checkflix.py

# Raymond Ho
# Oct 7, 2014

""" 
Checks if the movie / TV show you've been waiting for is finally up on Netflix,
or if they have new seasons / episodes, whatever. Only works if Netflix updated
in the past two weeks.
"""

from urllib import request, parse  # Used to generate URLs and open links
from bs4 import BeautifulSoup  # Used to parse HTML

BASEURL = 'http://instantwatcher.com/'
INSTANTWATCHER = BASEURL + '/titles/popular_new/'

# This is your list of TV shows and movies, checks if updated on netflix.
my_movies = ['Walking Dead',
            'Vampire Diaries',
            'Pretty Little Liars',
            'Blacklist',
            'Originals',
            'Bones'
            ]

def check_page(url):
    """ Returns a list of movies/link given a link """

    link_soup = BeautifulSoup(request.urlopen(url).read())

    results = []
    for link in link_soup.findAll('a', {'class': 'title-list-item-link title-detail-link'}):
        pair = link.text, BASEURL+link.get('href')
        results.append(pair)

    return results

def check_all_pages(link):
    """ Gets the total movies/link from all pages """

    total_pages = 6
    total_result = []

    for page in range(1, total_pages+1):
        print ('Checking page:', page)
        link_page = link + str(page)
        # Combine list
        total_result += check_page(link_page)

    return total_result

def main():

    movies = check_all_pages(INSTANTWATCHER)
    results = []

    # Check if any matches found
    for movie in movies:
        for my_movie in my_movies:
            if my_movie.lower() in movie[0].lower():
                results.append(movie)

    # Print the results
    if not results:
        print('\nSorry, nothing found.')
    else:
        print('\nI found the following:\n')
        for movie in results:
            print(movie[0], '(' + movie[1] + ')')

if __name__ == '__main__':
    main()
    print()