Added recipes: NSPM, NSPM in english, The market ticker, Tom's Hardware, Spiegel international (in english), Pescanik

Updated recipes: Vreme, B92, Politika, Novosti, jutarnji, la nacion, Clarin, Blic, Danas

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

@@ -19,7 +19,8 @@ recipe_modules = [
            'clarin', 'financial_times', 'heise', 'le_monde', 'harpers', 'science_aas',
            'science_news', 'the_nation', 'lrb', 'harpers_full', 'liberation',
            'linux_magazine', 'telegraph_uk', 'utne', 'sciencedaily', 'forbes',
-           'time_magazine', 'endgadget', 'fudzilla',
+           'time_magazine', 'endgadget', 'fudzilla', 'nspm_int', 'nspm', 'pescanik',
+           'spiegel_int', 'themarketticker', 'tomshardware',
           ]
 
 import re, imp, inspect, time, os

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

@@ -5,6 +5,7 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
 '''
 b92.net
 '''
+
 import string,re
 from calibre.web.feeds.news import BasicNewsRecipe
 
@@ -16,25 +17,29 @@ class B92(BasicNewsRecipe):
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
-    
+    cover_url = 'http://static.b92.net/images/fp/logo.gif'
-    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+    keep_only_tags = [ dict(name='div', attrs={'class':'sama_vest'}) ]
-
+    html2lrf_options = [
-    remove_tags_after  = dict(name='div', attrs={'class':'gas'})
+                          '--comment', description
-    remove_tags = [
+                        , '--base-font-size', '10'
-                     dict(name='div'  , attrs={'class':'interaction clearfix' })
+                        , '--category', 'news, Serbia'
-                    ,dict(name='div'  , attrs={'class':'gas'                  })
+                        , '--publisher', 'B92'
-                    ,dict(name='ul'   , attrs={'class':'comment-nav'          })
-                    ,dict(name='table', attrs={'class':'pages-navigation-form'})
                         ]
-
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
     feeds          = [
                         (u'Vesti', u'http://www.b92.net/info/rss/vesti.xml')
-                       ,(u'Kultura'   , u'http://www.b92.net/info/rss/kultura.xml'   )                      
-                       ,(u'Automobili', u'http://www.b92.net/info/rss/automobili.xml')                      
-                       ,(u'Zivot'     , u'http://www.b92.net/info/rss/zivot.xml'     )
-                       ,(u'Tehnopolis', u'http://www.b92.net/info/rss/tehnopolis.xml')
                        ,(u'Biz'  , u'http://www.b92.net/info/rss/biz.xml'  )
+                       ,(u'Zivot', u'http://www.b92.net/info/rss/zivot.xml')
+                       ,(u'Sport', u'http://www.b92.net/info/rss/sport.xml')
                      ]
 
     def print_version(self, url):
-        return url + '&version=print'
+        main, sep, article_id = url.partition('nav_id=')
+        rmain, rsep, rrest = main.partition('.php?')
+        mrmain , rsepp, nnt = rmain.rpartition('/')
+        mprmain, rrsep, news_type = mrmain.rpartition('/')
+        nurl = 'http://www.b92.net/mobilni/' + news_type + '/index.php?nav_id=' + article_id
+        brbiz, biz, bizrest = rmain.partition('/biz/')
+        if biz:
+            nurl = 'http://www.b92.net/mobilni/biz/index.php?nav_id=' + article_id
+        return nurl

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

@@ -11,12 +11,18 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class Blic(BasicNewsRecipe):
     title                 = u'Blic'
     __author__            = 'Darko Miletic'
-    description           = 'Vesti'    
+    description           = 'Blic.rs online verzija najtiraznije novine u Srbiji donosi najnovije vesti iz Srbije i sveta, komentare, politicke analize, poslovne i ekonomske vesti, vesti iz regiona, intervjue, informacije iz kulture, reportaze, pokriva sve sportske dogadjaje, detaljan tv program, nagradne igre, zabavu, fenomenalni Blic strip, dnevni horoskop, arhivu svih dogadjaja'
     oldest_article        = 7
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
-    timefmt               = ' [%A, %d %B, %Y]' 
+    cover_url = 'http://www.blic.rs/resources/images/header_back_tile.png'
+    html2lrf_options = [
+                          '--comment', description
+                        , '--base-font-size', '10'
+                        , '--category', 'news, Serbia'
+                        , '--publisher', 'Blic'
+                        ]
 
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
 

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

@@ -9,14 +9,19 @@ clarin.com
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Clarin(BasicNewsRecipe):
-    title                 = u'Clarin'
+    title                 = 'Clarin'
     __author__            = 'Darko Miletic'
     description           = 'Noticias de Argentina y mundo'
     oldest_article        = 2
     max_articles_per_feed = 100
     use_embedded_content  = False
-    simultaneous_downloads = 1
+    cover_url = 'http://www.clarin.com/shared/v10/img/Hd/lg_Clarin.gif'
-    delay = 1
+    html2lrf_options = [
+                          '--comment', description
+                        , '--base-font-size', '10'
+                        , '--category', 'news, Argentina'
+                        , '--publisher', 'Grupo Clarin'
+                        ]
     
     remove_tags = [
                      dict(name='a'   , attrs={'class':'Imp'   })

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

@@ -9,26 +9,33 @@ import string,re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Danas(BasicNewsRecipe):
-    title                 = u'Danas'
+    title                 = 'Danas'
     __author__            = 'Darko Miletic'
-    description           = 'Vesti'    
+    description           = 'Dnevne novine sa vestima iz sveta, politike, ekonomije, kulture, sporta, Beograda, Novog Sada i cele Srbije.'    
-    oldest_article        = 7
+    oldest_article        = 2
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
-    timefmt               = ' [%A, %d %B, %Y]' 
+    cover_url = 'http://www.danas.rs/images/basic/danas.gif'
+    html2lrf_options = [
+                          '--comment', description
+                        , '--base-font-size', '10'
+                        , '--category', 'news, Serbia'
+                        , '--publisher', 'Danas'
+                        ]
 
     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 = [
                      dict(name='div', attrs={'class':'width_1_4'  })
                     ,dict(name='div', attrs={'class':'metaClanka' })
                     ,dict(name='div', attrs={'id':'comments'      })
                     ,dict(name='div', attrs={'class':'baner'      })
+                    ,dict(name='div', attrs={'class':'slikaClanka'})                    
                   ]
 
-
-
     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

@@ -11,18 +11,30 @@ from calibre.web.feeds.news import BasicNewsRecipe
 from calibre.ebooks.BeautifulSoup import BeautifulSoup
 
 class Jutarnji(BasicNewsRecipe):
-    title                 = u'Jutarnji'
+    title                 = 'Jutarnji'
-    __author__            = u'Darko Miletic'
+    __author__            = 'Darko Miletic'
-    description           = u'Hrvatski portal'
+    description           = 'Online izdanje Jutarnjeg lista'
-    oldest_article        = 7
+    oldest_article        = 2
     max_articles_per_feed = 100
+    simultaneous_downloads = 1
+    delay = 1    
     no_stylesheets        = True
     use_embedded_content  = False
     encoding              = 'cp1250'
-
+    cover_url = 'http://www.jutarnji.hr/EPHResources/Images/2008/06/05/jhrlogo.png'
+    html2lrf_options = [
+                          '--comment', description
+                        , '--base-font-size', '10'
+                        , '--category', 'news, Croatia'
+                        , '--publisher', 'Europapress holding d.o.o.'
+                        ]    
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
     
-    remove_tags = [dict(name='embed')]
+    remove_tags = [ 
+                    dict(name='embed')
+                   ,dict(name='a', attrs={'class':'a11'})
+                   ,dict(name='hr')
+                  ]
     
     feeds = [
               (u'Naslovnica'      , u'http://www.jutarnji.hr/rss'           )
@@ -37,10 +49,11 @@ class Jutarnji(BasicNewsRecipe):
     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
+        return u'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)
+        soup.prettify()
         return soup
         

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

@@ -9,14 +9,21 @@ lanacion.com.ar
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Lanacion(BasicNewsRecipe):
-    title                 = u'La Nacion'
+    title                 = 'La Nacion'
     __author__            = 'Darko Miletic'
-    description           = 'Noticias de Argentina y el resto del mundo'    
+    description           = 'Informacion actualizada las 24 horas, con noticias de Argentina y del mundo - Informate ya!'    
-    oldest_article        = 7
+    oldest_article        = 2
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
     
+    html2lrf_options = [
+                          '--comment', description
+                        , '--base-font-size', '10'
+                        , '--category', 'news, Argentina'
+                        , '--publisher', 'La Nacion SA'
+                        ]    
+
     keep_only_tags = [dict(name='div', attrs={'class':'nota floatFix'})]
     remove_tags = [
                      dict(name='div' , attrs={'class':'notaComentario floatFix noprint' })
@@ -38,3 +45,12 @@ class Lanacion(BasicNewsRecipe):
                         ,(u'Ciencia/Salud'        , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=498' )
                         ,(u'Revista'              , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=494' )
                      ]
+
+    def get_cover_url(self):
+        index = 'http://www.lanacion.com.ar'
+        cover_url = None
+        soup = self.index_to_soup(index)
+        cover_item = soup.find('img',attrs={'class':'logo'})
+        if cover_item:
+           cover_url = index + cover_item['src']
+        return cover_url

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

@@ -9,14 +9,19 @@ import string,re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Novosti(BasicNewsRecipe):
-    title                 = u'Vecernje Novosti'
+    title                 = 'Vecernje Novosti'
-    __author__            = u'Darko Miletic'
+    __author__            = 'Darko Miletic'
-    description           = u'Vesti'
+    description           = 'novosti, vesti, politika, dosije, drustvo, ekonomija, hronika, reportaze, svet, kultura, sport, beograd, regioni, mozaik, feljton, intrvju, pjer, fudbal, kosarka, podvig, arhiva, komentari, kolumne, srbija, republika srpska,Vecernje novosti'
-    oldest_article        = 7
+    oldest_article        = 2
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
-    timefmt               = ' [%A, %d %B, %Y]' 
+    html2lrf_options = [
+                          '--comment', description
+                        , '--base-font-size', '10'
+                        , '--category', 'news, Serbia'
+                        , '--publisher', 'Novosti AD'
+                        ]
 
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
 

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

@@ -18,7 +18,13 @@ class Nspm(BasicNewsRecipe):
     no_stylesheets        = True
     use_embedded_content  = False
     INDEX                 = 'http://www.nspm.rs/?alphabet=l'
-    timefmt               = ' [%A, %d %B, %Y]' 
+    cover_url = 'http://nspm.rs/templates/jsn_epic_pro/images/logol.jpg'
+    html2lrf_options = [
+                          '--comment', description
+                        , '--base-font-size', '10'
+                        , '--category', 'news, politics, Serbia'
+                        , '--publisher', 'IIC NSPM'
+                        ]
 
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
 

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

@@ -0,0 +1,37 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+'''
+nspm.rs/nspm-in-english
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Nspm_int(BasicNewsRecipe):
+    title                 = 'NSPM in English'
+    __author__            = 'Darko Miletic'
+    description           = 'Magazine dedicated to political theory and sociological research'        
+    oldest_article        = 20
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    INDEX                 = 'http://www.nspm.rs/?alphabet=l'
+    cover_url = 'http://nspm.rs/templates/jsn_epic_pro/images/logol.jpg'
+    html2lrf_options = [
+                          '--comment', description
+                        , '--base-font-size', '10'
+                        , '--category', 'news, politics, Serbia, english'
+                        , '--publisher', 'IIC NSPM'
+                        ]
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        br.open(self.INDEX)
+        return br
+
+
+    keep_only_tags = [dict(name='div', attrs={'id':'jsn-mainbody'})]
+    remove_tags    = [dict(name='div', attrs={'id':'yvComment'   })]
+
+    feeds = [ (u'NSPM in English', u'http://nspm.rs/nspm-in-english/feed/rss.html')]

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

@@ -0,0 +1,35 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+'''
+pescanik.net
+'''
+
+import string,re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Pescanik(BasicNewsRecipe):
+    title                 = 'Pescanik'
+    __author__            = 'Darko Miletic'
+    description           = 'Pescanik'
+    oldest_article        = 7
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    html2lrf_options = ['--base-font-size', '10']
+    html2epub_options = 'base_font_size = "10pt"'
+    
+    cover_url = "http://pescanik.net/templates/ja_teline/images/logo.png"
+    
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+    
+    remove_tags_after = dict(name='div', attrs={'class':'article_seperator'})
+    
+    remove_tags = [dict(name='td'  , attrs={'class':'buttonheading'})]
+
+    feeds       = [(u'Pescanik Online', u'http://pescanik.net/index.php?option=com_rd_rss&id=12')]
+
+    def print_version(self, url):
+        nurl = url.replace('http://pescanik.net/index.php','http://pescanik.net/index2.php')        
+        return nurl + '&pop=1&page=0'

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

@@ -9,25 +9,30 @@ import string,re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Politika(BasicNewsRecipe):
-    title                 = u'Politika Online'
+    title                 = 'Politika Online'
     __author__            = 'Darko Miletic'
     description           = 'Najstariji dnevni list na Balkanu'    
-    oldest_article        = 7
+    oldest_article        = 2
     max_articles_per_feed = 100
     no_stylesheets        = True
     extra_css             = '.content_center_border {text-align: left;}' 
     use_embedded_content  = False
-    timefmt               = ' [%A, %d %B, %Y]' 
+    cover_url = 'http://www.politika.rs:8080/images/politika.gif'
+    html2lrf_options = [
+                          '--comment', description
+                        , '--base-font-size', '10'
+                        , '--category', 'news, Serbia'
+                        , '--publisher', 'POLITIKA NOVINE I MAGAZINI d.o.o.'
+                        ]
 
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
 
-    remove_tags_before = dict(name='div', attrs={'class':'content_center_border'})
+    keep_only_tags     = [ dict(name='div', attrs={'class':'contentcenter'}) ] 
     remove_tags_after  = dict(name='div', attrs={'class':'datum_item_details'})
 
     feeds          = [  
                          (u'Politika'             , u'http://www.politika.rs/rubrike/Politika/index.1.lt.xml'             )
                         ,(u'Svet'                 , u'http://www.politika.rs/rubrike/Svet/index.1.lt.xml'                 )
-                        ,(u'Redakcijski komentari', u'http://www.politika.rs/rubrike/redakcijski-komentari/index.1.lt.xml')
                         ,(u'Pogledi'              , u'http://www.politika.rs/pogledi/index.lt.xml'                        )
                         ,(u'Pogledi sa strane'    , u'http://www.politika.rs/rubrike/Pogledi-sa-strane/index.1.lt.xml'    )
                         ,(u'Tema dana'            , u'http://www.politika.rs/rubrike/tema-dana/index.1.lt.xml'            )

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

@@ -0,0 +1,34 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+'''
+spiegel.de
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Spiegel_int(BasicNewsRecipe):
+    title                 = u'Spiegel Online International'
+    __author__            = 'Darko Miletic'
+    description           = "News and POV from Europe's largest newsmagazine"
+    oldest_article        = 7
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    cover_url = 'http://www.spiegel.de/static/sys/v8/headlines/spiegelonline.gif'
+    html2lrf_options = [
+                          '--comment', description
+                        , '--base-font-size', '10'
+                        , '--category', 'news, politics, Germany'
+                        , '--publisher', 'SPIEGEL ONLINE GmbH'
+                        ]
+
+    remove_tags_after = dict(name='div', attrs={'id':'spArticleBody'})
+
+    feeds          = [(u'Spiegel Online', u'http://www.spiegel.de/schlagzeilen/rss/0,5291,676,00.xml')]
+
+    def print_version(self, url):
+        main, sep, rest = url.rpartition(',')
+        rmain, rsep, rrest = main.rpartition(',')
+        return rmain + ',druck-' + rrest + ',' + rest

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

@@ -0,0 +1,23 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+'''
+market-ticker.denninger.net
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Themarketticker(BasicNewsRecipe):
+    title                 = 'The Market Ticker'
+    __author__            = 'Darko Miletic'
+    description           = 'Commentary On The Capital Markets'    
+    oldest_article        = 7
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = True
+    html2lrf_options = [  '--comment'       , description
+                        , '--category'      , 'blog,news,finances'
+                        , '--base-font-size', '10'
+                       ]
+    feeds = [(u'Posts', u'http://market-ticker.denninger.net/feeds/index.rss2')]

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

@@ -0,0 +1,58 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+'''
+tomshardware.com
+'''
+
+from calibre.ebooks.BeautifulSoup import BeautifulSoup
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class Tomshardware(BasicNewsRecipe):
+    
+    title       = "Tom's Hardware US"
+    __author__  = 'Darko Miletic'
+    description = 'Hardware reviews and News'
+    no_stylesheets = True
+    needs_subscription = True
+    INDEX = 'http://www.tomshardware.com'
+    LOGIN = 'http://www.tomshardware.com/membres/?r=%2Fus%2F#loginForm'
+    cover_url = 'http://img.bestofmedia.com/img/tomshardware/design/tomshardware.jpg'
+    
+    html2lrf_options = [  '--comment'       , description
+                        , '--category'      , 'hardware,news'
+                        , '--base-font-size', '10'
+                       ]
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        if self.username is not None and self.password is not None:
+            br.open(self.LOGIN)
+            br.select_form(name='connexion')
+            br['login'] = self.username
+            br['mdp'  ] = self.password
+            br.submit()
+        return br
+
+    remove_tags = [
+                     dict(name='div' , attrs={'id':'header' })
+                    ,dict(name='object')
+                  ]
+    
+    feeds = [
+              (u'Latest Articles', u'http://www.tomshardware.com/feeds/atom/tom-s-hardware-us,18-2.xml')
+             ,(u'Latest News'    , u'http://www.tomshardware.com/feeds/atom/tom-s-hardware-us,18-1.xml')
+            ]
+                  
+    def print_version(self, url):
+        main, sep, rest = url.rpartition('.html')
+        rmain, rsep, article_id = main.rpartition(',')
+        tmain, tsep, trest = rmain.rpartition('/reviews/')
+        if tsep:
+           return 'http://www.tomshardware.com/review_print.php?p1=' + article_id
+        return 'http://www.tomshardware.com/news_print.php?p1=' + article_id        
+
+    def preprocess_html(self, soup):
+        del(soup.body['onload'])
+        return soup

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

@@ -15,13 +15,16 @@ class Vreme(BasicNewsRecipe):
     title       = 'Vreme'
     __author__  = 'Darko Miletic'
     description = 'Politicki Nedeljnik Srbije'
-    timefmt = ' [%A, %d %B, %Y]'
     no_stylesheets = True
-    simultaneous_downloads = 1
-    delay = 1
     needs_subscription = True    
     INDEX = 'http://www.vreme.com'
     LOGIN = 'http://www.vreme.com/account/index.php'
+    html2lrf_options = [
+                          '--comment', description
+                        , '--base-font-size', '10'
+                        , '--category', 'news, politics, Serbia'
+                        , '--publisher', 'Vreme d.o.o.'
+                        ]
 
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
 
@@ -66,3 +69,11 @@ class Vreme(BasicNewsRecipe):
         
     def print_version(self, url):
         return url + '&print=yes'
+
+    def get_cover_url(self):
+        cover_url = None
+        soup = self.index_to_soup(self.INDEX)
+        cover_item = soup.find('img',attrs={'alt':'Naslovna strana broja'})
+        if cover_item:
+           cover_url = self.INDEX + cover_item['src']
+        return cover_url