def get_movie_from_imdb(title):
id = movieLink.get(title)
return IMDb().get_movie(id)
def update(self, text):
if self.search:
self.fill((255, 255, 255))
im = IMDb()
series = im.search_movie(text)[0]
# Get title
self.title = series["long imdb title"]
# Get cover image
cover = series["full-size cover url"]
r = requests.get(cover)
img = Image.open(io.BytesIO(r.content))
img = img.resize((256, 384))
self.cover_img = pygame.image.fromstring(img.tobytes(), img.size,
img.mode)
self.overall_rating = im.get_movie(series.getID())["rating"]
if series["kind"] == "tv series":
im.update(series, "episodes")
num_of_series = sorted(series["episodes"].keys())
ratings = []
# Get each episodes rating
for s in num_of_series:
num_of_episodes = sorted(series["episodes"][s].keys())
e_ratings = []
for e in num_of_episodes:
e_ratings.append(series["episodes"][s][e].get(
"rating", 0))
ratings.append(e_ratings)
# Get box sizes
max_episodes = max(ratings, key=len)
box_width = (self.w - 30) / len(max_episodes)
box_height = (self.h - 30) / len(ratings)
# Draw axis labels
self.blit(self.font.render("Episodes", True, (0, 0, 0)),
((self.w // 2) - (font.size("Episodes")[0] // 2), 0))
letter_size = font.size("S")
vert_start = (self.h // 2) - ((letter_size[1] * 6) // 2)
for pos, letter in enumerate("Series"):
self.blit(self.font.render(letter, True, (0, 0, 0)),
(0, vert_start + (letter_size[1] * pos)))
# Get colour gradient
colours = list(Color("red").range_to(Color("green"), 50))
colours[:0] = [Color("red")] * 50
# Insert blank episode spaces
for s in ratings:
if len(s) < len(max_episodes):
s.extend([None] * (len(max_episodes) - len(s)))
# Draw episode text
for en in range(len(max_episodes)):
e_txt = self.font.render(str(en + 1), True, (0, 0, 0))
et_pos = ((en * box_width) + 30 + (box_width // 2), 15)
self.blit(e_txt, et_pos)
# Series loop
for s_pos, s in enumerate(ratings):
# Draw series text
s_txt = self.font.render(str(s_pos + 1), True, (0, 0, 0))
st_pos = (15,
(s_pos * box_height) + 30 + (box_height // 2))
self.blit(s_txt, st_pos)
# Episode loop
for e_pos, e in enumerate(s):
e_rect = pygame.Rect((e_pos * box_width) + 30,
(s_pos * box_height) + 30,
box_width, box_height)
if e is not None:
# Draw episode rect
c = list(
map(
lambda x: x * 255,
colours[int(e * 10) -
(1 if e > 0 else 0)].rgb))
pygame.draw.rect(self, c, e_rect)
# Draw rating text
r_txt = self.font.render(
str(e)[:3], True, (0, 0, 0))
r_size = font.size(str(e)[:3])
r_pos = (e_rect.centerx - (r_size[0] // 2),
e_rect.centery - (r_size[1] // 2))
self.blit(r_txt, r_pos)
pygame.draw.rect(self, (0, 0, 0), e_rect, 2)
else:
self.blit(font.render("NOT A SERIES", True, (0, 0, 0)),
(self.w // 2, self.h // 2))
self.search = False
def crawl_by_id(self, movie_id=None, driver=None):
driver = self.driver
ia = IMDb()
try:
x = ia.get_movie(movie_id[2:])
except:
return
# find popularity
popularity = find_pop(movie_id=movie_id, driver=driver)
try:
box_office = find_box_office(movie_id=movie_id, driver=driver)
except:
box_office = None
# find budget
try:
budget = find_budget(movie_id=movie_id, driver=driver)
if budget == box_office:
budget = None
except:
budget = None
# find title
try:
title = x['title'] # title
except:
title = None
# find cast
try:
cast_list = x['cast'] # cast_id
except:
cast_info = [None]
else:
cast_info = []
for i in range(len(cast_list)):
d = {'id': cast_list[i].getID(), 'name': cast_list[i]['name']}
cast_info.append(d)
# find run time
try:
run_time = x['runtimes'] # run time
except:
run_time = None
# find country
try:
country = x['country codes'] # country codes
except:
country = None
# find language
try:
language = x['language codes'] # language
except:
language = None
# find production companies
try:
company_list = x['production companies'] # production companies
except:
company = None
else:
product_company = []
for i in range(len(company_list)):
d = {
'id': company_list[i].getID(),
'name': company_list[i]['name']
}
product_company.append(d)
# find genres
try:
genres = x['genres']
except:
genres = None
# find rating
try:
rating = x['rating']
except:
rating = None
# find votes
try:
votes = x['votes']
except:
votes = None
# get crew members
try:
data_list = list(x.data.keys())
crew_list = list()
except:
crew_list = None
else:
for i in range(len(data_list)):
if 'ors' in data_list[i] or 'ers' in data_list[
i] or 'depart' in data_list[i]:
crew_list.append(data_list[i])
if 'distributors' in crew_list:
crew_list.remove('distributors')
crew_info = []
for i in range(0, len(crew_list)):
crew_temp = x[crew_list[i]]
for n in range(len(crew_temp)):
try:
id_temp = crew_temp[n].getID()
name_temp = crew_temp[n]['name']
except:
id_temp = None
name_temp = None
else:
d = {'id': id_temp, 'name': name_temp}
crew_info.append(d)
# get release date
try:
date_info = x['original air date']
date = get_date(date_info=date_info)
except:
date = "01/01/2019"
# driver.close()
dataset = {
'budget': [budget],
'genres': [genres],
'imdb_id': [movie_id],
'spocken_languages': [language],
'original_title': [title],
'popularity': [popularity],
'production_companies': [product_company],
'production_countries': [country],
'release_date': [date],
'runtime': run_time,
'cast': [cast_info],
'crew': [crew_info],
}
# 'wb_info':[box_office]}
df_meta = pd.DataFrame(dataset)
# df_meta.to_csv('./get_meta/meta_info.csv', columns=df_meta.columns, index=False)
return df_meta
from __future__ import division
import threading
import os
from imdb import IMDb
import xml.etree.ElementTree as ET
ib = IMDb()
def initMovieItems():
items = []
items.append("title")
items.append("year")
items.append("genres")
items.append("director")
items.append("producer")
items.append("writer")
items.append("editor")
items.append("cast")
items.append("original music")
items.append("production companies")
items.append("distributors")
items.append("runtimes")
items.append("countries")
items.append("languages")
return items
def getMovieByTitleAndYear(title, year):
movies = ib.search_movie(title)
main = Blueprint('main', __name__)
# local - use local mysql db
local = False
# enable_extra - loads poster and plot overview from tmdb for movie info
enable_extra = True
# to laod posters on profile page
posters_on_profile_page = True
tmdb_img_url = r'https://image.tmdb.org/t/p/w342'
if local:
ia = IMDb('s3', 'mysql+mysqldb://may:venom123@localhost/imdb')
else:
ia = IMDb()
def db_fav_exists(tconst, user_id):
"""
checks if the tconst exists as a favorite for the user of user id `user_id`
"""
fav_tconst = fav.query.filter_by(user_id=user_id).all()
if fav_tconst: # user already has favorites
for a in fav_tconst:
if a.tconst == int(tconst): # the same tconst already exists
return True
return False
def get_show_imdb_info(imdb_id):
from imdb import IMDb
ia = IMDb()
return ia.get_movie(imdb_id)
class Movie:
# Get location of Movie Malarkey source (for proper retrieval of stripped dataset)
movie_malarkey_loc = pathlib.Path(
__file__).parent.absolute().parent.absolute()
local_datastore = pathlib.Path.joinpath(movie_malarkey_loc,
'dataset/malarkey.tsv')
ia = IMDb()
def __init__(self, title: str, year: str, movie_id: str = None):
"""
Constructor for Movie object
Args:
title (str): Title of the Movie
year (str): Year of the Movie's release. Uses a str for non-standard years ('N/A', 'Unknown', etc.)
movie_id (str, Optional): IMDb ID of the Movie (if given). Defaults to None
"""
self.title = title
self.year = year
self.id = movie_id
self._imdbpy_movie = None
def __repr__(self):
return f'{self.title} ({self.year})'
def __str__(self):
return repr(self)
@property
def plot(self):
raw_plot = self._imdbpy_movie["plot"][0]
# Some plots seem to use '::' to credit the author of the plot summary
return raw_plot.split('::')[0]
def populate(self):
self._imdbpy_movie = Movie.ia.get_movie(self.id)
def serialize(self, full=False):
"""
Serializes the object as JSON.
Args:
full (bool): If True, returns all data. If False, does not return the Plot of the Movie. This can be useful
when hiding the 'correct' plot from the guessers.
Returns:
dict: JSON representation of this Movie
"""
return {'title': self.title, 'plot': self.plot if full else ''}
@staticmethod
def get_random():
"""
Gets a random Movie from the local datastore
Returns:
Movie: Random Movie object
"""
with open(Movie.local_datastore, "r") as local_ds:
content = local_ds.read()
movies = content.split("\n")[1:]
num_movies = len(movies)
selected_index = randrange(num_movies - 1)
selected = movies[selected_index]
movie_pieces = selected.split("\t")
movie_id = movie_pieces[0].split("tt")[-1]
movie_title = movie_pieces[2]
movie_year = str(movie_pieces[5])
movie = Movie(movie_title, movie_year, movie_id=movie_id)
movie.populate()
return movie
from imdb import IMDb
i = IMDb('sql', uri='postgresql://localhost/imdb')
resList = i.search_movie('Moana')
for x in resList:
print x
ti = resList[0]
i.update(ti)
print ti['director'][0]
def mail_send(self):
self.s1 = self.eadminmail.get()
self.s2 = self.eadminpass.get()
self.s3 = self.emailto.get()
s='select movie1,movie2,movie3,movie4 from userinput where email like %s;'
mydb.execute(s,(self.s3,))
self.r=mydb.fetchall();
for self.i in self.r:
self.mov1=self.i[0]
self.mov2=self.i[1]
self.mov3=self.i[2]
self.mov4=self.i[3]
imd = IMDb('http')
tm1=self.mov1
tm2=self.mov2
tm3=self.mov3
tm4=self.mov4
sm1=imd.search_movie(tm1)[0]
sm2=imd.search_movie(tm2)[0]
sm3=imd.search_movie(tm3)[0]
sm4=imd.search_movie(tm4)[0]
print(sm1)
print(sm2)
print(sm3)
print(sm4)
movid1 = sm1.movieID
movid2 = sm2.movieID
movid3 = sm3.movieID
movid4 = sm4.movieID
imd.get_movie(movid1)
imd.get_movie(movid2)
imd.get_movie(movid3)
imd.get_movie(movid4)
imd.update(sm1,'episodes')
imd.update(sm2,'episodes')
imd.update(sm3,'episodes')
imd.update(sm4,'episodes')
xa=sorted(sm1['episodes'].keys())
xb=sorted(sm2['episodes'].keys())
xc=sorted(sm3['episodes'].keys())
xd=sorted(sm4['episodes'].keys())
ja=max(xa)
jb=max(xb)
jc=max(xc)
jd=max(xd)
sea1=sm1['episodes'][ja]
sea2=sm2['episodes'][jb]
sea3=sm3['episodes'][jc]
sea4=sm4['episodes'][jd]
la=len(sea1)
lb=len(sea2)
lc=len(sea3)
ld=len(sea4)
e1=sm1['episodes'][ja][la]
e2=sm2['episodes'][jb][lb]
e3=sm3['episodes'][jc][lc]
e4=sm4['episodes'][jd][ld]
self.data1=e1['long imdb canonical title']
self.data2=e2['long imdb canonical title']
self.data3=e3['long imdb canonical title']
self.data4=e4['long imdb canonical title']
self.spl1=self.data1.split('#')
self.spl2=self.data2.split('#')
self.spl3=self.data3.split('#')
self.spl4=self.data4.split('#')
print(self.spl1)
print(self.spl2)
print(self.spl3)
print(self.spl4)
self.subject = 'TV series reminder'
self.msg =('Hi \n\nThere is latest tv series upates ,\n Status: \n'+str(self.spl1[0])+' '+str(self.spl1[1])+ ': \n\n'
+ str(self.spl2[0])+' '+str(self.spl2[1])+ ':\n\n'
+ str(self.spl3[0])+ ' '+str(self.spl3[1])+ ': \n\n'
+ str(self.spl4[0])+ ' '+str(self.spl4[1])+': \n\n')
server = smtplib.SMTP('smtp.gmail.com:587')
server.ehlo()
server.starttls()
server.login(self.s1,self.s2)
message='Subject: {}\n\n{}'.format(self.subject,self.msg)
server.sendmail(self.s1,self.s3,message)
server.quit()
tkinter.messagebox.showinfo(' send','message successfully send. ')
print("Success:Email send!")
def init_IMDBb():
ia = IMDb()
movie = ia.get_movie('0094878')
from imdb import IMDb
import bs4
import datetime
import random
import re
import requests
import sqlite3
import time
from tqdm import tqdm
ia = IMDb(adultSearch=False)
db = sqlite3.connect('usernames.db')
c = db.cursor()
# Initialise tables if they don't already exist
c.execute(
"CREATE TABLE IF NOT EXISTS details(username TEXT, password TEXT, lastFilms TEXT, likedFilms TEXT)")
c.execute("CREATE TABLE IF NOT EXISTS info(username TEXT, name TEXT, address TEXT, dateofbirth TEXT, gender TEXT, interests TEXT)")
db.commit()
# Changes ["spam", "eggs"] to "spam, eggs"
def listBeaut(ugly): return ', '.join(ugly)
def authLoop(expression, message):
# prompts the user for input until a regex expression is not met
variable = ''
while not(re.compile(expression).match(''.join(sorted(variable)))):
variable = input(message)
return variable
def tryAttr(movie, variable):
# checks if an attribute for a movie exists, catches any exceptions
def get_year(title):
id = movieLink.get(title)
movie = IMDb().get_movie(id)
return movie['year']
def get_genres(title):
id = movieLink.get(title)
movie = IMDb().get_movie(id)
return movie['genres']
def get_cover(title):
id = movieLink.get(title)
movie = IMDb().get_movie(id)
return movie['cover url']
import requests
from random import seed
import sqlite3
import pandas as pd
import re
import pickle
from flaskblog import creating_model
from math import isnan
from warnings import filterwarnings
from flaskblog import db
from flaskblog.models import User, Admin, Movie, Seat, Screening, Reserved, Cost
filterwarnings("ignore")
lm, IMDB, feature_columns = creating_model.create_model()
imdb_obj = IMDb()
proxy = {"https": "185.56.209.114:51386"}
s = requests.Session()
s.proxies = {"http": "http://50.203.239.28:80"}
seed(1)
def cost(predicted_movie_rating):
premium_cost = 0
if (predicted_movie_rating > 0 and predicted_movie_rating < 3):
premium_cost = 100
elif (predicted_movie_rating >= 3 and predicted_movie_rating < 6):
premium_cost = 120
elif (predicted_movie_rating >= 6 and predicted_movie_rating < 8):
premium_cost = 160
elif (predicted_movie_rating >= 8 and predicted_movie_rating <= 10):
def __init__(self, application):
self.application = application
self.settings = Gio.Settings(schema_id="org.x.hypnotix")
self.icon_theme = Gtk.IconTheme.get_default()
self.manager = Manager(self.settings)
self.providers = []
self.active_provider = None
self.active_group = None
self.active_serie = None
self.marked_provider = None
self.content_type = TV_GROUP # content being browsed
self.back_page = None # page to go back to if the back button is pressed
self.active_channel = None
self.fullscreen = False
self.mpv = None
self.ia = IMDb()
# Set the Glade file
gladefile = "/usr/share/hypnotix/hypnotix.ui"
self.builder = Gtk.Builder()
self.builder.set_translation_domain(APP)
self.builder.add_from_file(gladefile)
self.window = self.builder.get_object("main_window")
self.window.set_title(_("Hypnotix"))
self.window.set_icon_name("hypnotix")
provider = Gtk.CssProvider()
provider.load_from_path("/usr/share/hypnotix/hypnotix.css")
screen = Gdk.Display.get_default_screen(Gdk.Display.get_default())
# I was unable to found instrospected version of this
Gtk.StyleContext.add_provider_for_screen(
screen, provider, Gtk.STYLE_PROVIDER_PRIORITY_APPLICATION)
# Prefs variables
self.selected_pref_provider = None
self.edit_mode = False
# Create variables to quickly access dynamic widgets
self.generic_channel_pixbuf = GdkPixbuf.Pixbuf.new_from_file_at_size(
"/usr/share/hypnotix/generic_tv_logo.png", 22, 22)
widget_names = ["headerbar", "status_label", "status_bar", "sidebar", "go_back_button", "channels_box", \
"provider_button", "preferences_button", \
"mpv_drawing_area", "stack", "fullscreen_button", \
"provider_ok_button", "provider_cancel_button", \
"name_entry", "path_label", "path_entry", "browse_button", "url_label", "url_entry", \
"username_label", "username_entry", "password_label", "password_entry", "epg_label", "epg_entry", \
"tv_logo", "movies_logo", "series_logo", "tv_button", "movies_button", "series_button", \
"tv_label", "movies_label", "series_label", \
"categories_flowbox", \
"channels_flowbox", \
"vod_flowbox", \
"episodes_box", \
"stop_button", "pause_button", "show_button", "playback_label", "playback_bar", \
"providers_flowbox", "new_provider_button", "reset_providers_button", \
"delete_no_button", "delete_yes_button", \
"reset_no_button", "reset_yes_button", \
"info_section", "info_revealer", "info_name_label", "info_plot_label", "info_rating_label", "info_year_label", "close_info_button", \
"info_genre_label", "info_duration_label", "info_votes_label", "info_pg_label", "divider_label", \
"useragent_entry", "referer_entry", "mpv_entry", "mpv_link", \
"mpv_stack", "spinner"]
for name in widget_names:
widget = self.builder.get_object(name)
if widget == None:
print("Could not find widget %s!" % name)
sys.exit(1)
else:
setattr(self, name, widget)
self.divider_label.set_text("/10")
# Widget signals
self.window.connect("key-press-event", self.on_key_press_event)
self.mpv_drawing_area.connect("realize",
self.on_mpv_drawing_area_realize)
self.mpv_drawing_area.connect("draw", self.on_mpv_drawing_area_draw)
self.fullscreen_button.connect("clicked",
self.on_fullscreen_button_clicked)
self.provider_ok_button.connect("clicked", self.on_provider_ok_button)
self.provider_cancel_button.connect("clicked",
self.on_provider_cancel_button)
self.name_entry.connect("changed", self.toggle_ok_sensitivity)
self.url_entry.connect("changed", self.toggle_ok_sensitivity)
self.path_entry.connect("changed", self.toggle_ok_sensitivity)
self.tv_button.connect("clicked", self.show_groups, TV_GROUP)
self.movies_button.connect("clicked", self.show_groups, MOVIES_GROUP)
self.series_button.connect("clicked", self.show_groups, SERIES_GROUP)
self.go_back_button.connect("clicked", self.on_go_back_button)
self.stop_button.connect("clicked", self.on_stop_button)
self.pause_button.connect("clicked", self.on_pause_button)
self.show_button.connect("clicked", self.on_show_button)
self.provider_button.connect("clicked", self.on_provider_button)
self.preferences_button.connect("clicked", self.on_preferences_button)
self.new_provider_button.connect("clicked",
self.on_new_provider_button)
self.reset_providers_button.connect("clicked",
self.on_reset_providers_button)
self.delete_no_button.connect("clicked", self.on_delete_no_button)
self.delete_yes_button.connect("clicked", self.on_delete_yes_button)
self.reset_no_button.connect("clicked", self.on_reset_no_button)
self.reset_yes_button.connect("clicked", self.on_reset_yes_button)
self.browse_button.connect("clicked", self.on_browse_button)
self.close_info_button.connect("clicked", self.on_close_info_button)
# Settings widgets
self.bind_setting_widget("user-agent", self.useragent_entry)
self.bind_setting_widget("http-referer", self.referer_entry)
self.bind_setting_widget("mpv-options", self.mpv_entry)
# Menubar
accel_group = Gtk.AccelGroup()
self.window.add_accel_group(accel_group)
menu = self.builder.get_object("main_menu")
item = Gtk.ImageMenuItem()
item.set_image(
Gtk.Image.new_from_icon_name(
"preferences-desktop-keyboard-shortcuts-symbolic",
Gtk.IconSize.MENU))
item.set_label(_("Keyboard Shortcuts"))
item.connect("activate", self.open_keyboard_shortcuts)
key, mod = Gtk.accelerator_parse("<Control>K")
item.add_accelerator("activate", accel_group, key, mod,
Gtk.AccelFlags.VISIBLE)
menu.append(item)
item = Gtk.ImageMenuItem()
item.set_image(
Gtk.Image.new_from_icon_name("help-about-symbolic",
Gtk.IconSize.MENU))
item.set_label(_("About"))
item.connect("activate", self.open_about)
key, mod = Gtk.accelerator_parse("F1")
item.add_accelerator("activate", accel_group, key, mod,
Gtk.AccelFlags.VISIBLE)
menu.append(item)
item = Gtk.ImageMenuItem(label=_("Quit"))
image = Gtk.Image.new_from_icon_name("application-exit-symbolic",
Gtk.IconSize.MENU)
item.set_image(image)
item.connect('activate', self.on_menu_quit)
key, mod = Gtk.accelerator_parse("<Control>Q")
item.add_accelerator("activate", accel_group, key, mod,
Gtk.AccelFlags.VISIBLE)
key, mod = Gtk.accelerator_parse("<Control>W")
item.add_accelerator("activate", accel_group, key, mod,
Gtk.AccelFlags.VISIBLE)
menu.append(item)
menu.show_all()
# Type combox box (in preferences)
model = Gtk.ListStore(str, str) # PROVIDER_TYPE_ID, PROVIDER_TYPE_NAME
model.append([PROVIDER_TYPE_URL, _("M3U URL")])
model.append([PROVIDER_TYPE_LOCAL, _("Local M3U File")])
model.append([PROVIDER_TYPE_XTREAM, _("Xtream API")])
self.provider_type_combo = self.builder.get_object(
"provider_type_combo")
renderer = Gtk.CellRendererText()
self.provider_type_combo.pack_start(renderer, True)
self.provider_type_combo.add_attribute(renderer, "text",
PROVIDER_TYPE_NAME)
self.provider_type_combo.set_model(model)
self.provider_type_combo.set_active(0) # Select 1st type
self.provider_type_combo.connect("changed",
self.on_provider_type_combo_changed)
self.tv_logo.set_from_pixbuf(
GdkPixbuf.Pixbuf.new_from_file_at_size(
"/usr/share/hypnotix/pictures/tv.svg", 258, 258))
self.movies_logo.set_from_pixbuf(
GdkPixbuf.Pixbuf.new_from_file_at_size(
"/usr/share/hypnotix/pictures/movies.svg", 258, 258))
self.series_logo.set_from_pixbuf(
GdkPixbuf.Pixbuf.new_from_file_at_size(
"/usr/share/hypnotix/pictures/series.svg", 258, 258))
self.reload(page="landing_page")
# Redownload playlists after a little while...
GLib.timeout_add_seconds(60 * 5, self.force_reload)
self.window.show()
self.playback_bar.hide()
sp.getoutput("sudo ansible-playbook /mail.yml")
#--------------------------main------------------------------------------------------------
try:
conn = mysql.connector.connect(user=secret.mysqluser(),
password=secret.mysqlpwd(),
host='localhost')
except:
print("Error in connection to mysql")
mycursor = conn.cursor()
database()
tv = IMDb()
while True:
receiver_emailid = input("Email address: ")
Tv_series = input("Tv Series:")
params = (receiver_emailid, Tv_series.lower())
mycursor.execute("Insert into input_data(email,tv_series) values (%s,%s)",
params)
conn.commit()
mycursor.execute("select * from input_data")
data = mycursor.fetchall()
a = data[len(data) - 1] # fetch the last input value from table
s_list = a[1].split(
','
from imdb import IMDb
import csv
import re
#with open('zz-episode_data.csv', 'a') as csvfile:
# writer = csv.writer(csvfile)
# process each title
with open('approved_titles.txt') as titles:
for line in titles.readlines():
title = line[:-1]
i = IMDb()
try:
show_search = i.search_movie(title)
### get the id of the first search result
tv_show = show_search[0].movieID
### use id to get the specific show
show = i.get_movie(tv_show)
if show['kind'] == 'tv series':
#print title
i.update(show, 'episodes')
### process each season and episode, print to csv
for season in show['episodes']:
#print show['episodes'][season]
for episode in show['episodes'][season]:
#print episode
ep = show['episodes'][season][episode]
i.update(ep)
def send_to_s3(conn, filename):
api_stream = conn.get_bucket('flickbot-api')
k = Key(api_stream)
k.key = str(filename)
k.set_contents_from_filename(filename, policy='public-read')
def save_to_json(filename, dict_name):
with open(filename, 'w') as fp:
json.dump(dict_name, fp, ensure_ascii=False, encoding='utf-8',
sort_keys=True)
if __name__ == '__main__':
conn = IMDb()
conn_s3 = S3Connection()
credentials = yaml.load(open(os.path.expanduser(
'~/admin/bot-api.yml')))
youtube = build(credentials['youtube']["YOUTUBE_API_SERVICE_NAME"],
credentials['youtube']["YOUTUBE_API_VERSION"],
developerKey=credentials['youtube']["DEVELOPER_KEY"])
in_theaters = "https://api.themoviedb.org/3/movie/now_playing?api_key=" \
+ credentials['themoviedb']['API_KEY'] \
+ "&language=en-US&page=1"
coming_soon = "https://api.themoviedb.org/3/movie/upcoming?api_key=" \
+ credentials['themoviedb']['API_KEY'] \
+ "&language=en-US&page=1"
genres_url = "https://api.themoviedb.org/3/genre/movie/list?api_key=" \
+ credentials['themoviedb']['API_KEY'] \
+ "&language=en-US"
def tv_show_analysis(search_term):
ia = IMDb()
movie_search = search_term.title()
all_data = ia.search_movie(movie_search)
movie_id = all_data[0].movieID
episodes = ia.get_movie_episodes(movie_id)
seasons = episodes['data']['episodes']
season_eps = []
episode_ids = []
j = 0
while j < len(seasons):
for x in seasons:
season_eps.append(len(seasons[x]))
for f in seasons[x]:
episode_ids.append(seasons[x][f].movieID)
j += 1
season_eps_extend = []
q = 0
while q < len(season_eps):
season_eps_extend.extend(repeat(q + 1, season_eps[q]))
q += 1
rating = []
voting_demographics = ia.get_movie_vote_details(movie_id)
age_ratings = []
age_categories = ['Under 18', '18-29', '30-44', '45+']
try:
age_ratings.append(voting_demographics['data']['demographics']['aged under 18']['rating'])
except:
age_categories.pop(0)
try:
age_ratings.append(voting_demographics['data']['demographics']['aged 18 29']['rating'])
except:
age_categories.pop(1)
try:
age_ratings.append(voting_demographics['data']['demographics']['aged 30 44']['rating'])
except:
age_categories.pop(2)
try:
age_ratings.append(voting_demographics['data']['demographics']['aged 45 plus']['rating'])
except:
age_categories.pop(3)
p = 0
while p < len(episode_ids):
try:
rating.append(ia.get_movie_vote_details(episode_ids[p])['data']['arithmetic mean'])
p += 1
except:
episode_ids.pop(p)
season_eps_extend.pop(p)
p += 1
min_rating_index = rating.index(min(rating))
min_rating_episode = ia.get_movie(episode_ids[min_rating_index])
min_episode = str(min_rating_episode) + " (" + str(round(min(rating), 1)) + ")"
max_rating_index = rating.index(max(rating))
max_rating_episode = ia.get_movie(episode_ids[max_rating_index])
max_episode = str(max_rating_episode) + " (" + str(round(max(rating), 1)) + ")"
average_rating = round(statistics.mean(rating), 1)
episodes = []
myset = list(set(season_eps_extend))
test = []
for x in myset:
test.append(season_eps_extend.count(x))
for x in test:
for j in range(1, x + 1):
episodes.append(j)
df = pd.DataFrame(list(zip(episodes, season_eps_extend, rating)), columns=['Episode', 'Season', 'Rating'])
data = df.pivot("Episode", "Season", "Rating")
figsize = (8.333 + 3.333 * max(season_eps_extend)), (6.666 + 0.8333 * max(episodes))
font_size = round(22 / (8.333 + 3.333 * max(season_eps_extend)) * (6.666 + 0.8333 * max(episodes)))
plt.style.use('dark_background')
plt.rcParams['figure.facecolor'] = 'grey'
plt.figure(figsize=figsize)
font = {'family': 'DejaVu Sans',
'weight': 'normal',
'size': font_size}
plt.rc('font', **font)
ax = sns.heatmap(data, square=True, vmin=0, vmax=10, cmap="RdYlGn", annot=True, linewidths=.2,
annot_kws={"size": round((24.55 - .2758 * max(season_eps_extend)))})
ax.set(ylim=(0, max(episodes)))
ax.xaxis.set_ticks_position("top")
ax.xaxis.set_label_position('top')
plt.gca().invert_yaxis()
ax.xaxis.labelpad = font_size
ax.yaxis.labelpad = font_size
ax.xaxis.label.set_size(round(font_size * 1.25))
ax.yaxis.label.set_size(round(font_size * 1.25))
plt.rcParams['figure.facecolor'] = 'grey'
plot_name = 'test.png'
plt.savefig(plot_name, facecolor=(0.15, 0.15, 0.15))
plt.style.use('dark_background')
plt_size = (figsize[0] * 0.45, figsize[1] * 0.45)
plt.rcParams.update({'font.size': round(figsize[0] * 0.45 * figsize[1] * 0.45 * .3)})
fig = plt.figure(figsize=plt_size)
ax = fig.add_subplot(111)
ax.bar(age_categories, age_ratings, label=age_ratings)
ax.set(ylim=(1, 10.5))
ax.axes.get_yaxis().set_visible(False)
plt.title("Average Rating by Age Group")
try:
plt.annotate(str(age_ratings[0]), (-.15, age_ratings[0] + .25))
except:
pass
try:
plt.annotate(str(age_ratings[1]), (.85, age_ratings[1] + .25))
except:
pass
try:
plt.annotate(str(age_ratings[2]), (1.85, age_ratings[2] + .25))
except:
pass
try:
plt.annotate(str(age_ratings[3]), (2.85, age_ratings[3] + .25))
except:
pass
line_name = 'line.png'
plt.savefig(line_name, facecolor=(0.15, 0.15, 0.15))
season_rating = []
season_nums = []
for x in myset:
num = season_eps.count(x)
season_nums.append(num)
ep_count = 0
season_index = 0
while season_index < (len(season_eps) - 1):
s = slice(int(ep_count), int((season_eps[season_index]) + sum(season_eps[0:season_index])))
avg = statistics.mean(rating[s])
season_rating.append(avg)
ep_count += (season_eps[season_index])
season_index += 1
file1 = plot_name
file2 = line_name
best_season = season_rating.index(max(season_rating)) + 1
worst_season = season_rating.index(min(season_rating)) + 1
im2 = Image.open(file2)
im1 = Image.open(file1)
w1, h1 = im1.size
w2, h2 = im2.size
offset = (int(-15), ((h1 - h2) * 8) // 9)
offset_text_title = (int(w2 * .1), ((h1 - h2) * 1) // 6)
offset_text_body = (int(w2 * .1), ((h1 - h2) * 2) // 6)
im1.paste(im2, offset)
draw = ImageDraw.Draw((im1))
title_font_size = (w1 * h1 * 0.00001857) + 32.142
body_font_size = title_font_size * 0.58333
title_font = ImageFont.truetype("/Users/cartermeetze/PycharmProjects/shows/open-sans/OpenSans-Semibold.ttf",
round(title_font_size))
font_width = 0.45
body_font_height = 0.35
while title_font.getsize(movie_search)[0] > font_width * im1.size[0]:
title_font_size -= 1
title_font = ImageFont.truetype("/Users/cartermeetze/PycharmProjects/shows/open-sans/OpenSans-Semibold.ttf",
round(title_font_size))
body_font = ImageFont.truetype("/Users/cartermeetze/PycharmProjects/shows/open-sans/OpenSans-Light.ttf",
round(body_font_size))
draw.text(offset_text_title, movie_search + " \n", font=title_font)
body = "\n" + "Average Rating: " + str(average_rating) + "\n" + "\n" \
"Best Season: " + str(best_season) + " (" + str(
round(max(season_rating), 1)) + ")" + "\n" + "\n" \
"Worst Season: " + str(worst_season) + " (" + str(
round(min(season_rating), 1)) + ")"
while body_font.getsize("Average Rating: " + str(average_rating))[0] > font_width * im1.size[0]:
body_font_size -= 1
body_font = ImageFont.truetype("/Users/cartermeetze/PycharmProjects/shows/open-sans/OpenSans-Light.ttf",
round(body_font_size))
while body_font.getsize("Average Rating: " + str(average_rating))[1] * 6 > body_font_height * im1.size[1]:
body_font_size -= 1
body_font = ImageFont.truetype("/Users/cartermeetze/PycharmProjects/shows/open-sans/OpenSans-Light.ttf",
round(body_font_size))
draw.text(offset_text_body, body, font=body_font)
signature_offset = (0, h1 - (h1 * 0.045))
signature_font = ImageFont.truetype("/Users/cartermeetze/PycharmProjects/shows/open-sans/OpenSans-Light.ttf",
round(body_font_size * 0.75))
draw.text(signature_offset, "https://www.linkedin.com/in/carter-meetze/", font=signature_font)
file_name = movie_search + " Analysis.png"
im1.save(file_name)
return file_name + " Created"
def __init__(self):
self.dataSet = IMDb(reraiseExceptions=True)
def main():
count = 1
data_fetched = 0
if (len(sys.argv) > 1):
count = sys.argv[1]
ia = IMDb()
# Get url from the tblmovieurl
try:
url_object = movieurl.objects.filter(runcount__lt=1)[:count]
start_movie_id = url_object[0].id
except:
start_movie_id = 0
total_count = int(count)
total_run_count = 0
extractor_statistics = Movie_Fetch_Statistics(
start_date=datetime.now(),
total_count=total_count,
start_movie_imdbid=start_movie_id,
total_run_count=total_run_count,
end_date=datetime.now(),
end_movie_imdbid=0)
extractor_statistics.save()
for url in url_object:
sucess_factor = 0
imdbid = url.imdbid.replace('tt', '')
print "Get movie information : ", url.movie_name
the_matrix = ia.get_movie(imdbid)
tblmovie = fnMovie(the_matrix, sucess_factor)
try:
animation_department = the_matrix.data['animation department']
for person in animation_department:
tblperson = fnPerson(person, sucess_factor)
tblanimation_department, c = Animation_department.objects.get_or_create(
name=tblperson)
tblmovie.animation_department.add(tblanimation_department)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
art_department = the_matrix.data['art department']
for person in art_department:
tblperson = fnPerson(person, sucess_factor)
tblart_department, c = Art_department.objects.get_or_create(
name=tblperson)
tblmovie.art_department.add(tblart_department)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
art_direction = the_matrix.data['art direction']
for person in art_direction:
tblperson = fnPerson(person, sucess_factor)
tblart_direction, c = Art_direction.objects.get_or_create(
name=tblperson)
tblmovie.art_direction.add(tblart_direction)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
assistant_director = the_matrix.data['assistant director']
for person in assistant_director:
tblperson = fnPerson(person, sucess_factor)
tblassistant_director, c = Assistant_director.objects.get_or_create(
name=tblperson)
tblmovie.assistant_director.add(tblassistant_director)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
camera_and_electrical_department = the_matrix.data[
'camera and electrical department']
for person in camera_and_electrical_department:
tblperson = fnPerson(person, sucess_factor)
tblcamera_and_electrical_department, c = Camera_and_electrical_department.objects.get_or_create(
name=tblperson)
tblmovie.camera_and_electrical_department.add(
tblcamera_and_electrical_department)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
casting_department = the_matrix.data['casting department']
for person in casting_department:
tblperson = fnPerson(person, sucess_factor)
tblcasting_department, c = Casting_department.objects.get_or_create(
name=tblperson)
tblmovie.casting_department.add(tblcasting_department)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
casting_director = the_matrix.data['casting director']
for person in casting_director:
tblperson = fnPerson(person, sucess_factor)
tblcasting_director, c = Casting_director.objects.get_or_create(
name=tblperson)
tblmovie.casting_director.add(tblcasting_director)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
cinematographer = the_matrix.data['cinematographer']
for person in cinematographer:
tblperson = fnPerson(person, sucess_factor)
tblcinematographer, c = Cinematographer.objects.get_or_create(
name=tblperson)
tblmovie.cinematographer.add(tblcinematographer)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
costume_department = the_matrix.data['costume department']
for person in costume_department:
tblperson = fnPerson(person, sucess_factor)
tblcostume_department, c = Costume_department.objects.get_or_create(
name=tblperson)
tblmovie.costume_department.add(tblcostume_department)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
costume_designer = the_matrix.data['costume designer']
for person in costume_designer:
tblperson = fnPerson(person, sucess_factor)
tblcostume_designer, c = Costume_designer.objects.get_or_create(
name=tblperson)
tblmovie.costume_designer.add(tblcostume_designer)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
director = the_matrix.data['director']
for person in director:
tblperson = fnPerson(person, sucess_factor)
tbldirector, c = Director.objects.get_or_create(name=tblperson)
tblmovie.director.add(tbldirector)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
editor = the_matrix.data['editor']
for person in editor:
tblperson = fnPerson(person, sucess_factor)
tbleditor, c = Editor.objects.get_or_create(name=tblperson)
tblmovie.editor.add(tbleditor)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
make_up = the_matrix.data['make up']
for person in make_up:
tblperson = fnPerson(person, sucess_factor)
tblmake_up, c = Make_up.objects.get_or_create(name=tblperson)
tblmovie.make_up.add(tblmake_up)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
miscellaneous_crew = the_matrix.data['miscellaneous crew']
for person in miscellaneous_crew:
tblperson = fnPerson(person, sucess_factor)
tblmiscellaneous_crew, c = Miscellaneous_crew.objects.get_or_create(
name=tblperson)
tblmovie.miscellaneous_crew.add(tblmiscellaneous_crew)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
music_department = the_matrix.data['music department']
for person in music_department:
tblperson = fnPerson(person, sucess_factor)
tblmusic_department, c = Music_department.objects.get_or_create(
name=tblperson)
tblmovie.music_department.add(tblmusic_department)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
original_music = the_matrix.data['original music']
for person in original_music:
tblperson = fnPerson(person, sucess_factor)
tbloriginal_music, c = Original_music.objects.get_or_create(
name=tblperson)
tblmovie.original_music.add(tbloriginal_music)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
producer = the_matrix.data['producer']
for person in producer:
tblperson = fnPerson(person, sucess_factor)
tblproducer, c = Producer.objects.get_or_create(name=tblperson)
tblmovie.producer.add(tblproducer)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
production_design = the_matrix.data['production design']
for person in production_design:
tblperson = fnPerson(person, sucess_factor)
tblproduction_design, c = Production_design.objects.get_or_create(
name=tblperson)
tblmovie.production_design.add(tblproduction_design)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
production_manager = the_matrix.data['production manager']
for person in production_manager:
tblperson = fnPerson(person, sucess_factor)
tblproduction_manager, c = Production_manager.objects.get_or_create(
name=tblperson)
tblmovie.production_manager.add(tblproduction_manager)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
set_decoration = the_matrix.data['set decoration']
for person in set_decoration:
tblperson = fnPerson(person, sucess_factor)
tblset_decoration, c = Set_decoration.objects.get_or_create(
name=tblperson)
tblmovie.set_decoration.add(tblset_decoration)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
sound_crew = the_matrix.data['sound crew']
for person in sound_crew:
tblperson = fnPerson(person, sucess_factor)
tblsound_crew, c = Sound_crew.objects.get_or_create(
name=tblperson)
tblmovie.sound_crew.add(tblsound_crew)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
special_effects_department = the_matrix.data[
'special effects department']
for person in special_effects_department:
tblperson = fnPerson(person, sucess_factor)
tblspecial_effects_department, c = Special_effects_department.objects.get_or_create(
name=tblperson)
tblmovie.special_effects_department.add(
tblspecial_effects_department)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
stunt_performer = the_matrix.data['stunt performer']
for person in stunt_performer:
tblperson = fnPerson(person, sucess_factor)
tblstunt_performer, c = Stunt_performer.objects.get_or_create(
name=tblperson)
tblmovie.stunt_performer.add(tblstunt_performer)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
transportation_department = the_matrix.data[
'transportation department']
for person in transportation_department:
tblperson = fnPerson(person, sucess_factor)
tbltransportation_department, c = Transportation_department.objects.get_or_create(
name=tblperson)
tblmovie.transportation_department.add(
tbltransportation_department)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
visual_effects = the_matrix.data['visual effects']
for person in visual_effects:
tblperson = fnPerson(person, sucess_factor)
tblvisual_effects, c = Visual_effects.objects.get_or_create(
name=tblperson)
tblmovie.visual_effects.add(tblvisual_effects)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
writer = the_matrix.data['writer']
for person in writer:
tblperson = fnPerson(person, sucess_factor)
tblwriter, c = Writer.objects.get_or_create(name=tblperson)
tblmovie.writer.add(tblwriter)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
distributors = the_matrix.data['distributors']
for company in distributors:
tblperson = fnCompany(company)
tbldistributors, c = Distributors.objects.get_or_create(
name=tblperson)
tblmovie.distributors.add(tbldistributors)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
miscellaneous_companies = the_matrix.data[
'miscellaneous companies']
for company in miscellaneous_companies:
tblcompany = fnCompany(company)
tblmiscellaneous_companies, c = Miscellaneous_companies.objects.get_or_create(
name=tblcompany)
tblmovie.miscellaneous_companies.add(
tblmiscellaneous_companies)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
production_companies = the_matrix.data['production companies']
for company in production_companies:
tblcompany = fnCompany(company)
tblproduction_companies, c = Production_companies.objects.get_or_create(
name=tblcompany)
tblmovie.production_companies.add(tblproduction_companies)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
special_effects_companies = the_matrix.data[
'special effects companies']
for company in special_effects_companies:
tblcompany = fnCompany(company)
tblspecial_effects_companies, c = Special_effects_companies.objects.get_or_create(
name=tblcompany)
tblmovie.special_effects_companies.add(
tblspecial_effects_companies)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
cast = the_matrix.data['cast']
for person in cast:
tblcharactor = fnCharactor(person)
tblperson = fnPerson(person, sucess_factor)
tblcast, c = Cast.objects.get_or_create(name=tblperson)
tblcast.charactor.add(tblcharactor)
tblmovie.cast.add(tblcast)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
akas = the_matrix.data['akas']
for name in akas:
tblakas, c = Akas.objects.get_or_create(name=name)
tblmovie.akas_id.add(tblakas)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
plot = the_matrix.data['plot']
for name in plot:
tblplot, c = Plot.objects.get_or_create(name=name)
tblmovie.plot.add(tblplot)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
certificates = the_matrix.data['certificates']
for name in certificates:
tblcertificates, c = Certificates.objects.get_or_create(
name=name)
tblmovie.certificates.add(tblcertificates)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
color_info = the_matrix.data['color info']
for name in color_info:
tblcolor_info, c = Color_info.objects.get_or_create(color=name)
tblmovie.color_info.add(tblcolor_info)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
genres = the_matrix.data['genres']
for display_name in genres:
name = display_name.replace('-', '_').lower()
tblgenres, c = Genre.objects.get_or_create(
display_name=display_name, name=name)
tblmovie.genres.add(tblgenres)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
runtimes = the_matrix.data['runtimes']
for name in runtimes:
tblruntimes, c = Runtimes.objects.get_or_create(name=name)
tblmovie.runtimes.add(tblruntimes)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
countries = the_matrix.data['countries']
code = the_matrix.data['country codes']
i = 0
for name in countries:
tblcountries, c = Countries.objects.get_or_create(name=name,
code=code[i])
tblmovie.countries.add(tblcountries)
i = i + 1
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
sound_mix = the_matrix.data['sound mix']
for name in sound_mix:
tblsound_mix, c = Sound_mix.objects.get_or_create(name=name)
tblmovie.sound_mix.add(tblsound_mix)
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
try:
languages = the_matrix.data['languages']
code = the_matrix.data['language codes']
i = 0
for name in languages:
tbllanguages, c = Languages.objects.get_or_create(name=name,
code=code[i])
tblmovie.languages.add(tbllanguages)
i = i + 1
except Exception as e:
print e
sucess_factor = sucess_factor + 1
pass
url.runcount += 1
url.last_rundate = datetime.now()
url.save()
#Update Statistics
extractor_statistics.total_run_count += 1
extractor_statistics.end_date = datetime.now()
extractor_statistics.end_movie_imdbid = url.id
extractor_statistics.save()
return 0
import urlparse
from chalice import Chalice
from imdb import IMDb
app = Chalice(app_name='imdbbot')
imdb = IMDb()
def to_response(text, public=True):
response = {
'text': text,
'unfurl_links': True
}
if public:
response['response_type'] = 'in_channel'
return response
@app.route('/', cors=True)
def handler():
title = app.current_request.query_params.get('text', None)
if not title:
return to_response('Need a movie title, stupid', public=False)
results = imdb.search_movie(title)
if results:
for name in self.movie_list:
print(name)
try:
db = IMDb()
result = db.search_movie(name)
movie_ids = []
cache = []
for i, r in enumerate(result):
movieobj = db.get_movie(r.movieID)
cache.append([r.movieID, movieobj])
movie_ids.append(r.movieID)
if i > 5:
break
self.signals.callback.emit(cache)
except Exception as e:
self.error.emit(e)
if __name__ == '__main__':
db = IMDb()
m = db.get_movie("0075640")
for k in m.__dict__.keys():
print(k, m.__dict__[k])
print(db.get_imdbID(m))
# result = db.search_movie("Matrix")
# for r in result:
# movieobj = db.get_movie(r.movieID)
# print(movieobj.keys())
import pandas as pd
import numpy as np
from imdb import IMDb
##Creating the IMDb instance
ia = IMDb()
## Creating CSV filepath variables
movies_csv_path = "Resources/AllMoviesDetailsCleaned.csv"
streaming_csv_path = "Resources/MoviesOnStreamingPlatforms_updated.csv"
movies_df = pd.read_csv(movies_csv_path, encoding="utf-8", delimiter=";", parse_dates=["release_date"])
streaming_df = pd.read_csv(streaming_csv_path, encoding="utf-8", parse_dates=["Year"])
#Uniforming the dates between both CSVs.
movies_df["release_date"] = movies_df["release_date"].dt.year
streaming_df["Year"] = streaming_df["Year"].dt.year
movies_df = movies_df.loc[(movies_df["release_date"].isnull() != True),:]
movies_df["release_date"] = movies_df["release_date"].astype(int)
### Creating a merged dataframe on Title and Year
super_merge = pd.merge(movies_df, streaming_df, left_on=["title", "release_date"], right_on=["Title", "Year"]).reset_index(drop=True)
super_merge['genres'] = super_merge['genres'].str.replace(pat="|", repl=",")
movie_merge = pd.merge(movies_df, streaming_df, left_on=["title", "release_date"], right_on=["Title", "Year"]).reset_index(drop=True)
desiredColumns = ['title', 'genres', 'Genres', 'release_date', 'budget', 'revenue', 'Runtime', 'Country', 'Language', 'spoken_languages_number', 'Age', 'popularity', 'vote_average', 'vote_count', 'imdb_id', 'IMDb', 'Rotten Tomatoes', 'Directors']
super_merge = super_merge.loc[:, desiredColumns]
#cleaned up imdb_id with a left strip. now this id is usable with the imdb module
super_merge['imdb_id'] = super_merge['imdb_id'].str.lstrip('tt')
def imdb_ia_fixture() -> IMDb:
"""Return the IMDb class."""
return IMDb()
def getEps(title,max_len=1024,debug=False):
"""Returns a text string containing schedule info for the last aired and the next upcoming episodes for the given TV series title"""
# Validate title
assert isinstance(title,str), 'A string input was not provided.'
# Preprocess title
title=title.strip()
# Determine if the next upcoming episode's plot should be included if available (Default is True)
if title.lower().endswith('/noplot'):
title=title[:-len('/noplot')].rstrip()
include_plot=False
else:
include_plot=True
try:
# Validate title further
if len(title)==0: return 'A title was not provided.'
# Create IMDb object
i=IMDb()
# Get search results
max_attempts=3 # Set to anything greater than 1
for attempt in range(1,max_attempts+1):
try:
search_results=i.search_movie(title)
break
except:
if attempt<max_attempts:
if debug: print 'An error occurred while attempting to retrieve search results for "%s". %s attempts were made.'%(title,attempt)+'\n'
sleep(attempt*2)
else:
return 'An error occurred while attempting to retrieve search results for "%s". %s attempts were made.'%(title,attempt)
del attempt,max_attempts
# Get first search result that is a TV series
search_results=ifilter(lambda s:s['kind']=='tv series',search_results)
search_results=list(islice(search_results,0,1))
if len(search_results)==0: return 'No TV series match was found for "%s".'%title
s=search_results[0]
del search_results
# Get episodes
i.update(s,'episodes')
s_title=s['long imdb title']
if (not s.has_key('episodes')) or len(s['episodes'])==0: return 'Episode info is unavailable for %s.'%s_title
s=sortedEpisodes(s)
if len(s)==0: return 'Episode info is unavailable for %s.'%s_title
# Sort episodes in approximately the desired order
s.reverse() # This results in episodes that are sorted in the desired order. If, however, the episodes are not listed in proper order at the source, such as for "Showtime Championship Boxing" (1987) as of 2/29/08, the error will be copied here.
s=list(dropwhile(lambda e:e['season']=='unknown',s))+list(takewhile(lambda e:e['season']=='unknown',s)) # While this may not always produce the most accurate results, it prevents episodes belonging to an unknown season from being thought of as most recent.
# Process date related info for episodes
date_today=date.today()
for ep_ind in xrange(len(s)):
if s[ep_ind].has_key('original air date'):
try:
s[ep_ind]['date']=strptime(s[ep_ind]['original air date'],'%d %B %Y')
except: pass
if s[ep_ind].has_key('date'):
s[ep_ind]['date']=date(*s[ep_ind]['date'][0:3])
s[ep_ind]['age']=(s[ep_ind]['date']-date_today).days # Age is date delta in days
if s[ep_ind]['age']<0:
s[ep_ind]['has aired']=True
else:
s[ep_ind]['has aired']=False
else:
s[ep_ind]['has aired']=False
del date_today,ep_ind
# Print last 10 listed episodes (if debugging)
if debug:
print 'Last 10 listed episodes:\nS# Epi# Age Episode Title'
for e in s[:10]: print '%s %s %s %s'%(str(e['season']).zfill(2)[:2],str(e['episode']).zfill(4),e.has_key('age') and str(e['age']).zfill(5) or ' '*5,e['title'].encode('latin-1'))
print
# Declare convenient functions for use in generating output string
def getSE(e):
if not isinstance(e['season'],int): return ''
Sstr='S'+str(e['season']).zfill(2)
Estr='E'+str(e['episode']).zfill(2)
return ' ('+Sstr+Estr+')'
def getAge(e): return locale.format('%i',abs(e['age']),grouping=True)
def getDate(e): return 'i.e. on '+e['date'].strftime('%a, ')+str(e['date'].day)+e['date'].strftime(' %b %y')
# Determine last aired episode
# (An episode that airs today is considered to be not yet aired)
e=ifilter(lambda e:e['has aired'],s)
e=list(islice(e,0,1))
if len(e)>0:
e=e[0]
e_schedule= e['age']!=-1 and ('%s days ago'%getAge(e)) or 'yesterday'
# Generate output string when last aired episode is available
e_out='The episode that aired last for '+s_title+' is "'+e['title']+'"'+getSE(e)+'. It aired '+e_schedule+', '+getDate(e)+'. '
del e_schedule
else:
# Generate output string when last aired episode is unavailable
e_out=''
# Determine next upcoming episode
# (An episode that airs today is considered to be an upcoming episode)
e=list(takewhile(lambda e:e['has aired']==False,s)) # Memory inefficient
if len(e)>0:
e=e[-1]
# Generate output string when next upcoming episode is available
e_out=e_out+'The next upcoming episode '+(e_out=='' and ('for '+s_title+' ') or '')+'is "'+e['title']+'"'+getSE(e)+'.'
if e.has_key('age'):
e_schedule= e['age']>1 and ('in %s days'%getAge(e)) or e['age']==1 and 'tomorrow' or e['age']==0 and 'today'
e_out=e_out+' It airs '+e_schedule+', '+getDate(e)+'.'
del e_schedule
else:
e_out=e_out+' Its air date is unavailable.'
if include_plot:
if e.has_key('plot') and e['plot']!='Related Links':
e_out=e_out+' Its plot is: '+e['plot']
elif e_out.endswith('Its air date is unavailable.'):
e_out=e_out.replace('Its air date is unavailable.','Its air date and plot are unavailable.')
else:
e_out=e_out+' Its plot is unavailable.'
else:
if e_out!='': # Last: available; Next: unavailable
e_out=e_out+'No upcoming episode is scheduled.'
else: # Last: unavailable; Next: unavailable
e_out='Episode info is unavailable for %s.'%s_title
# Conditionally trim output string
if (max_len not in [0,None]) and len(e_out)>max_len-3: e_out=e_out[:max_len-3]+'...'
# Return output string
return e_out
except: return 'An unknown error occurred while attempting to retrieve episode info for "%s".'%title
from imdb import IMDb
import pickle
IA = IMDb()
## getting top 250 movies
top250 = IA.get_top250_movies()
dump = pickle.dumps(top250)
with open('top250.dat', 'wb') as file:
file.write(dump)
from bs4 import BeautifulSoup
import requests
import re
from imdb import IMDb
import json
from textblob import TextBlob
ia = IMDb() # create an imdb instance
url = "https://www.filmsite.org/boxoffice.html" # url from which the names of the top grossing movies are scraped from
url_request = requests.get(url)
soup = BeautifulSoup(url_request.content, 'html.parser') # gets content
scrape = soup.find_all("li") # saving all li tags
data = []
for names in scrape: # saving just the text from the tags
data.append(names.text)
# maybe combine lines 20 till 38 maybe in a function see if you can do a sapply like thing
titles = []
for x in data: # from the text, saving only the movie titles
if re.match(r">?.*\d{4}", x, re.DOTALL):
titles.append(x)
clean = []
for title in titles: # cleaning the movie title names
title = re.sub(r"Filmsite.org", "", title)
title = re.sub(r"\r|\n", "", title)
def get_plot(title):
id = movieLink.get(title)
movie = IMDb().get_movie(id)
return movie['plot']
