Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/unkn0w7n/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2025-05-11 10:03:37 +05:30
commit b39a4b86a9
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 47 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

80
recipes/nzherald.recipe
View File

@ -1,56 +1,70 @@
#!/usr/bin/env python
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
def classes(classes): def classes(classes):
q = frozenset(classes.split(' ')) q = frozenset(classes.split(' '))
return dict(attrs={ return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class NewZealandHerald(BasicNewsRecipe): class NewZealandHerald(BasicNewsRecipe):
title = 'New Zealand Herald' title = 'New Zealand Herald'
__author__ = 'Kovid Goyal' __author__ = 'unkn0wn'
description = 'Daily news' description = 'Daily news'
timefmt = ' [%d %b, %Y]' timefmt = ' [%d %b, %Y]'
language = 'en_NZ' language = 'en_NZ'
oldest_article = 2.5 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/the-new-zealand-herald/')
return (
'https://www.frontpages.com'
+ soup.find('img', attrs={'id': 'giornale-img'})['src']
)
extra_css = '.article-media__caption {font-size: small;}'
keep_only_tags = [ keep_only_tags = [
classes('article-header'), dict(
dict(id='article-content'), attrs={
'data-test-ui': [
'article__heading',
'author--text--body',
'article-top-body',
'article-bottom-body',
]
}
),
] ]
remove_tags = [ remove_tags = [classes('article__ad-wrapper article__action-bar')]
classes('ad-container pb-f-video-video-player pb-f-article-related-articles social-shares')
]
feeds = [ feeds = [
('Business', ('Business', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000003.xml'),
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000003.xml'), ('World', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000002.xml'),
('World', ('National', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000001.xml'),
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000002.xml'), ('Entertainment', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_001501119.xml'),
('National', ('Travel', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000007.xml'),
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000001.xml'), ('Opinion', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000466.xml'),
('Entertainment', ('Life & Style', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000006.xml'),
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_001501119.xml'), ('Technology', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000005.xml'),
('Travel', ('Sport', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000004.xml'),
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000007.xml'), ('Motoring', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000009.xml'),
('Opinion', ('Property', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000008.xml'),
'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): def preprocess_html(self, soup, *a):
for img in soup.findAll('img', attrs={'data-srcset': True}): for img in soup.findAll('img', attrs={'data-srcset': True}):
img['src'] = img['data-srcset'].split()[0] for x in img['data-srcset'].split(','):
if '768w' in x:
img['src'] = x.split()[0]
else:
img['src'] = img['data-srcset'].split(',')[-1].split()[0]
return soup return soup