Exemple #1
0
    def stats(self):
        query_directors = select(['persons.id', func.count('roles.person_id').label('count')],
                       from_obj=['persons', 'roles'],
                       whereclause="roles.person_id = persons.id AND roles.role_type = 'director'",
                       group_by=['persons.id'], order_by='count desc', limit=10)
        query_actors = select(['persons.id', func.count('roles.person_id').label('count')],
                       from_obj=['persons', 'roles'],
                       whereclause="roles.person_id = persons.id AND roles.role_type = 'cast'",
                       group_by=['persons.id'], order_by='count desc', limit=10)                       
        
        top_directors = DBSession.query(Person, 'count').from_statement(query_directors).all()
        top_actors = DBSession.query(Person, 'count').from_statement(query_actors).all()        
    
        ia = IMDb()

        top250_ids = [x.movieID for x in ia.get_top250_movies()]
        bottom100_ids = [x.movieID for x in ia.get_bottom100_movies()]
        
        top250_count = DBSession.query(Movie).filter(Movie.id.in_(top250_ids)).count()
        bottom100_count = DBSession.query(Movie).filter(Movie.id.in_(bottom100_ids)).count()
        total_count = DBSession.query(Movie).count()
        
        total_runtime = 1
        
        return {'top250_count': top250_count,
                'bottom100_count': bottom100_count,
                'total_count': total_count,
                'total_runtime' : total_runtime,
                'top_directors': top_directors,
                'top_actors': top_actors}
Exemple #2
0
class ImdbApi():

    def __init__(self):
        self.ia = IMDb()

    def get_top_movies(self):
        return self.ia.get_top250_movies()

    def get_bottom_movies(self):
        return self.ia.get_bottom100_movies()

    def get_movies_id(self, movies):
        return [i.getID() for i in movies]

    def list_of_filtered_movie_information(self, movies_id):
        l = []
        for i in movies_id[:10]:
            di = {}
            film = self.ia.get_movie_main(i)
            di['rating'] = [i[1] for i in film['data'].items() if i[0] == 'rating']
            di['year'] = [i[1] for i in film['data'].items() if i[0] == 'year']
            di['name'] = [i[1] for i in film['data'].items() if i[0] == 'title']
            di['director'] = [i[1] for i in film['data'].items() if i[0] == 'director'][0][0]
            di['index'] = random.randint(0, 9)
            l.append(di)
        return l
Exemple #3
0
def get_bottom_movies(args):
    connection = IMDb()
    items = connection.get_bottom100_movies()
    if args.first:
        connection.update(items[0])
        print(items[0].summary())
    else:
        list_ranking(items, n=args.n)
Exemple #4
0
def get_bottom_movies(args):
    connection = IMDb()
    items = connection.get_bottom100_movies()
    if args.first:
        connection.update(items[0])
        print(items[0].summary())
    else:
        list_ranking(items, n=args.n)
person = db.get_person(actor_id)
bio = db.get_person_biography(actor_id)

name = person['name']
bdate = person['birth date']
height = person['height']
trivia = person['trivia']
titleRefs = bio['titlesRefs']

print(f'name: {name}')
print(f'birth date: {bdate}')
print(f'height: {height}')
print(f'trivia: {trivia[0]}')

titleRefs = ', '.join(map(str, titleRefs))
print(f'bio title refs: {titleRefs}')

print('---------------------------------------')
# 4) Fetch top/bottom 10 movies
top = db.get_top250_movies()
bottom = db.get_bottom100_movies()

print('Top 10 movies are:')
for movie in top[0:9]:
    print(movie)
print()

print('Bottom 10 movies are:')
for movie in bottom[0:9]:
    print(movie)
Exemple #6
0
        for searches in search_return:
            if re.search(
                    movie_title, searches
            ):  # from the api's searched movie list, find the one that matches our title exactly
                movie_and_ids.append(searches)

movie_ids = []
movie_names = []

for info in movie_and_ids:  # from our matched result, we only need the title and id number
    movie_names.append(re.sub("_", "", (re.search(r"_.*_", info)).group()))
    movie_ids.append(re.search("\d{7}", info).group())

# getting imdb's own movies lists
top_250 = ia.get_top250_movies()
bottom_100 = ia.get_bottom100_movies()

# adding the titles and ids from imdb's list to our scraped list above
for x in top_250:
    if x.movieID not in movie_ids:
        movie_ids.append(x.movieID)
        movie_names.append(x['title'])

for x in bottom_100:
    if x.movieID not in movie_ids:
        movie_ids.append(x.movieID)
        movie_names.append(x['title'])

#creating a dictionary of our database
data_base = dict(zip(movie_names, movie_ids))
Exemple #7
0
import googleapiclient.errors
from src.common.Database import Database
from src.model.Movie import Movie
from src.model.User import User
import requests
from bs4 import BeautifulSoup
from werkzeug.utils import redirect
import random
from flask_share import Share

movielist = []
moviesDB = IMDb()
search = moviesDB.get_top250_movies()
search1 = moviesDB.get_top250_indian_movies()
search2 = moviesDB.get_popular100_tv()
search3 = moviesDB.get_bottom100_movies()
for m in search1:
    movielist.append(m.getID())

for i in movielist:
    movieurl = "https://www.imdb.com/title/tt" + i + "/"
    r = requests.get(url=movieurl)
    soup = BeautifulSoup(r.text, 'html.parser')
    try:
        title = soup.find('title')
        ratingValue = soup.find("span", {"itemprop": "ratingValue"})
        image = soup.find("div", {"class": "poster"}).find("img")["src"]
        link = soup.find("div", {"class": "slate"}).find("a")["href"]
        genre = soup.find("div", {"class": "subtext"}).find("a")
        if link != None and image != None and title != None and ratingValue != None:
            dm = Movie(title.string, "bollywood", genre.text,