Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge upstream changes

Browse Source
This commit is contained in:
Marshall T. Vandegrift 2009-01-18 21:48:37 -05:00
commit 97468e61fe
41 changed files with 705 additions and 110 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
setup.py
View File

@ -415,8 +415,9 @@ if __name__ == '__main__':
ext_modules.append(Extension('calibre.plugins.winutil',
sources=['src/calibre/utils/windows/winutil.c'],
libraries=['shell32', 'setupapi'],
include_dirs=['C:/WinDDK/6001.18001/inc/api/',
'C:/WinDDK/6001.18001/inc/crt/'],
include_dirs=os.environ.get('INCLUDE',
'C:/WinDDK/6001.18001/inc/api/;'
'C:/WinDDK/6001.18001/inc/crt/').split(';'),
extra_compile_args=['/X']
))
if isosx:
@ -425,7 +426,11 @@ if __name__ == '__main__':
extra_link_args=['-framework', 'IOKit'])
)
plugins = ['plugins/%s.so'%(x.name.rpartition('.')[-1]) for x in ext_modules]
if not iswindows:
plugins = ['plugins/%s.so'%(x.name.rpartition('.')[-1]) for x in ext_modules]
else:
plugins = ['plugins/%s.pyd'%(x.name.rpartition('.')[-1]) for x in ext_modules] + \
['plugins/%s.pyd.manifest'%(x.name.rpartition('.')[-1]) for x in ext_modules if 'pictureflow' not in x.name]
setup(
name = APPNAME,

2
src/calibre/constants.py
View File

@ -2,7 +2,7 @@ __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
__appname__ = 'calibre'
__version__ = '0.4.128'
__version__ = '0.4.129'
__author__ = "Kovid Goyal <kovid@kovidgoyal.net>"
'''
Various run time constants.

6
src/calibre/devices/__init__.py
View File

@ -10,8 +10,8 @@ def devices():
from calibre.devices.prs505.driver import PRS505
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)
from calibre.devices.kindle.driver import KINDLE
return (PRS500, PRS505, PRS700, CYBOOKG3, KINDLE)
import time
@ -31,4 +31,4 @@ def strftime(epoch, zone=time.gmtime):
src = time.strftime("%w, %d %m %Y %H:%M:%S GMT", zone(epoch)).split()
src[0] = INVERSE_DAY_MAP[int(src[0][:-1])]+','
src[2] = INVERSE_MONTH_MAP[int(src[2])]
return ' '.join(src)
return ' '.join(src)

82
src/calibre/devices/cybookg3/driver.py
View File

@ -4,9 +4,11 @@ __copyright__ = '2009, John Schember <john at nachtimwald.com>'
Device driver for Bookeen's Cybook Gen 3
'''
import os, fnmatch
import os, shutil
from itertools import cycle
from calibre.devices.usbms.driver import USBMS
import calibre.devices.cybookg3.t2b as t2b
class CYBOOKG3(USBMS):
# Ordered list of supported formats
@ -29,6 +31,76 @@ class CYBOOKG3(USBMS):
EBOOK_DIR_MAIN = "eBooks"
SUPPORTS_SUB_DIRS = True
def upload_books(self, files, names, on_card=False, end_session=True,
metadata=None):
if on_card and not self._card_prefix:
raise ValueError(_('The reader has no storage card connected.'))
if not on_card:
path = os.path.join(self._main_prefix, self.EBOOK_DIR_MAIN)
else:
path = os.path.join(self._card_prefix, self.EBOOK_DIR_CARD)
def get_size(obj):
if hasattr(obj, 'seek'):
obj.seek(0, os.SEEK_END)
size = obj.tell()
obj.seek(0)
return size
return os.path.getsize(obj)
sizes = map(get_size, files)
size = sum(sizes)
if on_card and size > self.free_space()[2] - 1024*1024:
raise FreeSpaceError(_("There is insufficient free space on the storage card"))
if not on_card and size > self.free_space()[0] - 2*1024*1024:
raise FreeSpaceError(_("There is insufficient free space in main memory"))
paths = []
names = iter(names)
metadata = iter(metadata)
for infile in files:
newpath = path
mdata = metadata.next()
if self.SUPPORTS_SUB_DIRS:
if 'tags' in mdata.keys():
for tag in mdata['tags']:
if tag.startswith('/'):
newpath += tag
newpath = os.path.normpath(newpath)
break
if not os.path.exists(newpath):
os.makedirs(newpath)
filepath = os.path.join(newpath, names.next())
paths.append(filepath)
if hasattr(infile, 'read'):
infile.seek(0)
dest = open(filepath, 'wb')
shutil.copyfileobj(infile, dest, 10*1024*1024)
dest.flush()
dest.close()
else:
shutil.copy2(infile, filepath)
coverdata = None
if 'cover' in mdata.keys():
if mdata['cover'] != None:
coverdata = mdata['cover'][2]
t2bfile = open('%s_6090.t2b' % (os.path.splitext(filepath)[0]), 'wb')
t2b.write_t2b(t2bfile, coverdata)
t2bfile.close()
return zip(paths, cycle([on_card]))
def delete_books(self, paths, end_session=True):
for path in paths:
@ -36,17 +108,15 @@ class CYBOOKG3(USBMS):
os.unlink(path)
filepath, ext = os.path.splitext(path)
basepath, filename = os.path.split(filepath)
# Delete the ebook auxiliary file
if os.path.exists(filepath + '.mbp'):
os.unlink(filepath + '.mbp')
# Delete the thumbnails file auto generated for the ebook
for p, d, files in os.walk(basepath):
for filen in fnmatch.filter(files, filename + "*.t2b"):
os.unlink(os.path.join(p, filen))
if os.path.exists(filepath + '_6090.t2b'):
os.unlink(filepath + '_6090.t2b')
try:
os.removedirs(os.path.dirname(path))
except:

48
src/calibre/devices/cybookg3/t2b.py Normal file
View File

File diff suppressed because one or more lines are too long

9
src/calibre/devices/kindle/driver.py
View File

@ -16,13 +16,18 @@ class KINDLE(USBMS):
PRODUCT_ID = 0x0001
BCD = [0x399]
VENDOR_NAME = 'AMAZON'
WINDOWS_MAIN_MEM = 'KINDLE'
VENDOR_NAME = 'KINDLE'
WINDOWS_MAIN_MEM = 'INTERNAL_STORAGE'
WINDOWS_CARD_MEM = 'CARD_STORAGE'
OSX_MAIN_MEM = 'Kindle Internal Storage Media'
OSX_CARD_MEM = 'Kindle Card Storage Media'
MAIN_MEMORY_VOLUME_LABEL = 'Kindle Main Memory'
STORAGE_CARD_VOLUME_LABEL = 'Kindle Storage Card'
EBOOK_DIR_MAIN = "documents"
SUPPORTS_SUB_DIRS = True
def delete_books(self, paths, end_session=True):
for path in paths:

52
src/calibre/devices/usbms/driver.py
View File

@ -125,10 +125,11 @@ class USBMS(Device):
if os.path.exists(path):
# Delete the ebook
os.unlink(path)
try:
os.removedirs(os.path.dirname(path))
except:
pass
if self.SUPPORTS_SUB_DIRS:
try:
os.removedirs(os.path.dirname(path))
except:
pass
@classmethod
def remove_books_from_metadata(cls, paths, booklists):
@ -148,7 +149,18 @@ class USBMS(Device):
path = self.munge_path(path)
src = open(path, 'rb')
shutil.copyfileobj(src, outfile, 10*1024*1024)
def put_file(self, infile, path, replace_file=False, end_session=True):
path = self.munge_path(path)
if os.path.isdir(path):
path = os.path.join(path, infile.name)
if not replace_file and os.path.exists(path):
raise PathError('File already exists: ' + path)
dest = open(path, 'wb')
shutil.copyfileobj(infile, dest, 10*1024*1024)
dest.flush()
dest.close()
def munge_path(self, path):
if path.startswith('/') and not (path.startswith(self._main_prefix) or \
(self._card_prefix and path.startswith(self._card_prefix))):
@ -157,6 +169,34 @@ class USBMS(Device):
path = path.replace('card:', self._card_prefix[:-1])
return path
def list(self, path, recurse=False, end_session=True, munge=True):
if munge:
path = self.munge_path(path)
if os.path.isfile(path):
return [(os.path.dirname(path), [File(path)])]
entries = [File(os.path.join(path, f)) for f in os.listdir(path)]
dirs = [(path, entries)]
for _file in entries:
if recurse and _file.is_dir:
dirs[len(dirs):] = self.list(_file.path, recurse=True, munge=False)
return dirs
def mkdir(self, path, end_session=True):
if self.SUPPORTS_SUB_DIRS:
path = self.munge_path(path)
os.mkdir(path)
def rm(self, path, end_session=True):
path = self.munge_path(path)
self.delete_books([path])
def touch(self, path, end_session=True):
path = self.munge_path(path)
if not os.path.exists(path):
open(path, 'w').close()
if not os.path.isdir(path):
os.utime(path, None)
@classmethod
def extract_book_metadata_by_filename(cls, filename):
book_title = ''
@ -183,5 +223,3 @@ class USBMS(Device):
return book_title, book_author, book_mime
# ls, rm, cp, mkdir, touch, cat

1
src/calibre/ebooks/epub/from_feeds.py
View File

@ -40,6 +40,7 @@ def convert(opts, recipe_arg, notification=None):
c.smart_update(recipe_opts, opts)
opts = recipe_opts
opts.chapter_mark = 'none'
opts.dont_split_on_page_breaks = True
opf = glob.glob(os.path.join(tdir, '*.opf'))
if not opf:
raise Exception('Downloading of recipe: %s failed'%recipe_arg)

5
src/calibre/ebooks/lit/from_any.py
View File

@ -38,7 +38,10 @@ def any2lit(opts, path):
os.mkdir(oebdir)
opts.output = os.path.join(tdir, 'dummy.epub')
opts.profile = 'None'
orig_bfs = opts.base_font_size2
opts.base_font_size2 = 0
any2epub(opts, path, create_epub=False, oeb_cover=True, extract_to=oebdir)
opts.base_font_size2 = orig_bfs
opf = glob.glob(os.path.join(oebdir, '*.opf'))[0]
opts.output = orig_output
logging.getLogger('html2epub').info(_('Creating LIT file from EPUB...'))
@ -56,4 +59,4 @@ def main(args=sys.argv):
return 0
if __name__ == '__main__':
sys.exit(main())
sys.exit(main())

6
src/calibre/ebooks/lit/writer.py
View File

@ -143,7 +143,7 @@ def warn(x):
class ReBinary(object):
NSRMAP = {'': None, XML_NS: 'xml'}
def __init__(self, root, path, oeb, map=HTML_MAP):
def __init__(self, root, item, oeb, map=HTML_MAP):
self.item = item
self.logger = oeb.logger
self.manifest = oeb.manifest
@ -713,7 +713,7 @@ def option_parser():
'-o', '--output', default=None,
help=_('Output file. Default is derived from input filename.'))
parser.add_option(
'--verbose', default=False, action='store_true',
'-v', '--verbose', default=0, action='count',
help=_('Useful for debugging.'))
return parser
@ -725,7 +725,7 @@ def oeb2lit(opts, inpath):
outpath = os.path.basename(inpath)
outpath = os.path.splitext(outpath)[0] + '.lit'
outpath = os.path.abspath(outpath)
context = Context('Firefox', 'MSReader')
context = Context('Browser', 'MSReader')
oeb = OEBBook(inpath, logger=logger)
tocadder = HTMLTOCAdder()
tocadder.transform(oeb, context)

12
src/calibre/ebooks/lrf/comic/convert_from.py
View File

@ -10,11 +10,6 @@ Based on ideas from comiclrf created by FangornUK.
import os, sys, shutil, traceback, textwrap
from uuid import uuid4
try:
from reportlab.pdfgen import canvas
_reportlab = True
except:
_reportlab = False
@ -396,10 +391,9 @@ def create_lrf(pages, profile, opts, thumbnail=None):
def create_pdf(pages, profile, opts, thumbnail=None):
width, height = PROFILES[profile]
if not _reportlab:
raise RuntimeError('Failed to load reportlab')
from reportlab.pdfgen import canvas
pdf = canvas.Canvas(filename=opts.output, pagesize=(width,height+15))
pdf.setAuthor(opts.author)
pdf.setTitle(opts.title)

12
src/calibre/ebooks/metadata/epub.py
View File

@ -103,8 +103,8 @@ class OCFDirReader(OCFReader):
return open(os.path.join(self.root, path), *args, **kwargs)
class CoverRenderer(QObject):
WIDTH = 1280
HEIGHT = 1024
WIDTH = 600
HEIGHT = 800
def __init__(self, url, size, loop):
QObject.__init__(self)
@ -113,7 +113,7 @@ class CoverRenderer(QObject):
pal = self.page.palette()
pal.setBrush(QPalette.Background, Qt.white)
self.page.setPalette(pal)
self.page.setViewportSize(QSize(600, 800))
self.page.setViewportSize(QSize(self.WIDTH, self.HEIGHT))
self.page.mainFrame().setScrollBarPolicy(Qt.Vertical, Qt.ScrollBarAlwaysOff)
self.page.mainFrame().setScrollBarPolicy(Qt.Horizontal, Qt.ScrollBarAlwaysOff)
QObject.connect(self.page, SIGNAL('loadFinished(bool)'), self.render_html)
@ -126,9 +126,9 @@ class CoverRenderer(QObject):
try:
if not ok:
return
size = self.page.mainFrame().contentsSize()
width, height = fit_image(size.width(), size.height(), self.WIDTH, self.HEIGHT)[1:]
self.page.setViewportSize(QSize(width, height))
#size = self.page.mainFrame().contentsSize()
#width, height = fit_image(size.width(), size.height(), self.WIDTH, self.HEIGHT)[1:]
#self.page.setViewportSize(QSize(width, height))
image = QImage(self.page.viewportSize(), QImage.Format_ARGB32)
image.setDotsPerMeterX(96*(100/2.54))
image.setDotsPerMeterY(96*(100/2.54))

4
src/calibre/ebooks/mobi/from_any.py
View File

@ -42,7 +42,11 @@ def any2mobi(opts, path):
os.mkdir(oebdir)
opts.output = os.path.join(tdir, 'dummy.epub')
opts.profile = 'None'
opts.dont_split_on_page_breaks = True
orig_bfs = opts.base_font_size2
opts.base_font_size2 = 0
any2epub(opts, path, create_epub=False, oeb_cover=True, extract_to=oebdir)
opts.base_font_size2 = orig_bfs
opf = glob.glob(os.path.join(oebdir, '*.opf'))[0]
opts.output = orig_output
logging.getLogger('html2epub').info(_('Creating Mobipocket file from EPUB...'))

24
src/calibre/ebooks/mobi/reader.py
View File

@ -267,6 +267,12 @@ class MobiReader(object):
'xx-large' : '6',
}
for tag in root.iter(etree.Element):
if tag.tag in ('country-region', 'place', 'placetype', 'placename',
'state', 'city'):
tag.tag = 'span'
for key in tag.attrib.keys():
tag.attrib.pop(key)
continue
styles, attrib = [], tag.attrib
if attrib.has_key('style'):
style = attrib.pop('style').strip()
@ -466,16 +472,28 @@ class MobiReader(object):
def get_metadata(stream):
mr = MobiReader(stream)
if mr.book_header.exth is None:
mi = MetaInformation(mr.name, ['Unknown'])
mi = MetaInformation(mr.name, [_('Unknown')])
else:
tdir = tempfile.mkdtemp('_mobi_meta', __appname__)
tdir = tempfile.mkdtemp('_mobi_meta', __appname__+'_')
atexit.register(shutil.rmtree, tdir)
mr.extract_images([], tdir)
mi = mr.create_opf('dummy.html')
if mi.cover:
cover = os.path.join(tdir, mi.cover)
if not os.access(cover, os.R_OK):
fname = os.path.basename(cover)
match = re.match(r'(\d+)(.+)', fname)
if match:
num, ext = int(match.group(1), 10), match.group(2)
while num > 0:
num -= 1
candidate = os.path.join(os.path.dirname(cover), '%05d%s'%(num, ext))
if os.access(candidate, os.R_OK):
cover = candidate
break
if os.access(cover, os.R_OK):
mi.cover_data = ('JPEG', open(os.path.join(tdir, mi.cover), 'rb').read())
mi.cover_data = ('JPEG', open(os.path.join(tdir, cover), 'rb').read())
else:
path = os.path.join(tdir, 'images', '00001.jpg')
if os.access(path, os.R_OK):

7
src/calibre/ebooks/mobi/writer.py
View File

@ -393,7 +393,7 @@ class MobiWriter(object):
return data
def _generate_images(self):
self._oeb.logger.warn('Serializing images...')
self._oeb.logger.info('Serializing images...')
images = [(index, href) for href, index in self._images.items()]
images.sort()
metadata = self._oeb.metadata
@ -502,7 +502,8 @@ def add_mobi_options(parser):
_('Mobipocket-specific options.'))
group.add_option(
'-c', '--compress', default=False, action='store_true',
help=_('Compress file text using PalmDOC compression.'))
help=_('Compress file text using PalmDOC compression. '
'Results in smaller files, but takes a long time to run.'))
group.add_option(
'-r', '--rescale-images', default=False, action='store_true',
help=_('Modify images to meet Palm device size limitations.'))
@ -525,7 +526,7 @@ def option_parser():
'-o', '--output', default=None,
help=_('Output file. Default is derived from input filename.'))
parser.add_option(
'-v', '--verbose', default=False, action='store_true',
'-v', '--verbose', default=0, action='count',
help=_('Useful for debugging.'))
add_mobi_options(parser)
return parser

48
src/calibre/gui2/dialogs/progress.py Normal file
View File

@ -0,0 +1,48 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
''''''
from PyQt4.Qt import QDialog, SIGNAL, Qt
from calibre.gui2.dialogs.progress_ui import Ui_Dialog
class ProgressDialog(QDialog, Ui_Dialog):
def __init__(self, title, msg='', min=0, max=99, parent=None):
QDialog.__init__(self, parent)
self.setupUi(self)
self.setWindowTitle(title)
self.title.setText(title)
self.message.setText(msg)
self.setWindowModality(Qt.ApplicationModal)
self.set_min(min)
self.set_max(max)
self.canceled = False
self.connect(self.button_box, SIGNAL('rejected()'), self._canceled)
def set_msg(self, msg=''):
self.message.setText(msg)
def set_value(self, val):
self.bar.setValue(val)
def set_min(self, min):
self.bar.setMinimum(min)
def set_max(self, max):
self.bar.setMaximum(max)
def _canceled(self, *args):
self.canceled = True
self.button_box.setDisabled(True)
self.title.setText(_('Aborting...'))
def keyPressEvent(self, ev):
if ev.key() == Qt.Key_Escape:
self._canceled()
else:
QDialog.keyPressEvent(self, ev)

72
src/calibre/gui2/dialogs/progress.ui Normal file
View File

@ -0,0 +1,72 @@
<ui version="4.0" >
<class>Dialog</class>
<widget class="QDialog" name="Dialog" >
<property name="geometry" >
<rect>
<x>0</x>
<y>0</y>
<width>712</width>
<height>308</height>
</rect>
</property>
<property name="windowTitle" >
<string>Dialog</string>
</property>
<property name="windowIcon" >
<iconset resource="../images.qrc" >
<normaloff>:/images/jobs.svg</normaloff>:/images/jobs.svg</iconset>
</property>
<layout class="QGridLayout" name="gridLayout" >
<item row="0" column="0" >
<widget class="QLabel" name="title" >
<property name="font" >
<font>
<weight>75</weight>
<bold>true</bold>
</font>
</property>
<property name="text" >
<string>TextLabel</string>
</property>
<property name="alignment" >
<set>Qt::AlignCenter</set>
</property>
<property name="wordWrap" >
<bool>true</bool>
</property>
</widget>
</item>
<item row="1" column="0" >
<widget class="QProgressBar" name="bar" >
<property name="value" >
<number>0</number>
</property>
</widget>
</item>
<item row="2" column="0" >
<widget class="QLabel" name="message" >
<property name="text" >
<string>TextLabel</string>
</property>
<property name="alignment" >
<set>Qt::AlignCenter</set>
</property>
<property name="wordWrap" >
<bool>true</bool>
</property>
</widget>
</item>
<item row="3" column="0" >
<widget class="QDialogButtonBox" name="button_box" >
<property name="standardButtons" >
<set>QDialogButtonBox::Abort</set>
</property>
</widget>
</item>
</layout>
</widget>
<resources>
<include location="../images.qrc" />
</resources>
<connections/>
</ui>

BIN
src/calibre/gui2/images/news/ambito.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 508 B

BIN
src/calibre/gui2/images/news/elargentino.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 805 B

BIN
src/calibre/gui2/images/news/ftd.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 383 B

BIN
src/calibre/gui2/images/news/heise.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 636 B

BIN
src/calibre/gui2/images/news/infobae.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 425 B

BIN
src/calibre/gui2/images/news/pagina12.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 414 B

BIN
src/calibre/gui2/images/news/security_watch.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 5.1 KiB

BIN
src/calibre/gui2/images/news/sueddeutsche.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 901 B

BIN
src/calibre/gui2/images/news/zdnet.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 592 B

13
src/calibre/gui2/library.py
View File

@ -198,13 +198,18 @@ class BooksModel(QAbstractTableModel):
''' Return list indices of all cells in index.row()'''
return [ self.index(index.row(), c) for c in range(self.columnCount(None))]
def save_to_disk(self, rows, path, single_dir=False, single_format=None):
def save_to_disk(self, rows, path, single_dir=False, single_format=None,
callback=None):
rows = [row.row() for row in rows]
if single_format is None:
return self.db.export_to_dir(path, rows, self.sorted_on[0] == 'authors',
single_dir=single_dir)
return self.db.export_to_dir(path, rows,
self.sorted_on[0] == 'authors',
single_dir=single_dir,
callback=callback)
else:
return self.db.export_single_format_to_dir(path, rows, single_format)
return self.db.export_single_format_to_dir(path, rows,
single_format,
callback=callback)
def delete_books(self, indices):

87
src/calibre/gui2/main.py
View File

@ -28,6 +28,7 @@ from calibre.gui2.cover_flow import CoverFlow, DatabaseImages, pictureflowerror
from calibre.library.database import LibraryDatabase
from calibre.gui2.dialogs.scheduler import Scheduler
from calibre.gui2.update import CheckForUpdates
from calibre.gui2.dialogs.progress import ProgressDialog
from calibre.gui2.main_window import MainWindow, option_parser as _option_parser
from calibre.gui2.main_ui import Ui_MainWindow
from calibre.gui2.device import DeviceManager
@ -339,6 +340,8 @@ class Main(MainWindow, Ui_MainWindow):
self.connect(self.search, SIGNAL('search(PyQt_PyObject, PyQt_PyObject)'),
self.tags_view.model().reinit)
self.connect(self.library_view.model(), SIGNAL('count_changed(int)'), self.location_view.count_changed)
self.connect(self.library_view.model(), SIGNAL('count_changed(int)'),
self.tags_view.recount)
self.library_view.model().count_changed()
########################### Cover Flow ################################
self.cover_flow = None
@ -598,29 +601,26 @@ class Main(MainWindow, Ui_MainWindow):
root = choose_dir(self, 'recursive book import root dir dialog', 'Select root folder')
if not root:
return
progress = QProgressDialog('', '&'+_('Stop'),
0, 0, self)
progress.setWindowModality(Qt.ApplicationModal)
progress.setWindowTitle(_('Adding books recursively...'))
progress = ProgressDialog(_('Adding books recursively...'),
min=0, max=0, parent=self)
progress.show()
def callback(msg):
if msg != '.':
progress.setLabelText((_('Added ')+msg) if msg else _('Searching...'))
stop = progress.wasCanceled()
progress.set_msg((_('Added ')+msg) if msg else _('Searching...'))
QApplication.processEvents()
QApplication.sendPostedEvents()
QApplication.flush()
return stop
return progress.canceled
try:
duplicates = self.library_view.model().db.recursive_import(root, single, callback=callback)
finally:
progress.hide()
progress.close()
progress.hide()
if duplicates:
files = _('<p>Books with the same title as the following already exist in the database. Add them anyway?<ul>')
for mi, formats in duplicates:
files += '<li>'+mi.title+'</li>\n'
d = WarningDialog(_('Duplicates found!'), _('Duplicates found!'), files+'</ul></p>', self)
d = WarningDialog(_('Duplicates found!'), _('Duplicates found!'),
files+'</ul></p>', self)
if d.exec_() == QDialog.Accepted:
for mi, formats in duplicates:
self.library_view.model().db.import_book(mi, formats )
@ -686,15 +686,13 @@ class Main(MainWindow, Ui_MainWindow):
return
# Get format and metadata information
formats, metadata, names, infos = [], [], [], []
progress = QProgressDialog(_('Reading metadata...'), _('Stop'), 0, len(paths), self)
progress.setWindowTitle(_('Adding books...'))
progress.setWindowModality(Qt.ApplicationModal)
progress.setLabelText(_('Reading metadata...'))
progress = ProgressDialog(_('Adding books...'), _('Reading metadata...'),
min=0, max=len(paths), parent=self)
progress.show()
try:
for c, book in enumerate(paths):
progress.setValue(c)
if progress.wasCanceled():
progress.set_value(c)
if progress.canceled:
return
format = os.path.splitext(book)[1]
format = format[1:] if format else None
@ -713,15 +711,14 @@ class Main(MainWindow, Ui_MainWindow):
infos.append({'title':mi.title, 'authors':', '.join(mi.authors),
'cover':self.default_thumbnail, 'tags':[]})
title = mi.title if isinstance(mi.title, unicode) else mi.title.decode(preferred_encoding, 'replace')
progress.setLabelText(_('Read metadata from ')+title)
progress.set_msg(_('Read metadata from ')+title)
if not to_device:
progress.setLabelText(_('Adding books to database...'))
progress.set_msg(_('Adding books to database...'))
model = self.library_view.model()
paths = list(paths)
duplicates, number_added = model.add_books(paths, formats, metadata)
progress.cancel()
if duplicates:
files = _('<p>Books with the same title as the following already exist in the database. Add them anyway?<ul>')
for mi in duplicates[2]:
@ -734,9 +731,7 @@ class Main(MainWindow, Ui_MainWindow):
else:
self.upload_books(paths, list(map(sanitize_file_name, names)), infos, on_card=on_card)
finally:
progress.setValue(progress.maximum())
progress.hide()
progress.close()
def upload_books(self, files, names, metadata, on_card=False, memory=None):
'''
@ -979,28 +974,49 @@ class Main(MainWindow, Ui_MainWindow):
self.save_to_disk(checked, True)
def save_to_disk(self, checked, single_dir=False, single_format=None):
rows = self.current_view().selectionModel().selectedRows()
if not rows or len(rows) == 0:
d = error_dialog(self, _('Cannot save to disk'), _('No books selected'))
d.exec_()
return
progress = ProgressDialog(_('Saving to disk...'), min=0, max=len(rows),
parent=self)
def callback(count, msg):
progress.set_value(count)
progress.set_msg(_('Saved')+' '+msg)
QApplication.processEvents()
QApplication.sendPostedEvents()
QApplication.flush()
return not progress.canceled
dir = choose_dir(self, 'save to disk dialog', _('Choose destination directory'))
if not dir:
return
if self.current_view() == self.library_view:
failures = self.current_view().model().save_to_disk(rows, dir,
single_dir=single_dir, single_format=single_format)
if failures and single_format is not None:
msg = _('<p>Could not save the following books to disk, because the %s format is not available for them:<ul>')%single_format.upper()
for f in failures:
msg += '<li>%s</li>'%f[1]
msg += '</ul>'
warning_dialog(self, _('Could not save some ebooks'), msg).exec_()
QDesktopServices.openUrl(QUrl('file:'+dir))
else:
paths = self.current_view().model().paths(rows)
self.device_manager.save_books(Dispatcher(self.books_saved), paths, dir)
progress.show()
QApplication.processEvents()
QApplication.sendPostedEvents()
QApplication.flush()
try:
if self.current_view() == self.library_view:
failures = self.current_view().model().save_to_disk(rows, dir,
single_dir=single_dir, callback=callback,
single_format=single_format)
if failures and single_format is not None:
msg = _('<p>Could not save the following books to disk, because the %s format is not available for them:<ul>')%single_format.upper()
for f in failures:
msg += '<li>%s</li>'%f[1]
msg += '</ul>'
warning_dialog(self, _('Could not save some ebooks'), msg).exec_()
QDesktopServices.openUrl(QUrl('file:'+dir))
else:
paths = self.current_view().model().paths(rows)
self.device_manager.save_books(Dispatcher(self.books_saved), paths, dir)
finally:
progress.hide()
def books_saved(self, job):
if job.exception is not None:
@ -1115,6 +1131,7 @@ class Main(MainWindow, Ui_MainWindow):
os.remove(f.name)
except:
pass
self.tags_view.recount()
if self.current_view() is self.library_view:
current = self.library_view.currentIndex()
self.library_view.model().current_changed(current, QModelIndex())

10
src/calibre/gui2/tags.py
View File

@ -7,7 +7,7 @@ __docformat__ = 'restructuredtext en'
Browsing book collection by tags.
'''
from PyQt4.Qt import QAbstractItemModel, Qt, QVariant, QTreeView, QModelIndex, \
QFont, SIGNAL, QSize, QColor, QIcon
QFont, SIGNAL, QSize, QColor, QIcon, QPoint
from calibre.gui2 import config
NONE = QVariant()
@ -36,6 +36,14 @@ class TagsView(QTreeView):
if self._model.toggle(index):
self.emit(SIGNAL('tags_marked(PyQt_PyObject, PyQt_PyObject)'),
self._model.tokens(), self.match_all.isChecked())
def recount(self, *args):
ci = self.currentIndex()
if not ci.isValid():
ci = self.indexAt(QPoint(10, 10))
self.model().refresh()
if ci.isValid():
self.scrollTo(ci, QTreeView.PositionAtTop)
class TagsModel(QAbstractItemModel):

18
src/calibre/library/database.py
View File

@ -1390,10 +1390,11 @@ ALTER TABLE books ADD COLUMN isbn TEXT DEFAULT "" COLLATE NOCASE;
return [i[0] for i in self.conn.get('SELECT id FROM books')]
def export_to_dir(self, dir, indices, byauthor=False, single_dir=False,
index_is_id=False):
index_is_id=False, callback=None):
if not os.path.exists(dir):
raise IOError('Target directory does not exist: '+dir)
by_author = {}
count = 0
for index in indices:
id = index if index_is_id else self.id(index)
au = self.conn.get('SELECT author_sort FROM books WHERE id=?',
@ -1403,8 +1404,6 @@ ALTER TABLE books ADD COLUMN isbn TEXT DEFAULT "" COLLATE NOCASE;
if not au:
au = _('Unknown')
au = au.split(',')[0]
else:
au = au.replace(',', ';')
if not by_author.has_key(au):
by_author[au] = []
by_author[au].append(index)
@ -1456,6 +1455,11 @@ ALTER TABLE books ADD COLUMN isbn TEXT DEFAULT "" COLLATE NOCASE;
print 'Error setting metadata for book:', mi.title
traceback.print_exc()
f.close()
count += 1
if callable(callback):
if not callback(count, mi.title):
return
def import_book(self, mi, formats):
@ -1569,12 +1573,13 @@ ALTER TABLE books ADD COLUMN isbn TEXT DEFAULT "" COLLATE NOCASE;
return duplicates
def export_single_format_to_dir(self, dir, indices, format, index_is_id=False):
def export_single_format_to_dir(self, dir, indices, format,
index_is_id=False, callback=None):
dir = os.path.abspath(dir)
if not index_is_id:
indices = map(self.id, indices)
failures = []
for id in indices:
for count, id in enumerate(indices):
try:
data = self.format(id, format, index_is_id=True)
if not data:
@ -1599,6 +1604,9 @@ ALTER TABLE books ADD COLUMN isbn TEXT DEFAULT "" COLLATE NOCASE;
except:
pass
f.close()
if callable(callback):
if not callback(count, title):
break
return failures

6
src/calibre/linux.py
View File

@ -192,6 +192,8 @@ def setup_completion(fatal_errors):
from calibre.ebooks.epub.from_any import option_parser as any2epub
from calibre.ebooks.lit.from_any import option_parser as any2lit
from calibre.ebooks.epub.from_comic import option_parser as comic2epub
from calibre.ebooks.mobi.from_any import option_parser as any2mobi
from calibre.ebooks.mobi.writer import option_parser as oeb2mobi
from calibre.gui2.main import option_parser as guiop
any_formats = ['epub', 'htm', 'html', 'xhtml', 'xhtm', 'rar', 'zip',
'txt', 'lit', 'rtf', 'pdf', 'prc', 'mobi', 'fb2', 'odt']
@ -216,6 +218,8 @@ def setup_completion(fatal_errors):
f.write(opts_and_exts('calibre', guiop, any_formats))
f.write(opts_and_exts('any2epub', any2epub, any_formats))
f.write(opts_and_exts('any2lit', any2lit, any_formats))
f.write(opts_and_exts('any2mobi', any2mobi, any_formats))
f.write(opts_and_exts('oeb2mobi', oeb2mobi, ['mobi', 'prc']))
f.write(opts_and_exts('lrf2lrs', lrf2lrsop, ['lrf']))
f.write(opts_and_exts('lrf-meta', metaop, ['lrf']))
f.write(opts_and_exts('rtf-meta', metaop, ['rtf']))
@ -232,7 +236,7 @@ def setup_completion(fatal_errors):
f.write(opts_and_exts('lit2oeb', lit2oeb, ['lit']))
f.write(opts_and_exts('comic2lrf', comicop, ['cbz', 'cbr']))
f.write(opts_and_exts('comic2epub', comic2epub, ['cbz', 'cbr']))
f.write(opts_and_exts('comic2pdf', comic2epub, ['cbz', 'cbr']))
f.write(opts_and_exts('comic2pdf', comic2epub, ['cbz', 'cbr']))
f.write(opts_and_words('feeds2disk', feeds2disk, feed_titles))
f.write(opts_and_words('feeds2lrf', feeds2lrf, feed_titles))
f.write(opts_and_words('feeds2lrf', feeds2epub, feed_titles))

1
src/calibre/trac/bzr_commit_plugin.py
View File

@ -38,7 +38,6 @@ class cmd_commit(_cmd_commit):
print attributes['summary']
return attributes['summary']
def expand_bug(self, msg, nick, config, bug_tracker, type='trac'):
prefix = '%s_%s_'%(type, nick)
username = config.get_user_option(prefix+'username')

2
src/calibre/web/feeds/recipes/__init__.py
View File

@ -22,7 +22,7 @@ recipe_modules = ['recipe_' + r for r in (
'time_magazine', 'endgadget', 'fudzilla', 'nspm_int', 'nspm', 'pescanik',
'spiegel_int', 'themarketticker', 'tomshardware', 'xkcd', 'ftd', 'zdnet',
'joelonsoftware', 'telepolis', 'common_dreams', 'nin', 'tomshardware_de',
'pagina12', 'infobae', 'ambito', 'elargentino', 'sueddeutsche',
)]
import re, imp, inspect, time, os

44
src/calibre/web/feeds/recipes/recipe_ambito.py Normal file
View File

@ -0,0 +1,44 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
ambito.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Ambito(BasicNewsRecipe):
title = 'Ambito.com'
__author__ = 'Darko Miletic'
description = 'Informacion Libre las 24 horas'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'iso--8859-1'
cover_url = 'http://www.ambito.com/img/logo_.jpg'
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Argentina'
, '--publisher' , title
]
feeds = [
(u'Principales Noticias', u'http://www.ambito.com/rss/noticiasp.asp' )
,(u'Economia' , u'http://www.ambito.com/rss/noticias.asp?S=Econom%EDa' )
,(u'Politica' , u'http://www.ambito.com/rss/noticias.asp?S=Pol%EDtica' )
,(u'Informacion General' , u'http://www.ambito.com/rss/noticias.asp?S=Informaci%F3n%20General')
,(u'Agro' , u'http://www.ambito.com/rss/noticias.asp?S=Agro' )
,(u'Internacionales' , u'http://www.ambito.com/rss/noticias.asp?S=Internacionales' )
,(u'Deportes' , u'http://www.ambito.com/rss/noticias.asp?S=Deportes' )
,(u'Espectaculos' , u'http://www.ambito.com/rss/noticias.asp?S=Espect%E1culos' )
,(u'Tecnologia' , u'http://www.ambito.com/rss/noticias.asp?S=Tecnologia' )
,(u'Salud' , u'http://www.ambito.com/rss/noticias.asp?S=Salud' )
,(u'Ambito Nacional' , u'http://www.ambito.com/rss/noticias.asp?S=Ambito%20Nacional' )
]
def print_version(self, url):
return url.replace('http://www.ambito.com/noticia.asp?','http://www.ambito.com/noticias/imprimir.asp?')

29
src/calibre/web/feeds/recipes/recipe_clarin.py
View File

@ -6,6 +6,7 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
clarin.com
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Clarin(BasicNewsRecipe):
@ -15,33 +16,35 @@ class Clarin(BasicNewsRecipe):
oldest_article = 2
max_articles_per_feed = 100
use_embedded_content = False
cover_url = 'http://www.clarin.com/shared/v10/img/Hd/lg_Clarin.gif'
no_stylesheets = True
cover_url = strftime('http://www.clarin.com/diario/%Y/%m/%d/portada.jpg')
html2lrf_options = [
'--comment', description
, '--base-font-size', '10'
, '--category', 'news, Argentina'
, '--publisher', 'Grupo Clarin'
]
remove_tags = [
dict(name='a' , attrs={'class':'Imp' })
,dict(name='div' , attrs={'class':'Perma' })
,dict(name='h1' , text='Imprimir' )
]
feeds = [
(u'Ultimo Momento', u'http://www.clarin.com/diario/hoy/um/sumariorss.xml')
,(u'El Pais' , u'http://www.clarin.com/diario/hoy/elpais.xml' )
,(u'Opinion' , u'http://www.clarin.com/diario/hoy/opinion.xml' )
,(u'El Mundo' , u'http://www.clarin.com/diario/hoy/elmundo.xml' )
,(u'Sociedad' , u'http://www.clarin.com/diario/hoy/sociedad.xml' )
,(u'La Ciudad' , u'http://www.clarin.com/diario/hoy/laciudad.xml' )
feeds = [
(u'Ultimo Momento', u'http://www.clarin.com/diario/hoy/um/sumariorss.xml')
,(u'El Pais' , u'http://www.clarin.com/diario/hoy/elpais.xml' )
,(u'Opinion' , u'http://www.clarin.com/diario/hoy/opinion.xml' )
,(u'El Mundo' , u'http://www.clarin.com/diario/hoy/elmundo.xml' )
,(u'Sociedad' , u'http://www.clarin.com/diario/hoy/sociedad.xml' )
,(u'La Ciudad' , u'http://www.clarin.com/diario/hoy/laciudad.xml' )
,(u'Policiales' , u'http://www.clarin.com/diario/hoy/policiales.xml' )
,(u'Deportes' , u'http://www.clarin.com/diario/hoy/deportes.xml' )
,(u'Deportes' , u'http://www.clarin.com/diario/hoy/deportes.xml' )
]
def get_article_url(self, article):
artl = article.get('link', None)
rest = artl.partition('-0')[-1]
lmain = rest.partition('.')[0]
return 'http://www.servicios.clarin.com/notas/jsp/clarin/v9/notas/imprimir.jsp?pagid=' + lmain
return 'http://www.servicios.clarin.com/notas/jsp/clarin/v9/notas/imprimir.jsp?pagid=' + lmain

55
src/calibre/web/feeds/recipes/recipe_elargentino.py Normal file
View File

@ -0,0 +1,55 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
elargentino.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ElArgentino(BasicNewsRecipe):
title = 'ElArgentino.com'
__author__ = 'Darko Miletic'
description = 'Informacion Libre las 24 horas'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
cover_url = 'http://www.elargentino.com/TemplateWeb/MediosFooter/tapa_elargentino.png'
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Argentina'
, '--publisher' , 'ElArgentino.com'
]
remove_tags = [
dict(name='div', attrs={'id':'noprint' })
,dict(name='div', attrs={'class':'encabezadoImprimir'})
,dict(name='a' , attrs={'target':'_blank' })
]
feeds = [
(u'Portada' , u'http://www.elargentino.com/Highlights.aspx?Content-Type=text/xml&ChannelDesc=Home' )
,(u'Pais' , u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=112&Content-Type=text/xml&ChannelDesc=Pa%C3%ADs' )
,(u'Economia' , u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=107&Content-Type=text/xml&ChannelDesc=Econom%C3%ADa' )
,(u'Mundo' , u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=113&Content-Type=text/xml&ChannelDesc=Mundo' )
,(u'Tecnologia' , u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=118&Content-Type=text/xml&ChannelDesc=Tecnolog%C3%ADa' )
,(u'Espectaculos', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=114&Content-Type=text/xml&ChannelDesc=Espect%C3%A1culos')
,(u'Deportes' , u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=106&Content-Type=text/xml&ChannelDesc=Deportes' )
,(u'Sociedad' , u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=109&Content-Type=text/xml&ChannelDesc=Sociedad' )
,(u'Entrevistas' , u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=115&Content-Type=text/xml&ChannelDesc=Entrevistas' )
]
def print_version(self, url):
main, sep, article_part = url.partition('/nota-')
article_id, rsep, rrest = article_part.partition('-')
return u'http://www.elargentino.com/Impresion.aspx?Id=' + article_id
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8">'
soup.head.insert(0,mtag)
soup.prettify()
return soup

40
src/calibre/web/feeds/recipes/recipe_infobae.py Normal file
View File

@ -0,0 +1,40 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
infobae.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Infobae(BasicNewsRecipe):
title = 'Infobae.com'
__author__ = 'Darko Miletic'
description = 'Informacion Libre las 24 horas'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'iso-8859-1'
cover_url = 'http://www.infobae.com/imgs/header/header.gif'
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Argentina'
, '--publisher' , 'Infobae.com'
]
feeds = [
(u'Noticias' , u'http://www.infobae.com/adjuntos/html/RSS/hoy.xml' )
,(u'Salud' , u'http://www.infobae.com/adjuntos/html/RSS/salud.xml' )
,(u'Tecnologia', u'http://www.infobae.com/adjuntos/html/RSS/tecnologia.xml')
,(u'Deportes' , u'http://www.infobae.com/adjuntos/html/RSS/deportes.xml' )
]
def print_version(self, url):
main, sep, article_part = url.partition('contenidos/')
article_id, rsep, rrest = article_part.partition('-')
return u'http://www.infobae.com/notas/nota_imprimir.php?Idx=' + article_id

39
src/calibre/web/feeds/recipes/recipe_pagina12.py Normal file
View File

@ -0,0 +1,39 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
pagina12.com.ar
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Pagina12(BasicNewsRecipe):
title = u'Pagina/12'
__author__ = 'Darko Miletic'
description = 'Noticias de Argentina y el resto del mundo'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
cover_url = strftime('http://www.pagina12.com.ar/fotos/%Y%m%d/diario/TAPAN.jpg')
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Argentina'
, '--publisher' , 'La Pagina S.A.'
]
remove_tags = [
dict(name='div', attrs={'id':'volver'})
,dict(name='div', attrs={'id':'logo' })
]
feeds = [(u'Pagina/12', u'http://www.pagina12.com.ar/diario/rss/principal.xml')]
def print_version(self, url):
return url.replace('http://www.pagina12.com.ar/','http://www.pagina12.com.ar/imprimir/')

2
src/calibre/web/feeds/recipes/recipe_security_watch.py
View File

@ -4,7 +4,7 @@ class SecurityWatch(BasicNewsRecipe):
title = u'securitywatch'
description = 'security news'
timefmt = ' [%d %b %Y]'
__author__ = 'Oliver'
__author__ = 'Oliver Niesner'
no_stylesheets = True
oldest_article = 14
max_articles_per_feed = 100

62
src/calibre/web/feeds/recipes/recipe_sueddeutsche.py Normal file
View File

@ -0,0 +1,62 @@
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
Fetch sueddeutsche.
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Sueddeutsche(BasicNewsRecipe):
title = u'Sueddeutsche'
description = 'News from Germany'
__author__ = 'Oliver Niesner'
use_embedded_content = False
timefmt = ' [%d %b %Y]'
max_articles_per_feed = 40
no_stylesheets = True
encoding = 'latin1'
remove_tags_after = [dict(name='div', attrs={'class':'artikelBox navigatorBox'})]
#dict(name='table', attrs={'class':'bgf2f2f2 absatz print100'})]
remove_tags = [dict(name='div', attrs={'class':'bannerSuperBanner'}),
dict(name='div', attrs={'class':'bannerSky'}),
dict(name='div', attrs={'class':'footerLinks'}),
dict(name='div', attrs={'class':'seitenanfang'}),
dict(name='td', attrs={'class':'mar5'}),
dict(name='table', attrs={'class':'pageAktiv'}),
dict(name='table', attrs={'class':'xartable'}),
dict(name='table', attrs={'class':'wpnavi'}),
dict(name='table', attrs={'class':'bgcontent absatz'}),
dict(name='table', attrs={'class':'footer'}),
dict(name='table', attrs={'class':'artikelBox'}),
dict(name='table', attrs={'class':'kommentare'}),
dict(name='table', attrs={'class':'pageBoxBot'}),
dict(name='div', attrs={'class':'artikelBox navigatorBox'}),
dict(name='div', attrs={'class':'similar-article-box'}),
dict(name='div', attrs={'class':'videoBigHack'}),
dict(name='td', attrs={'class':'artikelDruckenRight'}),
dict(name='span', attrs={'class':'hidePrint'}),
dict(id='headerLBox'),
dict(id='rechteSpalte'),
dict(id='newsticker-list-small'),
dict(id='ntop5'),
dict(id='ntop5send'),
dict(id='ntop5commented'),
dict(id='nnav-bgheader'),
dict(id='nnav-headerteaser'),
dict(id='nnav-head'),
dict(id='nnav-top'),
dict(id='nnav-logodiv'),
dict(id='nnav-logo'),
dict(id='nnav-oly'),
dict(id='readcomment')]
feeds = [ (u'Sueddeutsche', u'http://www.sueddeutsche.de/app/service/rss/alles/rss.xml') ]
def postprocess_html(self, soup, first_fetch):
for t in soup.findAll(['table', 'tr', 'td']):
t.name = 'div'
return soup

6
src/calibre/web/fetch/simple.py
View File

@ -395,7 +395,11 @@ class RecursiveFetcher(object, LoggingInterface):
if self.download_stylesheets:
self.process_stylesheets(soup, newbaseurl)
res = os.path.join(linkdiskpath, basename(iurl))
_fname = basename(iurl)
if not isinstance(_fname, unicode):
_fname.decode('latin1', 'replace')
_fname.encode('ascii', 'replace').replace('%', '')
res = os.path.join(linkdiskpath, _fname)
self.downloaded_paths.append(res)
self.filemap[nurl] = res
if recursion_level < self.max_recursions: