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

76 lines
2.7 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import absolute_import, division, print_function, unicode_literals
from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
)
class Federalist(BasicNewsRecipe):
title = 'The Federalist'
__author__ = 'Kovid Goyal'
language = 'en'
oldest_article = 10
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
remove_attributes = ['xmlns', 'lang', 'style', 'width', 'height']
extra_css = '''
.shortbio,.article-excerpt{font-style: italic}
.article-author-details,.article-author-description,.article-meta-author,.article-meta-date,.article-thumbnail-caption{font-size: small}
'''
keep_only_tags = [
classes(
'title-lg article-thumbnail post-categories article-excerpt article-author-details'
' article-meta-author article-meta-date article-content article-body shortbio entry-header'
' byline-month byline-standard alpha-byline article-author-description article-author-details'),
]
remove_tags = [
dict(name=['meta', 'link']),
classes('auth-ad article-share article-tags attachment-post-thumbnail attachment-author-bio'),
]
feeds = [
('All', 'https://thefederalist.com/feed/'),
]
# def parse_index(self):
# return [('Articles', [
# {
# 'title': 'test',
# 'url': 'https://thefederalist.com/2022/03/09/propaganda-press-wield-bidens-russia-blame-game-to-gaslight-americans-about-expensive-gas/'},
# {
# 'title': 'test2',
# 'url': 'https://thefederalist.com/2022/03/10/white-house-will-blame-anyone-but-biden-for-februarys-7-9-inflation-jump/',
# }
# ])]
def preprocess_raw_html_(self, raw_html, url):
soup = self.index_to_soup(raw_html)
# this website puts article-thumbnail images inside article-body in
# some articles and outside it in others, so we have to special case it
for ab in soup.findAll(**classes('article-body')):
for img in ab.findAll(**classes('article-thumbnail')):
del img['class']
return str(soup)
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-lazy-src': True}):
img['src'] = img['data-lazy-src']
seen = set()
for img in soup.findAll('img', src=True):
src = img['src']
if src in seen:
img.extract()
seen.add(src)
return soup