mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-01-01 01:30:21 -05:00
91 lines
3.4 KiB
Python
91 lines
3.4 KiB
Python
from calibre.ptempfile import PersistentTemporaryFile
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
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'}
|
|
resolve_internal_links = True
|
|
articles_are_obfuscated = 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 get_obfuscated_article(self, url):
|
|
br = self.get_browser()
|
|
try:
|
|
br.open(url)
|
|
except Exception as e:
|
|
url = e.hdrs.get('location')
|
|
soup = self.index_to_soup(url)
|
|
link = soup.find('a', href=True)
|
|
skip_sections =[ # add sections you want to skip
|
|
'/video/', '/videos/', '/media/', '/podcast'
|
|
]
|
|
if any(x in link['href'] for x in skip_sections):
|
|
self.log('Aborting Article', link['href'])
|
|
self.abort_article('skipping video links')
|
|
|
|
self.log('Found', link['href'])
|
|
html = br.open(link['href']).read()
|
|
pt = PersistentTemporaryFile('.html')
|
|
pt.write(html)
|
|
pt.close()
|
|
return pt.name
|
|
|
|
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 = []
|
|
|
|
sections = [
|
|
'ireland', 'world', 'opinion', 'politics', 'crime-law', 'culture', 'business',
|
|
'life-style', 'health', 'sport', 'property', 'food', 'abroad', 'environment',
|
|
'obituaries'
|
|
]
|
|
|
|
for sec in sections:
|
|
a = 'https://news.google.com/rss/search?q=when:27h+allinurl:irishtimes.com{}&hl=en-IE&gl=IE&ceid=IE:en'
|
|
feeds.append((sec.capitalize(), a.format('%2F' + sec + '%2F')))
|
|
feeds.append(('Others', a.format('')))
|