Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2026-05-20 22:12:37 -04:00
Code Issues Packages Projects Releases Wiki Activity

Sync to trunk.

Browse Source
This commit is contained in:
John Schember
2009-07-06 19:14:58 -04:00
parent a2457cb939 4f1c599581
commit 0e8cc35f18
48 changed files with 22137 additions and 20673 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/calibre/customize/profiles.py
+13
View File
@@ -250,6 +250,19 @@ class KindleDXOutput(OutputProfile):
def tags_to_string(cls, tags):
return 'ttt '.join(tags)+'ttt '
class IlliadOutput(OutputProfile):
name = 'Illiad'
short_name = 'illiad'
description = _('This profile is intended for the Irex Illiad.')
screen_size = (760, 925)
comic_screen_size = (760, 925)
dpi = 160.0
fbase = 12
fsizes = [7.5, 9, 10, 12, 15.5, 20, 22, 24]
output_profiles = [OutputProfile, SonyReaderOutput, MSReaderOutput,
MobipocketOutput, HanlinV3Output, CybookG3Output, KindleOutput,
src/calibre/ebooks/epub/output.py
+47 -21
View File
@@ -17,6 +17,34 @@ from calibre.customize.conversion import OptionRecommendation
from lxml import etree
block_level_tags = (
'address',
'body',
'blockquote',
'center',
'dir',
'div',
'dl',
'fieldset',
'form',
'h1',
'h2',
'h3',
'h4',
'h5',
'h6',
'hr',
'isindex',
'menu',
'noframes',
'noscript',
'ol',
'p',
'pre',
'table',
'ul',
)
class EPUBOutput(OutputFormatPlugin):
@@ -197,8 +225,6 @@ class EPUBOutput(OutputFormatPlugin):
if 'titlepage' in self.oeb.guide.refs:
self.oeb.guide.refs['titlepage'].href = item.href
def condense_ncx(self, ncx_path):
if not self.opts.pretty_print:
tree = etree.parse(ncx_path)
@@ -210,46 +236,46 @@ class EPUBOutput(OutputFormatPlugin):
compressed = etree.tostring(tree.getroot(), encoding='utf-8')
open(ncx_path, 'wb').write(compressed)
def workaround_ade_quirks(self):
'''
Perform various markup transforms to get the output to render correctly
in the quirky ADE.
'''
from calibre.ebooks.oeb.base import XPNSMAP, XHTML, OEB_STYLES
from lxml.etree import XPath as _XPath
from functools import partial
XPath = partial(_XPath, namespaces=XPNSMAP)
from calibre.ebooks.oeb.base import XPath, XHTML, OEB_STYLES, barename
for x in self.oeb.spine:
root = x.data
body = XPath('//h:body')(root)
if body:
body = body[0]
# Replace <br> that are children of <body> as ADE doesn't handle them
if hasattr(body, 'xpath'):
for br in XPath('./h:br')(body):
if br.getparent() is None:
continue
try:
sibling = br.itersiblings().next()
prior = br.itersiblings(preceding=True).next()
priortag = barename(prior.tag)
priortext = prior.tail
except:
sibling = None
priortag = 'body'
priortext = body.text
if priortext:
priortext = priortext.strip()
br.tag = XHTML('p')
br.text = u'\u00a0'
if (br.tail and br.tail.strip()) or sibling is None or \
getattr(sibling, 'tag', '') != XHTML('br'):
style = br.get('style', '').split(';')
style = filter(None, map(lambda x: x.strip(), style))
style.append('margin: 0pt; border:0pt; height:0pt')
br.set('style', '; '.join(style))
style = br.get('style', '').split(';')
style = filter(None, map(lambda x: x.strip(), style))
style.append('margin:0pt; border:0pt')
# If the prior tag is a block (including a <br> we replaced)
# then this <br> replacement should have a 1-line height.
# Otherwise it should have no height.
if not priortext and priortag in block_level_tags:
style.append('height:1em')
else:
sibling.getparent().remove(sibling)
if sibling.tail:
if not br.tail:
br.tail = ''
br.tail += sibling.tail
style.append('height:0pt')
br.set('style', '; '.join(style))
for tag in XPath('//h:embed')(root):
tag.getparent().remove(tag)
src/calibre/ebooks/metadata/__init__.py
+9 -3
View File
@@ -218,7 +218,7 @@ class MetaInformation(object):
'isbn', 'tags', 'cover_data', 'application_id', 'guide',
'manifest', 'spine', 'toc', 'cover', 'language',
'book_producer', 'timestamp', 'lccn', 'lcc', 'ddc',
'pubdate'):
'pubdate', 'rights', 'publication_type'):
if hasattr(mi, attr):
setattr(ans, attr, getattr(mi, attr))
@@ -243,7 +243,8 @@ class MetaInformation(object):
for x in ('author_sort', 'title_sort', 'comments', 'category', 'publisher',
'series', 'series_index', 'rating', 'isbn', 'language',
'application_id', 'manifest', 'toc', 'spine', 'guide', 'cover',
'book_producer', 'timestamp', 'lccn', 'lcc', 'ddc', 'pubdate'
'book_producer', 'timestamp', 'lccn', 'lcc', 'ddc', 'pubdate',
'rights', 'publication_type',
):
setattr(self, x, getattr(mi, x, None))
@@ -262,7 +263,8 @@ class MetaInformation(object):
'publisher', 'series', 'series_index', 'rating',
'isbn', 'application_id', 'manifest', 'spine', 'toc',
'cover', 'language', 'guide', 'book_producer',
'timestamp', 'lccn', 'lcc', 'ddc', 'pubdate'):
'timestamp', 'lccn', 'lcc', 'ddc', 'pubdate', 'rights',
'publication_type'):
if hasattr(mi, attr):
val = getattr(mi, attr)
if val is not None:
@@ -332,6 +334,8 @@ class MetaInformation(object):
fmt('Timestamp', self.timestamp.isoformat(' '))
if self.pubdate is not None:
fmt('Published', self.pubdate.isoformat(' '))
if self.rights is not None:
fmt('Rights', unicode(self.rights))
if self.lccn:
fmt('LCCN', unicode(self.lccn))
if self.lcc:
@@ -362,6 +366,8 @@ class MetaInformation(object):
ans += [(_('Timestamp'), unicode(self.timestamp.isoformat(' ')))]
if self.pubdate is not None:
ans += [(_('Published'), unicode(self.pubdate.isoformat(' ')))]
if self.rights is not None:
ans += [(_('Rights'), unicode(self.rights.isoformat(' ')))]
for i, x in enumerate(ans):
ans[i] = u'<tr><td><b>%s</b></td><td>%s</td></tr>'%x
return u'<table>%s</table>'%u'\n'.join(ans)
src/calibre/ebooks/metadata/ncx.xml
+3
View File
@@ -7,6 +7,7 @@ import re
xml:lang="en"
xmlns="http://www.daisy.org/z3986/2005/ncx/"
xmlns:py="http://genshi.edgewall.org/"
xmlns:calibre="http://calibre.kovidgoyal.net/2009/metadata"
>
<head>
<meta name="dtb:uid" content="${uid}"/>
@@ -23,6 +24,8 @@ import re
${'%*s'%(4*level,'')}<text>${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 '')}" />
${'%*s'%(4*level,'')}<calibre:meta py:if="np.author" name="author">${np.author}</calibre:meta>
${'%*s'%(4*level,'')}<calibre:meta py:if="np.description" name="description">${np.description}</calibre:meta>
<py:for each="np2 in np">${navpoint(np2, level+1)}</py:for>
${'%*s'%(4*level,'')}</navPoint>
</py:def>
src/calibre/ebooks/metadata/opf.xml
+1
View File
@@ -19,6 +19,7 @@
<meta py:if="mi.series_index is not None" name="calibre:series_index" content="${mi.format_series_index()}"/>
<meta py:if="mi.rating is not None" name="calibre:rating" content="${mi.rating}"/>
<meta py:if="mi.timestamp is not None" name="calibre:timestamp" content="${mi.timestamp.isoformat()}"/>
<meta py:if="mi.publication_type is not None" name="calibre:publication_type" content="${mi.publication_type}" />
<py:for each="tag in mi.tags">
<dc:subject py:if="mi.tags is not None">${tag}</dc:subject>
</py:for>
src/calibre/ebooks/metadata/opf2.py
+2
View File
@@ -440,10 +440,12 @@ class OPF(object):
language = MetadataField('language')
comments = MetadataField('description')
category = MetadataField('category')
rights = MetadataField('rights')
series = MetadataField('series', is_dc=False)
series_index = MetadataField('series_index', is_dc=False, formatter=float, none_is=1)
rating = MetadataField('rating', is_dc=False, formatter=int)
pubdate = MetadataField('date', formatter=parser.parse)
publication_type = MetadataField('publication_type', is_dc=False)
timestamp = MetadataField('timestamp', is_dc=False, formatter=parser.parse)
src/calibre/ebooks/metadata/toc.py
+8 -3
View File
@@ -21,7 +21,8 @@ class NCXSoup(BeautifulStoneSoup):
class TOC(list):
def __init__(self, href=None, fragment=None, text=None, parent=None, play_order=0,
base_path=os.getcwd(), type='unknown'):
base_path=os.getcwd(), type='unknown', author=None,
description=None):
self.href = href
self.fragment = fragment
if not self.fragment:
@@ -31,6 +32,8 @@ class TOC(list):
self.base_path = base_path
self.play_order = play_order
self.type = type
self.author = author
self.description = description
def __str__(self):
lines = ['TOC: %s#%s'%(self.href, self.fragment)]
@@ -59,11 +62,13 @@ class TOC(list):
list.remove(self, entry)
entry.parent = None
def add_item(self, href, fragment, text, play_order=None, type='unknown'):
def add_item(self, href, fragment, text, play_order=None, type='unknown',
author=None, description=None):
if play_order is None:
play_order = (self[-1].play_order if len(self) else self.play_order) + 1
self.append(TOC(href=href, fragment=fragment, text=text, parent=self,
base_path=self.base_path, play_order=play_order, type=type))
base_path=self.base_path, play_order=play_order,
type=type, author=author, description=description))
return self[-1]
def top_level_items(self):
src/calibre/ebooks/mobi/output.py
+70 -4
View File
@@ -6,6 +6,7 @@ __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
from cStringIO import StringIO
from calibre.customize.conversion import OutputFormatPlugin
from calibre.customize.conversion import OptionRecommendation
@@ -31,16 +32,80 @@ class MOBIOutput(OutputFormatPlugin):
OptionRecommendation(name='toc_title', recommended_value=None,
help=_('Title for any generated in-line table of contents.')
),
OptionRecommendation(name='mobi_periodical',
recommended_value=False, level=OptionRecommendation.LOW,
help=_('Generate a periodical rather than a book.')
),
OptionRecommendation(name='dont_compress',
recommended_value=False, level=OptionRecommendation.LOW,
help=_('Disable compression of the file contents.')
),
])
def check_for_periodical(self):
if self.oeb.metadata.publication_type and \
unicode(self.oeb.metadata.publication_type[0]).startswith('periodical:'):
self.periodicalize_toc()
self.check_for_masthead()
self.opts.mobi_periodical = True
else:
self.opts.mobi_periodical = False
def check_for_masthead(self):
found = False
for typ in self.oeb.guide:
if type == 'masthead':
found = True
break
if not found:
self.oeb.log.debug('No masthead found, generating default one...')
from calibre.resources import server_resources
try:
from PIL import Image as PILImage
PILImage
except ImportError:
import Image as PILImage
raw = StringIO(server_resources['calibre.png'])
im = PILImage.open(raw)
of = StringIO()
im.save(of, 'GIF')
raw = of.getvalue()
id, href = self.oeb.manifest.generate('masthead', 'masthead')
self.oeb.manifest.add(id, href, 'image/gif', data=raw)
self.oeb.guide.add('masthead', 'Masthead Image', href)
def periodicalize_toc(self):
from calibre.ebooks.oeb.base import TOC
toc = self.oeb.toc
if toc and toc[0].klass != 'periodical':
self.log('Converting TOC for MOBI periodical indexing...')
articles = {}
if toc.depth < 3:
sections = [TOC(klass='section')]
for x in toc:
sections[0].append(x)
else:
sections = list(toc)
for x in sections:
x.klass = 'section'
for sec in sections:
articles[id(sec)] = []
for a in list(sec):
a.klass = 'article'
articles[id(sec)].append(a)
sec.nodes.remove(a)
root = TOC(klass='periodical',
title=unicode(self.oeb.metadata.title[0]))
for s in sections:
if articles[id(s)]:
for a in articles[id(s)]:
s.nodes.append(a)
root.nodes.append(s)
for x in list(toc.nodes):
toc.nodes.remove(x)
toc.nodes.append(root)
def convert(self, oeb, output_path, input_plugin, opts, log):
self.log, self.opts, self.oeb = log, opts, oeb
from calibre.ebooks.mobi.writer import PALM_MAX_IMAGE_SIZE, \
@@ -60,6 +125,7 @@ class MOBIOutput(OutputFormatPlugin):
rasterizer(oeb, opts)
mobimlizer = MobiMLizer(ignore_tables=opts.linearize_tables)
mobimlizer(oeb, opts)
self.check_for_periodical()
write_page_breaks_after_item = not input_plugin is plugin_for_input_format('cbz')
writer = MobiWriter(opts, imagemax=imagemax,
compression=UNCOMPRESSED if opts.dont_compress else PALMDOC,
src/calibre/ebooks/mobi/writer.py
+1895 -336
View File
File diff suppressed because it is too large Load Diff
src/calibre/ebooks/oeb/base.py
+3 -2
View File
@@ -47,7 +47,7 @@ XPNSMAP = {'h' : XHTML_NS, 'o1' : OPF1_NS, 'o2' : OPF2_NS,
'd09': DC09_NS, 'd10': DC10_NS, 'd11': DC11_NS,
'xsi': XSI_NS, 'dt' : DCTERMS_NS, 'ncx': NCX_NS,
'svg': SVG_NS, 'xl' : XLINK_NS, 're': RE_NS,
'mbp': MBP_NS }
'mbp': MBP_NS, 'calibre': CALIBRE_NS }
OPF1_NSMAP = {'dc': DC11_NS, 'oebpackage': OPF1_NS}
OPF2_NSMAP = {'opf': OPF2_NS, 'dc': DC11_NS, 'dcterms': DCTERMS_NS,
@@ -455,7 +455,8 @@ class Metadata(object):
'description', 'format', 'identifier', 'language',
'publisher', 'relation', 'rights', 'source',
'subject', 'title', 'type'])
CALIBRE_TERMS = set(['series', 'series_index', 'rating', 'timestamp'])
CALIBRE_TERMS = set(['series', 'series_index', 'rating', 'timestamp',
'publication_type'])
OPF_ATTRS = {'role': OPF('role'), 'file-as': OPF('file-as'),
'scheme': OPF('scheme'), 'event': OPF('event'),
'type': XSI('type'), 'lang': XML('lang'), 'id': 'id'}
src/calibre/ebooks/oeb/reader.py
+9 -4
View File
@@ -192,6 +192,7 @@ class OEBReader(object):
if not scheme and href not in known:
new.add(href)
unchecked.clear()
warned = set([])
for href in new:
known.add(href)
is_invalid = False
@@ -202,9 +203,13 @@ class OEBReader(object):
if is_invalid:
continue
if not self.oeb.container.exists(href):
self.logger.warn('Referenced file %r not found' % href)
if href not in warned:
self.logger.warn('Referenced file %r not found' % href)
warned.add(href)
continue
self.logger.warn('Referenced file %r not in manifest' % href)
if href not in warned:
self.logger.warn('Referenced file %r not in manifest' % href)
warned.add(href)
id, _ = manifest.generate(id='added')
guessed = guess_type(href)[0]
media_type = guessed or BINARY_MIME
@@ -330,14 +335,14 @@ class OEBReader(object):
po = int(child.get('playOrder', self.oeb.toc.next_play_order()))
authorElement = xpath(child,
'descendant::mbp:meta[@name = "author"]')
'descendant::calibre:meta[@name = "author"]')
if authorElement :
author = authorElement[0].text
else :
author = None
descriptionElement = xpath(child,
'descendant::mbp:meta[@name = "description"]')
'descendant::calibre:meta[@name = "description"]')
if descriptionElement :
description = descriptionElement[0].text
else :
src/calibre/ebooks/oeb/transforms/metadata.py
+6 -1
View File
@@ -63,11 +63,16 @@ def meta_info_to_oeb_metadata(mi, m, log):
if mi.timestamp is not None:
m.clear('timestamp')
m.add('timestamp', mi.timestamp.isoformat())
if mi.rights is not None:
m.clear('rights')
m.add('rights', mi.rights)
if mi.publication_type is not None:
m.clear('publication_type')
m.add('publication_type', mi.publication_type)
if not m.timestamp:
m.add('timestamp', datetime.utcnow().isoformat())
class MergeMetadata(object):
'Merge in user metadata, including cover'
src/calibre/ebooks/oeb/transforms/structure.py
+1
View File
@@ -13,6 +13,7 @@ from urlparse import urlparse
from calibre.ebooks.oeb.base import XPNSMAP, TOC, XHTML
from calibre.ebooks import ConversionError
def XPath(x):
try:
return etree.XPath(x, namespaces=XPNSMAP)
src/calibre/ebooks/oeb/transforms/trimmanifest.py
-3
View File
@@ -64,8 +64,5 @@ class ManifestTrimmer(object):
unchecked = new
for item in oeb.manifest.values():
if item not in used:
if getattr(self.opts, 'mobi_periodical', False) and \
item.href == 'images/mastheadImage.gif':
continue
oeb.logger.info('Trimming %r from manifest' % item.href)
oeb.manifest.remove(item)
src/calibre/gui2/convert/mobi_output.py
+1 -1
View File
@@ -19,7 +19,7 @@ class PluginWidget(Widget, Ui_Form):
def __init__(self, parent, get_option, get_help, db=None, book_id=None):
Widget.__init__(self, parent, 'mobi_output',
['prefer_author_sort', 'rescale_images', 'toc_title',
'dont_compress', 'mobi_periodical']
'dont_compress',]
)
self.db, self.book_id = db, book_id
self.initialize_options(get_option, get_help, db, book_id)
src/calibre/gui2/convert/mobi_output.ui
+1 -8
View File
@@ -41,7 +41,7 @@
</property>
</widget>
</item>
<item row="6" column="0">
<item row="5" column="0">
<spacer name="verticalSpacer">
<property name="orientation">
<enum>Qt::Vertical</enum>
@@ -61,13 +61,6 @@
</property>
</widget>
</item>
<item row="5" column="0">
<widget class="QCheckBox" name="opt_mobi_periodical">
<property name="text">
<string>Generate a periodical rather than a book</string>
</property>
</widget>
</item>
<item row="0" column="0">
<widget class="QCheckBox" name="opt_no_inline_toc">
<property name="text">
src/calibre/gui2/library.py
+12 -2
View File
@@ -16,6 +16,7 @@ from PyQt4.QtCore import QAbstractTableModel, QVariant, Qt, QString, \
from calibre import strftime
from calibre.ptempfile import PersistentTemporaryFile
from calibre.utils.pyparsing import ParseException
from calibre.library.database2 import FIELD_MAP
from calibre.gui2 import NONE, TableView, qstring_to_unicode, config, \
error_dialog
@@ -267,7 +268,11 @@ class BooksModel(QAbstractTableModel):
self.count_changed()
def search(self, text, refinement, reset=True):
self.db.search(text)
try:
self.db.search(text)
except ParseException:
self.emit(SIGNAL('parse_exception()'))
return
self.last_search = text
if reset:
self.clear_caches()
@@ -898,7 +903,12 @@ class DeviceBooksModel(BooksModel):
if not text or not text.strip():
self.map = list(range(len(self.db)))
else:
matches = self.search_engine.parse(text)
try:
matches = self.search_engine.parse(text)
except ParseException:
self.emit(SIGNAL('parse_exception()'))
return
self.map = []
for i in range(len(self.db)):
if i in matches:
src/calibre/library/server.py
+12 -1
View File
@@ -221,9 +221,20 @@ class LibraryServer(object):
def get_format(self, id, format):
format = format.upper()
fmt = self.db.format(id, format, index_is_id=True, as_file=True, mode='rb')
fmt = self.db.format(id, format, index_is_id=True, as_file=True,
mode='r+b')
if fmt is None:
raise cherrypy.HTTPError(404, 'book: %d does not have format: %s'%(id, format))
if format == 'EPUB':
from tempfile import TemporaryFile
from calibre.ebooks.metadata.meta import set_metadata
raw = fmt.read()
fmt = TemporaryFile()
fmt.write(raw)
fmt.seek(0)
set_metadata(fmt, self.db.get_metadata(id, index_is_id=True),
'epub')
fmt.seek(0)
mt = guess_type('dummy.'+format.lower())[0]
if mt is None:
mt = 'application/octet-stream'
src/calibre/translations/ar.po
+687 -726
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/bg.po
+669 -729
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/ca.po
+656 -716
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/cs.po
+723 -728
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/da.po
+725 -730
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/de.po
+1052 -880
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/el.po
+666 -726
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/es.po
+756 -739
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/fr.po
+944 -857
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/gl.po
+669 -729
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/he.po
+669 -729
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/hr.po
+758 -736
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/hu.po
+672 -728
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/it.po
+686 -718
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/ja.po
+666 -726
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/nb.po
+666 -726
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/nds.po
+1331 -997
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/nl.po
+672 -728
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/pl.po
+678 -726
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/pt.po
+747 -730
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/ro.po
+669 -729
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/ru.po
+745 -728
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/sk.po
+745 -728
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/sl.po
+672 -728
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/sv.po
+669 -729
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/te.po
+666 -726
View File
File diff suppressed because it is too large Load Diff
src/calibre/translations/uk.po
+669 -729
View File
File diff suppressed because it is too large Load Diff
src/calibre/web/feeds/news.py
+14 -2
View File
@@ -64,6 +64,10 @@ class BasicNewsRecipe(Recipe):
#: Delay between consecutive downloads in seconds
delay = 0
#: Publication type
#: Set to newspaper, magazine or blog
publication_type = 'unknown'
#: Number of simultaneous downloads. Set to 1 if the server is picky.
#: Automatically reduced to 1 if :attr:`BasicNewsRecipe.delay` > 0
simultaneous_downloads = 5
@@ -848,6 +852,7 @@ class BasicNewsRecipe(Recipe):
mi = MetaInformation(self.title + strftime(self.timefmt), [__appname__])
mi.publisher = __appname__
mi.author_sort = __appname__
mi.publication_type = 'periodical:'+self.publication_type
opf_path = os.path.join(dir, 'index.opf')
ncx_path = os.path.join(dir, 'index.ncx')
opf = OPFCreator(dir, mi)
@@ -878,13 +883,16 @@ class BasicNewsRecipe(Recipe):
for j, a in enumerate(f):
if getattr(a, 'downloaded', False):
adir = 'feed_%d/article_%d/'%(num, j)
desc = a.text_summary
if not desc:
desc = None
entries.append('%sindex.html'%adir)
po = self.play_order_map.get(entries[-1], None)
if po is None:
self.play_order_counter += 1
po = self.play_order_counter
parent.add_item('%sindex.html'%adir, None, a.title if a.title else _('Untitled Article'),
play_order=po)
play_order=po, description=desc)
last = os.path.join(self.output_dir, ('%sindex.html'%adir).replace('/', os.sep))
for sp in a.sub_pages:
prefix = os.path.commonprefix([opf_path, sp])
@@ -915,7 +923,11 @@ class BasicNewsRecipe(Recipe):
if po is None:
self.play_order_counter += 1
po = self.play_order_counter
feed_index(i, toc.add_item('feed_%d/index.html'%i, None, f.title, play_order=po))
desc = f.description
if not desc:
desc = None
feed_index(i, toc.add_item('feed_%d/index.html'%i, None,
f.title, play_order=po, description=desc))
else:
entries.append('feed_%d/index.html'%0)
feed_index(0, toc)
src/calibre/web/feeds/recipes/recipe_clarin.py
+21 -13
View File
@@ -7,9 +7,9 @@ clarin.com
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
from calibre.web.feeds.news import BasicNewsRecipe
class Clarin(BasicNewsRecipe):
title = 'Clarin'
__author__ = 'Darko Miletic'
@@ -22,14 +22,19 @@ class Clarin(BasicNewsRecipe):
no_stylesheets = True
cover_url = strftime('http://www.clarin.com/diario/%Y/%m/%d/portada.jpg')
remove_javascript = True
encoding = 'cp1252'
language = _('Spanish')
lang = 'es-AR'
direction = 'ltr'
extra_css = ' .Txt{ font-family: sans-serif } .Volan{ font-family: sans-serif; font-size: x-small} .Pie{ font-family: sans-serif; font-size: x-small} .Copete{font-family: sans-serif; font-size: large} .Hora{font-family: sans-serif; font-size: large} .Autor{font-family: sans-serif; font-size: small} '
html2lrf_options = [
'--comment', description
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\npretty_print=True\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
remove_tags = [
dict(name='a' , attrs={'class':'Imp' })
@@ -48,17 +53,20 @@ class Clarin(BasicNewsRecipe):
,(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]
def print_version(self, url):
rest = url.partition('-0')[-1]
lmain = rest.partition('.')[0]
return 'http://www.servicios.clarin.com/notas/jsp/clarin/v9/notas/imprimir.jsp?pagid=' + lmain
lurl = u'http://www.servicios.clarin.com/notas/jsp/clarin/v9/notas/imprimir.jsp?pagid=' + lmain
return lurl
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="es-AR"/>'
soup.head.insert(0,mtag)
soup.html['lang'] = self.lang
soup.html['dir' ] = self.direction
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
soup.head.insert(0,mlang)
soup.head.insert(1,mcharset)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')
src/calibre/web/feeds/recipes/recipe_wsj.py
+82 -68
View File
@@ -7,94 +7,108 @@ from calibre.web.feeds.news import BasicNewsRecipe
# http://online.wsj.com/page/us_in_todays_paper.html
class WallStreetJournal(BasicNewsRecipe):
title = 'The Wall Street Journal'
__author__ = 'Kovid Goyal'
class WallStreetJournal(BasicNewsRecipe):
title = 'The Wall Street Journal'
__author__ = 'Kovid Goyal and Sujata Raman'
description = 'News and current affairs.'
needs_subscription = True
language = _('English')
max_articles_per_feed = 10
timefmt = ' [%a, %b %d, %Y]'
timefmt = ' [%a, %b %d, %Y]'
no_stylesheets = True
extra_css = '''h1{color:#093D72 ; font-size:large ; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; }
h2{color:gray; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;}
.subhead{color:gray; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;}
.insettipUnit {color:#666666; font-family:Arial,Sans-serif;font-size:xx-small }
.targetCaption{ font-size:x-small; color:#333333; font-family:Arial,Helvetica,sans-serif}
.article{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
.tagline {color:#333333; font-size:xx-small}
.dateStamp {color:#666666; font-family:Arial,Helvetica,sans-serif}
h3{color:blue ;font-family:Arial,Helvetica,sans-serif; font-size:xx-small}
.byline{color:blue;font-family:Arial,Helvetica,sans-serif; font-size:xx-small}
h6{color:#333333; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small;font-style:italic; }
.paperLocation{color:#666666; font-size:xx-small}'''
remove_tags_before = dict(name='h1')
remove_tags = [
dict(id=["articleTabs_tab_article", "articleTabs_tab_comments", "articleTabs_tab_interactive"]),
{'class':['more_in', "insetContent", 'articleTools_bottom', 'aTools', "tooltip", "adSummary", "nav-inline"]},
dict(id=["articleTabs_tab_article", "articleTabs_tab_comments", "articleTabs_tab_interactive","articleTabs_tab_video","articleTabs_tab_map","articleTabs_tab_slideshow"]),
{'class':['footer_columns','network','insetCol3wide','interactive','video','slideshow','map','insettip','more_in', "insetContent", 'articleTools_bottom', 'aTools', "tooltip", "adSummary", "nav-inline"]},
dict(rel='shortcut icon'),
]
remove_tags_after = [dict(id="article_story_body"), {'class':"article story"},]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None:
br.open('http://commerce.wsj.com/auth/login')
br.select_form(nr=0)
br['user'] = self.username
br['password'] = self.password
br.submit()
def get_browser(self):
br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None:
br.open('http://commerce.wsj.com/auth/login')
br.select_form(nr=0)
br['user'] = self.username
br['password'] = self.password
br.submit()
return br
def postprocess_html(self, soup, first):
for tag in soup.findAll(name=['table', 'tr', 'td']):
tag.name = 'div'
return soup
def get_article_url(self, article):
try:
return article.feedburner_origlink.split('?')[0]
except AttributeError:
return article.link.split('?')[0]
def cleanup(self):
self.browser.open('http://online.wsj.com/logout?url=http://online.wsj.com')
feeds = [
#('Most Emailed - Day', 'http://online.wsj.com/xml/rss/3_7030.xml'),
#('Most Emailed - Week', 'http://online.wsj.com/xml/rss/3_7253.xml'),
#('Most Emailed - Month', 'http://online.wsj.com/xml/rss/3_7254.xml'),
(' Most Viewed - Day', 'http://online.wsj.com/xml/rss/3_7198.xml'),
(' Most Viewed - Week', 'http://online.wsj.com/xml/rss/3_7251.xml'),
# ('Most Viewed - Month', 'http://online.wsj.com/xml/rss/3_7252.xml'),
('Today\'s Newspaper - Page One', 'http://online.wsj.com/xml/rss/3_7205.xml'),
('Today\'s Newspaper - Marketplace', 'http://online.wsj.com/xml/rss/3_7206.xml'),
('Today\'s Newspaper - Money & Investing', 'http://online.wsj.com/xml/rss/3_7207.xml'),
('Today\'s Newspaper - Personal Journal', 'http://online.wsj.com/xml/rss/3_7208.xml'),
('Today\'s Newspaper - Weekend Journal', 'http://online.wsj.com/xml/rss/3_7209.xml'),
('Opinion', 'http://online.wsj.com/xml/rss/3_7041.xml'),
('News - U.S.: What\'s News', 'http://online.wsj.com/xml/rss/3_7011.xml'),
('News - U.S. Business', 'http://online.wsj.com/xml/rss/3_7014.xml'),
('News - Europe: What\'s News', 'http://online.wsj.com/xml/rss/3_7012.xml'),
('News - Asia: What\'s News', 'http://online.wsj.com/xml/rss/3_7013.xml'),
('News - World News', 'http://online.wsj.com/xml/rss/3_7085.xml'),
('News - Economy', 'http://online.wsj.com/xml/rss/3_7086.xml'),
('News - Earnings', 'http://online.wsj.com/xml/rss/3_7088.xml'),
('News - Health', 'http://online.wsj.com/xml/rss/3_7089.xml'),
('News - Law', 'http://online.wsj.com/xml/rss/3_7091.xml'),
('News - Media & Marketing', 'http://online.wsj.com/xml/rss/3_7020.xml'),
('Technology - What\'s News', 'http://online.wsj.com/xml/rss/3_7015.xml'),
('Technology - Gadgets', 'http://online.wsj.com/xml/rss/3_7094.xml'),
('Technology - Telecommunications', 'http://online.wsj.com/xml/rss/3_7095.xml'),
('Technology - E-commerce/Media', 'http://online.wsj.com/xml/rss/3_7096.xml'),
('Technology - Asia', 'http://online.wsj.com/xml/rss/3_7097.xml'),
('Technology - Europe', 'http://online.wsj.com/xml/rss/3_7098.xml'),
('Markets - News', 'http://online.wsj.com/xml/rss/3_7031.xml'),
('Markets - Europe News', 'http://online.wsj.com/xml/rss/3_7101.xml'),
('Markets - Asia News', 'http://online.wsj.com/xml/rss/3_7102.xml'),
('Markets - Deals & Deal Makers', 'http://online.wsj.com/xml/rss/3_7099.xml'),
('Markets - Hedge Funds', 'http://online.wsj.com/xml/rss/3_7199.xml'),
('Personal Journal', 'http://online.wsj.com/xml/rss/3_7200.xml'),
('Personal Journal - Money', 'http://online.wsj.com/xml/rss/3_7104.xml'),
('Personal Journal - Health', 'http://online.wsj.com/xml/rss/3_7089.xml'),
('Personal Journal - Autos', 'http://online.wsj.com/xml/rss/3_7092.xml'),
('Personal Journal - Homes', 'http://online.wsj.com/xml/rss/3_7105.xml'),
('Personal Journal - Travel', 'http://online.wsj.com/xml/rss/3_7106.xml'),
('Personal Journal - Careers', 'http://online.wsj.com/xml/rss/3_7107.xml'),
('Weekend & Leisure', 'http://online.wsj.com/xml/rss/3_7201.xml'),
('Weekend & Leisure - Weekend Journal', 'http://online.wsj.com/xml/rss/3_7202.xml'),
('Weekend & Leisure - Arts & Entertainment', 'http://online.wsj.com/xml/rss/3_7177.xml'),
('Weekend & Leisure - Books', 'http://online.wsj.com/xml/rss/3_7203.xml'),
('Weekend & Leisure - Sports', 'http://online.wsj.com/xml/rss/3_7204.xml'),
def cleanup(self):
self.browser.open('http://online.wsj.com/logout?url=http://online.wsj.com')
feeds = [
#('Most Emailed - Day', 'http://online.wsj.com/xml/rss/3_7030.xml'),
#('Most Emailed - Week', 'http://online.wsj.com/xml/rss/3_7253.xml'),
#('Most Emailed - Month', 'http://online.wsj.com/xml/rss/3_7254.xml'),
(' Most Viewed - Day', 'http://online.wsj.com/xml/rss/3_7198.xml'),
(' Most Viewed - Week', 'http://online.wsj.com/xml/rss/3_7251.xml'),
# ('Most Viewed - Month', 'http://online.wsj.com/xml/rss/3_7252.xml'),
('Today\'s Newspaper - Page One', 'http://online.wsj.com/xml/rss/3_7205.xml'),
('Today\'s Newspaper - Marketplace', 'http://online.wsj.com/xml/rss/3_7206.xml'),
('Today\'s Newspaper - Money & Investing', 'http://online.wsj.com/xml/rss/3_7207.xml'),
('Today\'s Newspaper - Personal Journal', 'http://online.wsj.com/xml/rss/3_7208.xml'),
('Today\'s Newspaper - Weekend Journal', 'http://online.wsj.com/xml/rss/3_7209.xml'),
('Opinion', 'http://online.wsj.com/xml/rss/3_7041.xml'),
('News - U.S.: What\'s News', 'http://online.wsj.com/xml/rss/3_7011.xml'),
('News - U.S. Business', 'http://online.wsj.com/xml/rss/3_7014.xml'),
('News - Europe: What\'s News', 'http://online.wsj.com/xml/rss/3_7012.xml'),
('News - Asia: What\'s News', 'http://online.wsj.com/xml/rss/3_7013.xml'),
('News - World News', 'http://online.wsj.com/xml/rss/3_7085.xml'),
('News - Economy', 'http://online.wsj.com/xml/rss/3_7086.xml'),
('News - Earnings', 'http://online.wsj.com/xml/rss/3_7088.xml'),
('News - Health', 'http://online.wsj.com/xml/rss/3_7089.xml'),
('News - Law', 'http://online.wsj.com/xml/rss/3_7091.xml'),
('News - Media & Marketing', 'http://online.wsj.com/xml/rss/3_7020.xml'),
('Technology - What\'s News', 'http://online.wsj.com/xml/rss/3_7015.xml'),
('Technology - Gadgets', 'http://online.wsj.com/xml/rss/3_7094.xml'),
('Technology - Telecommunications', 'http://online.wsj.com/xml/rss/3_7095.xml'),
('Technology - E-commerce/Media', 'http://online.wsj.com/xml/rss/3_7096.xml'),
('Technology - Asia', 'http://online.wsj.com/xml/rss/3_7097.xml'),
('Technology - Europe', 'http://online.wsj.com/xml/rss/3_7098.xml'),
('Markets - News', 'http://online.wsj.com/xml/rss/3_7031.xml'),
('Markets - Europe News', 'http://online.wsj.com/xml/rss/3_7101.xml'),
('Markets - Asia News', 'http://online.wsj.com/xml/rss/3_7102.xml'),
('Markets - Deals & Deal Makers', 'http://online.wsj.com/xml/rss/3_7099.xml'),
('Markets - Hedge Funds', 'http://online.wsj.com/xml/rss/3_7199.xml'),
('Personal Journal', 'http://online.wsj.com/xml/rss/3_7200.xml'),
('Personal Journal - Money', 'http://online.wsj.com/xml/rss/3_7104.xml'),
('Personal Journal - Health', 'http://online.wsj.com/xml/rss/3_7089.xml'),
('Personal Journal - Autos', 'http://online.wsj.com/xml/rss/3_7092.xml'),
('Personal Journal - Homes', 'http://online.wsj.com/xml/rss/3_7105.xml'),
('Personal Journal - Travel', 'http://online.wsj.com/xml/rss/3_7106.xml'),
('Personal Journal - Careers', 'http://online.wsj.com/xml/rss/3_7107.xml'),
('Weekend & Leisure', 'http://online.wsj.com/xml/rss/3_7201.xml'),
('Weekend & Leisure - Weekend Journal', 'http://online.wsj.com/xml/rss/3_7202.xml'),
('Weekend & Leisure - Arts & Entertainment', 'http://online.wsj.com/xml/rss/3_7177.xml'),
('Weekend & Leisure - Books', 'http://online.wsj.com/xml/rss/3_7203.xml'),
('Weekend & Leisure - Sports', 'http://online.wsj.com/xml/rss/3_7204.xml'),
]