Updated LifeHacker

recipes/estadao.recipe

@@ -1,4 +1,3 @@
-#!/usr/bin/env  python
 from calibre.web.feeds.news import BasicNewsRecipe
 from datetime import datetime, timedelta
 from calibre.ebooks.BeautifulSoup import Tag,BeautifulSoup
@@ -6,18 +5,17 @@ from calibre.utils.magick import Image, PixelWand
 from urllib2 import Request, urlopen, URLError
 
 class Estadao(BasicNewsRecipe):
-    THUMBALIZR_API        = "0123456789abcdef01234567890" # ---->Get your at http://www.thumbalizr.com/
+    THUMBALIZR_API        = '' # ---->Get your at http://www.thumbalizr.com/ and put here
     LANGUAGE              = 'pt_br'
     language = 'pt'
     LANGHTM               = 'pt-br'
     ENCODING              = 'utf'
     ENCHTM                = 'utf-8'
     directionhtm          = 'ltr'
-    requires_version      = (0,8,47)
+    requires_version      = (0,7,47)
     news                  = True
-    publication_type      = 'newsportal'
 
-    title                 = u'Estadao'
+    title                 = u'Estad\xe3o'
     __author__            = 'Euler Alves'
     description           = u'Brazilian news from Estad\xe3o'
     publisher             = u'Estad\xe3o'
@@ -33,14 +31,6 @@ class Estadao(BasicNewsRecipe):
     remove_empty_feeds    = True
     timefmt               = ' [%d %b %Y (%a)]'
 
-    html2lrf_options      = [
-                            '--comment', description
-                            ,'--category', category
-                            ,'--publisher', publisher
-    ]
-
-    html2epub_options     = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
-
     hoje                  = datetime.now()-timedelta(days=2)
     pubdate               = hoje.strftime('%a, %d %b')
     if hoje.hour<10:
@@ -69,6 +59,7 @@ class Estadao(BasicNewsRecipe):
                     ,dict(name='script')
     ]
 
+
     feeds = [
     (u'\xDAltimas Not\xEDcias', u'http://www.estadao.com.br/rss/ultimas.xml')
     ,(u'Manchetes', u'http://www.estadao.com.br/rss/manchetes.xml')
@@ -109,6 +100,8 @@ class Estadao(BasicNewsRecipe):
             img.open(iurl)
             width, height = img.size
             print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
+            if img < 0:
+                raise RuntimeError('Out of memory')
             pw = PixelWand()
             if( width > height and width > 590) :
                 print 'Rotate image'
@@ -117,6 +110,7 @@ class Estadao(BasicNewsRecipe):
         return soup
 
     def get_cover_url(self):
+        if self.THUMBALIZR_API:
             cover_url      = self.CAPA
             pedido         = Request(self.CAPA)
             pedido.add_header('User-agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; '+self.LANGHTM+'; userid='+self.THUMBALIZR_API+') Calibre/0.8.47 (like Gecko)')
@@ -132,3 +126,4 @@ class Estadao(BasicNewsRecipe):
             except URLError:
                 cover_url='http://api.thumbalizr.com/?api_key='+self.THUMBALIZR_API+'&url='+self.SCREENSHOT+'&width=600&quality=90'
                 return cover_url
+

recipes/folhadesaopaulo.recipe

@@ -5,16 +5,15 @@ from calibre.utils.magick import Image, PixelWand
 from urllib2 import Request, urlopen, URLError
 
 class FolhaOnline(BasicNewsRecipe):
-    THUMBALIZR_API        = "0123456789abcdef01234567890" # ---->Get your at http://www.thumbalizr.com/
+    THUMBALIZR_API        = '' # ---->Get your at http://www.thumbalizr.com/ and put here
     LANGUAGE              = 'pt_br'
     language = 'pt'
     LANGHTM               = 'pt-br'
     ENCODING              = 'cp1252'
     ENCHTM                = 'iso-8859-1'
     directionhtm          = 'ltr'
-    requires_version      = (0,8,47)
+    requires_version      = (0,7,47)
     news                  = True
-    publication_type      = 'newsportal'
 
     title                 = u'Folha de S\xE3o Paulo'
     __author__            = 'Euler Alves'
@@ -96,6 +95,7 @@ class FolhaOnline(BasicNewsRecipe):
     ,(u'Valdo Cruz', u'http://http://feeds.folha.uol.com.br/folha/pensata/valdocruz/rss091.xml')
     ]
 
+
     conversion_options = {
     'title'            : title
     ,'comments'        : description
@@ -124,6 +124,8 @@ class FolhaOnline(BasicNewsRecipe):
             img.open(iurl)
             width, height = img.size
             print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
+            if img < 0:
+                raise RuntimeError('Out of memory')
             pw = PixelWand()
             if( width > height and width > 590) :
                 print 'Rotate image'

recipes/lifehacker.recipe

@@ -1,37 +1,100 @@
-__license__   = 'GPL v3'
-__copyright__ = '2010, NA'
-'''
-lifehacker.com
-'''
-
 from calibre.web.feeds.news import BasicNewsRecipe
+from datetime import datetime
+from calibre.ebooks.BeautifulSoup import Tag
+from calibre.utils.magick import Image, PixelWand
 
-class Lifehacker(BasicNewsRecipe):
+class LifeHacker(BasicNewsRecipe):
-    title                 = 'Lifehacker'
+    THUMBALIZR_API        = '' # ---->Get your at http://www.thumbalizr.com/ and put here
-    __author__            = 'Kovid Goyal'
+    LANGUAGE              = 'en'
-    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."
+    LANGHTM               = 'en'
-    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  = True
     language = 'en'
+    ENCODING              = 'utf'
+    ENCHTM                = 'utf-8'
+    requires_version      = (0,7,47)
+    news                  = True
+
+    title                 = u'LifeHacker'
+    __author__            = 'Euler Alves'
+    description           = u'Tips, tricks, and downloads for getting things done.'
+    publisher             = u'lifehacker.com'
+    author                = u'Adam Pash & Kevin Purdy & Adam Dachis & Whitson Gordon & Gina Trapani'
+    category              = 'news, rss'
+
+    oldest_article        = 4
+    max_articles_per_feed = 20
+    summary_length        = 1000
+
+    remove_javascript     = True
+    no_stylesheets        = True
+    use_embedded_content  = True
+    remove_empty_feeds    = True
+    timefmt               = ' [%d %b %Y (%a)]'
+
+    hoje                  = datetime.now()
+    pubdate               = hoje.strftime('%a, %d %b')
+    cover_url             = 'http://api.thumbalizr.com/?api_key='+THUMBALIZR_API+'&url=http://lifehacker.com&width=600&quality=90'
+    cover_margins         = (0,0,'white')
     masthead_url          = 'http://cache.gawkerassets.com/assets/lifehacker.com/img/logo.png'
-    conversion_options = {
-                          'comment'   : description
-                        , 'tags'      : category
-                        , 'publisher' : publisher
-                        , 'language'  : language
-                        }
 
     remove_tags = [
                     {'class': 'feedflare'},
+                    dict(name='div',
+                        attrs={'class':[
+                            'ad_container'
+                            ,'ad_300x250'
+                            ,'ad_interstitial'
+                            ,'share-wrap'
+                            ,'ad_300x600'
+                            ,'ad_perma-footer-adsense'
+                            ,'ad_perma-panorama'
+                            ,'ad panorama'
+                            ,'ad_container'
+                        ]})
+                    ,dict(name='div',
+                        attrs={'id':[
+                            'agegate_container'
+                            ,'agegate_container_rejected'
+                            ,'sharemenu-wrap'
+                        ]})
     ]
 
     feeds = [(u'Articles', u'http://feeds.gawker.com/lifehacker/vip?format=xml')]
 
-    def preprocess_html(self, soup):
+    conversion_options = {
-        return self.adeify_images(soup)
+    'title'            : title
+    ,'comments'        : description
+    ,'publisher'       : publisher
+    ,'tags'            : category
+    ,'language'        : LANGUAGE
+    ,'linearize_tables': True
+    }
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        if not soup.find(attrs={'http-equiv':'Content-Language'}):
+            meta0 = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.LANGHTM)])
+            soup.head.insert(0,meta0)
+        if not soup.find(attrs={'http-equiv':'Content-Type'}):
+            meta1 = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset="+self.ENCHTM)])
+            soup.head.insert(0,meta1)
+        return soup
+
+    def postprocess_html(self, soup, first):
+        #process all the images. assumes that the new html has the correct path
+        for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
+            iurl = tag['src']
+            img = Image()
+            img.open(iurl)
+            width, height = img.size
+            print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
+            if img < 0:
+                raise RuntimeError('Out of memory')
+            pw = PixelWand()
+            if( width > height and width > 590) :
+                print 'Rotate image'
+                img.rotate(pw, -90)
+                img.save(iurl)
+        return soup
+