Sync to trunk

installer/linux/freeze.py

@@ -38,6 +38,10 @@ def freeze():
                        '/usr/lib/libxml2.so.2',
                        '/usr/lib/libxslt.so.1',
                        '/usr/lib/libxslt.so.1',
+                       '/usr/lib/libgthread-2.0.so.0',
+                       '/usr/lib/libglib-2.0.so.0',
+                       '/usr/lib/gcc/i686-pc-linux-gnu/4.3.3/libstdc++.so.6',
+                       '/usr/lib/libpng12.so.0',
                        '/usr/lib/libexslt.so.0',
                        '/usr/lib/libMagickWand.so',
                        '/usr/lib/libMagickCore.so',

src/calibre/__init__.py

@@ -69,7 +69,7 @@ def sanitize_file_name(name, substitute='_', as_unicode=False):
     one = re.sub(r'^\.+$', '_', one)
     if as_unicode:
         one = one.decode(filesystem_encoding)
-    return one
+    return one.replace('..', '_')
 
 
 class CommandLineError(Exception):
@@ -382,8 +382,10 @@ def walk(dir):
         for f in record[-1]:
             yield os.path.join(record[0], f)
 
-def strftime(fmt, t=time.localtime()):
+def strftime(fmt, t=None):
     ''' A version of strtime that returns unicode strings. '''
+    if t is None:
+        t = time.localtime()
     if iswindows:
         if isinstance(fmt, unicode):
             fmt = fmt.encode('mbcs')

src/calibre/constants.py

@@ -2,7 +2,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
 __docformat__ = 'restructuredtext en'
 __appname__   = 'calibre'
-__version__   = '0.4.136'
+__version__   = '0.4.137'
 __author__    = "Kovid Goyal <kovid@kovidgoyal.net>"
 '''
 Various run time constants.

src/calibre/devices/prs505/driver.py

@@ -32,7 +32,7 @@ class PRS505(Device):
     BCD          = [0x229]  #: Needed to disambiguate 505 and 700 on linux
     PRODUCT_NAME = 'PRS-505'
     VENDOR_NAME  = 'SONY'
-    FORMATS      = ['lrf', 'epub', 'lrx', 'rtf', 'pdf', 'txt']
+    FORMATS      = ['epub', 'lrf', 'lrx', 'rtf', 'pdf', 'txt']
     
     MEDIA_XML    = 'database/cache/media.xml'
     CACHE_XML    = 'Sony Reader/database/cache.xml'

src/calibre/ebooks/metadata/ncx.xml

@@ -1,6 +1,7 @@
 <?xml version="1.0"  encoding="UTF-8"?>
 <?python
 from uuid import uuid4
+import re
 ?>
 <ncx version="2005-1" 
      xml:lang="en" 
@@ -19,7 +20,7 @@ from uuid import uuid4
     <py:def function="navpoint(np, level)">
         ${'%*s'%(4*level,'')}<navPoint id="${str(uuid4())}" playOrder="${str(np.play_order)}">
             ${'%*s'%(4*level,'')}<navLabel>
-                ${'%*s'%(4*level,'')}<text>${np.text}</text>
+                ${'%*s'%(4*level,'')}<text>${re.sub(r'\s+', ' ', np.text)}</text>
             ${'%*s'%(4*level,'')}</navLabel>
             ${'%*s'%(4*level,'')}<content src="${unicode(np.href)+(('#' + unicode(np.fragment)) if np.fragment else '')}" />
             <py:for each="np2 in np">${navpoint(np2, level+1)}</py:for>

src/calibre/ebooks/mobi/reader.py

@@ -186,6 +186,8 @@ class MobiReader(object):
         self.processed_html = self.processed_html.decode(self.book_header.codec, 'ignore')
         for pat in ENCODING_PATS:
             self.processed_html = pat.sub('', self.processed_html)
+        self.processed_html = re.sub(r'&(\S+?);', entity_to_unicode,
+                                     self.processed_html)
         self.extract_images(processed_records, output_dir)
         self.replace_page_breaks()
         self.cleanup_html()
@@ -271,6 +273,8 @@ class MobiReader(object):
                 for key in tag.attrib.keys():
                     tag.attrib.pop(key)
                 continue
+            if tag.tag == 'pre' and not tag.text:
+                tag.tag = 'div'
             styles, attrib = [], tag.attrib
             if attrib.has_key('style'):
                 style = attrib.pop('style').strip()
@@ -452,6 +456,7 @@ class MobiReader(object):
             pos = end
         self.processed_html += self.mobi_html[pos:]
         
+    
     def extract_images(self, processed_records, output_dir):
         if self.verbose:
             print 'Extracting images...'

src/calibre/gui2/main.py

@@ -330,11 +330,16 @@ class Main(MainWindow, Ui_MainWindow):
             self.cover_flow.setVisible(False)
             if not config['separate_cover_flow']:
                 self.library.layout().addWidget(self.cover_flow)
-            self.connect(self.cover_flow, SIGNAL('currentChanged(int)'), self.sync_cf_to_listview)
+            self.connect(self.cover_flow, SIGNAL('currentChanged(int)'), 
-            self.connect(self.cover_flow, SIGNAL('itemActivated(int)'), self.show_book_info)
+                         self.sync_cf_to_listview)
-            self.connect(self.status_bar.cover_flow_button, SIGNAL('toggled(bool)'), self.toggle_cover_flow)
+            self.connect(self.cover_flow, SIGNAL('itemActivated(int)'), 
-            self.connect(self.cover_flow, SIGNAL('stop()'), self.status_bar.cover_flow_button.toggle)
+                         self.show_book_info)
-            QObject.connect(self.library_view.selectionModel(), SIGNAL('currentRowChanged(QModelIndex, QModelIndex)'),
+            self.connect(self.status_bar.cover_flow_button, 
+                         SIGNAL('toggled(bool)'), self.toggle_cover_flow)
+            self.connect(self.cover_flow, SIGNAL('stop()'), 
+                         self.status_bar.cover_flow_button.toggle)
+            QObject.connect(self.library_view.selectionModel(), 
+                            SIGNAL('currentRowChanged(QModelIndex, QModelIndex)'),
                             self.sync_cf_to_listview)
             self.db_images = DatabaseImages(self.library_view.model())
             self.cover_flow.setImages(self.db_images)
@@ -482,7 +487,8 @@ class Main(MainWindow, Ui_MainWindow):
         if not hasattr(index, 'row') and self.library_view.currentIndex().row() != index:
             index = self.library_view.model().index(index, 0)
             self.library_view.setCurrentIndex(index)
-        if hasattr(index, 'row') and self.cover_flow.isVisible() and self.cover_flow.currentSlide() != index.row():
+        if hasattr(index, 'row') and self.cover_flow.isVisible() and \
+                self.cover_flow.currentSlide() != index.row():
             self.cover_flow.setCurrentSlide(index.row())
 
     def another_instance_wants_to_talk(self, msg):
@@ -709,6 +715,7 @@ class Main(MainWindow, Ui_MainWindow):
                 t.process_duplicates()
         if t.number_of_books_added > 0:
             self.library_view.model().books_added(t.number_of_books_added)
+            self.db_images.reset()
         
     def upload_books(self, files, names, metadata, on_card=False, memory=None):
         '''

src/calibre/manual/faq.rst

@@ -28,7 +28,7 @@ What formats does |app| support conversion to/from?
 |                   |        |                  |                       |                       |
 |                   |  LIT   |       ✔          |          ✔            |          ✔            |
 |                   |        |                  |                       |                       |
-|                   |  PRC   |       ✔          |          ✔            |          ✔            |
+|                   |  PRC** |       ✔          |          ✔            |          ✔            |
 |                   |        |                  |                       |                       |
 |                   |  EPUB  |       ✔          |          ✔            |          ✔            |
 |                   |        |                  |                       |                       |
@@ -49,6 +49,7 @@ What formats does |app| support conversion to/from?
 |                   |  LRS   |                  |          ✔            |                       |
 +-------------------+--------+------------------+-----------------------+-----------------------+
 
+** PRC is a generic format, |app| supports PRC files with TextRead and MOBIBook headers
 
 
 What are the best source formats to convert?
@@ -146,7 +147,7 @@ When you first run |app|, it will ask you for a folder in which to store your bo
 Why doesn't |app| let me store books in my own directory structure?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-The whole point if |app|'s library management features is that they provide an interface for locating books that is *much* more efficient than any possible directory scheme you could come up with for your collection. Indeed, once you become comfortable using |app|'s interface to find, sort and browse your collection, you wont ever feel the need to hunt through the files on your disk to find a book again. By managing books in its own directory struture of Author -> Title -> Book files, |app| is able to achieve a high level of reliability and standardization.  
+The whole point of |app|'s library management features is that they provide an interface for locating books that is *much* more efficient than any possible directory scheme you could come up with for your collection. Indeed, once you become comfortable using |app|'s interface to find, sort and browse your collection, you wont ever feel the need to hunt through the files on your disk to find a book again. By managing books in its own directory struture of Author -> Title -> Book files, |app| is able to achieve a high level of reliability and standardization.  
 
 Why doesn't |app| have a column for foo?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

src/calibre/trac/plugins/download.py

@@ -1,26 +1,7 @@
 __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
-import re
-from pkg_resources import resource_filename
-
-from trac.core import Component, implements
-from trac.web.chrome import INavigationContributor, ITemplateProvider, add_stylesheet
-from trac.web.main import IRequestHandler
-from trac.util import Markup
-
-
 __appname__ = 'calibre'
-DOWNLOAD_DIR = '/var/www/calibre.kovidgoyal.net/htdocs/downloads'
+import re, textwrap
-MOBILEREAD = 'https://dev.mobileread.com/dist/kovid/calibre/'
-
-class OS(dict):
-    """Dictionary with a default value for unknown keys."""
-    def __init__(self, dict):
-        self.update(dict)
-        if not dict.has_key('img'):
-            self['img'] = self['name']
-
-class Distribution(object):
 
 DEPENDENCIES = [
             #(Generic, version, gentoo, ubuntu, fedora)
@@ -30,7 +11,7 @@ class Distribution(object):
             ('libusb', '0.1.12', None, None, None),
             ('Qt', '4.4.0', 'qt', 'libqt4-core libqt4-gui', 'qt4'),
             ('PyQt', '4.4.2', 'PyQt4', 'python-qt4', 'PyQt4'),
-        ('mechanize for python', '0.1.11', 'dev-python/mechanize', 'python-mechanize', 'python-mechanize'),
+            ('python-mechanize', '0.1.11', 'dev-python/mechanize', 'python-mechanize', 'python-mechanize'),
             ('ImageMagick', '6.3.5', 'imagemagick', 'imagemagick', 'ImageMagick'),
             ('xdg-utils', '1.0.2', 'xdg-utils', 'xdg-utils', 'xdg-utils'),
             ('dbus-python', '0.82.2', 'dbus-python', 'python-dbus', 'dbus-python'),
@@ -40,51 +21,59 @@ class Distribution(object):
             ('help2man', '1.36.4', 'help2man', 'help2man', 'help2man'),
             ]
         
-    DISTRO_MAP = {'gentoo':2, 'ubuntu':3, 'fedora':4, 'debian':3}
 
-    INSTALLERS = ('emerge -avn', 'apt-get install', 'yum install')
+class CoolDistro:
-    AS_ROOT    = (True, False, True)
     
-    TITLEMAP = {'gentoo':'Gentoo', 'ubuntu':'Ubuntu Intrepid Ibex',
+    def __init__(self, name, title, prefix=''):
-                'fedora':'Fedora 10', 'debian':'Debian sid', 'generic': 'Install from source'}
+        self.title = title
+        url = prefix + '/chrome/dl/images/%s_logo.png'
+        self.img = url%name
 
-    MANUAL_MAP = {
+def get_linux_data(version='1.0.0'):
-                  'fedora' : '''<li>You have to upgrade Qt to at least 4.4.0 and PyQt to at least 4.4.2</li>''',
+    data = {'version':version, 'app':__appname__}
-                  }
+    data['title'] = 'Download calibre for linux'
+    data['supported'] = []
+    for name, title in [
+                        ('ubuntu', 'Ubuntu Jaunty Jackalope'),
+                        ('debian', 'Debian Sid'),
+                        ('exherbo', 'Exherbo'),
+                        ]:
+        data['supported'].append(CoolDistro(name, title, 
+                                        prefix='http://calibre.kovidgoyal.net'))
+        data['dependencies'] = DEPENDENCIES
+    return data
 
-    def __init__(self, os):
+if __name__ == '__main__':
-        self.os = os
+    import os
-        self.img = os
+    from calibre.utils.genshi.template import MarkupTemplate
-        self.title = self.TITLEMAP[os]
+    import cherrypy
-        self.app = __appname__
+    class Test:
-        self.is_generic = os == 'generic'
+        def index(self):
-        offset = 0
+            raw = open(os.path.dirname(os.path.abspath(__file__))+'/templates/linux.html').read()
-        if not self.is_generic:
+            return MarkupTemplate(raw).generate(**get_linux_data()).render('xhtml')
-            index = self.DISTRO_MAP[self.os]
+        index.exposed = True
-            if os == 'debian':
+    t = Test()
-                self.as_root = True  
+    t.index()    
-            else: self.as_root = self.AS_ROOT[index-2]
+    cherrypy.quickstart(t)
-            prefix = '' 
-            if not self.as_root: prefix =  'sudo '
-            cmd = prefix + self.INSTALLERS[index-2]
-            pre = ' \\\n '.ljust(len(cmd)+4)
-            for dep in self.DEPENDENCIES:
-                if len(cmd) > 70+offset:
-                    offset += 70
-                    cmd += pre
-                cmd += ' ' 
-                if dep[index]: cmd += dep[index]
-            self.command = cmd.strip()
-            easy_install = 'easy_install'
-            if os == 'debian':
-                easy_install = 'easy_install-2.5'
-            self.command += '\n'+prefix+easy_install+' -U calibre \n'+prefix+'calibre_postinstall'
-            try:
-                self.manual = Markup(self.MANUAL_MAP[os])
-            except KeyError:
-                self.manual = None
 else:
-            self.img = 'linux'
+    from pkg_resources import resource_filename
+    
+    from trac.core import Component, implements
+    from trac.web.chrome import INavigationContributor, ITemplateProvider, add_stylesheet
+    from trac.web.main import IRequestHandler
+    from trac.util import Markup
+    
+    
+    
+    DOWNLOAD_DIR = '/var/www/calibre.kovidgoyal.net/htdocs/downloads'
+    MOBILEREAD = 'https://dev.mobileread.com/dist/kovid/calibre/'
+    
+    class OS(dict):
+        """Dictionary with a default value for unknown keys."""
+        def __init__(self, dict):
+            self.update(dict)
+            if not dict.has_key('img'):
+                self['img'] = self['name']
     
         
     class Download(Component):
@@ -125,16 +114,6 @@ class Download(Component):
                         return self.osx(req)
                     elif os == 'linux':
                         return self.linux(req)
-                elif 'binary' in os:
-                    return self.linux_binary(req)
-                else:
-                    return self.linux_distro(req, os)       
-    
-    def linux_distro(self, req, os):
-        version = self.version_from_filename()
-        distro = Distribution(os)
-        data = dict(distro=distro,title=distro.title, version=version)
-        return 'distro.html', data, None
         
         def top_level(self, req):
             operating_systems = [
@@ -189,10 +168,6 @@ select Install.</li>
     '''%dict(appname=__appname__)))
             return 'binary.html', data, None
         
-    def linux_binary(self, req):
-        version = self.version_from_filename()
-        return 'pyinstaller.html', {'app':__appname__, 'version':version}, None
-    
         def osx(self, req):
             version = self.version_from_filename()
             file = 'calibre-%s.dmg'%(version,) 
@@ -212,20 +187,11 @@ select Install.</li>
             return 'binary.html', data, None
         
         def linux(self, req):
-        operating_systems = [
+            data = get_linux_data(version=self.version_from_filename())
-            OS({'name' : 'binary', 'title': 'Binary Installer'}),
+            return 'linux.html', data, None
-            OS({'name' : 'gentoo', 'title': 'Gentoo'}),
-            OS({'name' : 'ubuntu', 'title': 'Ubuntu'}),
-            OS({'name' : 'fedora', 'title': 'Fedora'}),
-            OS({'name' : 'debian', 'title': 'Debian'}),
-            OS({'name' : 'generic','title': 'Install from source', 'img':'linux'}),
-                             ]
-        data = dict(title='Choose linux distribution', width=100,
-                    operating_systems=operating_systems, font_size='x-large', top_level=False)
-        return 'download.html', data, None
                                 
     
-LINUX_INSTALLER = r'''
+    LINUX_INSTALLER = textwrap.dedent(r'''
     import sys, os, shutil, tarfile, subprocess, tempfile, urllib2, re, stat
     
     MOBILEREAD='https://dev.mobileread.com/dist/kovid/calibre/'
@@ -416,4 +382,5 @@ def main():
         pi = os.path.join(destdir, 'calibre_postinstall')
         subprocess.call(pi, shell=True)
         return 0
-'''
+    ''')
+    

src/calibre/trac/plugins/templates/distro.html

@@ -1,68 +0,0 @@
-<!DOCTYPE html
-    PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml"
-      xmlns:py="http://genshi.edgewall.org/"
-      xmlns:xi="http://www.w3.org/2001/XInclude">
-  <xi:include href="layout.html" />
-  <head>
-    <title>$title</title>
-  </head>
-
-  <body>
-    <div id="ctxtnav" class="nav"></div>
-
-    <div id="content" class="download">
-      <h1><img src="${href.chrome('/dl/images/%s_logo.png'%(distro.img,))}" valign="middle" width="60" height="80"/> $title</h1>
-      See the <a href="/wiki/Changelog">Changelog</a> for the changes in the latest version. <span py:if="not distro.is_generic"><b>Note:</b> As of 0.4.80 this install
-      will not work on 64-bit CPUs. Try the precompiled binary available <a href="/download_binary">here</a> instead.</span>
-      <div py:if="not distro.is_generic">
-        First verify that you have a sufficiently new installation of python
-        <pre class="wiki">python --version</pre> should return at least 2.5.1<br />
-        <p py:if="distro.os == 'gentoo'">
-            Make sure your python is compiled with the sqlite USE flag. 
-        </p>
-        <br />
-        Run the following commands in a terminal <span py:if="distro.as_root">as root</span>
-        <pre class="wiki">${distro.command}</pre>
-        <div py:if="distro.manual">
-            <h2>Manual steps</h2>
-            <ul>
-                ${distro.manual}
-            </ul>
-        </div>
-      </div>
-      <div py:if="distro.is_generic">
-        <ol>
-            <li>Make sure that your system has <code>python &gt;= 2.5</code></li>
-            <li>Install the various dependencies listed below: Make sure that any python packages are installed into python2.5 (e.g. setuptools, python-imaging, PyQt4, etc). You will also have to install the development versions of the packages (these packages usually have  -dev added to their names).</li>
-            <li>Run the following commands in a terminal:
-            <pre class="wiki">
-wget -O- http://calibre.kovidgoyal.net/downloads/calibre-${version}.tar.gz | tar xvz 
-cd calibre*
-python setup.py build &amp;&amp; sudo python setup.py install
-            </pre></li>
-        </ol>
-        <h2>Dependencies</h2>
-        <table border="1" cellpadding="10">
-            <tr><th style="font-weight:bold">Name</th><th style="font-weight:bold">Minimum version</th></tr>
-            <tr py:for="dep in distro.DEPENDENCIES">
-                <td>${dep[0]}</td><td>${dep[1]}</td>
-            </tr>
-            <tr>
-                <td>HAL</td><td>0.5.10</td>
-            </tr>
-        </table>
-      </div>
-      While you wait for the installation to complete, please consider donating to support the development of ${distro.app}.
-        <div>
-            <form action="https://www.paypal.com/cgi-bin/webscr" method="post">
-                <input type="hidden" name="cmd" value="_s-xclick" />
-                <input type="hidden" name="hosted_button_id" value="3029289" />
-                <input type="image" src="https://www.paypal.com/en_US/i/btn/btn_donateCC_LG.gif" border="0" name="submit" alt="Donate to support calibre development" />
-                <img alt="" border="0" src="https://www.paypal.com/en_US/i/scr/pixel.gif" width="1" height="1" />
-          </form>
-        </div>
-    </div>
-  </body>
-</html>

src/calibre/trac/plugins/templates/linux.html

@@ -0,0 +1,155 @@
+<!DOCTYPE html
+    PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml"
+      xmlns:py="http://genshi.edgewall.org/"
+      xmlns:xi="http://www.w3.org/2001/XInclude">
+  <xi:include href="layout.html" />
+  <head>
+    <title>${title}</title>
+    <style type="text/css">
+        table tr th.distro_type { 
+            font-family: monospace;
+            font-weight: bold;
+            font-size: larger;
+            vertical-align:middle;
+            text-align: center;
+            border-bottom: solid 1pt black;
+         }
+        
+        .right {
+            margin-left:2em;
+            border-left: solid 1pt black;
+            }
+        
+        table#install_info {
+            border-collapse: collapse;
+            border-width: 1pt;
+            border-style: solid;
+            table-layout: fixed;
+            width: 95%;
+            background: #F7F7F0 none repeat scroll 0 0;
+        }
+        table#dependencies {
+            border-collapse: collapse;
+            border-width: 0pt;
+            font-family:monospace;
+        }
+        .tdata {vertical-align: top;}
+    </style>
+  </head>
+
+  <body>
+    <div id="ctxtnav" class="nav"></div>
+    <div id="content" class="download">
+        <h1>${title}</h1>
+        <p>
+            The latest release of ${app} is ${version}. See the 
+            <a href="/wiki/Changelog">Changelog</a> for a list of new features.
+        </p>
+        <p>
+            ${app} is available in the software repositories of the following 
+            linux distributions:
+            <table id="install_info">
+                <col width="150" /><col width="*" />
+                <tr>
+                    <th class="left distro_type">Supported<br/>distributions</th>
+                    <th class="right distro_type">Unsupported distributions</th>
+                </tr>
+                <tr class="tdata">
+                    <td class="left" style="overflow-y:scroll">
+                        <div py:for="distro in supported" 
+                        style="text-align:center;margin-top:2ex;">
+                            <div>
+                                <img width="64px" height="64px" 
+                                    src="${distro.img}" alt="${distro.title}" />
+                            </div>
+                            ${distro.title}
+                        </div>
+                    </td>
+                    <td class="right">
+                        <div style="margin-left:2em">
+                            <h3>Binary install</h3>
+                            <p>
+                                ${app} has a binary installer that has been 
+                                tested on a number of distributions on both 
+                                32-bit and 64-bit x86 machines. To install, 
+                                copy paste the following command into a terminal 
+                                and press Enter: 
+                            </p>
+                            <pre class="wiki">
+sudo python -c "import urllib2; exec urllib2.urlopen('http://calibre.kovidgoyal.net/download_linux_binary_installer').read(); main()"
+                            </pre>
+                            <h4>Note</h4>
+                            <ul>
+                                <li>
+                                    When running the command line utilities,
+                                    they will segfault after completion. This can
+                                    be ignored.
+                                </li>
+                                <li>
+                                    You must have help2man and xdg-utils installed 
+                                    on your system before running the installer.
+                                </li>
+                                <li>
+                                    On a 64bit machine, you must have 32-bit versions
+                                    of common libraries like X11, freetype, fontconfig,
+                                    expat and their varios dependencies installed.
+                                </li>
+                            </ul>
+                            <h3>Source install</h3>
+                            <p>
+                                <ol>
+                                    <li>
+                                        Make sure your system has python &ge; ${dependencies[0][1]}
+                                    </li>
+                                    <li>
+                                        Install the various dependencies listed below
+                                    </li>
+                                    <li>
+                                        Run the following commands in a terminal:
+                                    </li>
+                                </ol>
+                                <pre class="wiki">
+wget -O- http://calibre.kovidgoyal.net/downloads/${app}-${version}.tar.gz | tar xvz 
+cd calibre*
+python setup.py build &amp;&amp; sudo python setup.py install
+                                </pre>
+                                Note that if your distribution does not have a
+                                correctly compiled libunrar.so, ${app} will not 
+                                support rar files.
+                            </p>
+                        </div>
+                    </td>
+                </tr>
+            </table>
+        </p>
+        <p>
+            While you wait for the download to complete, please consider 
+            donating to support the development of ${app}.
+        </p>
+      <div>
+        <form action="https://www.paypal.com/cgi-bin/webscr" method="post">
+            <input type="hidden" name="cmd" value="_s-xclick" />
+            <input type="image" src="https://www.paypal.com/en_US/i/btn/btn_donateCC_LG.gif" border="0" name="submit" alt="PayPal - The safer, easier way to pay online!" />
+            <img alt="" border="0" src="https://www.paypal.com/en_US/i/scr/pixel.gif" width="1" height="1" />
+            <input type="hidden" name="encrypted" value="-----BEGIN PKCS7-----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-----END PKCS7-----" />
+        </form>
+      </div>
+      <hr/>
+      <h3>Dependencies</h3>
+      ${app} has the following dependencies (the listed version is the minimum version)
+      <br/><br/>
+      <table id="dependencies">
+          <tr>
+              <th class="distro_type" style="margin-right:2em">Package</th>
+              <th class="distro_type">Version</th>
+          </tr>
+              
+          <tr class="dependency" py:for="dep in dependencies">
+              <td style="margin-right:2em">${dep[0]}</td><td>${dep[1]}</td>
+          </tr>
+      </table>    
+    </div>
+  </body>
+</html>

src/calibre/trac/plugins/templates/pyinstaller.html

@@ -1,47 +0,0 @@
-<!DOCTYPE html
-    PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml"
-      xmlns:py="http://genshi.edgewall.org/"
-      xmlns:xi="http://www.w3.org/2001/XInclude">
-  <xi:include href="layout.html" />
-  <head>
-    <title>Download $app for Linux</title>
-  </head>
-
-  <body>
-    <div id="ctxtnav" class="nav"></div>
-
-    <div id="content" class="binary">
-      <h1>Download $app for Linux</h1>
-      <p>This binary package is compatible with most recent linux distributions running on Intel 32 bit CPUs. It needs testing on 64 bit CPUs. There have been reports of its working on some 64bit machines. </p>
-      <p>
-      <img width="50" height="50" style="border:1px red solid" src="${href.chrome('/dl/images/binary_logo.png')}" /> 
-      (Version: $version <a href="/wiki/Changelog">Changelog</a>)
-      </p>
-      <p>To install, copy paste the following command into a terminal and press Enter:
-      </p>
-      <pre class="wiki">sudo python -c "import urllib2; exec urllib2.urlopen('http://calibre.kovidgoyal.net/download_linux_binary_installer').read(); main()"</pre>
-      <p>
-      While you wait for the download to complete, please consider donating to support the development
-      of ${app}.</p>
-      <div>
-        <form action="https://www.paypal.com/cgi-bin/webscr" method="post">
-            <input type="hidden" name="cmd" value="_s-xclick" />
-            <input type="image" src="https://www.paypal.com/en_US/i/btn/btn_donateCC_LG.gif" border="0" name="submit" alt="PayPal - The safer, easier way to pay online!" />
-            <img alt="" border="0" src="https://www.paypal.com/en_US/i/scr/pixel.gif" width="1" height="1" />
-            <input type="hidden" name="encrypted" value="-----BEGIN PKCS7-----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-----END PKCS7-----" />
-        </form>
-        
-      </div>        
-      <h2>Note</h2>
-      <div class="note">
-      <ul>
-      <li>This installer is very new and has only been tested on a couple of systems, so if you encounter
-      problems, please report them.</li>
-      <li>You shoud have help2man and xdg-utils installed on your system.</li>
-      </ul>
-      </div>
-    </div>
-  </body>
-</html>

src/calibre/utils/config.py

@@ -6,7 +6,7 @@ __docformat__ = 'restructuredtext en'
 '''
 Manage application-wide preferences.
 '''
-import os, re, cPickle, textwrap
+import os, re, cPickle, textwrap, traceback
 from copy import deepcopy
 from functools import partial
 from optparse import OptionParser as _OptionParser
@@ -314,7 +314,12 @@ class OptionSet(object):
         if not isinstance(src, unicode):
             src = src.decode('utf-8')
         if src is not None:
+            try:
                 exec src in options
+            except:
+                print 'Failed to parse options string:'
+                print repr(src)
+                traceback.print_exc()
         opts = OptionValues()
         for pref in self.preferences:
             val = options.get(pref.name, pref.default)
@@ -539,7 +544,7 @@ def _prefs():
               help=_('Path to directory in which your library of books is stored'))
     c.add_opt('language', default=None,
               help=_('The language in which to display the user interface'))
-    c.add_opt('output_format', default='LRF', 
+    c.add_opt('output_format', default='EPUB', 
               help=_('The default output format for ebook conversions.'))
     c.add_opt('read_file_metadata', default=True,
               help=_('Read metadata from files'))

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

@@ -28,7 +28,7 @@ recipe_modules = ['recipe_' + r for r in (
            'la_tercera', 'el_mercurio_chile', 'la_cuarta', 'lanacion_chile', 'la_segunda',
            'jb_online', 'estadao', 'o_globo', 'vijesti', 'elmundo', 'the_oz',
            'honoluluadvertiser', 'starbulletin', 'exiled', 'indy_star', 'dna',
-           'pobjeda',
+           'pobjeda', 'chicago_breaking_news', 'glasgow_herald',
           )]
 
 import re, imp, inspect, time, os

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

@@ -1,50 +1,60 @@
 #!/usr/bin/env  python
-__license__   = 'GPL v3'
-__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
-__docformat__ = 'restructuredtext en'
 
+__license__   = 'GPL v3'
+__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
 '''
 arstechnica.com
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
 
-class ArsTechnica(BasicNewsRecipe):
+class ArsTechnica2(BasicNewsRecipe):
-    title          = 'Ars Technica'
+    title                 = u'Ars Technica'
-    description    = 'The art of technology'
-    oldest_article = 7
     language              = _('English')
-    no_stylesheets = True
+    __author__            = 'Darko Miletic'
-    __author__     = 'Michael Warner'
+    description           = 'The art of technology'    
+    publisher             = 'Ars Technica'
+    category              = 'news, IT, technology'    
+    language              = _('English')
+    oldest_article        = 2
     max_articles_per_feed = 100
-    extra_css = """
+    no_stylesheets        = True
-body {
+    encoding              = 'utf8'
-   font: normal 19px/180% Times, serif;
+    remove_javascript     = True
-}
+    use_embedded_content  = False
+    
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+
+    keep_only_tags = [dict(name='div', attrs={'id':['news-item-info','news-item']})]
 
-h1, h2, h3, h4 {
-   font: bold 28px/100% Verdana, Arial, Helvetica, sans-serif;
-   margin-top: 19px
-}
-"""
     remove_tags = [
-                   dict(id="Masthead"),
+                     dict(name=['object','link','embed'])
-                   dict(id="Banner"),
+                    ,dict(name='div', attrs={'class':'related-stories'})
-                   dict(id="Nav"),
+                  ]
-                   dict(name='div', attrs={'class':'ContentHeader'}), 
+
-                   dict(name='img'), 
+    
-                   dict(name='div', attrs={'class':'Inset RelatedStories'}), 
+    feeds = [
-                   dict(name='div', attrs={'class':'Tags'}), 
+              (u'Infinite Loop (Apple content)'        , u'http://feeds.arstechnica.com/arstechnica/apple/'      )
-                   dict(name='div', attrs={'class':'PostOptions flat'}),
+             ,(u'Opposable Thumbs (Gaming content)'    , u'http://feeds.arstechnica.com/arstechnica/gaming/'     )
-                   dict(name='div', attrs={'class':'ContentFooter'}),
+             ,(u'Gear and Gadgets'                     , u'http://feeds.arstechnica.com/arstechnica/gadgets/'    )
-                   dict(id="Sidebar"),
+             ,(u'Chipster (Hardware content)'          , u'http://feeds.arstechnica.com/arstechnica/hardware/'   )
-                   dict(id="LatestPosts"),
+             ,(u'Uptime (IT content)'                  , u'http://feeds.arstechnica.com/arstechnica/business/'   )
-                   dict(id="Footer")]
+             ,(u'Open Ended (Open Source content)'     , u'http://feeds.arstechnica.com/arstechnica/open-source/')
-    feeds       = [(u'News and Features', u'http://feeds.arstechnica.com/arstechnica/BAaf'),
+             ,(u'One Microsoft Way'                    , u'http://feeds.arstechnica.com/arstechnica/microsoft/'  )
-                   (u'Nobel Intent (Science)', u'http://arstechnica.com/journals/science.rssx'),
+             ,(u'Nobel Intent (Science content)'       , u'http://feeds.arstechnica.com/arstechnica/science/'    )
-                   (u'Infinite Loop (Apple)', u'http://arstechnica.com/journals/apple.rssx'),
+             ,(u'Law & Disorder (Tech policy content)' , u'http://feeds.arstechnica.com/arstechnica/tech-policy/')
-                   (u'M-Dollar (Microsoft)', u'http://arstechnica.com/journals/microsoft.rssx'),
+            ]
-                   (u'Open Ended (Linux)', u'http://arstechnica.com/journals/linux.rssx'),
+
-                   (u'Opposable Thumbs (Games)', u'http://arstechnica.com/journals/thumbs.rssx'),
+    def preprocess_html(self, soup):
-                   (u'Kit (Hardware)', u'http://arstechnica.com/journals/hardware.rssx'),
+        ftag = soup.find('div', attrs={'class':'news-item-byline'})
-                   (u'Journals', u'http://arstechnica.com/journals.rssx')]
+        if ftag:
+           ftag.insert(4,'<br /><br />')
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup

src/calibre/web/feeds/recipes/recipe_b92.py

@@ -1,13 +1,12 @@
 #!/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>'
 '''
 b92.net
 '''
 
 import re
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class B92(BasicNewsRecipe):
@@ -22,19 +21,22 @@ class B92(BasicNewsRecipe):
     no_stylesheets        = True
     use_embedded_content  = False
     cover_url = 'http://static.b92.net/images/fp/logo.gif'
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
+    language              = _('Serbian')
-
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
-    keep_only_tags = [ dict(name='div', attrs={'class':'sama_vest'}) ]
     
     html2lrf_options = [
                           '--comment'  , description
                         , '--category' , category
                         , '--publisher', publisher
+                        , '--ignore-tables'
                         ]
     
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
+
+    keep_only_tags = [ dict(name='div', attrs={'class':'sama_vest'}) ]
         
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+
     feeds          = [
                         (u'Vesti', u'http://www.b92.net/info/rss/vesti.xml')
                        ,(u'Biz'  , u'http://www.b92.net/info/rss/biz.xml'  )
@@ -54,9 +56,10 @@ class B92(BasicNewsRecipe):
         return nurl
 
     def preprocess_html(self, soup):
-        soup.html['xml:lang'] = 'sr-Latn'
+        lng = 'sr-Latn-RS'
-        soup.html['lang']     = 'sr-Latn'
+        soup.html['xml:lang'] = lng
-        mtag = '<meta http-equiv="Content-Language" content="sr-Latn"/>'
+        soup.html['lang']     = lng
+        mtag = '<meta http-equiv="Content-Language" content="sr-Latn-RS"/>'
         soup.head.insert(0,mtag)    
         for item in soup.findAll(style=True):
             del item['style']
@@ -64,4 +67,3 @@ class B92(BasicNewsRecipe):
             del item['align']
             item.insert(0,'<br /><br />')
         return soup
-    language = _('Serbian')

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

@@ -1,13 +1,12 @@
 #!/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>'
 '''
 blic.rs
 '''
 
 import re
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Blic(BasicNewsRecipe):
@@ -21,15 +20,17 @@ class Blic(BasicNewsRecipe):
     remove_javascript     = True
     no_stylesheets        = True
     use_embedded_content  = False
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
+    language              = _('Serbian')
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
     
     html2lrf_options = [
                           '--comment'  , description
                         , '--category' , category
                         , '--publisher', publisher
+                        , '--ignore-tables'
                         ]
     
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
     
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
 
@@ -44,10 +45,9 @@ class Blic(BasicNewsRecipe):
         return u'http://www.blic.rs/_print.php?' + rest_url
 
     def preprocess_html(self, soup):
-        mtag = '<meta http-equiv="Content-Language" content="sr-Latn"/>'
+        mtag = '<meta http-equiv="Content-Language" content="sr-Latn-RS"/>'
         soup.head.insert(0,mtag)    
         for item in soup.findAll(style=True):
             del item['style']
         return soup
         
-    language              = _('Serbian')

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

@@ -0,0 +1,45 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+chicagobreakingnews.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class ChicagoBreakingNews(BasicNewsRecipe):
+    title                 = 'Chicago Breaking News'
+    __author__            = 'Darko Miletic'
+    description           = 'Breaking News from Chicago'    
+    oldest_article        = 1
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = True
+    publisher             = 'Chicago Breaking News'
+    category              = 'news, politics, USA, Chicago'
+    encoding              = 'utf8'
+    language              = _('English')
+    
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+
+    feeds = [(u'Breaking news', u'http://feeds2.feedburner.com/ChicagoBreakingNews/')]
+
+    def preprocess_html(self, soup):
+        links = soup.findAll('a')
+        for item in soup.findAll('a'):
+            if item['href'].find('http://feedads.googleadservices.com') > -1:
+               item.extract()
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll(color=True):
+            del item['color']
+        for item in soup.findAll(size=True):
+            del item['size']
+        return soup

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

@@ -1,12 +1,11 @@
 #!/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>'
 '''
 danas.rs
 '''
 import re
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Danas(BasicNewsRecipe):
@@ -20,15 +19,17 @@ class Danas(BasicNewsRecipe):
     no_stylesheets        = False
     remove_javascript     = True
     use_embedded_content  = False
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
+    language              = _('Serbian')
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
     
     html2lrf_options = [
                           '--comment'  , description
                         , '--category' , category
                         , '--publisher', publisher
+                        , '--ignore-tables'
                         ]
     
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
  
 
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
@@ -43,9 +44,8 @@ class Danas(BasicNewsRecipe):
     feeds          = [ (u'Vesti', u'http://www.danas.rs/rss/rss.asp')]
 
     def preprocess_html(self, soup):
-        mtag = '<meta http-equiv="Content-Language" content="sr-Latn"/>'
+        mtag = '<meta http-equiv="Content-Language" content="sr-Latn-RS"/>'
         soup.head.insert(0,mtag)    
         for item in soup.findAll(style=True):
             del item['style']
         return soup
-    language              = _('Serbian')

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

@@ -5,7 +5,6 @@ __copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
 '''
 elargentino.com
 '''
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class ElArgentino(BasicNewsRecipe):
@@ -21,6 +20,7 @@ class ElArgentino(BasicNewsRecipe):
     use_embedded_content  = False
     encoding              = 'utf8'
     cover_url             = 'http://www.elargentino.com/TemplateWeb/MediosFooter/tapa_elargentino.png'
+    language              = _('Spanish')
 
     html2lrf_options = [
                           '--comment', description
@@ -59,5 +59,3 @@ class ElArgentino(BasicNewsRecipe):
         for item in soup.findAll(style=True):
             del item['style']        
         return soup
-    
-    language = _('Spanish')

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

@@ -0,0 +1,34 @@
+import re
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class GlasgowHerald(BasicNewsRecipe):
+    title          = u'Glasgow Herald'
+    oldest_article = 1
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    language       = _('English')
+    __author__     = 'McCande' 
+
+    preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
+    [
+                (r'<center><h3>', lambda match : '<h3>'),
+                (r'Click here to comment on this story...', lambda match : ''),
+                (r'<h3>Related links</h3>.*?</head>', lambda match : '</head>'),
+        ]
+        ]
+
+
+
+
+    feeds          = [
+                        (u'News', u'http://www.theherald.co.uk/news/news/rss.xml'),
+                        (u'Politics', u'http://www.theherald.co.uk/politics/news/rss.xml'),
+                        (u'Features', u'http://www.theherald.co.uk/features/features/rss.xml'),
+                        (u'Business', u'http://www.theherald.co.uk/business/news/rss.xml')]
+
+    def print_version(self, url):
+        (beginning,end)=url.split(".var.")
+        num=end[0:7]
+        main="http://www.theherald.co.uk/misc/print.php?artid="+num
+        return main

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

@@ -1,7 +1,7 @@
 #!/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>'
 '''
 granma.cubaweb.cu
 '''
@@ -21,6 +21,7 @@ class Granma(BasicNewsRecipe):
     use_embedded_content  = False
     encoding              = 'cp1252'
     cover_url             = 'http://www.granma.cubaweb.cu/imagenes/granweb229d.jpg'
+    language              = _('Spanish')
     remove_javascript     = True
     
     html2lrf_options = [
@@ -30,10 +31,12 @@ class Granma(BasicNewsRecipe):
                         , '--ignore-tables'
                         ]
     
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
 
     keep_only_tags = [dict(name='table', attrs={'height':'466'})]
     
+    remove_tags = [dict(name=['embed','link','object'])]
+
     feeds = [(u'Noticias', u'http://www.granma.cubaweb.cu/noticias.xml' )]
 
     
@@ -49,4 +52,3 @@ class Granma(BasicNewsRecipe):
             del item['style']
         return soup
     
-    language = _('Spanish')

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

@@ -14,10 +14,11 @@ class Infobae(BasicNewsRecipe):
     description           = 'Informacion Libre las 24 horas'
     publisher             = 'Infobae.com'
     category              = 'news, politics, Argentina'     
-    oldest_article        = 2
+    oldest_article        = 1
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
+    language              = _('Spanish')
     encoding              = 'iso-8859-1'
     cover_url             = 'http://www.infobae.com/imgs/header/header.gif'
     remove_javascript     = True
@@ -26,9 +27,15 @@ class Infobae(BasicNewsRecipe):
                           '--comment'  , description
                         , '--category' , category
                         , '--publisher', publisher
+                        , '--ignore-tables'
                         ]
     
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
+
+    remove_tags = [
+                     dict(name=['embed','link','object'])
+                    ,dict(name='a', attrs={'onclick':'javascript:window.print()'})
+                  ]
     
     feeds = [ 
               (u'Noticias'  , u'http://www.infobae.com/adjuntos/html/RSS/hoy.xml'       )
@@ -48,5 +55,3 @@ class Infobae(BasicNewsRecipe):
         for item in soup.findAll(style=True):
             del item['style']
         return soup
-
-    language = _('Spanish')

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

@@ -1,13 +1,12 @@
 #!/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>'
 '''
 jutarnji.hr
 '''
 
 import re
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Jutarnji(BasicNewsRecipe):
@@ -16,32 +15,32 @@ class Jutarnji(BasicNewsRecipe):
     description           = u'Hrvatski portal'
     publisher             = 'Jutarnji.hr'
     category              = 'news, politics, Croatia'    
-    oldest_article        = 2
+    oldest_article        = 1
     max_articles_per_feed = 100
-    simultaneous_downloads = 1
+    simultaneous_downloads = 2
     delay                 = 1
     language              = _('Croatian')
     no_stylesheets        = True
     use_embedded_content  = False
     remove_javascript     = True
     encoding              = 'cp1250'
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: justify; font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
     
     html2lrf_options = [
                           '--comment'  , description
                         , '--category' , category
                         , '--publisher', publisher
+                        , '--ignore-tables'
                         ]
     
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
 
 
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
     
     remove_tags = [ 
-                    dict(name='embed')
+                    dict(name=['embed','hr','link','object'])
                    ,dict(name='a', attrs={'class':'a11'})
-                   ,dict(name='hr')
                   ]
     
     feeds = [
@@ -60,9 +59,7 @@ class Jutarnji(BasicNewsRecipe):
         return 'http://www.jutarnji.hr/ispis_clanka.jl?artid=' + rrest
 
     def preprocess_html(self, soup):
-        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8">'
+        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8">\n<meta http-equiv="Content-Language" content="hr-HR"/>'
-        soup.head.insert(0,mtag)
-        mtag = '<meta http-equiv="Content-Language" content="hr"/>'
         soup.head.insert(0,mtag)
         for item in soup.findAll(style=True):
             del item['style']        

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

@@ -1,12 +1,12 @@
 #!/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>'
 '''
 juventudrebelde.cu
 '''
-from calibre import strftime
 
+from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Juventudrebelde(BasicNewsRecipe):
@@ -20,6 +20,7 @@ class Juventudrebelde(BasicNewsRecipe):
     no_stylesheets        = True
     use_embedded_content  = False
     encoding              = 'cp1252'
+    language              = _('Spanish')
     cover_url             = strftime('http://www.juventudrebelde.cu/UserFiles/File/impreso/iportada-%Y-%m-%d.jpg')
     remove_javascript     = True
     
@@ -30,7 +31,7 @@ class Juventudrebelde(BasicNewsRecipe):
                         , '--ignore-tables'
                         ]
     
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
 
     keep_only_tags = [dict(name='div', attrs={'id':'noticia'})]
 
@@ -51,4 +52,3 @@ class Juventudrebelde(BasicNewsRecipe):
             del item['style']
         return soup
              
-    language = _('Spanish')

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

@@ -1,13 +1,12 @@
 #!/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>'
 '''
 nin.co.yu
 '''
 
 import re, urllib
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Nin(BasicNewsRecipe):    
@@ -27,15 +26,17 @@ class Nin(BasicNewsRecipe):
     LOGIN                  = PREFIX + '/?logout=true'
     remove_javascript      = True
     use_embedded_content   = False
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
+    language              = _('Serbian')
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: justify; font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
     
     html2lrf_options = [
                           '--comment'  , description
                         , '--category' , category
                         , '--publisher', publisher
+                        , '--ignore-tables'
                         ]
     
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
                           
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
     
@@ -69,5 +70,3 @@ class Nin(BasicNewsRecipe):
         for item in soup.findAll(style=True):
             del item['style']
         return soup
-
-    language              = _('Serbian')

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

@@ -1,13 +1,12 @@
 #!/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>'
 '''
 novosti.rs
 '''
 
 import re
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Novosti(BasicNewsRecipe):
@@ -22,15 +21,17 @@ class Novosti(BasicNewsRecipe):
     use_embedded_content  = False
     encoding              = 'utf8'
     remove_javascript     = True
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
+    language              = _('Serbian')
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
     
     html2lrf_options = [
                           '--comment'  , description
                         , '--category' , category
                         , '--publisher', publisher
+                        , '--ignore-tables'
                         ]
     
-    html2epub_options  = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
 
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
 
@@ -40,10 +41,8 @@ class Novosti(BasicNewsRecipe):
     feeds              = [(u'Vesti', u'http://www.novosti.rs/php/vesti/rss.php')]
 
     def preprocess_html(self, soup):
-        mtag = '<meta http-equiv="Content-Language" content="sr-Latn"/>'
+        mtag = '<meta http-equiv="Content-Language" content="sr-Latn-RS"/>'
         soup.head.insert(0,mtag)    
         for item in soup.findAll(style=True):
             del item['style']        
         return soup
-
-    language              = _('Serbian')

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

@@ -1,13 +1,12 @@
 #!/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>'
 '''
 nspm.rs
 '''
 
 import re
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Nspm(BasicNewsRecipe):
@@ -16,14 +15,15 @@ class Nspm(BasicNewsRecipe):
     description           = 'Casopis za politicku teoriju i drustvena istrazivanja'    
     publisher             = 'NSPM'
     category              = 'news, politics, Serbia'    
-    oldest_article        = 7
+    oldest_article        = 2
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
     INDEX                 = 'http://www.nspm.rs/?alphabet=l'
     encoding              = 'utf8'
     remove_javascript     = True
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
+    language              = _('Serbian')
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: justify; font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
     
     html2lrf_options = [
                           '--comment'  , description
@@ -32,10 +32,13 @@ class Nspm(BasicNewsRecipe):
                         , '--ignore-tables'
                         ]
     
-    html2epub_options  = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
 
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
-    remove_tags        = [dict(name='a')]
+    remove_tags        = [
+                            dict(name=['a','img','link','object','embed'])
+                           ,dict(name='td', attrs={'class':'buttonheading'})
+                         ]
     
     def get_browser(self):
         br = BasicNewsRecipe.get_browser()
@@ -48,13 +51,12 @@ class Nspm(BasicNewsRecipe):
         return url.replace('.html','/stampa.html')
 
     def preprocess_html(self, soup):
-        soup.html['xml:lang'] = 'sr-Latn-RS'
+        lng = 'sr-Latn-RS'
-        soup.html['lang']     = 'sr-Latn-RS'
+        soup.html['xml:lang'] = lng
+        soup.html['lang']     = lng
         ftag = soup.find('meta',attrs={'http-equiv':'Content-Language'})
         if ftag:
-           ftag['content'] = 'sr-Latn-RS'
+           ftag['content'] = lng
         for item in soup.findAll(style=True):
             del item['style']     
         return soup
-
-    language = _('Serbian')

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

@@ -1,13 +1,12 @@
 #!/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>'
 '''
 pescanik.net
 '''
 
 import re
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Pescanik(BasicNewsRecipe):
@@ -16,30 +15,32 @@ class Pescanik(BasicNewsRecipe):
     description           = 'Pescanik'
     publisher             = 'Pescanik'
     category              = 'news, politics, Serbia'    
-    oldest_article        = 7
+    oldest_article        = 5
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
     remove_javascript     = True
     encoding              = 'utf8'
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
+    cover_url             = "http://pescanik.net/templates/ja_teline/images/logo.png"
+    language              = _('Serbian')
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
     
     html2lrf_options = [
                           '--comment'  , description
                         , '--category' , category
                         , '--publisher', publisher
+                        , '--ignore-tables'
                         ]
     
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
     
-    cover_url = "http://pescanik.net/templates/ja_teline/images/logo.png"
     
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
     
     remove_tags = [
                      dict(name='td'  , attrs={'class':'buttonheading'})
                     ,dict(name='span', attrs={'class':'article_seperator'})
-                    ,dict(name=['object','link'])
+                    ,dict(name=['object','link','img','h4','ul'])
                   ]
 
     feeds       = [(u'Pescanik Online', u'http://pescanik.net/index.php?option=com_rd_rss&id=12')]
@@ -54,5 +55,3 @@ class Pescanik(BasicNewsRecipe):
         for item in soup.findAll(style=True):
             del item['style']
         return soup
-
-    language              = _('Serbian')

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

@@ -6,7 +6,6 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
 politika.rs
 '''
 import re
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Politika(BasicNewsRecipe):
@@ -16,13 +15,13 @@ class Politika(BasicNewsRecipe):
     publisher             = 'Politika novine i Magazini d.o.o'
     category              = 'news, politics, Serbia'            
     oldest_article        = 2
-    language              = _('Serbian')
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
     remove_javascript     = True
     encoding              = 'utf8'
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
+    language              = _('Serbian')
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
     
     html2lrf_options = [
                           '--comment', description
@@ -61,6 +60,6 @@ class Politika(BasicNewsRecipe):
         for item in soup.findAll(style=True):
             del item['style']
         ftag = soup.find('div',attrs={'class':'content_center_border'})
-        if ftag:
+        if ftag.has_key('align'):
-           ftag['align'] = 'left'
+           del ftag['align']
         return soup

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

@@ -4,11 +4,10 @@ __license__   = 'GPL v3'
 __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
 
 '''
-vijesti.cg.yu
+vijesti.me
 '''
 
 import re
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Vijesti(BasicNewsRecipe):
@@ -22,10 +21,11 @@ class Vijesti(BasicNewsRecipe):
     no_stylesheets        = True
     remove_javascript     = True
     encoding              = 'cp1250'
-    cover_url             = 'http://www.vijesti.cg.yu/img/logo.gif'
+    cover_url             = 'http://www.vijesti.me/img/logo.gif'
     remove_javascript     = True
     use_embedded_content  = False
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
+    language              = _('Serbian')
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: justify; font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
     
     html2lrf_options = [
                           '--comment', description
@@ -39,12 +39,9 @@ class Vijesti(BasicNewsRecipe):
 
     keep_only_tags = [dict(name='div', attrs={'id':'mainnews'})]
 
-    remove_tags = [
+    remove_tags = [dict(name=['object','link','embed'])]
-                     dict(name='div', attrs={'align':'right'})
-                    ,dict(name=['object','link'])
-                  ]
 
-    feeds = [(u'Sve vijesti', u'http://www.vijesti.cg.yu/rss.php' )]
+    feeds = [(u'Sve vijesti', u'http://www.vijesti.me/rss.php' )]
 
     def preprocess_html(self, soup):
         soup.html['xml:lang'] = 'sr-Latn-ME'
@@ -56,5 +53,3 @@ class Vijesti(BasicNewsRecipe):
                del item['align']
                item.insert(0,'<br /><br />')
         return soup
-
-    language              = _('Serbian')

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

@@ -1,14 +1,13 @@
 #!/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>'
 '''
 vreme.com
 '''
 
 import re
 from calibre import strftime
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Vreme(BasicNewsRecipe):    
@@ -24,15 +23,17 @@ class Vreme(BasicNewsRecipe):
     LOGIN = 'http://www.vreme.com/account/index.php'
     remove_javascript     = True
     use_embedded_content  = False
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
+    language              = _('Serbian')
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
     
     html2lrf_options = [
                           '--comment'  , description
                         , '--category' , category
                         , '--publisher', publisher
+                        , '--ignore-tables'
                         ]
     
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
     
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
 
@@ -87,7 +88,12 @@ class Vreme(BasicNewsRecipe):
         del soup.body['text'   ]
         del soup.body['bgcolor']
         del soup.body['onload' ]
-        mtag = '<meta http-equiv="Content-Language" content="sr-Latn"/>'
+        for item in soup.findAll('table'):
+            if item.has_key('width'):
+               del item['width']
+            if item.has_key('height'):
+               del item['height']                    
+        mtag = '<meta http-equiv="Content-Language" content="sr-Latn-RS"/>'
         soup.head.insert(0,mtag)
         tbl = soup.body.table
         tbbb = soup.find('td')
@@ -104,5 +110,3 @@ class Vreme(BasicNewsRecipe):
         if cover_item:
            cover_url = self.INDEX + cover_item['src']
         return cover_url
-
-    language              = _('Serbian')

src/calibre/web/fetch/simple.py

@@ -8,7 +8,7 @@ Fetch a webpage and its links recursively. The webpages are saved to disk in
 UTF-8 encoding with any charset declarations removed.
 '''
 import sys, socket, os, urlparse, logging, re, time, copy, urllib2, threading, traceback
-from urllib import url2pathname
+from urllib import url2pathname, quote
 from threading import RLock
 from httplib import responses
 from PIL import Image
@@ -179,6 +179,8 @@ class RecursiveFetcher(object, LoggingInterface):
         delta = time.time() - self.last_fetch_at 
         if  delta < self.delay:
             time.sleep(delta)
+        if re.search(r'\s+', url) is not None:
+            url = quote(url)
         with self.browser_lock:
             try:
                 with closing(self.browser.open(url)) as f:

src/cherrypy/_cpchecker.py

@@ -58,7 +58,7 @@ class Checker(object):
                             "specific sections. You must explicitly pass "
                             "application config via "
                             "cherrypy.tree.mount(..., config=app_config)")
-                warnings.warn(msg)
+                    warnings.warn(msg[:5])
                 return
     
     def check_static_paths(self):