Merge from trunk

recipes/njp.recipe

@@ -1,14 +1,25 @@
 #!/usr/bin/env  python
 # -*- coding: utf-8 -*-
 
-__license__     = 'GPL v3'
+##
+## Title:        New Journal of Physics
+## License:      GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html
+## Copyright:    Chema Cort\xe9s
+##
+## Written:      Jan 2011
+## Last Edited:  Jan 2012 - by Kiavash
+##
+
+__license__   = 'GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html'
 __copyright__   = u'Chema Cort\xe9s - 2011-01-05'
-__version__     = 'v0.01'
-__date__        = '2011-01-05'
+__version__     = 'v0.5.0'
+__date__        = '2012-01-13'
+
 '''
 njp.org
 '''
 
+import re	# Import the regular expressions module.
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class NewJournalOfPhysics(BasicNewsRecipe):
@@ -19,14 +30,60 @@ class NewJournalOfPhysics(BasicNewsRecipe):
     category       = 'physics, journal, science'
     language       = 'en'
     
-    oldest_article = 30
-    max_articles_per_feed = 100
-
-    keep_only_tags = [dict(id=['fulltextContainer'])]
-    no_stylesheets=True
-    use_embedded_content=False
-
     feeds          = [(u'Latest Papers', u'http://iopscience.iop.org/1367-2630/?rss=1')]
     
+    cover_url      = 'http://images.iop.org/journals_icons/Info/1367-2630/cover.gif'
+    
+    oldest_article = 7
+    max_articles_per_feed = 30
+    timeout = 30
+    
+    no_stylesheets = True
+    use_embedded_content = False
+    remove_javascript = True
+    remove_empty_feeds = True
+    asciiize = True	# Converts all none ascii characters to their ascii equivalents
+    
+    keep_only_tags = [
+                        dict(id=['articleEvoContainer']),
+                     ]
+    
+    remove_tags    = [
+                        dict(name='div', attrs={'class':'affiliations'}), # Removes Shoow Affiliations
+                        dict(name='div', attrs={'class':'abst-icon-links'}), # Removes Tags and PDF export
+                        dict(name='p', attrs={'class':'studyimage'}),	# remove Studay image
+                        dict(name='a', attrs={'class':'icon powerpoint'}),	# remove Export to PowerPoint Slide
+                        dict(name='a', attrs={'title':'CrossRef'}),	# remove CrossRef icon
+                        dict(name='a', attrs={'title':'PubMed'}),	# remove PubMed icon
+                        dict(name='a', attrs={'e4f5426941':'true'}),	# remove cross ref image
+                        dict(name='img', attrs={'src':''}),	# remove empty image
+                        dict(name='a', attrs={'class':'closeChap'}),	# remove 'Close'
+                        dict(name='ul', attrs={'class':'breadcrumbs'}),	# remove Top breadcrumbs
+                     ]
+    
+    extra_css = 'body { font-family: verdana, helvetica, sans-serif; } \
+                 .introduction, .first { font-weight: bold; } \
+                 .cross-head { font-weight: bold; font-size: 125%; } \
+                 .cap, .caption { display: block; font-size: 80%; font-style: italic; } \
+                 .cap, .caption, .caption img, .caption span { display: block; margin: 5px auto; } \
+                 .byl, .byd, .byline img, .byline-name, .byline-title, .author-name, .author-position, \
+                    .correspondent-portrait img, .byline-lead-in, .name, .bbc-role { display: block; \
+                    font-size: 80%; font-style: italic; margin: 1px auto; } \
+                 .story-date, .published { font-size: 80%; } \
+                 table { width: 100%; } \
+                 td img { display: block; margin: 5px auto; } \
+                 ul { padding-top: 10px; } \
+                 ol { padding-top: 10px; } \
+                 li { padding-top: 5px; padding-bottom: 5px; } \
+                 h1 { font-size: 175%; font-weight: bold; } \
+                 h2 { font-size: 150%; font-weight: bold; } \
+                 h3 { font-size: 125%; font-weight: bold; } \
+                 h4, h5, h6 { font-size: 100%; font-weight: bold; }'
+    
+    # Remove the line breaks.
+    preprocess_regexps     = [(re.compile(r'<br[ ]*/>', re.IGNORECASE), lambda m: ''),
+                              (re.compile(r'<br[ ]*clear.*/>', re.IGNORECASE), lambda m: ''),
+                              ]
+
     def print_version(self, url):
-        return url+"/fulltext"
+        return url+"/article"

recipes/novilist_novine_hr.recipe

@@ -0,0 +1,101 @@
+__license__   = 'GPL v3'
+__copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>'
+'''
+novine.novilist.hr
+'''
+
+import re
+from calibre import strftime
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class NoviList_hr(BasicNewsRecipe):
+    title                 = 'Novi List'
+    __author__            = 'Darko Miletic'
+    description           = 'Vijesti iz Hrvatske'
+    publisher             = 'NOVI LIST d.d.'
+    category              = 'Novi list, politika, hrvatski dnevnik, Novine, Hrvatska, Croatia, News, newspaper, Hrvatski,Primorje, dnevni list, Rijeka'
+    oldest_article        = 2
+    max_articles_per_feed = 200
+    no_stylesheets        = True
+    encoding              = 'cp1250'
+    use_embedded_content  = False
+    language              = 'hr'
+    remove_empty_feeds    = True
+    publication_type      = 'newspaper'
+    needs_subscription    = 'required'
+    masthead_url          = 'http://novine.novilist.hr/images/system/novilist-logo.jpg'
+    extra_css             = """
+                               body{font-family: Geneva,Arial,Helvetica,Swiss,sans-serif }
+                               img{display:block; margin-bottom: 0.4em; margin-top: 0.4em}
+                               .nadnaslov,.podnaslov{font-size: small; text-align: center}
+                               .naslov{font-size: x-large; color: maroon; font-weight: bold}
+                            """
+
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        , 'linearize_tables' : True
+                        }
+
+    keep_only_tags = [
+                       dict(name='td', attrs={'class':['nadnaslov', 'naslov', 'podnaslov']}),
+                       dict(name='font', attrs={'face':'Geneva,Arial,Helvetica,Swiss'})
+                     ]
+
+    remove_tags = [dict(name=['meta', 'link', 'iframe', 'embed', 'object'])]
+    remove_attributes=['border', 'lang']
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        if self.username is not None and self.password is not None:
+            br.open('http://novine.novilist.hr/loginnow.asp')
+            br.select_form(nr=0)
+            br['username'] = self.username
+            br['password'] = self.password
+            br.submit()
+        return br
+
+    def parse_index(self):
+        articles = []
+        count = 0
+        soup = self.index_to_soup('http://novine.novilist.hr/')
+        #cover url
+        for alink in soup.findAll('a'):
+           if alink['href'].startswith('images/clanci/DOC_'):
+              self.cover_url = 'http://novine.novilist.hr/' + alink['href']
+        #feeds
+        for item in soup.findAll('td',attrs={'class':'tocrubrika'}):
+            count = count +1
+            if self.test and count > 2:
+               return articles
+            aitem = item.a
+            section  = self.tag_to_string(aitem)
+            feedlink = 'http://novine.novilist.hr/' + aitem['href']
+            feedpage = self.index_to_soup(feedlink)
+            self.report_progress(0, _('Fetching feed')+' %s...'%(section))
+            inarts   = []
+            for alink in feedpage.findAll('a',attrs={'class':'naslovlinkdesno'}):
+                url   = 'http://novine.novilist.hr/' + alink['href']
+                title = self.tag_to_string(alink)
+                date = strftime(self.timefmt)
+                description = ''
+                inarts.append({
+                                  'title'      :title
+                                 ,'date'       :date
+                                 ,'url'        :url
+                                 ,'description':description
+                                })
+            articles.append((section,inarts))
+        return articles
+
+    def print_version(self, url):
+        return url.replace('?WCI=Rubrike&','?WCI=Pretrazivac&')
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup

recipes/tagesspiegel.recipe

@@ -14,6 +14,7 @@ class TagesspiegelRSS(BasicNewsRecipe):
     language = 'de'
     oldest_article = 7
     max_articles_per_feed = 100
+    publication_type = 'newspaper'
 
     extra_css = '''
                 .hcf-overline{color:#990000; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;display:block}
@@ -33,13 +34,16 @@ class TagesspiegelRSS(BasicNewsRecipe):
     no_javascript = True
     remove_empty_feeds = True
     encoding = 'utf-8'
-    remove_tags = [{'class':'hcf-header'}]
+    remove_tags = [{'class':'hcf-header'}, {'class':'hcf-atlas'}, {'class':'hcf-date hcf-separate'}]
 
     def print_version(self, url):
         url = url.split('/')
         url[-1] = 'v_print,%s?p='%url[-1]
         return '/'.join(url)
 
+    def get_masthead_url(self):
+        return 'http://www.tagesspiegel.de/images/tsp_logo/3114/6.png'
+
     def parse_index(self):
         soup = self.index_to_soup('http://www.tagesspiegel.de/zeitung/')
 
@@ -51,7 +55,7 @@ class TagesspiegelRSS(BasicNewsRecipe):
         ans = []
         maincol = soup.find('div', attrs={'class':re.compile('hcf-main-col')})
 
-        for div in maincol.findAll(True, attrs={'class':['hcf-teaser', 'hcf-header', 'story headline']}):
+        for div in maincol.findAll(True, attrs={'class':['hcf-teaser', 'hcf-header', 'story headline', 'hcf-teaser hcf-last']}):
 
              if div['class'] == 'hcf-header':
                  try:
@@ -61,7 +65,7 @@ class TagesspiegelRSS(BasicNewsRecipe):
                  except:
                      continue
 
-             elif div['class'] == 'hcf-teaser' and getattr(div.contents[0],'name','') == 'h2':
+             elif div['class'] in ['hcf-teaser', 'hcf-teaser hcf-last'] and getattr(div.contents[0],'name','') == 'h2':
                  a = div.find('a', href=True)
                  if not a:
                      continue

setup/iso_639/de.po

@@ -6167,7 +6167,7 @@ msgstr ""
 
 #. name for deu
 msgid "German"
-msgstr ""
+msgstr "Deutsch"
 
 #. name for dev
 msgid "Domung"

src/calibre/customize/builtins.py

@@ -550,7 +550,7 @@ from calibre.devices.cybook.driver import CYBOOK, ORIZON
 from calibre.devices.eb600.driver import (EB600, COOL_ER, SHINEBOOK,
                 POCKETBOOK360, GER2, ITALICA, ECLICTO, DBOOK, INVESBOOK,
                 BOOQ, ELONEX, POCKETBOOK301, MENTOR, POCKETBOOK602,
-                POCKETBOOK701, POCKETBOOK360P)
+                POCKETBOOK701, POCKETBOOK360P, PI2)
 from calibre.devices.iliad.driver import ILIAD
 from calibre.devices.irexdr.driver import IREXDR1000, IREXDR800
 from calibre.devices.jetbook.driver import JETBOOK, MIBUK, JETBOOK_MINI
@@ -657,6 +657,7 @@ plugins += [
     MIBUK,
     SHINEBOOK,
     POCKETBOOK360, POCKETBOOK301, POCKETBOOK602, POCKETBOOK701, POCKETBOOK360P,
+    PI2,
     KINDLE, KINDLE2, KINDLE_DX, KINDLE_FIRE,
     NOOK, NOOK_COLOR,
     PRS505, PRST1,

src/calibre/devices/eb600/driver.py

@@ -286,3 +286,21 @@ class POCKETBOOK701(USBMS):
             drives['carda'] = main
         return drives
 
+class PI2(EB600):
+
+    name           = 'Infibeam Pi2 Device Interface'
+    gui_name       = 'Infibeam Pi2'
+    author         = 'Michael Scalet'
+    description    = _('Communicate with the Infibeam Pi2 reader.')
+    version        = (1,0,1)
+
+    # Ordered list of supported formats
+    FORMATS     = ['epub', 'mobi', 'prc', 'html', 'htm', 'doc', 'pdf', 'rtf',
+            'txt']
+
+    VENDOR_NAME      = 'INFIBEAM'
+    WINDOWS_MAIN_MEM = 'INFIBEAM_PI'
+    WINDOWS_CARD_A_MEM = 'INFIBEAM_PI'
+
+    DELETE_EXTS = ['.rec']
+

src/calibre/devices/hanvon/driver.py

@@ -61,7 +61,7 @@ class LIBREAIR(N516):
     FORMATS = ['epub', 'mobi', 'prc', 'fb2', 'rtf', 'txt', 'pdf']
 
     BCD = [0x399]
-    VENDOR_NAME      = 'ALURATEK'
+    VENDOR_NAME      = ['ALURATEK', 'LINUX']
     WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = 'FILE-STOR_GADGET'
     EBOOK_DIR_MAIN = 'Books'
 

src/calibre/ebooks/metadata/fb2.py

@@ -67,10 +67,10 @@ def get_metadata(stream):
         _parse_pubdate(root, mi)
     except:
         pass
-    try:
-        _parse_timestamp(root, mi)
-    except:
-        pass
+    #try:
+    #    _parse_timestamp(root, mi)
+    #except:
+    #    pass
 
     try:
         _parse_language(root, mi)

src/calibre/ebooks/oeb/display/cfi.coffee

@@ -557,6 +557,13 @@ class CanonicalFragmentIdentifier
         null
     # }}}
 
+    current_cfi: () -> # {{{
+        [winx, winy] = window_scroll_pos()
+        [winw, winh] = [window.innerWidth, window.innerHeight]
+        winw = max(winw, 400)
+        winh = max(winh, 600)
+    # }}}
+
 if window?
     window.cfi = new CanonicalFragmentIdentifier()
 else if process?

src/calibre/gui2/dialogs/scheduler.py

@@ -375,7 +375,7 @@ class SchedulerDialog(QDialog, Ui_Dialog):
             author=recipe.get('author', _('Unknown')),
             description=recipe.get('description', '')))
         self.download_button.setToolTip(
-                _('Downlod %s now')%recipe.get('title'))
+                _('Download %s now')%recipe.get('title'))
         scheduled = schedule_info is not None
         self.schedule.setChecked(scheduled)
         self.toggle_schedule_info()

src/calibre/library/custom_columns.py

@@ -279,12 +279,7 @@ class CustomColumns(object):
 
     def is_item_used_in_multiple(self, item, label=None, num=None):
         existing_tags = self.all_custom(label=label, num=num)
-        lt = [t.lower() for t in existing_tags]
-        try:
-            lt.index(item.lower())
-            return True
-        except ValueError:
-            return False
+        return item.lower() in {t.lower() for t in existing_tags}
 
     def delete_item_from_multiple(self, item, label=None, num=None):
         if label is not None:
@@ -302,10 +297,10 @@ class CustomColumns(object):
         books_affected = []
         if idx > -1:
             table, lt = self.custom_table_names(data['num'])
-            id_ = self.conn.get('SELECT id FROM %s where value = ?'%table,
+            id_ = self.conn.get('SELECT id FROM %s WHERE value = ?'%table,
                                 (existing_tags[idx],), all=False)
             if id_:
-                books = self.conn.get('SELECT book FROM %s where value = ?'%lt, (id_,))
+                books = self.conn.get('SELECT book FROM %s WHERE value = ?'%lt, (id_,))
                 if books:
                     books_affected = [b[0] for b in books]
                 self.conn.execute('DELETE FROM %s WHERE value=?'%lt, (id_,))

src/calibre/library/server/browse.py

@@ -669,10 +669,15 @@ class BrowseServer(object):
         args = {'id':id_, 'mi':mi,
                 }
         ccache = self.categories_cache() if add_category_links else {}
+        ftitle = fauthors = ''
         for key in mi.all_field_keys():
             val = mi.format_field(key)[1]
             if not val:
                 val = ''
+            if key == 'title':
+                ftitle = xml(val, True)
+            elif key == 'authors':
+                fauthors = xml(val, True)
             if add_category_links:
                 added_key = False
                 fm = mi.metadata_for_field(key)
@@ -710,8 +715,8 @@ class BrowseServer(object):
                     args[key] = xml(val, True)
             else:
                 args[key] = xml(val, True)
-        fname = quote(ascii_filename(args['title']) + ' - ' +
-                ascii_filename(args['authors']))
+        fname = quote(ascii_filename(ftitle) + ' - ' +
+                ascii_filename(fauthors))
         return args, fmt, fmts, fname
 
     @Endpoint(mimetype='application/json; charset=utf-8')

src/calibre/translations/calibre.pot

@@ -5,8 +5,8 @@
 msgid ""
 msgstr ""
 "Project-Id-Version: calibre 0.8.35\n"
-"POT-Creation-Date: 2012-01-13 09:36+IST\n"
-"PO-Revision-Date: 2012-01-13 09:36+IST\n"
+"POT-Creation-Date: 2012-01-13 17:39+IST\n"
+"PO-Revision-Date: 2012-01-13 17:39+IST\n"
 "Last-Translator: Automatically generated\n"
 "Language-Team: LANGUAGE\n"
 "MIME-Version: 1.0\n"
@@ -9012,7 +9012,7 @@ msgstr ""
 
 #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/scheduler.py:378
 #, python-format
-msgid "Downlod %s now"
+msgid "Download %s now"
 msgstr ""
 
 #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/scheduler.py:382