calibre/recipes/bar_and_bench.recipe
un-pogaz 41cee6f02d various whitespace (auto-fix)
ruff 'E201,E202,E211,E251,E275'
2025-01-24 11:14:24 +01:00

62 lines
2.1 KiB
Python

#!/usr/bin/env python
from calibre.web.feeds.news import BasicNewsRecipe, prefixed_classes
class bar(BasicNewsRecipe):
title = 'Bar and Bench'
__author__ = 'unkn0wn'
description = (
'Bar & Bench is the premier online portal for Indian legal news. News, interviews,'
' and columns related to the Supreme Court of India and the High Courts are published.'
)
language = 'en_IN'
masthead_url = 'https://gumlet.assettype.com/barandbench/2019-12/7a743b15-5d5d-44d7-96c2-13616780ed95/brand_2x.png'
no_stylesheets = True
remove_javascript = True
remove_attributes = ['height', 'width', 'style']
keep_only_tags = [
prefixed_classes(
'text-story-m_header-details__ text-story-m_hero-image__ text-story-m_story-content-inner-wrapper__'
)
]
remove_tags = [
prefixed_classes(
'text-story-m_story-tags__ story-footer-module__metype__'
),
dict(name='svg')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src':True}):
img['src'] = img['data-src']
return soup
ignore_duplicate_articles = {'title'}
resolve_internal_links = True
remove_empty_feeds = True
def parse_index(self):
index = 'https://www.barandbench.com/'
sections = [
'news', 'columns', 'interviews', 'law-firms', 'apprentice-lawyer', 'legal-jobs'
]
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'].split('?')[0]
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