#!/usr/bin/env python
##
# Title:        Il Post recipe for calibre
# Author:       Marco Scirea, based on a recipe by frafra
# Contact:      marco.prolog at gmail.com
##
# License:      GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html
# Copyright:    Copyright 2019 Marco Scirea
##

from __future__ import absolute_import, division, print_function, unicode_literals
from calibre.web.feeds.news import BasicNewsRecipe
from datetime import date, timedelta

dates = [ date.today().strftime('%Y/%m/%d'), (date.today() - timedelta(1)).strftime('%Y/%m/%d') ]

# ----------- CUSTOMIZATION OPTIONS START -----------

# Comment (add # in front) to disable the sections you are not interested in
# Commenta (aggiungi # davanti alla riga) per disabilitare le sezioni che non vuoi scaricare
sections = [
    ("Italia", "https://www.ilpost.it/italia/"),
    ("Mondo", "https://www.ilpost.it/mondo/"),
    ("Politica", "https://www.ilpost.it/politica/"),
    ("Tecnologia", "https://www.ilpost.it/tecnologia/"),
    ("Internet", "https://www.ilpost.it/internet/"),
    ("Scienza", "https://www.ilpost.it/scienza/"),
    ("Cultura", "https://www.ilpost.it/cultura/"),
    ("Economia", "https://www.ilpost.it/economia/"),
    ("Sport", "https://www.ilpost.it/sport/"),
    ("Media", "https://www.ilpost.it/media/"),
    ("Moda", "https://www.ilpost.it/moda/"),
    ("Libri", "https://www.ilpost.it/libri/"),
    ("Auto", "https://www.ilpost.it/auto/"),
    ("Konrad", "https://www.ilpost.it/europa/"),
]

# ----------- CUSTOMIZATION OPTIONS OVER -----------


class IlPost(BasicNewsRecipe):
    __author__ = 'Marco Scirea, unkn0wn'
    __license__ = 'GPL v3'
    __copyright__ = '2019, Marco Scirea <marco.prolog at gmail.com>'

    title = "Il Post"
    language = "it"
    description = (
        'Puoi decidere quali sezioni scaricare modificando la ricetta.'
        ' Di default le immagini sono convertite in scala di grigio per risparmiare spazio,'
        ' la ricetta puo\' essere configurata per tenerle a colori'
    )
    tags = "news"
    masthead_url = 'https://www.ilpost.it/error/images/ilpost.svg'
    ignore_duplicate_articles = {"title", "url"}
    no_stylesheets = True
    extra_css = ' .wp-caption-text { font-size:small; } '
    keep_only_tags = [dict(name='main', attrs={'id':lambda x: x and x.startswith('index_main-content__')})]
    remove_tags_before = [dict(name='article')]
    remove_tags_after = [dict(name='article')]
    remove_tags = [
        dict(attrs={'class':lambda x: x and x.startswith(
            ('index_actions__', 'index_il-post-comments___', 'index_art_tag__')
        )}),
        dict(attrs={'id':'audioPlayerArticle'})
    ]

    def parse_page(self, name, url):
        self.log.debug(url)
        soup = self.index_to_soup(url)
        entries = []
        for article in soup.findAll('article'):
            for link in article.findAll('a', href=True):
                if not any(x in link['href'] for x in dates):
                    continue
                title = self.tag_to_string(link.h2)
                desc = self.tag_to_string(link.p)
                if not title:
                    continue
                self.log('\t', title)
                entries.append({
                    "url": link["href"],
                    "title": title,
                    "description": desc
                })
        return (name, entries)

    def parse_index(self):
        feeds = []
        for section in sections:
            feeds.append(self.parse_page(section[0], section[1]))
        return feeds