Updated serbian and croation recipes

src/calibre/web/feeds/recipes/b92.py

@@ -5,7 +5,7 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
 '''
 b92.net
 '''
-import locale
+import string,re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class B92(BasicNewsRecipe):
@@ -16,6 +16,8 @@ class B92(BasicNewsRecipe):
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
+    
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
 
     remove_tags_after  = dict(name='div', attrs={'class':'gas'})
     remove_tags = [

src/calibre/web/feeds/recipes/blic.py

@@ -5,7 +5,7 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
 '''
 blic.rs
 '''
-import locale
+import string,re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Blic(BasicNewsRecipe):
@@ -18,6 +18,8 @@ class Blic(BasicNewsRecipe):
     use_embedded_content  = False
     timefmt               = ' [%A, %d %B, %Y]' 
 
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+
     keep_only_tags = [ dict(name='div', attrs={'class':'single_news'}) ]
 
     feeds          = [ (u'Vesti', u'http://www.blic.rs/rssall.php')]

src/calibre/web/feeds/recipes/danas.py

@@ -5,7 +5,7 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
 '''
 danas.rs
 '''
-import locale
+import string,re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Danas(BasicNewsRecipe):
@@ -14,10 +14,12 @@ class Danas(BasicNewsRecipe):
     description           = 'Vesti'    
     oldest_article        = 7
     max_articles_per_feed = 100
-    no_stylesheets        = False
+    no_stylesheets        = True
     use_embedded_content  = False
     timefmt               = ' [%A, %d %B, %Y]' 
 
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+
     keep_only_tags     = [ dict(name='div', attrs={'id':'left'}) ]
     remove_tags_after  = dict(name='div', attrs={'id':'comments'})
     remove_tags = [
@@ -30,6 +32,3 @@ class Danas(BasicNewsRecipe):
 
 
     feeds          = [ (u'Vesti', u'http://www.danas.rs/rss/rss.asp')]
-
-#    def print_version(self, url):
-#        return url + '&action=print'

src/calibre/web/feeds/recipes/jutarnji.py

@@ -1,42 +1,46 @@
-#!/usr/bin/env  python
-
-__license__   = 'GPL v3'
-__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
-'''
-jutarnji.hr
-'''
-
-from calibre.web.feeds.news import BasicNewsRecipe
-
-class Jutarnji(BasicNewsRecipe):
-    title                 = u'Jutarnji'
-    __author__            = u'Darko Miletic'
-    description           = u'Hrvatski portal'
-    oldest_article        = 7
-    max_articles_per_feed = 100
-    no_stylesheets        = True
-    use_embedded_content  = False
-    encoding              = 'cp1250'
-
-    remove_tags = [dict(name='embed')]
-    
-    feeds = [
-              (u'Naslovnica'      , u'http://www.jutarnji.hr/rss'           )
-             ,(u'Sport'           , u'http://www.jutarnji.hr/sport/rss'     )
-             ,(u'Jutarnji2'       , u'http://www.jutarnji.hr/j2/rss'        )
-             ,(u'Kultura'         , u'http://www.jutarnji.hr/kultura/rss'   )
-             ,(u'Spektakli'       , u'http://www.jutarnji.hr/spektakli/rss' )
-             ,(u'Dom i nekretnine', u'http://www.jutarnji.hr/nekretnine/rss')
-             ,(u'Uhvati ritam'    , u'http://www.jutarnji.hr/kalendar/rss'  )
-            ]
-
-    def print_version(self, url):
-        main = url.partition('.jl')[0]
-        rrest = main.rpartition(',')[-1]
-        return 'http://www.jutarnji.hr/ispis_clanka.jl?artid=' + rrest
-
-    def preprocess_html(self, soup):
-        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8">'
-        soup.head.insert(0,mtag)
-        return soup
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+'''
+jutarnji.hr
+'''
+
+import string, re
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup
+
+class Jutarnji(BasicNewsRecipe):
+    title                 = u'Jutarnji'
+    __author__            = u'Darko Miletic'
+    description           = u'Hrvatski portal'
+    oldest_article        = 7
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'cp1250'
+
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+    
+    remove_tags = [dict(name='embed')]
+    
+    feeds = [
+              (u'Naslovnica'      , u'http://www.jutarnji.hr/rss'           )
+             ,(u'Sport'           , u'http://www.jutarnji.hr/sport/rss'     )
+             ,(u'Jutarnji2'       , u'http://www.jutarnji.hr/j2/rss'        )
+             ,(u'Kultura'         , u'http://www.jutarnji.hr/kultura/rss'   )
+             ,(u'Spektakli'       , u'http://www.jutarnji.hr/spektakli/rss' )
+             ,(u'Dom i nekretnine', u'http://www.jutarnji.hr/nekretnine/rss')
+             ,(u'Uhvati ritam'    , u'http://www.jutarnji.hr/kalendar/rss'  )
+            ]
+
+    def print_version(self, url):
+        main, split, rest = url.partition('.jl')
+        rmain, rsplit, rrest = main.rpartition(',')
+        return 'http://www.jutarnji.hr/ispis_clanka.jl?artid=' + rrest
+
+    def preprocess_html(self, soup):
+        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8">'
+        soup.head.insert(0,mtag)
+        return soup
         

src/calibre/web/feeds/recipes/novosti.py

@@ -5,7 +5,7 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
 '''
 novosti.rs
 '''
-import locale
+import string,re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Novosti(BasicNewsRecipe):
@@ -18,6 +18,8 @@ class Novosti(BasicNewsRecipe):
     use_embedded_content  = False
     timefmt               = ' [%A, %d %B, %Y]' 
 
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+
     keep_only_tags     = [ dict(name='div', attrs={'class':'jednaVest'}) ]
     remove_tags_after  = dict(name='div', attrs={'class':'info_bottom'})
     remove_tags = [

src/calibre/web/feeds/recipes/nspm.py

@@ -0,0 +1,33 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+'''
+nspm.rs
+'''
+
+import string,re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Nspm(BasicNewsRecipe):
+    title                 = u'Nova srpska politicka misao'
+    __author__            = 'Darko Miletic'
+    description           = 'Casopis za politicku teoriju i drustvena istrazivanja'    
+    oldest_article        = 7
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    INDEX                 = 'http://www.nspm.rs/?alphabet=l'
+    timefmt               = ' [%A, %d %B, %Y]' 
+
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        br.open(self.INDEX)
+        return br
+
+    feeds = [ (u'Nova srpska politicka misao', u'http://www.nspm.rs/feed/rss.html')]
+
+    def print_version(self, url):
+        return url.replace('.html','/stampa.html')

src/calibre/web/feeds/recipes/politika.py

@@ -5,7 +5,7 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
 '''
 politika.rs
 '''
-import locale
+import string,re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Politika(BasicNewsRecipe):
@@ -18,6 +18,9 @@ class Politika(BasicNewsRecipe):
     extra_css             = '.content_center_border {text-align: left;}' 
     use_embedded_content  = False
     timefmt               = ' [%A, %d %B, %Y]' 
+
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+
     remove_tags_before = dict(name='div', attrs={'class':'content_center_border'})
     remove_tags_after  = dict(name='div', attrs={'class':'datum_item_details'})
 

src/calibre/web/feeds/recipes/vreme.py

@@ -6,8 +6,7 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
 vreme.com
 '''
 
-import string
-import locale
+import string,re
 from calibre import strftime
 from calibre.web.feeds.recipes import BasicNewsRecipe
 
@@ -24,6 +23,8 @@ class Vreme(BasicNewsRecipe):
     INDEX = 'http://www.vreme.com'
     LOGIN = 'http://www.vreme.com/account/index.php'
 
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+
     def get_browser(self):
         br = BasicNewsRecipe.get_browser()
         if self.username is not None and self.password is not None:
@@ -39,16 +40,29 @@ class Vreme(BasicNewsRecipe):
         soup = self.index_to_soup(self.INDEX)
         
         for item in soup.findAll('span', attrs={'class':'toc2'}):
+            description = ''
+            title_prefix = ''
+
+            descript_title_tag = item.findPreviousSibling('span', attrs={'class':'toc1'})
+            if descript_title_tag:
+               title_prefix = self.tag_to_string(descript_title_tag) + ' '
+
+            descript_tag = item.findNextSibling('span', attrs={'class':'toc3'})
+            if descript_tag:
+               description = self.tag_to_string(descript_tag)
+               
             feed_link = item.find('a')
             if feed_link and feed_link.has_key('href'):
-                url = self.INDEX+feed_link['href']+'&print=yes'
-                title = self.tag_to_string(feed_link)
-                date = strftime('%A, %d %B, %Y')
-                description = ''
+                url   = self.INDEX + feed_link['href']
+                title = title_prefix + self.tag_to_string(feed_link)
+                date  = strftime(self.timefmt)                
                 articles.append({
-                                 'title':title,
-                                 'date':date,
-                                 'url':url,
-                                 'description':description
+                                  'title'      :title
+                                 ,'date'       :date
+                                 ,'url'        :url
+                                 ,'description':description
                                 })
         return [(soup.head.title.string, articles)]
+        
+    def print_version(self, url):
+        return url + '&print=yes'