calibre/recipes/ap.recipe
Kovid Goyal 813296adb5
pep8
2025-03-28 07:35:18 +05:30

82 lines
2.8 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
'''
https://apnews.com
'''
from calibre.web.feeds.news import BasicNewsRecipe, classes
class AssociatedPress(BasicNewsRecipe):
title = 'Associated Press'
description = (
'Read the latest headlines, breaking news, and videos at APNews.com, the definitive '
'source for independent journalism from every corner of the globe. Articles from Front Page.'
)
__author__ = 'unkn0wn'
language = 'en'
encoding = 'utf-8'
no_stylesheets = True
remove_javascript = True
ignore_duplicate_articles = {'url'}
remove_empty_feeds = False
remove_attributes = ['style', 'height', 'width']
simultaneous_downloads = 1
cover_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/0/0c/Associated_Press_logo_2012.svg/662px-Associated_Press_logo_2012.svg.png'
keep_only_tags = [
classes('StoryPage-lede-content Page-lead Page-byline-info RichTextStoryBody'),
]
remove_tags = [
classes('displayNone Advertisement HTMLModuleEnhancement AudioEnhancement'),
dict(
name=[
'source',
'button',
'svg',
'template',
'video',
'astro-island',
'iframe',
'document',
]
),
dict(attrs={'data-parsely-title': 'Related Stories'}),
]
extra_css = '''
.Page-byline-info, .Page-breadcrumbs, .CarouselSlide-info, .Figure-caption { font-size:small; }
img {display:block; margin:0 auto;}
em { color: #202020; }
'''
def parse_index(self):
feeds = []
soup = self.index_to_soup('https://apnews.com')
for a in soup.findAll(
'a',
attrs={'href': lambda x: x and x.startswith('https://apnews.com/article/')},
):
url = a['href']
title = self.tag_to_string(a)
self.log(title, '\n\t', url)
feeds.append({'title': title, 'url': url})
return [('Articles', feeds)]
def preprocess_html(self, soup):
for v in soup.findAll('bsp-jw-player', attrs={'poster': True}):
v.name = 'img'
v.attrs = {'src': v.get('poster', '')}
for st in soup.findAll(**classes('CarouselSlide-infoDescription Figure-caption')):
if p := st.find('p'):
p.name = 'span'
for h in soup.findAll(['h2', 'h3']):
h.name = 'h4'
for img in soup.findAll('img', attrs={'srcset': True}):
img['src'] = img['srcset'].split()[0]
for img_ in soup.findAll(
'img', attrs={'data-flickity-lazyload-srcset': True, 'srcset': False}
):
img_['src'] = img_['data-flickity-lazyload-srcset'].split()[0]
return soup