calibre/recipes/nypost.recipe
2024-11-03 10:07:57 +05:30

80 lines
3.0 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe, classes
class NewYorkPost(BasicNewsRecipe):
title = 'New York Post'
__author__ = 'unkn0wn'
description = 'Daily newspaper'
publisher = 'NYP Holdings, Inc.'
category = 'news, politics, USA'
oldest_article = 1
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
language = 'en_US'
remove_attributes = ['style', 'height', 'width']
masthead_url = 'https://static.storied.co/gQlwL7PA4X5XM6b8/projects/JYX3m27B8zP9BW4D/assets/images/81e851fd6c5d8fc747c41064d8aee316.png'
extra_css = '.byline, .date, .article-header__top, .calibre-nuked-tag-figcaption { font-size: small; }'
def get_cover_url(self):
soup = self.index_to_soup('https://www.frontpages.com/new-york-post/')
return (
'https://www.frontpages.com'
+ soup.find('img', attrs={'id': 'giornale-img'})['src']
)
recipe_specific_options = {
'days': {
'short': 'Oldest article to download from this news source. In days ',
'long': 'For example, 0.5, gives you articles from the past 12 hours',
'default': str(oldest_article),
}
}
def __init__(self, *args, **kwargs):
BasicNewsRecipe.__init__(self, *args, **kwargs)
d = self.recipe_specific_options.get('days')
if d and isinstance(d, str):
self.oldest_article = float(d)
ignore_duplicate_articles = {'title', 'url'}
keep_only_tags = [
classes('article-header single__content'),
]
remove_tags = [
dict(attrs={'id': ['connatix-outstream-video']}),
classes(
'article-header__social-icons wpcom-liveblog-container nyp-s2n-wrapper '
'nyp-slideshow-modal-image__icon inline-module inline-module__inner'
),
dict(name=['svg', 'link', 'meta', 'aside']),
]
# https://nypost.com/rssfeeds/
feeds = [
('US-News', 'https://nypost.com/us-news/feed/'),
('Metro', 'https://nypost.com/metro/feed/'),
('Politics', 'https://nypost.com/politics/feed/'),
('World News', 'https://nypost.com/world-news/feed/'),
('Sports', 'https://nypost.com/sports/feed/'),
('Business', 'https://nypost.com/business/feed/'),
('Opinion', 'https://nypost.com/opinion/feed/'),
('Entertainment', 'https://nypost.com/entertainment/feed/'),
('Fashion & Beauty', 'https://nypost.com/fashion-and-beauty/feed/'),
('Lifestyle', 'https://nypost.com/lifestyle/feed/'),
('Tech', 'https://nypost.com/tech/feed/'),
('Media', 'https://nypost.com/media/feed/'),
('Real Estate', 'https://nypost.com/real-estate/feed/'),
('Page Six', 'https://pagesix.com/feed/'),
('Others', 'https://nypost.com/feed/'),
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'src': True}):
img['src'] = img['src'].split('?')[0] + '?w=600'
return soup