Merge from trunk

resources/recipes/journalgazette.recipe

@@ -0,0 +1,64 @@
+#!/usr/bin/env  python
+__license__   = 'GPL v3'
+__author__    = 'somedayson & TonytheBookworm, revised by Cynthia Clavey'
+__copyright__ = '2010, Cynthia Clavey cynvision@yahoo.com'
+__version__   = '1.02'
+__date__      = '05, september 2010'
+__docformat__ = 'restructuredtext en'
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class AdvancedUserRecipe1283666183(BasicNewsRecipe):
+    title          = u'Journal Gazette Ft. Wayne IN'
+    __author__     = 'cynvision'
+    oldest_article = 1
+    max_articles_per_feed = 8
+    no_stylesheets = True
+    remove_javascript     = True
+    use_embedded_content  = False
+    keep_only_tags = [dict(name='div', attrs={'id':'mainContent'})]
+    extra_css = '#copyinfo { font-size: 6 ;} \n #photocredit { font-size: 6 ;} \n  .pubinfo { font-size: 6 ;}'
+    masthead_url          = 'http://www.journalgazette.net/img/icons/jgmini.gif'
+#    cover_url = 'http://www.journalgazette.net/img/icons/jgmini.gif'
+    encoding = 'cp1252'
+
+    feeds = [(u'Opinion', u'http://journalgazette.net/apps/pbcs.dll/section?Category=EDIT&template=blogrss&mime=xml'),
+             (u'Local News',u'http://journalgazette.net/apps/pbcs.dll/section?Category=LOCAL&template=blogrss&mime=xml') ,
+             (u'Sports',u'http://journalgazette.net/apps/pbcs.dll/section?Category=SPORTS&template=blogrss&mime=xml' ),
+             (u'Features',u'http://journalgazette.net/apps/pbcs.dll/section?Category=FEAT&template=blogrss&mime=xml'),
+             (u'Business',u'http://journalgazette.net/apps/pbcs.dll/section?Category=BIZ&template=blogrss&mime=xml'),
+             (u'Ice Chips',u'http://journalgazette.net/apps/pbcs.dll/section?Category=BLOGS11&template=blogrss&mime=xml '),
+             (u'Entertainment',u'http://journalgazette.net/apps/pbcs.dll/section?Category=ENT&template=blogrss&mime=xml'),
+             (u'Food',u'http://journalgazette.net/apps/pbcs.dll/section?Category=FOOD&template=blogrss&mime=xml')
+            ]
+
+
+
+
+    def print_version(self, url):
+        split1 = url.split("/")
+        #print 'THE SPLIT IS: ', split1
+        #url1 = split1[0]
+        #url2 = split1[1]
+        url3 = split1[2]
+        #url4 = split1[3]
+        url5 = split1[4]
+        url6 = split1[5]
+        url7 = split1[6]
+        #url8 = split1[7]
+
+  #need to convert to print_version
+  #originalversion is : http://www.journalgazette.net/article/20100905/EDIT10/309059959/1021/EDIT
+  #printversion should be: http://www.journalgazette.net/apps/pbcs.dll/article?AID=/20100905/EDIT10/309059959/-1/EDIT01&template=printart
+  #results of the split
+  #THE SPLIT IS:  [u'http:', u'', u'www.journalgazette.net', u'article', u'20100905', u'EDIT10', u'309059959', u'1021', u'EDIT']
+
+
+
+        print_url = 'http://' + url3 + '/apps/pbcs.dll/article?AID=/' + url5 + '/' + url6 + '/' + url7 + '/-1/EDIT01&template=printart'
+        #print 'THIS URL WILL PRINT: ', print_url # this is a test string to see what the url is it will return
+        return print_url
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup

resources/recipes/wsj_free.recipe

@@ -0,0 +1,153 @@
+#!/usr/bin/env  python
+__license__   = 'GPL v3'
+__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
+__docformat__ = 'restructuredtext en'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import copy
+
+class WallStreetJournal(BasicNewsRecipe):
+
+    title = 'Wall Street Journal (free)'
+    __author__ = 'Kovid Goyal, Sujata Raman, Joshua Oster-Morris, Starson17'
+    description = 'News and current affairs'
+    language = 'en'
+    cover_url           = 'http://dealbreaker.com/images/thumbs/Wall%20Street%20Journal%20A1.JPG'
+    max_articles_per_feed = 1000
+    timefmt  = ' [%a, %b %d, %Y]'
+    no_stylesheets = True
+
+    extra_css      = '''h1{color:#093D72 ; font-size:large ; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; }
+                    h2{color:#474537; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;}
+                    .subhead{color:gray; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;}
+                    .insettipUnit {color:#666666; font-family:Arial,Sans-serif;font-size:xx-small }
+                    .targetCaption{ font-size:x-small; color:#333333; font-family:Arial,Helvetica,sans-serif}
+                    .article{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
+                    .tagline {color:#333333; font-size:xx-small}
+                    .dateStamp {color:#666666; font-family:Arial,Helvetica,sans-serif}
+                        h3{color:blue ;font-family:Arial,Helvetica,sans-serif; font-size:xx-small}
+                        .byline{color:blue;font-family:Arial,Helvetica,sans-serif; font-size:xx-small}
+                        h6{color:#333333; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small;font-style:italic; }
+                    .paperLocation{color:#666666; font-size:xx-small}'''
+
+    remove_tags_before = dict(name='h1')
+    remove_tags = [
+                    dict(id=["articleTabs_tab_article", "articleTabs_tab_comments", "articleTabs_tab_interactive","articleTabs_tab_video","articleTabs_tab_map","articleTabs_tab_slideshow"]),
+                    {'class':['footer_columns','network','insetCol3wide','interactive','video','slideshow','map','insettip','insetClose','more_in', "insetContent", 'articleTools_bottom', 'aTools', "tooltip", "adSummary", "nav-inline"]},
+                    dict(name='div', attrs={'data-flash-settings':True}),
+                    {'class':['insetContent embedType-interactive insetCol3wide','insetCol6wide','insettipUnit']},
+                    dict(rel='shortcut icon'),
+                    ]
+    remove_tags_after = [dict(id="article_story_body"), {'class':"article story"},]
+
+    def postprocess_html(self, soup, first):
+        for tag in soup.findAll(name=['table', 'tr', 'td']):
+            tag.name = 'div'
+
+        for tag in soup.findAll('div', dict(id=["articleThumbnail_1", "articleThumbnail_2", "articleThumbnail_3", "articleThumbnail_4", "articleThumbnail_5", "articleThumbnail_6", "articleThumbnail_7"])):
+            tag.extract()
+
+        return soup
+
+    def wsj_get_index(self):
+        return self.index_to_soup('http://online.wsj.com/itp')
+
+    def wsj_add_feed(self,feeds,title,url):
+        self.log('Found section:', title)
+        if url.endswith('whatsnews'):
+           articles = self.wsj_find_wn_articles(url)
+        else:
+           articles = self.wsj_find_articles(url)
+        if articles:
+           feeds.append((title, articles))
+        return feeds
+
+    def parse_index(self):
+        soup = self.wsj_get_index()
+
+        date = soup.find('span', attrs={'class':'date-date'})
+        if date is not None:
+            self.timefmt = ' [%s]'%self.tag_to_string(date)
+
+        feeds = []
+        div = soup.find('div', attrs={'class':'itpHeader'})
+        div = div.find('ul', attrs={'class':'tab'})
+        for a in div.findAll('a', href=lambda x: x and '/itp/' in x):
+            pageone = a['href'].endswith('pageone')
+            if pageone:
+               title = 'Front Section'
+               url = 'http://online.wsj.com' + a['href']
+               feeds = self.wsj_add_feed(feeds,title,url)
+               title = 'What''s News'
+               url = url.replace('pageone','whatsnews')
+               feeds = self.wsj_add_feed(feeds,title,url)
+            else:
+               title = self.tag_to_string(a)
+               url = 'http://online.wsj.com' + a['href']
+               feeds = self.wsj_add_feed(feeds,title,url)
+        return feeds
+
+    def wsj_find_wn_articles(self, url):
+        soup = self.index_to_soup(url)
+        articles = []
+
+        whats_news = soup.find('div', attrs={'class':lambda x: x and 'whatsNews-simple' in x})
+        if whats_news is not None:
+          for a in whats_news.findAll('a', href=lambda x: x and '/article/' in x):
+            container = a.findParent(['p'])
+            meta = a.find(attrs={'class':'meta_sectionName'})
+            if meta is not None:
+                meta.extract()
+            title = self.tag_to_string(a).strip()
+            url = a['href']
+            desc = ''
+            if container is not None:
+                desc = self.tag_to_string(container)
+
+            articles.append({'title':title, 'url':url,
+                'description':desc, 'date':''})
+
+            self.log('\tFound WN article:', title)
+
+        return articles
+
+    def wsj_find_articles(self, url):
+        soup = self.index_to_soup(url)
+
+        whats_news = soup.find('div', attrs={'class':lambda x: x and 'whatsNews-simple' in x})
+        if whats_news is not None:
+           whats_news.extract()
+
+        articles = []
+
+        flavorarea = soup.find('div', attrs={'class':lambda x: x and 'ahed' in x})
+        if flavorarea is not None:
+           flavorstory = flavorarea.find('a', href=lambda x: x and x.startswith('/article'))
+           if flavorstory is not None:
+              flavorstory['class'] = 'mjLinkItem'
+              metapage = soup.find('span', attrs={'class':lambda x: x and 'meta_sectionName' in x})
+              if metapage is not None:
+                 flavorstory.append( copy.copy(metapage) ) #metapage should always be A1 because that should be first on the page
+
+        for a in soup.findAll('a', attrs={'class':'mjLinkItem'}, href=True):
+            container = a.findParent(['li', 'div'])
+            meta = a.find(attrs={'class':'meta_sectionName'})
+            if meta is not None:
+                meta.extract()
+            title = self.tag_to_string(a).strip() + ' [%s]'%self.tag_to_string(meta)
+            url = 'http://online.wsj.com'+a['href']
+            desc = ''
+            p = container.find('p')
+            if p is not None:
+                desc = self.tag_to_string(p)
+
+            articles.append({'title':title, 'url':url,
+                'description':desc, 'date':''})
+
+            self.log('\tFound article:', title)
+
+        return articles
+
+    def cleanup(self):
+        self.browser.open('http://online.wsj.com/logout?url=http://online.wsj.com')
+

src/calibre/gui2/actions/delete.py

@@ -159,7 +159,7 @@ class DeleteAction(InterfaceAction):
         if self.gui.stack.currentIndex() == 0:
             if not confirm('<p>'+_('The selected books will be '
                                    '<b>permanently deleted</b> and the files '
-                                   'removed from your computer. Are you sure?')
+                                   'removed from your calibre library. Are you sure?')
                                 +'</p>', 'library_delete_books', self.gui):
                 return
             ci = view.currentIndex()

src/calibre/gui2/actions/edit_metadata.py

@@ -51,7 +51,8 @@ class EditMetadataAction(InterfaceAction):
                 self.merge_books)
         mb.addSeparator()
         mb.addAction(_('Merge into first selected book - keep others'),
-                partial(self.merge_books, safe_merge=True))
+                partial(self.merge_books, safe_merge=True),
+                Qt.AltModifier+Qt.Key_M)
         self.merge_menu = mb
         self.action_merge.setMenu(mb)
         md.addSeparator()

src/calibre/gui2/preferences/main.py

@@ -125,7 +125,7 @@ class Browser(QScrollArea): # {{{
             self.close_button.clicked.connect(self.close_requested)
             self._osxl.addStretch(10)
             self._osxl.addWidget(self.close_button)
-            self._osxl.addStretch(10)
+            #self._osxl.addStretch(10)
             self._layout.addLayout(self._osxl)
 
         for name, plugins in self.category_map.items():

src/calibre/gui2/ui.py

@@ -522,13 +522,12 @@ class Main(MainWindow, MainWindowMixin, DeviceMixin, # {{{
 
 
     def shutdown(self, write_settings=True):
-        l = getattr(self, 'library_view', None)
-        if l:
-            l = getattr(l, 'model', None);
-        if l:
-            l = l().db
-        if l:
-            l.clean()
+        try:
+            cf = self.library_view.model().db.clean
+        except:
+            pass
+        else:
+            cf()
         for action in self.iactions.values():
             if not action.shutting_down():
                 return

src/calibre/manual/gui.rst

@@ -345,6 +345,8 @@ Calibre has several keyboard shortcuts to save you time and mouse movement. Thes
       - Show book details
     * - :kbd:`M` 
       - Merge selected records
+    * - :kbd:`Alt+M` 
+      - Merge selected records, keeping originals
     * - :kbd:`O` 
       - Open containing folder
     * - :kbd:`S`