mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-05-08 10:32:28 +00:00
Luca Caviness
d80a145db0
Same fix as Financial Times: use category listing pages instead of individual newspaper pages which no longer have the giornale-img element. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
73 lines
2.7 KiB
Python
73 lines
2.7 KiB
Python
#!/usr/bin/env python
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
|
|
|
|
def classes(classes):
|
|
q = frozenset(classes.split(' '))
|
|
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
|
|
|
|
|
|
class NewZealandHerald(BasicNewsRecipe):
|
|
title = 'New Zealand Herald'
|
|
__author__ = 'unkn0wn'
|
|
description = 'Daily news'
|
|
timefmt = ' [%d %b, %Y]'
|
|
language = 'en_NZ'
|
|
oldest_article = 1
|
|
remove_attributes = ['style', 'height', 'width']
|
|
use_embedded_content = False
|
|
encoding = 'utf-8'
|
|
ignore_duplicate_articles = {'url'}
|
|
no_stylesheets = True
|
|
resolve_internal_links = True
|
|
remove_empty_feeds = True
|
|
|
|
def get_cover_url(self):
|
|
soup = self.index_to_soup('https://www.frontpages.com/new-zealand-newspapers/')
|
|
for img in soup.findAll('img', src=True):
|
|
if 'new-zealand-herald' in img['src']:
|
|
return 'https://www.frontpages.com' + img['src']
|
|
|
|
extra_css = '''
|
|
[data-test-ui="author--text--body"], .article-media__caption {font-size: small;}
|
|
'''
|
|
|
|
keep_only_tags = [
|
|
dict(
|
|
attrs={
|
|
'data-test-ui': [
|
|
'article__heading',
|
|
'author--text--body',
|
|
'article-top-body',
|
|
'article-bottom-body',
|
|
]
|
|
}
|
|
),
|
|
]
|
|
|
|
remove_tags = [classes('related-articles article__ad-wrapper article__action-bar')]
|
|
|
|
feeds = [
|
|
('Business', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000003.xml'),
|
|
('World', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000002.xml'),
|
|
('National', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000001.xml'),
|
|
('Entertainment', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_001501119.xml'),
|
|
('Travel', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000007.xml'),
|
|
('Opinion', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000466.xml'),
|
|
('Life & Style', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000006.xml'),
|
|
('Technology', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000005.xml'),
|
|
('Sport', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000004.xml'),
|
|
('Motoring', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000009.xml'),
|
|
('Property', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000008.xml'),
|
|
]
|
|
|
|
def preprocess_html(self, soup, *a):
|
|
for img in soup.findAll('img', attrs={'data-srcset': True}):
|
|
for x in img['data-srcset'].split(','):
|
|
if '768w' in x:
|
|
img['src'] = x.split()[0]
|
|
break
|
|
else:
|
|
img['src'] = img['data-srcset'].split(',')[-1].split()[0]
|
|
return soup
|