Merge from trunk

recipes/dobanevinosti.recipe

@@ -0,0 +1,46 @@
+
+__license__   = 'GPL v3'
+__copyright__ = '2013, Darko Miletic <darko.miletic at gmail.com>'
+'''
+dobanevinosti.blogspot.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class DobaNevinosti(BasicNewsRecipe):
+    title                 = 'Doba Nevinosti'
+    __author__            = 'Darko Miletic'
+    description           = 'Filmski blog'
+    oldest_article        = 15
+    max_articles_per_feed = 100
+    language              = 'sr'
+    encoding              = 'utf-8'
+    no_stylesheets        = True
+    use_embedded_content  = True
+    publication_type      = 'blog'
+    auto_cleanup          = True
+    extra_css             = """
+                               @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
+                               body{font-family: "Trebuchet MS",Trebuchet,Verdana,sans1,sans-serif}
+                               img{margin-bottom: 0.8em; display:block;}
+                            """
+
+    conversion_options = {
+                          'comment'  : description
+                        , 'tags'     : 'film, blog, srbija, tv'
+                        , 'publisher': 'Dimitrije Vojinov'
+                        , 'language' : language
+                        }
+    remove_attributes = ['lang', 'border']
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+
+    feeds = [(u'Tekstovi', u'http://dobanevinosti.blogspot.com/feeds/posts/default')]
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll('img'):
+            if not item.has_key('alt'):
+               item['alt'] = 'image'
+        return soup
+

recipes/scmp.recipe

@@ -4,7 +4,6 @@ __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
 scmp.com
 '''
 
-import re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class SCMP(BasicNewsRecipe):
@@ -18,10 +17,11 @@ class SCMP(BasicNewsRecipe):
     max_articles_per_feed = 200
     no_stylesheets        = True
     encoding              = 'utf-8'
+    auto_cleanup = True
     use_embedded_content  = False
     language              = 'en_CN'
     remove_empty_feeds    = True
-    needs_subscription    = True
+    needs_subscription    = 'optional'
     publication_type      = 'newspaper'
     masthead_url          = 'http://www.scmp.com/images/logo_scmp_home.gif'
     extra_css             = ' body{font-family: Arial,Helvetica,sans-serif } '
@@ -46,17 +46,17 @@ class SCMP(BasicNewsRecipe):
            br.submit()
         return br
 
-    remove_attributes=['width','height','border']
+    #remove_attributes=['width','height','border']
 
-    keep_only_tags = [
+    #keep_only_tags = [
-                        dict(attrs={'id':['ART','photoBox']})
+                        #dict(attrs={'id':['ART','photoBox']})
-                       ,dict(attrs={'class':['article_label','article_byline','article_body']})
+                       #,dict(attrs={'class':['article_label','article_byline','article_body']})
-                     ]
+                     #]
 
-    preprocess_regexps = [
+    #preprocess_regexps = [
-       (re.compile(r'<P><table((?!<table).)*class="embscreen"((?!</table>).)*</table>', re.DOTALL|re.IGNORECASE),
+       #(re.compile(r'<P><table((?!<table).)*class="embscreen"((?!</table>).)*</table>', re.DOTALL|re.IGNORECASE),
-        lambda match: ''),
+        #lambda match: ''),
-    ]
+    #]
 
     feeds = [
               (u'Business'     , u'http://www.scmp.com/rss/business.xml'       )
@@ -68,13 +68,13 @@ class SCMP(BasicNewsRecipe):
              ,(u'Sport'        , u'http://www.scmp.com/rss/sport.xml'          )
             ]
 
-    def print_version(self, url):
+    #def print_version(self, url):
-        rpart, sep, rest = url.rpartition('&')
+        #rpart, sep, rest = url.rpartition('&')
-        return rpart #+ sep + urllib.quote_plus(rest)
+        #return rpart #+ sep + urllib.quote_plus(rest)
 
-    def preprocess_html(self, soup):
+    #def preprocess_html(self, soup):
-        for item in soup.findAll(style=True):
+        #for item in soup.findAll(style=True):
-            del item['style']
+            #del item['style']
-        items = soup.findAll(src="/images/label_icon.gif")
+        #items = soup.findAll(src="/images/label_icon.gif")
-        [item.extract() for item in items]
+        #[item.extract() for item in items]
-        return self.adeify_images(soup)
+        #return self.adeify_images(soup)

src/calibre/web/feeds/news.py

@@ -422,7 +422,7 @@ class BasicNewsRecipe(Recipe):
         Times recipe to login for full access::
 
             def get_browser(self):
-                br = BasicNewsRecipe.get_browser()
+                br = BasicNewsRecipe.get_browser(self)
                 if self.username is not None and self.password is not None:
                     br.open('http://www.nytimes.com/auth/login')
                     br.select_form(name='login')