Merge from trunk

resources/recipes/esquire.recipe

@@ -1,7 +1,5 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
 
 '''
 www.esquire.com
@@ -9,7 +7,6 @@ www.esquire.com
 
 from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag
 
 class Esquire(BasicNewsRecipe):
     title                 = 'Esquire'
@@ -22,23 +19,21 @@ class Esquire(BasicNewsRecipe):
     no_stylesheets        = True
     encoding              = 'cp1250'
     use_embedded_content  = False
-    language = 'en'
+    language              = 'en'
-
+    publication_type      = 'magazine'    
-    lang                  = 'en-US'
+    masthead_url          = 'http://www.esquire.com/cm/shared/site_images/print_this/esquire_logo.gif'    
-    cover_url             = strftime('http://www.esquire.com/cm/esquire/cover-images/%Y_') + strftime('%m').strip('0') + '.jpg'
 
     conversion_options = {
-                          'comment'          : description
+                          'comment'   : description
-                        , 'tags'             : category
+                        , 'tags'      : category
-                        , 'publisher'        : publisher
+                        , 'publisher' : publisher
-                        , 'language'         : lang
+                        , 'language'  : language
-                        , 'pretty_print'     : True
                         }
 
-    keep_only_tags = [dict(name='div', attrs={'id':'content'})]
+    keep_only_tags    = [dict(name='div', attrs={'id':['article_header','article_content']})]
-
+    remove_tags       = [dict(name=['object','link','embed','iframe','base'])]
-    remove_tags = [dict(name=['object','link','embed','iframe'])]
+    remove_attributes = ['width','height']
-
+    
     feeds = [
                (u'Style'    , u'http://www.esquire.com/style/rss/'    )
               ,(u'Women'    , u'http://www.esquire.com/women/rss/'    )
@@ -47,17 +42,7 @@ class Esquire(BasicNewsRecipe):
               ,(u'Frontpage', u'http://www.esquire.com/rss/'          )
             ]
 
-
-    def print_version(self, url):
-        rest = url.rpartition('?')[0]
-        article = rest.rpartition('/')[2]
-        return 'http://www.esquire.com/print-this/' + article
-
     def preprocess_html(self, soup):
-        soup.html['xml:lang'] = self.lang
-        soup.html['lang']     = self.lang
-        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
-        soup.head.insert(0,mlang)
         for item in soup.findAll(style=True):
             del item['style']
         return soup

resources/recipes/fe_india.recipe

@@ -0,0 +1,46 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
+'''
+financialexpress.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class FE_India(BasicNewsRecipe):
+    title                 = 'The Financial Express'
+    __author__            = 'Darko Miletic'
+    description           = 'Financial news from India'
+    publisher             = 'The Indian Express Limited'
+    category              = 'news, politics, finances, India'
+    oldest_article        = 30
+    max_articles_per_feed = 200
+    no_stylesheets        = True
+    encoding              = 'cp1252'
+    use_embedded_content  = False
+    language              = 'en_IN'
+    remove_empty_feeds    = True
+    masthead_url          = 'http://static.expressindia.com/frontend/fe/images/fe_logo.jpg'
+    publication_type      = 'magazine'
+    extra_css             = ' body{font-family: Arial,Helvetica,sans-serif } '
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    keep_only_tags = [dict(attrs={'class':'txt'})]
+    remove_attributes = ['width','height']
+
+    feeds = [(u'Articles', u'http://www.expressindia.com/syndications/fe.xml')]
+
+    def print_version(self, url):
+        article_raw = url.rpartition('/')[0]
+        article_id = article_raw.rpartition('/')[2]
+        return 'http://www.financialexpress.com/printer/news/' + article_id + '/'
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup

src/calibre/gui2/dialogs/config/__init__.py

@@ -515,15 +515,15 @@ class ConfigDialog(ResizableDialog, Ui_Dialog):
         self.reset_confirmation_button.clicked.connect(self.reset_confirmation)
 
         deft, curt = read_raw_tweaks()
-        self.current_tweaks.setPlainText(curt)
+        self.current_tweaks.setPlainText(curt.decode('utf-8'))
-        self.default_tweaks.setPlainText(deft)
+        self.default_tweaks.setPlainText(deft.decode('utf-8'))
         self.restore_tweaks_to_default_button.clicked.connect(self.restore_tweaks_to_default)
 
         self.category_view.setCurrentIndex(self.category_view.model().index_for_name(initial_category))
 
     def restore_tweaks_to_default(self, *args):
         deft, curt = read_raw_tweaks()
-        self.current_tweaks.setPlainText(deft)
+        self.current_tweaks.setPlainText(deft.decode('utf-8'))
 
 
     def reset_confirmation(self):
@@ -698,8 +698,7 @@ class ConfigDialog(ResizableDialog, Ui_Dialog):
             self.input_order.setCurrentRow(idx-1)
 
     def set_tweaks(self):
-        raw = unicode(self.current_tweaks.toPlainText())
+        raw = unicode(self.current_tweaks.toPlainText()).encode('utf-8')
-        raw = re.sub(r'(?m)^#.*fileencoding.*', '# ', raw)
         try:
             exec raw
         except: