calibre/recipes/irish_times_free.recipe
Kovid Goyal c4fd1200b6
pep8
2024-09-25 23:09:09 +05:30

89 lines
3.3 KiB
Python

#!/usr/bin/env python
from datetime import date
from calibre.web.feeds.news import BasicNewsRecipe, classes
def absurl(url):
if url.startswith('/'):
return 'https://www.irishtimes.com' + url
class IrishTimes(BasicNewsRecipe):
title = 'The Irish Times (free)'
__author__ = 'unkn0wn'
description = 'Daily news from The Irish Times'
language = 'en_IE'
masthead_url = 'http://www.irishtimes.com/assets/images/generic/website/logo_theirishtimes.png'
encoding = 'utf-8'
max_articles_per_feed = 50
remove_empty_feeds = True
no_stylesheets = True
keep_only_tags = [
classes('custom-headline custom-subheadline lead-art-wrapper article-body-wrapper byline-text'),
]
remove_tags = [
dict(name=['button', 'svg']),
classes('sm-promo-headline top-table-list-container single-divider interstitial-link'),
]
remove_attributes = ['width', 'height']
ignore_duplicate_articles = {'title', 'url'}
resolve_internal_links = True
def get_cover_url(self):
from datetime import date
cover = 'https://img.kiosko.net/' + date.today().strftime('%Y/%m/%d') + '/ie/irish_times.750.jpg'
br = BasicNewsRecipe.get_browser(self, verify_ssl_certificates=False)
try:
br.open(cover)
except:
index = 'https://en.kiosko.net/ie/np/irish_times.html'
soup = self.index_to_soup(index)
for image in soup.find('img', attrs={'src': lambda x: x and x.endswith('750.jpg')}):
if image['src'].startswith('/'):
return 'https:' + image['src']
return image['src']
self.log("\nCover unavailable")
cover = None
return cover
def __init__(self, *args, **kwargs):
BasicNewsRecipe.__init__(self, *args, **kwargs)
if self.output_profile.short_name.startswith('kindle'):
# Reduce image sizes to get file size below amazon's email
# sending threshold
self.web2disk_options.compress_news_images = True
self.web2disk_options.compress_news_images_auto_size = 5
self.log.warn('Kindle Output profile being used, reducing image quality to keep file size below amazon email threshold')
feeds = []
def parse_index(self):
index = 'https://www.irishtimes.com/'
sections = [
'ireland', 'world', 'opinion', 'politics', 'crime-law', 'culture', 'business',
'life-style', 'health', 'sport', 'property', 'food', 'abroad', 'environment',
'obituaries'
]
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 date.today().strftime('%Y') not in url:
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