calibre/recipes/chr_mon.recipe

114 lines
5.3 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>'
'''
www.csmonitor.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class CSMonitor(BasicNewsRecipe):
title = 'The Christian Science Monitor - daily'
__author__ = 'Darko Miletic'
description = 'The Christian Science Monitor is an international news organization that delivers thoughtful, global coverage via its website, weekly magazine, daily news briefing, and email newsletters.'
publisher = 'The Christian Science Monitor'
category = 'news, politics, USA'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'en'
remove_empty_feeds = True
publication_type = 'newspaper'
masthead_url = 'http://www.csmonitor.com/extension/csm_base/design/csm_design/images/csmlogo_179x46.gif'
extra_css = """
body{font-family: Arial,Tahoma,Verdana,Helvetica,sans-serif }
img{margin-bottom: 0.4em; display:block}
.head {font-family: Georgia,"Times New Roman",Times,serif}
.sByline,.caption{font-size: x-small}
.hide{display: none}
.sLoc{font-weight: bold}
ul{list-style-type: none}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
remove_tags = [
dict(name=['meta','link','iframe','object','embed'])
,dict(attrs={'class':re.compile('(^|| )podStoryRel($|| )', re.DOTALL)})
,dict(attrs={'class':['bottom-rel','hide']})
,dict(attrs={'id':['pgallerycarousel_enlarge','pgallerycarousel_related']})
]
keep_only_tags = [
dict(name='h1', attrs={'class':'head'})
,dict(name='h2', attrs={'class':'subhead'})
,dict(attrs={'class':['sByline','thePhoto','ui-body-header']})
,dict(attrs={'class':re.compile('(^|| )sBody($|| )', re.DOTALL)})
]
remove_attributes=['xmlns:fb']
feeds = [
(u'USA' , u'http://rss.csmonitor.com/feeds/usa' )
,(u'World' , u'http://rss.csmonitor.com/feeds/world' )
,(u'Politics' , u'http://rss.csmonitor.com/feeds/politics' )
,(u'Business' , u'http://rss.csmonitor.com/feeds/wam' )
,(u'Commentary' , u'http://rss.csmonitor.com/feeds/commentary' )
,(u'Books' , u'http://rss.csmonitor.com/feeds/books' )
,(u'Arts' , u'http://rss.csmonitor.com/feeds/arts' )
,(u'Environment' , u'http://rss.csmonitor.com/feeds/environment')
,(u'Innovation' , u'http://rss.csmonitor.com/feeds/scitech' )
,(u'Living' , u'http://rss.csmonitor.com/feeds/living' )
,(u'Science' , u'http://rss.csmonitor.com/feeds/science' )
,(u'The Culture' , u'http://rss.csmonitor.com/feeds/theculture' )
,(u'The Home Forum', u'http://rss.csmonitor.com/feeds/homeforum' )
,(u'Articles' , u'http://rss.csmonitor.com/feeds/csarticles' )
]
def append_page(self, soup):
pager = soup.find('div', attrs={'class':'navigation'})
if pager:
nexttag = pager.find(attrs={'id':'next-button'})
if nexttag:
nurl = 'http://www.csmonitor.com' + nexttag['href']
soup2 = self.index_to_soup(nurl)
texttag = soup2.find(attrs={'class':re.compile('(^|| )sBody($|| )', re.DOTALL)})
if texttag:
appendtag = soup.find(attrs={'class':re.compile('(^|| )sBody($|| )', re.DOTALL)})
for citem in texttag.findAll(attrs={'class':[re.compile('(^|| )podStoryRel($|| )', re.DOTALL),'bottom-rel','hide']}):
citem.extract()
self.append_page(soup2)
texttag.extract()
pager.extract()
appendtag.append(texttag)
def preprocess_html(self, soup):
self.append_page(soup)
pager = soup.find('div', attrs={'class':'navigation'})
if pager:
pager.extract()
for item in soup.findAll('a'):
limg = item.find('img')
if item.string is not None:
str = item.string
item.replaceWith(str)
else:
if limg:
item.name = 'div'
item.attrs = []
else:
str = self.tag_to_string(item)
item.replaceWith(str)
for item in soup.findAll('img'):
if 'scorecardresearch' in item['src']:
item.extract()
else:
if not item.has_key('alt'):
item['alt'] = 'image'
return soup