calibre/recipes/natgeo.recipe

81 lines
2.6 KiB
Python

#!/usr/bin/env python2
# vim:fileencoding=utf-8
from __future__ import absolute_import, division, print_function, unicode_literals
import json
from calibre.ebooks.BeautifulSoup import Tag
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)})
def new_tag(soup, name, attrs=()):
impl = getattr(soup, 'new_tag', None)
if impl is not None:
return impl(name, attrs=dict(attrs))
return Tag(soup, name, attrs=attrs or None)
class NatGeo(BasicNewsRecipe):
title = u'National Geographic'
description = 'Daily news articles from The National Geographic'
language = 'en'
oldest_article = 20
max_articles_per_feed = 25
encoding = 'utf8'
publisher = 'nationalgeographic.com'
category = 'science, nat geo'
__author__ = 'Kovid Goyal'
masthead_url = 'http://s.ngeo.com/wpf/sites/themes/global/i/presentation/ng_logo_small.png'
description = 'Inspiring people to care about the planet since 1888'
timefmt = ' [%a, %d %b, %Y]'
no_stylesheets = True
use_embedded_content = False
remove_attributes = ['style']
remove_javascript = False
keep_only_tags = [
classes('mainArt byline'),
dict(id='article__body'),
]
remove_tags = [
classes('hide-from-mobile ad-holder enlarge-button'),
dict(name='svg meta'.split()),
]
feeds = [
(u'Daily News', u'http://feeds.nationalgeographic.com/ng/News/News_Main')
]
def parse_feeds(self):
feeds = BasicNewsRecipe.parse_feeds(self)
for feed in feeds:
for article in feed.articles[:]:
if 'Presented' in article.title or 'Pictures' in article.title:
feed.articles.remove(article)
return feeds
def preprocess_html(self, soup):
for div in soup.findAll(attrs={'data-pestle-module': 'PictureFill'}):
script = div.find('script')
src = json.loads(self.tag_to_string(script))['src']
div.name = 'img'
div['src'] = src
for div in soup.findAll(attrs={'data-src': True, 'class': 'delayed-image-load'}):
url = div['data-src']
idx = url.find('.jpg/{width')
if idx != -1:
url = url[:idx + 4]
img = new_tag(soup, "img")
img['src'] = url
div.append(img)
for script in soup.findAll('script'):
script.extract()
return soup