mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
aa1482d782
Fixes #1895457 [Pro Publica news only creates Table of Contents, no articles.](https://bugs.launchpad.net/calibre/+bug/1895457)
52 lines
1.5 KiB
Plaintext
52 lines
1.5 KiB
Plaintext
|
|
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)})
|
|
|
|
|
|
class ProPublicaRecipe(BasicNewsRecipe):
|
|
__license__ = 'GPL v3'
|
|
__author__ = 'kwetal'
|
|
language = 'en'
|
|
version = 1
|
|
|
|
title = u'Pro Publica'
|
|
publisher = u'ProPublica.org'
|
|
category = u'Political blog'
|
|
description = u'Independent investigative journalism in the public interest.'
|
|
|
|
oldest_article = 14
|
|
max_articles_per_feed = 100
|
|
use_embedded_content = False
|
|
|
|
remove_empty_feeds = True
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
|
|
keep_only_tags = [
|
|
classes('title-wrapper content-wrapper article-header lead-art article-body')
|
|
]
|
|
remove_tags = [
|
|
classes('email-signup story-tools newsletter topics-list')
|
|
]
|
|
remove_tags_after = classes('article-body')
|
|
|
|
feeds = [
|
|
(u'Top Stories', u'http://feeds.propublica.org/propublica/main'),
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', **classes('lazyload')):
|
|
source = img.findParent('picture')
|
|
if source is not None:
|
|
source = source.find('source')
|
|
if source is not None:
|
|
img['src'] = source['data-srcset']
|
|
for img in soup.findAll('img', srcset=True):
|
|
img['src'] = img['srcset'].split()[0]
|
|
return soup
|