Exploratory Data Analysis on Black Directors - The Clean Up

import pandas as pd
from imdb import Cinemagoer
import re
import os.path

ia = Cinemagoer()
file = 'missing_directors.csv'
check_missing_directors_file = os.path.isfile(file)
df_director_films = pd.read_csv('imdb_movies_directors.csv', encoding= 'unicode_escape')
df_director_names = pd.read_csv('director_names.csv', encoding='unicode_escape')




for name in df_director_names.itertuples(): 
    for director in df_director_films.itertuples(): 
        if name.Name == director.Name:
            df_director_names.at[name.Index, 'Person_ID'] = int(director.Person_ID)




df_director_names['Person_ID'] = df_director_names['Person_ID'].fillna(0)
df_director_names = df_director_names.astype({"Person_ID": int})
df_director_names = df_director_names.drop("Unnamed: 0", axis=1)
df_director_names.to_csv("director_names_imdb_person_id.csv")
df_director_names

#Currently as of 6/23/2023 getting biography information like birth dates is not working
#https://github.com/cinemagoer/cinemagoer/issues/462
person = ia.get_person('0000332', info=['biography'])
print(person.infoset2keys)

def imdb_search (name):
    imdb_people_search = []
    people = ia.search_person(name)
    for person in people:            
        if person['name'] == name:
            imdb_people_search.append([person.personID, person['name']])
    
    if len(imdb_people_search) > 1 or not len(imdb_people_search):
        imdb_people_search = 0

    return imdb_people_search

# if there isn't already a missing_directors.csv then create one
# else take the missing_directors.csv and check to see if any directors can 
# be added to the director_names_imdb_person_id.csv
# also their movies added to imdb_movies_diretors to the end of that list
if not check_missing_directors_file:
    missing_directors_df = df_director_names.loc[df_director_names['Person_ID'] == 0]
    missing_directors_df.to_csv("missing_directors.csv")
    missing_directors_df
else:
    missing_directors_df = pd.read_csv(file, encoding= 'unicode_escape')

missing = ia.search_person(missing_directors_df.loc[7]['Name'])
print(missing)

madeline = ia.get_person('7507414')
print(madeline)

if madeline.has_key('director'):
    for movies in madeline['filmography']['director']:
        year = 0000 if 'year' not in movies else int(movies['year']) 
        print(movies['title'], year)

   [<Person id:1919862[http] name:_Mya Baker_>, 
    <Person id:7983695[http] name:_Mya Baker_>, 
    <Person id:1263939[http] name:_Danielle Panabaker_>, 
    <Person id:0659048[http] name:_Kay Panabaker_>, 
    <Person id:6803655[http] name:_Julia Maren Baker_>,
    <Person id:5208385[http] name:_Brianna Baker_>,
    <Person id:1019674[http] name:_Sala Baker_>,
    <Person id:1128564[http] name:_Kitana Baker_>,
    <Person id:10453571[http] name:_Malia Baker_>, 
    <Person id:0000711[http] name:_Rick Baker_>, 
    <Person id:6966400[http] name:_Stella Baker_>, 
    <Person id:12140549[http] name:_Maya Baker_>, 
    <Person id:4124843[http] name:_Mia Baker_>, 
    <Person id:11325477[http] name:_Eva Brooke Baker_>,
    <Person id:9698063[http] name:_Ekaterina Baker_>, 
    <Person id:1179722[http] name:_Anita Baker_>, 
    <Person id:0851963[http] name:_Andrea Baker_>,
    <Person id:0672060[http] name:_D.A. Pennebaker_>,
    <Person id:4080841[http] name:_Lucy May Barker_>,
    <Person id:2531646[http] name:_Shauna Baker_>]

    Madeline Anderson
    Being Me 1975
    I Am Somebody 1970
    A Tribute to Malcolm X 1967
    Integration Report I 1960

def update_directors_name(tmpID, tmpName):
    for name in df_director_names.itertuples(): 
             if name.Name == tmpName:                
                missing_directors_df.at[name.Index, 'Person_ID'] = int(tmpID)

for n in range(0, len(missing_directors_df.index)):
    imdb_person = imdb_search(missing_directors_df['Name'][n])
    if imdb_person == 0:
        continue
    else:
        person = ia.get_person(imdb_person[0][0])
        print(person)
        if person.has_key('director'):
            for movies in person['filmography']['director']:                
                update_directors_name(imdb_person[0][0], imdb_person[0][1])                            

missing_directors_df.to_csv("missing_directors.csv")

def wiki_imdb(imdb_id, wiki_name):
    imdb_person = [imdb_id, wiki_name]
    person = ia.get_person(imdb_person[0])
    if person.has_key('director'):
        for movies in person['filmography']['director']:
            year = 0000 if 'year' not in movies else int(movies['year'])            
            df_director_films.loc[len(df_director_films.index)] = [movies.movieID, movies['title'], year, imdb_person[0], imdb_person[1]]
            update_directors_name(imdb_person[0], imdb_person[1])            

wiki_imdb('10555174', 'Robert Van Lierop')

df_director_films.to_csv("Director_Movies_Clean.csv", index=False)

from bs4 import BeautifulSoup
import requests

imdb_re = 'https://www.imdb.com/name/'
total = 0
for i in range(0, len(test_df.index)):   
    wiki_url = "https://en.wikipedia.org" + test_df['wiki_link'][i]   
    print(wiki_url)  
    table_check = False

    try:
        result = requests.get(wiki_url)
        result.raise_for_status()
        doc = BeautifulSoup(result.text, "html.parser")
    except Exception as e:
        print(e)


    imdb_id = doc.find_all(rel="nofollow")

    for imdb in imdb_id:        
        if re.search(imdb_re, imdb.get('href')):            
            # print(imdb)
            print(imdb.text)
            id = re.search('\d+', imdb.get("href"))
            print(id.group())
            wiki_imdb(id.group(), imdb.text)
            table_check = True            
    if not table_check:        
        total += 1
        print(f"Total: {total} - There wasn't a match for {wiki_url}")

df_director_films.describe()