calibre/recipes/revista_muy.recipe
unkn0wn 687d9a98a5
Update revista_muy.recipe
magzter cover
2025-06-27 11:04:54 +05:30

61 lines
2.2 KiB
Python

#!/usr/bin/env python
from calibre.web.feeds.news import BasicNewsRecipe, classes
class RevistaMuyInteresante(BasicNewsRecipe):
title = 'Revista Muy Interesante'
__author__ = 'unkn0wn'
description = 'Revista Muy Interesante, es un sitio con información sobre ciencia, tecnología, historia, sociedad, medio ambiente, etc.'
language = 'es'
encoding = 'utf-8'
no_stylesheets = True
remove_javascript = True
remove_attributes = ['style', 'height', 'width']
ignore_duplicate_articles = {'url'}
masthead_url = 'https://www.muyinteresante.com/static/img/logo_web.svg'
resolve_internal_links = True
def get_cover_url(self):
soup = self.index_to_soup(
'https://www.magzter.com/ES/Zinet-Media-Global/Muy-Interesante-Espa%C3%B1a/Science/1806044'
)
return soup.find('img', id=lambda s: s and 'mgd__lhd__cover' in s.split())['src']
extra_css = '''
.c-detail__bar, .c-detail__author, .c-detail__media__txt { font-size:small; }
.default-epigraph { font-style:italic; }
'''
keep_only_tags = [dict(name='article', attrs={'class':'c-detail'})]
remove_tags = [
dict(name=['aside', 'svg', 'script']),
classes('c-detail__share')
]
def preprocess_html(self, soup):
au = soup.find(**classes('c-detail__author'))
if au:
for p in au.findAll('p'):
p.name = 'div'
for h in soup.findAll(['h2', 'h3']):
h.name = 'h4'
return soup
def parse_index(self):
soup = self.index_to_soup('https://www.muyinteresante.com/')
ans = []
for articles in soup.findAll('article'):
a = articles.find('a', attrs={'class':'page-link', 'href':True})
if not a:
continue
title = self.tag_to_string(a)
url = a['href']
desc = ''
info = articles.find(**classes('c-article__info_content'))
if info:
desc = self.tag_to_string(info)
self.log('\t', title, '\n\t', desc, '\n\t\t', url)
ans.append({'title': title, 'url': url, 'description': desc})
return [('Articles', ans)]