Updated recipe for DIscover Magazine and new Recipes for The Metro Montreal and The Gazette by Jerry Clapperton

resources/recipes/discover_magazine.recipe

@@ -10,26 +10,44 @@ doscovermagazine.com
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class DiscoverMagazine(BasicNewsRecipe):
+
     title = u'Discover Magazine'
-    description = u'Science, Technology and the Future' 
+    description = u'Science, Technology and the Future'
-    __author__ = 'Mike Diaz' 
+    __author__ = 'Mike Diaz'
-    oldest_article = 33
     language = 'en'
- 
+
-    max_articles_per_feed = 20 
+    oldest_article = 33
+    max_articles_per_feed = 20
+    no_stylesheets = True
+    remove_javascript     = True
+    use_embedded_content  = False
+    encoding = 'utf-8'
+
+    extra_css = '.headline {font-size: x-large;} \n .fact {padding-top: 10pt}'
+
+    remove_tags_before = dict(id='articlePage')
+
+    keep_only_tags = [dict(name='div', attrs={'id':'articlePage'})]
+
+    remove_tags = [dict(attrs={'id':['buttons', 'tool-box', 'teaser', 'already-subscriber', 'teaser-suite',  'related-articles', 'relatedItem', 'box-popular', 'box-blogs', 'box-news', 'footer']}),
+                            dict(attrs={'class':'popularNewsBox'}),
+                            dict(name=['img', 'style', 'head'])]
+
+    remove_tags_after = dict(id='articlePage')
+
     feeds = [
-             (u'Technology', u'http://discovermagazine.com/topics/technology/rss.xml'), 
+             (u'Technology', u'http://discovermagazine.com/topics/technology/rss.xml'),
-             (u'Health - Medicine', u'http://discovermagazine.com/topics/health-medicine/rss.xml'), 
+             (u'Health - Medicine', u'http://discovermagazine.com/topics/health-medicine/rss.xml'),
-             (u'Mind Brain', u'http://discovermagazine.com/topics/mind-brain/rss.xml'), 
+             (u'Mind Brain', u'http://discovermagazine.com/topics/mind-brain/rss.xml'),
-             (u'Space', u'http://discovermagazine.com/topics/space/rss.xml'), 
+             (u'Space', u'http://discovermagazine.com/topics/space/rss.xml'),
-             (u'Human Origins', u'http://discovermagazine.com/topics/human-origins/rss.xml'), 
+             (u'Human Origins', u'http://discovermagazine.com/topics/human-origins/rss.xml'),
-             (u'Living World', u'http://discovermagazine.com/topics/living-world/rss.xml'), 
+             (u'Living World', u'http://discovermagazine.com/topics/living-world/rss.xml'),
-             (u'Environment', u'http://discovermagazine.com/topics/environment/rss.xml'), 
+             (u'Environment', u'http://discovermagazine.com/topics/environment/rss.xml'),
-             (u'Physics & Math', u'http://discovermagazine.com/topics/physics-math/rss.xml'), 
+             (u'Physics & Math', u'http://discovermagazine.com/topics/physics-math/rss.xml'),
-             (u'Vital Signs', u'http://discovermagazine.com/columns/vital-signs/rss.xml'), 
+             (u'Vital Signs', u'http://discovermagazine.com/columns/vital-signs/rss.xml'),
-             (u"20 Things you didn't know about...", u'http://discovermagazine.com/columns/20-things-you-didnt-know/rss.xml'), 
+             (u"20 Things you didn't know about...", u'http://discovermagazine.com/columns/20-things-you-didnt-know/rss.xml'),
-             (u'Fuzzy Math', u'http://discovermagazine.com/columns/fuzzy-math/rss.xml'), 
+             (u'Fuzzy Math', u'http://discovermagazine.com/columns/fuzzy-math/rss.xml'),
-             (u'The Brain', u'http://discovermagazine.com/columns/the-brain/rss.xml'), 
+             (u'The Brain', u'http://discovermagazine.com/columns/the-brain/rss.xml'),
-             (u'Stupid Science Word of the Month', u'http://discovermagazine.com/columns/stupid-science-word-of-the-month/rss.xml'), 
+             (u'Stupid Science Word of the Month', u'http://discovermagazine.com/columns/stupid-science-word-of-the-month/rss.xml'),
              (u'Science Not Fiction', u'http://blogs.discovermagazine.com/sciencenotfiction/wp-rss.php')
-            ]
+            ]

resources/recipes/metro_montreal.recipe

@@ -0,0 +1,24 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Metro_Montreal(BasicNewsRecipe):
+
+    title          = u'M\xe9tro Montr\xe9al'
+    __author__     = 'Jerry Clapperton'
+    description    = 'Le quotidien le plus branché sur le monde'
+    language = 'fr'
+
+    oldest_article = 7
+    max_articles_per_feed = 20
+    use_embedded_content  = False
+    remove_javascript = True
+    no_stylesheets = True
+    encoding = 'utf-8'
+
+    extra_css = '.headline {font-size: x-large;} \n .fact {padding-top: 10pt}'
+
+    remove_tags = [dict(attrs={'id':'buttons'}), dict(name=['img', 'style'])]
+
+    feeds = [(u"L'info", u'http://journalmetro.com/linfo/rss'), (u'Monde', u'http://journalmetro.com/monde/rss'), (u'Culture', u'http://journalmetro.com/culture/rss'), (u'Sports', u'http://journalmetro.com/sports/rss'), (u'Paroles', u'http://journalmetro.com/paroles/rss')]
+
+    def print_version(self, url):
+          return url.replace('article', 'ArticlePrint') + '?language=fr'

resources/recipes/pagina12.recipe

@@ -32,7 +32,7 @@ class Pagina12(BasicNewsRecipe):
                         }
 
     remove_tags = [dict(name='div', attrs={'id':['volver','logo','logo_suple','fin','permalink']})]
-    
+
 
     feeds = [
               (u'Edicion impresa', u'http://www.pagina12.com.ar/diario/rss/principal.xml'   )
@@ -55,4 +55,4 @@ class Pagina12(BasicNewsRecipe):
         imgnames = ['tapan.jpg','tapagn.jpg','tapan_gr.jpg','tapagn.jpg','tapagn.jpg','tapan.jpg','tapagn.jpg']
         weekday = time.localtime().tm_wday
         return strftime('http://www.pagina12.com.ar/fotos/%Y%m%d/diario/') + imgnames[weekday]
-        
+

resources/recipes/the_gazette.recipe

@@ -0,0 +1,22 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class The_Gazette(BasicNewsRecipe):
+
+    cover_url      = 'file:///D:/Documents/Pictures/Covers/The_Gazette.jpg'
+    title          = u'The Gazette'
+    __author__     = 'Jerry Clapperton'
+    description    = 'Montreal news in English'
+    language = 'en_CA'
+
+    oldest_article = 7
+    max_articles_per_feed = 20
+    use_embedded_content  = False
+    remove_javascript = True
+    no_stylesheets = True
+    encoding = 'utf-8'
+
+    keep_only_tags = [dict(name='div', attrs={'id':['storyheader','page1']})]
+
+    extra_css = '.headline {font-size: x-large;} \n .fact {padding-top: 10pt}'
+
+    feeds = [(u'News', u'http://feeds.canada.com/canwest/F297'), (u'Opinion', u'http://feeds.canada.com/canwest/F7383'), (u'Arts', u'http://feeds.canada.com/canwest/F7366'), (u'Life', u'http://rss.canada.com/get/?F6934'), (u'Business', u'http://feeds.canada.com/canwest/F6939'), (u'Travel', u'http://rss.canada.com/get/?F6938'), (u'Health', u'http://feeds.canada.com/canwest/F7397'), (u'Technology', u'http://feeds.canada.com/canwest/F7411')]