calibre/recipes/frontline.recipe
2022-11-27 10:14:25 +05:30

80 lines
3.2 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 = '''
.overline{ font-size:small; color:#404040; }
.person-name { font-size:small; font-weight:bold; }
.lead-img-caption, .caption-cont { font-size:small; text-align:center; }
'''
keep_only_tags = [
classes('article')
]
remove_tags = [
classes('shareicon-article articleBottomLine secheader mobilesocialicons'),
dict(name='h2', attrs={'class':'title'})
]
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']
source.name = 'img'
else:
img['src'] = img['data-original']
for cap in soup.findAll(**classes('caption-cont')):
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/magazine/')
issue = soup.find(**classes('sptar-archive-item')).find('a')['href']
self.log(issue)
soup = self.index_to_soup(issue)
time = soup.find(**classes('date')).findNext('h3')
if time:
self.timefmt = ' ' + self.tag_to_string(time)
self.log('Downloading Issue:', self.timefmt)
self.cover_url = soup.find(**classes('sptar-cover-item')).find('img')['data-original'].replace('FREE_320', 'FREE_810')
feeds_dict = defaultdict(list)
for div in soup.findAll('div', attrs={'class':'brief-list-item'}):
a = div.find(**classes('brief-title')).find('a')
url = a['href']
title = self.tag_to_string(a)
section = 'Articles'
cat = div.find(**classes('brief-cat'))
if cat:
section = self.tag_to_string(cat)
desc = ''
art = div.find(**classes('artbody'))
if art:
desc = self.tag_to_string(art)
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})
return [(section, articles) for section, articles in feeds_dict.items()]