def main():
api = IMDB()
# for movie in my_api.get_movies_near_you():
# print movie
query = raw_input("Search: ")
print len(api.search_movie(query))
def main(data_path, output_path):
start_time = time.time()
db = IMDB()
data = db.get_data()
train_sets, val_sets = split_imdb_data(data, 0.3)
# convert_to_tfrecord(train_sets, data_path, output_path, 'train')
convert_to_tfrecord(val_sets, data_path, output_path, 'val')
duration = time.time() - start_time
print("Running %.3f sec All done!" % duration)
def selective_search_roidb(self, gt_roidb, append_gt=False):
"""
get selective search roidb and ground truth roidb
:param gt_roidb: ground truth roidb
:param append_gt: append ground truth
:return: roidb of selective search
"""
cache_file = os.path.join(self.cache_path, self.name + '_ss_roidb.pkl')
if os.path.exists(cache_file):
with open(cache_file, 'rb') as fid:
roidb = cPickle.load(fid)
print '{} ss roidb loaded from {}'.format(self.name, cache_file)
return roidb
if append_gt:
print 'appending ground truth annotations'
ss_roidb = self.load_selective_search_roidb(gt_roidb)
roidb = IMDB.merge_roidbs(gt_roidb, ss_roidb)
else:
roidb = self.load_selective_search_roidb(gt_roidb)
with open(cache_file, 'wb') as fid:
cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
print 'wrote ss roidb to {}'.format(cache_file)
return roidb
def selective_search_roidb(self, gt_roidb, append_gt=False):
"""
get selective search roidb and ground truth roidb
:param gt_roidb: ground truth roidb
:param append_gt: append ground truth
:return: roidb of selective search
"""
cache_file = os.path.join(self.cache_path, self.name + '_ss_roidb.pkl')
if os.path.exists(cache_file):
with open(cache_file, 'rb') as fid:
roidb = cPickle.load(fid)
print '{} ss roidb loaded from {}'.format(self.name, cache_file)
return roidb
if append_gt:
print 'appending ground truth annotations'
ss_roidb = self.load_selective_search_roidb(gt_roidb)
roidb = IMDB.merge_roidbs(gt_roidb, ss_roidb)
else:
roidb = self.load_selective_search_roidb(gt_roidb)
with open(cache_file, 'wb') as fid:
cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
print 'wrote ss roidb to {}'.format(cache_file)
return roidb
def main(ARGS, device):
"""
Prepares the datasets for training, and optional, validation and
testing. Then, initializes the VAE model and runs the training (/validation)
process for a given number of epochs.
"""
data_splits = ['train', 'val']
datasets = {
split: IMDB(ARGS.data_dir, split, ARGS.max_sequence_length,
ARGS.min_word_occ, ARGS.create_data)
for split in data_splits
}
pretrained_embeddings = datasets['train'].get_pretrained_embeddings(
ARGS.embed_dim).to(device)
model = VAE(
datasets['train'].vocab_size,
ARGS.batch_size,
device,
pretrained_embeddings=pretrained_embeddings,
trainset=datasets['train'],
max_sequence_length=ARGS.max_sequence_length,
lstm_dim=ARGS.lstm_dim,
z_dim=ARGS.z_dim,
embed_dim=ARGS.embed_dim,
n_lstm_layers=ARGS.n_lstm_layers,
kl_anneal_type=ARGS.kl_anneal_type,
kl_anneal_x0=ARGS.kl_anneal_x0,
kl_anneal_k=ARGS.kl_anneal_k,
kl_fbits_lambda=ARGS.kl_fbits_lambda,
word_keep_rate=ARGS.word_keep_rate,
)
model.to(device)
optimizer = torch.optim.Adam(model.parameters())
print('Starting training process...')
amount_of_files = len(os.listdir("trained_models"))
for epoch in range(ARGS.epochs):
elbos = run_epoch(model, datasets, device, optimizer)
train_elbo, val_elbo = elbos
print(
f"[Epoch {epoch} train elbo: {train_elbo}, val_elbo: {val_elbo}]")
# Perform inference on the trained model
with torch.no_grad():
model.eval()
samples = model.inference()
print(*idx2word(samples,
i2w=datasets['train'].i2w,
pad_idx=datasets['train'].pad_idx),
sep='\n')
model.save(f"trained_models/{amount_of_files + 1}.model")
def rpn_roidb(self, gt_roidb):
"""
get rpn roidb and ground truth roidb
:param gt_roidb: ground truth roidb
:return: roidb of rpn (ground truth included)
"""
if self.image_set != 'test':
rpn_roidb = self.load_rpn_roidb(gt_roidb)
roidb = IMDB.merge_roidbs(gt_roidb, rpn_roidb)
else:
print 'rpn database need not be used in test'
roidb = self.load_rpn_roidb(gt_roidb)
return roidb
def rpn_roidb(self, gt_roidb):
"""
get rpn roidb and ground truth roidb
:param gt_roidb: ground truth roidb
:return: roidb of rpn (ground truth included)
"""
if self.image_set != 'test':
rpn_roidb = self.load_rpn_roidb(gt_roidb)
roidb = IMDB.merge_roidbs(gt_roidb, rpn_roidb)
else:
print 'rpn database need not be used in test'
roidb = self.load_rpn_roidb(gt_roidb)
return roidb
def rpn_roidb(self, gt_roidb, append_gt=False):
"""
get rpn roidb and ground truth roidb
:param gt_roidb: ground truth roidb
:param append_gt: append ground truth
:return: roidb of rpn
"""
if append_gt:
print 'appending ground truth annotations'
rpn_roidb = self.load_rpn_roidb(gt_roidb)
roidb = IMDB.merge_roidbs(gt_roidb, rpn_roidb)
else:
roidb = self.load_rpn_roidb(gt_roidb)
return roidb
def rpn_roidb(self, gt_roidb, append_gt=False):
"""
get rpn roidb and ground truth roidb
:param gt_roidb: ground truth roidb
:param append_gt: append ground truth
:return: roidb of rpn
"""
if append_gt:
print 'appending ground truth annotations'
rpn_roidb = self.load_rpn_roidb(gt_roidb)
roidb = IMDB.merge_roidbs(gt_roidb, rpn_roidb)
else:
roidb = self.load_rpn_roidb(gt_roidb)
return roidb
def selective_search_roidb(self, gt_roidb):
"""
get selective search roidb and ground truth roidb
:param gt_roidb: ground truth roidb
:return: roidb of selective search (ground truth included)
"""
cache_file = os.path.join(self.cache_path, self.name + '_ss_roidb.pkl')
if os.path.exists(cache_file):
with open(cache_file, 'rb') as fid:
roidb = cPickle.load(fid)
print '{} ss roidb loaded from {}'.format(self.name, cache_file)
return roidb
if self.image_set != 'test':
ss_roidb = self.load_selective_search_roidb(gt_roidb)
roidb = IMDB.merge_roidbs(gt_roidb, ss_roidb)
else:
roidb = self.load_selective_search_roidb(None)
with open(cache_file, 'wb') as fid:
cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
print 'wrote ss roidb to {}'.format(cache_file)
return roidb
def selective_search_roidb(self, gt_roidb):
"""
get selective search roidb and ground truth roidb
:param gt_roidb: ground truth roidb
:return: roidb of selective search (ground truth included)
"""
cache_file = os.path.join(self.cache_path, self.name + '_ss_roidb.pkl')
if os.path.exists(cache_file):
with open(cache_file, 'rb') as fid:
roidb = cPickle.load(fid)
print '{} ss roidb loaded from {}'.format(self.name, cache_file)
return roidb
if self.image_set != 'test':
ss_roidb = self.load_selective_search_roidb(gt_roidb)
roidb = IMDB.merge_roidbs(gt_roidb, ss_roidb)
else:
roidb = self.load_selective_search_roidb(None)
with open(cache_file, 'wb') as fid:
cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
print 'wrote ss roidb to {}'.format(cache_file)
return roidb
help='type of recurrent layer to use (rnn or birnn)')
parser.set_defaults()
args = parser.parse_args()
# these hyperparameters are from the paper
args.batch_size = 128
time_steps = 128
hidden_size = 10
gradient_clip_value = 15
embed_size = 128
vocab_size = 20000
pad_idx = 0
# download IMDB
imdb_dataset = IMDB(path=args.data_dir,
sentence_length=time_steps,
pad_idx=pad_idx)
imdb_data = imdb_dataset.load_data()
train_set = ArrayIterator(imdb_data['train'],
batch_size=args.batch_size,
total_iterations=args.num_iterations)
valid_set = ArrayIterator(imdb_data['valid'], batch_size=args.batch_size)
inputs = train_set.make_placeholders()
ax.Y.length = imdb_dataset.nclass
# weight initialization
init = UniformInit(low=-0.08, high=0.08)
if args.layer_type == "rnn":
def search_query(self):
query = raw_input('\nEnter the torrent to be searched : \t').strip().lower()
if re.match(r'quit\b', query, flags=re.IGNORECASE):
print '\nGoodbye...'
sys.exit(0)
elif re.match(r'search\b', query, flags=re.IGNORECASE):
title_head = query[7:].strip()
try:
Download_Torrent().search_begins_kat(name=title_head, boolean=True)
self.search_query()
except:
print '\nSorry torrent can not be downloaded.\nPlease Try again'
self.search_query()
elif re.match(r'add\b', query, flags=re.IGNORECASE):
title_head = query[4:].strip()
title_exist = False
if os.path.isfile(os.path.expanduser(self.file_path)):
file = open(os.path.expanduser(self.file_path), 'r')
lines = file.readlines()
file.close()
for line in lines:
if line.__contains__(title_head):
title_exist = True
if title_exist:
print '\n' + 'You already follow ' + title_head.upper()
else:
file = open(os.path.expanduser(self.file_path), 'a')
season, age = IMDB().get_next_episode(title=title_head)
data = title_head + '/' + str(season) + '/' + str(age)
file.write(data + '\n')
file.close()
print '\n' + title_head.upper() + ' has been added.'
if age is not None:
print '\nThe new episode will air on ' + age
print '\n' + 'New torrent will be downloaded automatically.'
else:
print '\nThe new episode air date is not out yet.'
print '\nNew torrent will be downloaded when the air date arrives.'
else:
file = open(os.path.expanduser(self.file_path), 'a')
season, age = IMDB().get_next_episode(title=title_head)
data = title_head + '/' + str(season) + '/' + str(age)
file.write(data + '\n')
file.close()
print '\n' + title_head.upper() + ' has been added.'
if age is not None:
print '\nThe new episode will air on ' + age
print '\n' + 'New torrent will be downloaded automatically.'
else:
print '\nThe new episode air date is not out yet.'
print '\nNew torrent will be downloaded when the air date arrives.'
self.search_query()
elif re.match(r'remove\b', query, flags=re.IGNORECASE):
title_head = query[7:].strip()
if os.path.isfile(os.path.expanduser(self.file_path)):
file = open(os.path.expanduser(self.file_path), 'r')
lines = file.readlines()
file.close()
file = open(os.path.expanduser(self.file_path), 'w')
for line in lines:
if not line.__contains__(title_head):
file.write(line)
file.write("\n")
file.close()
print 'Removed ' + title_head.upper()
else:
print '\nYou are not following ' + title_head.upper()
print '\nUse the commnad ADD <title> to start following'
self.search_query()
elif re.match(r'info\b', query, flags=re.IGNORECASE):
print '\nGetting information...'
i = IMDB()
title_head = query[5:].strip()
title, season, age = i.get_latest_episode(title=title_head)
print '\nCurrent Episode Details'
if age is None:
print '\n Information not available yet'
else:
print '\n Title : ' + str(title).upper()
print '\n Episode : ' + str(season).upper()
print '\n Air Date : ' + age
season, age = i.get_next_episode(title=title_head)
print '\nNext Episode details : '
if age is None:
print '\n Information not available yet'
else:
print '\n Episode : ' + str(season).upper()
print '\n Air Date : ' + age
self.search_query()
elif re.match(r'print\b', query, flags=re.IGNORECASE):
if os.path.isfile(os.path.expanduser(self.file_path)):
file = open(os.path.expanduser(self.file_path), 'r')
lines = file.readlines()
file.close()
for line in lines:
title = str(line).split('/')[0].strip()
print title
else:
print '\nYou are not following anything'
print '\nUse the commnad ADD <title> to start following'
self.search_query()
elif re.match(r'top\b', query, flags=re.IGNORECASE):
print '\nFetching data...'
title_head = query[4:].strip()
result = IMDB_TOP().top_items(type=title_head)
if not result:
print '\nSorry the following keyword is not present.\nPlease try again'
self.search_query()
else:
try:
Download_Torrent().search_begins_kat(name=query, boolean=True)
self.search_query()
except:
print '\nSorry torrent can not be downloaded.\nPlease Try again'
self.search_query()
blurayURL = [
"https://www.blu-ray.com/movies/A-Star-Is-Born-Blu-ray/217109/"
]
config = ConfigParser()
config.read("conf.txt")
bdinfoPath = config["user_settings"]["bdinfo"]
tempDir = config["user_settings"]["output_dir"]
for url in blurayURL:
blurayObj = Bluray(url)
blurayObj.build()
blurayObj.printAttrs()
directory = Folder()
directory.build(tempDir, blurayObj.title)
imdbObj = IMDB()
imdbObj.build(blurayObj.imdbLink, blurayObj.title, blurayObj.year,
blurayObj.runtime)
imdbObj.printAttrs()
tmdbObj = MovieDB()
tmdbObj.build(blurayObj.imdbLink, directory.screenDir)
tmdbObj.printAttrs()
if args.bdinfo:
bdiObj = BDInfo()
bdiObj.build(args.bdinfo, directory.movieDir)
print(bdiObj.prettyBDInfo)
# templateObj = Template(url, blurayObj.title, blurayObj.year, etc.)
""" Created on Wed Sep 29 10:06:27 2021 ContentAI @author: Herais """ #%% Import Libraries import os from selenium import webdriver from selenium.webdriver.chrome.options import Options from selenium.webdriver.support.wait import WebDriverWait from selenium.webdriver.common.by import By from selenium.webdriver.common.action_chains import ActionChains from selenium.webdriver.remote.command import Command #%% instantiate imdb from imdb import IMDB imdb = IMDB() #%% df_mpm = imdb.get_most_popular_movies() #%% element_table = imdb.driver.find_element(By.XPATH, "//table") #%% elements_td = element_table.find_elements(By.CLASS_NAME, "posterColumn") #%% html = imdb.driver.page_source #%% #%% Get movie pages from table path_wip = 'wip' element_table = imdb.driver.find_element(By.XPATH, "//table")
