Merge from trunk

recipes/heise_online.recipe

@@ -1,11 +1,11 @@
 from calibre.web.feeds.news import BasicNewsRecipe
-import re
-
 class AdvancedUserRecipe(BasicNewsRecipe):
 
-    title = 'heise online'
+    title = 'Heise-online'
     description = 'News vom Heise-Verlag'
     __author__ = 'schuster'
+    masthead_url = 'http://www.heise.de/icons/ho/heise_online_logo.gif'
+    publisher   = 'Heise Zeitschriften Verlag GmbH & Co. KG'
     use_embedded_content   = False
     language = 'de'
     oldest_article = 2
@@ -14,11 +14,10 @@ class AdvancedUserRecipe(BasicNewsRecipe):
     remove_empty_feeds = True
     timeout = 5
     no_stylesheets = True
-    encoding = 'utf-8'
 
 
     remove_tags_after = dict(name ='p', attrs={'class':'editor'})
-    remove_tags = [{'class':'navi_top_container'},
+    remove_tags = [dict(id='navi_top_container'),
                             dict(id='navi_bottom'),
                             dict(id='mitte_rechts'),
                             dict(id='navigation'),
@@ -29,27 +28,31 @@ class AdvancedUserRecipe(BasicNewsRecipe):
                             dict(id='seiten_navi'),
                             dict(id='adbottom'),
                             dict(id='sitemap'),
-                            dict(name='a', href=re.compile(r'^/([a-zA-Z]+/)?')),
+                            dict(name='div', attrs={'id':'sitemap'}),
-                ]
+                            dict(name='ul', attrs={'class':'erste_zeile'}),
+                            dict(name='ul', attrs={'class':'zweite_zeile'}),
+                            dict(name='div', attrs={'class':'navi_top_container'})]
 
     feeds =  [
                    ('Newsticker', 'http://www.heise.de/newsticker/heise.rdf'),
-                   ('iX', 'http://www.heise.de/ix/news/news.rdf'),
+                   ('Auto', 'http://www.heise.de/autos/rss/news.rdf'),
-                      ('Technology Review', 'http://www.heise.de/tr/news-atom.xml'),
-                   ('mobil', 'http://www.heise.de/mobil/newsticker/heise-atom.xml'),
-                   ('Security', 'http://www.heise.de/security/news/news-atom.xml'),
-                   ('Netze', 'http://www.heise.de/netze/rss/netze-atom.xml'),
-                   ('Open Source', 'http://www.heise.de/open/news/news-atom.xml'),
-                   ('Resale ', 'http://www.heise.de/resale/rss/resale.rdf'),
                    ('Foto ', 'http://www.heise.de/foto/rss/news-atom.xml'),
-                   ('Autos', 'http://www.heise.de/autos/rss/news.rdf'),
                    ('Mac&i', 'http://www.heise.de/mac-and-i/news.rdf'),
+                   ('Mobile ', 'http://www.heise.de/mobil/newsticker/heise-atom.xml'),
+                   ('Netz ', 'http://www.heise.de/netze/rss/netze-atom.xml'),
+                   ('Open ', 'http://www.heise.de/open/news/news-atom.xml'),
+                   ('Resale ', 'http://www.heise.de/resale/rss/resale.rdf'),
+                   ('Security ', 'http://www.heise.de/security/news/news-atom.xml'),
+                   ('C`t', 'http://www.heise.de/ct/rss/artikel-atom.xml'),
+                   ('iX', 'http://www.heise.de/ix/news/news.rdf'),
+                   ('Mach-flott', 'http://www.heise.de/mach-flott/rss/mach-flott-atom.xml'),
                    ('Blog: Babel-Bulletin', 'http://www.heise.de/developer/rss/babel-bulletin/blog.rdf'),
                    ('Blog: Der Dotnet-Doktor', 'http://www.heise.de/developer/rss/dotnet-doktor/blog.rdf'),
                    ('Blog: Bernds Management-Welt', 'http://www.heise.de/developer/rss/bernds-management-welt/blog.rdf'),
-                   ('Blog: The World of IT', 'http://www.heise.de/developer/rss/world-of-it/blog.rdf'),
+                   ('Blog: IT conversation', 'http://www.heise.de/developer/rss/world-of-it/blog.rdf'),
-                   ('Blog: Kais bewegtes Web', 'http://www.heise.de/developer/rss/kais-bewegtes-web/blog.rdf')
+                   ('Blog: Kais bewegtes Web', 'http://www.heise.de/developer/rss/kais-bewegtes-web/blog.rdf')]
-             ]
 
     def print_version(self, url):
         return url + '?view=print'
+
+

recipes/the_week_magazine_free.recipe

@@ -5,7 +5,6 @@ www.theweek.com
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
-import re
 
 class TheWeek(BasicNewsRecipe):
     title                 = 'The Week Magazine'
@@ -21,23 +20,7 @@ class TheWeek(BasicNewsRecipe):
     encoding              = 'utf-8'
     use_embedded_content  = False
     language              = 'en'
-    preprocess_regexps      = [(re.compile(r'<h3><a href=.*</body>', re.DOTALL), lambda match: '</body>')]
+    auto_cleanup = True
-    remove_tags_before    = dict(name='h1')
-    remove_tags_after     = dict(name='div', attrs={'class':'articleSubscribe4free'})
-    remove_tags           = [
-                              dict(name='div', attrs={'class':['floatLeft','imageCaption','slideshowImageAttribution','postDate','utilities','cartoonInfo','left','middle','col300','articleSubscribe4free',' articleFlyout','articleFlyout floatRight','fourFreeBar']})
-                             ,dict(name='div', attrs={'id':['cartoonThumbs','rightColumn','header','partners']})
-                             ,dict(name='ul', attrs={'class':['slideshowNav','hotTopicsList topicList']})
-                              ]
-    remove_attributes     = ['width','height', 'style', 'font', 'color']
-    extra_css = '''
-                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
-                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
-                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
-                p {font-family:Arial,Helvetica,sans-serif;}
-                '''
-    filter_regexps = [r'www\.palmcoastdata\.com']
-
     feeds          =  [
                (u'News-Opinion', u'http://theweek.com/section/index/news_opinion.rss'),
                (u'Business', u'http://theweek.com/section/index/business.rss'),

resources/jacket/template.xhtml

@@ -40,8 +40,7 @@
         In addition you can add code to show the values of custom columns here.
         The value is available as _column_name and the title as _column_name_label.
         For example, if you have a custom column with label #genre, you can add it to
-        this template with:
+        this template with _genre_label and _genre. Note that the # is replaced by an underscore.
-        <div>{_genre_label}: {_genre}</div>
         -->
 
         <div class="cbj_comments">{comments}</div>

src/calibre/devices/kindle/driver.py

@@ -388,13 +388,9 @@ class KINDLE_FIRE(KINDLE2):
 
     EBOOK_DIR_MAIN = 'Documents'
     SUPPORTS_SUB_DIRS = False
+    SCAN_FROM_ROOT = True
+    SUPPORTS_SUB_DIRS_FOR_SCAN = True
     VENDOR_NAME = 'AMAZON'
     WINDOWS_MAIN_MEM = 'KINDLE'
 
-    def get_main_ebook_dir(self, for_upload=False):
-        if for_upload:
-            return self.EBOOK_DIR_MAIN
-        return ''
-
-
 

src/calibre/devices/nook/driver.py

@@ -81,7 +81,7 @@ class NOOK(USBMS):
         return [x.replace('#', '_') for x in components]
 
 class NOOK_COLOR(NOOK):
-    description    = _('Communicate with the Nook Color and TSR eBook readers.')
+    description    = _('Communicate with the Nook Color, TSR and Tablet eBook readers.')
 
     PRODUCT_ID  = [0x002, 0x003, 0x004]
     BCD         = [0x216]

src/calibre/devices/usbms/deviceconfig.py

@@ -28,6 +28,8 @@ class DeviceConfig(object):
     EXTRA_CUSTOMIZATION_DEFAULT = None
 
     SUPPORTS_SUB_DIRS = False
+    SUPPORTS_SUB_DIRS_FOR_SCAN = False # This setting is used when scanning for
+                                       # books when SUPPORTS_SUB_DIRS is False
     MUST_READ_METADATA = False
     SUPPORTS_USE_AUTHOR_SORT = False
 

src/calibre/devices/usbms/driver.py

@@ -202,7 +202,7 @@ class USBMS(CLI, Device):
             debug_print('USBMS: scan from root', self.SCAN_FROM_ROOT, ebook_dir)
             if not os.path.exists(ebook_dir): continue
             # Get all books in the ebook_dir directory
-            if self.SUPPORTS_SUB_DIRS:
+            if self.SUPPORTS_SUB_DIRS or self.SUPPORTS_SUB_DIRS_FOR_SCAN:
                 # build a list of files to check, so we can accurately report progress
                 flist = []
                 for path, dirs, files in os.walk(ebook_dir):