calibre/recipes/theindiaforum.recipe
2024-08-14 18:39:18 +05:30

86 lines
3.2 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from datetime import datetime, timedelta, timezone
from calibre.utils.date import parse_date
from calibre.web.feeds.news import BasicNewsRecipe, classes
class mains(BasicNewsRecipe):
title = 'The India Forum'
__author__ = 'unkn0wn'
description = (
'The India Forum is an independent online journal-magazine that seeks to widen and '
'deepen our conversations on the issues that concern us.'
)
language = 'en_IN'
encoding = 'utf-8'
ignore_duplicate_articles = {'url'}
remove_attributes = ['height', 'width', 'style']
no_stylesheets = True
resolve_internal_links = True
remove_empty_feeds = True
use_embedded_content = False
oldest_article = 30 # days
masthead_url = 'https://www.theindiaforum.in/themes/the_india_forum/images/tif_logo.png'
extra_css = '''
[class*="caption"], [class*="references"], #article-author-top-container { font-size:small; }
[class*="blurb"] { font-style:italic; }
blockquote, em { color:#202020; }
'''
keep_only_tags = [
classes('article-lead-container block-views-blockarticle-block-1'),
dict(name='section', attrs={'id':'article-author-top-container'}),
classes('block-field-blocknodearticlebody block-field-blocknodearticlefield-references')
]
remove_tags = [
dict(name=['source', 'svg']),
dict(attrs={'src':lambda x: x and x.endswith('quote_logo.png')}),
classes('s_info')
]
def parse_index(self):
soup = self.index_to_soup('https://www.theindiaforum.in/')
ul = soup.find('ul', attrs={'class':'float-left'})
section_list = []
for x in ul.findAll('a', href=True):
if '/podcast' in x['href']:
continue
section_list.append(
(self.tag_to_string(x).strip().replace('',''), 'https://www.theindiaforum.in' + x['href'])
)
feeds = []
for section in section_list:
section_title = section[0]
section_url = section[1]
self.log(section_title, section_url)
soup = self.index_to_soup(section_url)
articles = self.articles_from_soup(soup)
if articles:
feeds.append((section_title, articles))
return feeds
def articles_from_soup(self, soup):
ans = []
for art in soup.findAll('div', attrs={'class':lambda x: x and 'views-col' in x.split()}):
h2 = art.find(['h2', 'h3'])
url = 'https://www.theindiaforum.in' + h2.a['href']
title = self.tag_to_string(h2).strip()
desc = ''
if summ := art.find(**classes('summary')):
desc = self.tag_to_string(summ)
if inline := summ.find(**classes('inline-date')):
date = parse_date(self.tag_to_string(inline))
today = (datetime.now(timezone.utc)).replace(microsecond=0)
if (today - date) > timedelta(self.oldest_article):
continue
self.log('\t', title, '\n\t', desc, '\n\t\t', url)
ans.append({'title': title, 'url': url, 'description': desc})
return ans