mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
89 lines
3.2 KiB
Python
89 lines
3.2 KiB
Python
#!/usr/bin/env python2
|
|
# -*- coding: cp1252 -*-
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
politico.com
|
|
'''
|
|
|
|
import re, traceback
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class Politico(BasicNewsRecipe):
|
|
|
|
title = 'Politico'
|
|
__author__ = 'Darko Miletic and Sujata Raman'
|
|
description = 'Political news from USA'
|
|
publisher = 'Capitol News Company, LLC'
|
|
category = 'news, politics, USA'
|
|
oldest_article = 7
|
|
max_articles_per_feed = 100
|
|
use_embedded_content = False
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
encoding = 'UTF-8'
|
|
language = 'en'
|
|
|
|
html2lrf_options = [
|
|
'--comment', description
|
|
, '--category', category
|
|
, '--publisher', publisher
|
|
, '--ignore-tables'
|
|
]
|
|
|
|
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
|
|
|
|
remove_tags = [
|
|
dict(name=['notags','embed','object','link','img']),
|
|
]
|
|
|
|
extra_css = '''
|
|
body{font-family:Arial,Sans-serif;}
|
|
element.style{color:#FF0000;font-family:Arial,Sans-serif;}
|
|
.author{color:#808080;font-size:x-small;}
|
|
a{ color:#003399;}
|
|
.byline{color:#696969 ; font-size:x-small;}
|
|
.story{color:#000000;}
|
|
td{color:#000000;}
|
|
'''
|
|
|
|
feeds = [
|
|
(u'Top Stories' , u'http://www.politico.com/rss/politicopicks.xml' )
|
|
,(u'Congress' , u'http://www.politico.com/rss/congress.xml' )
|
|
,(u'Ideas' , u'http://www.politico.com/rss/ideas.xml' )
|
|
,(u'Life' , u'http://www.politico.com/rss/life.xml' )
|
|
,(u'Lobbyists' , u'http://www.politico.com/rss/lobbyists.xml' )
|
|
,(u'Pitboss' , u'http://www.politico.com/rss/pitboss.xml' )
|
|
,(u'Politics' , u'http://www.politico.com/rss/politics.xml' )
|
|
,(u'Roger Simon' , u'http://www.politico.com/rss/rogersimon.xml' )
|
|
,(u'Suite Talk' , u'http://www.politico.com/rss/suitetalk.xml' )
|
|
,(u'Playbook' , u'http://www.politico.com/rss/playbook.xml' )
|
|
#(u'The Huddle' , u'http://www.politico.com/rss/huddle.xml' )
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
mtag = '<meta http-equiv="Content-Language" content="en"/>'
|
|
soup.head.insert(0,mtag)
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return soup
|
|
|
|
url_pat = re.compile(r'<a href="([^"]+print.*\.cfm[^"]+)"')
|
|
|
|
def postprocess_html(self, soup, first):
|
|
|
|
for tag in soup.findAll(name=['table', 'tr', 'td']):
|
|
tag.name = 'div'
|
|
return soup
|
|
|
|
def print_version(self, url):
|
|
raw = self.index_to_soup(url, raw=True)
|
|
try:
|
|
url = self.url_pat.search(raw).group(1)
|
|
except:
|
|
traceback.print_exc()
|
|
url = None
|
|
return url
|