Oriental Daily by Larry Chan

2025-07-09 03:04:10 -04:00 · 2010-09-30 09:43:53 -06:00 · 2010-09-30 09:43:53 -06:00 · 75d55a38a0
commit 75d55a38a0
parent 9ddd785824
1 changed files with 50 additions and 0 deletions
--- a/resources/recipes/oriental_daily.recipe
+++ b/resources/recipes/oriental_daily.recipe
@ -0,0 +1,50 @@
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, Larry Chan <larry1chan at gmail.com>'
+'''
+oriental daily
+'''
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class OrientalDaily(BasicNewsRecipe):
+    title                  = 'Oriental Dailly'
+    __author__             = 'Larry Chan'
+    description            = 'News from HK'
+    oldest_article         = 2
+    max_articles_per_feed  = 100
+    simultaneous_downloads = 5
+    no_stylesheets         = True
+    #delay                  = 1
+    use_embedded_content   = False
+    encoding               = 'utf8'
+    publisher              = 'Oriental Daily'
+    category               = 'news, HK, world'
+    language               = 'zh'
+    publication_type       = 'newsportal'
+    extra_css              = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif } .introduction{font-weight: bold} .story-feature{display: block; padding: 0; border: 1px solid; width: 40%; font-size: small} .story-feature h2{text-align: center; text-transform: uppercase} '
+
+    conversion_options = {
+                             'comments'        : description
+                            ,'tags'            : category
+                            ,'language'        : language
+                            ,'publisher'       : publisher
+                            ,'linearize_tables': True
+                         }
+
+    remove_tags_after  = dict(id='bottomNavCTN')
+
+    keep_only_tags    = [
+                       dict(name='div', attrs={'id':['leadin', 'contentCTN-right']})
+
+                        ]
+
+    remove_tags = [
+                       dict(name='div', attrs={'class':['largeAdsCTN', 'contentCTN-left', 'textAdsCTN', 'footerAds clear']}),
+                       dict(name='div', attrs={'id':['articleNav']})
+
+                        ]
+
+    remove_attributes = ['width','height','href']
+
+
+    feeds          = [(u'Oriental Daily', u'http://orientaldaily.on.cc/rss/news.xml')]