New recipe for the Arizona Star by Darko Miletic

src/calibre/ebooks/__init__.py

@@ -1,3 +1,4 @@
+from __future__ import with_statement
 __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
 

src/calibre/gui2/__init__.py

@@ -466,5 +466,3 @@ class Application(QApplication):
                 self.translator.loadFromData(data)
                 self.installTranslator(self.translator)
 
-
-

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

@@ -37,7 +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', 'laprensa_ni',
+           'krstarica', 'krstarica_en', 'tanjug', 'laprensa_ni', 'azstarnet',
           )]
 
 import re, imp, inspect, time, os

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

@@ -0,0 +1,63 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+www.azstarnet.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Azstarnet(BasicNewsRecipe):
+    title                 = 'Arizona  Daily Star'
+    __author__            = 'Darko Miletic'
+    description           = 'news from Arizona'
+    publisher             = 'azstarnet.com'
+    category              = 'news, politics, Arizona, USA'
+    delay                 = 1    
+    oldest_article        = 1
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'utf-8'
+    needs_subscription    = True
+    remove_javascript     = True
+
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        if self.username is not None and self.password is not None:
+            br.open('http://azstarnet.com/registration/retro.php')
+            br.select_form(nr=1)
+            br['email'] = self.username
+            br['pass' ] = self.password
+            br.submit()
+        return br
+    
+    
+    keep_only_tags = [dict(name='div', attrs={'id':'storycontent'})]
+
+    remove_tags = [
+                     dict(name=['object','link','iframe','base','img'])
+                    ,dict(name='div',attrs={'class':'bannerinstory'})
+                  ]
+
+    
+    feeds = [(u'Tucson Region', u'http://rss.azstarnet.com/index.php?site=metro')]
+
+    def preprocess_html(self, soup):
+        soup.html['dir' ] = 'ltr'
+        soup.html['lang'] = 'en-US'
+        mtag = '\n<meta http-equiv="Content-Language" content="en-US"/>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8">\n'
+        soup.head.insert(0,mtag)    
+        for item in soup.findAll(style=True):
+            del item['style']    
+        return soup
+    

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

@@ -11,13 +11,13 @@ class WashingtonPost(BasicNewsRecipe):
     max_articles_per_feed = 20
     language = _('English')
 
-    
-    remove_javascript = True   
 
-  
+    remove_javascript = True
+
+
     feeds = [ ('Today\'s Highlights', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/03/24/LI2005032400102.xml'),
      	         ('Politics', 'http://www.washingtonpost.com/wp-dyn/rss/politics/index.xml'),
-     	         ('Nation', 'http://www.www.washingtonpost.com/wp-dyn/rss/nation/index.xml'),
+     	         ('Nation', 'http://www.washingtonpost.com/wp-dyn/rss/nation/index.xml'),
      	         ('World', 'http://www.washingtonpost.com/wp-dyn/rss/world/index.xml'),
      	         ('Business', 'http://www.washingtonpost.com/wp-dyn/rss/business/index.xml'),
      	         ('Technology', 'http://www.washingtonpost.com/wp-dyn/rss/technology/index.xml'),
@@ -25,7 +25,7 @@ class WashingtonPost(BasicNewsRecipe):
      	         ('Education', 'http://www.washingtonpost.com/wp-dyn/rss/education/index.xml'),
      	         ('Editorials', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/05/30/LI2005053000331.xml'),
      	]
-    
+
     remove_tags = [{'id':['pfmnav', 'ArticleCommentsWrapper']}]
 
 
@@ -34,7 +34,7 @@ class WashingtonPost(BasicNewsRecipe):
 
     def print_version(self, url):
         return url.rpartition('.')[0] + '_pf.html'
-    
+
     def postprocess_html(self, soup, first):
         for div in soup.findAll(name='div', style=re.compile('margin')):
             div['style'] = ''