| 1 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 2 |
|
| 3 |
|
| 4 |
def classes(classes): |
| 5 |
q = frozenset(classes.split(' ')) |
| 6 |
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) |
| 7 |
|
| 8 |
|
| 9 |
class ProPublicaRecipe(BasicNewsRecipe): |
| 10 |
__license__ = 'GPL v3' |
| 11 |
__author__ = 'kwetal' |
| 12 |
language = 'en' |
| 13 |
version = 1 |
| 14 |
|
| 15 |
title = 'Pro Publica' |
| 16 |
publisher = 'ProPublica.org' |
| 17 |
category = 'Political blog' |
| 18 |
description = 'Independent investigative journalism in the public interest.' |
| 19 |
|
| 20 |
oldest_article = 14 |
| 21 |
max_articles_per_feed = 100 |
| 22 |
use_embedded_content = False |
| 23 |
|
| 24 |
remove_empty_feeds = True |
| 25 |
no_stylesheets = True |
| 26 |
remove_javascript = True |
| 27 |
|
| 28 |
keep_only_tags = [classes('title-wrapper content-wrapper article-header lead-art article-body')] |
| 29 |
remove_tags = [ |
| 30 |
classes('email-signup story-tools newsletter topics-list'), |
| 31 |
classes('wp-block-propublica-notes--top'), |
| 32 |
] |
| 33 |
remove_tags_after = classes('article-body') |
| 34 |
|
| 35 |
feeds = [ |
| 36 |
('Top Stories', 'http://feeds.propublica.org/propublica/main'), |
| 37 |
] |
| 38 |
|
| 39 |
def preprocess_html(self, soup): |
| 40 |
for img in soup.findAll('img', **classes('lazyload')): |
| 41 |
source = img.findParent('picture') |
| 42 |
if source is not None: |
| 43 |
source = source.find('source') |
| 44 |
if source is not None: |
| 45 |
img['src'] = source['data-srcset'] |
| 46 |
for img in soup.findAll('img', srcset=True): |
| 47 |
img['src'] = img['srcset'].split()[0] |
| 48 |
return soup |