calibre/recipes/el_diplo.recipe
2025-01-24 11:14:14 +01:00

148 lines
4.4 KiB
Python

# -*- mode: python; coding: utf-8; -*-
# vim: set syntax=python fileencoding=utf-8
__license__ = 'GPL v3'
__copyright__ = '2023, Tomás Di Domenico <tdido at tdido.eu>'
'''
www.eldiplo.org
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ElDiplo2023(BasicNewsRecipe):
title = 'Le Monde Diplomatique - cono sur'
__author__ = 'Tomás Di Domenico'
description = 'Publicación de Le Monde Diplomatique para el cono sur.'
publisher = 'Capital Intelectual'
category = 'News, Politics, Argentina, Uruguay, Paraguay, South America, World'
oldest_article = 31
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'es_AR'
remove_empty_feeds = True
publication_type = 'magazine'
delay = 1
simultaneous_downloads = 1
timeout = 8
needs_subscription = True
ignore_duplicate_articles = {'url'}
temp_files = []
fetch_retries = 10
handle_gzip = True
compress_news_images = True
scale_news_images_to_device = True
masthead_url = (
'https://www.eldiplo.org/wp-content/themes/_polenta_/assets/diplo.png'
)
INDEX = 'https://www.eldiplo.org/'
conversion_options = {'series': 'El Dipló', 'publisher': publisher, 'base_font_size': 8, 'tags': category}
keep_only_tags = [dict(name=['article'])]
remove_tags = [dict(name=['button'])]
extra_css = '''
.entry-title {
text-align: center;
}
.text-right {
text-align: right;
}
.bajada {
display: block;
font-family: sans-serif;
text-align: center;
font-size: 110%;
padding: 2%;
}
.Destacado{
display: block;
font-size: 120%;
font-weight: bold;
font-style: italic;
padding-left: 10%;
padding-right: 10%;
}
'''
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open(self.INDEX)
if self.username is not None and self.password is not None:
br.select_form(id='loginform')
br['log'] = self.username
br['pwd'] = self.password
br.submit()
return br
def get_cover_url(self):
soup_index = self.index_to_soup(self.INDEX)
tag_sumario = soup_index.find('span', text='Sumario')
url_sumario = 'https://www.eldiplo.org' + tag_sumario.parent['href']
soup = self.index_to_soup(url_sumario)
container = soup.find('div', class_='px-16')
url = container.find('img')['src']
return getattr(self, 'cover_url', url)
def _process_article(self, article):
url = article.find('a', href=True, attrs={'class': 'title'})['href']
title = self.tag_to_string(article).replace('Editorial', 'Editorial: ')
try:
title, authors = title.split(', por')
authors = f'por {authors}'
except ValueError:
authors = ''
self.log('title: ', title, ' url: ', url)
return {'title': title, 'url': url, 'description': authors, 'date': ''}
def preprocess_html(self, soup):
font_size = '90%'
# make the footnotes smaller
for p in soup.find('div', id='nota_pie').findChildren('p', recursive=False):
p['style'] = f'font-size: {font_size};'
return soup
def parse_index(self):
soup_index = self.index_to_soup(self.INDEX)
tag_sumario = soup_index.find('span', text='Sumario')
if tag_sumario is None:
return None
url_sumario = 'https://www.eldiplo.org' + tag_sumario.parent['href']
self.log(url_sumario)
soup_sumario = self.index_to_soup(url_sumario)
feeds = []
articles = []
dossiers = []
sumario = soup_sumario.find('div', class_='sumario')
for section in sumario.find_all('div', recursive=False):
classes = section.attrs['class']
if 'dossier' in classes:
dtitle = self.tag_to_string(section.find('h3'))
darticles = []
for article in section.find_all('div', recursive=False):
darticles.append(self._process_article(article))
dossiers.append((dtitle, darticles))
else:
articles.append(self._process_article(section))
feeds.append(('Artículos', articles))
feeds += dossiers
return feeds