calibre/recipes/chicago_tribune.recipe
Kovid Goyal e28f5b52ee
...
2019-07-25 13:56:15 +05:30

88 lines
2.7 KiB
Plaintext

from __future__ import with_statement
__license__ = 'GPL 3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
def absolutize(x):
x = x.lstrip('/')
if not x.startswith('https:'):
x = 'https://www.chicagotribune.com/' + x
return x
class ChicagoTribune(BasicNewsRecipe):
title = 'Chicago Tribune'
__author__ = 'Kovid Goyal'
description = 'Politics, local and business news from Chicago'
language = 'en'
use_embedded_content = False
no_stylesheets = True
remove_javascript = True
compress_news_images = True
compress_news_images_auto_size = 5
keep_only_tags = [
dict(name='h1'),
classes('byline-container pb-f-utilities-lead-art pb-f-article-gallery'),
dict(attrs={'data-type': 'text'}),
]
remove_tags = [
classes('trb_ar_cont trb_ar_main_ad trb_em_r_cc'),
]
def ct_articles(self, slug):
url = absolutize(slug)
soup = self.index_to_soup(url)
for div in soup.findAll(**classes('pb-f-homepage-story pb-f-homepage-story-feed')):
h = div.find(('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))
a = h.find('a', href=True)
title = self.tag_to_string(a)
url = absolutize(a['href'])
self.log('\t', title, url)
desc = ''
p = div.find(**classes('preview-text'))
if p:
desc = self.tag_to_string(p)
self.log('\t\t', desc)
yield {'title': title, 'description': desc, 'url': url}
def parse_index(self):
feed = []
for slug, title in (
('news/breaking', 'Breaking News'),
('sports', 'Sports'),
('business', 'Business'),
('entertainment', 'Entertainment'),
('dining', 'Chicago Dining'),
('columns', 'Tribune Voices'),
):
self.log('Found section:', title)
articles = list(self.ct_articles(slug))
if articles:
feed.append((title, articles))
return feed
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-baseurl': True}):
img['src'] = img['data-baseurl']
return soup
def skip_ad_pages(self, soup):
text = soup.find(text='click here to continue to article')
if text:
a = text.parent
url = a.get('href')
if url:
return self.index_to_soup(url, raw=True)