#!/usr/bin/python3 """ Simple script that extracts information from Télé 7 jours and TMDB to help choosing the movies you want to record with your Freebox Todo : * Prompt the user for movies he wants to record and plan them with the FB API """ import json import logging import requests import datetime import tmdbsimple import textwrap from bs4 import BeautifulSoup from collections import deque class Movie: def __init__(self): self.day = '' self.title = '' self.genre = '' self.channel = '' self.rating = '' self.original_title = '' self.overview = '' self.good = False self.tmdb_id = '' self.url = '' def __str__(self): return '{}: {} - {} ({})\n TMDB: {} - {}\n @ {}\n {}'.format( 'Today' if self.day == '' else self.day, self.title, self.genre, self.channel, self.rating, self.original_title, self.url, self.overview ) def __repr__(self): return 'Movie <{}({})>'.format(self.title, self.rating) class TVGuideScraper: TV_GUIDE_URL = 'https://www.programme-television.org/{}?bouquet=tnt' def findAllMovies(): movies = [] days = deque(['lundi', 'mardi', 'mercredi', 'jeudi', 'vendredi', 'samedi', 'dimanche']) offset = datetime.datetime.today().weekday() days.rotate(-1-offset) days.appendleft('') for day in days: movies += TVGuideScraper._getMovies(day) logging.info('Found the following movies: {}'.format(movies)) return movies @staticmethod def _getMovies(day=''): logging.info('Connecting to {}'.format(TVGuideScraper.TV_GUIDE_URL)) r = requests.get(TVGuideScraper.TV_GUIDE_URL.format(day)) r.raise_for_status() html = BeautifulSoup(r.text, 'html.parser') movies = [] for channel in html.select('.bloc_cnt'): if len(channel.select('em')): for movietag in channel.find_all(TVGuideScraper._tag_is_film): movie = Movie() movie.title = \ movietag.select('.texte_titre a')[0]['title'] movie.genre = movietag.select('.texte_cat a')[0].string movie.channel = channel.select('em')[0]\ .string.replace('Programme ', '') movie.day = day.title() logging.info('Found movie: {0!r}'.format(movie)) movies.append(movie) return movies @staticmethod def _tag_is_film(tag): """ Helper to check if a tag is a film """ return ( tag.has_attr('data-nature') and tag['data-nature'] == 'films-telefilms' ) class FreeboxMoviePlanner: def __init__(self, movies): logging.info('Opening config file: config.json') with open('config.json') as config_file: self.config = json.load(config_file) tmdbsimple.API_KEY = self.config['tmdb-api'] self.movies = movies def __repr__(self): result = 'FreeboxMoviePlanner = self.config['minimum-rating'] movie.url = 'https://www.themoviedb.org/movie/{}?language={}' \ .format(movie.tmdb_id, self.config['tmdb-language']) def filterBadRatings(self): self.movies = [movie for movie in self.movies if movie.good] def _findMovieOnTMDB(self, movie): logging.info("Searching for '{}' on TMDB".format(movie)) search = tmdbsimple.Search() search.movie(query=movie, language=self.config['tmdb-language']) if len(search.results): logging.info("Found '{}'".format( search.results[0]['title'] )) return search.results[0] else: logging.warning("'{}' not found on TMDB!".format(movie)) return [] if __name__ == '__main__': logging.basicConfig( level=logging.INFO, format=' %(asctime)s - %(levelname)s - %(message)s' ) fmp = FreeboxMoviePlanner(TVGuideScraper.findAllMovies()) fmp.findMoviesOnTMDB() fmp.filterBadRatings() fmp.printAllMovies()