Merge from trunk

resources/recipes/7seri.recipe

@@ -0,0 +1,51 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+sapteseri.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class SapteSeri(BasicNewsRecipe):
+    title                 = u'Sapte Seri'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'Sapte Seri'
+    publisher             = u'Sapte Seri'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Oras,Distractie,Fun'
+    encoding              = 'utf-8'
+    remove_empty_feeds    = True
+    remove_javascript     = True
+    cover_url             = 'http://www.sapteseri.ro/Images/logo.jpg'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+                          dict(name='h1', attrs={'id':'title'})
+                        , dict(name='div', attrs={'class':'mt10 mb10'})
+                        , dict(name='div', attrs={'class':'mb20 mt10'})
+                        , dict(name='div', attrs={'class':'mt5 mb20'})
+                     ]
+
+    remove_tags = [
+                    dict(name='div', attrs={'id':['entityimgworking']})
+                   ]
+
+    feeds          = [
+                        (u'Ce se intampla azi in Bucuresti', u'http://www.sapteseri.ro/ro/feed/ce-se-intampla-azi/bucuresti/')
+                    ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/aventurilapescuit.recipe

@@ -0,0 +1,51 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+aventurilapescuit.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AventuriLaPescuit(BasicNewsRecipe):
+    title                 = u'Aventuri La Pescuit'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = 'Aventuri La Pescuit'
+    publisher             = 'Aventuri La Pescuit'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Pescuit,Hobby'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.aventurilapescuit.ro/images/logo.gif'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+               ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+            dict(name='div', attrs={'id':'Article'})
+                     ]
+
+    remove_tags = [
+               dict(name='div', attrs={'class':['right option']})
+             , dict(name='iframe', attrs={'scrolling':['no']})
+                  ]
+
+    remove_tags_after = [
+             dict(name='iframe', attrs={'scrolling':['no']})
+           ]
+
+    feeds          = [
+            (u'Feeds', u'http://www.aventurilapescuit.ro/sections/rssread/1')
+                 ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/chipro.recipe

@@ -0,0 +1,52 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+chip.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class ChipRo(BasicNewsRecipe):
+    title                       = u'Chip Online'
+    __author__                  = u'Silviu Cotoar\u0103'
+    description                 = 'Chip Online'
+    publisher                   = 'Chip Online'
+    oldest_article              = 5
+    language                    = 'ro'
+    max_articles_per_feed   = 100
+    no_stylesheets              = True
+    use_embedded_content    = False
+    category                    = 'Ziare,Reviste,IT'
+    encoding                    = 'utf-8'
+    cover_url       = 'http://www.chip.ro/images/logo.png'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                           ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+                          dict(name='h2', attrs={'class':'contentheading clearfix'})
+                        , dict(name='span', attrs={'class':'createby'})
+                        , dict(name='div', attrs={'class':'article-content'})
+                               ]
+
+    remove_tags = [
+                       dict(name='div', attrs={'class':['sharemecompactbutton']})
+                     ,dict(name='div', attrs={'align':['left']})
+                     ,dict(name='div', attrs={'align':['center']})
+                     ,dict(name='th', attrs={'class':['pagenav_prev']})
+                     ,dict(name='table', attrs={'class':['pagenav']})
+                           ]
+
+    feeds          = [
+        (u'Feeds', u'http://www.chip.ro/index.php?option=com_ninjarsssyndicator&feed_id=9&format=raw')
+             ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/csid.recipe

@@ -0,0 +1,52 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+csid.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class CSID(BasicNewsRecipe):
+    title                 = u'Ce se \u00eent\u00e2mpl\u0103 doctore?'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'Ce se \u00eent\u00e2mpl\u0103 doctore?'
+    publisher             = 'CSID'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Reviste,Femei,Health,Beauty'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.csid.ro/images/default/csid.gif'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+          dict(name='div', attrs={'class':'content floatleft'})
+                               ]
+
+    remove_tags = [
+             dict(name='div', attrs={'id':['article_links']})
+           , dict(name='div', attrs={'id':['tags']})
+           , dict(name='p', attrs={'id':['tags']})
+                           ]
+
+    remove_tags_after = [
+             dict(name='p', attrs={'id':['tags']})
+           ]
+
+    feeds          = [
+            (u'Feeds', u'http://www.csid.ro/rss/')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/curierulnational.recipe

@@ -0,0 +1,54 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+curierulnational.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class CurierulNal(BasicNewsRecipe):
+    title                 = u'Curierul Na\u0163ional'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = ''
+    publisher             = 'Curierul Na\u0163ional'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Stiri'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.curierulnational.ro/logo.gif'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+            dict(name='div', attrs={'id':'col1'})
+            , dict(name='img', attrs={'id':'placeholder'})
+                     ]
+
+    remove_tags = [
+             dict(name='p', attrs={'id':['alteArticole']})
+           , dict(name='div', attrs={'id':['textSize']})
+           , dict(name='ul', attrs={'class':['unit-rating']})
+           , dict(name='div', attrs={'id':['comments']})
+                  ]
+
+    remove_tags_after = [
+              dict(name='ul', attrs={'class':'unit-rating'})
+            ]
+
+    feeds          = [
+            (u'Feeds', u'http://www.curierulnational.ro/feed.xml')
+                 ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/descopera.recipe

@@ -0,0 +1,57 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+descopera.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Descopera(BasicNewsRecipe):
+    title                       = u'Descoper\u0103'
+    __author__          = u'Silviu Cotoar\u0103'
+    description             = 'E lumea ta'
+    publisher                   = 'Descopera'
+    oldest_article              = 5
+    language                    = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets          = True
+    use_embedded_content  = False
+    category                  = 'Ziare,Reviste,Descopera'
+    encoding                = 'utf-8'
+    cover_url     = 'http://www.descopera.ro/images/header_images/logo.gif'
+
+    conversion_options = {
+                             'comments'  : description
+                            ,'tags'           : category
+                            ,'language'    : language
+                ,'publisher'   : publisher
+                         }
+
+
+    keep_only_tags = [
+        dict(name='h1', attrs={'style':'font-family: Arial,Helvetica,sans-serif; font-size: 18px; color: rgb(51, 51, 51); font-weight: bold; margin: 10px 0pt; clear: both; float: left;width: 610px;'})
+        ,dict(name='div', attrs={'style':'margin-right: 15px; margin-bottom: 15px; float: left;'})
+        , dict(name='p', attrs={'id':'itemDescription'})
+        ,dict(name='div', attrs={'id':'itemBody'})
+                 ]
+
+    remove_tags = [
+             dict(name='div', attrs={'class':['tools']})
+           , dict(name='div', attrs={'class':['share']})
+           , dict(name='div', attrs={'class':['category']})
+           , dict(name='div', attrs={'id':['comments']})
+                          ]
+
+    remove_tags_after = [
+               dict(name='div', attrs={'id':'comments'})
+           ]
+
+    feeds          = [
+        (u'Feeds', u'http://www.descopera.ro/rss')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/ecuisine.recipe

@@ -0,0 +1,55 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+ecuisine.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class EcuisineRo(BasicNewsRecipe):
+    title                 = u'eCuisine'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'Reinventeaz\u0103 pl\u0103cerea de a g\u0103ti'
+    publisher             = 'eCuisine'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Retete,Bucatarie'
+    encoding              = 'utf-8'
+    cover_url             = ''
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+            dict(name='div', attrs={'class':'page-title'})
+            , dict(name='div', attrs={'class':'content clearfix'})
+                     ]
+
+    remove_tags = [
+             dict(name='ul', attrs={'id':['recipe-tabs']})
+           , dict(name='div', attrs={'class':['recipe-body-rating clearfix']})
+           , dict(name='div', attrs={'class':['recipe-body-flags']})
+           , dict(name='div', attrs={'id':['tweetmeme_button']})
+           , dict(name='div', attrs={'class':['fbshare']})
+           , dict(name='a', attrs={'class':['button-rounded']})
+           , dict(name='div', attrs={'class':['recipe-body-related']})
+           , dict(name='div', attrs={'class':['fbshare']})
+           , dict(name='div', attrs={'class':['link-wrapper']})
+                  ]
+
+    feeds          = [
+            (u'Feeds', u'http://www.ecuisine.ro/rss')
+                 ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/egirl.recipe

@@ -0,0 +1,43 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+egirl.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class EgirlRo(BasicNewsRecipe):
+    title                 = u'egirl'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'Necesar pentru tine'
+    publisher             = u'egirl'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Reviste,Femei'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.egirl.ro/images/egirlNou/logo_egirl.gif'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+                          dict(name='div', attrs={'id':'title_art'})
+                        , dict(name='div', attrs={'class':'content_style'})
+                     ]
+
+    feeds          = [
+                        (u'Feeds', u'http://www.egirl.ro/rss/egirl.xml')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/fhmro.recipe

@@ -0,0 +1,53 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+fhm.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class FHMro(BasicNewsRecipe):
+    title                 = u'FHM Ro'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'Pentru c\u0103 noi putem'
+    publisher             = 'FHM'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Reviste'
+    encoding              = 'utf-8'
+    cover_url         = 'http://www.fhm.com/App_Resources/Images/Site/re-design/logo.gif'
+
+    conversion_options = {
+                              'comments'   : description
+                             ,'tags'       : category
+                             ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+                          dict(name='div', attrs={'class':'contentMainTitle'})
+                        , dict(name='div', attrs={'class':'entry'})
+                               ]
+
+    remove_tags_after = [
+                          dict(name='div', attrs={'class':['ratingblock ']})
+                        , dict(name='a', attrs={'rel':['tag']})
+        ]
+
+    remove_tags = [
+                      dict(name='div', attrs={'class':['ratingblock ']})
+                    , dict(name='div', attrs={'class':['socialize-containter']})
+                  ]
+
+    feeds         = [
+                        (u'Feeds', u'http://www.fhm.ro/feed')
+                    ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/go4it.recipe

@@ -0,0 +1,48 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+go4it.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Go4ITro(BasicNewsRecipe):
+    title                           = u'go4it'
+    __author__              = u'Silviu Cotoar\u0103'
+    description                 = 'Gadgeturi, Lifestyle, Tehnologie'
+    publisher                   = 'go4it'
+    oldest_article              = 5
+    language                    = 'ro'
+    max_articles_per_feed   = 100
+    no_stylesheets          = True
+    use_embedded_content        = False
+    category                                = 'Reviste,Ziare,IT'
+    encoding                               = 'utf-8'
+    cover_url                  = 'http://www.go4it.ro/images/logo.png'
+
+    conversion_options = {
+                                  'comments'   : description
+                                 ,'tags'       : category
+                                 ,'language'   : language
+                     ,'publisher'  : publisher
+                                     }
+
+    keep_only_tags = [
+              dict(name='div', attrs={'class':'subTitle clearfix'})
+            , dict(name='div', attrs={'class':'story'})
+                               ]
+
+    remove_tags = [
+             dict(name='span', attrs={'class':['data']})
+           , dict(name='a', attrs={'class':['comments']})
+                           ]
+
+    feeds          = [
+           (u'Feeds', u'http://feeds2.feedburner.com/Go4itro-Stiri')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/hotcity.recipe

@@ -0,0 +1,43 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+hotcity.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class HotcityRo(BasicNewsRecipe):
+    title                         = u'Hotcity'
+    __author__                    = u'Silviu Cotoar\u0103'
+    description                   = u'Cultura urban\u0103 feminin\u0103'
+    publisher                     = 'Hotcity'
+    oldest_article            = 5
+    language                     = 'ro'
+    max_articles_per_feed    = 100
+    no_stylesheets           = True
+    use_embedded_content     = False
+    category                 = 'Ziare,Reviste'
+    encoding                     = 'utf-8'
+    cover_url        = 'http://www.hotcity.ro/i/bg_header.gif'
+
+    conversion_options = {
+                                  'comments'   : description
+                                 ,'tags'       : category
+                                 ,'language'   : language
+             ,'publisher'  : publisher
+                                      }
+
+    keep_only_tags = [
+              dict(name='div', attrs={'class':'articol_title'})
+                , dict(name='div', attrs={'class':'text'})
+                               ]
+
+    feeds          =      [
+            (u'Feeds', u'http://www.hotcity.ro/rss')
+                          ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/intrefete.recipe

@@ -0,0 +1,52 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+intrefete.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Intrefete(BasicNewsRecipe):
+    title                    = u'\u00centre fete'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'Petrece ziua cu stil, afl\u0103 ce e nou \u00eentre fete'
+    publisher             = u'Intre fete'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Reviste,Femei'
+    encoding              = 'utf-8'
+    cover_url            = 'http://storage0.dms.mpinteractiv.ro/media/2/1401/16788/5878693/5/logo.jpg?width=300'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+            dict(name='div', attrs={'class':'article'})
+                               ]
+
+    remove_tags = [
+             dict(name='div', attrs={'class':['author']})
+           , dict(name='div', attrs={'class':['tags']})
+           , dict(name='iframe', attrs={'scrolling':['no']})
+                           ]
+
+    remove_tags_after = [
+              dict(name='iframe', attrs={'scrolling':['no']})
+            ]
+
+    feeds          = [
+        (u'Feeds', u'http://www.intrefete.ro/rss/')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/kudika.recipe

@@ -0,0 +1,47 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+kudika.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Kudika(BasicNewsRecipe):
+    title                  = u'Kudika'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'Revist\u0103 pentru femei'
+    publisher             = 'Kudika'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Reviste,Femei'
+    encoding              = 'utf-8'
+    cover_url             = 'http://img.kudika.ro/images/template/page-logo.png'
+
+    conversion_options = {
+                                              'comments'   : description
+                                 ,'tags'       : category
+                                ,'language'   : language
+                    ,'publisher'  : publisher
+                          }
+
+    keep_only_tags = [
+         dict(name='div', attrs={'class':'header_recommend_article'}),
+                     dict(name='div', attrs={'id':'intertext_women'})
+                   ]
+
+    remove_tags = [
+        dict(name='p', attrs={'class':['page_breadcrumbs']})
+        , dict(name='div', attrs={'class':['standard']})
+        , dict(name='div', attrs={'id':['recommend_allover']})
+                           ]
+
+    feeds          = [ (u'Feeds', u'http://www.kudika.ro/feed.xml')  ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/nationalgeoro.recipe

@@ -0,0 +1,48 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+natgeo.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class NationalGeoRo(BasicNewsRecipe):
+    title                 = u'National Geographic RO'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'S\u0103 avem grij\u0103 de planet\u0103'
+    publisher             = 'National Geographic'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Reviste'
+    encoding              = 'utf-8'
+    cover_url             = 'http://wiki.benecke.com/images/c/c4/NatGeographic_Logo.jpg'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+                 dict(name='h2', attrs={'class':'contentheading clearfix'})
+                , dict(name='div', attrs={'class':'article-content'})
+
+                     ]
+
+    remove_tags = [
+                    dict(name='div', attrs={'class':['phocagallery']})
+                  ]
+
+    feeds          = [
+            (u'Feeds', u'http://www.natgeo.ro/index.php?format=feed&type=rss')
+                 ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/romanialibera.recipe

@@ -0,0 +1,59 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+romanialibera.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class RomaniaLibera(BasicNewsRecipe):
+    title                 = u'Rom\u00e2nia Liber\u0103'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'Rom\u00e2nia Liber\u0103'
+    publisher             = u'Rom\u00e2nia Liber\u0103'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Stiri'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.romanialibera.ro/templates/lilac/images/sigla_1.gif'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+            dict(name='div', attrs={'id':'articol'})
+                     ]
+
+    remove_tags = [
+             dict(name='div', attrs={'id':['art_actions']})
+           , dict(name='div', attrs={'class':['stats']})
+           , dict(name='div', attrs={'class':['data']})
+            , dict(name='div', attrs={'class':['autori']})
+            , dict(name='div', attrs={'class':['banda_explicatii_text']})
+           , dict(name='td', attrs={'class':['connect_widget_vertical_center connect_widget_button_cell']})
+           , dict(name='div', attrs={'class':['aceeasi_tema']})
+           , dict(name='div', attrs={'class':['art_after_text']})
+           , dict(name='div', attrs={'class':['navigare']})
+            , dict(name='div', attrs={'id':['art_text_left']})
+                           ]
+
+    remove_tags_after = [
+              dict(name='div', attrs={'class':'art_after_text'})
+            ]
+
+    feeds          = [
+            (u'Feeds', u'http://www.romanialibera.ro/rss.xml')
+                 ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/sfin.recipe

@@ -0,0 +1,55 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+sfin.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Sfin(BasicNewsRecipe):
+    title                 = u'S\u0103pt\u0103m\u00e2na Financiar\u0103'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = 'SFIN'
+    publisher             = 'SFIN'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Stiri,Economie,Business'
+    encoding              = 'utf-8'
+    cover_url             = 'http://img.9am.ro/images/logo_surse/saptamana_financiara.gif'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+                    dict(name='div', attrs={'class':'col2ContentLeft'})
+                    , dict(name='div', attrs={'id':'contentArticol'})
+                     ]
+
+    remove_tags = [
+             dict(name='div', attrs={'class':['infoArticol']})
+           , dict(name='div', attrs={'class':['separator']})
+           , dict(name='div', attrs={'class':['tags']})
+           , dict(name='div', attrs={'id':['comments']})
+           , dict(name='div', attrs={'class':'boxForm'})
+                  ]
+
+    remove_tags_after = [
+              dict(name='div', attrs={'class':'tags'})
+            ]
+
+    feeds          = [
+            (u'Feeds', u'http://www.sfin.ro/rss')
+                 ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/superbebe.recipe

@@ -0,0 +1,51 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+superbebe.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Superbebe(BasicNewsRecipe):
+    title                 = u'Superbebe'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = 'Superbebe'
+    publisher             = 'Superbebe'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Reviste,Bebe,Mamici'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.superbebe.ro/images/superbebe.gif'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+            dict(name='div', attrs={'class':'articol'})
+                     ]
+
+    remove_tags = [
+             dict(name='div', attrs={'class':['info']})
+            , dict(name='div', attrs={'class':['tags']})
+                  ]
+
+    remove_tags_after = [
+             dict(name='div', attrs={'class':['tags']})
+            ]
+
+    feeds          = [
+            (u'Feeds', u'http://www.superbebe.ro/rss')
+                 ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/swiatkindle.recipe

@@ -8,6 +8,8 @@ swiatkindle.pl
 
 import re
 
+from calibre.web.feeds.news import BasicNewsRecipe
+
 class swiatkindle(BasicNewsRecipe):
     title          = u'Swiat Kindle'
     description    = u'Blog o czytniku Amazon Kindle. Wersje, ksi\u0105\u017cki, kupowanie i korzystanie w Polsce'

resources/recipes/tabu.recipe

@@ -0,0 +1,54 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+tabu.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class TabuRo(BasicNewsRecipe):
+    title                 = u'Tabu'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = 'Cel mai curajos site de femei'
+    publisher             = 'Tabu'
+    oldest_article        = 5
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Reviste,Femei'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.tabu.ro/img/tabu-logo2.png'
+
+    conversion_options = {
+                                     'comments'   : description
+                                  ,'tags'       : category
+                                 ,'language'   : language
+                      ,'publisher'  : publisher
+                                 }
+
+    keep_only_tags = [
+           dict(name='div', attrs={'id':'Article'}),
+                              ]
+
+    remove_tags = [
+            dict(name='div', attrs={'id':['advertisementArticle']}),
+                        dict(name='div', attrs={'class':'voting_number'}),
+            dict(name='div', attrs={'id':'number_votes'}),
+            dict(name='div', attrs={'id':'rating_one'}),
+            dict(name='div', attrs={'class':'float: right;'})
+                           ]
+
+    remove_tags_after = [
+                      dict(name='div', attrs={'id':'comments'}),
+           ]
+
+    feeds          = [
+        (u'Feeds', u'http://www.tabu.ro/rss_all.xml')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/unica.recipe

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+unica.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Unica(BasicNewsRecipe):
+    title                     = u'Unica'
+    __author__             = u'Silviu Cotoar\u0103'
+    description               = 'Asa cum esti tu'
+    publisher                 = 'Unica'
+    oldest_article            = 5
+    language                 = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category               = 'Ziare,Reviste,Femei'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.unica.ro/fileadmin/images/logo.gif'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+             dict(name='div', attrs={'id':'sticky'})
+            , dict(name='p', attrs={'class':'bodytext'})
+
+                     ]
+
+    remove_tags = [
+             dict(name='div', attrs={'class':['top-links']})
+           , dict(name='div', attrs={'id':['autor_name']})
+           , dict(name='div', attrs={'class':['box-r']})
+           , dict(name='div', attrs={'class':['category']})
+           , dict(name='div', attrs={'class':['data']})
+                  ]
+
+    remove_tags_after = [
+             dict(name='ul', attrs={'class':'pager'})
+            ]
+
+    feeds          = [
+        (u'Feeds', u'http://www.unica.ro/rss.html')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

src/calibre/ebooks/conversion/utils.py

@@ -33,7 +33,7 @@ class HeuristicProcessor(object):
         self.any_multi_blank = re.compile(r'(\s*<p[^>]*>\s*</p>(\s*<div[^>]*>\s*</div>\s*)*){2,}', re.IGNORECASE)
         self.line_open = "<(?P<outer>p|div)[^>]*>\s*(<(?P<inner1>font|span|[ibu])[^>]*>)?\s*(<(?P<inner2>font|span|[ibu])[^>]*>)?\s*(<(?P<inner3>font|span|[ibu])[^>]*>)?\s*"
         self.line_close = "(</(?P=inner3)>)?\s*(</(?P=inner2)>)?\s*(</(?P=inner1)>)?\s*</(?P=outer)>"
-        self.single_blank = re.compile(r'(\s*<p[^>]*>\s*</p>)', re.IGNORECASE)
+        self.single_blank = re.compile(r'(\s*<(p|div)[^>]*>\s*</(p|div)>)', re.IGNORECASE)
         self.scene_break_open = '<p class="scenebreak" style="text-align:center; text-indent:0%; margin-top:1em; margin-bottom:1em; page-break-before:avoid">'
         self.common_in_text_endings = u'[\"\'—’”,\.!\?\…\)„\w]'
         self.common_in_text_beginnings = u'[\w\'\"“‘‛]'
@@ -451,8 +451,8 @@ class HeuristicProcessor(object):
         return html
 
     def detect_whitespace(self, html):
-        blanks_around_headings = re.compile(r'(?P<initparas>(<p[^>]*>\s*</p>\s*){1,}\s*)?(?P<heading><h(?P<hnum>\d+)[^>]*>.*?</h(?P=hnum)>)(?P<endparas>\s*(<p[^>]*>\s*</p>\s*){1,})?', re.IGNORECASE)
-        blanks_n_nopunct = re.compile(r'(?P<initparas>(<p[^>]*>\s*</p>\s*){1,}\s*)?<p[^>]*>\s*(<(span|[ibu]|em|strong|font)[^>]*>\s*)*.{1,100}?[^\W](</(span|[ibu]|em|strong|font)>\s*)*</p>(?P<endparas>\s*(<p[^>]*>\s*</p>\s*){1,})?', re.IGNORECASE)
+        blanks_around_headings = re.compile(r'(?P<initparas>(<(p|div)[^>]*>\s*</(p|div)>\s*){1,}\s*)?(?P<heading><h(?P<hnum>\d+)[^>]*>.*?</h(?P=hnum)>)(?P<endparas>\s*(<(p|div)[^>]*>\s*</(p|div)>\s*){1,})?', re.IGNORECASE|re.DOTALL)
+        blanks_n_nopunct = re.compile(r'(?P<initparas>(<p[^>]*>\s*</p>\s*){1,}\s*)?<p[^>]*>\s*(<(span|[ibu]|em|strong|font)[^>]*>\s*)*.{1,100}?[^\W](</(span|[ibu]|em|strong|font)>\s*)*</p>(?P<endparas>\s*(<p[^>]*>\s*</p>\s*){1,})?', re.IGNORECASE|re.DOTALL)
 
         def merge_header_whitespace(match):
             initblanks = match.group('initparas')
@@ -485,6 +485,21 @@ class HeuristicProcessor(object):
         return html
 
     def detect_soft_breaks(self, html):
+        line = '(?P<initline>'+self.line_open+'\s*(?P<init_content>.*?)'+self.line_close+')'
+        line_two = '(?P<line_two>'+re.sub('(ou|in|cha)', 'linetwo_', self.line_open)+'\s*(?P<line_two_content>.*?)'+re.sub('(ou|in|cha)', 'linetwo_', self.line_close)+')'
+        div_break_candidate_pattern = line+'\s*<div[^>]*>\s*</div>\s*'+line_two
+        div_break_candidate = re.compile(r'%s' % div_break_candidate_pattern, re.IGNORECASE|re.UNICODE)
+
+        def convert_div_softbreaks(match):
+            init_is_paragraph = self.check_paragraph(match.group('init_content'))
+            line_two_is_paragraph = self.check_paragraph(match.group('line_two_content'))
+            if init_is_paragraph and line_two_is_paragraph:
+                return match.group('initline')+'\n<p class="softbreak" style="margin-top:.5em; page-break-before:avoid; text-align:center"> </p>\n'+match.group('line_two')
+            else:
+                return match.group(0)
+
+        html = div_break_candidate.sub(convert_div_softbreaks, html)
+
         if not self.blanks_deleted and self.blanks_between_paragraphs:
             html = self.multi_blank.sub('\n<p class="softbreak" style="margin-top:1em; page-break-before:avoid; text-align:center"> </p>', html)
         else:
@@ -523,6 +538,14 @@ class HeuristicProcessor(object):
 
         return scene_break
 
+    def check_paragraph(self, content):
+        content = re.sub('\s*</?span[^>]*>\s*', '', content)
+        if re.match('.*[\"\'.!?:]$', content):
+            #print "detected this as a paragraph"
+            return True
+        else:
+            return False
+
     def abbyy_processor(self, html):
         abbyy_line = re.compile('((?P<linestart><p\sstyle="(?P<styles>[^\"]*?);?">)(?P<content>.*?)(?P<lineend></p>)|(?P<image><img[^>]*>))', re.IGNORECASE)
         empty_paragraph = '\n<p> </p>\n'
@@ -530,14 +553,6 @@ class HeuristicProcessor(object):
         self.previous_was_paragraph = False
         html = re.sub('</?a[^>]*>', '', html)
 
-        def check_paragraph(content):
-            content = re.sub('\s*</?span[^>]*>\s*', '', content)
-            if re.match('.*[\"\'.!?:]$', content):
-                #print "detected this as a paragraph"
-                return True
-            else:
-                return False
-
         def convert_styles(match):
             #print "raw styles are: "+match.group('styles')
             content = match.group('content')
@@ -565,7 +580,7 @@ class HeuristicProcessor(object):
                 return blockquote_close_loop+'\n'+image+'\n'
             else:
                 styles = match.group('styles').split(';')
-                is_paragraph = check_paragraph(content)
+                is_paragraph = self.check_paragraph(content)
                 #print "styles for this line are: "+str(styles)
                 split_styles = []
                 for style in styles:

src/calibre/ebooks/mobi/reader.py

@@ -485,8 +485,8 @@ class MobiReader(object):
         # - lxml and beautifulsoup expect/assume a specific order based on xhtml spec
         self.processed_html = re.sub(r'(?i)(?P<styletags>(<(h\d+|i|b|u|em|small|big|strong|tt)>\s*){1,})(?P<para><p[^>]*>)', '\g<para>'+'\g<styletags>', self.processed_html)
         self.processed_html = re.sub(r'(?i)(?P<para></p[^>]*>)\s*(?P<styletags>(</(h\d+|i|b|u|em|small|big|strong|tt)>\s*){1,})', '\g<styletags>'+'\g<para>', self.processed_html)
-        self.processed_html = re.sub(r'(?i)(?P<blockquote>(</blockquote[^>]*>\s*){1,})(?P<para></p[^>]*>)', '\g<para>'+'\g<blockquote>', self.processed_html)
-        self.processed_html = re.sub(r'(?i)(?P<para><p[^>]*>)\s*(?P<blockquote>(<blockquote[^>]*>\s*){1,})', '\g<blockquote>'+'\g<para>', self.processed_html)
+        self.processed_html = re.sub(r'(?i)(?P<blockquote>(</(blockquote|div)[^>]*>\s*){1,})(?P<para></p[^>]*>)', '\g<para>'+'\g<blockquote>', self.processed_html)
+        self.processed_html = re.sub(r'(?i)(?P<para><p[^>]*>)\s*(?P<blockquote>(<(blockquote|div)[^>]*>\s*){1,})', '\g<blockquote>'+'\g<para>', self.processed_html)
 
 
     def remove_random_bytes(self, html):

src/calibre/gui2/comments_editor.py

@@ -254,7 +254,8 @@ class EditorWidget(QWebView): # {{{
             f = QFontInfo(QApplication.font(self)).pixelSize()
             style = 'font-size: %dpx;' % (f,)
 
-            for body in self.page().mainFrame().documentElement().findAll('body'):
+            # toList() is needed because PyQt on Debian is old/broken
+            for body in self.page().mainFrame().documentElement().findAll('body').toList():
                 body.setAttribute('style', style)
             self.page().setContentEditable(True)