mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
32 lines
1.2 KiB
Plaintext
32 lines
1.2 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class AdvancedUserRecipe1282101454(BasicNewsRecipe):
|
|
title = 'Popular Science'
|
|
language = 'en'
|
|
__author__ = 'Kovid Goyal'
|
|
description = 'Popular Science'
|
|
publisher = 'Popular Science'
|
|
oldest_article = 7 # change this if you want more current articles. I like to go a week in
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
use_embedded_content = False
|
|
|
|
feeds = [
|
|
|
|
('Gadgets', 'http://www.popsci.com/full-feed/gadgets'),
|
|
('Cars', 'http://www.popsci.com/full-feed/cars'),
|
|
('Science', 'http://www.popsci.com/full-feed/science'),
|
|
('Technology', 'http://www.popsci.com/full-feed/technology'),
|
|
('DIY', 'http://www.popsci.com/full-feed/diy'),
|
|
|
|
]
|
|
keep_only_tags = [
|
|
dict(attrs={'class':lambda x: x and {'pane-node-header', 'pane-node-body'} & set(x.split())}),
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'data-medsrc':True}):
|
|
img['src'] = img['data-medsrc']
|
|
return soup
|