calibre/recipes/newsminute.recipe
unkn0w7n 69ba1b60c2 change google feeds based recipes..
..to parse their front pages instead.
2024-09-25 22:43:18 +05:30

56 lines
2.1 KiB
Python

#!/usr/bin/env python
from calibre.web.feeds.news import BasicNewsRecipe, classes
class newsminute(BasicNewsRecipe):
title = 'The News Minute'
__author__ = 'unkn0wn'
description = (
'The News Minute is a digital news platform reporting and writing on issues in India, with a '
'specific focus on the 5 southern states. Our content includes news, ground reportage, news '
'analysis, opinion and blogs. Our core strengths include our deep access in the southern states, '
'incisive editorial acumen and insightful news analysis and opinions.'
)
language = 'en_IN'
no_stylesheets = True
remove_javascript = True
masthead_url = 'https://pkcindia.com/wp-content/uploads/2021/09/TMN-Logo-1.png'
ignore_duplicate_articles = {'title', 'url'}
resolve_internal_links = True
remove_empty_feeds = True
remove_attributes = ['style', 'height', 'width']
keep_only_tags = [
classes(
'arr--section-name arr--story--headline-h1 arr--sub-headline arr--hero-image author-card-wrapper arr--story-page-card-wrapper'
),
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src':True}):
img['src'] = img['data-src']
return soup
def parse_index(self):
index = 'https://www.thenewsminute.com/'
sections = [
'tamil-nadu', 'telangana', 'andhra-pradesh', 'karnataka', 'kerala'
]
feeds = []
soup = self.index_to_soup(index)
for sec in sections:
section = sec.capitalize()
self.log(section)
articles = []
for a in soup.findAll('a', attrs={'href':lambda x: x and x.startswith(index + sec + '/')}):
url = a['href']
if url in {index + sec + '/', index + sec}:
continue
title = self.tag_to_string(a)
self.log('\t', title, '\n\t\t', url)
articles.append({'title': title, 'url': url})
if articles:
feeds.append((section, articles))
return feeds