Thanks for the hint Kovid.
Fixes:
cover image
clean up unwanted text (comments, ads, menus)
better text formatting
remove text overlapping images on K3
Here's the updated recipe:
Spoiler:
Code:
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class SmithsonianMagazine(BasicNewsRecipe):
title = u'Smithsonian Magazine'
language = 'en'
__author__ = 'Krittika Goyal (mod by TerminalVeracity)'
oldest_article = 31#days
max_articles_per_feed = 50
use_embedded_content = False
recursions = 1
cover_url = 'http://sphotos.xx.fbcdn.net/hphotos-snc7/431147_10150602715983253_764313347_n.jpg'
match_regexps = ['&page=[2-9]$']
preprocess_regexps = [
(re.compile(r'for more of Smithsonian\'s coverage on history, science and nature.', re.DOTALL), lambda m: '')
]
extra_css = """
h1{font-size: large; margin: .2em 0}
h2{font-size: medium; margin: .2em 0}
h3{font-size: medium; margin: .2em 0}
#byLine{margin: .2em 0}
.articleImageCaptionwide{font-style: italic}
.wp-caption-text{font-style: italic}
img{display: block}
"""
remove_stylesheets = True
remove_tags_after = dict(name='div', attrs={'class':['post','articlePaginationWrapper']})
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':['article_sidebar_border','viewMorePhotos','addtoany_share_save_container','meta','social','OUTBRAIN','related-articles-inpage']}),
dict(name='div', attrs={'id':['article_sidebar_border', 'most-popular_large', 'most-popular-body_large','comment_section','article-related']}),
dict(name='ul', attrs={'class':'cat-breadcrumb col three last'}),
dict(name='h4', attrs={'id':'related-topics'}),
dict(name='table'),
dict(name='a', attrs={'href':['/subArticleBottomWeb','/subArticleTopWeb','/subArticleTopMag','/subArticleBottomMag']}),
dict(name='a', attrs={'name':'comments_shaded'}),
]
feeds = [
('History and Archeology',
'http://feeds.feedburner.com/smithsonianmag/history-archaeology'),
('People and Places',
'http://feeds.feedburner.com/smithsonianmag/people-places'),
('Science and Nature',
'http://feeds.feedburner.com/smithsonianmag/science-nature'),
('Arts and Culture',
'http://feeds.feedburner.com/smithsonianmag/arts-culture'),
('Travel',
'http://feeds.feedburner.com/smithsonianmag/travel'),
]
def preprocess_html(self, soup):
story = soup.find(name='div', attrs={'id':'article-body'})
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
body = soup.find(name='body')
body.insert(0, story)
return soup