calibre/recipes/frontline.recipe
2023-04-15 21:24:44 +05:30

83 lines
3.4 KiB
Plaintext

from collections import defaultdict
from calibre.web.feeds.news import BasicNewsRecipe, classes
class Frontline(BasicNewsRecipe):
title = u'Frontline'
__author__ = 'unkn0wn'
description = 'Frontline, the fortnightly English magazine from the stable of The Hindu, has been a distinguished presence in the media world since 1984.'
language = 'en_IN'
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
encoding = 'utf-8'
ignore_duplicate_articles = {'url'}
masthead_url = 'https://frontline.thehindu.com/theme/images/fl-online/frontline-logo.png'
remove_attributes = ['height', 'width']
resolve_internal_links = True
extra_css = '''
.environment, .publish-time, .author { font-size:small; color:#404040; }
.caption { font-size:small; text-align:center; }
img { display:block; margin:0 auto; }
.question {font-weight:bold;}
'''
keep_only_tags = [
dict(name='div', attrs={'class':'container article-section'})
]
remove_tags = [
classes(
'breadcrumb comments-shares share-page article-video '
'referpara slide-mobile title-patch hide-mobile related-stories'
),
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-original':True}):
if img['data-original'].endswith('1x1_spacer.png'):
source = img.findPrevious('source', srcset=True)
img.extract()
if source:
source['src'] = source['srcset'].replace('_320','_1200')
source.name = 'img'
else:
img['src'] = img['data-original']
for cap in soup.findAll(**classes('caption')):
cap.name = 'figcaption'
return soup
def postprocess_html(self, soup, first_fetch):
for src in soup.findAll('source'):
src.extract()
return soup
def parse_index(self):
soup = self.index_to_soup('https://frontline.thehindu.com/current-issue/')
if cover := soup.find('div', attrs={'class':'magazine'}):
self.cover_url = cover.find(**classes('sptar-image')).img['data-original'].replace('_320', '_1200')
self.log('Cover ', self.cover_url)
if desc := cover.find(**classes('sub-text')):
self.description = self.tag_to_string(desc)
feeds_dict = defaultdict(list)
mag = soup.find(**classes('section-magazine'))
for div in mag.findAll('div', attrs={'class':'content'}):
a = div.find(**classes('title')).find('a')
url = a['href']
title = self.tag_to_string(a)
section = 'Articles'
if cat := div.find(**classes('label')):
section = self.tag_to_string(cat)
desc = ''
if art := div.find(**classes('sub-text')):
desc = self.tag_to_string(art)
if auth := div.find(**classes('author')):
desc = self.tag_to_string(auth) + ' | ' + desc
if not url or not title:
continue
self.log(section, '\n\t', title, '\n\t', desc, '\n\t\t', url)
feeds_dict[section].append({"title": title, "url": url, "description": desc})
return [(section, articles) for section, articles in feeds_dict.items()]