def get_mojo_rank_info():
"""
Function to calculate weekend box office rank summaries from mojo info
"""
#get movies from the db and calulate rank info
rank_info_df = movie_helper.get_highest_mojo_rank()
with tqdm(total=len(rank_info_df)) as pbar:
for index, row in rank_info_df.iterrows():
#update the database
updates = {
"best_rank": int(row['best_rank']),
'weekends_at_best_rank': int(row['weekends_at_best_rank']),
'weekends_in_top_3': int(row['weekends_in_top_3']),
'weekends_in_top_5': int(row['weekends_in_top_5']),
'weekends_in_top_10': int(row['weekends_in_top_10']),
'weekends_in_top_15': int(row['weekends_in_top_15'])
}
selects = {"movieId": int(row["movieId"])}
database_helper.update_data("movies",
update_params=updates,
select_params=selects)
pbar.update(1)
def get_mojo_data():
"""
Function which uses imdb id to scrape movie financial summary from BoxOfficeMojo
"""
#get all movies from db
movies_df = movie_helper.get_movies_df()
with tqdm(total=len(movies_df)) as pbar:
for index, row in movies_df.iterrows():
#if imdb id exists use it to scrape info from box office mojo
if (row['imdbId']):
#get stats and update the db
stats = mojo_helper.get_mojo_stats(row['imdbId'])
updates = {
"budget_usd": stats["Budget"],
"uk_gross_usd": stats["UK"],
"domestic_gross_usd": stats["Domestic"],
"worldwide_gross_usd": stats["Worldwide"],
"international_gross_usd": stats["International"]
}
selects = {"movieId": row["movieId"]}
database_helper.update_data("movies",
update_params=updates,
select_params=selects)
pbar.update(1)
def get_mojo_run_info():
"""
Function to calculate weekend box office summaries from mojo info
"""
#get movies from the db and calulate run info
run_info_df = movie_helper.get_movie_run_info()
with tqdm(total=len(run_info_df)) as pbar:
for index, row in run_info_df.iterrows():
#update the database
updates = {
"end_weekend": row['end_weekend'],
"total_weekends": row['total_weekends'],
"total_release_weeks": row['total_release_weeks'],
"first_run_end": row['first_run_end'],
"first_run_weeks": row['first_run_weeks']
}
selects = {"movieId": row["movieId"]}
database_helper.update_data("movies",
update_params=updates,
select_params=selects)
pbar.update(1)
def get_release_dates():
"""
Funciton which uses imdb to collect uk release date of films.
"""
#get all movies from db
movies_df = movie_helper.get_movies_df()
with tqdm(total=len(movies_df)) as pbar:
for index, row in movies_df.iterrows():
#get list of release dates from API
movie = ia.get_movie(str(row['imdbId']), info='release dates')
release_dates = movie['release dates']
#try to extract UK release dates (string from imdb is a mess)
uk = [
i for i in movie['release dates'] if 'UK' in i and not '(' in i
]
if (len(uk) > 0):
#if successful update the db with the release date
date_string = uk[0].split('::')[1]
date = datetime.strptime(date_string, '%d %B %Y')
database_helper.update_data(
"movies",
update_params={"ukReleaseDate": date},
select_params={"movieId": row["movieId"]})
else:
#if no uk release date found print to console
print("No UK release for ", row.title)
pbar.update(1)
def get_cast_notes():
"""Function which uses imdb to collect cast notes eg Credited/Uncredited"""
#get all movies from db
movies_df = movie_helper.get_movies_df()
with tqdm(total=len(movies_df)) as pbar:
for index, row in movies_df.iterrows():
#if imdbid exists use it to collect cast notes
if (row['imdbId']):
movie = ia.get_movie(str(row['imdbId']))
cast_list = movie.get('cast')
if (cast_list != None):
for cast_member in cast_list:
imdb_id = cast_member.personID
updates = {'notes': cast_member.notes}
selects = {
"p_imdbId": imdb_id,
"m_imdbId": row['imdbId']
}
database_helper.update_data("actors",
update_params=updates,
select_params=selects)
pbar.update(1)
def get_keywords():
"""
Function which uses imdb id to collect plot keywords
"""
#get all movies from db
movies_df = movie_helper.get_movies_df()
with tqdm(total=len(movies_df)) as pbar:
for index, row in movies_df.iterrows():
#if imbdid exists use it to look up the API
if (row['imdbId']):
#get list of keywords and created delimted string
movie = ia.get_movie(str(row['imdbId']), info='keywords')
try:
keywords = ",".join(movie['keywords'])
except:
keywords = None
#update the movies table in the db
database_helper.update_data(
"movies",
update_params={"keywords": keywords},
select_params={"movieId": row["movieId"]})
pbar.update(1)
def update_tweet_sentiments():
"""Function to assign sentiment socres and classification to all tweets in the movie_tweets2019 table"""
with tqdm(total=len(movies)) as pbar:
#assign tweet sentiment to tweets for each movie
for movie in movies:
sentiment_df = tweet_helper.get_tweet_sentiments_scores(
movie.movieId)
#update the db with newly assigned tweet sentiment and classes
for index, row in sentiment_df.iterrows():
update_params = {
"negative_scr": row["negative_scr"],
"positive_scr": row["positive_scr"],
"neutral_scr": row["neutral_scr"],
"compound_scr": row["compound_scr"],
"senti_class": row["senti_class"]
}
select_params = {"id": row["id"]}
database_helper.update_data("movie_tweets2019",
update_params=update_params,
select_params=select_params)
pbar.update(1)
def get_trailer_metadata():
"""
Function which uses youtubeId to collect trailer metadata
"""
#get all trailers from the database
trailers_df = database_helper.select_query("trailers")
with tqdm(total=len(trailers_df)) as pbar:
for index, row in trailers_df.iterrows():
#use the youtube id to make an api request for video meta data
trailer_data = yt.get_video_metadata(row['youtubeId'])
#update the db with collected meta data
update_params = {
'title': trailer_data['video_title'],
'channelTitle': trailer_data['channel_title'],
'channelId': trailer_data['channel_id'],
'categoryId': trailer_data['video_category'],
'commentCount': trailer_data['video_comment_count'],
'description': trailer_data['video_description'],
'likeCount': trailer_data['video_like_count'],
'dislikeCount': trailer_data['video_dislike_count'],
'viewCount': trailer_data['video_view_count'],
'publishDate': trailer_data['video_publish_date'],
'tags': trailer_data['video_tags']
}
select_params = {"youtubeId": row["youtubeId"]}
database_helper.update_data("trailers",
update_params=update_params,
select_params=select_params)
pbar.update(1)
def get_metaData():
"""
Function which uses imdbId to retreive metadata from IMDb for each movie
"""
#get all movies from db
movies_df = movie_helper.get_movies_df()
#get movie meta data
with tqdm(total=len(movies_df)) as pbar:
for index, row in movies_df.iterrows():
#if an imdbid exists use it to look up the API
if (row['imdbId']):
#get base meta data from imdb
movie = ia.get_movie(str(row['imdbId']))
year = movie['year']
#created delimited list of genre strings
if (movie.get('genres')):
genres = ','.join(movie.get('genres'))
rating = movie.get('rating')
votes = movie.get('votes')
#create delimited list of movie certificates
certificates = None
if (movie.get('certificates')):
certificates = ','.join(movie.get('certificates'))
#update database with collected meta data
update_params = {
"year": year,
"genres": genres,
"rating": rating,
"votes": votes,
"certificates": certificates
}
select_params = {"movieId": row["movieId"]}
database_helper.update_data("movies",
update_params=update_params,
select_params=select_params)
pbar.update(1)
def get_imdbIds():
"""
Function which uses the movie title from BFI to get the imdb id from IMDb api
"""
#get all movies from db
movies_df = movie_helper.get_movies_df()
for index, row in movies_df.iterrows():
#use the api to search imdb for films with the the title
search_results = ia.search_movie(row['title'])
#only interested in movie objects
movie_results = list(
filter(lambda x: x.get('kind') == 'movie', search_results))
if (len(movie_results) > 0):
#take the first results by default
movie = movie_results[0]
#if there is more than one then get most recent?
if (len(movie_results) > 1):
#flag issue to console so movie can be manually checked
print("Check: ", row['title'])
#try to get the one from 2019
year_results = list(
filter(lambda x: x.get('year') == 2019, movie_results))
if (len(year_results) > 0):
movie = year_results[0]
#extract imdb url and id using API
movie_url = ia.get_imdbURL(movie)
movie_id = ia.get_imdbID(movie)
#update database
database_helper.update_data(
"movies",
update_params={
"imdbId": movie_id,
"url": movie_url
},
select_params={"movieId", row["movieId"]})
def get_trailer_release_dates():
"""Function to specifically update the trailer release dates which could not be retreived by get_trailer_metadata()"""
#get all trailers from the db
trailers_df = database_helper.select_query("trailers")
with tqdm(total=len(trailers_df)) as pbar:
for index, row in trailers_df.iterrows():
#use customized api request to correctly retreive the release dates of the trailers
trailer_date = youtube_helper.get_trailer_release(
row['youtubeId'], yt)
#update the database
update_params = {'publishDate': trailer_date}
select_params = {"youtubeId": row["youtubeId"]}
database_helper.update_data("trailers",
update_params=update_params,
select_params=select_params)
pbar.update(1)
def get_critical_period():
"""
Function to calculate the film critical period based on the release date and weekend box office info
"""
#get movies from df and calculate crticial period
movies_df = movie_helper.get_critical_period()
with tqdm(total=len(movies_df)) as pbar:
for index, row in movies_df.iterrows():
#update the database
updates = {
"critical_start": row['critical_start'],
'critical_end': row['critical_end']
}
selects = {"movieId": int(row["movieId"])}
database_helper.update_data("movies",
update_params=updates,
select_params=selects)
pbar.update(1)
if (greta_res.get('certificates')):
certificates = ','.join(greta_res.get('certificates'))
#update database
update_params = {
"imdbId": '2639336',
"url": 'https://www.imdb.com/title/tt2639336/',
"year": year,
"genres": genres,
"rating": rating,
"votes": votes,
"certificates": certificates
}
select_params = {"movieId": int(greta["movieId"])}
database_helper.update_data("movies",
update_params=update_params,
select_params=select_params)
#"Kobiety Mafii 2"
# kobiety_mafii = database_helper.select_query("movies", { "movieId" : 262 })
# kobiety_mafii = kobiety_mafii.iloc[0]
# kobiety_mafii_res = ia.get_movie('8858420')
# year = kobiety_mafii_res['year']
# if (kobiety_mafii_res.get('genres')):
# genres = ','.join(kobiety_mafii_res.get('genres'))
# rating = kobiety_mafii_res.get('rating')
# votes = kobiety_mafii_res.get('votes')
# certificates = None
# if (kobiety_mafii_res.get('certificates')):
# certificates = ','.join(kobiety_mafii_res.get('certificates'))