New recipes for E-Novine and Al Jazeera by Darko Miletic

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

@@ -30,7 +30,8 @@ recipe_modules = ['recipe_' + r for r in (
            'honoluluadvertiser', 'starbulletin', 'exiled', 'indy_star', 'dna',
            'pobjeda', 'chicago_breaking_news', 'glasgow_herald', 'linuxdevices',
            'hindu', 'cincinnati_enquirer', 'physics_world', 'pressonline',
-           'la_republica', 'physics_today', 'chicago_tribune',
+           'la_republica', 'physics_today', 'chicago_tribune', 'e_novine',
+           'al_jazeera',
           )]
 
 import re, imp, inspect, time, os

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

@@ -0,0 +1,50 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+
+'''
+aljazeera.net
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AlJazeera(BasicNewsRecipe):
+    title                  = 'Al Jazeera in English'
+    __author__             = 'Darko Miletic'
+    description            = 'News from Middle East'
+    publisher              = 'Al Jazeera'
+    category               = 'news, politics, middle east'
+    simultaneous_downloads = 1
+    delay                  = 4    
+    oldest_article         = 1
+    max_articles_per_feed  = 100
+    no_stylesheets         = True
+    encoding               = 'iso-8859-1'
+    remove_javascript      = True
+    use_embedded_content   = False
+    
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        , '--ignore-tables'
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_table=True' 
+     
+    keep_only_tags = [dict(name='div', attrs={'id':'ctl00_divContent'})]
+
+    remove_tags = [
+                     dict(name=['object','link'])
+                    ,dict(name='td', attrs={'class':['MostActiveDescHeader','MostActiveDescBody']})
+                  ]
+
+    feeds = [(u'AL JAZEERA ENGLISH (AJE)', u'http://english.aljazeera.net/Services/Rss/?PostingId=2007731105943979989' )]
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll(face=True):
+            del item['face']
+        return soup
+

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

@@ -0,0 +1,58 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+
+'''
+e-novine.com
+'''
+
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class E_novine(BasicNewsRecipe):
+    title                 = 'E-Novine'
+    __author__            = 'Darko Miletic'
+    description           = 'News from Serbia'
+    publisher             = 'E-novine'
+    category              = 'news, politics, Balcans'
+    oldest_article        = 1
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    encoding              = 'cp1250'
+    cover_url             = 'http://www.e-novine.com/slike/slike_3/r1/g2008/m03/y3165525326702598.jpg'
+    remove_javascript     = True
+    use_embedded_content  = False
+    language              = _('Serbian')
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: justify; font-family: serif1, serif} .article_description{font-family: sans1, sans-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} img {margin-top: 0em; margin-bottom: 0.4em}"' 
+     
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+
+    keep_only_tags = [dict(name='div', attrs={'id':['css_47_0_2844H']})]
+
+    remove_tags = [dict(name=['object','link','embed','iframe'])]
+
+    feeds = [(u'Sve vesti', u'http://www.e-novine.com/rss/e-novine.xml' )]
+
+    def preprocess_html(self, soup):
+        soup.html['xml:lang'] = 'sr-Latn-ME'
+        soup.html['lang']     = 'sr-Latn-ME'
+        mtag = '<meta http-equiv="Content-Language" content="sr-Latn-ME"/>'
+        soup.head.insert(0,mtag)
+        for item in soup.findAll(style=True):
+            del item['style']
+        ftag = soup.find('div', attrs={'id':'css_47_0_2844H'})
+        if ftag:
+           it = ftag.div
+           it.extract()
+           ftag.div.extract()
+           ftag.insert(0,it)
+        return soup

upload.py

@@ -676,7 +676,7 @@ class stage3(OptionlessCommand):
     
     def run(self):
         OptionlessCommand.run(self)
-        self.misc() 
+        self.misc()
         
 class stage2(OptionlessCommand):
     description = 'Stage 2 of the build process' 
@@ -705,4 +705,4 @@ class upload(OptionlessCommand):
             ('stage1', None),
             ('stage2', None),
             ('stage3', None)
-            ]
+            ]