Updated Ming Pao and Various Taiwanese news sources by Eddie Lau

recipes/china_times.recipe

@@ -0,0 +1,42 @@
+# -*- coding: utf-8 -*-
+__license__   = 'GPL v3'
+# dug from http://www.mobileread.com/forums/showthread.php?p=1012294
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1277443634(BasicNewsRecipe):
+    title = u'中時電子報'
+    oldest_article = 1
+    max_articles_per_feed = 100
+
+    feeds = [(u'焦點', u'http://rss.chinatimes.com/rss/focus-u.rss'),
+             (u'政治', u'http://rss.chinatimes.com/rss/Politic-u.rss'),
+             (u'社會', u'http://rss.chinatimes.com/rss/social-u.rss'),
+             (u'國際', u'http://rss.chinatimes.com/rss/international-u.rss'),
+             (u'兩岸', u'http://rss.chinatimes.com/rss/mainland-u.rss'),
+             (u'地方', u'http://rss.chinatimes.com/rss/local-u.rss'),
+             (u'言論', u'http://rss.chinatimes.com/rss/comment-u.rss'),
+             (u'科技', u'http://rss.chinatimes.com/rss/technology-u.rss'),
+             (u'運動', u'http://rss.chinatimes.com/rss/sport-u.rss'),
+             (u'藝文', u'http://rss.chinatimes.com/rss/philology-u.rss'),
+             #(u'旺報', u'http://rss.chinatimes.com/rss/want-u.rss'),
+             #(u'財經', u'http://rss.chinatimes.com/rss/finance-u.rss'),  # broken links
+             #(u'股市', u'http://rss.chinatimes.com/rss/stock-u.rss')  # broken links
+             ]
+
+    __author__ = 'einstuerzende, updated by Eddie Lau'
+    __version__ = '1.0'
+    language = 'zh'
+    publisher = 'China Times Group'
+    description = 'China Times (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://www.fcuaa.org/gif/chinatimeslogo.gif'
+    cover_url = 'http://www.fcuaa.org/gif/chinatimeslogo.gif'
+    keep_only_tags = [dict(name='div', attrs={'class':['articlebox','articlebox clearfix']})]
+    remove_tags = [dict(name='div', attrs={'class':['focus-news']})]
+

recipes/liberty_times.recipe

@@ -0,0 +1,44 @@
+# -*- coding: utf-8 -*-
+__license__   = 'GPL v3'
+# dug from http://www.mobileread.com/forums/showthread.php?p=1012294
+
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1277443634(BasicNewsRecipe):
+	title = u'自由電子報'
+	oldest_article = 1
+	max_articles_per_feed = 100
+
+	feeds = [(u'焦點新聞', u'http://www.libertytimes.com.tw/rss/fo.xml'),
+                  (u'政治新聞', u'http://www.libertytimes.com.tw/rss/p.xml'),
+                  (u'生活新聞', u'http://www.libertytimes.com.tw/rss/life.xml'),
+                  (u'國際新聞', u'http://www.libertytimes.com.tw/rss/int.xml'),
+                  (u'自由廣場', u'http://www.libertytimes.com.tw/rss/o.xml'),
+                  (u'社會新聞', u'http://www.libertytimes.com.tw/rss/so.xml'),
+                  (u'體育新聞', u'http://www.libertytimes.com.tw/rss/sp.xml'),
+                  (u'財經焦點', u'http://www.libertytimes.com.tw/rss/e.xml'),
+                  (u'證券理財', u'http://www.libertytimes.com.tw/rss/stock.xml'),
+                  (u'影視焦點', u'http://www.libertytimes.com.tw/rss/show.xml'),
+                  (u'北部新聞', u'http://www.libertytimes.com.tw/rss/north.xml'),
+                  (u'中部新聞', u'http://www.libertytimes.com.tw/rss/center.xml'),
+                  (u'南部新聞', u'http://www.libertytimes.com.tw/rss/south.xml'),
+                  (u'大台北新聞', u'http://www.libertytimes.com.tw/rss/taipei.xml'),
+                  (u'藝術文化', u'http://www.libertytimes.com.tw/rss/art.xml'),
+                 ]
+	extra_css = '''span[class='insubject1'][id='newtitle'] {font-size:200%; font-weight:bold;}'''
+	__author__ = 'einstuerzende, updated by Eddie Lau'
+	__version__ = '1.1'
+	language = 'zh'
+	publisher = 'Liberty Times Group'
+	description = 'Liberty Times (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://www.libertytimes.com.tw/2008/images/img_auto/005/logo_new.gif'
+	cover_url = 'http://www.libertytimes.com.tw/2008/images/img_auto/005/logo_new.gif'
+	keep_only_tags = [dict(name='td', attrs={'id':['newsContent']})]
+

recipes/ming_pao.recipe

@@ -1,15 +1,18 @@
+# -*- coding: utf-8 -*-
 __license__   = 'GPL v3'
 __copyright__ = '2010-2011, Eddie Lau'
 
-# Users of Kindle 3 (with limited system-level CJK support)
+# Users of Kindle 3 with limited system-level CJK support
 # please replace the following "True" with "False".
 __MakePeriodical__ = True
-# Turn it to True if your device supports display of CJK titles
+# Turn below to true if your device supports display of CJK titles
 __UseChineseTitle__ = False
-
+# Trun below to true if you wish to use life.mingpao.com as the main article source
+__UseLife__ = True
 
 '''
 Change Log:
+2011/05/12: switch the main parse source to life.mingpao.com, which has more photos on the article pages
 2011/03/06: add new articles for finance section, also a new section "Columns"
 2011/02/28: rearrange the sections
             [Disabled until Kindle has better CJK support and can remember last (section,article) read in Sections & Articles
@@ -32,6 +35,7 @@ import os, datetime, re
 from calibre.web.feeds.recipes import BasicNewsRecipe
 from contextlib import nested
 
+
 from calibre.ebooks.BeautifulSoup import BeautifulSoup
 from calibre.ebooks.metadata.opf2 import OPFCreator
 from calibre.ebooks.metadata.toc import TOC
@@ -60,10 +64,11 @@ class MPHKRecipe(BasicNewsRecipe):
                       dict(name='font', attrs={'color':['AA0000']}), # for column articles title
                       dict(attrs={'id':['newscontent']}), # entertainment and column page content
                       dict(attrs={'id':['newscontent01','newscontent02']}),
-                      dict(attrs={'class':['photo']})
+                      dict(attrs={'class':['photo']}),
+                      dict(name='img', attrs={'width':['180'], 'alt':['按圖放大']}) # images for source from life.mingpao.com
                       ]
     remove_tags = [dict(name='style'),
-    			   dict(attrs={'id':['newscontent135']}),  # for the finance page
+                   dict(attrs={'id':['newscontent135']}),  # for the finance page from mpfinance.com
                    dict(name='table')]  # for content fetched from life.mingpao.com
     remove_attributes = ['width']
     preprocess_regexps = [
@@ -130,7 +135,9 @@ class MPHKRecipe(BasicNewsRecipe):
         return self.get_dtlocal().strftime("%Y-%m-%d")
 
     def get_fetchday(self):
+        # dt_utc = datetime.datetime.utcnow()
         # convert UTC to local hk time - at around HKT 6.00am, all news are available
+        # dt_local = dt_utc - datetime.timedelta(-2.0/24)
         return self.get_dtlocal().strftime("%d")
 
     def get_cover_url(self):
@@ -146,6 +153,28 @@ class MPHKRecipe(BasicNewsRecipe):
         feeds = []
         dateStr = self.get_fetchdate()
 
+        if __UseLife__:
+            for title, url, keystr in [(u'\u8981\u805e Headline', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalga', 'nal'),
+                                       (u'\u6e2f\u805e Local', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgb', 'nal'),
+                                       (u'\u6559\u80b2 Education', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgf', 'nal'),
+                                       (u'\u793e\u8a55/\u7b46\u9663 Editorial', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr', 'nal'),
+                                       (u'\u8ad6\u58c7 Forum', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalfa', 'nal'),
+                                       (u'\u4e2d\u570b China', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalca', 'nal'),
+                                       (u'\u570b\u969b World', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalta', 'nal'),
+                                       (u'\u7d93\u6fdf Finance', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea', 'nal'),
+                                       (u'\u9ad4\u80b2 Sport', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalsp', 'nal'),
+                                       (u'\u5f71\u8996 Film/TV', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalma', 'nal'),
+                                       (u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')]:
+                articles = self.parse_section2(url, keystr)
+                if articles:
+                    feeds.append((title, articles))
+
+            for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'),
+                               (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]:
+                articles = self.parse_section(url)
+                if articles:
+                    feeds.append((title, articles))
+        else:
             for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'),
                                (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'),
                                (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm')]:
@@ -196,6 +225,7 @@ class MPHKRecipe(BasicNewsRecipe):
 
         return feeds
 
+    # parse from news.mingpao.com
     def parse_section(self, url):
         dateStr = self.get_fetchdate()
         soup = self.index_to_soup(url)
@@ -214,6 +244,23 @@ class MPHKRecipe(BasicNewsRecipe):
         current_articles.reverse()
         return current_articles
 
+    # parse from life.mingpao.com
+    def parse_section2(self, url, keystr):
+        self.get_fetchdate()
+        soup = self.index_to_soup(url)
+        a = soup.findAll('a', href=True)
+        a.reverse()
+        current_articles = []
+        included_urls = []
+        for i in a:
+            title = self.tag_to_string(i)
+            url = 'http://life.mingpao.com/cfm/' + i.get('href', False)
+            if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind(keystr) == -1):
+                current_articles.append({'title': title, 'url': url, 'description': ''})
+                included_urls.append(url)
+        current_articles.reverse()
+        return current_articles
+
     def parse_ed_section(self, url):
         self.get_fetchdate()
         soup = self.index_to_soup(url)
@@ -426,3 +473,4 @@ class MPHKRecipe(BasicNewsRecipe):
 
         with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file):
             opf.render(opf_file, ncx_file)
+

recipes/united_daily.recipe

@@ -0,0 +1,67 @@
+# -*- coding: utf-8 -*-
+__license__   = 'GPL v3'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+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'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'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'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'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'食樂指南', u'http://udn.com/udnrss/food.xml'),
+             (u'折扣好康', u'http://udn.com/udnrss/shopping.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'),
+             ]
+
+    extra_css = '''div[id='story_title'] {font-size:200%; font-weight:bold;}'''
+
+    __author__ = 'Eddie Lau'
+    __version__ = '1.0'
+    language = 'zh'
+    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='div', attrs={'id':['story_title','story_author', 'story']})]
+    remove_tags = [dict(name='div', attrs={'id':['mvouter']})]