# First, let us create a simple list with some movie titles.
movies = [
    ' the matrix ', 
    'inception',
    'Titanic ', 
    'The Godfather',
    '    avatar',
    'spider-man',
    ' star wars '
]
print('Here are our raw movie titles:')
print(movies)

# Let us fix extra spaces using the strip() function.
cleaned_movies = []
for title in movies:
    cleaned_title = title.strip()
    cleaned_movies.append(cleaned_title)
print(cleaned_movies)

# Let us make all the titles have the same style with title().
uniform_titles = []
for name in cleaned_movies:
    uniform_titles.append(name.title())
print(uniform_titles)

# Imagine you got a typo in your list. Let us fix it.
uniform_titles[2] = 'Titanic'
print(uniform_titles)

# What if there is a duplicate?
movies_with_duplicates = uniform_titles + ['Inception']
print(movies_with_duplicates)

# Let us remove duplicates by making a set.
unique_movies = list(set(movies_with_duplicates))
print(unique_movies)

# Now let us ask the user to add a movie title.
new_movie = input('Type a movie to add: ')
new_movie_clean = new_movie.strip().title()
if new_movie_clean not in unique_movies:
    unique_movies.append(new_movie_clean)
    print('Added:', new_movie_clean)
else:
    print('That movie is already in the list!')
print(unique_movies)

# Maybe we decide we do not want 'Avatar' on our list.
if 'Avatar' in unique_movies:
    unique_movies.remove('Avatar')
    print('Removed Avatar!')
else:
    print('Avatar was not in the list.')
print(unique_movies)

# What if a movie is missing? Let us try to find it.
search_title = input('Type a movie to search for: ').strip().title()
if search_title in unique_movies:
    print(search_title, 'is in our cleaned movie list!')
else:
    print(search_title, 'is not found.')
    

# What about sorting our movies?
sorted_movies = sorted(unique_movies)
print('Sorted movie titles:')
print(sorted_movies)

# Sometimes we want just the movies that start with 'T'.
t_movies = [movie for movie in sorted_movies if movie.startswith('T')]
print('Movies starting with T:', t_movies)

# You can count how many movies you have.
print('Total number of cleaned movies:', len(unique_movies))

# Let us add extra info: a release year for each movie!
movie_years = {
    'The Matrix': 1999,
    'Inception': 2010,
    'Titanic': 1997,
    'The Godfather': 1972,
    'Spider-Man': 2002,
    'Star Wars': 1977,
    'Jurassic Park': 1993
}
print(movie_years)

# Let us show all movies released after 2000.
for m, y in movie_years.items():
    if y > 2000:
        print(m, '-', y)
        

# Let us merge two small movie lists.
old_movies = ['E.T.', 'Back to the Future']
all_movies = sorted_movies + old_movies
print('Combined list:', all_movies)

# Let us try a tiny real-world style dataset with errors.
messy_data = [
    {'title': 'Inception ', 'year': '2010'},
    {'title': ' the godfather', 'year': '1972'},
    {'title': 'Spider-man', 'year': None},
    {'title': 'titanic', 'year': ''},
    {'title': 'Avatar', 'year': '2009'},
    {'title': '', 'year': '1982'}
]
for entry in messy_data:
    print(entry)
    

# Let us clean up the messy movie dataset.
fixed_movies = []
for entry in messy_data:
    title = entry['title'].strip().title()
    year_str = entry['year']
    try:
        year = int(year_str)
    except:
        year = None
    if title != '' and year:
        fixed_movies.append({'title': title, 'year': year})
print('Cleaned dataset:')
for m in fixed_movies:
    print(m)
    

# Mini-project: Find all movies between two years.
start = int(input('Start year: '))
end = int(input('End year: '))
matching = [m for m in fixed_movies if start <= m['year'] <= end]
print('Movies in that range:')
for m in matching:
    print(m['title'], '-', m['year'])
    

# Extra: Find oldest and newest movie in the clean dataset.
if fixed_movies:
    oldest = min(fixed_movies, key=lambda m: m['year'])
    newest = max(fixed_movies, key=lambda m: m['year'])
    print('Oldest:', oldest['title'], '-', oldest['year'])
    print('Newest:', newest['title'], '-', newest['year'])
    

# Sometimes, users enter numbers or funny symbols instead of letters.
test_titles = ['Shrek!', 'Up#', ' the 40-Year-Old Virgin ', 'Toy-Story']
for t in test_titles:
    clean_t = ''.join([c for c in t if c.isalnum() or c.isspace()]).strip().title()
    print('Clean title:', clean_t)
    

# Tip: If you want to undo a change, use list slices.
original = unique_movies.copy()
removed = unique_movies.pop()
print('Latest list:', unique_movies)
unique_movies = original  # Revert
print('Reverted:', unique_movies)