plex_list_to_collection_v3

#!/usr/bin/python
# -*- coding: utf-8 -*-

import requests
from math import ceil
from plexapi.server import PlexServer
from lxml.html import parse
from plexapi.utils import NA

### Plex server details ###
PLEX_URL = 'http://127.0.0.1:32400'
PLEX_TOKEN = 'XXXXXXX'

### Existing movie library details ###
MOVIE_LIBRARY_NAME = 'Movies'
LIST_ID = 'ls027955354'

IMDB_LIST_URL = 'http://www.imdb.com/list/{}/?view=compact&sort=listorian:asc&defaults=1&' \
                'lists={}&mode=detail&page='.format(LIST_ID, LIST_ID)
IMDB_COLLECTION_NAME = 'Independent_Spirit_Best_Film'

def add_collection(library_key, rating_key):
    headers = {"X-Plex-Token": PLEX_TOKEN}
    params = {"type": 1,
              "id": rating_key,
              "collection[0].tag.tag": IMDB_COLLECTION_NAME,
              "collection.locked": 1
              }

    url = "{base_url}/library/sections/{library}/all".format(base_url=PLEX_URL, library=library_key)
    r = requests.put(url, headers=headers, params=params)

def run_imdb_list():
    try:
        plex = PlexServer(PLEX_URL, PLEX_TOKEN)
    except:
        print("No Plex server found at: {base_url}".format(base_url=PLEX_URL))
        print("Exiting script.")
        return [], 0

    # Get the IMDB  list
    print("Retrieving the IMDB list...")
    i = 1
    remaining_pages = 0
    url = IMDB_LIST_URL + str(i)
    tree = parse(url)
    total_tiles = int(tree.xpath("//div[@class='desc lister-total-num-results']/text()")[0].strip().split(' ')[0].replace(",", ""))
    list_picture_titles = tree.xpath("//div[@class='lister-item-content']//h3[@class='lister-item-header']//a/text()")
    list_picture_years = tree.xpath("//div[@class='lister-item-content']//h3[@class='lister-item-header']//span[@class='lister-item-year text-muted unbold']/text()")
    list_picture_ids = [a.split('/')[2] for a in
                        tree.xpath("//div[@class='lister-item-content']//h3[@class='lister-item-header']//a//@href")]
    if (total_tiles > 100):
        total_tiles = total_tiles - 100
        remaining_pages = int(ceil(total_tiles / 100.0))
        i = i + 1

    while(remaining_pages > 0):
        url = IMDB_LIST_URL + str(i)
        tree = parse(url)
        list_picture_titles = list_picture_titles + tree.xpath(
            "//div[@class='lister-item-content']//h3[@class='lister-item-header']//a/text()")
        list_picture_years = list_picture_years + tree.xpath(
            "//div[@class='lister-item-content']//h3[@class='lister-item-header']//span[@class='lister-item-year text-muted unbold']/text()")
        list_picture_ids = list_picture_ids + [a.split('/')[2] for a in
                            tree.xpath(
                                "//div[@class='lister-item-content']//h3[@class='lister-item-header']//a//@href")]

        remaining_pages = remaining_pages - 1
        i = i + 1

    # Get list of movies from the Plex server
    print("Retrieving a list of movies from the '{library}' library in Plex...".format(library=MOVIE_LIBRARY_NAME))
    try:
        movie_library = plex.library.section(MOVIE_LIBRARY_NAME)
        movie_library_key = movie_library.key
        all_movies = movie_library.all()
    except:
        print("The '{library}' library does not exist in Plex.".format(library=MOVIE_LIBRARY_NAME))
        print("Exiting script.")
        return

    # Create a dictionary of {imdb_id: movie}
    imdb_map = {}
    for m in all_movies:
        if m.guid != NA and 'imdb://' in m.guid:
            imdb_id = m.guid.split('imdb://')[1].split('?')[0]
            if imdb_id in list_picture_ids:
                imdb_map[imdb_id] = m


    print("Setting the collection for the '{}' library...".format(MOVIE_LIBRARY_NAME))
    in_library_idx = []
    for i, imdb_id in enumerate(list_picture_ids):
        movie = imdb_map.pop(imdb_id, None)
        if movie:
            add_collection(movie_library_key, movie.ratingKey)
            in_library_idx.append(i)

    # Get list of missing movies
    missing_imdb_list = [(idx, imdb) for idx, imdb in enumerate(zip(list_picture_ids, list_picture_titles, list_picture_years))
                        if idx not in in_library_idx]

    return missing_imdb_list, len(list_picture_ids)

if __name__ == "__main__":
    print("===================================================================")
    import time
    print time.strftime("%d/%m/%Y")
    print("===================================================================\n")

    missing_imdb_list, list_count = run_imdb_list()

    print("\n===================================================================\n")
    print("Number of IMDB movies in the library: {count}".format(count=list_count - len(missing_imdb_list)))
    print("Number of missing IMDB movies: {count}".format(count=len(missing_imdb_list)))
    print("\nList of missing movies:\n")

    for idx, (imdb_id, title, year) in missing_imdb_list:
        print("{idx}\t{imdb_id}\t{title} {year}".format(idx=idx + 1, imdb_id=imdb_id, title=title.encode('utf-8'),
                                                        year=year.encode('utf-8')))

    print("\n===================================================================")
    print("                               Done!                               ")
    print("===================================================================\n")
f = open('taschen_decadas.txt','w')
f.write("===================================================================\n")
f.write(time.strftime("%d/%m/%Y") + '\n')
f.write("===================================================================\n")
f.write("\nNumber of IMDB movies in the library: {count}".format(count=list_count - len(missing_imdb_list)))
f.write("\nNumber of missing IMDB movies: {count}\n".format(count=len(missing_imdb_list)))
f.write("\nList of missing movies:")

for idx, (imdb_id, title, year) in missing_imdb_list:
    f.write("\n{idx}\t{imdb_id}\t{title} {year}".format(idx=idx + 1, imdb_id=imdb_id, title=title.encode('utf-8'),
                                                        year=year.encode('utf-8')))

f.write("\n===================================================================")
f.write("\n                               Done!                               ")
f.write("\n===================================================================")

   # raw_input("Press Enter to finish...")