...

resources/recipes/ming_pao.recipe

@@ -1,7 +1,9 @@
-cense__   = 'GPL v3'
+__license__   = 'GPL v3'
 __copyright__ = '2010, Eddie Lau'
 '''
 modified from Singtao Toronto calibre recipe by rty
+Change Log:
+2010/10/31: skip repeated articles in section pages
 '''
 
 import datetime
@@ -23,14 +25,13 @@ class AdvancedUserRecipe1278063072(BasicNewsRecipe):
     recursions = 0
     conversion_options = {'linearize_tables':True}
     masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif'
-
     keep_only_tags = [dict(name='h1'),
                       dict(attrs={'id':['newscontent01','newscontent02']})]
 
     def get_fetchdate(self):
         dt_utc = datetime.datetime.utcnow()
-        # convert UTC to local hk time
-        dt_local = dt_utc - datetime.timedelta(-8.0/24)
+        # convert UTC to local hk time - at around HKT 5.30am, all news are available
+        dt_local = dt_utc - datetime.timedelta(-2.5/24)
         return dt_local.strftime("%Y%m%d")
 
     def parse_index(self):
@@ -47,18 +48,14 @@ class AdvancedUserRecipe1278063072(BasicNewsRecipe):
         soup = self.index_to_soup(url)
         divs = soup.findAll(attrs={'class': ['bullet']})
         current_articles = []
+        included_urls = []
         for i in divs:
             a = i.find('a', href = True)
             title = self.tag_to_string(a)
             url = a.get('href', False)
             url = 'http://news.mingpao.com/' + dateStr + '/' +url
+            if url not in included_urls:
                 current_articles.append({'title': title, 'url': url, 'description':''})
+                included_urls.append(url)
         return current_articles
 
-    def preprocess_html(self, soup):
-        for item in soup.findAll(style=True):
-           del item['style']
-        for item in soup.findAll(width=True):
-           del item['width']
-        return soup
-