Consumerist and Gawker Media by Trickery

resources/recipes/consumerist.recipe

@@ -0,0 +1,53 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, NA'
+'''
+consumerist.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Consumerist(BasicNewsRecipe):
+    title                 = 'Consumerist'
+    __author__            = 'NA'
+    description           = "Consumerist, Shoppers Bite Back."
+    publisher             = 'consumerist.com'
+    category              = 'news, consumer news, consumer rights'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    encoding              = 'utf-8'
+    use_embedded_content  = False
+    language              = 'en'
+    masthead_url          = 'http://consumerist.com/css/images/footer_man.gif'
+    extra_css             = '''
+	body{font-family: "Lucida Grande",Helvetica,Arial,sans-serif}
+	img{margin-bottom: 1em}
+	h1{font-family :Arial,Helvetica,sans-serif; font-size:x-large}
+	h2{font-family :Arial,Helvetica,sans-serif; font-size:large}
+	              '''
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_attributes  = ['width','height']
+    #keep_only_tags     = [dict(attrs={'class':['', 'category-breadcrumb']}),]
+    remove_tags_before = dict(name='h2')
+
+    remove_tags = [
+       #dict(name='iframe'),
+       dict(name='div', attrs={'class':['e-comments', 'more-about', 'entry-tags']}),
+       #dict(name='div', attrs={'id':['IEContainer', 'clickIncludeBox']}),
+       #dict(name='ul', attrs={'class':'article-tools'}),
+       #dict(name='ul', attrs={'class':'articleTools'}),
+    ]
+
+    remove_tags_after  = dict(attrs={'class':'e-body'})
+
+    feeds = [(u'Articles', u'http://consumerist.com/index.xml')]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+

resources/recipes/deadspin.recipe

@@ -0,0 +1,44 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, NA'
+'''
+deadspin.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Deadspin(BasicNewsRecipe):
+    title                 = 'Deadspin'
+    __author__            = 'NA'
+    description           = "Deadspin, Sports News without Access, Favor, or Discretion."
+    publisher             = 'deadspin.com'
+    category              = 'news, sports, meltdowns'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    encoding              = 'utf-8'
+    use_embedded_content  = False
+    language              = 'en'
+    masthead_url          = 'http://cache.gawkerassets.com/assets/deadspin.com/img/logo.png'
+    extra_css             = '''
+	body{font-family: "Lucida Grande",Helvetica,Arial,sans-serif}
+	img{margin-bottom: 1em}
+	h1{font-family :Arial,Helvetica,sans-serif; font-size:large}
+	              '''
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_attributes  = ['width','height']
+    keep_only_tags     = [dict(attrs={'class':'content permalink'})]
+    remove_tags_before = dict(name='h1')
+    remove_tags        = [dict(attrs={'class':'contactinfo'})]
+    remove_tags_after  = dict(attrs={'class':'contactinfo'})
+
+    feeds = [(u'Articles', u'http://feeds.gawker.com/deadspin/full')]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+

resources/recipes/fleshbot.recipe

@@ -0,0 +1,44 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, NA'
+'''
+fleshbot.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Fleshbot(BasicNewsRecipe):
+    title                 = 'Fleshbot'
+    __author__            = 'NA'
+    description           = "Fleshbot, Pure Filth."
+    publisher             = 'Fleshbot.com'
+    category              = 'news, sex, sex industry, celebs, nudes, adult, adult toys, sex toys'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    encoding              = 'utf-8'
+    use_embedded_content  = False
+    language              = 'en'
+    masthead_url          = 'http://cache.fleshbot.com/assets/base/img/thumbs140x140/fleshbot.com.png'
+    extra_css             = '''
+	body{font-family: "Lucida Grande",Helvetica,Arial,sans-serif}
+	img{margin-bottom: 1em}
+	h1{font-family :Arial,Helvetica,sans-serif; font-size:x-large}
+	              '''
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_attributes  = ['width','height']
+    keep_only_tags     = [dict(attrs={'class':'content permalink'})]
+    remove_tags_before = dict(name='h1')
+    remove_tags        = [dict(attrs={'class':'contactinfo'})]
+    remove_tags_after  = dict(attrs={'class':'contactinfo'})
+
+    feeds = [(u'Articles', u'http://feeds.gawker.com/fleshbot/full')]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+

resources/recipes/gawker.recipe

@@ -0,0 +1,44 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, NA'
+'''
+gawker.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Gawker(BasicNewsRecipe):
+    title                 = 'Gawker'
+    __author__            = 'NA'
+    description           = "Gawker, Gossip from Manhattan and the Beltway to Hollywood and the Valley."
+    publisher             = 'gawker.com'
+    category              = 'news, gossip'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    encoding              = 'utf-8'
+    use_embedded_content  = False
+    language              = 'en'
+    masthead_url          = 'http://cache.gawkerassets.com/assets/gawker.com/img/logo.png'
+    extra_css             = '''
+	body{font-family: "Lucida Grande",Helvetica,Arial,sans-serif}
+	img{margin-bottom: 1em}
+	h1{font-family :Arial,Helvetica,sans-serif; font-size:large}
+	              '''
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_attributes  = ['width','height']
+    keep_only_tags     = [dict(attrs={'class':'content permalink'})]
+    remove_tags_before = dict(name='h1')
+    remove_tags        = [dict(attrs={'class':'contactinfo'})]
+    remove_tags_after  = dict(attrs={'class':'contactinfo'})
+
+    feeds = [(u'Articles', u'http://feeds.gawker.com/gawker/full')]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+

resources/recipes/io9.recipe

@@ -0,0 +1,46 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, NA'
+'''
+io9.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class i09(BasicNewsRecipe):
+    title                 = 'io9'
+    __author__            = 'NA'
+    description           = "io9, We Come From the Future."
+    publisher             = 'io9.com'
+    category              = 'news, science, education'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    encoding              = 'utf-8'
+    use_embedded_content  = False
+    language              = 'en'
+    masthead_url          = 'http://cache.gawkerassets.com/assets/io9.com/img/logo.png'
+    extra_css             = '''
+	body{font-family: "Lucida Grande",Helvetica,Arial,sans-serif}
+	img{margin-bottom: 1em}
+	h1{font-family :Arial,Helvetica,sans-serif; font-size:large}
+	h2{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
+	              '''
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_attributes  = ['width','height']
+    keep_only_tags     = [dict(attrs={'class':'content permalink'})]
+    remove_tags_before = dict(name='h1')
+    remove_tags        = [dict(attrs={'class':'contactinfo'})]
+    remove_tags_after  = dict(attrs={'class':'contactinfo'})
+
+    feeds = [(u'Articles', u'http://feeds.gawker.com/io9/full')]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+

resources/recipes/jalopnik.recipe

@@ -0,0 +1,45 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, NA'
+'''
+jalopnik.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Jalopnik(BasicNewsRecipe):
+    title                 = 'Jalopnik'
+    __author__            = 'NA'
+    description           = "Jalopnik, Obsessed With The Cult of Cars."
+    publisher             = 'jalopnik.com'
+    category              = 'news, cars, spyshots'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    encoding              = 'utf-8'
+    use_embedded_content  = False
+    language              = 'en'
+    masthead_url          = 'http://cache.gawkerassets.com/assets/jalopnik.com/img/logo.png'
+    extra_css             = '''
+	body{font-family: "Lucida Grande",Helvetica,Arial,sans-serif}
+	img{margin-bottom: 1em}
+	h1{font-family :Arial,Helvetica,sans-serif; font-size:large}
+	h2{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
+	              '''
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_attributes  = ['width','height']
+    keep_only_tags     = [dict(attrs={'class':'content permalink'})]
+    remove_tags_before = dict(name='h1')
+    remove_tags        = [dict(attrs={'class':'contactinfo'})]
+    remove_tags_after  = dict(attrs={'class':'contactinfo'})
+
+    feeds = [(u'Articles', u'http://feeds.gawker.com/jalopnik/full')]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+

resources/recipes/jezebel.recipe

@@ -0,0 +1,45 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, NA'
+'''
+jezebel.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Jezebel(BasicNewsRecipe):
+    title                 = 'Jezebel'
+    __author__            = 'NA'
+    description           = "Jezebel, Celebrity, Sex, Fashion for Women. Without Airbrushing."
+    publisher             = 'jezebel.com'
+    category              = 'news, cars, spyshots'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    encoding              = 'utf-8'
+    use_embedded_content  = False
+    language              = 'en'
+    masthead_url          = 'http://cache.gawkerassets.com/assets/jezebel.com/img/logo.png'
+    extra_css             = '''
+	body{font-family: "Lucida Grande",Helvetica,Arial,sans-serif}
+	img{margin-bottom: 1em}
+	h1{font-family :Arial,Helvetica,sans-serif; font-size:large}
+	h2{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
+	              '''
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_attributes  = ['width','height']
+    keep_only_tags     = [dict(attrs={'class':'content permalink'})]
+    remove_tags_before = dict(name='h1')
+    remove_tags        = [dict(attrs={'class':'contactinfo'})]
+    remove_tags_after  = dict(attrs={'class':'contactinfo'})
+
+    feeds = [(u'Articles', u'http://feeds.gawker.com/jezebel/full')]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+

resources/recipes/kotaku.recipe

@@ -0,0 +1,44 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, NA'
+'''
+kotaku.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Kotaku(BasicNewsRecipe):
+    title                 = 'Kotaku'
+    __author__            = 'NA'
+    description           = "Kotaku, the Gamer's Guide."
+    publisher             = 'kotaku.com'
+    category              = 'news, games, Internet, xbox 360, playstation 3, tips and tricks'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    encoding              = 'utf-8'
+    use_embedded_content  = False
+    language              = 'en'
+    masthead_url          = 'http://cache.gawkerassets.com/assets/kotaku.com/img/logo.png'
+    extra_css             = '''
+	body{font-family: "Lucida Grande",Helvetica,Arial,sans-serif}
+	img{margin-bottom: 1em}
+	h1{font-family :Arial,Helvetica,sans-serif; font-size:large}
+	              '''
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_attributes  = ['width','height']
+    keep_only_tags     = [dict(attrs={'class':'content permalink'})]
+    remove_tags_before = dict(name='h1')
+    remove_tags        = [dict(attrs={'class':'contactinfo'})]
+    remove_tags_after  = dict(attrs={'class':'contactinfo'})
+
+    feeds = [(u'Articles', u'http://feeds.gawker.com/kotaku/full')]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+

resources/recipes/lifehacker.recipe

@@ -0,0 +1,45 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, NA'
+'''
+lifehacker.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Lifehacker(BasicNewsRecipe):
+    title                 = 'Lifehacker'
+    __author__            = 'NA'
+    description           = "Computers make us more productive. Yeah, right. Lifehacker recommends the software downloads and web sites that actually save time. Don't live to geek; geek to live."
+    publisher             = 'lifehacker.com'
+    category              = 'news, IT, Internet, gadgets, tips and tricks, howto, diy'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    encoding              = 'utf-8'
+    use_embedded_content  = False
+    language              = 'en'
+    masthead_url          = 'http://cache.gawkerassets.com/assets/lifehacker.com/img/logo.png'
+    extra_css             = '''
+	body{font-family: "Lucida Grande",Helvetica,Arial,sans-serif}
+	img{margin-bottom: 1em}
+	h1{font-family :Arial,Helvetica,sans-serif; font-size:large}
+	h2{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
+	              '''
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_attributes  = ['width','height']
+    keep_only_tags     = [dict(attrs={'class':'content permalink'})]
+    remove_tags_before = dict(name='h1')
+    remove_tags        = [dict(attrs={'class':'contactinfo'})]
+    remove_tags_after  = dict(attrs={'class':'contactinfo'})
+
+    feeds = [(u'Articles', u'http://feeds.gawker.com/lifehacker/full')]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+