mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
87 lines
4.5 KiB
Plaintext
87 lines
4.5 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.independent.co.uk
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
|
|
|
class TheIndependent(BasicNewsRecipe):
|
|
title = 'The Independent'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Independent News - Breaking news, comment and features from The Independent newspaper'
|
|
publisher = 'The Independent'
|
|
category = 'news, politics, UK'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 200
|
|
no_stylesheets = True
|
|
encoding = 'cp1252'
|
|
use_embedded_content = False
|
|
language = 'en_GB'
|
|
remove_empty_feeds = True
|
|
publication_type = 'newspaper'
|
|
masthead_url = 'http://www.independent.co.uk/independent.co.uk/images/logo-london.png'
|
|
extra_css = """
|
|
h1{font-family: Georgia,serif }
|
|
body{font-family: Verdana,Arial,Helvetica,sans-serif}
|
|
img{margin-bottom: 0.4em; display:block}
|
|
.info,.caption,.credits{font-size: x-small}
|
|
"""
|
|
|
|
conversion_options = {
|
|
'comment' : description
|
|
, 'tags' : category
|
|
, 'publisher' : publisher
|
|
, 'language' : language
|
|
}
|
|
|
|
remove_tags =[
|
|
dict(name=['meta','link','object','embed','iframe','base','style'])
|
|
,dict(attrs={'class':['related-articles','share','googleCols','article-tools','paging','googleArt']})
|
|
,dict(attrs={'id':['newsVideoPlayer','yahoobook','google-intext']})
|
|
]
|
|
keep_only_tags =[dict(attrs={'id':'article'})]
|
|
remove_attributes=['lang','onclick','width','xmlns:fb']
|
|
|
|
|
|
feeds = [
|
|
(u'UK' , u'http://www.independent.co.uk/news/uk/rss' )
|
|
,(u'World' , u'http://www.independent.co.uk/news/world/rss' )
|
|
,(u'Business' , u'http://www.independent.co.uk/news/business/rss' )
|
|
,(u'People' , u'http://www.independent.co.uk/news/people/rss' )
|
|
,(u'Science' , u'http://www.independent.co.uk/news/science/rss' )
|
|
,(u'Media' , u'http://www.independent.co.uk/news/media/rss' )
|
|
,(u'Education' , u'http://www.independent.co.uk/news/education/rss' )
|
|
,(u'Leading Articles' , u'http://www.independent.co.uk/opinion/leading-articles/rss')
|
|
,(u'Comentators' , u'http://www.independent.co.uk/opinion/commentators/rss' )
|
|
,(u'Columnists' , u'http://www.independent.co.uk/opinion/columnists/rss' )
|
|
,(u'Letters' , u'http://www.independent.co.uk/opinion/letters/rss' )
|
|
,(u'Big Question' , u'http://www.independent.co.uk/extras/big-question/rss' )
|
|
,(u'Sport' , u'http://www.independent.co.uk/sport/rss' )
|
|
,(u'Life&Style' , u'http://www.independent.co.uk/life-style/rss' )
|
|
,(u'Arts&Entertainment' , u'http://www.independent.co.uk/arts-entertainment/rss' )
|
|
,(u'Travel' , u'http://www.independent.co.uk/travel/rss' )
|
|
,(u'Money' , u'http://www.independent.co.uk/money/rss' )
|
|
]
|
|
|
|
def get_article_url(self, article):
|
|
return article.get('guid', None)
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.body.findAll(style=True):
|
|
del item['style']
|
|
for item in soup.body.findAll(['author','preform']):
|
|
item.name='span'
|
|
for item in soup.body.findAll('img'):
|
|
if not item.has_key('alt'):
|
|
item['alt'] = 'image'
|
|
for item in soup.body.findAll('div', attrs={'class':['clear-o','body','photoCaption']}):
|
|
item.name = 'p'
|
|
for item in soup.body.findAll('div'):
|
|
if not item.attrs and not item.contents:
|
|
item.extract()
|
|
soup2 = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
|
|
soup2.body.replaceWith(soup.body)
|
|
return soup2
|