mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
95 lines
3.2 KiB
Python
95 lines
3.2 KiB
Python
#!/usr/bin/env python
|
|
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
|
|
|
__license__ = 'GPL v3'
|
|
|
|
'''
|
|
calibre recipe for slate.com
|
|
'''
|
|
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
|
|
|
|
def classes(classes):
|
|
q = frozenset(classes.split(' '))
|
|
return dict(attrs={
|
|
'class': lambda x: x and frozenset(x.split()).intersection(q)})
|
|
|
|
|
|
class Slate(BasicNewsRecipe):
|
|
title = 'Slate'
|
|
description = 'A general-interest publication offering analysis and commentary about politics, news and culture.'
|
|
__author__ = 'unkn0wn'
|
|
no_stylesheets = True
|
|
language = 'en'
|
|
encoding = 'utf-8'
|
|
remove_attributes = ['style', 'height', 'width']
|
|
INDEX = 'https://slate.com/'
|
|
resolve_internal_links = True
|
|
remove_empty_feeds = True
|
|
ignore_duplicate_articles = {'url'}
|
|
|
|
extra_css = '''
|
|
.article__rubric { font-size:small; color:#404040; }
|
|
.article__byline, time { font-size:small; }
|
|
.article__top-image, .image__credit, .image__meta { font-size:small; text-align:center; }
|
|
em, blockquote, .alternativeHeadline { color:#202020; }
|
|
'''
|
|
|
|
keep_only_tags = [
|
|
classes('article__header article__top-image article__content article-hotseats__body'),
|
|
]
|
|
remove_tags = [
|
|
dict(name=['aside', 'svg', 'iframe']),
|
|
classes('social-share slate-ad newsletter-signup in-article-recirc'),
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for h2 in soup.findAll('h2'):
|
|
h2.name = 'h4'
|
|
for img in soup.findAll('img', attrs={'data-srcset': True}):
|
|
img['src'] = img['data-src'] + '&width=600'
|
|
return soup
|
|
|
|
def parse_index(self):
|
|
ans = []
|
|
for sectitle, url in (
|
|
('News & Politics', 'news-and-politics'),
|
|
('Culture', 'culture'),
|
|
('Technology', 'technology'),
|
|
('Business', 'business'),
|
|
('Life', 'life'),
|
|
('Advice', 'advice'),
|
|
):
|
|
url = self.INDEX + url
|
|
self.log('\nFound section:', sectitle, url)
|
|
articles = self.slate_section_articles(url)
|
|
if articles:
|
|
ans.append((sectitle, articles))
|
|
return ans
|
|
|
|
def slate_section_articles(self, url):
|
|
from datetime import date
|
|
soup = self.index_to_soup(url)
|
|
ans = []
|
|
dt = date.today().strftime('/%Y/')
|
|
for a in soup.findAll('a', attrs={'href':lambda x: x and x.startswith(url + dt)}):
|
|
url = a['href']
|
|
head = a.find(attrs={'class':[
|
|
'section-feed-two-column__card-headline',
|
|
'section-feed-three-column__teaser-headline',
|
|
'section-feed-two-column__teaser-headline',
|
|
'topic-story__hed'
|
|
]})
|
|
if head:
|
|
title = self.tag_to_string(head).strip()
|
|
self.log('\t' + title)
|
|
self.log('\t\t' + url)
|
|
ans.append({'title': title, 'url': url})
|
|
return ans
|
|
|
|
def populate_article_metadata(self, article, soup, first):
|
|
summ = soup.find(attrs={'class':'article__dek'})
|
|
if summ:
|
|
article.summary = article.text_summary = self.tag_to_string(summ)
|