calibre/recipes/usatoday.recipe
2025-01-24 11:14:22 +01:00

98 lines
3.0 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
usatoday.com
'''
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)})
def absurl(url):
if url.startswith('/'):
return 'https://www.usatoday.com' + url
class USAToday(BasicNewsRecipe):
title = 'USA Today'
__author__ = 'Kovid Goyal, unkn0wn'
description = 'newspaper'
encoding = 'utf-8'
language = 'en_US'
use_embedded_content = False
timefmt = ' [%d %b %Y]'
max_articles_per_feed = 25
no_stylesheets = True
keep_only_tags = [
classes('gnt_ar_hl gnt_ar_by gnt_ar_b topper__inner in-depth-content'),
]
remove_tags = [
classes('component--pullquote__icon gnt_ss gnt_em_vp__tp'),
dict(attrs={'aria-label': ['advertisement']}),
dict(name=['link', 'media-gallery', 'button']),
]
extra_css = '''
h1, h2 {
font-size:xx-large;
font-family:Arial,Helvetica,sans-serif;}
#post-attributes, .info,
.clear {
font-size:xx-small; color:#4D4D4D;
font-family:Arial,Helvetica,sans-serif;
}
#post-body,
#content {
font-size:medium;
font-family:Arial,Helvetica,sans-serif;
}
.gnt_em_img_ccw__cap {
font-size:small;
text-align:center;
}
'''
ignore_duplicate_articles = {'title', 'url'}
resolve_internal_links = True
remove_empty_feeds = True
def parse_index(self):
index = 'https://www.usatoday.com/'
sections = [
'news', 'opinion', 'tech', 'entertainment', 'money', 'sports', 'travel', 'life', 'investigations',
]
feeds = []
soup = self.index_to_soup(index)
for sec in sections:
section = sec.capitalize()
self.log(section)
articles = []
for a in soup.findAll('a', attrs={'href':lambda x: x and x.startswith('/story/' + sec + '/')}):
url = absurl(a['href'].split('?')[0])
if url == index + '/story/' + sec + '/':
continue
title = self.tag_to_string(a)
self.log('\t', title, '\n\t\t', url)
articles.append({'title': title, 'url': url})
if articles:
feeds.append((section, articles))
return feeds
def preprocess_html(self, soup):
for img in soup.findAll('img', src=True):
img['src'] = 'https://www.usatoday.com' + img['src']
for div in soup.findAll(attrs={'data-c-caption':True}):
div.string = div['data-c-caption']
return soup