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

67 lines
1.9 KiB
Python

from __future__ import unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2013, Malah <malah at neuf dot fr>'
'''
Le GORAFI.fr
'''
__author__ = '2013, Malah <malah at neuf dot fr>'
from calibre.web.feeds.news import BasicNewsRecipe
class LeGorafi(BasicNewsRecipe):
title = u'Le GORAFI.fr'
__author__ = 'Malah, LAntoine'
description = u"Depuis 1826, toute l'information de sources contradictoires"
oldest_article = 7
language = 'fr'
max_articles_per_feed = 100
use_embedded_content = False
no_stylesheets = True
compress_news_images = True
extra_css = '''
img {
max-width: 100% !important;
height: auto !important;
}
'''
keep_only_tags = [
dict(name='h1'),
dict(name='img', attrs={'class': 'attachment- size- wp-post-image'}),
dict(name='div', attrs={'id': 'mvp-content-main'}),
]
remove_tags = [
dict(name='div', attrs={'class': 'heateor_sss_sharing_container'}),
]
feeds = ['http://www.legorafi.fr/feed/']
def preprocess_html(self, soup):
for img in soup.findAll('img'):
if 'svg' in img['src']:
img.decompose() # Removes the tag entirely
return soup
def is_cover(article):
return 'gorafi-magazine' in article.url
def get_cover_url(self):
feeds = BasicNewsRecipe.parse_feeds(self)
for feed in feeds:
for article in feed.articles:
if LeGorafi.is_cover(article):
soup = self.index_to_soup(article.url)
img = soup.select_one('#mvp-post-feat-img img')
return img['data-lazy-src']
print('No cover found')
return None
def parse_feeds(self):
feeds = BasicNewsRecipe.parse_feeds(self)
for feed in feeds:
for article in feed.articles:
if LeGorafi.is_cover(article):
feed.articles.remove(article)
return feeds