| 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 NatureNews(BasicNewsRecipe): |
| 10 |
title = 'Nature News' |
| 11 |
language = 'en' |
| 12 |
__author__ = 'Kovid Goyal' |
| 13 |
oldest_article = 31 # days |
| 14 |
remove_empty_feeds = True |
| 15 |
max_articles_per_feed = 50 |
| 16 |
|
| 17 |
no_stylesheets = True |
| 18 |
use_embedded_content = False |
| 19 |
remove_javascript = True |
| 20 |
keep_only_tags = [ |
| 21 |
classes('container-type-article'), |
| 22 |
] |
| 23 |
remove_tags = [ |
| 24 |
dict(id='related-articles'), |
| 25 |
classes('u-hide-print hide-print visually-hidden'), |
| 26 |
dict(name=['meta', 'link', 'source']), |
| 27 |
] |
| 28 |
|
| 29 |
# News and comments |
| 30 |
feeds = [('Nature News', 'http://feeds.nature.com/nature/rss/current')] |
| 31 |
|
| 32 |
def preprocess_html(self, soup): |
| 33 |
for img in soup.findAll('img', src=lambda x: x and x.startswith('//')): |
| 34 |
img['src'] = 'https:' + img['src'] |
| 35 |
print(img) |
| 36 |
return soup |