Implement #2173 (New recipes)

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

@@ -37,6 +37,7 @@ recipe_modules = ['recipe_' + r for r in (
            'new_york_review_of_books_no_sub', 'politico', 'adventuregamers',
            'mondedurable', 'instapaper', 'dnevnik_cro', 'vecernji_list',
            'nacional_cro', '24sata', 'dnevni_avaz', 'glas_srpske', '24sata_rs',
+           'krstarica', 'krstarica_en', 'tanjug',
           )]
 
 import re, imp, inspect, time, os

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

@@ -0,0 +1,65 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+vesti.krstarica.com
+'''
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Krstarica(BasicNewsRecipe):
+    title                 = 'Krstarica - Vesti'
+    __author__            = 'Darko Miletic'
+    description           = 'Dnevne vesti iz Srbije i sveta'    
+    publisher             = 'Krstarica'
+    category              = 'news, politics, Serbia'
+    oldest_article        = 1
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    remove_javascript     = True
+    encoding              = 'utf-8'
+    language              = _('Serbian')
+    extra_css             = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: serif1, serif}'
+    
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0em; margin-top: 0em; margin-bottom: 0.5em}"' 
+    
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+    
+    feeds          = [
+                        (u'Vesti dana'         , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=aktuelno&lang=0'     )
+                       ,(u'Srbija'             , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=scg&lang=0'          )
+                       ,(u'Svet'               , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=svet&lang=0'         )
+                       ,(u'Politika'           , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=politika&lang=0'     )
+                       ,(u'Ekonomija'          , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=ekonomija&lang=0'    )
+                       ,(u'Drustvo'            , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=drustvo&lang=0'      )
+                       ,(u'Kultura'            , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=kultura&lang=0'      )
+                       ,(u'Nauka i Tehnologija', u'http://vesti.krstarica.com/index.php?rss=1&rubrika=nauka&lang=0'        )
+                       ,(u'Medicina'           , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=medicina&lang=0'     )
+                       ,(u'Sport'              , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=sport&lang=0'        )
+                       ,(u'Zanimljivosti'      , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=zanimljivosti&lang=0')
+                     ]
+
+    def preprocess_html(self, soup):
+        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>'
+        soup.head.insert(0,mtag)
+        titletag = soup.find('h4')
+        if titletag:
+           realtag = titletag.parent.parent
+           realtag.extract()
+           for item in soup.findAll(['table','center']):
+               item.extract()
+           soup.body.insert(1,realtag)            
+           realtag.name = 'div'
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll(align=True):
+            del item['align']
+        return soup

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

@@ -0,0 +1,57 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+vesti.krstarica.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Krstarica_en(BasicNewsRecipe):
+    title                 = 'Krstarica - news in english'
+    __author__            = 'Darko Miletic'
+    description           = 'News from Serbia and world'    
+    publisher             = 'Krstarica'
+    category              = 'news, politics, Serbia'
+    oldest_article        = 1
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    remove_javascript     = True
+    encoding              = 'utf-8'
+    language              = _('English')
+    
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0em; margin-top: 0em; margin-bottom: 0.5em}"' 
+        
+    feeds          = [
+                        (u'Daily news', u'http://vesti.krstarica.com/index.php?rss=1&rubrika=aktuelno&lang=1'     )
+                       ,(u'Serbia'    , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=scg&lang=1'          )
+                       ,(u'Politics'  , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=politika&lang=1'     )
+                       ,(u'Economy'   , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=ekonomija&lang=1'    )
+                       ,(u'Culture'   , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=kultura&lang=1'      )
+                       ,(u'Sports'    , u'http://vesti.krstarica.com/index.php?rss=1&rubrika=sport&lang=1'        )
+                     ]
+
+    def preprocess_html(self, soup):
+        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>'
+        soup.head.insert(0,mtag)
+        titletag = soup.find('h4')
+        if titletag:
+           realtag = titletag.parent.parent
+           realtag.extract()
+           for item in soup.findAll(['table','center']):
+               item.extract()
+           soup.body.insert(1,realtag)            
+           realtag.name = 'div'
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll(align=True):
+            del item['align']
+        return soup

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

@@ -0,0 +1,43 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+tanjug.rs
+'''
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Tanjug(BasicNewsRecipe):
+    title                 = 'Tanjug'
+    __author__            = 'Darko Miletic'
+    description           = 'Novinska agencija TANJUG - Dnevne vesti iz Srbije i sveta'
+    publisher             = 'Tanjug'
+    category              = 'news, politics, Serbia'
+    oldest_article        = 1
+    max_articles_per_feed = 100
+    use_embedded_content  = True
+    encoding              = 'utf-8'
+    lang                  = 'sr-Latn-RS'
+    language              = _('Serbian')
+    extra_css             = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: serif1, serif}'
+    
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0em; margin-top: 0em; margin-bottom: 0.5em}"' 
+    
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+    
+    feeds          = [(u'Vesti', u'http://www.tanjug.rs/StaticPages/RssTanjug.aspx')]
+
+    def preprocess_html(self, soup):
+        soup.html['xml:lang'] = self.lang
+        soup.html['lang'    ] = self.lang
+        soup.html['dir'     ] = "ltr"
+        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>'
+        soup.head.insert(0,mtag)
+        return soup