mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
75 lines
2.8 KiB
Python
75 lines
2.8 KiB
Python
#!/usr/bin/env python2
|
|
# vim:fileencoding=utf-8
|
|
from __future__ import (unicode_literals, division, absolute_import,
|
|
print_function)
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import Tag
|
|
import html5lib
|
|
from lxml.html import tostring
|
|
from css_selectors import Select
|
|
|
|
|
|
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']
|
|
|
|
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_raw_html(self, raw_html, url):
|
|
# BeautifulSoup does not parse the natgeo html correctly, so we use a
|
|
# custom cleanup routine
|
|
|
|
# NatGeo embeds huge inline svg images as interactive graphics, this
|
|
# breaks conversion because split points cannot be found
|
|
raw_html = re.sub(r'<svg.+?</svg>', '', raw_html, flags=re.DOTALL)
|
|
root = html5lib.parse(
|
|
raw_html, namespaceHTMLElements=False, treebuilder='lxml')
|
|
select = Select(root)
|
|
keep = tuple(select('.mainArt')) + tuple(select('.byline')
|
|
) + tuple(select('#article__body'))
|
|
body = root.xpath('//body')[0]
|
|
for elem in keep:
|
|
body.append(elem)
|
|
for child in tuple(body.iterchildren('*')):
|
|
if child not in keep:
|
|
body.remove(child)
|
|
for head in root.xpath('//head'):
|
|
for child in tuple(head.iterchildren('*')):
|
|
head.remove(child)
|
|
return tostring(root, encoding=unicode)
|
|
|
|
def preprocess_html(self, soup):
|
|
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 = Tag(soup, "img")
|
|
img['src'] = url
|
|
div.append(img)
|
|
return soup
|