from bs4 import BeautifulSoup from progress.bar import Bar from imdb_utils import IMDbUtils from wiki_utils import WikiUtils JACKNET_WIKI_URL = "https://wiki.jacknet.io" def get_vcinema_viewings(token_id, token_secret): # Page ID of /Vcinema/CSV page_id = 11 html_page = WikiUtils.get_page_export_html(page_id, JACKNET_WIKI_URL, token_id, token_secret) soup = BeautifulSoup(html_page, 'html.parser') elements = soup.find("code").text.strip().split("\n") headers = elements.pop(0).split(",") viewings = [dict(zip(headers, row.split(","))) for row in elements] return viewings def add_imdb_data_to_viewings(viewings, field_name): viewing_count = len(viewings) with Bar('Processing', max=viewing_count) as bar: bar.message = "Processing" bar.suffix = '%(percent).1f%% - %(eta)ds' for (viewing_num, viewing) in enumerate(viewings): imdb_entry = IMDbUtils.get_movie(viewing['imdb_id']) viewing[field_name] = imdb_entry[field_name] bar.next() bar.finish() def filter_viewings(viewings, filter_field, remove_duplicates=True): viewings_filtered = {} for viewing in viewings: viewing_field = viewing[filter_field] if viewing_field in viewings_filtered.keys(): if not remove_duplicates or not any(x['imdb_id'] == viewing['imdb_id'] for x in viewings_filtered[viewing_field]): viewings_filtered[viewing_field] += [viewing] else: viewings_filtered[viewing[filter_field]] = [viewing] return viewings_filtered