Updated Harpers and Le Monde Diplomatique. Fixes #5205 (Updated recipes for Le monde diplomatique and Harper's)

resources/recipes/harpers_full.recipe

@@ -1,7 +1,5 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
 '''
 harpers.org - paid subscription/ printed issue articles
 This recipe only get's article's published in text format
@@ -10,39 +8,40 @@ images and pdf's are ignored
 
 from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag
 
 class Harpers_full(BasicNewsRecipe):
-    title                 = u"Harper's Magazine - articles from printed edition"
+    title                 = "Harper's Magazine - articles from printed edition"
-    __author__            = u'Darko Miletic'
+    __author__            = 'Darko Miletic'
-    description           = u"Harper's Magazine: Founded June 1850."
+    description           = "Harper's Magazine: Founded June 1850."
     publisher             = "Harpers's"
     category              = 'news, politics, USA'
     oldest_article        = 30
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
-    delay                  = 1
+    delay                 = 1
-    language = 'en'
+    language              = 'en'
+    needs_subscription    = True
+    masthead_url          = 'http://www.harpers.org/media/image/Harpers_305x100.gif'
+    publication_type      = 'magazine'    
+    INDEX                 = strftime('http://www.harpers.org/archive/%Y/%m')
+    LOGIN                 = 'http://www.harpers.org'
+    cover_url             = strftime('http://www.harpers.org/media/pages/%Y/%m/gif/0001.gif')
+    extra_css             = ' body{font-family: "Georgia",serif} '
 
-    needs_subscription = True
+    conversion_options = {
-    INDEX = strftime('http://www.harpers.org/archive/%Y/%m')
+                          'comment'          : description
-    LOGIN = 'http://www.harpers.org'
+                        , 'tags'             : category
-    cover_url = strftime('http://www.harpers.org/media/pages/%Y/%m/gif/0001.gif')
+                        , 'publisher'        : publisher
-
+                        , 'language'         : language
-    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}"'
 
     keep_only_tags = [ dict(name='div', attrs={'id':'cached'}) ]
     remove_tags = [
                      dict(name='table', attrs={'class':['rcnt','rcnt topline']})
                     ,dict(name='link')
                   ]
+    remove_attributes=['xmlns']              
 
     def get_browser(self):
         br = BasicNewsRecipe.get_browser()
@@ -71,12 +70,3 @@ class Harpers_full(BasicNewsRecipe):
                                  ,'description':''
                                 })
         return [(soup.head.title.string, articles)]
-
-    def preprocess_html(self, soup):
-        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
-        soup.head.insert(1,mcharset)
-        for item in soup.findAll(style=True):
-            del item['style']
-        for item in soup.findAll(xmlns=True):
-            del item['xmlns']
-        return soup

resources/recipes/lemonde_dip.recipe

@@ -1,7 +1,5 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
 '''
 mondediplo.com
 '''
@@ -21,11 +19,14 @@ class LeMondeDiplomatiqueEn(BasicNewsRecipe):
     delay                  = 1
     encoding               = 'utf-8'
     needs_subscription     = True
+    masthead_url           = 'http://mondediplo.com/squelettes/pics/logo-30.gif'
+    publication_type       = 'magazine'
     PREFIX                 = 'http://mondediplo.com/'
     LOGIN                  = PREFIX + '2009/09/02congo'
     INDEX                  = PREFIX + strftime('%Y/%m/')
     use_embedded_content   = False
     language               = 'en'
+    extra_css              = ' body{font-family: "Luxi sans","Lucida sans","Lucida Grande",Lucida,"Lucida Sans Unicode",sans-serif} .surtitre{font-size: 1.2em; font-variant: small-caps; margin-bottom: 0.5em} .chapo{font-size: 1.2em; font-weight: bold; margin: 1em 0 0.5em} .texte{font-family: Georgia,"Times New Roman",serif} h1{color: #990000} .notes{border-top: 1px solid #CCCCCC; font-size: 0.9em; line-height: 1.4em} '
 
     conversion_options = {
                           'comment'          : description
@@ -45,7 +46,10 @@ class LeMondeDiplomatiqueEn(BasicNewsRecipe):
             br.open(self.LOGIN,data)
         return br
 
-    keep_only_tags    =[dict(name='div', attrs={'id':'contenu'})]
+    keep_only_tags    =[  
+                          dict(name='div', attrs={'id':'contenu'})
+                        , dict(name='div',attrs={'class':'notes surlignable'})
+                        ]
     remove_tags = [dict(name=['object','link','script','iframe','base'])]
 
     def parse_index(self):

src/calibre/web/feeds/__init__.py

@@ -193,6 +193,9 @@ class Feed(object):
                     title = title.decode('utf-8', 'replace')
                 self.logger.debug('Skipping article %s as it is too old'%title)
 
+    def reverse(self):
+        self.articles.reverse()
+
     def __iter__(self):
         return iter(self.articles)
 

src/calibre/web/feeds/news.py

@@ -801,7 +801,10 @@ class BasicNewsRecipe(Recipe):
         self.jobs = []
 
         if self.reverse_article_order:
-            feeds = [list(reversed(list(feed))) for feed in feeds]
+            for feed in feeds:
+                if hasattr(feed, 'reverse'):
+                    print 111111
+                    feed.reverse()
 
         for f, feed in enumerate(feeds):
             feed_dir = os.path.join(self.output_dir, 'feed_%d'%f)