mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-03-22 09:27:57 -04:00
79 lines
2.6 KiB
Python
79 lines
2.6 KiB
Python
#!/usr/bin/env python
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
def absurl(url):
|
|
if url.startswith('/'):
|
|
return 'https://www.livelaw.in' + url
|
|
|
|
|
|
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
|
|
|
|
extra_css = '''
|
|
.news_detail_person_detail {font-size:small; color:#202020;}
|
|
.news-description { color:#202020; font-style:italic; }
|
|
'''
|
|
|
|
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
|
|
|
|
def parse_index(self):
|
|
index = 'https://www.livelaw.in/'
|
|
sections = [
|
|
'top-stories', 'supreme-court', 'high-court', 'news-updates', 'consumer-cases', 'articles',
|
|
'lawschool', 'law-firms', 'round-ups'
|
|
]
|
|
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('/' + sec + '/')}):
|
|
url = absurl(a['href'].split('?')[0])
|
|
if url in {index + sec + '/', index + sec}:
|
|
continue
|
|
if not url[-1].isdigit():
|
|
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
|