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

Sync to trunk.

Browse Source
This commit is contained in:
John Schember 2009-07-05 15:41:44 -04:00
commit b92567f538
33 changed files with 715 additions and 577 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
installer/windows/build_installer.py
View File

@ -36,7 +36,7 @@ def run_install_jammer(installer_name='<%AppName%>-<%Version%><%Ext%>', build_fo
compression = 'zlib'
if build_for_release:
cmdline += ['--build-for-release']
compression = 'lzma (solid)'
#compression = 'lzma (solid)'
cmdline += ['-DCompressionMethod', compression]
cmdline += ['--build', mpi]
#print 'Running installjammer with cmdline:'

5
src/calibre/devices/prs500/cli/main.py
View File

@ -180,7 +180,8 @@ def main():
if not cols: # On windows terminal width is unknown
cols = 80
parser = OptionParser(usage="usage: %prog [options] command args\n\ncommand is one of: info, books, df, ls, cp, mkdir, touch, cat, rm\n\n"+
parser = OptionParser(usage="usage: %prog [options] command args\n\ncommand "+
"is one of: info, books, df, ls, cp, mkdir, touch, cat, rm, eject\n\n"+
"For help on a particular command: %prog command", version=__appname__+" version: " + __version__)
parser.add_option("--log-packets", help="print out packet stream to stdout. "+\
"The numbers in the left column are byte offsets that allow the packet size to be read off easily.",
@ -222,6 +223,8 @@ def main():
for i in range(3):
print "%-10s\t%s\t%s\t%s\t%s"%(where[i], human_readable(total[i]), human_readable(total[i]-free[i]), human_readable(free[i]),\
str(0 if total[i]==0 else int(100*(total[i]-free[i])/(total[i]*1.)))+"%")
elif command == 'eject':
dev.eject()
elif command == "books":
print "Books in main memory:"
for book in dev.books():

14
src/calibre/devices/usbms/device.py
View File

@ -7,7 +7,7 @@ intended to be subclassed with the relevant parts implemented for a particular
device. This class handles device detection.
'''
import os, subprocess, time, re, sys, glob
import os, subprocess, time, re, sys, glob, shutil
from itertools import repeat
from calibre.devices.interface import DevicePlugin
@ -548,13 +548,23 @@ class Device(DeviceConfig, DevicePlugin):
drives = self.find_device_nodes()
for drive in drives:
if drive:
cmd = ['pumount']
cmd = ['pumount', '-l']
try:
p = subprocess.Popen(cmd + [drive])
except:
pass
while p.poll() is None:
time.sleep(0.1)
if p.returncode == 0:
for x in ('_main_prefix', '_card_a_prefix', '_card_b_prefix'):
x = getattr(self, x, None)
if x is not None:
if x.startswith('/media/') and os.path.exists(x):
try:
shutil.rmtree(x)
except:
pass
def eject(self):
if islinux:

2
src/calibre/ebooks/comic/input.py
View File

@ -283,7 +283,7 @@ class ComicInput(InputFormatPlugin):
OptionRecommendation(name='disable_trim', recommended_value=False,
help=_('Disable trimming of comic pages. For some comics, '
'trimming might remove content as well as borders.')),
OptionRecommendation(name='landspace', recommended_value=False,
OptionRecommendation(name='landscape', recommended_value=False,
help=_("Don't split landscape images into two portrait images")),
OptionRecommendation(name='wide', recommended_value=False,
help=_("Keep aspect ratio and scale image using screen height as "

21
src/calibre/ebooks/lit/writer.py
View File

@ -161,7 +161,7 @@ class ReBinary(object):
def tree_to_binary(self, elem, nsrmap=NSRMAP, parents=[],
inhead=False, preserve=False):
if not isinstance(elem.tag, basestring):
self.write(etree.tostring(elem))
# Don't emit any comments or raw entities
return
nsrmap = copy.copy(nsrmap)
attrib = dict(elem.attrib)
@ -308,23 +308,6 @@ class LitWriter(object):
else:
self._logger.warn('No suitable cover image found.')
# Remove comments because they are not supported by LIT HTML
for item in oeb.spine:
for elem in item.data.getiterator():
print elem.tag
if isinstance(elem, etree._Comment):
tail = elem.tail
parent = elem.getparent()
parent.remove(elem)
text = u''
if parent.text:
text += parent.text
if tail:
text += tail
parent.text = text
def __call__(self, oeb, path):
if hasattr(path, 'write'):
return self._dump_stream(oeb, path)
@ -726,5 +709,3 @@ class LitWriter(object):
ichunk = ''.join(['AOLI', pack('<IQ', rem, len(dchunks)),
ichunk.getvalue(), ('\0' * pad), pack('<H', len(dchunks))])
return dcounts, dchunks, ichunk

20
src/calibre/ebooks/metadata/mobi.py
View File

@ -11,11 +11,14 @@ __docformat__ = 'restructuredtext en'
from struct import pack, unpack
from cStringIO import StringIO
from datetime import datetime
from calibre.ebooks.mobi import MobiError
from calibre.ebooks.mobi.writer import rescale_image, MAX_THUMB_DIMEN
from calibre.ebooks.mobi.langcodes import iana2mobi
class StreamSlicer(object):
def __init__(self, stream, start=0, stop=None):
self._stream = stream
self.start = start
@ -84,17 +87,22 @@ class MetadataUpdater(object):
flags, = unpack('>I', record0[128:132])
have_exth = self.have_exth = (flags & 0x40) != 0
self.cover_record = self.thumbnail_record = None
self.timestamp = None
if not have_exth:
return
exth_off = unpack('>I', record0[20:24])[0] + 16 + record0.start
exth = self.exth = StreamSlicer(stream, exth_off, record0.stop)
nitems, = unpack('>I', exth[8:12])
pos = 12
# Store any EXTH fields not specifiable in GUI
for i in xrange(nitems):
id, size = unpack('>II', exth[pos:pos + 8])
content = exth[pos + 8: pos + size]
pos += size
if id == 201:
if id == 106:
self.timestamp = content
elif id == 201:
rindex, = self.cover_rindex, = unpack('>I', content)
self.cover_record = self.record(rindex + image_base)
elif id == 202:
@ -134,6 +142,16 @@ class MetadataUpdater(object):
if mi.tags:
subjects = '; '.join(mi.tags)
recs.append((105, subjects.encode(self.codec, 'replace')))
if mi.pubdate:
recs.append((106, str(mi.pubdate).encode(self.codec, 'replace')))
elif mi.timestamp:
recs.append((106, str(mi.timestamp).encode(self.codec, 'replace')))
elif self.timestamp:
recs.append(106, self.timestamp)
else:
recs.append((106, str(datetime.now()).encode(self.codec, 'replace')))
if self.cover_record is not None:
recs.append((201, pack('>I', self.cover_rindex)))
recs.append((203, pack('>I', 0)))

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

@ -49,6 +49,7 @@ class BlockState(object):
class FormatState(object):
def __init__(self):
self.rendered = False
self.left = 0.
self.halign = 'auto'
self.indent = 0.
@ -159,13 +160,15 @@ class MobiMLizer(object):
indent = 0
elif indent != 0 and abs(indent) < self.profile.fbase:
indent = (indent / abs(indent)) * self.profile.fbase
if tag in NESTABLE_TAGS:
if tag in NESTABLE_TAGS and not istate.rendered:
para = wrapper = etree.SubElement(
parent, XHTML(tag), attrib=istate.attrib)
bstate.nested.append(para)
if tag == 'li' and len(istates) > 1:
istates[-2].list_num += 1
para.attrib['value'] = str(istates[-2].list_num)
elif tag in NESTABLE_TAGS and istate.rendered:
para = wrapper = bstate.nested[-1]
elif left > 0 and indent >= 0:
para = wrapper = etree.SubElement(parent, XHTML('blockquote'))
para = wrapper
@ -189,6 +192,7 @@ class MobiMLizer(object):
vspace -= 1
if istate.halign != 'auto' and isinstance(istate.halign, (str, unicode)):
para.attrib['align'] = istate.halign
istate.rendered = True
pstate = bstate.istate
if tag in CONTENT_TAGS:
bstate.inline = para
@ -253,6 +257,7 @@ class MobiMLizer(object):
return
tag = barename(elem.tag)
istate = copy.copy(istates[-1])
istate.rendered = False
istate.list_num = 0
istates.append(istate)
left = 0

12
src/calibre/ebooks/mobi/output.py
View File

@ -24,6 +24,10 @@ class MOBIOutput(OutputFormatPlugin):
recommended_value=False, level=OptionRecommendation.LOW,
help=_('When present, use author sort field as author.')
),
OptionRecommendation(name='no_inline_toc',
recommended_value=False, level=OptionRecommendation.LOW,
help=_('Don\'t add Table of Contents to end of book. Useful if '
'the book has its own table of contents.')),
OptionRecommendation(name='toc_title', recommended_value=None,
help=_('Title for any generated in-line table of contents.')
),
@ -35,8 +39,6 @@ class MOBIOutput(OutputFormatPlugin):
recommended_value=False, level=OptionRecommendation.LOW,
help=_('Disable compression of the file contents.')
),
])
def convert(self, oeb, output_path, input_plugin, opts, log):
@ -49,8 +51,9 @@ class MOBIOutput(OutputFormatPlugin):
from calibre.ebooks.oeb.transforms.htmltoc import HTMLTOCAdder
from calibre.customize.ui import plugin_for_input_format
imagemax = PALM_MAX_IMAGE_SIZE if opts.rescale_images else None
tocadder = HTMLTOCAdder(title=opts.toc_title)
tocadder(oeb, opts)
if not opts.no_inline_toc:
tocadder = HTMLTOCAdder(title=opts.toc_title)
tocadder(oeb, opts)
mangler = CaseMangler()
mangler(oeb, opts)
rasterizer = SVGRasterizer()
@ -58,7 +61,6 @@ class MOBIOutput(OutputFormatPlugin):
mobimlizer = MobiMLizer(ignore_tables=opts.linearize_tables)
mobimlizer(oeb, opts)
write_page_breaks_after_item = not input_plugin is plugin_for_input_format('cbz')
print 111111, write_page_breaks_after_item
writer = MobiWriter(opts, imagemax=imagemax,
compression=UNCOMPRESSED if opts.dont_compress else PALMDOC,
prefer_author_sort=opts.prefer_author_sort,

5
src/calibre/ebooks/mobi/reader.py
View File

@ -345,10 +345,13 @@ class MobiReader(object):
root.insert(0, head)
head.text = '\n\t'
link = head.makeelement('link', {'type':'text/css',
'href':'styles.css'})
'href':'styles.css', 'rel':'stylesheet'})
head.insert(0, link)
link.tail = '\n\t'
title = head.xpath('descendant::title')
m = head.makeelement('meta', {'http-equiv':'Content-Type',
'content':'text/html; charset=utf-8'})
head.insert(0, m)
if not title:
title = head.makeelement('title', {})
title.text = self.book_header.title

5
src/calibre/ebooks/oeb/base.py
View File

@ -455,7 +455,7 @@ class Metadata(object):
'description', 'format', 'identifier', 'language',
'publisher', 'relation', 'rights', 'source',
'subject', 'title', 'type'])
CALIBRE_TERMS = set(['series', 'series_index', 'rating'])
CALIBRE_TERMS = set(['series', 'series_index', 'rating', 'timestamp'])
OPF_ATTRS = {'role': OPF('role'), 'file-as': OPF('file-as'),
'scheme': OPF('scheme'), 'event': OPF('event'),
'type': XSI('type'), 'lang': XML('lang'), 'id': 'id'}
@ -693,6 +693,7 @@ class Metadata(object):
def to_opf2(self, parent=None):
nsmap = self._opf2_nsmap
nsrmap = dict((value, key) for key, value in nsmap.items())
nsmap.pop('opf', '')
elem = element(parent, OPF('metadata'), nsmap=nsmap)
for term in self.items:
for item in self.items[term]:
@ -877,7 +878,7 @@ class Manifest(object):
if title:
title = unicode(title[0])
else:
title = 'No title'
title = _('Unknown')
return self._parse_xhtml(txt_to_markdown(data, title))

3
src/calibre/ebooks/oeb/output.py
View File

@ -28,9 +28,8 @@ class OEBOutput(OutputFormatPlugin):
href, root = results.pop(key, [None, None])
if root is not None:
raw = etree.tostring(root, pretty_print=True,
encoding='utf-8')
encoding='utf-8', xml_declaration=True)
with open(href, 'wb') as f:
f.write('<?xml version="1.0" encoding="UTF-8" ?>\n')
f.write(raw)
for item in oeb_book.manifest:

5
src/calibre/ebooks/oeb/reader.py
View File

@ -129,6 +129,9 @@ class OEBReader(object):
from calibre.ebooks.oeb.transforms.metadata import meta_info_to_oeb_metadata
stream = cStringIO.StringIO(etree.tostring(opf))
mi = MetaInformation(OPF(stream))
if not mi.language:
mi.language = get_lang()
self.oeb.metadata.add('language', mi.language)
if not mi.title:
mi.title = self.oeb.translate(__('Unknown'))
if not mi.authors:
@ -136,8 +139,6 @@ class OEBReader(object):
if not mi.book_producer:
mi.book_producer = '%(a)s (%(v)s) [http://%(a)s.kovidgoyal.net]'%\
dict(a=__appname__, v=__version__)
if not mi.language:
mi.language = get_lang()
meta_info_to_oeb_metadata(mi, self.oeb.metadata, self.logger)
bookid = "urn:uuid:%s" % str(uuid.uuid4()) if mi.application_id is None \
else mi.application_id

10
src/calibre/ebooks/oeb/transforms/metadata.py
View File

@ -7,6 +7,7 @@ __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
import os
from datetime import datetime
def meta_info_to_oeb_metadata(mi, m, log):
if mi.title:
@ -56,6 +57,15 @@ def meta_info_to_oeb_metadata(mi, m, log):
m.clear('subject')
for t in mi.tags:
m.add('subject', t)
if mi.pubdate is not None:
m.clear('date')
m.add('date', mi.pubdate.isoformat())
if mi.timestamp is not None:
m.clear('timestamp')
m.add('timestamp', mi.timestamp.isoformat())
if not m.timestamp:
m.add('timestamp', datetime.utcnow().isoformat())
class MergeMetadata(object):

4
src/calibre/ebooks/oeb/transforms/trimmanifest.py
View File

@ -24,6 +24,7 @@ class ManifestTrimmer(object):
def __call__(self, oeb, context):
oeb.logger.info('Trimming unused files from manifest...')
self.opts = context
used = set()
for term in oeb.metadata:
for item in oeb.metadata[term]:
@ -63,5 +64,8 @@ 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)

2
src/calibre/ebooks/oeb/writer.py
View File

@ -35,7 +35,7 @@ class OEBWriter(object):
help=_('OPF version to generate. Default is %default.'))
oeb('adobe_page_map', ['--adobe-page-map'], default=False,
help=_('Generate an Adobe "page-map" file if pagination '
'information is avaliable.'))
'information is available.'))
return cfg
@classmethod

2
src/calibre/ebooks/pdb/input.py
View File

@ -23,7 +23,7 @@ class PDBInput(InputFormatPlugin):
Reader = get_reader(header.ident)
if Reader is None:
raise PDBError('No reader avaliable for format within container.\n Identity is %s. Book type is %s' % (header.ident, IDENTITY_TO_NAME.get(header.ident, _('Unknown'))))
raise PDBError('No reader available for format within container.\n Identity is %s. Book type is %s' % (header.ident, IDENTITY_TO_NAME.get(header.ident, _('Unknown'))))
log.debug('Detected ebook format as: %s with identity: %s' % (IDENTITY_TO_NAME[header.ident], header.ident))

2
src/calibre/ebooks/pdb/output.py
View File

@ -42,7 +42,7 @@ class PDBOutput(OutputFormatPlugin):
Writer = get_writer(opts.format)
if Writer is None:
raise PDBError('No writer avaliable for format %s.' % format)
raise PDBError('No writer available for format %s.' % format)
writer = Writer(opts, log)

4
src/calibre/ebooks/txt/processor.py
View File

@ -17,9 +17,9 @@ def txt_to_markdown(txt, title=''):
md = markdown.Markdown(
extensions=['footnotes', 'tables', 'toc'],
safe_mode=False,)
html = '<html><head><title>%s</title></head><body>%s</body></html>' % (title,
html = u'<html><head><title>%s</title></head><body>%s</body></html>' % (title,
md.convert(txt))
return html
def opf_writer(path, opf_name, manifest, spine, mi):

2
src/calibre/gui2/convert/metadata.py
View File

@ -57,7 +57,7 @@ class MetadataWidget(Widget, Ui_Form):
try:
self.series_index.setValue(mi.series_index)
except:
self.series_index.setValue(0)
self.series_index.setValue(1.0)
cover = self.db.cover(self.book_id, index_is_id=True)
if cover:

21
src/calibre/gui2/convert/mobi_output.ui
View File

@ -14,7 +14,7 @@
<string>Form</string>
</property>
<layout class="QGridLayout" name="gridLayout">
<item row="0" column="0">
<item row="1" column="0">
<widget class="QLabel" name="label">
<property name="text">
<string>&amp;Title for Table of Contents:</string>
@ -24,24 +24,24 @@
</property>
</widget>
</item>
<item row="0" column="1">
<item row="1" column="1">
<widget class="QLineEdit" name="opt_toc_title"/>
</item>
<item row="1" column="0" colspan="2">
<item row="2" column="0" colspan="2">
<widget class="QCheckBox" name="opt_rescale_images">
<property name="text">
<string>Rescale images for &amp;Palm devices</string>
</property>
</widget>
</item>
<item row="2" column="0" colspan="2">
<item row="3" column="0" colspan="2">
<widget class="QCheckBox" name="opt_prefer_author_sort">
<property name="text">
<string>Use author &amp;sort for author</string>
</property>
</widget>
</item>
<item row="5" column="0">
<item row="6" column="0">
<spacer name="verticalSpacer">
<property name="orientation">
<enum>Qt::Vertical</enum>
@ -54,20 +54,27 @@
</property>
</spacer>
</item>
<item row="3" column="0">
<item row="4" column="0">
<widget class="QCheckBox" name="opt_dont_compress">
<property name="text">
<string>Disable compression of the file contents</string>
</property>
</widget>
</item>
<item row="4" column="0">
<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">
<string>Do not add Table of Contents to book</string>
</property>
</widget>
</item>
</layout>
</widget>
<resources/>

2
src/calibre/gui2/device_drivers/configwidget.ui
View File

@ -17,7 +17,7 @@
<item row="0" column="0">
<widget class="QGroupBox" name="groupBox">
<property name="title">
<string>Select avaliable formats and their order for this device</string>
<string>Select available formats and their order for this device</string>
</property>
<layout class="QVBoxLayout" name="verticalLayout_7">
<item>

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

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 5.3 KiB

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

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 837 B

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

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 269 B

17
src/calibre/gui2/library.py
View File

@ -267,20 +267,7 @@ class BooksModel(QAbstractTableModel):
self.endInsertRows()
self.count_changed()
def clean_search_text(self, text):
if not text:
return text
tokens = text.split(' ')
for i, token in enumerate(tokens):
if token.strip().endswith(':') or token.strip() == '':
del tokens[i]
text = ' '.join(tokens)
if text.strip() == '':
text = None
return text
def search(self, text, refinement, reset=True):
text = self.clean_search_text(text)
self.db.search(text)
self.last_search = text
if reset:
@ -899,9 +886,9 @@ class DeviceBooksModel(BooksModel):
flags |= Qt.ItemIsEditable
return flags
def search(self, text, refinement, reset=True):
text = self.clean_search_text(text)
if not text:
if not text or not text.strip():
self.map = list(range(len(self.db)))
else:
matches = self.search_engine.parse(text)

2
src/calibre/gui2/viewer/main.py
View File

@ -313,6 +313,8 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
self.view.goto_bookmark(m)
else:
self.pending_bookmark = bm
if spine_index < 0 or spine_index >= len(self.iterator.spine):
spine_index = 0
self.load_path(self.iterator.spine[spine_index])
def toc_clicked(self, index):

706
src/calibre/translations/calibre.pot
View File

File diff suppressed because it is too large Load Diff

3
src/calibre/web/feeds/recipes/__init__.py
View File

@ -50,7 +50,8 @@ recipe_modules = ['recipe_' + r for r in (
'marca', 'kellog_faculty', 'kellog_insight',
'theeconomictimes_india', '7dias', 'buenosaireseconomico',
'diagonales', 'miradasalsur', 'newsweek_argentina', 'veintitres',
'gva_be', 'hln', 'tijd', 'degentenaar',
'gva_be', 'hln', 'tijd', 'degentenaar', 'inquirer_net', 'uncrate',
'fastcompany', 'accountancyage',
)]
import re, imp, inspect, time, os

58
src/calibre/web/feeds/recipes/recipe_accountancyage.py Normal file
View File

@ -0,0 +1,58 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.accountancyage.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class AccountancyAge(BasicNewsRecipe):
title = 'Accountancy Age'
__author__ = 'Darko Miletic'
description = 'business news'
publisher = 'accountancyage.com'
category = 'news, politics, finances'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
simultaneous_downloads = 1
encoding = 'utf-8'
lang = 'en'
language = _('English')
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'class':'bodycol'})]
remove_tags = [dict(name=['embed','object'])]
remove_tags_after = dict(name='div', attrs={'id':'permalink'})
remove_tags_before = dict(name='div', attrs={'class':'gap6'})
feeds = [(u'All News', u'http://feeds.accountancyage.com/rss/latest/accountancyage/all')]
def print_version(self, url):
rest, sep, miss = url.rpartition('/')
rr, ssep, artid = rest.rpartition('/')
return u'http://www.accountancyage.com/articles/print/' + artid
def get_article_url(self, article):
return article.get('guid', None)
def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang
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)
return self.adeify_images(soup)

54
src/calibre/web/feeds/recipes/recipe_fastcompany.py Normal file
View File

@ -0,0 +1,54 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.fastcompany.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class FastCompany(BasicNewsRecipe):
title = 'Fast Company'
__author__ = 'Darko Miletic'
description = 'Where ideas and people meet'
publisher = 'fastcompany.com'
category = 'news, technology, gadgets, games'
oldest_article = 15
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = True
simultaneous_downloads = 1
encoding = 'utf-8'
lang = 'en'
language = _('English')
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
remove_tags = [dict(name=['embed','object']), dict(name='div',attrs={'class':'feedflare'})]
feeds = [(u'All News', u'http://feeds.feedburner.com/fastcompany/headlines')]
def get_article_url(self, article):
return article.get('guid', None)
def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang
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('a'):
sp = item['href'].find('http://feedads.g.doubleclick.net/')
if sp != -1:
item.extract()
return self.adeify_images(soup)

61
src/calibre/web/feeds/recipes/recipe_inquirer_net.py Normal file
View File

@ -0,0 +1,61 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.inquirer.net
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class InquirerNet(BasicNewsRecipe):
title = 'Inquirer.net'
__author__ = 'Darko Miletic'
description = 'News from Philipines'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
publisher = 'inquirer.net'
category = 'news, politics, philipines'
lang = 'en'
language = _('English')
extra_css = ' .fontheadline{font-size: x-large} .fontsubheadline{font-size: large} .fontkick{font-size: medium}'
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
remove_tags = [dict(name=['object','link','script','iframe','form'])]
feeds = [
(u'Breaking news', u'http://services.inquirer.net/rss/breakingnews.xml' )
,(u'Top stories' , u'http://services.inquirer.net/rss/topstories.xml' )
,(u'Sports' , u'http://services.inquirer.net/rss/brk_breakingnews.xml' )
,(u'InfoTech' , u'http://services.inquirer.net/rss/infotech_tech.xml' )
,(u'InfoTech' , u'http://services.inquirer.net/rss/infotech_tech.xml' )
,(u'Business' , u'http://services.inquirer.net/rss/inq7money_breaking_news.xml' )
,(u'Editorial' , u'http://services.inquirer.net/rss/opinion_editorial.xml' )
,(u'Global Nation', u'http://services.inquirer.net/rss/globalnation_breakingnews.xml')
]
def preprocess_html(self, soup):
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
def print_version(self, url):
rest, sep, art = url.rpartition('/view/')
art_id, sp, rrest = art.partition('/')
return 'http://services.inquirer.net/print/print.php?article_id=' + art_id

194
src/calibre/web/feeds/recipes/recipe_time_magazine.py
View File

@ -1,95 +1,99 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
time.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Time(BasicNewsRecipe):
title = u'Time'
__author__ = 'Kovid Goyal'
description = 'Weekly magazine'
encoding = 'utf-8'
no_stylesheets = True
language = _('English')
remove_tags_before = dict(id="artHd")
remove_tags_after = {'class':"ltCol"}
remove_tags = [
{'class':['articleTools', 'enlarge', 'search']},
{'id':['quigoArticle', 'contentTools', 'articleSideBar', 'header', 'navTop']},
{'target':'_blank'},
]
recursions = 1
match_regexps = [r'/[0-9,]+-(2|3|4|5|6|7|8|9)(,\d+){0,1}.html']
def parse_index(self):
soup = self.index_to_soup('http://www.time.com/time/magazine')
img = soup.find('a', title="View Large Cover", href=True)
if img is not None:
cover_url = 'http://www.time.com'+img['href']
try:
nsoup = self.index_to_soup(cover_url)
img = nsoup.find('img', src=re.compile('archive/covers'))
if img is not None:
self.cover_url = img['src']
except:
self.log.exception('Failed to fetch cover')
feeds = []
parent = soup.find(id='tocGuts')
for seched in parent.findAll(attrs={'class':'toc_seched'}):
section = self.tag_to_string(seched).capitalize()
articles = list(self.find_articles(seched))
feeds.append((section, articles))
return feeds
def find_articles(self, seched):
for a in seched.findNextSiblings('a', href=True, attrs={'class':'toc_hed'}):
yield {
'title' : self.tag_to_string(a),
'url' : 'http://www.time.com'+a['href'],
'date' : '',
'description' : self.article_description(a)
}
def article_description(self, a):
ans = []
while True:
t = a.nextSibling
if t is None:
break
a = t
if getattr(t, 'name', False):
if t.get('class', '') == 'toc_parens' or t.name == 'br':
continue
if t.name in ('div', 'a'):
break
ans.append(self.tag_to_string(t))
else:
ans.append(unicode(t))
return u' '.join(ans).replace(u'\xa0', u'').strip()
def postprocess_html(self, soup, first_page):
div = soup.find(attrs={'class':'artPag'})
if div is not None:
div.extract()
if not first_page:
for cls in ('photoBkt', 'artHd'):
div = soup.find(attrs={'class':cls})
if div is not None:
div.extract()
div = soup.find(attrs={'class':'artTxt'})
if div is not None:
p = div.find('p')
if p is not None:
p.extract()
return soup
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid@kovidgoyal.net>'
'''
time.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Time(BasicNewsRecipe):
title = u'Time'
__author__ = 'Kovid Goyal and Sujata Raman'
description = 'Weekly magazine'
encoding = 'utf-8'
no_stylesheets = True
language = _('English')
extra_css = '''.headline {font-size: large;}
.fact { padding-top: 10pt }
h1 {font-family:Arial,Sans-serif}
.byline{font-family:Arial,Sans-serif; font-size:xx-small ;color:blue}
.timestamp{font-family:Arial,Sans-serif; font-size:x-small ;color:gray}'''
remove_tags_before = dict(id="artHd")
remove_tags_after = {'class':"ltCol"}
remove_tags = [
{'class':['articleTools', 'enlarge', 'search','socialtools','blogtools','moretools','page','nextUp','next','subnav','RSS','line2','first','ybuzz','articlePagination','chiclets','imgcont','createListLink','rlinks','tabsWrap','pagination']},
{'id':['quigoArticle', 'contentTools', 'articleSideBar', 'header', 'navTop','articleTools','feedmodule','feedmodule3','promos','footer','linksFooter','timeArchive','belt','relatedStories','packages','Features']},
{'target':'_blank'},
]
recursions = 1
match_regexps = [r'/[0-9,]+-(2|3|4|5|6|7|8|9)(,\d+){0,1}.html']
def parse_index(self):
soup = self.index_to_soup('http://www.time.com/time/magazine')
img = soup.find('a', title="View Large Cover", href=True)
if img is not None:
cover_url = 'http://www.time.com'+img['href']
try:
nsoup = self.index_to_soup(cover_url)
img = nsoup.find('img', src=re.compile('archive/covers'))
if img is not None:
self.cover_url = img['src']
except:
self.log.exception('Failed to fetch cover')
feeds = []
parent = soup.find(id='tocGuts')
for seched in parent.findAll(attrs={'class':'toc_seched'}):
section = self.tag_to_string(seched).capitalize()
articles = list(self.find_articles(seched))
feeds.append((section, articles))
return feeds
def find_articles(self, seched):
for a in seched.findNextSiblings('a', href=True, attrs={'class':'toc_hed'}):
yield {
'title' : self.tag_to_string(a),
'url' : 'http://www.time.com'+a['href'],
'date' : '',
'description' : self.article_description(a)
}
def article_description(self, a):
ans = []
while True:
t = a.nextSibling
if t is None:
break
a = t
if getattr(t, 'name', False):
if t.get('class', '') == 'toc_parens' or t.name == 'br':
continue
if t.name in ('div', 'a'):
break
ans.append(self.tag_to_string(t))
else:
ans.append(unicode(t))
return u' '.join(ans).replace(u'\xa0', u'').strip()
def postprocess_html(self, soup, first_page):
div = soup.find(attrs={'class':'artPag'})
if div is not None:
div.extract()
if not first_page:
for cls in ('photoBkt', 'artHd'):
div = soup.find(attrs={'class':cls})
if div is not None:
div.extract()
div = soup.find(attrs={'class':'artTxt'})
if div is not None:
p = div.find('p')
if p is not None:
p.extract()
return soup

47
src/calibre/web/feeds/recipes/recipe_uncrate.py Normal file
View File

@ -0,0 +1,47 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.uncrate.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
class Uncrate(BasicNewsRecipe):
title = 'Uncrate'
__author__ = 'Darko Miletic'
description = 'Uncrate is a web magazine for guys who love stuff. Our team digs up the best gadgets, clothes, cars, DVDs and more. New items are posted daily. Enjoy responsively.'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
publisher = 'Zombie corp.'
category = 'news, gadgets, clothes, cars, DVDs'
lang = 'en-US'
language = _('English')
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'class':'lefttext'})]
remove_tags_after = dict(name='div', attrs={'class':'serif'})
remove_tags = [dict(name=['object','link','script','iframe','form'])]
feeds = [(u'Articles', u'http://feeds.feedburner.com/uncrate')]
def preprocess_html(self, soup):
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 self.adeify_images(soup)