mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
102 lines
3.2 KiB
Python
102 lines
3.2 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
|
|
extra_css = '''
|
|
img {display:block; margin:0 auto;}
|
|
em, blockquote { color:#202020; }
|
|
.b-it-subheadline { font-style:italic; }
|
|
.calibre-nuked-tag-figcaption, .b-it-byline-block {font-size:small;}
|
|
'''
|
|
|
|
keep_only_tags = [
|
|
classes(
|
|
'b-it-headline b-it-subheadline b-it-byline-block__text '
|
|
'b-it-lead-art__wrapper b-it-article-body'
|
|
),
|
|
]
|
|
|
|
remove_tags_after = [
|
|
classes('b-it-article-body'),
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name=['button', 'svg']),
|
|
classes(
|
|
'b-top-table-list arcad-feature c-unordered-list b-it-article-body__podcast'
|
|
),
|
|
]
|
|
|
|
remove_attributes = ['width', 'height', 'style']
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
resolve_internal_links = True
|
|
|
|
def get_cover_url(self):
|
|
soup = self.index_to_soup('https://www.frontpages.com/the-irish-times/')
|
|
return (
|
|
'https://www.frontpages.com'
|
|
+ soup.find('img', attrs={'id': 'giornale-img'})['src']
|
|
)
|
|
|
|
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
|
|
|
|
def preprocess_html(self, soup):
|
|
h2 = soup.find(**classes('b-it-subheadline'))
|
|
if h2:
|
|
h2.name = 'p'
|
|
for img in soup.findAll('img', attrs={'srcset': True}):
|
|
img['src'] = img['srcset'].split()[0]
|
|
return soup
|
|
|
|
def populate_article_metadata(self, article, soup, first):
|
|
desc = soup.find(**classes('b-it-subheadline'))
|
|
if desc:
|
|
article.summary = article.text_summary = self.tag_to_string(desc)
|