A new update for this recipe. HCN made some changes.
Spoiler:
Code:
# -*- coding: utf-8 -*-
##
## Written: 2012-01-28
## Last Edited: 2013-09-06
## Remark: Version 1.3
## Update cleanup for new web article design
##
__license__ = 'GPL v3'
__copyright__ = '2013, Armin Geller'
'''
Fetch High Country News
'''
from calibre.web.feeds.news import BasicNewsRecipe
class HighCountryNews(BasicNewsRecipe):
title = u'High Country News'
description = u'High Country News (RSS Version)'
__author__ = 'Armin Geller'
publisher = 'High Country News'
category = 'news, politics'
timefmt = ' [%a, %d %b %Y]'
language = 'en-Us'
encoding = 'UTF-8'
publication_type = 'newspaper'
oldest_article = 14
max_articles_per_feed = 100
no_stylesheets = True
auto_cleanup = False
remove_javascript = True
remove_empty_feeds = True
use_embedded_content = False
masthead_url = 'http://www.hcn.org/logo.jpg'
cover_source = 'http://www.hcn.org'
def get_cover_url(self):
cover_source_soup = self.index_to_soup(self.cover_source)
preview_image_div = cover_source_soup.find(attrs={'class':' portaltype-Plone Site content--hcn template-homepage_view'})
return preview_image_div.div.img['src']
feeds = [
(u'Most recent', u'http://feeds.feedburner.com/hcn/most-recent?format=xml'),
(u'Current Issue', u'http://feeds.feedburner.com/hcn/current-issue?format=xml'),
(u'From the Blogs', u'http://feeds.feedburner.com/hcn/FromTheBlogs?format=xml'),
(u'Heard around the West', u'http://feeds.feedburner.com/hcn/heard?format=xml'),
(u'The GOAT Blog', u'http://feeds.feedburner.com/hcn/goat?format=xml'),
(u'The Range', u'http://feeds.feedburner.com/hcn/range?format=xml'),
(u'Writers on the Range', u'http://feeds.feedburner.com/hcn/wotr'),
(u'High Country Views', u'http://feeds.feedburner.com/hcn/HighCountryViews'),
]
# 2013-07-23 AGe New coding w/o using print_version
keep_only_tags = [
dict(name='div', attrs={'id':['content']}),
]
remove_tags = [
dict(name='div', attrs={'class':['documentActions supercedeDocumentActions editorialDocumentActions',
'documentActions supercedeDocumentActions editorialDocumentActions editorialFooterDocumentActions',
'article-sidebar',
'image-viewer-controls nojs',
'protectedArticleWrapper',
'visualClear',
'feed-icons', #2013-09-06 AGe add
'PayWallEmail', #2013-09-06 AGe add
]}),
dict(name='div', attrs={'id':['offer-below-locked-article']}), #2013-09-06 AGe add
]
INDEX = ''
def append_page(self, soup, appendtag, position):
pager = soup.find('span',attrs={'class':'next'})
if pager:
nexturl = self.INDEX + pager.a['href']
soup2 = self.index_to_soup(nexturl)
texttag = soup2.find('div', attrs={'class':'article-text'})
newpos = len(texttag.contents)
self.append_page(soup2,texttag,newpos)
texttag.extract()
appendtag.insert(position,texttag)
def preprocess_html(self, soup):
self.append_page(soup, soup.body, 3)
pager = soup.find('div',attrs={'class':'listingBar listingBar-article'})
if pager:
pager.extract()
return self.adeify_images(soup)