mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
60 lines
2.6 KiB
Plaintext
60 lines
2.6 KiB
Plaintext
from calibre.ptempfile import PersistentTemporaryFile
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class AdvancedUserRecipe1276486274(BasicNewsRecipe):
|
|
title = u'Today Online - Singapore'
|
|
publisher = 'MediaCorp Press Ltd - Singapore'
|
|
__author__ = 'rty'
|
|
category = 'news, Singapore'
|
|
oldest_article = 7
|
|
max_articles_per_feed = 100
|
|
remove_javascript = True
|
|
use_embedded_content = False
|
|
no_stylesheets = True
|
|
language = 'en_SG'
|
|
temp_files = []
|
|
articles_are_obfuscated = True
|
|
masthead_url = 'http://www.todayonline.com/App_Themes/Default/images/icons/TodayOnlineLogo.gif'
|
|
conversion_options = {'linearize_tables':True}
|
|
extra_css = '''
|
|
.author{font-style: italic; font-size: small}
|
|
.date{font-style: italic; font-size: small}
|
|
.Headline{font-weight: bold; font-size: xx-large}
|
|
.headerStrap{font-weight: bold; font-size: x-large; font-syle: italic}
|
|
.bodyText{font-size: 4px;font-family: Times New Roman;}
|
|
'''
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'id':['fullPrintBodyHolder']})
|
|
]
|
|
remove_tags_after = [ dict(name='div', attrs={'class':'button'})]
|
|
|
|
|
|
remove_tags = [
|
|
dict(name='div', attrs={'class':['url','button']})
|
|
]
|
|
feeds = [
|
|
(u'Singapore', u'http://www.todayonline.com/RSS/Singapore'),
|
|
(u'Hot News', u'http://www.todayonline.com/RSS/Hotnews'),
|
|
(u'Today Online', u'http://www.todayonline.com/RSS/Todayonline'),
|
|
(u'Voices', u'http://www.todayonline.com/RSS/Voices'),
|
|
(u'Commentary', u'http://www.todayonline.com/RSS/Commentary'),
|
|
(u'World', u'http://www.todayonline.com/RSS/World'),
|
|
(u'Business', u'http://www.todayonline.com/RSS/Business'),
|
|
(u'Column', u'http://www.todayonline.com/RSS/Columns'),
|
|
]
|
|
|
|
def get_obfuscated_article(self, url):
|
|
br = self.get_browser()
|
|
br.open(url)
|
|
response = br.follow_link(url_regex = r'/Print/', nr = 0)
|
|
html = response.read()
|
|
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
|
|
self.temp_files[-1].write(html)
|
|
self.temp_files[-1].close()
|
|
return self.temp_files[-1].name
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return soup
|