mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
110 lines
3.7 KiB
Python
110 lines
3.7 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
from __future__ import absolute_import, division, print_function, unicode_literals
|
|
|
|
import json
|
|
from collections import defaultdict
|
|
|
|
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)
|
|
|
|
|
|
def entry_to_article(entry):
|
|
url = entry.get('uri')
|
|
if not url:
|
|
return None, None
|
|
section = 'Articles'
|
|
article = {'url': url}
|
|
for component in entry.get('components', ()):
|
|
if component.get('content_type') == 'title':
|
|
article['title'] = component['title']['text']
|
|
elif component.get('content_type') == 'kicker':
|
|
v = component['kicker'].get('vertical') or {}
|
|
if v.get('name'):
|
|
section = v['name']
|
|
elif component.get('content_type') == 'dek':
|
|
if component['dek'].get('text'):
|
|
article['description'] = component['dek']['text']
|
|
if 'title' in article:
|
|
return article, section
|
|
return None, None
|
|
|
|
|
|
class NatGeo(BasicNewsRecipe):
|
|
title = u'National Geographic'
|
|
description = 'Daily news articles from The National Geographic'
|
|
language = 'en'
|
|
encoding = 'utf8'
|
|
publisher = 'nationalgeographic.com'
|
|
category = 'science, nat geo'
|
|
__author__ = 'Kovid Goyal'
|
|
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('main-title article__dek byline-component publishDate mainArt byline'),
|
|
dict(id='article__body'),
|
|
]
|
|
remove_tags = [
|
|
classes('hide-from-mobile ad-holder enlarge-button'),
|
|
dict(name='svg meta'.split()),
|
|
]
|
|
|
|
def parse_index(self):
|
|
feeds = defaultdict(list)
|
|
br = self.get_browser()
|
|
# br.open('https://www.nationalgeographic.com/latest-stories/').read()
|
|
res = br.open_novisit(
|
|
'https://www.nationalgeographic.com/latest-stories/_jcr_content/content/hubfeed.promo-hub-feed-all-stories.json?offset=0&max=18')
|
|
entries = json.loads(res.read())
|
|
for entry in entries:
|
|
art, section = entry_to_article(entry)
|
|
if art is None:
|
|
continue
|
|
feeds[section].append(art)
|
|
ans = [(sec, feeds[sec]) for sec in sorted(feeds) if feeds[sec]]
|
|
for (sec, articles) in ans:
|
|
self.log('Found section:', sec)
|
|
for art in articles:
|
|
self.log('\t', art['title'], art['url'])
|
|
if 'description' in art:
|
|
self.log('\t\t', art['description'])
|
|
return ans
|
|
|
|
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
|