Last active
August 7, 2019 22:34
-
-
Save zperk13/c4b2f9775bf6fd7e5ee456222c72465e to your computer and use it in GitHub Desktop.
You give it multiple imdb title id's (eg: tt4154796) and it will look at the full cast and crew and find people who were in all of them
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import re | |
import requests | |
from time import sleep | |
def unique(iter): | |
result = [] | |
for x in iter: | |
if x not in result: | |
result.append(x) | |
return result | |
class Movie(object): | |
def __init__(self, id): | |
self.id = id | |
self.cast_url = f'https://www.imdb.com/title/{id}/fullcredits' | |
self.cast_txt = requests.get(self.cast_url).text | |
self.title = re.findall(r'>.+?</a>', re.findall(fr"<a href=\"/title/{id}/\"\sitemprop='url'>.+?</a>", self.cast_txt)[0])[0][1:-4] | |
self.cast = unique([re.findall(r'/"\n>.+?\n</a>', x)[0][5:-5].lower() for x in re.findall(r'<a href="/name/.+?/"\s>.+?\s</a>', self.cast_txt)]) | |
def print_cast(self): | |
print(' ', ', '.join([' '.join([x.capitalize() for x in y.split(' ')]) for y in self.cast])) | |
movies = [] | |
num_of_movies = int(input('How many movies/episodes/shows do you want to check? ')) | |
if num_of_movies < 2: | |
raise ValueError('Number of movies must be at least 2') | |
for x in range(1, num_of_movies+1): | |
movies.append(Movie(input(f'Please type in the IMDB title id for #{x}: '))) | |
print(movies[-1].title, 'added.', end=' ') | |
movies[-1].print_cast() | |
print('\n\n') | |
duplicates = [] | |
for person in movies[0].cast: | |
person_in_all = True | |
for movie in movies[1:]: | |
if person not in movie.cast: | |
person_in_all = False | |
break | |
if person_in_all: | |
duplicates.append(person) | |
duplicates = [' '.join([x.capitalize() for x in y.split(' ')]) for y in duplicates] | |
num_of_duplicates = len(duplicates) | |
print('\n\n') | |
if num_of_duplicates == 0: | |
print('No duplicates found') | |
elif num_of_duplicates == 1: | |
print('One duplicate found:') | |
print(f' {duplicates[0]}') | |
else: | |
print(f'{num_of_duplicates} duplicates found:') | |
sleep(3) | |
for dupe in duplicates: | |
print(' ', dupe) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment