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

Update MSNBC

Browse Source
This commit is contained in:
Kovid Goyal 2021-07-28 22:13:56 +05:30
parent 8b0ae7bde2
commit b6236975ec
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 19 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
recipes/msnbc.recipe
View File

@ -7,10 +7,16 @@ msnbc.msn.com
from calibre.web.feeds.recipes import BasicNewsRecipe 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 MsNBC(BasicNewsRecipe): class MsNBC(BasicNewsRecipe):
title = 'msnbc.com' title = 'MSNBC'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'A Fuller Spectrum of News' description = 'A Fuller Spectrum of News from msnbc.com and nbcnews.com'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
@ -21,27 +27,23 @@ class MsNBC(BasicNewsRecipe):
remove_empty_feeds = True remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'} ignore_duplicate_articles = {'title', 'url'}
keep_only_tags = [ keep_only_tags = [
dict(itemprop='headline'), classes('article-hero__container article-body')
dict(attrs={'class': lambda x: x and set(x.split()).intersection(
{'byline_article', 'article_main'})}),
dict(attrs={'class': lambda x: x and set(x.split()).intersection(
{'authors-names', 'pane-node-body'})}),
] ]
remove_tags = [ remove_tags = [
dict(name=['iframe', 'button', 'meta', 'link']), dict(name=['iframe', 'button', 'meta', 'link']),
dict(attrs={'class': lambda x: x and set( classes('widget_video ad-container related'),
x.split()).intersection({'widget_video', 'ad-container'})}), dict(attrs={'data-test': ['social-share-inline']}),
dict(name='source'),
] ]
feeds = [ feeds = [
('Latest', 'https://feeds.nbcnews.com/msnbc/public/news'),
('Latest', 'http://www.msnbc.com/feeds/latest'), ('Top stories', 'https://feeds.nbcnews.com/nbcnews/public/news'),
('Politics', 'https://feeds.nbcnews.com/nbcnews/public/politics'),
(u'US News', u'http://rss.msnbc.msn.com/id/3032524/device/rss/rss.xml'), ('U.S. News', 'https://feeds.nbcnews.com/nbcnews/public/us-news'),
(u'Politics', u'http://rss.msnbc.msn.com/id/3032552/device/rss/rss.xml'), ('World', 'https://feeds.nbcnews.com/nbcnews/public/world'),
(u'Business', u'http://rss.msnbc.msn.com/id/3032071/device/rss/rss.xml'), ('Business', 'https://feeds.nbcnews.com/nbcnews/public/business'),
(u'Health', u'http://rss.msnbc.msn.com/id/3088327/device/rss/rss.xml'), ('Opinion', 'https://feeds.nbcnews.com/nbcnews/public/think'),
(u'Tech & Science', u'http://rss.msnbc.msn.com/id/3032117/device/rss/rss.xml')
] ]
def get_article_url(self, article): def get_article_url(self, article):