calibre/recipes/hindufeeds.recipe
un-pogaz 8d28380515 add/remove blank-line (extra-edit)
ruff 'E302,E303,E304,E305,W391'
2025-01-24 11:14:21 +01:00

97 lines
3.8 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe, classes
class TheHindufeeds(BasicNewsRecipe):
title = 'The Hindu (Feeds)'
__author__ = 'unkn0wn'
description = 'The Hindu, based on RSS feeds.'
language = 'en_IN'
no_stylesheets = True
masthead_url = 'https://www.thehindu.com/theme/images/th-online/thehindu-logo.svg'
remove_attributes = ['style', 'height', 'width']
resolve_internal_links = True
remove_empty_feeds = True
max_articles_per_feed = 25
oldest_article = 1.15 # days
extra_css = '''
.caption {font-size:small; text-align:center;}
.author, .dateLine, .publish-time {font-size:small; font-weight:bold;}
.subhead, .subhead_lead, .bold {font-weight:bold;}
img {display:block; margin:0 auto;}
.italic {font-style:italic; color:#202020;}
'''
recipe_specific_options = {
'days': {
'short': 'Oldest article to download from this news source. In days ',
'long': 'For example, 0.5, gives you articles from the past 12 hours',
'default': str(oldest_article)
}
}
def __init__(self, *args, **kwargs):
BasicNewsRecipe.__init__(self, *args, **kwargs)
d = self.recipe_specific_options.get('days')
if d and isinstance(d, str):
self.oldest_article = float(d)
ignore_duplicate_articles = {'url'}
keep_only_tags = [
classes('article-section')
]
remove_tags = [
dict(name='button'),
dict(attrs={'target':'_self'}),
classes(
'hide-mobile comments-shares share-page editiondetails breadcrumb'
' related-topics related-stories also-read premium-label'
)
]
def preprocess_html(self, soup):
for cap in soup.findAll('p', attrs={'class':'caption'}):
cap.name = 'figcaption'
for img in soup.findAll('img', attrs={'data-original':True}):
if img['data-original'].endswith('1x1_spacer.png'):
source = img.findPrevious('source', srcset=True)
img.extract()
if source:
source['src'] = source['srcset'].replace('_320','_1200')
source.name = 'img'
else:
img['src'] = img['data-original']
for img in soup.findAll('img', attrs={'data-src-template':True}):
img['src'] = img['data-src-template']
return soup
def postprocess_html(self, soup, first_fetch):
for src in soup.findAll('source'):
src.extract()
return soup
def get_cover_url(self):
soup = self.index_to_soup('https://www.thehindu.com/todays-paper/')
if cover := soup.find(attrs={'class':'hindu-ad'}):
return cover.img['src']
# https://www.thehindu.com/rssfeeds/
feeds = [
('India', 'https://www.thehindu.com/news/national/feeder/default.rss'),
('States', 'https://www.thehindu.com/news/states/feeder/default.rss'),
# ('Cities', 'https://www.thehindu.com/news/cities/feeder/default.rss'),
('Opinion', 'https://www.thehindu.com/opinion/feeder/default.rss'),
('Business', 'https://www.thehindu.com/business/feeder/default.rss'),
('World', 'https://www.thehindu.com/news/international/feeder/default.rss'),
# ('Sport', 'https://www.thehindu.com/sport/feeder/default.rss'),
('Entertainment', 'https://www.thehindu.com/entertainment/feeder/default.rss'),
# ('Crossword', 'https://crossword.thehindu.com/?utm_source=thehindu&utm_medium=mainmenufeeder/default.rss'),
('Science', 'https://www.thehindu.com/sci-tech/science/feeder/default.rss'),
('Life and Style', 'https://www.thehindu.com/life-and-style/feeder/default.rss'),
('thRead', 'https://www.thehindu.com/thread/feeder/default.rss')
]