtitles([{'sublanguageid': 'cze', 'moviehash': h, 'moviebytesize': f.size}])
import urllib2
from StringIO import StringIO
import gzip
for item in data:
print(item['SubDownloadLink'])
request = urllib2.Request(item['SubDownloadLink'])
response = urllib2.urlopen(request)
def opensub(relpath):
"""OpenSubtitle identification of movie
Uses the OpenSubtitles API to identify movie
Args:
relpath(str): relative path of movie file
Returns:
imdb_id(int): on success, returns idetified imdb id
None: on failure
Raises:
None
"""
if 'sub' not in opensub.__dict__:
sub = opensub_initiate()
if sub:
opensub.sub = sub
token = sub.login(
OpenSubKey.get_solo().uid,
OpenSubKey.get_solo().key
)
opensub.token = token
opensub.lock = Lock()
try:
# login to opensub using API
sub = opensub.sub
token = opensub.token
if not token:
# return sub
print 'null token'
log.error('path: %s open sub null token' % relpath)
return
# check that the file is accessible
if not path.exists(path.join(
HDDRoot.get_solo().path,
MovieFolder.get_solo().relpath,
relpath,
)):
print "ERROR: " + relpath
log.error('path: %s does not exist' % relpath)
return
f = File(path.join(
HDDRoot.get_solo().path,
MovieFolder.get_solo().relpath,
relpath,
))
if f is None:
log.error('path: %s open sub file error' % relpath)
return
hash = f.get_hash()
size = f.size
with opensub.lock:
data = sub.search_subtitles([{
'sublanguageid': 'all',
'moviehash': hash,
'moviebytesize': size,
}])
if type(data) is list:
if data[0].get('IDMovieImdb', None):
return data[0]['IDMovieImdb']
else:
log.warning('%s opensub failed to identify movie' % relpath)
except ProtocolError as e:
# most likely network error or API server error
print "E: " + str(e)
except AssertionError:
print 'Failed to authenticate opensubtitles login.'
except ProtocolError as e:
"""
TODO: gaierror:
[Errno 8] nodename nor servname provided, or not known
"""
if e.errcode == 503:
# ProtocolError - 503 Service Unavailable
print 'Check network connection and try again.'
log.error('path: %s open sub error occured' % relpath)
log.error(traceback.format_exc())
except Exception:
log.error('path: %s open sub error occured' % relpath)
log.error(traceback.format_exc())
def calculate_hash(self, filePath):
logger.debug("filePath: {}".format(filePath))
f = File(filePath)
hash = f.get_hash()
logger.debug("hash: {}".format(hash))
return hash
def download_all_subtitles(filepath, skip=[]):
dirname = os.path.dirname(filepath)
basename = os.path.basename(filepath)
basename_without_ext = os.path.splitext(basename)[0]
ost = OpenSubtitles()
ost.login(settings.OPENSUBTITLES_USERNAME, settings.OPENSUBTITLES_PASSWORD)
f = File(filepath)
h = f.get_hash()
language_ids = [
languages.get(part1=lang).part2b
for lang in settings.SUBTITLE_LANGUAGES if lang not in skip
]
results_from_hash = ([
item for sublist in [
ost.search_subtitles([{
"sublanguageid": langid,
"moviehash": h
}]) or [] for langid in language_ids
] for item in sublist
])
languages_in_results_from_hash = [
lang_id
for lang_id in [r.get("SubLanguageID") for r in results_from_hash]
]
results_from_filename = ([
item for sublist in [
ost.search_subtitles([{
"sublanguageid": langid,
"query": basename_without_ext
}]) or [] for langid in language_ids
] for item in sublist
])
results_from_filename_but_not_from_hash = [
r for r in results_from_filename if r.get("SubLanguageID")
and r.get("SubLanguageID") not in languages_in_results_from_hash
]
results = results_from_hash + results_from_filename_but_not_from_hash
results = [
r for r in results if r["ISO639"] in settings.SUBTITLE_LANGUAGES
]
wait_before_next_chunk = False
sub_filenames = []
for chunk in _chunks(results, 10):
sub_ids = {
r["IDSubtitleFile"]: f'{basename_without_ext}.{r["ISO639"]}.srt'
for r in chunk
}
sub_filenames = list(set(sub_filenames + list(sub_ids.values())))
def _download_subtitle_chunk(retries=5):
nonlocal ost
if not sub_ids:
return
try:
ost.download_subtitles(
[_id for _id in sub_ids.keys()],
override_filenames=sub_ids,
output_directory=dirname,
extension="srt",
)
except ProtocolError as e:
if retries == 0:
raise e
time.sleep(10)
ost = OpenSubtitles()
ost.login(None, None)
_download_subtitle_chunk(retries=retries - 1)
if wait_before_next_chunk:
time.sleep(10)
_download_subtitle_chunk()
wait_before_next_chunk = True
for sub_filename in sub_filenames:
tmp_path = os.path.join(dirname, "fixed_" + sub_filename)
output_path = os.path.join(dirname, sub_filename)
os.system(
f"timeout 5m alass '{filepath}' '{output_path}' '{tmp_path}'")
os.system(f"mv '{tmp_path}' '{output_path}'")
return ''.join(
filter(lambda x: x in printable,
s.lower().replace(" ", "-")))
ost = OpenSubtitles()
from pythonopensubtitles.utils import File as OstFile
token = ost.login('', '')
print('OpenSubtitles token: %s' % token, file=sys.stderr)
movies_list = []
movies_without_reference_sub_count = 0
for file_idx, file_path in enumerate(video_paths):
f = OstFile(file_path)
file_hash = f.get_hash()
print(file=sys.stderr)
print('-------------------------------------------------------',
file=sys.stderr)
print('Movie `%s` with hash `%s`:' % (file_path, file_hash),
file=sys.stderr)
subtitle_files = ost.search_subtitles([{
'moviehash': file_hash,
'sublanguageid': 'eng'
}])
if len(subtitle_files) == 0:
file_basename = os.path.splitext(os.path.basename(file_path))[0]
print('Video file `%s` not registered on OpenSubtitles' % file_path,
def get_subtitles(self, resource, language=None):
"""
Get the subtitles data for a video resource
:param resource: Media file, torrent or URL to the media resource
:type resource: str
:param language: Language name or code (default: configured preferred language).
Choose 'all' for all the languages
:type language: str
"""
from pythonopensubtitles.utils import File
if resource.startswith('file://'):
resource = resource[len('file://'):]
resource = os.path.abspath(os.path.expanduser(resource))
if not os.path.isfile(resource):
return None, '{} is not a valid file'.format(resource)
file = resource
cwd = os.getcwd()
media_dir = os.path.dirname(resource)
os.chdir(media_dir)
file = file.split(os.sep)[-1]
local_subs = [{
'IsLocal':
True,
'MovieName':
'[Local subtitle]',
'SubFileName':
sub.split(os.sep)[-1],
'SubDownloadLink':
'file://' + os.path.join(media_dir, sub),
} for sub in find_files_by_ext(media_dir, '.srt', '.vtt')]
self.logger.info('Found {} local subtitles for {}'.format(
len(local_subs), file))
languages = [language.lower()] if language else self.languages
try:
file_hash = File(file).get_hash()
subs = self._ost.search_subtitles([{
'sublanguageid': 'all',
'moviehash': file_hash,
}])
subs = [
sub for sub in subs if not languages or languages[0] == 'all'
or sub.get('LanguageName', '').lower() in languages
or sub.get('SubLanguageID', '').lower() in languages
or sub.get('ISO639', '').lower() in languages
]
for sub in subs:
sub['IsLocal'] = False
self.logger.info('Found {} OpenSubtitles items for {}'.format(
len(subs), file))
return local_subs + subs
finally:
os.chdir(cwd)
# the link to the git repository of the library
# https://github.com/agonzalezro/python-opensubtitles
from pythonopensubtitles.opensubtitles import OpenSubtitles
from pythonopensubtitles.utils import File
ost = OpenSubtitles()
# the username and password of the opensubtitle account
ost.login("username", "password")
# the movie or episode path
f = File(r'path\to\file')
# you can get the subtitles Language Information with the function get_subtitle_language()
# ost.get_subtitle_languages()
# and then set the sublanguageid to the language id
data = ost.search_subtitles([{
'sublanguageid': 'all',
'moviehash': f.get_hash(),
'moviebytesize': f.size
}])
id_subtitle_file = data[0].get('IDSubtitleFile')
# the output directory not set to any location so the subtitles will be downloaded in the
# current location
ost.download_subtitles([id_subtitle_file],
output_directory='',
extension='srt')
def test_hash(self):
f = File(self.temp.name)
assert f.get_hash() == '1e1e1e1e1e200000'
def process_file(video_path):
f = File(video_path)
ext = os.path.splitext(video_path)[1]
for i in range(5):
try:
data = opensubtitles.search_subtitles([{
'sublanguageid': args.language,
'moviehash': f.get_hash(),
'moviebytesize': f.size
}])
break
except ProtocolError as e:
print('Retrying...')
sleep(5)
if len(data) == 0:
print('No subtitles found')
return False
print('Found %d %s subtitles' % (len(data), args.language), end='')
max_download_count = -1
subtitle = None
for s in data:
d = int(s['SubDownloadsCnt'])
if d > max_download_count:
max_download_count = d
subtitle = s
print(' with %d downloads' % max_download_count)
url = subtitle['ZipDownloadLink']
encoding = subtitle['SubEncoding']
imdb_id = 'tt' + subtitle['IDMovieImdb'].rjust(7, '0')
imdb_info = get_imdb_info(imdb_id)
# series
series_info = None
if 'seriesID' in imdb_info:
series_info = get_imdb_info(imdb_info['seriesID'])
episode_info = imdb_info
imdb_info = series_info
title = imdb_info['Title']
year = imdb_info['Year']
if '–' in year:
year = year[:year.find('–')]
rating = imdb_info['imdbRating']
print('Title: %s, score: %s, year: %s' % (title, rating, year))
folder = os.path.join(args.destination,
title + ' (%s, %s)' % (year, rating))
if series_info != None:
folder = os.path.join(
folder, 'Season_' + pad_with_zero(episode_info['Season']))
title = pad_with_zero(
episode_info['Episode']) + '-' + episode_info['Title']
if not os.path.exists(folder):
os.makedirs(folder)
response = urllib.request.urlopen(url)
data = response.read()
zf = zipfile.ZipFile(io.BytesIO(data), 'r')
for name in zf.namelist():
if name.endswith('.srt'):
content = zf.read(name)
with open(os.path.join(folder, title + '.srt'), 'w') as f:
f.write(content.decode(encoding))
break
if args.move:
destination = os.path.join(folder, title + ext)
if os.path.abspath(video_path) != os.path.abspath(destination):
print('Moving video: ' + title + ext)
shutil.move(video_path, destination)
else:
print('Not moving: same location')
return True
# --- title
print()
console.print(
Panel.fit("sub_scan.py",
box=rich.box.ASCII,
style="bold magenta",
border_style="bright_black"))
console.print(Markdown("> Checking file"))
file = sys.argv[-1]
console.print(file) #sys.argv[1] is the file to upload
if not os.path.isfile(file):
raise ("error: could not find file.")
else:
print('> ok.')
f = File(file)
(path, filename) = os.path.split(os.path.abspath(file))
filename_root = filename[:-4]
console.print(Markdown("> Checking OpenSubtitles API access"))
ost = OpenSubtitles()
if ost.login(args.user, args.password) is None:
raise (
"error: cannot login to OpenSubtitles API using the given username/password."
)
else:
print('> ok.')
# best solution: hash size
# if no result => search for title on IMDB (manually)
# then search by IMDB movie id
def com_meta_opensub_search(self, file_name):
f = File(file_name)
return self.opensubtitles_inst.search_subtitles([{'sublanguageid': 'all',
'moviehash': f.get_hash(),
'moviebytesize': f.size}])
movies_features_to_extract = get_movies_status(movies_raw_path,
movies_prep_path)
movies_to_extract = [
k for k, v in movies_features_to_extract.items() if 'subtitle' in v
]
movies_to_extract
# -
# Loop through movie files, save their audio on folder prep
for movie_id in movies_to_extract:
try:
movie_file = movie_file_dict[movie_id]
print(movie_id)
f = File(str(movie_file))
data = ost.search_subtitles([{
'sublanguageid': 'eng',
'imdbid': movie_id[2:],
'moviehash': f.get_hash(),
'moviebytesize': f.size
}])
id_subtitle_file = data[0].get('IDSubtitleFile')
movie_prep_folder = movies_prep_path / f"{movie_id}"
Path(movie_prep_folder).mkdir(parents=True, exist_ok=True)
movie_subtitle_folder = movie_prep_folder / 'subtitle/'
Path(movie_subtitle_folder).mkdir(parents=True, exist_ok=True)
ost.download_subtitles([id_subtitle_file],
video = 'Trance.2013 WEBRip XViD juggs.avi'
#title = 'Dark.City.1998.Directors.Cut.BRRip.H264.AAC.5.1ch.Gopo.srt'
#subtitle = 'Dark.City.1998.Directors.Cut.BRRip.H264.AAC.5.1ch.Gopo.srt'
token = fd.login(Data.username, Data.password)
if not token:
print("Chyba prihlaseni")
sys.exit(1)
print(token)
from pythonopensubtitles.utils import File
f = File(os.path.join(Data.path, Data.video))
h = f.get_hash()
print("Hash: %s" % h)
print("Size: %f" % f.size)
data = fd.search_subtitles([{
'sublanguageid': 'cze',
'moviehash': h,
'moviebytesize': f.size
}])
import urllib2
from StringIO import StringIO
import gzip
for item in data:
def download(path, dir_mode=False):
if not dir_mode:
print("")
print(
colored(
'=============================================================================',
'yellow'))
ost = OpenSubtitles()
ost.login('subspy', 'subspy')
f = File(path)
data = ost.search_subtitles([{
'sublanguageid': 'eng',
'moviehash': f.get_hash(),
'moviebytesize': f.size
}])
if data is None or len(data) == 0:
print(
colored(
"Subtitles could not be found for " + os.path.basename(path),
'red'))
return
best_match = {"index": 0, "ratio": 0}
for current_index, search_result in enumerate(data):
current_ratio = SequenceMatcher(
None, search_result.get('MovieName'),
os.path.basename(path).replace(".", " ")).ratio()
if (current_ratio > best_match['ratio']):
best_match['index'] = current_index
best_match['ratio'] = current_ratio
if (current_index > 10):
break
if (best_match['ratio'] < 0.5):
print(
colored(
"Subtitles could not be found for " + os.path.basename(path),
'red'))
return
print("[ TITLE ] " + colored(
data[best_match['index']].get('MovieName') + " (" +
data[best_match['index']].get('MovieYear') + ")", 'cyan'))
print("[ RATING ] " + colored(
data[best_match['index']].get('MovieImdbRating') +
"/10 on IMDb", 'cyan'))
confidence = round(best_match['ratio'] * 100, 1)
print("Matched with " + str(confidence) + '% confidence')
id_subtitle_file = data[best_match['index']].get('IDSubtitleFile')
existing_subtitle = os.path.join(
os.path.dirname(path),
Path(os.path.basename(path)).stem + ".srt")
abort_flag = False
suffix = ""
if (os.path.isfile(existing_subtitle)):
suffix = ".SubsPY"
print(colored("\nSubtitles already exist for this file.", 'red'))
if globals()['keep_all']:
print(
colored("Keeping both subtitles (added suffix) for ALL FILES.",
"cyan"))
else:
r = input(
colored(
'Overwrite [o], keep existing [k], keep both [b] or keep both for all conflicts [a]? : ',
'magenta'))
if r.lower() == "o":
suffix = ""
print(colored("Overwriting existing Subtitles", "cyan"))
elif r.lower() == "k":
print(colored("Skipping this download.", "cyan"))
abort_flag = True
elif r.lower() == "a":
globals()['keep_all'] = True
print(
colored(
"Keeping both subtitles (added suffix) for ALL FILES.",
"cyan"))
else:
print(
colored(
"Keeping both subtitles (added suffix) for this file.",
"cyan"))
if not abort_flag:
overrides = {
id_subtitle_file:
Path(os.path.basename(path)).stem + suffix + ".srt"
}
status = ost.download_subtitles([id_subtitle_file],
override_filenames=overrides,
output_directory=os.path.dirname(path),
extension='srt')
if status is None:
input(
colored(
"\nSubtitles could not be downloaded for " +
os.path.basename(path), 'red'))
return
print(colored("\nSubtitles downloaded successfully!", "green"))
if not dir_mode:
print(
colored(
'=============================================================================',
'yellow'))
def test_size(self):
assert File(self.temp.name).size == "131072"
from pythonopensubtitles.utils import File
ost = OpenSubtitles()
auth_info = json.load(
open(Path.home() / "Dropbox" / "scripts" / "opensubtitles.json"))
ost.login(auth_info["user"], auth_info["password"])
file_path = Path(sys.argv[1])
file_name = file_path.name
file_dir = file_path.parent
output_dir = file_dir / 'downloaded_subtitles'
output_dir.mkdir(exist_ok=True, parents=True)
f = File(file_path)
data = ost.search_subtitles([{
'sublanguageid': 'eng',
'moviehash': f.get_hash(),
'moviebytesize': f.size
}])
for i, sub in enumerate(data):
id_subtitle_file = sub.get('IDSubtitleFile')
sub_file = file_path.stem + "_" + str(i) + ".srt"
ost.download_subtitles(
[id_subtitle_file],
override_filenames={
id_subtitle_file: sub_file,
import os
import time
EMAIL = "YOUR OpenSubtitles email"
PASSW = "YOUR OpenSubtitles password"
token = ost.login(EMAIL, PASSW)
filename=input("Enter path to file: ")
sub_path = os.path.dirname(filename)
name = '.'.join(filename.split('.')[0:-1])
sname = name+'.srt'
zname = name+'.zip'
f = File(filename)
hashh = f.get_hash()
size = f.size
print(hashh)
print(size)
data = ost.search_subtitles([{'sublanguageid': 'all', 'moviehash': hashh, 'moviebytesize': size}])
assert type(data)!=None
link = data[0]['ZipDownloadLink']
print(link)
file = open(os.path.join(sub_path,zname),'wb')
s = requests.get(link)
for chunk in s.iter_content(100000):
if chunk:
file.write(chunk)
def processOS(filename, detay):
from pythonopensubtitles.opensubtitles import OpenSubtitles
from pythonopensubtitles.utils import File
trsubtitlelist = list()
ensubtitlelist = list()
ost = OpenSubtitles()
ost.login('katates', 'hijuhiji')
f = File(filename)
data = ost.search_subtitles([{
'imdbid': detay["imdb"],
'season': detay["season"],
'episode': detay["episode"],
'sublanguageid': 'tur,eng',
'tag': detay["group"] + "," + detay["vers"]
}])
for sub in data:
realep = detay["episode"]
name = "OS " + detay["name"]
subhref = sub["SubDownloadLink"]
sublang = sub["LanguageName"].replace("English",
"en").replace("Turkish", "tr")
subtrns = sub["SubTranslator"]
subdown = int(sub["SubDownloadsCnt"])
subep = sub["SeriesEpisode"]
season = sub["SeriesSeason"]
subgr = sub["InfoReleaseGroup"].lower()
subvers = sub["InfoFormat"].lower()
if int(realep) < 10:
realep = realep[1:]
if subep == realep:
if "tr" == sublang:
if detay["group"] in subgr:
if detay[
"vers"] in subvers: # in because web can be web-dl or webrip
trsubtitlelist.append([
name, subhref, sublang, subtrns, subdown, subep,
season, subgr, subvers, 100
]) # Both matches #1
break
else:
trsubtitlelist.append([
name, subhref, sublang, subtrns, subdown, subep,
season, subgr, subvers, 80
]) # Only Group matches #3
else:
if detay["vers"] in subvers:
trsubtitlelist.append([
name, subhref, sublang, subtrns, subdown, subep,
season, subgr, subvers, 90
]) # Version matches #2
else:
trsubtitlelist.append([
name, subhref, sublang, subtrns, subdown, subep,
season, subgr, subvers, 0
]) # Nothing matches #4
else:
if detay["group"] in subgr:
if detay[
"vers"] in subvers: # in because web can be web-dl or webrip
ensubtitlelist.append([
name, subhref, sublang, subtrns, subdown, subep,
season, subgr, subvers, 100
]) # Both matches #1
else:
ensubtitlelist.append([
name, subhref, sublang, subtrns, subdown, subep,
season, subgr, subvers, 80
]) # Only Group matches #3
else:
if detay["vers"] in subvers:
ensubtitlelist.append([
name, subhref, sublang, subtrns, subdown, subep,
season, subgr, subvers, 90
]) # Version matches #2
else:
ensubtitlelist.append([
name, subhref, sublang, subtrns, subdown, subep,
season, subgr, subvers, 0
]) # Nothing matches #4
if len(trsubtitlelist) > 0:
subtitlelistOS = sorted(trsubtitlelist,
key=lambda tup: (tup[-1], tup[4]),
reverse=True)
else:
subtitlelistOS = sorted(ensubtitlelist,
key=lambda tup: (tup[-1], tup[4]),
reverse=True)
return subtitlelistOS
