Pull from trunk

src/calibre/devices/__init__.py

@@ -13,7 +13,9 @@ def devices():
     from calibre.devices.kindle.driver import KINDLE
     from calibre.devices.kindle.driver import KINDLE2
     from calibre.devices.blackberry.driver import BLACKBERRY
-    return (PRS500, PRS505, PRS700, CYBOOKG3, KINDLE, KINDLE2, BLACKBERRY)
+    from calibre.devices.eb600.driver import EB600
+    return (PRS500, PRS505, PRS700, CYBOOKG3, KINDLE, KINDLE2,
+            BLACKBERRY, EB600)
 
 import time
 

src/calibre/devices/cybookg3/driver.py

@@ -11,7 +11,6 @@ from calibre.ebooks.metadata import authors_to_string
 from calibre.devices.errors import FreeSpaceError
 from calibre.devices.usbms.driver import USBMS
 import calibre.devices.cybookg3.t2b as t2b
-from calibre.devices.errors import FreeSpaceError
 
 class CYBOOKG3(USBMS):
     # Ordered list of supported formats

src/calibre/devices/eb600/__init__.py

@@ -0,0 +1,2 @@
+__license__   = 'GPL v3'
+__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'

src/calibre/devices/eb600/driver.py

@@ -0,0 +1,41 @@
+__license__   = 'GPL v3'
+__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
+'''
+Device driver for the Netronix EB600
+'''
+
+from calibre.devices.usbms.driver import USBMS
+
+class EB600(USBMS):
+    # Ordered list of supported formats
+    FORMATS     = ['epub', 'prc', 'chm', 'djvu', 'html', 'rtf', 'txt', 'pdf']
+    DRM_FORMATS = ['prc', 'mobi', 'html', 'pdf', 'txt']
+
+    VENDOR_ID   = [0x1f85]
+    PRODUCT_ID  = [0x1688]
+    BCD         = [0x110]
+
+    VENDOR_NAME      = 'NETRONIX'
+    WINDOWS_MAIN_MEM = 'EBOOK'
+    WINDOWS_CARD_MEM = 'EBOOK'
+
+    OSX_MAIN_MEM = 'EB600 Internal Storage Media'
+    OSX_CARD_MEM = 'EB600 Card Storage Media'
+
+    MAIN_MEMORY_VOLUME_LABEL  = 'EB600 Main Memory'
+    STORAGE_CARD_VOLUME_LABEL = 'EB600 Storage Card'
+
+    EBOOK_DIR_MAIN = ''
+    EBOOK_DIR_CARD = ''
+    SUPPORTS_SUB_DIRS = True
+
+    def windows_sort_drives(self, drives):
+        main = drives['main']
+        card = drives['card']
+        if card and main and card < main:
+            drives['main'] = card
+            drives['card'] = main
+
+        return drives
+
+

src/calibre/devices/usbms/device.py

@@ -174,6 +174,14 @@ class Device(_Device):
 
         return prefix
 
+    def windows_sort_drives(self, drives):
+        '''
+        Called to disambiguate main memory and storage card for devices that
+        do not distinguish between them on the basis of `WINDOWS_CARD_NAME`.
+        For e.g.: The EB600
+        '''
+        return drives
+
     def open_windows(self):
         time.sleep(6)
         drives = {}
@@ -188,11 +196,14 @@ class Device(_Device):
             if 'main' in drives.keys() and 'card' in drives.keys():
                 break
 
+        drives = self.windows_sort_drives(drives)
         self._main_prefix = drives.get('main')
         self._card_prefix = drives.get('card')
 
         if not self._main_prefix:
-            raise DeviceError(_('Unable to detect the %s disk drive. Try rebooting.') % self.__class__.__name__)
+            raise DeviceError(
+                _('Unable to detect the %s disk drive. Try rebooting.') %
+                self.__class__.__name__)
 
     def get_osx_mountpoints(self, raw=None):
         if raw is None:

src/calibre/ebooks/metadata/__init__.py

@@ -11,9 +11,7 @@ from urllib import unquote, quote
 from urlparse import urlparse
 
 
-from calibre.constants import __version__ as VERSION
 from calibre import relpath
-from calibre.utils.config import OptionParser
 
 def string_to_authors(raw):
     raw = raw.replace('&&', u'\uffff')
@@ -189,11 +187,11 @@ class MetaInformation(object):
                      'publisher', 'series', 'series_index', 'rating',
                      'isbn', 'tags', 'cover_data', 'application_id', 'guide',
                      'manifest', 'spine', 'toc', 'cover', 'language',
-                     'book_producer', 'timestamp'):
+                     'book_producer', 'timestamp', 'lccn', 'lcc', 'ddc'):
             if hasattr(mi, attr):
                 setattr(ans, attr, getattr(mi, attr))
 
-    def __init__(self, title, authors=[_('Unknown')]):
+    def __init__(self, title, authors=(_('Unknown'),)):
         '''
         @param title: title or ``_('Unknown')`` or a MetaInformation object
         @param authors: List of strings or []
@@ -204,9 +202,9 @@ class MetaInformation(object):
             title = mi.title
             authors = mi.authors
         self.title = title
-        self.author = authors # Needed for backward compatibility
+        self.author = list(authors) if authors else []# Needed for backward compatibility
         #: List of strings or []
-        self.authors = authors
+        self.authors = list(authors) if authors else []
         self.tags = getattr(mi, 'tags', [])
         #: mi.cover_data = (ext, data)
         self.cover_data   = getattr(mi, 'cover_data', (None, None))
@@ -214,7 +212,7 @@ class MetaInformation(object):
         for x in ('author_sort', 'title_sort', 'comments', 'category', 'publisher',
                   'series', 'series_index', 'rating', 'isbn', 'language',
                   'application_id', 'manifest', 'toc', 'spine', 'guide', 'cover',
-                  'book_producer', 'timestamp'
+                  'book_producer', 'timestamp', 'lccn', 'lcc', 'ddc'
                   ):
             setattr(self, x, getattr(mi, x, None))
 
@@ -229,15 +227,15 @@ class MetaInformation(object):
         if mi.authors and mi.authors[0] != _('Unknown'):
             self.authors = mi.authors
 
-            
         for attr in ('author_sort', 'title_sort', 'category',
                      'publisher', 'series', 'series_index', 'rating',
                      'isbn', 'application_id', 'manifest', 'spine', 'toc',
                      'cover', 'language', 'guide', 'book_producer',
-                     'timestamp'):
+                     'timestamp', 'lccn', 'lcc', 'ddc'):
-            val = getattr(mi, attr, None)
+            if hasattr(mi, attr):
-            if val is not None:
+                val = getattr(mi, attr)
-                setattr(self, attr, val)
+                if val is not None:
+                    setattr(self, attr, val)
 
         if mi.tags:
             self.tags += mi.tags
@@ -293,6 +291,13 @@ class MetaInformation(object):
             fmt('Rating', self.rating)
         if self.timestamp is not None:
             fmt('Timestamp', self.timestamp.isoformat(' '))
+        if self.lccn:
+            fmt('LCCN', unicode(self.lccn))
+        if self.lcc:
+            fmt('LCC', unicode(self.lcc))
+        if self.ddc:
+            fmt('DDC', unicode(self.ddc))
+
         return u'\n'.join(ans)
 
     def to_html(self):
@@ -302,6 +307,12 @@ class MetaInformation(object):
         ans += [(_('Producer'), unicode(self.book_producer))]
         ans += [(_('Comments'), unicode(self.comments))]
         ans += [('ISBN', unicode(self.isbn))]
+        if self.lccn:
+            ans += [('LCCN', unicode(self.lccn))]
+        if self.lcc:
+            ans += [('LCC', unicode(self.lcc))]
+        if self.ddc:
+            ans += [('DDC', unicode(self.ddc))]
         ans += [(_('Tags'), u', '.join([unicode(t) for t in self.tags]))]
         if self.series:
             ans += [(_('Series'), unicode(self.series)+ ' #%s'%self.format_series_index())]

src/calibre/ebooks/mobi/reader.py

@@ -59,8 +59,9 @@ class EXTHHeader(object):
             elif id == 502:
                 # last update time
                 pass
-            elif id == 503 and (not title or title == _('Unknown')):
+            elif id == 503: # Long title
-                title = content
+                if not title or title == _('Unknown'):
+                    title = content
             #else:
             #    print 'unknown record', id, repr(content)
         if title:
@@ -87,6 +88,8 @@ class EXTHHeader(object):
                         content, '%Y-%m-%d',).date()
             except:
                 pass
+        elif id == 108:
+            pass # Producer
         #else:
         #    print 'unhandled metadata record', id, repr(content)
 
@@ -522,7 +525,8 @@ class MobiReader(object):
         else:
             raise MobiError('Unknown compression algorithm: %s'%repr(self.book_header.compression_type))
         if self.book_header.ancient and '<html' not in self.mobi_html[:300].lower():
-            self.mobi_html = self.mobi_html.replace('\r ', '\n\n').replace('\0', '')
+            self.mobi_html = self.mobi_html.replace('\r ', '\n\n ')
+        self.mobi_html = self.mobi_html.replace('\0', '')
         return processed_records
 
 

src/calibre/gui2/__init__.py

@@ -466,5 +466,3 @@ class Application(QApplication):
                 self.translator.loadFromData(data)
                 self.installTranslator(self.translator)
 
-
-

src/calibre/gui2/dialogs/config.py

@@ -199,7 +199,7 @@ class EmailAccounts(QAbstractTableModel):
             return (account, self.accounts[account])
         if role == Qt.ToolTipRole:
             return self.tooltips[col]
-        if role == Qt.DisplayRole:
+        if role in [Qt.DisplayRole, Qt.EditRole]:
             if col == 0:
                 return QVariant(account)
             if col ==  1:
@@ -397,6 +397,9 @@ class ConfigDialog(QDialog, Ui_Dialog):
         self.separate_cover_flow.setChecked(config['separate_cover_flow'])
         self.setup_email_page()
         self.category_view.setCurrentIndex(self.category_view.model().index(0))
+        self.delete_news.setEnabled(bool(self.sync_news.isChecked()))
+        self.connect(self.sync_news, SIGNAL('toggled(bool)'),
+                self.delete_news.setEnabled)
 
     def setup_email_page(self):
         opts = smtp_prefs().parse()

src/calibre/gui2/dialogs/config.ui

@@ -371,7 +371,7 @@
          <item>
           <widget class="QCheckBox" name="delete_news">
            <property name="text">
-            <string>&amp;Delete news from library when it is sent to reader</string>
+            <string>&amp;Delete news from library when it is automatically sent to reader</string>
            </property>
           </widget>
          </item>

src/calibre/gui2/dialogs/metadata_single.ui

@@ -324,7 +324,7 @@
                     <string>Book </string>
                    </property>
                    <property name="minimum">
-                    <number>1</number>
+                    <number>0</number>
                    </property>
                    <property name="maximum">
                     <number>10000</number>

src/calibre/gui2/dialogs/scheduler.py

@@ -82,7 +82,8 @@ def load_recipes():
     recipes = []
     for r in config.get('scheduled_recipes', []):
         r = Recipe().unpickle(r)
-        if r.builtin and not str(r.id).startswith('recipe_'):
+        if r.builtin and \
+            (not str(r.id).startswith('recipe_') or not str(r.id) in recipe_modules):
             continue
         recipes.append(r)
     return recipes

src/calibre/gui2/main.py

@@ -1119,27 +1119,30 @@ class Main(MainWindow, Ui_MainWindow, DeviceGUI):
             return
         self._view_file(job.result)
 
-    def _view_file(self, name):
+    def _launch_viewer(self, name=None, viewer='ebook-viewer', internal=True):
         self.setCursor(Qt.BusyCursor)
         try:
-            ext = os.path.splitext(name)[1].upper().replace('.', '')
+            if internal:
-            if ext in config['internally_viewed_formats']:
+                args = [viewer]
-                if ext == 'LRF':
+                if isosx and 'ebook' in viewer:
-                    args = ['lrfviewer', name]
+                    args.append('--raise-window')
-                    self.job_manager.server.run_free_job('lrfviewer',
+                if name is not None:
-                                                        kwdargs=dict(args=args))
+                    args.append(name)
-                else:
+                self.job_manager.server.run_free_job(viewer,
-                    args = ['ebook-viewer', name]
+                        kwdargs=dict(args=args))
-                    if isosx:
-                        args.append('--raise-window')
-                    self.job_manager.server.run_free_job('ebook-viewer',
-                                                        kwdargs=dict(args=args))
             else:
-                QDesktopServices.openUrl(QUrl('file:'+name))#launch(name)
+                QDesktopServices.openUrl(QUrl.fromLocalFile(name))#launch(name)
+
             time.sleep(5) # User feedback
         finally:
             self.unsetCursor()
 
+    def _view_file(self, name):
+        ext = os.path.splitext(name)[1].upper().replace('.', '')
+        viewer = 'lrfviewer' if ext == 'LRF' else 'ebook-viewer'
+        internal = ext in config['internally_viewed_formats']
+        self._launch_viewer(name, viewer, internal)
+
     def view_specific_format(self, triggered):
         rows = self.library_view.selectionModel().selectedRows()
         if not rows or len(rows) == 0:
@@ -1174,8 +1177,7 @@ class Main(MainWindow, Ui_MainWindow, DeviceGUI):
         rows = self.current_view().selectionModel().selectedRows()
         if self.current_view() is self.library_view:
             if not rows or len(rows) == 0:
-                d = error_dialog(self, _('Cannot view'), _('No book selected'))
+                self._launch_viewer()
-                d.exec_()
                 return
 
             row = rows[0].row()

src/calibre/library/cli.py

@@ -15,6 +15,7 @@ from calibre import terminal_controller, preferred_encoding
 from calibre.utils.config import OptionParser, prefs
 try:
     from calibre.utils.single_qt_application import send_message
+    send_message
 except:
     send_message = None
 from calibre.ebooks.metadata.meta import get_metadata

src/calibre/startup.py

@@ -32,7 +32,8 @@ if not _run_once:
         lang = prefs['language']
         if lang is not None:
             return lang
-        lang = locale.getdefaultlocale()[0]
+        lang = locale.getdefaultlocale(['LANGUAGE', 'LC_ALL', 'LC_CTYPE',
+                                       'LC_MESSAGES', 'LANG'])[0]
         if lang is None and os.environ.has_key('LANG'): # Needed for OS X
             try:
                 lang = os.environ['LANG']

src/calibre/trac/plugins/download.py

@@ -38,6 +38,7 @@ def get_linux_data(version='1.0.0'):
                         ('exherbo', 'Exherbo'),
                         ('foresight', 'Foresight 2.1'),
                         ('ubuntu', 'Ubuntu Jaunty Jackalope'),
+                        ('linux_mint', 'Linux Mint Gloria'),
                         ]:
         data['supported'].append(CoolDistro(name, title,
                                         prefix='http://calibre.kovidgoyal.net'))

src/calibre/web/feeds/recipes/__init__.py

@@ -8,7 +8,7 @@ recipe_modules = ['recipe_' + r for r in (
            'newsweek', 'atlantic', 'economist', 'portfolio', 'the_register',
            'usatoday', 'outlook_india', 'bbc', 'greader', 'wsj',
            'wired', 'globe_and_mail', 'smh', 'espn', 'business_week', 'miami_herald',
-           'ars_technica', 'upi', 'new_yorker', 'irish_times', 'iht', 'lanacion',
+           'ars_technica', 'upi', 'new_yorker', 'irish_times', 'lanacion',
            'discover_magazine', 'scientific_american', 'new_york_review_of_books',
            'daily_telegraph', 'guardian', 'el_pais', 'new_scientist', 'b92',
            'politika', 'moscow_times', 'latimes', 'japan_times', 'san_fran_chronicle',
@@ -37,7 +37,8 @@ recipe_modules = ['recipe_' + r for r in (
            'new_york_review_of_books_no_sub', 'politico', 'adventuregamers',
            'mondedurable', 'instapaper', 'dnevnik_cro', 'vecernji_list',
            'nacional_cro', '24sata', 'dnevni_avaz', 'glas_srpske', '24sata_rs',
-           'krstarica', 'krstarica_en', 'tanjug', 'laprensa_ni',
+           'krstarica', 'krstarica_en', 'tanjug', 'laprensa_ni', 'azstarnet',
+           'corriere_della_sera_it', 'corriere_della_sera_en', 'msdnmag_en',
           )]
 
 import re, imp, inspect, time, os

src/calibre/web/feeds/recipes/recipe_azstarnet.py

@@ -0,0 +1,63 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+www.azstarnet.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Azstarnet(BasicNewsRecipe):
+    title                 = 'Arizona  Daily Star'
+    __author__            = 'Darko Miletic'
+    description           = 'news from Arizona'
+    publisher             = 'azstarnet.com'
+    category              = 'news, politics, Arizona, USA'
+    delay                 = 1    
+    oldest_article        = 1
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'utf-8'
+    needs_subscription    = True
+    remove_javascript     = True
+
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        if self.username is not None and self.password is not None:
+            br.open('http://azstarnet.com/registration/retro.php')
+            br.select_form(nr=1)
+            br['email'] = self.username
+            br['pass' ] = self.password
+            br.submit()
+        return br
+    
+    
+    keep_only_tags = [dict(name='div', attrs={'id':'storycontent'})]
+
+    remove_tags = [
+                     dict(name=['object','link','iframe','base','img'])
+                    ,dict(name='div',attrs={'class':'bannerinstory'})
+                  ]
+
+    
+    feeds = [(u'Tucson Region', u'http://rss.azstarnet.com/index.php?site=metro')]
+
+    def preprocess_html(self, soup):
+        soup.html['dir' ] = 'ltr'
+        soup.html['lang'] = 'en-US'
+        mtag = '\n<meta http-equiv="Content-Language" content="en-US"/>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8">\n'
+        soup.head.insert(0,mtag)    
+        for item in soup.findAll(style=True):
+            del item['style']    
+        return soup
+    

src/calibre/web/feeds/recipes/recipe_corriere_della_sera_en.py

@@ -0,0 +1,45 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+www.corriere.it/english
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Corriere_en(BasicNewsRecipe):
+    title                 = 'Corriere della Sera in English'
+    __author__            = 'Darko Miletic'
+    description           = 'News from Milan and Italy'
+    oldest_article        = 15
+    publisher             = 'Corriere della Sera'
+    category              = 'news, politics, Italy'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'cp1252'
+    remove_javascript     = True
+    language              = _('English')
+
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        , '--ignore-tables'
+                        ]
+
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
+
+    keep_only_tags = [dict(name='div', attrs={'class':['news-dettaglio article','article']})]
+
+    remove_tags = [
+                    dict(name=['base','object','link','embed','img'])
+                   ,dict(name='div', attrs={'class':'news-goback'})
+                   ,dict(name='ul', attrs={'class':'toolbar'})
+                  ]
+
+    remove_tags_after = dict(name='p', attrs={'class':'footnotes'})
+
+    feeds = [(u'Italian Life', u'http://www.corriere.it/rss/english.xml')]
+

src/calibre/web/feeds/recipes/recipe_corriere_della_sera_it.py

@@ -0,0 +1,55 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+www.corriere.it
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+class Corriere_it(BasicNewsRecipe):
+    title                 = 'Corriere della Sera'
+    __author__            = 'Darko Miletic'
+    description           = 'News from Milan and Italy'    
+    oldest_article        = 7
+    publisher             = 'Corriere della Sera'
+    category              = 'news, politics, Italy'        
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'cp1252'
+    remove_javascript     = True
+    language              = _('Italian')
+
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        , '--ignore-tables'
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
+
+    keep_only_tags = [dict(name='div', attrs={'class':['news-dettaglio article','article']})]
+
+    remove_tags = [
+                    dict(name=['base','object','link','embed','img'])
+                   ,dict(name='div', attrs={'class':'news-goback'})
+                   ,dict(name='ul', attrs={'class':'toolbar'})
+                  ]
+
+    remove_tags_after = dict(name='p', attrs={'class':'footnotes'})
+    
+    feeds = [ 
+              (u'Ultimora'  , u'http://www.corriere.it/rss/ultimora.xml'  )
+             ,(u'Cronache'  , u'http://www.corriere.it/rss/cronache.xml'  )
+             ,(u'Economia'  , u'http://www.corriere.it/rss/economia.xml'  )
+             ,(u'Editoriali', u'http://www.corriere.it/rss/editoriali.xml')
+             ,(u'Esteri'    , u'http://www.corriere.it/rss/esteri.xml'    )
+             ,(u'Politica'  , u'http://www.corriere.it/rss/politica.xml'  )
+             ,(u'Salute'    , u'http://www.corriere.it/rss/salute.xml'    )
+             ,(u'Scienze'   , u'http://www.corriere.it/rss/scienze.xml'   )
+             ,(u'Spettacolo', u'http://www.corriere.it/rss/spettacoli.xml')
+             ,(u'Sport'     , u'http://www.corriere.it/rss/sport.xml'     )
+            ]
+

src/calibre/web/feeds/recipes/recipe_iht.py

@@ -12,7 +12,7 @@ from calibre.ptempfile import PersistentTemporaryFile
 class InternationalHeraldTribune(BasicNewsRecipe):
     title          = u'The International Herald Tribune'
     __author__     = 'Derry FitzGerald'
-    language = _('English')
+    language       = _('English')
     oldest_article = 1
     max_articles_per_feed = 10
     no_stylesheets = True

src/calibre/web/feeds/recipes/recipe_msdnmag_en.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+msdn.microsoft.com/en-us/magazine
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class MSDNMagazine_en(BasicNewsRecipe):
+    title                 = 'MSDN Magazine'
+    __author__            = 'Darko Miletic'
+    description           = 'The Microsoft Journal for Developers'
+    publisher             = 'Microsoft Press'
+    category              = 'news, IT, Microsoft, programming, windows'        
+    oldest_article        = 31
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'utf-8'
+    remove_javascript     = True
+    current_issue         = 'http://msdn.microsoft.com/en-us/magazine/default.aspx'
+    language              = _('English')
+    
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+                            
+    feeds = [(u'Articles', u'http://msdn.microsoft.com/en-us/magazine/rss/default.aspx?z=z&iss=1')]
+
+    keep_only_tags = [dict(name='div', attrs={'class':'topic'})]
+
+    remove_tags = [
+                     dict(name=['object','link','base','table'])
+                    ,dict(name='div', attrs={'class':'MTPS_CollapsibleRegion'})
+                  ]
+    
+    def get_cover_url(self):
+        cover_url = None
+        soup = self.index_to_soup(self.current_issue)
+        link_item = soup.find('span',attrs={'class':'ContentsImageSpacer'})
+        if link_item:
+           imgt = link_item.find('img')
+           if imgt:
+              cover_url = imgt['src']
+        return cover_url
+
+    
+    def preprocess_html(self, soup):
+        for item in soup.findAll('div',attrs={'class':['FeatureSmallHead','ColumnTypeSubTitle']}):
+            item.name="h2"
+        for item in soup.findAll('div',attrs={'class':['FeatureHeadline','ColumnTypeTitle']}):
+            item.name="h1"
+        for item in soup.findAll('div',attrs={'class':'ArticleTypeTitle'}):
+            item.name="h3"
+        return soup
+    

src/calibre/web/feeds/recipes/recipe_new_yorker.py

@@ -9,11 +9,12 @@ newyorker.com
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class NewYorker(BasicNewsRecipe):
+
     title                 = u'The New Yorker'
     __author__            = 'Darko Miletic'
     description           = 'The best of US journalism'
     oldest_article        = 7
-    language = _('English')
+    language              = _('English')
     max_articles_per_feed = 100
     no_stylesheets        = False
     use_embedded_content  = False

src/calibre/web/feeds/recipes/recipe_tomshardware.py

@@ -1,38 +1,47 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
 '''
-tomshardware.com
+tomshardware.com/us
 '''
 
+import urllib
+from calibre.ebooks.BeautifulSoup import BeautifulSoup
 from calibre.web.feeds.recipes import BasicNewsRecipe
 
 class Tomshardware(BasicNewsRecipe):    
+    title               = "Tom's Hardware US"
+    __author__          = 'Darko Miletic'
+    description         = 'Hardware reviews and News'
+    publisher           = "Tom's Hardware"
+    category            = 'news, IT, hardware, USA'        
+    no_stylesheets      = True
+    needs_subscription  = True
+    language            = _('English')    
+    INDEX               = 'http://www.tomshardware.com'
+    LOGIN               = INDEX + '/membres/'
+    remove_javascript   = True
+    use_embedded_content= False
     
-    title       = "Tom's Hardware US"
+    html2lrf_options = [
-    __author__  = 'Darko Miletic'
+                          '--comment', description
-    description = 'Hardware reviews and News'
+                        , '--category', category
-    no_stylesheets = True
+                        , '--publisher', publisher
-    needs_subscription = True
+                        ]
-    language = _('English')
-    INDEX = 'http://www.tomshardware.com'
-    LOGIN = 'http://www.tomshardware.com/membres/?r=%2Fus%2F#loginForm'
-    cover_url = 'http://img.bestofmedia.com/img/tomshardware/design/tomshardware.jpg'
     
-    html2lrf_options = [  '--comment'       , description
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
-                        , '--category'      , 'hardware,news'
-                        , '--base-font-size', '10'
-                       ]
 
     def get_browser(self):
         br = BasicNewsRecipe.get_browser()
+        br.open(self.INDEX+'/us/')
         if self.username is not None and self.password is not None:
-            br.open(self.LOGIN)
+            data = urllib.urlencode({ 'action':'login_action'
-            br.select_form(name='connexion')
+                                     ,'r':self.INDEX+'/us/'
-            br['login'] = self.username
+                                     ,'login':self.username
-            br['mdp'  ] = self.password
+                                     ,'mdp':self.password
-            br.submit()
+                                   })
+            br.open(self.LOGIN,data)
         return br
 
     remove_tags = [
@@ -41,7 +50,7 @@ class Tomshardware(BasicNewsRecipe):
                   ]
     
     feeds = [
-              (u'Latest Articles', u'http://www.tomshardware.com/feeds/atom/tom-s-hardware-us,18-2.xml')
+              (u'Latest Articles', u'http://www.tomshardware.com/feeds/atom/tom-s-hardware-us,18-2.xml'          )
              ,(u'Latest News'    , u'http://www.tomshardware.com/feeds/atom/tom-s-hardware-us,18-1.xml')
             ]
 
@@ -49,9 +58,10 @@ class Tomshardware(BasicNewsRecipe):
         main, sep, rest = url.rpartition('.html')
         rmain, rsep, article_id = main.rpartition(',')
         tmain, tsep, trest = rmain.rpartition('/reviews/')
+        rind = 'http://www.tomshardware.com/news_print.php?p1='
         if tsep:
-            return 'http://www.tomshardware.com/review_print.php?p1=' + article_id
+           rind = 'http://www.tomshardware.com/review_print.php?p1='
-        return 'http://www.tomshardware.com/news_print.php?p1=' + article_id        
+        return rind + article_id        
 
     def preprocess_html(self, soup):
         del(soup.body['onload'])

src/calibre/web/feeds/recipes/recipe_wash_post.py

@@ -17,7 +17,7 @@ class WashingtonPost(BasicNewsRecipe):
 
     feeds = [ ('Today\'s Highlights', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/03/24/LI2005032400102.xml'),
      	         ('Politics', 'http://www.washingtonpost.com/wp-dyn/rss/politics/index.xml'),
-     	         ('Nation', 'http://www.www.washingtonpost.com/wp-dyn/rss/nation/index.xml'),
+     	         ('Nation', 'http://www.washingtonpost.com/wp-dyn/rss/nation/index.xml'),
      	         ('World', 'http://www.washingtonpost.com/wp-dyn/rss/world/index.xml'),
      	         ('Business', 'http://www.washingtonpost.com/wp-dyn/rss/business/index.xml'),
      	         ('Technology', 'http://www.washingtonpost.com/wp-dyn/rss/technology/index.xml'),