calibre/recipes/slate.recipe
2011-10-03 22:18:28 -06:00

97 lines
3.3 KiB
Python

#!/usr/bin/env python
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
__license__ = 'GPL v3'
'''
calibre recipe for slate.com
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
class Slate(BasicNewsRecipe):
description = 'A general-interest publication offering analysis and commentary about politics, news and culture.'
__author__ = 'Kovid Goyal'
timefmt = ''
no_stylesheets = True
language = 'en'
title = 'Slate'
INDEX = 'http://slate.com'
encoding = 'utf-8'
preprocess_regexps = [
(re.compile(r'<!--.*?-->', re.DOTALL), lambda x: ''),
(re.compile(r'^.*?<html', re.DOTALL), lambda x:'<html'),
(re.compile(r'<meta[^>]+?/>', re.DOTALL), lambda x:''),
]
remove_tags = [
{'name':['link', 'script']},
{'class':['share-box-flank', 'sl-crumbs', 'sl-tbar',
'sl-chunky-tbar']},
]
remove_tags_after = [{'class':'sl-art-creds-cntr'}]
keep_only_tags = {'class':'sl-body-wrapper'}
remove_attributes = ['style']
def print_version(self, url):
return url.replace('.html', '.single.html')
def parse_index(self) :
ans = []
for sectitle, url in (
('News & Politics', '/articles/news_and_politics.html'),
('Technology', '/articles/technology.html'),
('Business', '/articles/business.html'),
('Arts', '/articles/arts.html'),
('Life', '/articles/life.html'),
('Health & Science', '/articles/health_and_science.html'),
('Sports', '/articles/sports.html'),
('Double X', '/articles/double_x.html'),
):
url = self.INDEX + url
self.log('Found section:', sectitle)
articles = self.slate_section_articles(self.index_to_soup(url))
if articles:
ans.append((sectitle, articles))
return ans
def slate_section_articles(self, soup):
cont = soup.find('div', id='most_read')
seen = set()
ans = []
for h4 in cont.findAll('h4'):
a = h4.find('a', href=True)
if a is None: continue
url = a['href']
if url.startswith('/'):
url = self.INDEX + url
if url in seen: continue
seen.add(url)
title = self.tag_to_string(a)
parent = h4.parent
h3 = parent.find('h3')
desc = ''
if h3 is not None:
desc = self.tag_to_string(h3)
a = parent.find('a', rel='author')
if a is not None:
a = self.tag_to_string(a)
art = {'title':title, 'description':desc, 'date':'', 'url':url}
if a:
art['author'] = a
self.log('\tFound article:', title, ' by ', a)
ans.append(art)
return ans
def get_masthead_url(self):
masthead = 'http://img.slate.com/images/redesign2008/slate_logo.gif'
br = BasicNewsRecipe.get_browser()
try:
br.open(masthead)
except:
self.log("\nMasthead unavailable")
masthead = None
return masthead