mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-10-30 18:22:25 -04:00
54 lines
2.0 KiB
Plaintext
54 lines
2.0 KiB
Plaintext
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'
|
|
oldest_article = 31#days
|
|
max_articles_per_feed = 50
|
|
use_embedded_content = False
|
|
#encoding = 'latin1'
|
|
recursions = 1
|
|
match_regexps = ['&page=[2-9]$']
|
|
|
|
remove_stylesheets = True
|
|
#remove_tags_before = dict(name='h1', attrs={'class':'heading'})
|
|
remove_tags_after = dict(name='p', attrs={'id':'articlePaginationWrapper'})
|
|
remove_tags = [
|
|
dict(name='iframe'),
|
|
dict(name='div', attrs={'class':'article_sidebar_border'}),
|
|
dict(name='div', attrs={'id':['article_sidebar_border', 'most-popular_large', 'most-popular-body_large']}),
|
|
##dict(name='ul', attrs={'class':'article-tools'}),
|
|
dict(name='ul', attrs={'class':'cat-breadcrumb col three last'}),
|
|
]
|
|
|
|
|
|
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'})
|
|
##td = heading.findParent(name='td')
|
|
##td.extract()
|
|
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
|
|
body = soup.find(name='body')
|
|
body.insert(0, story)
|
|
return soup
|
|
|
|
#def postprocess_html(self, soup, first):
|
|
#for p in soup.findAll(id='articlePaginationWrapper'): p.extract()
|
|
#if not first:
|
|
#for div in soup.findAll(id='article-head'): div.extract()
|
|
#return soup
|