Code:
# -*- coding: utf-8 -*-
##
## Written: 2012-01-28
## Last Edited: 2014-09-18
## Remark: Version 2.0 first check
## Update cleanup for new web article design and extra css
##
__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/issues' # AGE 2014-09-18 new
def get_cover_url(self):
cover_source_soup = self.index_to_soup(self.cover_source)
preview_image_div = cover_source_soup.find(attrs={'class':'articles'}) # AGE 2014-09-18 new
return preview_image_div.div.a.figure.img['src'] # AGE 2014-09-18 newm take always the first one (hopefully)
# AGe new extra css to get rid of ugly style
# li for delete disc style,
# caption and credit for description & author of pictures
extra_css = '''
h1 {font-size: 1.6em; text-align: left}
h2 {font-size: 1em; font-style: italic; font-weight: normal}
h3 {font-size: 1.3em;text-align: left}
h4, h5, h6, {font-size: 1em;text-align: left}
li {list-style-type: none}
.caption, .credit {font-size: 0.9em; font-style: italic}
'''
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'),
]
# 2014-09-18 AGe New coding related to design changes
keep_only_tags = [
dict(name='div', attrs={'id':'content'}),
dict(name='div', attrs={'class':'opaque'}),
]
remove_tags = [
dict(name='div', attrs={'class':[
'large-4 columns right-portlets',
'small-12 columns',
'pagination-share',
'tiny content f-dropdown',
'image-viewer-controls',
]}),
dict(name='ul', attrs={'class':[
'document-actions',
'topics',
]}),
dict(name='a', attrs={'name':[
'body',
]}),
]
# AGE 2014-09-18 this will stay for a while
# but have no impact for now ...
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)