Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Nature News

Browse Source 
Fixes #1936786 [Error when downloading recipe](https://bugs.launchpad.net/calibre/+bug/1936786)
This commit is contained in:
Kovid Goyal 2021-07-27 12:09:18 +05:30
parent 406c989f2b
commit 3e09d4f456
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 22 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
recipes/freenature.recipe
View File

@ -1,10 +1,16 @@
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 NatureNews(BasicNewsRecipe):
title = u'Nature News'
language = 'en'
__author__ = 'Krittika Goyal, Starson17, adrianf0'
__author__ = 'Kovid Goyal'
oldest_article = 31 # days
remove_empty_feeds = True
max_articles_per_feed = 50
@ -12,38 +18,20 @@ class NatureNews(BasicNewsRecipe):
no_stylesheets = True
use_embedded_content = False
remove_javascript = True
keep_only_tags = [dict(name='div', attrs={'id': 'article'})]
extra_css = '''
.author { text-align: right; font-size: small; line-height:1em; margin-top:0px; margin-left:0; margin-right:0; margin-bottom: 0; }
.imagedescription { font-size: small;
font-style:italic; line-height:1em; margin-top:5px;
margin-left:0; margin-right:0; margin-bottom: 0; }
.imagecredit { font-size: x-small; font-style: normal; font-weight: bold}
'''
keep_only_tags = [
classes('container-type-article'),
]
remove_tags = [
dict(id='related-articles'),
classes('u-hide-print hide-print visually-hidden'),
dict(name=['meta', 'link', 'source']),
]
# News and comments
feeds = [(u'Nature News', 'http://feeds.nature.com/NatureNewsComment')]
remove_tags = []
remove_tags.append(dict(name='div', attrs={'class': 'top-row'}))
remove_tags.append(dict(name='ul', attrs={'class': 'authors cleared'}))
remove_tags.append(
dict(name='div', attrs={'class': 'cleared article-tools extra'}))
remove_tags.append(
dict(name='div', attrs={'class': 'related-stories-box box'}))
remove_tags.append(dict(name='div', attrs={'id': 'related-links'}))
remove_tags.append(dict(name='p', attrs={'class': 'not-logged-in'}))
remove_tags.append(dict(name='ul', attrs={'class': 'endnotes'}))
remove_tags.append(
dict(name='div', attrs={'class': 'author-details-below'}))
remove_tags.append(dict(name='div', attrs={'id': 'references'}))
remove_tags.append(dict(name='a', attrs={'class': 'rss-link'}))
remove_tags.append(dict(name='div', attrs={'class': 'comment-avatar'}))
remove_tags.append(dict(name='ul', attrs={'class': 'moderation'}))
# links to other articles, main conntent is img-middle
remove_tags.append(dict(name='div', attrs={'class': 'img img-right'}))
remove_tags.append(
dict(name='div', attrs={'class': 'pullquote pullquote-left'}))
remove_tags.append(
dict(name='div', attrs={'class': 'pullquote pullquote-right'}))
remove_tags.append(
dict(name='div', attrs={'class': 'cleared subject-terms-container'}))
feeds = [(u'Nature News', 'http://feeds.nature.com/nature/rss/current')]
def preprocess_html(self, soup):
for img in soup.findAll('img', src=lambda x: x and x.startswith('//')):
img['src'] = 'https:' + img['src']
print(img)
return soup