Pull from trunk

installer/linux/freeze.py

@@ -36,6 +36,7 @@ def freeze():
                        '/lib/libbz2.so.1',
                        '/usr/lib/libpoppler.so.4',
                        '/usr/lib/libxml2.so.2',
+                       '/usr/lib/libdbus-1.so.3',
                        '/usr/lib/libxslt.so.1',
                        '/usr/lib/libxslt.so.1',
                        '/usr/lib/libgthread-2.0.so.0',

src/calibre/constants.py

@@ -2,7 +2,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
 __docformat__ = 'restructuredtext en'
 __appname__   = 'calibre'
-__version__   = '0.4.139'
+__version__   = '0.4.140'
 __author__    = "Kovid Goyal <kovid@kovidgoyal.net>"
 '''
 Various run time constants.

src/calibre/devices/__init__.py

@@ -11,7 +11,8 @@ def devices():
     from calibre.devices.prs700.driver import PRS700
     from calibre.devices.cybookg3.driver import CYBOOKG3
     from calibre.devices.kindle.driver import KINDLE
-    return (PRS500, PRS505, PRS700, CYBOOKG3, KINDLE)
+    from calibre.devices.kindle.driver import KINDLE2
+    return (PRS500, PRS505, PRS700, CYBOOKG3, KINDLE, KINDLE2)
 
 import time
 

src/calibre/devices/interface.py

@@ -150,10 +150,13 @@ class Device(object):
         the device. 
         @param locations: Result of a call to L{upload_books}
         @param metadata: List of dictionaries. Each dictionary must have the
-        keys C{title}, C{authors}, C{cover}, C{tags}. The value of the C{cover} 
+        keys C{title}, C{authors}, C{author_sort}, C{cover}, C{tags}. 
+        The value of the C{cover} 
         element can be None or a three element tuple (width, height, data)
         where data is the image data in JPEG format as a string. C{tags} must be
         a possibly empty list of strings. C{authors} must be a string.
+        C{author_sort} may be None. It is upto the driver to decide whether to
+        use C{author_sort} or not.
         The dictionary can also have an optional key "tag order" which should be
         another dictionary that maps tag names to lists of book ids. The ids are
         ids from the book database.

src/calibre/devices/kindle/driver.py

@@ -4,13 +4,13 @@ __copyright__ = '2009, John Schember <john at nachtimwald.com>'
 Device driver for Amazon's Kindle
 '''
 
-import os, fnmatch
+import os
 
 from calibre.devices.usbms.driver import USBMS
 
 class KINDLE(USBMS):
     # Ordered list of supported formats
-    FORMATS     = ['azw', 'mobi', 'prc', 'txt']
+    FORMATS     = ['azw', 'mobi', 'prc', 'azw1', 'tpz', 'txt']
     
     VENDOR_ID   = [0x1949]
     PRODUCT_ID  = [0x0001]
@@ -35,10 +35,13 @@ class KINDLE(USBMS):
             if os.path.exists(path):
                 os.unlink(path)
                 
-                filepath, ext = os.path.splitext(path)
-                basepath, filename = os.path.split(filepath)
+                filepath = os.path.splitext(path)[0]
                 
                 # Delete the ebook auxiliary file
                 if os.path.exists(filepath + '.mbp'):
                     os.unlink(filepath + '.mbp')
 
+class KINDLE2(KINDLE):
+    
+    PRODUCT_ID = [0x0002]
+    BCD        = [0x0100]

src/calibre/devices/prs505/books.py

@@ -55,7 +55,7 @@ class Book(object):
     
     title        = book_metadata_field("title")
     authors      = book_metadata_field("author", \
-                            formatter=lambda x: x if x and x.strip() else "Unknown")
+                            formatter=lambda x: x if x and x.strip() else _('Unknown'))
     mime         = book_metadata_field("mime")
     rpath        = book_metadata_field("path")
     id           = book_metadata_field("id", formatter=int)
@@ -193,7 +193,7 @@ class BookList(_BookList):
         attrs = {
                  "title"  : info["title"], 
                  'titleSorter' : sortable_title(info['title']),
-                 "author" : info["authors"] if info['authors'] else 'Unknown', \
+                 "author" : info["authors"] if info['authors'] else _('Unknown'), 
                  "page":"0", "part":"0", "scale":"0", \
                  "sourceid":sourceid,  "id":str(cid), "date":"", \
                  "mime":mime, "path":name, "size":str(size)

src/calibre/ebooks/epub/iterator.py

@@ -98,7 +98,7 @@ class EbookIterator(object):
                     url    = re.compile(r'url\s*\([\'"]*(.+?)[\'"]*\)', re.DOTALL).search(block)
                     if url:
                         path = url.group(1).split('/')
-                        path = os.path.join(os.path.dirname(item.path), *path) 
+                        path = os.path.join(os.path.dirname(item.path), *path)
                         id = QFontDatabase.addApplicationFont(path)
                         if id != -1:
                             families = [unicode(f) for f in QFontDatabase.applicationFontFamilies(id)]
@@ -106,6 +106,8 @@ class EbookIterator(object):
                                 family = family.group(1).strip().replace('"', '')
                                 if family not in families:
                                     print 'WARNING: Family aliasing not supported:', block
+                                else:
+                                    print 'Loaded embedded font:', repr(family)
     
     def __enter__(self):
         self._tdir = TemporaryDirectory('_ebook_iter')

src/calibre/ebooks/lit/reader.py

@@ -284,7 +284,11 @@ class UnBinary(object):
                     state = 'get attr'
                 elif count > 0:
                     if not in_censorship:
-                        buf.write(encode(c))
+                        if c == '"':
+                            c = '"'
+                        elif c == '<':
+                            c = '&lt;'
+                        self.buf.write(c.encode('ascii', 'xmlcharrefreplace'))
                     count -= 1
                 if count == 0:
                     if not in_censorship:

src/calibre/ebooks/lrf/pdf/convert_from.py

@@ -3,6 +3,7 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
 ''''''
 
 import sys, os, subprocess, logging
+import errno
 from functools import partial
 from calibre import isosx, setup_cli_handlers, filename_to_utf8, iswindows, islinux
 from calibre.ebooks import ConversionError, DRMError
@@ -41,14 +42,26 @@ def generate_html(pathtopdf, tdir):
     try:
         os.chdir(tdir)
         try:
-            p = popen(cmd, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
+            p = popen(cmd, stderr=subprocess.PIPE)
         except OSError, err:
             if err.errno == 2:
                 raise ConversionError(_('Could not find pdftohtml, check it is in your PATH'), True)
             else:
                 raise
+
+        '''
         print p.stdout.read()
-        ret = p.wait()
+        '''
+        while True:
+            try:
+                ret = p.wait()
+                break
+            except OSError, e:
+                if e.errno == errno.EINTR:
+                    continue
+                else:
+                    raise
+
         if ret != 0:
             err = p.stderr.read()
             raise ConversionError, err

src/calibre/ebooks/metadata/opf2.py

@@ -18,7 +18,7 @@ from calibre.ebooks.chardet import xml_to_unicode
 from calibre import relpath
 from calibre.constants import __appname__, __version__
 from calibre.ebooks.metadata.toc import TOC
-from calibre.ebooks.metadata import MetaInformation
+from calibre.ebooks.metadata import MetaInformation, string_to_authors
 
 
 class Resource(object):
@@ -614,7 +614,7 @@ class OPF(object):
         def fget(self):
             ans = []
             for elem in self.authors_path(self.metadata):
-                ans.extend([x.strip() for x in self.get_text(elem).split(',')])
+                ans.extend(string_to_authors(self.get_text(elem)))
             return ans
 
         def fset(self, val):
@@ -624,8 +624,8 @@ class OPF(object):
             for author in val:
                 attrib = {'{%s}role'%self.NAMESPACES['opf']: 'aut'}
                 elem = self.create_metadata_element('creator', attrib=attrib)
-                self.set_text(elem, author)
-
+                self.set_text(elem, author.strip())
+            
         return property(fget=fget, fset=fset)
 
     @dynamic_property

src/calibre/ebooks/mobi/reader.py

@@ -505,7 +505,7 @@ def get_metadata(stream):
         except:
             import traceback
             traceback.print_exc()
-        return mi
+    return mi
         
         
 def option_parser():

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

@@ -37,17 +37,20 @@ class KeyMapper(object):
 
     @staticmethod
     def relate(size, base):
+        if size == 0:
+            return base
         size = float(size)
         base = float(base)
         if abs(size - base) < 0.1: return 0
         sign = -1 if size < base else 1
         endp = 0 if size < base else 36
         diff = (abs(base - size) * 3) + ((36 - size) / 100)
-        logb = abs(base - endp) 
+        logb = abs(base - endp)
         result = sign * math.log(diff, logb)
         return result
         
     def __getitem__(self, ssize):
+        ssize = asfloat(ssize, 0)
         if ssize in self.cache:
             return self.cache[ssize]
         dsize = self.map(ssize)
@@ -66,6 +69,7 @@ class ScaleMapper(object):
         self.dscale = float(dbase) / float(sbase)
 
     def __getitem__(self, ssize):
+        ssize = asfloat(ssize, 0)
         dsize = ssize * self.dscale
         return dsize
 

src/calibre/gui2/add.py

@@ -90,19 +90,25 @@ class AddFiles(Add):
         
         
     def run(self):
-        self.canceled = False
-        for c, book in enumerate(self.paths):
-            if self.pd.canceled:
-                self.canceled = True
-                break
-            format = os.path.splitext(book)[1]
-            format = format[1:] if format else None
-            stream = open(book, 'rb')
-            self.formats.append(format)
-            self.names.append(os.path.basename(book))
-            self.get_metadata(c, stream, stream_type=format, 
-                                  use_libprs_metadata=True)
-            self.wait_for_condition()
+        try:
+            self.canceled = False
+            for c, book in enumerate(self.paths):
+                if self.pd.canceled:
+                    self.canceled = True
+                    break
+                format = os.path.splitext(book)[1]
+                format = format[1:] if format else None
+                stream = open(book, 'rb')
+                self.formats.append(format)
+                self.names.append(os.path.basename(book))
+                self.get_metadata(c, stream, stream_type=format, 
+                                      use_libprs_metadata=True)
+                self.wait_for_condition()
+        finally:
+            self.disconnect(self.get_metadata, 
+                            SIGNAL('metadata(PyQt_PyObject, PyQt_PyObject)'), 
+                            self.metadata_delivered)
+            self.get_metadata = None
         
                     
     def process_duplicates(self):
@@ -178,34 +184,40 @@ class AddRecursive(Add):
     
    
     def run(self):
-        root = os.path.abspath(self.path)
-        for dirpath in os.walk(root):
-            if self.is_canceled():
-                return
-            self.emit(SIGNAL('update(PyQt_PyObject)'), 
-                      _('Searching in')+' '+dirpath[0])
-            self.books += list(self.db.find_books_in_directory(dirpath[0], 
-                                            self.single_book_per_directory))
-        self.books = [formats for formats in self.books if formats]
-        # Reset progress bar
-        self.emit(SIGNAL('searching_done()'))
-        
-        for c, formats in enumerate(self.books):
-            self.get_metadata.from_formats(c, formats)
-            self.wait_for_condition()
+        try:
+            root = os.path.abspath(self.path)
+            for dirpath in os.walk(root):
+                if self.is_canceled():
+                    return
+                self.emit(SIGNAL('update(PyQt_PyObject)'), 
+                          _('Searching in')+' '+dirpath[0])
+                self.books += list(self.db.find_books_in_directory(dirpath[0], 
+                                                self.single_book_per_directory))
+            self.books = [formats for formats in self.books if formats]
+            # Reset progress bar
+            self.emit(SIGNAL('searching_done()'))
+            
+            for c, formats in enumerate(self.books):
+                self.get_metadata.from_formats(c, formats)
+                self.wait_for_condition()
+                
+            # Add books to database
+            for c, x in enumerate(self.metadata):
+                mi, formats = x
+                if self.is_canceled():
+                    break
+                if self.db.has_book(mi):
+                    self.duplicates.append((mi, formats))
+                else:
+                    self.db.import_book(mi, formats, notify=False)
+                    self.number_of_books_added += 1
+                self.emit(SIGNAL('pupdate(PyQt_PyObject)'), c)
+        finally:
+            self.disconnect(self.get_metadata, 
+                            SIGNAL('metadataf(PyQt_PyObject, PyQt_PyObject)'), 
+                            self.metadata_delivered)
+            self.get_metadata = None
             
-        # Add books to database
-        for c, x in enumerate(self.metadata):
-            mi, formats = x
-            if self.is_canceled():
-                break
-            if self.db.has_book(mi):
-                self.duplicates.append((mi, formats))
-            else:
-                self.db.import_book(mi, formats, notify=False)
-                self.number_of_books_added += 1
-            self.emit(SIGNAL('pupdate(PyQt_PyObject)'), c)
- 
         
     def process_duplicates(self):
         if self.duplicates:

src/calibre/gui2/dialogs/config.py

@@ -180,11 +180,12 @@ class ConfigDialog(QDialog, Ui_Dialog):
         self.toolbar_button_size.setCurrentIndex(0 if icons == self.ICON_SIZES[0] else 1 if icons == self.ICON_SIZES[1] else 2)
         self.show_toolbar_text.setChecked(config['show_text_in_toolbar'])
 
-        for ext in BOOK_EXTENSIONS:
+        book_exts = sorted(BOOK_EXTENSIONS)
+        for ext in book_exts:
             self.single_format.addItem(ext.upper(), QVariant(ext))
         
         single_format = config['save_to_disk_single_format']
-        self.single_format.setCurrentIndex(BOOK_EXTENSIONS.index(single_format))
+        self.single_format.setCurrentIndex(book_exts.index(single_format))
         self.cover_browse.setValue(config['cover_flow_queue_length'])
         self.systray_notifications.setChecked(not config['disable_tray_notification'])
         from calibre.translations.compiled import translations
@@ -203,7 +204,7 @@ class ConfigDialog(QDialog, Ui_Dialog):
         self.pdf_metadata.setChecked(prefs['read_file_metadata'])
         
         added_html = False
-        for ext in BOOK_EXTENSIONS:
+        for ext in book_exts:
             ext = ext.lower()
             ext = re.sub(r'(x{0,1})htm(l{0,1})', 'html', ext)
             if ext == 'lrf' or is_supported('book.'+ext):

src/calibre/gui2/library.py

@@ -20,6 +20,7 @@ from calibre.gui2 import NONE, TableView, qstring_to_unicode, config, \
                          error_dialog
 from calibre.utils.search_query_parser import SearchQueryParser
 from calibre.ebooks.metadata.meta import set_metadata as _set_metadata
+from calibre.ebooks.metadata import string_to_authors
 
 class LibraryDelegate(QItemDelegate):
     COLOR    = QColor("blue")
@@ -364,12 +365,13 @@ class BooksModel(QAbstractTableModel):
         return data
 
 
-    def get_metadata(self, rows, rows_are_ids=False):
-        metadata = []
+    def get_metadata(self, rows, rows_are_ids=False, full_metadata=False):
+        metadata, _full_metadata = [], []
         if not rows_are_ids:
             rows = [self.db.id(row.row()) for row in rows]
         for id in rows:
             mi = self.db.get_metadata(id, index_is_id=True)
+            _full_metadata.append(mi)
             au = authors_to_string(mi.authors if mi.authors else [_('Unknown')])
             tags = mi.tags if mi.tags else []
             if mi.series is not None:
@@ -377,6 +379,7 @@ class BooksModel(QAbstractTableModel):
             info = {
                   'title'   : mi.title,
                   'authors' : au,
+                  'author_sort' : mi.author_sort,
                   'cover'   : self.db.cover(id, index_is_id=True),
                   'tags'    : tags,
                   'comments': mi.comments,
@@ -387,7 +390,10 @@ class BooksModel(QAbstractTableModel):
                 }
 
             metadata.append(info)
-        return metadata
+        if full_metadata:
+            return metadata, _full_metadata
+        else:
+            return metadata
 
     def get_preferred_formats_from_ids(self, ids, all_formats, mode='r+b'):
         ans = []
@@ -928,12 +934,8 @@ class DeviceBooksModel(BooksModel):
                     au = self.unknown
                 if role == Qt.EditRole:
                     return QVariant(au)
-                au = au.split(',')
-                authors = []
-                for i in au:
-                    authors += i.strip().split('&')
-                jau = [ a.strip() for a in authors ]
-                return QVariant("\n".join(jau))
+                authors = string_to_authors(au)
+                return QVariant("\n".join(authors))
             elif col == 2:
                 size = self.db[self.map[row]].size
                 return QVariant(BooksView.human_readable(size))

src/calibre/gui2/main.py

@@ -1,3 +1,4 @@
+from __future__ import with_statement
 __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
 import os, sys, textwrap, collections, traceback, time
@@ -43,7 +44,6 @@ from calibre.gui2.dialogs.search import SearchDialog
 from calibre.gui2.dialogs.choose_format import ChooseFormatDialog
 from calibre.gui2.dialogs.book_info import BookInfo
 from calibre.ebooks.metadata.meta import set_metadata
-from calibre.ebooks.metadata import MetaInformation
 from calibre.ebooks import BOOK_EXTENSIONS
 from calibre.library.database2 import LibraryDatabase2, CoverCache
 from calibre.parallel import JobKilled
@@ -398,7 +398,7 @@ class Main(MainWindow, Ui_MainWindow):
     def change_output_format(self, x):
         of = unicode(x).strip()
         if of != prefs['output_format']:
-            if of not in ('LRF', 'EPUB'):
+            if of not in ('LRF', 'EPUB', 'MOBI'):
                 warning_dialog(self, 'Warning', 
                                '<p>%s support is still in beta. If you find bugs, please report them by opening a <a href="http://calibre.kovidgoyal.net">ticket</a>.'%of).exec_()
             prefs.set('output_format', of)
@@ -910,12 +910,13 @@ class Main(MainWindow, Ui_MainWindow):
         if not self.device_manager or not rows or len(rows) == 0:
             return
         ids = iter(self.library_view.model().id(r) for r in rows)
-        metadata = self.library_view.model().get_metadata(rows)
+        metadata, full_metadata = self.library_view.model().get_metadata(
+                                                    rows, full_metadata=True)
         for mi in metadata:
             cdata = mi['cover']
             if cdata:
                 mi['cover'] = self.cover_to_thumbnail(cdata)
-        metadata = iter(metadata)
+        metadata, full_metadata = iter(metadata), iter(full_metadata)
         _files   = self.library_view.model().get_preferred_formats(rows,
                                     self.device_manager.device_class.FORMATS, 
                                     paths=True, set_metadata=True,
@@ -923,22 +924,15 @@ class Main(MainWindow, Ui_MainWindow):
         files = [getattr(f, 'name', None) for f in _files]
         bad, good, gf, names, remove_ids = [], [], [], [], []
         for f in files:
-            mi = metadata.next()
+            mi, smi = metadata.next(), full_metadata.next()
             id = ids.next()
             if f is None:
                 bad.append(mi['title'])
             else:
                 remove_ids.append(id)
-                aus = mi['authors'].split(',')
-                aus2 = []
-                for a in aus:
-                    aus2.extend(a.split('&'))
                 try:
-                    smi = MetaInformation(mi['title'], aus2)
-                    smi.comments = mi.get('comments', None)
-                    _f = open(f, 'r+b')
-                    set_metadata(_f, smi, f.rpartition('.')[2])
-                    _f.close()
+                    with open(f, 'r+b') as _f:
+                        set_metadata(_f, smi, f.rpartition('.')[2])
                 except:
                     print 'Error setting metadata in book:', mi['title']
                     traceback.print_exc()

src/calibre/gui2/viewer/main.py

@@ -9,7 +9,7 @@ from PyQt4.Qt import QMovie, QApplication, Qt, QIcon, QTimer, QWidget, SIGNAL, \
                      QDesktopServices, QDoubleSpinBox, QLabel, QTextBrowser, \
                      QPainter, QBrush, QColor, QStandardItemModel, QPalette, \
                      QStandardItem, QUrl, QRegExpValidator, QRegExp, QLineEdit, \
-                     QToolButton, QMenu, QInputDialog
+                     QToolButton, QMenu, QInputDialog, QAction
 
 from calibre.gui2.viewer.main_ui import Ui_EbookViewer
 from calibre.gui2.main_window import MainWindow
@@ -221,8 +221,14 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
         self.view.set_manager(self)
         self.pi = ProgressIndicator(self)
         self.toc.setVisible(False)
+        self.action_quit = QAction(self)
+        self.addAction(self.action_quit)
+        self.action_quit.setShortcut(Qt.CTRL+Qt.Key_Q)
+        self.connect(self.action_quit, SIGNAL('triggered(bool)'), 
+                     lambda x:QApplication.instance().quit())
         self.action_copy.setDisabled(True)
         self.action_metadata.setCheckable(True)
+        self.action_metadata.setShortcut(Qt.CTRL+Qt.Key_I)
         self.action_table_of_contents.setCheckable(True)
         self.action_reference_mode.setCheckable(True)
         self.connect(self.action_reference_mode, SIGNAL('triggered(bool)'), 

src/calibre/library/cli.py

@@ -174,6 +174,9 @@ def do_list(db, fields, sort_by, ascending, search_text, line_width, separator,
         return template.generate(data=data).render('xml')
     elif output_format == 'stanza':
         data = [i for i in data if i.has_key('fmt_epub')]
+        for x in data:
+            if isinstance(x['fmt_epub'], unicode):
+                x['fmt_epub'] = x['fmt_epub'].encode('utf-8')
         template = MarkupTemplate(STANZA_TEMPLATE)
         return template.generate(id="urn:calibre:main", data=data, subtitle=subtitle, 
                 sep=os.sep, quote=quote, updated=db.last_modified()).render('xml')

src/calibre/library/database2.py

@@ -916,12 +916,18 @@ class LibraryDatabase2(LibraryDatabase):
             else:
                 aid = self.conn.execute('INSERT INTO authors(name) VALUES (?)', (a,)).lastrowid
             try:
-                self.conn.execute('INSERT INTO books_authors_link(book, author) VALUES (?,?)', (id, aid))
+                self.conn.execute('INSERT INTO books_authors_link(book, author) VALUES (?,?)',
+                                   (id, aid))
             except IntegrityError: # Sometimes books specify the same author twice in their metadata
                 pass
+        ss = authors_to_sort_string(authors)    
+        self.conn.execute('UPDATE books SET author_sort=? WHERE id=?',
+                          (ss, id))
         self.conn.commit()
-        self.data.set(id, FIELD_MAP['authors'], ','.join([a.replace(',', '|') for a in authors]), row_is_id=True)
-        self.data.set(id, FIELD_MAP['author_sort'], self.data[self.data.row(id)][FIELD_MAP['authors']], row_is_id=True)
+        self.data.set(id, FIELD_MAP['authors'],
+                      ','.join([a.replace(',', '|') for a in authors]), 
+                      row_is_id=True)
+        self.data.set(id, FIELD_MAP['author_sort'], ss, row_is_id=True) 
         self.set_path(id, True)
         if notify:
             self.notify('metadata', [id])
@@ -1147,8 +1153,8 @@ class LibraryDatabase2(LibraryDatabase):
             path = pt.name
         else:
             path = path_or_stream
-            return run_plugins_on_import(path, format)
-
+        return run_plugins_on_import(path, format)
+    
     def add_books(self, paths, formats, metadata, uris=[], add_duplicates=True):
         '''
         Add a book to the database. The result cache is not updated.

src/calibre/manual/faq.rst

@@ -103,7 +103,7 @@ Device Integration
 
 What devices does |app| support?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-At the moment |app| has full support for the SONY PRS 500/505/700, Cybook Gen 3, Amazon Kindle as well as the iPhone. In addition, using the :guilabel:`Save to disk` function you can use it with any ebook reader that exports itself as a USB disk.
+At the moment |app| has full support for the SONY PRS 500/505/700, Cybook Gen 3, Amazon Kindle 1 and 2 as well as the iPhone. In addition, using the :guilabel:`Save to disk` function you can use it with any ebook reader that exports itself as a USB disk.
 
 I used |app| to transfer some books to my reader, and now the SONY software hangs every time I connect the reader?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

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

@@ -31,7 +31,7 @@ recipe_modules = ['recipe_' + r for r in (
            'pobjeda', 'chicago_breaking_news', 'glasgow_herald', 'linuxdevices',
            'hindu', 'cincinnati_enquirer', 'physics_world', 'pressonline',
            'la_republica', 'physics_today', 'chicago_tribune', 'e_novine',
-           'al_jazeera', 'winsupersite', 
+           'al_jazeera', 'winsupersite', 'borba',
           )]
 
 import re, imp, inspect, time, os

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

@@ -0,0 +1,92 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+
+'''
+borba.rs
+'''
+
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Borba(BasicNewsRecipe):
+    title                 = 'Borba Online'
+    __author__            = 'Darko Miletic'
+    description           = 'Dnevne novine Borba Online'
+    publisher             = 'IP Novine Borba'
+    category              = 'news, politics, Serbia'    
+    language              = _('Serbian')
+    oldest_article        = 1
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    encoding              = 'utf8'
+    remove_javascript     = True
+    use_embedded_content  = False
+    cover_url             = 'http://www.borba.rs/images/stories/novine/naslovna_v.jpg'
+    INDEX                 = u'http://www.borba.rs/'
+    extra_css = '@font-face {font-family: "serif0";src:url(res:///Data/FONT/serif0.ttf)} @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif0, serif1, serif} .article_description{font-family: serif0, serif1, serif}'
+    
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        , '--ignore-tables'
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
+     
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+
+    keep_only_tags = [dict(name='div', attrs={'class':'main'})]
+
+    remove_tags_after = dict(name='div',attrs={'id':'written_comments_title'})
+ 
+    remove_tags = [
+                     dict(name=['object','link','iframe','base','img'])
+                    ,dict(name='div',attrs={'id':'written_comments_title'})
+                  ]
+
+    feeds = [
+               (u'Najnovije vesti', u'http://www.borba.rs/content/blogsection/28/105/')
+              ,(u'Prvi plan'      , u'http://www.borba.rs/content/blogsection/4/92/'  )
+              ,(u'Dogadjaji'      , u'http://www.borba.rs/content/blogsection/21/83/' )
+              ,(u'Ekonomija'      , u'http://www.borba.rs/content/blogsection/5/35/'  )
+              ,(u'Komentari'      , u'http://www.borba.rs/content/blogsection/23/94/' )
+              ,(u'Svet'           , u'http://www.borba.rs/content/blogsection/7/36/'  )
+              ,(u'Sport'          , u'http://www.borba.rs/content/blogsection/6/37/'  )
+              ,(u'Fama'           , u'http://www.borba.rs/content/blogsection/25/89/' )
+              ,(u'B2 Dodatak'     , u'http://www.borba.rs/content/blogsection/30/116/')
+            ]
+
+    def preprocess_html(self, soup):
+        soup.html['xml:lang'] = 'sr-Latn-ME'
+        soup.html['lang']     = 'sr-Latn-ME'
+        mtag = '<meta http-equiv="Content-Language" content="sr-Latn-ME"/>'
+        soup.head.insert(0,mtag)
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll(font=True):
+            del item['font']
+        return soup
+
+    def parse_index(self):
+        totalfeeds = []
+        lfeeds = self.get_feeds()
+        for feedobj in lfeeds:
+            feedtitle, feedurl = feedobj
+            self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
+            articles = []
+            soup = self.index_to_soup(feedurl)
+            for item in soup.findAll('a', attrs={'class':'contentpagetitle'}):
+                url         = item['href']
+                title       = self.tag_to_string(item)
+                articles.append({
+                                      'title'      :title
+                                     ,'date'       :''
+                                     ,'url'        :url
+                                     ,'description':''
+                                    })
+            totalfeeds.append((feedtitle, articles))
+        return totalfeeds
+        

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

@@ -17,9 +17,19 @@ class NewYorkReviewOfBooks(BasicNewsRecipe):
     description = u'Book reviews'
     language = _('English')
     __author__ = 'Kovid Goyal' 
-    
+    needs_subscription = True
     remove_tags_before = {'id':'container'}
     remove_tags = [{'class':['noprint', 'ad', 'footer']}, {'id':'right-content'}]
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        if self.username is not None and self.password is not None:
+            br.open('http://www.nybooks.com/register/')
+            br.select_form(name='login')
+            br['email']   = self.username
+            br['password'] = self.password
+            br.submit()
+        return br
     
     def parse_index(self):
         root = html.fromstring(self.browser.open('http://www.nybooks.com/current-issue').read())
@@ -42,10 +52,4 @@ class NewYorkReviewOfBooks(BasicNewsRecipe):
                     articles.append(article)
                     
         return [('Current Issue', articles)]
-                    
-            
-        
-        
-        
-        
-        
+       

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

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