mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
65 lines
2.3 KiB
Python
65 lines
2.3 KiB
Python
__license__ = 'GPL v3'
|
|
__copyright__ = '2009-2013, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.thestar.com
|
|
'''
|
|
|
|
from collections import defaultdict
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
def absolutize(url):
|
|
if url.startswith('/'):
|
|
url = 'https://www.thestar.com' + url
|
|
return url
|
|
|
|
|
|
class TheTorontoStar(BasicNewsRecipe):
|
|
title = 'The Toronto Star'
|
|
__author__ = 'Darko Miletic'
|
|
description = "Thestar.com is Canada's largest online news site. Stay current with our sports, business entertainment news and more from the Toronto Star and thestar.com" # noqa: E501
|
|
oldest_article = 2
|
|
language = 'en_CA'
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
delay = 2
|
|
publisher = 'The Toronto Star'
|
|
encoding = 'utf-8'
|
|
|
|
keep_only_tags = [
|
|
classes('headline asset-summary metaPrimary tsArticleContainer')
|
|
]
|
|
remove_tags = [
|
|
classes('share-container shareIcons articleFeedbackCTA asset-comments'),
|
|
dict(name='button')
|
|
]
|
|
|
|
def parse_section(self, section):
|
|
for article in section.findAll('article'):
|
|
a = article.find('a', attrs={'class': 'tnt-asset-link', 'href':True, 'aria-label': True})
|
|
if a is not None:
|
|
title = a['aria-label']
|
|
url = absolutize(a['href'])
|
|
desc = ''
|
|
summ = article.find(attrs={'class':'tnt-summary'})
|
|
if summ is not None:
|
|
desc = self.tag_to_string(summ)
|
|
section = ''
|
|
sec = article.find(attrs={'class':'label-flag-section'})
|
|
if sec is not None:
|
|
section = self.tag_to_string(sec).strip().lower().capitalize()
|
|
if section == 'Gta':
|
|
section = 'GTA'
|
|
self.log(section + ':', title)
|
|
yield section, {'title': title, 'url': url, 'description': desc}
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup('https://www.thestar.com/')
|
|
ans = defaultdict(list)
|
|
for section in soup.findAll('section', attrs={'class': 'block'}):
|
|
for sec, article in self.parse_section(section):
|
|
ans[sec].append(article)
|
|
return list(ans.items())
|