Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/unkn0w7n/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2024-05-25 15:36:14 +05:30
commit d2f093824c
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 42 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
recipes/slate.recipe
View File

@ -19,13 +19,12 @@ def classes(classes):
class Slate(BasicNewsRecipe): class Slate(BasicNewsRecipe):
title = 'Slate' title = 'Slate'
description = 'A general-interest publication offering analysis and commentary about politics, news and culture.' description = 'A general-interest publication offering analysis and commentary about politics, news and culture.'
__author__ = 'Kovid Goyal' __author__ = 'unkn0wn'
no_stylesheets = True no_stylesheets = True
language = 'en' language = 'en'
encoding = 'utf-8' encoding = 'utf-8'
remove_attributes = ['style', 'height', 'width'] remove_attributes = ['style', 'height', 'width']
oldest_article = 2 # days INDEX = 'https://slate.com/'
INDEX = 'https://slate.com'
resolve_internal_links = True resolve_internal_links = True
remove_empty_feeds = True remove_empty_feeds = True
ignore_duplicate_articles = {'url'} ignore_duplicate_articles = {'url'}
@ -52,16 +51,44 @@ class Slate(BasicNewsRecipe):
img['src'] = img['data-src'] + '&width=600' img['src'] = img['data-src'] + '&width=600'
return soup return soup
feeds = [ def parse_index(self):
('News & Politics', 'https://slate.com/feeds/news-and-politics.rss'), ans = []
('Culture', 'https://slate.com/feeds/culture.rss'), for sectitle, url in (
('Technology', 'https://slate.com/feeds/technology.rss'), ('News & Politics', 'news-and-politics'),
('Business', 'https://slate.com/feeds/business.rss'), ('Culture', 'culture'),
('Human Interest', 'https://slate.com/feeds/human-interest.rss'), ('Technology', 'technology'),
('Others', 'https://slate.com/feeds/all.rss') ('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 get_article_url(self, article): def slate_section_articles(self, url):
url = BasicNewsRecipe.get_article_url(self, article) from datetime import date
if '/podcasts/' not in url: soup = self.index_to_soup(url)
return url.split('?')[0] ans = []
dt = date.today().strftime('/%Y/%m')
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)