Pull from trunk

src/calibre/ebooks/oeb/iterator.py

@@ -101,7 +101,7 @@ class EbookIterator(object):
         '''
         for item in self.opf.manifest:
             if item.mime_type and 'css' in item.mime_type.lower():
-                css = open(item.path, 'rb').read().decode('utf-8')
+                css = open(item.path, 'rb').read().decode('utf-8', 'replace')
                 for match in re.compile(r'@font-face\s*{([^}]+)}').finditer(css):
                     block  = match.group(1)
                     family = re.compile(r'font-family\s*:\s*([^;]+)').search(block)

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

@@ -44,6 +44,7 @@ recipe_modules = ['recipe_' + r for r in (
            'stackoverflow', 'telepolis_artikel', 'zaobao', 'usnews',
            'straitstimes', 'index_hu', 'pcworld_hu', 'hrt', 'rts',
            'h1', 'h2', 'h3', 'phd_comics', 'woz_die', 'elektrolese',
+           'climate_progress', 'carta',
           )]
 
 import re, imp, inspect, time, os

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

@@ -0,0 +1,45 @@
+__license__   = 'GPL v3'
+__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
+
+'''
+Fetch Carta.info.
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+
+class Carta(BasicNewsRecipe):
+
+    title = u'Carta'
+    description = 'News about electronic publishing'
+    __author__ = 'Oliver Niesner'
+    use_embedded_content   = False
+    timefmt = ' [%a %d %b %Y]'
+    oldest_article = 7
+    max_articles_per_feed = 50
+    no_stylesheets = True
+    remove_javascript = True
+    #html2epub_options = 'linearize_tables = True\nbase_font_size2=14'
+    encoding = 'utf-8'
+    language = _('German')
+
+
+    remove_tags_after = [dict(name='p', attrs={'class':'tags-blog'})]
+
+    remove_tags = [dict(name='p', attrs={'class':'print'}),
+                   dict(name='p', attrs={'class':'tags-blog'}),
+                   dict(name='p', attrs={'class':'mail'}),
+                   dict(name='p', attrs={'style':'text-align: center;'}),
+                   dict(name='p', attrs={'align':'left'}),
+                   dict(name='p', attrs={'class':'date'}),
+                   dict(id='comments'),
+                   dict(id='headerleft'),
+                   dict(id='subnav'),
+                   dict(id='headerright')]
+
+
+    feeds =  [ (u'Carta', u'http://feeds2.feedburner.com/carta-standard-rss') ]
+
+
+    def print_version(self, url):
+        return url + 'print/'

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

@@ -0,0 +1,47 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+climateprogress.org
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
+
+class ClimateProgress(BasicNewsRecipe):
+    title                 = 'Climate Progress'
+    __author__            = 'Darko Miletic'
+    description           = "An insider's view of climate science, politics and solutions"
+    publisher             = 'Climate Progress'
+    category              = 'news, ecology, climate, blog'
+    oldest_article        = 7
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = True
+    encoding              = 'utf-8'
+    language              = _("English")
+    lang                  = 'en-US'
+    direction             = 'ltr'
+    
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+
+    remove_tags = [dict(name='a', attrs={'rel':'bookmark'})]
+    
+    feeds = [(u'Posts', u'http://feeds.feedburner.com/climateprogress/lCrX')]
+    
+    def preprocess_html(self, soup):
+        soup.html['lang'] = self.lang
+        soup.html['dir' ] = self.direction
+        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
+        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
+        soup.head.insert(0,mlang)
+        soup.head.insert(1,mcharset)
+        return self.adeify_images(soup)
+