calibre/recipes/live_law.recipe
2024-03-30 13:03:29 +05:30

87 lines
2.8 KiB
Python

from urllib.parse import quote
from calibre.web.feeds.news import BasicNewsRecipe, classes
class livelaw(BasicNewsRecipe):
title = 'Live Law'
__author__ = 'unkn0wn'
description = (
'Live Law is a comprehensive legal news portal which is committed to providing accurate'
' and honest news about legal developments.'
)
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = 'en_IN'
remove_attributes = ['height', 'width', 'style']
masthead_url = 'https://www.livelaw.in/images/logo.png'
remove_empty_feeds = True
remove_javascript = True
ignore_duplicate_articles = {'title', 'url'}
simultaneous_downloads = 1
art_url = ''
extra_css = '''
.news_detail_person_detail {font-size:small; color:#202020;}
.news-description { color:#202020; font-style:italic; }
'''
articles_are_obfuscated = True
def get_obfuscated_article(self, url):
br = self.get_browser()
soup = self.index_to_soup(url)
link = soup.a['href']
skip_sections =[ # add sections you want to skip
'/video/', '/videos/', '/multimedia/',
]
if any(x in link for x in skip_sections):
self.abort_article('skipping video links ', link)
self.log('Found ', link)
self.art_url = link
html = br.open(link).read()
return ({ 'data': html, 'url': link })
keep_only_tags = [
dict(name='div', attrs={'id':'page-content-wrapper'})
]
remove_tags = [
classes(
'in-image-ad-wrap news_details_social_media_icons news_details_social_icon_desktop '
'audioSection news_details_tags_row nextpage'
),
dict(attrs={'class':lambda x: x and 'inside-post-ad' in x}),
dict(attrs={'id':[
'news_buzz_updates', 'after_tags', 'comments_before', 'comments', 'comments_after'
]})
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src':True}):
img['src'] = img['data-src']
for h2 in soup.findAll(['h2', 'h6']):
h2.name = 'p'
return soup
feeds = []
when = '27' # hours
index = 'https://www.livelaw.in/'
sections = [
'top-stories', 'supreme-court', 'high-court', 'news-updates', 'consumer-cases', 'articles',
'lawschool', 'law-firms', 'round-ups'
]
a = 'https://news.google.com/rss/search?q=when:{}h+allinurl:{}&hl=en-IN&gl=IN&ceid=IN:en'
for sec in sections:
feeds.append((sec.capitalize(), a.format(when, quote(index + sec, safe=''))))
feeds.append(('Others' , a.format(when, quote(index, safe=''))))
def populate_article_metadata(self, article, soup, first):
article.url = self.art_url
article.title = article.title.replace(' - Live Law - Indian Legal News', '')