Pull from trunk

COPYRIGHT

@@ -352,7 +352,7 @@ License: other
 Liberation Fonts
 -----------------
 calibre includes a copy of the liberation fonts, available from
-https://fedorahosted.org/liberation-fonts
+https://calibre.kovidgoyal.net/downloads/liberation-fonts
 
 BSD License (for all the BSD licensed code indicated above)
 -----------------------------------------------------------

src/calibre/trac/plugins/download.py

@@ -39,6 +39,7 @@ def get_linux_data(version='1.0.0'):
                         ('debian', 'Debian Sid'),
                         ('exherbo', 'Exherbo'),
                         ('foresight', 'Foresight 2.1'),
+                        ('gentoo', 'Gentoo'),
                         ('ubuntu', 'Ubuntu Jaunty Jackalope'),
                         ('linux_mint', 'Linux Mint Gloria'),
                         ]:

src/calibre/utils/help2man.py

@@ -54,6 +54,9 @@ def create_man_page(prog, parser):
               'http://calibre.kovidgoyal.net/user_manual',
               '.PP', '.B Created by '+__author__]
 
-    return  bz2.compress('\n'.join(lines))
+    lines = [x if isinstance(x, unicode) else unicode(x, 'utf-8', 'replace') for
+            x in lines]
+
+    return  bz2.compress((u'\n'.join(lines)).encode('utf-8'))
 
 

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

@@ -43,7 +43,7 @@ recipe_modules = ['recipe_' + r for r in (
            'seattle_times', 'scott_hanselman', 'coding_horror', 'twitchfilms',
            'stackoverflow', 'telepolis_artikel', 'zaobao', 'usnews',
            'straitstimes', 'index_hu', 'pcworld_hu', 'hrt', 'rts',
-           'h1', 'h2', 'h3', 'phd_comics', 'woz_die',
+           'h1', 'h2', 'h3', 'phd_comics', 'woz_die', 'elektrolese',
           )]
 
 import re, imp, inspect, time, os

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

@@ -0,0 +1,35 @@
+__license__   = 'GPL v3'
+__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
+
+'''
+Fetch elektrolese.
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+
+class elektrolese(BasicNewsRecipe):
+
+    title = u'elektrolese'
+    description = 'News about electronic publishing'
+    __author__ = 'Oliver Niesner'
+    use_embedded_content   = False
+    timefmt = ' [%a %d %b %Y]'
+    language = _('German')
+    oldest_article = 14
+    max_articles_per_feed = 50
+    no_stylesheets = True
+    #html2epub_options = 'linearize_tables = True\nbase_font_size2=14'
+    encoding = 'utf-8'
+
+
+    remove_tags_after = [dict(id='comments')]
+    filter_regexps = [r'ad\.doubleclick\.net']
+
+    remove_tags = [dict(name='div', attrs={'class':'bannerSuperBanner'}),
+                   dict(id='comments')]
+
+
+
+    feeds =  [ (u'electrolese', u'http://elektrolese.blogspot.com/feeds/posts/default?alt=rss') ]
+

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

@@ -8,7 +8,7 @@ Fetch heise.
 from calibre.web.feeds.news import BasicNewsRecipe
 
 
-class HeiseDe(BasicNewsRecipe):
+class heiseDe(BasicNewsRecipe):
 
     title = 'heise'
     description = 'Computernews from Germany'
@@ -31,6 +31,7 @@ class HeiseDe(BasicNewsRecipe):
 		   dict(id='bannerzone'),
 		   dict(name='span', attrs={'class':'rsaquo'}),
 		   dict(name='div', attrs={'class':'news_logo'}),
+		   dict(name='div', attrs={'class':'bcadv ISI_IGNORE'}),
 		   dict(name='p', attrs={'class':'news_option'}),
 		   dict(name='p', attrs={'class':'news_navi'}),
 		   dict(name='p', attrs={'class':'news_foren'})]
@@ -40,3 +41,5 @@ class HeiseDe(BasicNewsRecipe):
 
 
 
+
+

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

@@ -1,53 +1,57 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
 '''
 newyorker.com
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
 
 class NewYorker(BasicNewsRecipe):
-
+    title                 = 'The New Yorker'
-    title                 = u'The New Yorker'
     __author__            = 'Darko Miletic'
     description           = 'The best of US journalism'    
     oldest_article        = 7
     language              = _('English')
     max_articles_per_feed = 100
-    no_stylesheets        = False
+    no_stylesheets        = True
     use_embedded_content  = False
-    extra_css = '''
+    publisher             = 'Conde Nast Publications'
-    .calibre_feed_list {font-size:xx-small}
+    category              = 'news, politics, USA'
-    .calibre_article_list {font-size:xx-small}
+    encoding              = 'cp1252'
-    .calibre_feed_title {font-size:normal}
-    .calibre_recipe_title {font-size:normal}
-    .calibre_feed_description {font-size:xx-small}
-    '''
                     
-
+    html2lrf_options = [
-    keep_only_tags = [
+                          '--comment', description
-                        dict(name='div'  , attrs={'id':'printbody'   })
+                        , '--category', category
+                        , '--publisher', publisher
                         ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+
+    keep_only_tags = [dict(name='div', attrs={'id':'printbody'})]
+    remove_tags_after = dict(name='div',attrs={'id':'articlebody'})
     remove_tags = [
-                     dict(name='div'  , attrs={'class':'utils'       })
+                     dict(name='div', attrs={'class':['utils','articleRailLinks','icons'] })
-                    ,dict(name='div'  , attrs={'id':'bottomFeatures' })
+                    ,dict(name='link')
-                    ,dict(name='div'  , attrs={'id':'articleBottom'  })
                   ]
 
-    feeds          = [
+    feeds          = [(u'The New Yorker', u'http://feeds.newyorker.com/services/rss/feeds/everything.xml')]
-                        (u'The New Yorker', u'http://feeds.newyorker.com/services/rss/feeds/everything.xml')
-                     ]
 
     def print_version(self, url):
         return url + '?printable=true'
 
+    def get_article_url(self, article):
+        return article.get('guid',  None)
+
     def postprocess_html(self, soup, x):
         body = soup.find('body')
         if body:
             html = soup.find('html')
             if html:
                 body.extract()
-                html.insert(-1, body)
+                html.insert(2, body)
+        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
+        soup.head.insert(1,mcharset)
         return soup

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

@@ -9,15 +9,15 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class Sueddeutsche(BasicNewsRecipe):
 
-    title = u'S\xc3\xbcddeutsche'
+    title = u'S\xfcddeutsche'
     description = 'News from Germany'
     __author__ = 'Oliver Niesner'
     use_embedded_content   = False
-    language = _('German')
     timefmt = ' [%d %b %Y]'
     oldest_article = 7
     max_articles_per_feed = 50
     no_stylesheets = True
+    language = _('German')
     encoding = 'iso-8859-15'
     remove_javascript = True
 
@@ -89,3 +89,5 @@ class Sueddeutsche(BasicNewsRecipe):
     def print_version(self, url):
         return url.replace('/text/', '/text/print.html')
 
+
+

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

@@ -6,7 +6,6 @@ Fetch zdnet.
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
-import re
 
 
 class cdnet(BasicNewsRecipe):
@@ -19,15 +18,9 @@ class cdnet(BasicNewsRecipe):
     timefmt = ' [%d %b %Y]'
     max_articles_per_feed = 40
     no_stylesheets = True
-    encoding = 'iso-8859-1'
+    encoding = 'latin1'
+
 
-    #preprocess_regexps = \
-#	[(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
-#		[
-#		(r'<84>', lambda match: ''),
-#		(r'<93>', lambda match: ''),
-#		]
-#	]
 
     remove_tags = [dict(id='eyebrows'),
 		   dict(id='header'),
@@ -36,12 +29,16 @@ class cdnet(BasicNewsRecipe):
 		   dict(id=''),
 		   dict(name='div', attrs={'class':'banner'}),
 		   dict(name='p', attrs={'class':'tags'}),
+		   dict(name='a', attrs={'href':'http://www.twitter.com/ryanaraine'}),
 		   dict(name='div', attrs={'class':'special1'})]
     remove_tags_after = [dict(name='div', attrs={'class':'bloggerDesc clear'})]
 
     feeds =  [ ('zdnet', 'http://feeds.feedburner.com/zdnet/security') ]
 
 
-
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup