calibre/recipes/natgeo_kids.recipe
2025-01-24 11:14:22 +01:00

96 lines
3.4 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe
class NatGeo(BasicNewsRecipe):
title = 'National Geographic Kids'
description = ('The National Geographic, an American monthly magazine. '
'Inspiring people to care about the planet since 1888')
language = 'en'
encoding = 'utf8'
publisher = 'kids.nationalgeographic.com'
category = 'science, nat geo'
__author__ = 'unkn0wn'
timefmt = ' [%a, %d %b, %Y]'
use_embedded_content = False
remove_javascript = True
masthead_url = 'https://i.natgeofe.com/n/e76f5368-6797-4794-b7f6-8d757c79ea5c/ng-logo-2fl.png?w=600&h=600'
remove_empty_feeds = True
resolve_internal_links = True
ignore_duplicate_articles = {'title', 'url'}
recipe_specific_options = {
'res': {
'short': 'For hi-res images, select a resolution from the\nfollowing options: 800, 1000, 1200 or 1500',
'long': 'This is useful for non e-ink devices, and for a lower file size\nthan the default, use 400 or 300.',
'default': '600',
},
}
@property
def natgeo_parser(self):
ans = getattr(self, '_natgeo_parser', None)
if ans is None:
from calibre.live import load_module
self._natgeo_parser = ans = load_module('calibre.web.site_parsers.natgeo')
return ans
def preprocess_raw_html(self, raw_html, url):
return self.natgeo_parser.extract_html(raw_html)
extra_css = '''
blockquote { color:#404040; }
.byline, i { font-style:italic; color:#202020; }
.cap { font-size:small; }
img {display:block; margin:0 auto;}
.cred { font-style:italic; font-size:small; color:#404040; }
.auth, .time, .sub { font-size:small; color:#5c5c5c; }
'''
def parse_index(self):
index = 'https://kids.nationalgeographic.com/'
sections = [
'Front Page', 'animals', 'history', 'science',
'space', 'homework-help', 'crafts',
]
feeds = []
for sec in sections:
section = sec.capitalize()
self.log(section)
url = index + sec
if sec.startswith('Front'):
url = index
self.log('Fetching articles from ', url)
soup = self.index_to_soup(url)
articles = []
for a in soup.findAll('a', attrs={'href': lambda x: x and '/article/' in x}):
if a.find('img') and '/games/' in a['href']:
continue
url = a['href']
title = self.tag_to_string(a)
self.log('\t', title, '\n\t\t', url)
articles.append({'title': title, 'url': url})
if articles:
feeds.append((section, articles))
return feeds
def preprocess_html(self, soup):
for h2 in soup.findAll('h2'):
h2.name = 'h4'
for img in soup.findAll('img', src=True):
res = '?w=600'
w = self.recipe_specific_options.get('res')
if w and isinstance(w, str):
res = '?w=' + w
img['src'] = img['src'] + res
return soup
def populate_article_metadata(self, article, soup, first):
summ = soup.find(attrs={'class': 'byline'})
if summ:
article.summary = self.tag_to_string(summ)
article.text_summary = self.tag_to_string(summ)