Sync to 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/ming_pao.recipe

@@ -1,7 +1,9 @@
 __license__   = 'GPL v3'
-__copyright__ = '2010, Eddie Lau'
+__copyright__ = '2010-2011, Eddie Lau'
 '''
 Change Log:
+2011/02/20: skip duplicated links in finance section, put photos which may extend a whole page to the back of the articles
+            clean up the indentation
 2010/12/07: add entertainment section, use newspaper front page as ebook cover, suppress date display in section list
             (to avoid wrong date display in case the user generates the ebook in a time zone different from HKT)
 2010/11/22: add English section, remove eco-news section which is not updated daily, correct
@@ -18,21 +20,21 @@ from calibre.web.feeds.recipes import BasicNewsRecipe
 from contextlib import nested
 
 
-from calibre import __appname__
 from calibre.ebooks.BeautifulSoup import BeautifulSoup
 from calibre.ebooks.metadata.opf2 import OPFCreator
 from calibre.ebooks.metadata.toc import TOC
 from calibre.ebooks.metadata import MetaInformation
 
 class MPHKRecipe(BasicNewsRecipe):
-    IsKindleUsed = True  # to avoid generating periodical in which CJK characters can't be displayed in section/article view
-
+    IsCJKWellSupported = True  # Set to False to avoid generating periodical in which CJK characters can't be displayed in section/article view
     title          = 'Ming Pao - Hong Kong'
     oldest_article = 1
     max_articles_per_feed = 100
     __author__            = 'Eddie Lau'
-    description           = 'Hong Kong Chinese Newspaper'
-    publisher             = 'news.mingpao.com'
+    description = ('Hong Kong Chinese Newspaper (http://news.mingpao.com). If'
+                  'you are using a Kindle with firmware < 3.1, customize the'
+                  'recipe')
+    publisher             = 'MingPao'
     category              = 'Chinese, News, Hong Kong'
     remove_javascript = True
     use_embedded_content   = False
@@ -46,19 +48,20 @@ class MPHKRecipe(BasicNewsRecipe):
     masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif'
     keep_only_tags = [dict(name='h1'),
                       dict(name='font', attrs={'style':['font-size:14pt; line-height:160%;']}), # for entertainment page title
-                      dict(attrs={'class':['photo']}),
                       dict(attrs={'id':['newscontent']}), # entertainment page content
-                      dict(attrs={'id':['newscontent01','newscontent02']})]
+                      dict(attrs={'id':['newscontent01','newscontent02']}),
+                      dict(attrs={'class':['photo']})
+                      ]
     remove_tags = [dict(name='style'),
                    dict(attrs={'id':['newscontent135']})]  # for the finance page
     remove_attributes = ['width']
     preprocess_regexps = [
-                            (re.compile(r'<h5>', re.DOTALL|re.IGNORECASE),
-                            lambda match: '<h1>'),
-                            (re.compile(r'</h5>', re.DOTALL|re.IGNORECASE),
-                            lambda match: '</h1>'),
-                            (re.compile(r'<p><a href=.+?</a></p>', re.DOTALL|re.IGNORECASE), # for entertainment page
-                            lambda match: '')
+                          (re.compile(r'<h5>', re.DOTALL|re.IGNORECASE),
+                          lambda match: '<h1>'),
+                          (re.compile(r'</h5>', re.DOTALL|re.IGNORECASE),
+                          lambda match: '</h1>'),
+                          (re.compile(r'<p><a href=.+?</a></p>', re.DOTALL|re.IGNORECASE), # for entertainment page
+                          lambda match: '')
                          ]
 
     def image_url_processor(cls, baseurl, url):
@@ -107,6 +110,9 @@ class MPHKRecipe(BasicNewsRecipe):
     def get_fetchdate(self):
         return self.get_dtlocal().strftime("%Y%m%d")
 
+    def get_fetchformatteddate(self):
+        return self.get_dtlocal().strftime("%Y-%m-%d")
+
     def get_fetchday(self):
         # convert UTC to local hk time - at around HKT 6.00am, all news are available
         return self.get_dtlocal().strftime("%d")
@@ -121,84 +127,66 @@ class MPHKRecipe(BasicNewsRecipe):
         return cover
 
     def parse_index(self):
-            feeds = []
-            dateStr = self.get_fetchdate()
-            for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'),
-                               (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm'),
-                               (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'),
-                               (u'\u793e\u8a55\u2027\u7b46\u9663 Editorial', 'http://news.mingpao.com/' + dateStr + '/mrindex.htm'),
-                               (u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'),
-                               (u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'),
-                               (u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm'),
-                               ('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'),
-                               (u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm'),
-                               (u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'),
-                               (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]:
-                articles = self.parse_section(url)
-                if articles:
-                    feeds.append((title, articles))
-            # special - finance
-            fin_articles = self.parse_fin_section('http://www.mpfinance.com/htm/Finance/' + dateStr + '/News/ea,eb,ecindex.htm')
-            if fin_articles:
-                feeds.append((u'\u7d93\u6fdf Finance', fin_articles))
-            # special - eco-friendly
-            # eco_articles = self.parse_eco_section('http://tssl.mingpao.com/htm/marketing/eco/cfm/Eco1.cfm')
-            # if eco_articles:
-            #   feeds.append((u'\u74b0\u4fdd Eco News', eco_articles))
-            # special - entertainment
-            ent_articles = self.parse_ent_section('http://ol.mingpao.com/cfm/star1.cfm')
-            if ent_articles:
-                feeds.append((u'\u5f71\u8996 Entertainment', ent_articles))
-            return feeds
+        feeds = []
+        dateStr = self.get_fetchdate()
+        for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'),
+                           (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'),
+                           (u'\u793e\u8a55/\u7b46\u9663 Editorial', 'http://news.mingpao.com/' + dateStr + '/mrindex.htm'),
+                           (u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'),
+                           (u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'),
+                           (u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm'),
+                           ('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'),
+                           (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm'),
+                           (u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm'),
+                           (u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'),
+                           (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]:
+            articles = self.parse_section(url)
+            if articles:
+                feeds.append((title, articles))
+        # special - finance
+        fin_articles = self.parse_fin_section('http://www.mpfinance.com/htm/Finance/' + dateStr + '/News/ea,eb,ecindex.htm')
+        if fin_articles:
+            feeds.append((u'\u7d93\u6fdf Finance', fin_articles))
+        # special - entertainment
+        ent_articles = self.parse_ent_section('http://ol.mingpao.com/cfm/star1.cfm')
+        if ent_articles:
+            feeds.append((u'\u5f71\u8996 Film/TV', ent_articles))
+        return feeds
 
     def parse_section(self, url):
-            dateStr = self.get_fetchdate()
-            soup = self.index_to_soup(url)
-            divs = soup.findAll(attrs={'class': ['bullet','bullet_grey']})
-            current_articles = []
-            included_urls = []
-            divs.reverse()
-            for i in divs:
-                a = i.find('a', href = True)
-                title = self.tag_to_string(a)
-                url = a.get('href', False)
-                url = 'http://news.mingpao.com/' + dateStr + '/' +url
-                if url not in included_urls and url.rfind('Redirect') == -1:
-                    current_articles.append({'title': title, 'url': url, 'description':'', 'date':''})
-                    included_urls.append(url)
-            current_articles.reverse()
-            return current_articles
+        dateStr = self.get_fetchdate()
+        soup = self.index_to_soup(url)
+        divs = soup.findAll(attrs={'class': ['bullet','bullet_grey']})
+        current_articles = []
+        included_urls = []
+        divs.reverse()
+        for i in divs:
+            a = i.find('a', href = True)
+            title = self.tag_to_string(a)
+            url = a.get('href', False)
+            url = 'http://news.mingpao.com/' + dateStr + '/' +url
+            if url not in included_urls and url.rfind('Redirect') == -1:
+                current_articles.append({'title': title, 'url': url, 'description':'', 'date':''})
+                included_urls.append(url)
+        current_articles.reverse()
+        return current_articles
 
     def parse_fin_section(self, url):
         dateStr = self.get_fetchdate()
         soup = self.index_to_soup(url)
         a = soup.findAll('a', href= True)
         current_articles = []
-        for i in a:
-            url = i.get('href', False)
-            if not url.rfind(dateStr) == -1 and url.rfind('index') == -1:
-                title = self.tag_to_string(i)
-                url = 'http://www.mpfinance.com/cfm/' +url
-                current_articles.append({'title': title, 'url': url, 'description':''})
-        return current_articles
-
-    def parse_eco_section(self, url):
-        dateStr = self.get_fetchdate()
-        soup = self.index_to_soup(url)
-        divs = soup.findAll(attrs={'class': ['bullet']})
-        current_articles = []
         included_urls = []
-        for i in divs:
-            a = i.find('a', href = True)
-            title = self.tag_to_string(a)
-            url = a.get('href', False)
-            url = 'http://tssl.mingpao.com/htm/marketing/eco/cfm/' +url
-            if url not in included_urls and url.rfind('Redirect') == -1 and not url.rfind('.txt') == -1 and not url.rfind(dateStr) == -1:
+        for i in a:
+            url = 'http://www.mpfinance.com/cfm/' + i.get('href', False)
+            if url not in included_urls and not url.rfind(dateStr) == -1 and url.rfind('index') == -1:
+                title = self.tag_to_string(i)
                 current_articles.append({'title': title, 'url': url, 'description':''})
                 included_urls.append(url)
         return current_articles
 
     def parse_ent_section(self, url):
+        self.get_fetchdate()
         soup = self.index_to_soup(url)
         a = soup.findAll('a', href=True)
         a.reverse()
@@ -223,67 +211,71 @@ class MPHKRecipe(BasicNewsRecipe):
         return soup
 
     def create_opf(self, feeds, dir=None):
-        if self.IsKindleUsed == False:
-            super(MPHKRecipe,self).create_opf(feeds, dir)
-            return
         if dir is None:
             dir = self.output_dir
-        title = self.short_title()
-        title += ' ' + self.get_fetchdate()
-        #if self.output_profile.periodical_date_in_title:
-        #    title += strftime(self.timefmt)
-        mi = MetaInformation(title, [__appname__])
-        mi.publisher = __appname__
-        mi.author_sort = __appname__
-        mi.publication_type = self.publication_type+':'+self.short_title()
-        #mi.timestamp = nowf()
-        mi.timestamp = self.get_dtlocal()
-        mi.comments = self.description
-        if not isinstance(mi.comments, unicode):
-            mi.comments = mi.comments.decode('utf-8', 'replace')
-        #mi.pubdate = nowf()
-        mi.pubdate = self.get_dtlocal()
-        opf_path = os.path.join(dir, 'index.opf')
-        ncx_path = os.path.join(dir, 'index.ncx')
-        opf = OPFCreator(dir, mi)
-        # Add mastheadImage entry to <guide> section
-        mp = getattr(self, 'masthead_path', None)
-        if mp is not None and os.access(mp, os.R_OK):
-            from calibre.ebooks.metadata.opf2 import Guide
-            ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu())
-            ref.type = 'masthead'
-            ref.title = 'Masthead Image'
-            opf.guide.append(ref)
+        if self.IsCJKWellSupported == True:
+            # use Chinese title
+            title = u'\u660e\u5831 (\u9999\u6e2f) ' + self.get_fetchformatteddate()
+        else:
+            # use English title
+            title = self.short_title() + ' ' + self.get_fetchformatteddate()
+        if True:  # force date in title
+            #    title += strftime(self.timefmt)
+            mi = MetaInformation(title, [self.publisher])
+            mi.publisher = self.publisher
+            mi.author_sort = self.publisher
+            if self.IsCJKWellSupported == True:
+                mi.publication_type = 'periodical:'+self.publication_type+':'+self.short_title()
+            else:
+                mi.publication_type = self.publication_type+':'+self.short_title()
+            #mi.timestamp = nowf()
+            mi.timestamp = self.get_dtlocal()
+            mi.comments = self.description
+            if not isinstance(mi.comments, unicode):
+                mi.comments = mi.comments.decode('utf-8', 'replace')
+            #mi.pubdate = nowf()
+            mi.pubdate = self.get_dtlocal()
+            opf_path = os.path.join(dir, 'index.opf')
+            ncx_path = os.path.join(dir, 'index.ncx')
+            opf = OPFCreator(dir, mi)
+            # Add mastheadImage entry to <guide> section
+            mp = getattr(self, 'masthead_path', None)
+            if mp is not None and os.access(mp, os.R_OK):
+                from calibre.ebooks.metadata.opf2 import Guide
+                ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu())
+                ref.type = 'masthead'
+                ref.title = 'Masthead Image'
+                opf.guide.append(ref)
 
-        manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))]
-        manifest.append(os.path.join(dir, 'index.html'))
-        manifest.append(os.path.join(dir, 'index.ncx'))
+            manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))]
+            manifest.append(os.path.join(dir, 'index.html'))
+            manifest.append(os.path.join(dir, 'index.ncx'))
 
-        # Get cover
-        cpath = getattr(self, 'cover_path', None)
-        if cpath is None:
-            pf = open(os.path.join(dir, 'cover.jpg'), 'wb')
-            if self.default_cover(pf):
-                cpath =  pf.name
-        if cpath is not None and os.access(cpath, os.R_OK):
-            opf.cover = cpath
-            manifest.append(cpath)
+            # Get cover
+            cpath = getattr(self, 'cover_path', None)
+            if cpath is None:
+                pf = open(os.path.join(dir, 'cover.jpg'), 'wb')
+                if self.default_cover(pf):
+                    cpath =  pf.name
+            if cpath is not None and os.access(cpath, os.R_OK):
+                opf.cover = cpath
+                manifest.append(cpath)
 
-        # Get masthead
-        mpath = getattr(self, 'masthead_path', None)
-        if mpath is not None and os.access(mpath, os.R_OK):
-            manifest.append(mpath)
+            # Get masthead
+            mpath = getattr(self, 'masthead_path', None)
+            if mpath is not None and os.access(mpath, os.R_OK):
+                manifest.append(mpath)
 
-        opf.create_manifest_from_files_in(manifest)
-        for mani in opf.manifest:
-            if mani.path.endswith('.ncx'):
-                mani.id = 'ncx'
-            if mani.path.endswith('mastheadImage.jpg'):
-                mani.id = 'masthead-image'
-        entries = ['index.html']
-        toc = TOC(base_path=dir)
-        self.play_order_counter = 0
-        self.play_order_map = {}
+            opf.create_manifest_from_files_in(manifest)
+            for mani in opf.manifest:
+                if mani.path.endswith('.ncx'):
+                    mani.id = 'ncx'
+                if mani.path.endswith('mastheadImage.jpg'):
+                    mani.id = 'masthead-image'
+            entries = ['index.html']
+            toc = TOC(base_path=dir)
+            self.play_order_counter = 0
+            self.play_order_map = {}
 
         def feed_index(num, parent):
             f = feeds[num]
@@ -321,7 +313,7 @@ class MPHKRecipe(BasicNewsRecipe):
                             prefix = '/'.join('..'for i in range(2*len(re.findall(r'link\d+', last))))
                             templ = self.navbar.generate(True, num, j, len(f),
                                             not self.has_single_feed,
-                                            a.orig_url, __appname__, prefix=prefix,
+                                            a.orig_url, self.publisher, prefix=prefix,
                                             center=self.center_navbar)
                             elem = BeautifulSoup(templ.render(doctype='xhtml').decode('utf-8')).find('div')
                             body.insert(len(body.contents), elem)
@@ -344,7 +336,7 @@ class MPHKRecipe(BasicNewsRecipe):
                 if not desc:
                     desc = None
                 feed_index(i, toc.add_item('feed_%d/index.html'%i, None,
-                    f.title, play_order=po, description=desc, author=auth))
+                           f.title, play_order=po, description=desc, author=auth))
 
         else:
             entries.append('feed_%d/index.html'%0)
@@ -357,4 +349,3 @@ class MPHKRecipe(BasicNewsRecipe):
 
         with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file):
             opf.render(opf_file, ncx_file)
-

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/osnews_pl.recipe

@@ -0,0 +1,50 @@
+#!/usr/bin/env  python
+
+__license__ = 'GPL v3'
+'''
+OSNews.pl
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class OSNewsRecipe(BasicNewsRecipe):
+    __author__ = u'Mori & Tomasz D\u0142ugosz'
+    language = 'pl'
+
+    title = u'OSnews.pl'
+    publisher = u'OSnews.pl'
+    description = u'OSnews.pl jest spo\u0142eczno\u015bciowym serwisem informacyjnym po\u015bwi\u0119conym oprogramowaniu, systemom operacyjnym i \u015bwiatowi IT'
+
+    no_stylesheets = True
+    remove_javascript = True
+    encoding = 'utf-8'
+    use_embedded_content = False;
+
+    oldest_article = 7
+    max_articles_per_feed = 100
+
+    extra_css = '''
+        .news-heading {font-size:150%}
+        .newsinformations li {display:inline;}
+        blockquote {border:2px solid #000; padding:5px;}
+    '''
+
+    feeds = [
+        (u'OSNews.pl', u'http://feeds.feedburner.com/OSnewspl')
+    ]
+
+    keep_only_tags = [
+        dict(name = 'a', attrs = {'class' : 'news-heading'}),
+        dict(name = 'div', attrs = {'class' : 'newsinformations'}),
+        dict(name = 'div', attrs = {'id' : 'news-content'})
+    ]
+
+    remove_tags = [
+        dict(name = 'div', attrs = {'class' : 'sociable'}),
+        dict(name = 'div', attrs = {'class' : 'post_prev'}),
+        dict(name = 'div', attrs = {'class' : 'post_next'}),
+        dict(name = 'div', attrs = {'class' : 'clr'})
+    ]
+
+    preprocess_regexps = [(re.compile(u'</span>Komentarze: \(?[0-9]+\)? ?<span'), lambda match: '</span><span')]

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

@@ -0,0 +1,26 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Tomasz Dlugosz <tomek3d@gmail.com>'
+'''
+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'
+    language = 'pl'
+    __author__ = u'Tomasz D\u0142ugosz'
+    oldest_article = 7
+    max_articles_per_feed = 100
+
+    feeds       = [(u'\u015awiat Kindle - wpisy', u'http://swiatkindle.pl/feed')]
+
+    remove_tags = [dict(name = 'ul', attrs = {'class' : 'similar-posts'})]
+
+    preprocess_regexps = [(re.compile(u'<h3>Czytaj dalej:</h3>'), lambda match: '')]
+

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/customize/builtins.py

@@ -573,8 +573,8 @@ from calibre.devices.edge.driver import EDGE
 from calibre.devices.teclast.driver import TECLAST_K3, NEWSMY, IPAPYRUS, \
         SOVOS, PICO, SUNSTECH_EB700, ARCHOS7O, STASH
 from calibre.devices.sne.driver import SNE
-from calibre.devices.misc import PALMPRE, AVANT, SWEEX, PDNOVEL, KOGAN, \
-        GEMEI, VELOCITYMICRO, PDNOVEL_KOBO, Q600, LUMIREAD, ALURATEK_COLOR, \
+from calibre.devices.misc import PALMPRE, AVANT, SWEEX, PDNOVEL, \
+        GEMEI, VELOCITYMICRO, PDNOVEL_KOBO, LUMIREAD, ALURATEK_COLOR, \
         TREKSTOR, EEEREADER, NEXTBOOK
 from calibre.devices.folder_device.driver import FOLDER_DEVICE_FOR_CONFIG
 from calibre.devices.kobo.driver import KOBO
@@ -691,8 +691,6 @@ plugins += [
     AVANT,
     MENTOR,
     SWEEX,
-    Q600,
-    KOGAN,
     PDNOVEL,
     SPECTRA,
     GEMEI,

src/calibre/customize/ui.py

@@ -121,7 +121,8 @@ def enable_plugin(plugin_or_name):
     config['enabled_plugins'] = ep
 
 default_disabled_plugins = set([
-    'Douban Books', 'Douban.com covers', 'Nicebooks', 'Nicebooks covers'
+    'Douban Books', 'Douban.com covers', 'Nicebooks', 'Nicebooks covers',
+    'Kent District Library'
 ])
 
 def is_disabled(plugin):

src/calibre/devices/android/driver.py

@@ -60,7 +60,12 @@ class ANDROID(USBMS):
             0x1004 : { 0x61cc : [0x100] },
 
             # Archos
-            0x0e79 : { 0x1419: [0x0216], 0x1420 : [0x0216], 0x1422 : [0x0216]},
+            0x0e79 : {
+                0x1400 : [0x0222, 0x0216],
+                0x1419 : [0x0216],
+                0x1420 : [0x0216],
+                0x1422 : [0x0216]
+            },
 
             # Huawei
             # Disabled as this USB id is used by various USB flash drives
@@ -84,10 +89,10 @@ class ANDROID(USBMS):
             'GT-I9000', 'FILE-STOR_GADGET', 'SGH-T959', 'SAMSUNG_ANDROID',
             'SCH-I500_CARD', 'SPH-D700_CARD', 'MB810', 'GT-P1000', 'DESIRE',
             'SGH-T849', '_MB300', 'A70S', 'S_ANDROID', 'A101IT', 'A70H',
-            'IDEOS_TABLET', 'MYTOUCH_4G', 'UMS_COMPOSITE', 'SCH-I800_CARD']
+            'IDEOS_TABLET', 'MYTOUCH_4G', 'UMS_COMPOSITE', 'SCH-I800_CARD', '7']
     WINDOWS_CARD_A_MEM = ['ANDROID_PHONE', 'GT-I9000_CARD', 'SGH-I897',
             'FILE-STOR_GADGET', 'SGH-T959', 'SAMSUNG_ANDROID', 'GT-P1000_CARD',
-            'A70S', 'A101IT']
+            'A70S', 'A101IT', '7']
 
     OSX_MAIN_MEM = 'Android Device Main Memory'
 

src/calibre/devices/misc.py

@@ -54,41 +54,24 @@ class AVANT(USBMS):
 class SWEEX(USBMS):
     # Identical to the Promedia
     name           = 'Sweex Device Interface'
-    gui_name       = 'Sweex'
-    description    = _('Communicate with the Sweex MM300')
+    gui_name       = 'Sweex/Kogan/Q600/Wink'
+    description    = _('Communicate with the Sweex/Kogan/Q600/Wink')
     author         = 'Kovid Goyal'
     supported_platforms = ['windows', 'osx', 'linux']
 
     # Ordered list of supported formats
-    FORMATS     = ['epub', 'prc', 'fb2', 'html', 'rtf', 'chm', 'pdf', 'txt']
+    FORMATS     = ['epub', 'mobi', 'prc', 'fb2', 'html', 'rtf', 'chm', 'pdf', 'txt']
 
     VENDOR_ID   = [0x0525, 0x177f]
     PRODUCT_ID  = [0xa4a5, 0x300]
-    BCD         = [0x0319, 0x110]
+    BCD         = [0x0319, 0x110, 0x325]
 
-    VENDOR_NAME = 'SWEEX'
-    WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = 'EBOOKREADER'
+    VENDOR_NAME = ['SWEEX', 'LINUX']
+    WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = ['EBOOKREADER', 'FILE-STOR_GADGET']
 
     EBOOK_DIR_MAIN = ''
     SUPPORTS_SUB_DIRS = True
 
-class Q600(SWEEX):
-
-    name = 'Digma Q600 Device interface'
-    gui_name = 'Q600'
-    description    = _('Communicate with the Digma Q600')
-
-    BCD = [0x325]
-    FORMATS     = ['epub', 'fb2', 'mobi', 'prc', 'html', 'rtf', 'chm', 'pdf', 'txt']
-
-class KOGAN(SWEEX):
-
-    name           = 'Kogan Device Interface'
-    gui_name       = 'Kogan'
-    description    = _('Communicate with the Kogan')
-    VENDOR_NAME = 'LINUX'
-    WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = 'FILE-STOR_GADGET'
-    EBOOK_DIR_MAIN = 'Kogan eBooks'
 
 class PDNOVEL(USBMS):
     name = 'Pandigital Novel device interface'

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/fb2/fb2ml.py

@@ -350,6 +350,8 @@ class FB2MLizer(object):
         # Number of blank lines above tag
         try:
             ems = int(round((float(style.marginTop) / style.fontSize) - 1))
+            if ems < 0:
+                ems = 0
         except:
             ems = 0
 
@@ -397,7 +399,7 @@ class FB2MLizer(object):
                     fb2_out += p_txt
                     tags += p_tag
                     fb2_out.append('<image xlink:href="#%s" />' % self.image_hrefs[page.abshref(elem_tree.attrib['src'])])
-        if tag in ('br', 'hr') or ems:
+        if tag in ('br', 'hr') or ems >= 1:
             if ems < 1:
                 multiplier = 1
             else:

src/calibre/ebooks/metadata/amazon.py

@@ -205,7 +205,10 @@ def main(args=sys.argv):
             open(cpath, 'wb').write(br.open_novisit(curl).read())
             print 'Cover for', title, 'saved to', cpath
 
+        #import time
+        #st = time.time()
         print get_social_metadata(title, None, None, isbn)
+        #print '\n\n', time.time() - st, '\n\n'
 
     return 0
 

src/calibre/ebooks/metadata/fetch.py

@@ -106,6 +106,9 @@ class MetadataSource(Plugin): # {{{
     def join(self):
         return self.worker.join()
 
+    def is_alive(self):
+        return self.worker.is_alive()
+
     def is_customizable(self):
         return True
 
@@ -251,7 +254,9 @@ class KentDistrictLibrary(MetadataSource): # {{{
 
     name = 'Kent District Library'
     metadata_type = 'social'
-    description = _('Downloads series information from ww2.kdl.org')
+    description = _('Downloads series information from ww2.kdl.org. '
+            'This website cannot handle large numbers of queries, '
+            'so the plugin is disabled by default.')
 
     def fetch(self):
         if not self.title or not self.book_author:

src/calibre/ebooks/metadata/kdl.py

@@ -5,7 +5,9 @@ __license__   = 'GPL v3'
 __copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
-import re, urllib, urlparse
+import re, urllib, urlparse, socket
+
+from mechanize import URLError
 
 from calibre.ebooks.metadata.book.base import Metadata
 from calibre import browser
@@ -17,7 +19,7 @@ URL = \
 
 _ignore_starts = u'\'"'+u''.join(unichr(x) for x in range(0x2018, 0x201e)+[0x2032, 0x2033])
 
-def get_series(title, authors):
+def get_series(title, authors, timeout=60):
     mi = Metadata(title, authors)
     if title and title[0] in _ignore_starts:
         title = title[1:]
@@ -39,7 +41,12 @@ def get_series(title, authors):
 
     url = URL.format(author, title)
     br = browser()
-    raw = br.open(url).read()
+    try:
+        raw = br.open_novisit(url, timeout=timeout).read()
+    except URLError, e:
+        if isinstance(e.reason, socket.timeout):
+            raise Exception('KDL Server busy, try again later')
+        raise
     if 'see the full results' not in raw:
         return mi
     raw = xml_to_unicode(raw)[0]

src/calibre/ebooks/metadata/sources/base.py

@@ -85,7 +85,8 @@ class Source(Plugin):
 
     # Metadata API {{{
 
-    def identify(self, log, result_queue, abort, title=None, authors=None, identifiers={}):
+    def identify(self, log, result_queue, abort, title=None, authors=None,
+            identifiers={}, timeout=5):
         '''
         Identify a book by its title/author/isbn/etc.
 
@@ -98,6 +99,8 @@ class Source(Plugin):
         :param authors: A list of authors of the book, can be None
         :param identifiers: A dictionary of other identifiers, most commonly
                             {'isbn':'1234...'}
+        :param timeout: Timeout in seconds, no network request should hang for
+                        longer than timeout.
         :return: None if no errors occurred, otherwise a unicode representation
                  of the error suitable for showing to the user
 

src/calibre/ebooks/metadata/sources/google.py

@@ -10,7 +10,6 @@ __docformat__ = 'restructuredtext en'
 import time
 from urllib import urlencode
 from functools import partial
-from threading import Thread
 
 from lxml import etree
 
@@ -18,6 +17,7 @@ from calibre.ebooks.metadata.sources.base import Source
 from calibre.ebooks.metadata.book.base import Metadata
 from calibre.ebooks.chardet import xml_to_unicode
 from calibre.utils.date import parse_date, utcnow
+from calibre.utils.cleantext import clean_ascii_chars
 from calibre import browser, as_unicode
 
 NAMESPACES = {
@@ -41,20 +41,20 @@ subject        = XPath('descendant::dc:subject')
 description    = XPath('descendant::dc:description')
 language       = XPath('descendant::dc:language')
 
-def get_details(browser, url):
+def get_details(browser, url, timeout):
     try:
-        raw = browser.open_novisit(url).read()
+        raw = browser.open_novisit(url, timeout=timeout).read()
     except Exception as e:
         gc = getattr(e, 'getcode', lambda : -1)
         if gc() != 403:
             raise
         # Google is throttling us, wait a little
-        time.sleep(2)
-        raw = browser.open_novisit(url).read()
+        time.sleep(1)
+        raw = browser.open_novisit(url, timeout=timeout).read()
 
     return raw
 
-def to_metadata(browser, log, entry_):
+def to_metadata(browser, log, entry_, timeout):
 
     def get_text(extra, x):
         try:
@@ -79,8 +79,9 @@ def to_metadata(browser, log, entry_):
 
     mi = Metadata(title_, authors)
     try:
-        raw = get_details(browser, id_url)
-        feed = etree.fromstring(xml_to_unicode(raw, strip_encoding_pats=True)[0])
+        raw = get_details(browser, id_url, timeout)
+        feed = etree.fromstring(xml_to_unicode(clean_ascii_chars(raw),
+            strip_encoding_pats=True)[0])
         extra = entry(feed)[0]
     except:
         log.exception('Failed to get additional details for', mi.title)
@@ -131,26 +132,19 @@ def to_metadata(browser, log, entry_):
 
     return mi
 
-class Worker(Thread):
 
-    def __init__(self, log, entries, abort, result_queue):
-        self.browser, self.log, self.entries = browser(), log, entries
-        self.abort, self.result_queue = abort, result_queue
-        Thread.__init__(self)
-        self.daemon = True
-
-    def run(self):
-        for i in self.entries:
-            try:
-                ans = to_metadata(self.browser, self.log, i)
-                if isinstance(ans, Metadata):
-                    self.result_queue.put(ans)
-            except:
-                self.log.exception(
-                    'Failed to get metadata for identify entry:',
-                    etree.tostring(i))
-            if self.abort.is_set():
-                break
+def get_all_details(br, log, entries, abort, result_queue, timeout):
+    for i in entries:
+        try:
+            ans = to_metadata(br, log, i, timeout)
+            if isinstance(ans, Metadata):
+                result_queue.put(ans)
+        except:
+            log.exception(
+                'Failed to get metadata for identify entry:',
+                etree.tostring(i))
+        if abort.is_set():
+            break
 
 
 class GoogleBooks(Source):
@@ -192,54 +186,40 @@ class GoogleBooks(Source):
             })
 
 
-    def identify(self, log, result_queue, abort, title=None, authors=None, identifiers={}):
+    def identify(self, log, result_queue, abort, title=None, authors=None,
+            identifiers={}, timeout=5):
         query = self.create_query(log, title=title, authors=authors,
                 identifiers=identifiers)
+        br = browser()
         try:
-            raw = browser().open_novisit(query).read()
+            raw = br.open_novisit(query, timeout=timeout).read()
         except Exception, e:
             log.exception('Failed to make identify query: %r'%query)
             return as_unicode(e)
 
         try:
             parser = etree.XMLParser(recover=True, no_network=True)
-            feed = etree.fromstring(xml_to_unicode(raw,
+            feed = etree.fromstring(xml_to_unicode(clean_ascii_chars(raw),
                 strip_encoding_pats=True)[0], parser=parser)
             entries = entry(feed)
         except Exception, e:
             log.exception('Failed to parse identify results')
             return as_unicode(e)
 
-
-        groups = self.split_jobs(entries, 5) # At most 5 threads
-        if not groups:
-            return None
-        workers = [Worker(log, entries, abort, result_queue) for entries in
-                groups]
-
-        if abort.is_set():
-            return None
-
-        for worker in workers: worker.start()
-
-        has_alive_worker = True
-        while has_alive_worker and not abort.is_set():
-            time.sleep(0.1)
-            has_alive_worker = False
-            for worker in workers:
-                if worker.is_alive():
-                    has_alive_worker = True
+        # There is no point running these queries in threads as google
+        # throttles requests returning Forbidden errors
+        get_all_details(br, log, entries, abort, result_queue, timeout)
 
         return None
 
 if __name__ == '__main__':
     # To run these test use: calibre-debug -e src/calibre/ebooks/metadata/sources/google.py
     from calibre.ebooks.metadata.sources.test import (test_identify_plugin,
-            isbn_test)
+            title_test)
     test_identify_plugin(GoogleBooks.name,
         [
             (
                 {'title': 'Great Expectations', 'authors':['Charles Dickens']},
-                [isbn_test('9781607541592')]
+                [title_test('Great Expectations', exact=True)]
             ),
     ])

src/calibre/ebooks/metadata/sources/test.py

@@ -7,7 +7,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
-import os, tempfile
+import os, tempfile, time
 from Queue import Queue, Empty
 from threading import Event
 
@@ -26,6 +26,17 @@ def isbn_test(isbn):
 
     return test
 
+def title_test(title, exact=False):
+
+    title = title.lower()
+
+    def test(mi):
+        mt = mi.title.lower()
+        return (exact and mt == title) or \
+                (not exact and title in mt)
+
+    return test
+
 def test_identify_plugin(name, tests):
     '''
     :param name: Plugin name
@@ -48,11 +59,15 @@ def test_identify_plugin(name, tests):
     abort = Event()
     prints('Log saved to', lf)
 
+    times = []
     for kwargs, test_funcs in tests:
         prints('Running test with:', kwargs)
         rq = Queue()
         args = (log, rq, abort)
+        start_time = time.time()
         err = plugin.identify(*args, **kwargs)
+        total_time = time.time() - start_time
+        times.append(total_time)
         if err is not None:
             prints('identify returned an error for args', args)
             prints(err)
@@ -87,6 +102,8 @@ def test_identify_plugin(name, tests):
             prints('Log saved to', lf)
             raise SystemExit(1)
 
+    prints('Average time per query', sum(times)/len(times))
+
     if os.stat(lf).st_size > 10:
         prints('There were some errors, see log', lf)
 

src/calibre/ebooks/metadata/xisbn.py

@@ -11,6 +11,12 @@ from calibre import browser
 
 class xISBN(object):
 
+    '''
+    This class is used to find the ISBN numbers of "related" editions of a
+    book, given its ISBN. Useful when querying services for metadata by ISBN,
+    in case they do not have the ISBN for the particular edition.
+    '''
+
     QUERY = 'http://xisbn.worldcat.org/webservices/xid/isbn/%s?method=getEditions&format=json&fl=form,year,lang,ed'
 
     def __init__(self):

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/ebooks/oeb/base.py

@@ -515,7 +515,7 @@ class Metadata(object):
                          'publisher', 'relation', 'rights', 'source',
                          'subject', 'title', 'type'])
     CALIBRE_TERMS = set(['series', 'series_index', 'rating', 'timestamp',
-                         'publication_type'])
+                         'publication_type', 'title_sort'])
     OPF_ATTRS     = {'role': OPF('role'), 'file-as': OPF('file-as'),
                      'scheme': OPF('scheme'), 'event': OPF('event'),
                      'type': XSI('type'), 'lang': XML('lang'), 'id': 'id'}

src/calibre/ebooks/oeb/transforms/metadata.py

@@ -18,7 +18,8 @@ def meta_info_to_oeb_metadata(mi, m, log, override_input_metadata=False):
     if mi.title_sort:
         if not m.title:
             m.add('title', mi.title_sort)
-        m.title[0].file_as = mi.title_sort
+        m.clear('title_sort')
+        m.add('title_sort', mi.title_sort)
     if not mi.is_null('authors'):
         m.filter('creator', lambda x : x.role.lower() in ['aut', ''])
         for a in mi.authors:

src/calibre/gui2/actions/add.py

@@ -259,6 +259,7 @@ class AddAction(InterfaceAction):
             if hasattr(self.gui, 'db_images'):
                 self.gui.db_images.reset()
             self.gui.tags_view.recount()
+
         if getattr(self._adder, 'merged_books', False):
             books = u'\n'.join([x if isinstance(x, unicode) else
                     x.decode(preferred_encoding, 'replace') for x in
@@ -266,6 +267,17 @@ class AddAction(InterfaceAction):
             info_dialog(self.gui, _('Merged some books'),
                     _('The following duplicate books were found and incoming book formats were '
                         'processed and merged into your Calibre database according to your automerge settings:'), det_msg=books, show=True)
+
+        if getattr(self._adder, 'number_of_books_added', 0) > 0 or \
+                getattr(self._adder, 'merged_books', False):
+            # The formats of the current book could have changed if
+            # automerge is enabled
+            current_idx = self.gui.library_view.currentIndex()
+            if current_idx.isValid():
+                self.gui.library_view.model().current_changed(current_idx,
+                        current_idx)
+
+
         if getattr(self._adder, 'critical', None):
             det_msg = []
             for name, log in self._adder.critical.items():

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)
 

src/calibre/gui2/tag_view.py

@@ -1096,7 +1096,8 @@ class TagsModel(QAbstractItemModel): # {{{
                         if tag in nodes_seen:
                             continue
                         nodes_seen.add(tag)
-                        ans.append('%s%s:"=%s"'%(prefix, category, tag.name))
+                        ans.append('%s%s:"=%s"'%(prefix, category,
+                                                 tag.name.replace(r'"', r'\"')))
         return ans
 
     def find_item_node(self, key, txt, start_path):

src/calibre/library/database2.py

@@ -2356,7 +2356,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
         rating = int(rating)
         self.conn.execute('DELETE FROM books_ratings_link WHERE book=?',(id,))
         rat = self.conn.get('SELECT id FROM ratings WHERE rating=?', (rating,), all=False)
-        rat = rat if rat else self.conn.execute('INSERT INTO ratings(rating) VALUES (?)', (rating,)).lastrowid
+        rat = rat if rat is not None else self.conn.execute('INSERT INTO ratings(rating) VALUES (?)', (rating,)).lastrowid
         self.conn.execute('INSERT INTO books_ratings_link(book, rating) VALUES (?,?)', (id, rat))
         self.dirtied([id], commit=False)
         if commit:

src/calibre/library/server/opds.py

@@ -313,24 +313,10 @@ class CategoryFeed(NavFeed):
         ignore_count = False
         if which == 'search':
             ignore_count = True
-        uc = None
-        if which.endswith(':'):
-            # We have a user category. Translate back to original categories
-            uc = {}
-            try:
-                ucs = db.prefs['user_categories']
-                ucs = ucs.get(which[:-1])
-                for name, category, index in ucs:
-                    uc[name] = category
-            except:
-                import traceback
-                traceback.print_exc()
-                uc = None
         for item in items:
-            if uc: which = uc.get(item.name, which)
-            self.root.append(CATALOG_ENTRY(item, which, base_href, version,
+            self.root.append(CATALOG_ENTRY(item, item.category, base_href, version,
                                            updated, ignore_count=ignore_count,
-                                           add_kind=uc is not None))
+                                           add_kind=which != item.category))
 
 class CategoryGroupFeed(NavFeed):