def imdbGetMovie(imdb_id):
cached = ImdbCache.objects.filter(imdb_id=get_imdb_movie_id(imdb_id))
if cached.__len__() > 0 and cached[0].is_full:
return cPickle.loads(base64.b64decode(cached[0].content))
else:
imdb = IMDb()
m = imdb.get_movie(imdb_id)
content = base64.b64encode(cPickle.dumps(m, 2))
c = ImdbCache(imdb_id=get_imdb_id(m), content=content, is_full=True)
c.save()
return m
def imdbGetMovie(imdb_id): cached = ImdbCache.objects.filter(imdb_id = get_imdb_movie_id(imdb_id)) if cached.__len__() > 0 and cached[0].is_full: return cPickle.loads(base64.b64decode(cached[0].content)) else: imdb = IMDb() m = imdb.get_movie(imdb_id) content = base64.b64encode(cPickle.dumps(m, 2)) c = ImdbCache(imdb_id = get_imdb_id(m), content = content, is_full = True) c.save() return m
def corrigir_titulo_serie():
print('corrigir_titulo_serie Iniciado')
repetir = False
for r in db.registros.find({
'titulo': {
'$exists': False
},
'imdb': {
'$regex': '.* .*'
}
}).limit(1):
# print(r)
try:
im = str(r['imdb']).strip()[2:r['imdb'].index(" ")]
imdb = IMDb()
print(int(im))
movie = imdb.get_movie(int(im))
movie.fetch()
print(movie.__dict__['title'])
print(movie.__dict__['year'])
print('.*' + str(im) + '.*')
db.registros.update_many(
{'imdb': {
'$regex': '.*' + str(im) + '.*'
}}, {
"$set": {
"titulo": movie.__dict__['title'],
"ano": movie.__dict__['year']
}
})
print('Sem Título: ', im, movie.__dict__['title'])
repetir = True
except:
im = str(r['imdb']).strip()[2:r['imdb'].index(" ")]
db.registros.update_many(
{'imdb': {
'$regex': '.*' + str(im) + '.*'
}}, {"$set": {
"titulo": 'Título não encontrado',
"ano": 0
}})
repetir = True
print('Erro Sem Título: ', im)
if repetir:
corrigir_titulo_serie()
def corrigir_titulo_filme():
print('corrigir_titulo_filme: Iniciado')
repetir = False
for r in db.registros.find({
'titulo': {
'$exists': False
},
'imdb': {
'$not': {
'$regex': '.* .*'
}
}
}).limit(20):
# print(r)
try:
im = str(r['imdb']).strip()[2:]
imdb = IMDb()
print(int(im))
movie = imdb.get_movie(int(im))
movie.fetch()
print(movie.__dict__['title'])
print(movie.__dict__['year'])
db.registros.update_one({"_id": r['_id']}, {
"$set": {
"titulo": movie.__dict__['title'],
"ano": movie.__dict__['year']
}
})
print('Sem Título: ', im, movie.__dict__['title'])
repetir = True
except:
db.registros.update_one(
{"_id": r['_id']},
{"$set": {
"titulo": 'Título não encontrado',
"ano": 0
}})
repetir = True
print('Erro Sem Título: ', im)
if repetir:
corrigir_titulo_filme()
def _movies(self):
movies_dat = os.path.join(self.dataset_path, 'movies.dat')
with open(movies_dat) as f:
for l in f:
movie_id, title, tags = l.split("::")
print("Loading movie `%s`" % title)
matches = re.match(r'([^\(]+?)((\([^\(]+\)) (\([^\(]+\)))',
title)
if matches:
title = "%s %s" % (matches.groups()[0],
matches.groups()[-1])
released_date = title.split()[-1][1:-1]
self.movies[movie_id] = {
'title': title,
'tags': tags.split("|"),
'released_date': released_date
}
try:
movie = imdb.get_movie(title)
for k, v in movie.items():
self.movies[movie_id][k] = v
except:
print("Error `%s`" % title)
print("Type the TV Show or Movie wanted: ")
name = input('>')
search = imdb.search_movie(name)
count = 1
print("The top five searhed items are:")
for index in search[0:5]:
print(str(count) + ". " + index['title'] + " (" + str(index['year']) + ")")
count += 1
print("Please select the one you want: [1-5]")
selection = input('>')
select_id = search[int(selection) - 1].getID()
item = imdb.get_movie(select_id)
#Add check for TVshow/movie and a way to get back to previous search
imdb.update(item, 'episodes')
item_basic_info = {
"title": item['title'],
"type": item['kind'],
"year": item['year'],
"nr_seasons": len(item['episodes'])
}
print("The selected item is: ")
print(item_basic_info['title'])
print(item_basic_info['year'])
print(item_basic_info['type'])
movie = currentSheet.cell(x, movieTitle).value try: #(imdb.get_movie(mov[0].movieID)["genre"]) #Searches for the movie on OMDB <<<<<<< HEAD baseInfo = Imdb().search_for_title(movie) search = baseInfo[0]['imdb_id'] genre = Imdb().get_title_genres(search)["genres"] runtime = (Imdb().get_title(search))["base"]["runningTimeInMinutes"] #Updates cells with genre and runtime currentSheet.update_cell(x, gColumn, comma.join(genre)) currentSheet.update_cell(x, rColumn, str(runtime) + ' min') ======= baseInfo = imdb.search_movie(movie)[0].movieID search = imdb.get_movie(baseInfo) #Updates cells with genre and runtime currentSheet.update_cell(x, gColumn, ", ".join(search["genres"])) currentSheet.update_cell(x, rColumn, str(int(search["runtimes"][0])) + ' min') >>>>>>> testing except Exception as c: print (str(c) + " at row " + str(x)) #if it f***s up it owns up to it currentSheet.update_cell(x, gColumn, 'f****d up') currentSheet.update_cell(x, rColumn, '') #currentSheet.update_cell(x, tColumn, '') def time(gsheet, sheet): currentSheet = gsheet.worksheet(sheet) columnTitles = currentSheet.row_values(1)
#Film suchen
filme_id = imdb.search_movie(filme)
if filme_id == []:
kategorie = "N/A"
jahr = "N/A"
besetzung = "N/A"
bewertung = "N/A"
laufzeit = "N/A"
typ = "N/A"
direktor = "N/A"
beschreibung = "N/A"
else:
#ID bekommen
filme_id = filme_id[0].movieID
#Werte holen
film = imdb.get_movie(filme_id)
#Genre
try:
kategorie = str(film['genres'])
except:
kategorie = "N/A"
#Jahr
try:
jahr = str(film['year'])
except:
jahr = "N/A"
#Besetzung
try:
besetzung = str(film['cast'])
except:
besetzung = "N/A"
def search(title: str):
# searches imdb for the first 3 most likely results and returns a list of processed info dictionaries
search = imdb.search_movie(title)[:3]
search_results = [imdb.get_movie(film.movieID) for film in search]
fixed_results = []
# mtm fields
genres = db.get_all('Genres')
directors = db.get_all('Directors')
actors = db.get_all('Actors')
studios = db.get_all('Studios')
# convert the dicts gotten from scraper into readable dicts we can use
for film in search_results:
info = {
'title': film.get('title'),
'alt_title': '',
'animated': True if 'Animation' in film.get('genres') else False,
'year': str(film.get('year')),
'genres': [g for g in film.get('genres') if g in genres],
'plot': film.get('plot outline')
}
# Countries we can only have one entry for this field and there can be more than one country in film.get, so we pick the first match
if film.get('countries'):
for country in film.get('countries'):
if country in db.get_all('Countries'):
info['country'] = country
break
if film.get('cast'):
info['actors'] = [
a for a in actors
if a in [c['name'] for c in film.get('cast')]
]
if film.get('languages'): # might return None
info['language'] = [
lang for lang in film.get('languages')
if lang in db.get_all('Languages')
]
# convert media types
if 'Documentary' in film.get('genres'):
info['media_type'] = 'Documentary'
elif 'movie' == film.get('kind'):
info['media_type'] = 'Movie'
elif 'tv series' == film.get('kind'):
info['media_type'] = 'TV Series'
else:
info['media_type'] = ''
# directors
if film.get('director'): # film.get('director') could return None
for director in film.get('director'):
if director['name'] in directors:
info['director'] = director['name']
break
if 'director' not in info.keys():
info[
'director'] = '' # make sure it's at least a blank string because we need it to display to create window
# studio
if film.get('production companies'):
for studio in film.get('production companies'):
if studio['name'] in studios:
info['studio'] = studio['name']
break
fixed_results.append(info)
return fixed_results