def __init__(self, folder): self.folder = folder self.feeds = load_feeds(folder) self.entries = { feed: feed.get_entries() for feed in self.feeds } self.nlp = English()
def run(metadata_folder): global feeds, entries_metadata globals()['metadata_folder'] = metadata_folder feeds += load_feeds(metadata_folder) for feed in feeds: entries_metadata[feed.name] = feed.get_entries() return app.run(threaded=False, port=8080, debug=False)
def run(metadata_folder): global feeds, entries_metadata globals()['metadata_folder'] = metadata_folder feeds += load_feeds(metadata_folder) for feed in feeds: entries_metadata[feed.name] = feed.get_entries() return app.run( threaded=False, port=8080, debug=False )
def load_entries(folder, it=None): if it is None: feeds = load_feeds(folder) return [ BreakableEntry(entry.folder, feed, entry.get_metadata()) for feed in feeds for entry in feed.get_entries() if entry.data.get('newsbreaker') ] else: return [ BreakableEntry(entry.folder, feed, entry.get_metadata()) for feed, entries in it for entry in entries if entry.data.get('newsbreaker') ]
# -*- coding: utf-8-*- # Author: Álvaro Parafita ([email protected]) import pandas as pd from newsparser.data import load_feeds folder = '/Users/alvaro_parafita/Desktop/TFG/data' # Display statistics feeds = load_feeds(folder) entries = { feed: feed.get_entries() for feed in feeds } df = pd.DataFrame( [ [ feed.name, len(entries[feed]), sum( not entry.data.get('filter', {}).get('discarded', True) for entry in entries[feed] ), sum( not entry.data.get('filter', {}).get('duplicate', True) for entry in entries[feed] ), sum( not entry.data.get('filter', {}).get('news_agency_discarded', True) for entry in entries[feed] ), sum(
# -*- coding: utf-8-*- # Author: Álvaro Parafita ([email protected]) from newsparser.data import load_feeds folder = '/Users/alvaro_parafita/Desktop/TFG/data' feeds = load_feeds(folder) for feed in feeds: e = feed.get_entries(low=-1, high=feed.num_entries)[0] print(feed.name, e.published)
def __init__(self, folder): self.folder = folder self.feeds = load_feeds(folder) self.entries = {feed: feed.get_entries() for feed in self.feeds} self.nlp = English()