calibre/recipes/indian_express.recipe
2022-02-23 20:10:57 +05:30

56 lines
2.4 KiB
Plaintext

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)})
class IndianExpress(BasicNewsRecipe):
title = u'Indian Express'
language = 'en_IN'
__author__ = 'Krittika Goyal'
oldest_article = 1 # days
max_articles_per_feed = 25
encoding = 'utf-8'
no_stylesheets = True
use_embedded_content = False
remove_attributes = ['style','height','width']
ignore_duplicate_articles = {'url'}
keep_only_tags = [
classes('heading-part full-details')
]
remove_tags = [
dict(name='div', attrs={'id':'ie_story_comments'}),
dict(name='img', attrs={'src':'https://images.indianexpress.com/2021/06/explained-button-300-ie.jpeg'}),
dict(name='a', attrs={'href':'https://indianexpress.com/section/explained/?utm_source=newbanner'}),
dict(name='img', attrs={'src':'https://images.indianexpress.com/2021/06/opinion-button-300-ie.jpeg'}),
dict(name='a', attrs={'href':'https://indianexpress.com/section/opinion/?utm_source=newbanner'}),
classes('share-social appstext story-tags ie-int-campign-ad ie-breadcrumb custom_read_button unitimg copyright')
]
feeds = [
('Front Page', 'https://indianexpress.com/print/front-page/feed/'),
('Op-Ed', 'http://indianexpress.com/section/opinion/feed/'),
('Science & Technology', 'http://indianexpress.com/section/technology/feed/'),
('Movie Reviews', 'https://indianexpress.com/section/entertainment/movie-review/feed/'),
('Sunday Eye', 'https://indianexpress.com/print/eye/feed/'),
('Explained', 'https://indianexpress.com/section/explained/feed/'),
('Delhi Confidential', 'https://indianexpress.com/section/delhi-confidential/feed'),
('Economy', 'https://indianexpress.com/print/economy/feed'),
('Express Network', 'https://indianexpress.com/print/express-network/'),
# Want to add more? go-to:https://indianexpress.com/syndication/
]
def preprocess_html(self, soup):
for img in soup.findAll('img'):
noscript = img.findParent('noscript')
if noscript is not None:
lazy = noscript.findPreviousSibling('img')
if lazy is not None:
lazy.extract()
noscript.name = 'div'
return soup