calibre/recipes/toronto_sun.recipe
Kovid Goyal 29cd8d64ea
Change shebangs to python from python2
Also remove a few other miscellaneous references to python2
2020-08-22 18:47:51 +05:30

76 lines
3.6 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.torontosun.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class TorontoSun(BasicNewsRecipe):
title = 'Toronto SUN'
__author__ = 'Darko Miletic and Sujata Raman'
description = 'News from Canada'
publisher = 'Toronto Sun'
category = 'news, politics, Canada'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
language = 'en_CA'
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
keep_only_tags = [
dict(name='div', attrs={'class': ['articleHead', 'leftBox']}), dict(name='div', attrs={
'id': 'channelContent'}), dict(name='div', attrs={'id': 'rotateBox'}), dict(name='img')
]
remove_tags = [
dict(name='div', attrs={'class': ['bottomBox clear', 'bottomBox', 'breadCrumb', 'articleControls thin', 'articleControls thin short', 'extraVideoList']}), dict(name='h2', attrs={'class': 'microhead'}), dict(name='div', attrs={'id': 'commentsBottom'}), dict(name=['link', 'iframe', 'object']), dict(name='a', attrs={'rel': 'swap'}), dict(name='a', attrs={'href': '/news/haiti/'}), dict(name='ul', attrs={'class': ['tabs dl contentSwap', 'micrositeNav clearIt hList', 'galleryNav rotateNav']}) # noqa
]
remove_tags_after = [
dict(name='div', attrs={'class': 'bottomBox clear'}), dict(name='div', attrs={
'class': 'rotateBox'}), dict(name='div', attrs={'id': 'contentSwap'})
]
extra_css = '''
h1{font-family :Arial,Helvetica,sans-serif; font-size:large;}
h2{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#666666;}
h3{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#000000;}
p{font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
.bold{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;color:#444444;margin-left: 0px;}
.subheading{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#000000; font-weight: bold;}
.byline{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
.byline span{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small; text-transform: uppercase;}
.updated{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
.galleryCaption{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
.galleryUpdated{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
'''
feeds = [
(u'News', u'http://www.torontosun.com/news/rss.xml'),
(u'Canada', u'http://www.torontosun.com/news/canada/rss.xml'),
(u'Columnists', u'http://www.torontosun.com/news/columnists/rss.xml'),
(u'World', u'http://www.torontosun.com/news/world/rss.xml'),
(u'Money', u'http://www.torontosun.com/money/rss.xml')
]
def preprocess_html(self, soup):
# To fetch images from the specified source
for img in soup.findAll('img', src=True):
url = img.get('src').split('?')[-1].partition('=')[-1]
if url:
img['src'] = url.split('&')[0].partition('=')[0]
img['width'] = url.split(
'&')[-1].partition('=')[-1].split('x')[0]
img['height'] = url.split(
'&')[-1].partition('=')[-1].split('x')[1]
return soup