New recipe for The Bangkok Post by kwetal

This commit is contained in:
Kovid Goyal 2009-12-06 12:10:35 -07:00
parent f962231a7c
commit 95f5b3c176

View File

@ -0,0 +1,45 @@
from calibre.web.feeds.news import BasicNewsRecipe
class BangkokPostRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'kwetal'
language = 'en_TH'
version = 1
title = u'Bangkok Post'
publisher = u'Post Publishing PCL'
category = u'News'
description = u'The world\'s window to Thailand'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
# Feeds from: http://www.bangkokpost.com/rss/
feeds = []
feeds.append((u'Breaking News', u'http://www.bangkokpost.com/rss/data/breakingnews.xml'))
feeds.append((u'Top Stories', u'http://www.bangkokpost.com/rss/data/topstories.xml'))
feeds.append((u'News', u'http://www.bangkokpost.com/rss/data/news.xml'))
feeds.append((u'Business', u'http://www.bangkokpost.com/rss/data/business.xml'))
feeds.append((u'Opinion', u'http://www.bangkokpost.com/rss/data/opinion.xml'))
feeds.append((u'Travel', u'http://www.bangkokpost.com/rss/data/travel.xml'))
feeds.append((u'Leisure', u'http://www.bangkokpost.com/rss/data/leisure.xml'))
feeds.append((u'Entertainment', u'http://www.bangkokpost.com/rss/data/entertainment.xml'))
feeds.append((u'Auto', u'http://www.bangkokpost.com/rss/data/auto.xml'))
feeds.append((u'Life', u'http://www.bangkokpost.com/rss/data/life.xml'))
feeds.append((u'Tech', u'http://www.bangkokpost.com/rss/data/tect.xml'))
keep_only_tags = []
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'entry'}))
remove_tags = []
remove_tags.append(dict(name = 'div', attrs = {'class': 'article-features'}))
remove_tags.append(dict(name = 'div', attrs = {'class': 'socialBookmark'}))
remove_tags.append(dict(name = 'div', attrs = {'id': 'main-sns'}))
# Their YouTube movies are displayed in an iframe, if you want those you will have to parse the articles by hand.
# Setting self.recursion to 1, which might resolve this, makes calibre downloading a lot of PDF files, which will cause a very, very very, long download time
remove_tags.append(dict(name = 'iframe'))