View Single Post
Old 05-17-2011, 08:37 AM   #1
tylau0
Connoisseur
tylau0 began at the beginning.
 
Posts: 82
Karma: 10
Join Date: Oct 2010
Device: Kindle
Improved recipe - United Daily (Taiwan)

I have added a few news feeds to the "United Daily (聯合新聞網)" recipe. Would Kovid put that in the next release of Calibre? Thanks.

Code:
__license__   = 'GPL v3'

class UnitedDaily(BasicNewsRecipe):
	title = u'聯合新聞網'
	oldest_article = 1
	max_articles_per_feed = 100

	feeds = [(u'焦點', u'http://udn.com/udnrss/focus.xml'),
	         (u'政治', u'http://udn.com/udnrss/politics.xml'),
	         (u'社會', u'http://udn.com/udnrss/social.xml'),
	         (u'生活', u'http://udn.com/udnrss/life.xml'),
	         (u'綜合', u'http://udn.com/udnrss/education.xml'),
	         (u'意見評論', u'http://udn.com/udnrss/opinion.xml'),
	         (u'校園博覽會', u'http://mag.udn.com/udnrss/campus_rss.xml'),
	         (u'大台北', u'http://udn.com/udnrss/local_taipei.xml'),
	         (u'桃竹苗', u'http://udn.com/udnrss/local_tyhcml.xml'),
	         (u'中彰投', u'http://udn.com/udnrss/local_tcchnt.xml'),
	         (u'雲嘉南', u'http://udn.com/udnrss/local_ylcytn.xml'),
	         (u'高屏離島', u'http://udn.com/udnrss/local_ksptisland.xml'),
	         (u'基宜花東', u'http://udn.com/udnrss/local_klilhltt.xml'),
	         (u'台灣百寶鄉', u'http://udn.com/udnrss/local_oddlyenough.xml'),
	         (u'台灣人物', u'http://mag.udn.com/udnrss/people_rss.xml'),
	         (u'兩岸要聞', u'http://udn.com/udnrss/mainland.xml'),
	         (u'國際焦點', u'http://udn.com/udnrss/international.xml'),
	         (u'台商經貿', u'http://udn.com/udnrss/financechina.xml'),
	         (u'國際財經', u'http://udn.com/udnrss/financeworld.xml'),
	         (u'全球觀察', u'http://mag.udn.com/udnrss/world_rss.xml'),
	         (u'財經焦點', u'http://udn.com/udnrss/financesfocus.xml'),
	         (u'股市要聞', u'http://udn.com/udnrss/stock.xml'),
	         (u'股市快訊', u'http://udn.com/udnrss/stklatest.xml'),
	         (u'稅務法務', u'http://udn.com/udnrss/tax.xml'),
	         (u'房市情報', u'http://udn.com/udnrss/houses.xml'),
	         (u'個人理財', u'http://mag.udn.com/udnrss/wealth_rss.xml'),
	         (u'研究報告', u'http://mag.udn.com/udnrss/report_rss.xml'),
	         (u'基金', u'http://mag.udn.com/udnrss/fund_rss.xml'),
	         (u'理財會客室', u'http://mag.udn.com/udnrss/m_forum_rss.xml'),
	         (u'棒球', u'http://udn.com/udnrss/baseball.xml'),
	         (u'籃球', u'http://udn.com/udnrss/basketball.xml'),
	         (u'體壇動態', u'http://udn.com/udnrss/sportsfocus.xml'),
	         (u'熱門星聞', u'http://udn.com/udnrss/starsfocus.xml'),
	         (u'廣電港陸', u'http://udn.com/udnrss/tv.xml'),
	         (u'海外星球', u'http://udn.com/udnrss/starswestern.xml'),
	         (u'日韓星情', u'http://udn.com/udnrss/starsjk.xml'),
	         (u'電影世界', u'http://udn.com/udnrss/movie.xml'),
	         (u'流行音樂', u'http://udn.com/udnrss/music.xml'),
	         (u'觀點專題', u'http://udn.com/udnrss/starssubject.xml'),
	         (u'消費流行', u'http://mag.udn.com/udnrss/happylife_rss.xml'),
	         (u'食樂指南', u'http://udn.com/udnrss/food.xml'),
	         (u'數位資訊', u'http://mag.udn.com/udnrss/digital_rss.xml'),
	         (u'折扣好康', u'http://udn.com/udnrss/shopping.xml'),
	         (u'發燒車訊', u'http://mag.udn.com/udnrss/car_rss.xml'),
	         (u'醫藥新聞', u'http://udn.com/udnrss/health.xml'),
	         (u'家婦繽紛', u'http://udn.com/udnrss/benfen.xml'),
	         (u'談星論命', u'http://udn.com/udnrss/astrology.xml'),
	         (u'文化副刊', u'http://udn.com/udnrss/reading.xml'),
	         (u'旅遊休閒', u'http://travel.udn.com/udnrss/travel_rss.xml'),
	         (u'健康醫藥', u'http://mag.udn.com/udnrss/life_rss.xml'),
	         ]
	         
	extra_css = '''div[id='story_title'] {font-size:200%; font-weight:bold;} td[class='story_title'] {font-size:200%; font-weight:bold;} td[class='story_title'] td[class='story_title']>div {font-size:200%; font-weight:bold;}'''
	
	__author__ = 'Eddie Lau'
	__version__ = '1.1'
	language = 'zh-TW'
	publisher = 'United Daily News Group'
	description = 'United Daily (Taiwan)'
	category = 'News, Chinese, Taiwan'
	remove_javascript = True
	use_embedded_content = False
	no_stylesheets = True
	encoding = 'big5'
	conversion_options = {'linearize_tables':True}
	masthead_url = 'http://udn.com/NEWS/2004/images/logo_udn.gif'
	cover_url = 'http://udn.com/NEWS/2004/images/logo_udn.gif'
	keep_only_tags = [dict(name='td', attrs={'class':['story_title']}),
	                  dict(name='div', attrs={'id':['story_title']}),
	                  dict(name='td', attrs={'class':['story_author']}),
	                  dict(name='div', attrs={'id':['story_author']}),
	                  dict(name='td', attrs={'class':['story']}),
	                  dict(name='div', attrs={'id':['story']}),
	                  ]
	remove_tags = [dict(name='div', attrs={'id':['mvouter']})]
tylau0 is offline   Reply With Quote