sync to trunk.

This commit is contained in:
John Schember 2009-12-30 06:15:26 -05:00
commit 18963065a5
17 changed files with 375 additions and 9 deletions

View File

@ -7,6 +7,9 @@ class Aftenposten(BasicNewsRecipe):
language = 'no'
oldest_article = 5
max_articles_per_feed = 100
recipe_disabled = ('The recipe to download Aftenposten has been '
'temporarily disabled at the publisher\'s request, while '
'they finalize their digital strategy.')
no_stylesheets = True
encoding = 'ISO-8859-1'

View File

@ -0,0 +1,46 @@
from calibre.web.feeds.news import BasicNewsRecipe
class ChowkRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'kwetal'
language = 'en_IN'
version = 1
title = u'Chowk'
publisher = u'chowk.com'
category = u'Opinion, South Asia'
description = u'Ideas & Identities of South Asia'
use_embedded_content = False
remove_empty_feeds = True
oldest_article = 30
max_articles_per_feed = 100
#no_stylesheets = True
remove_javascript = True
encoding = 'utf-8'
feeds = []
feeds.append(('Chowk Articles', 'http://www.chowk.com/rss'))
keep_only_tags = []
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'content'}))
conversion_options = {'comments': description, 'tags': category, 'language': 'en',
'publisher': publisher}
extra_css = '''
body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
a {text-decoration: none; color: blue;}
div.pgtitle {font-size: x-large; font-weight: bold;}
div.wname, div.date {font-size: x-small; color: #696969;}
div.wname {margin-top: 1em;}
div.date {margin-bottom: 1em;}
div.title {font-weight: bold;}
'''
def print_version(self, url):
main, sep, id = url.rpartition('/')
return main + '/print/' + id

View File

@ -0,0 +1,92 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class DawnRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'kwetal'
language = 'en_PK'
version = 1
title = u'Dawn'
publisher = u'Dawn Media Group'
category = u'News, Pakistan'
description = u'Leading English Newspaper of Pakistan covering national & international news'
use_embedded_content = False
remove_empty_feeds = True
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
encoding = 'utf-8'
# Feeds from http://www.dawn.com/wps/wcm/connect/dawn-content-library/dawn/services/rss
feeds = []
feeds.append((u'Latest News', u'http://feedproxy.google.com/Dawn-All-News'))
feeds.append((u'Pakistan News', u'http://feeds2.feedburner.com/dawn/news/pakistan'))
feeds.append((u'World News', u'http://feeds2.feedburner.com/dawn/news/world'))
feeds.append((u'Business News', u'http://feeds2.feedburner.com/dawn/news/business'))
feeds.append((u'Sport News', u'http://feeds2.feedburner.com/dawn/news/sport'))
feeds.append((u'Cricket News', u'http://feeds2.feedburner.com/dawn/news/cricket'))
feeds.append((u'Sci-tech News', u'http://feeds2.feedburner.com/dawn/news/technology'))
feeds.append((u'Entertainment News', u'http://feeds2.feedburner.com/dawn/news/entertainment'))
feeds.append((u'Columnists', u'http://feeds2.feedburner.com/dawn/news/columnists'))
#feeds.append((u'', u''))
conversion_options = {'comments': description, 'tags': category, 'language': 'en',
'publisher': publisher}
extra_css = '''
body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
center {font-size: xx-small; color: #666666;}
strong {font-size: small; font-weight: bold;}
span.news_headline {font-size: xx-large; font-weight: bold; margin: 0em; padding: 0em}
span.news_byline {font-size: x-small; color: #696969; margin-top: 1em;}
'''
def print_version(self, url):
return url + '?pagedesign=Dawn_PrintlyFriendlyPage'
def preprocess_html(self, soup):
newBody = Tag(soup, 'body')
for cl in ['page_title', 'news_headline', 'news_byline']:
tag = soup.find('span', attrs = {'class': cl})
if tag:
# They like their <br> tags; I don't: does not work well on small screens.
if tag['class'] == 'news_byline':
for br in tag.findAll('br'):
br.extract()
newBody.append(tag)
table = soup.find('table', attrs = {'id': 'body table'})
if table:
for td in table.findAll('td', attrs = {'class': 'news_story'}):
for tag in td.findAll(True):
if tag.has_key('id') and tag['id'] == 'banner-img_slide':
tag.extract()
elif tag.has_key('style'):
del tag['style']
elif tag.name == 'script':
tag.extract()
# They like their <br> tags; I don't: does not work well on small screens.
center = td.find('center')
if center:
for br in center.findNextSiblings('br'):
br.extract()
for br in center.findPreviousSiblings('br'):
br.extract()
for attr in ['align', 'valign']:
if td.has_key(attr):
del td[attr]
td.name = 'div'
newBody.append(td)
soup.body.replaceWith(newBody)
return soup

View File

@ -0,0 +1,26 @@
from calibre.web.feeds.news import BasicNewsRecipe
class Independent(BasicNewsRecipe):
title = u'The Independent'
oldest_article = 1
language = 'en_GB'
__author__ = 'Jimmy Patrick'
max_articles_per_feed = 100
feeds = [(u'UK', u'http://www.independent.co.uk/news/uk/rss'),
(u'World', u'http://www.independent.co.uk/news/world/rss'),
(u'Sport', u'http://www.independent.co.uk/sport/rss'),
(u'Arts & Entertainment', u'http://www.independent.co.uk/arts-entertainment/rss'),
(u'Life & Style',u'http://www.independent.co.uk/life-style/fashion/news/rss'),
(u'Business',u'http://www.independent.co.uk/news/business/rss'),
(u'Science',u'http://www.independent.co.uk/news/science/rss'),
(u'Media',u'http://www.independent.co.uk/news/media/rss')
]
keep_only_tags = [dict(id=['article'])]
remove_tags = [dict(name='div', attrs={'class':'share-links'}),
dict(name='ul', attrs={'class':'article-tools'}),
dict(name='div', attrs={'class':'related-articles'})
]
extra_css = "body{color:black;}"

View File

@ -0,0 +1,74 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
theatlantic.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class NewYorkMagazine(BasicNewsRecipe):
title = 'New York Magazine'
__author__ = 'Kovid Goyal'
description = 'Food, culture, arts and entertainment in New York'
language = 'en'
no_stylesheets = True
remove_javascript = True
encoding = 'iso-8859-1'
recursions = 1
match_regexps = [r'http://nymag.com/.+/index[0-9]{1,2}.html$']
keep_only_tags = [dict(id='main')]
remove_tags = [
dict(attrs={'class':['start-discussion']}),
dict(id=['minibrowserbox', 'article-related', 'article-tools'])
]
PREFIX = 'http://nymag.com'
def nymag_get_index(self):
return self.index_to_soup('http://nymag.com/includes/tableofcontents.htm')
def parse_index(self):
soup = self.nymag_get_index()
self.cover_url = soup.find(attrs={'class':'cover'}).find('img',
src=True).get('src')
feeds = []
current_section = 'Cover Story'
current_articles = []
for h in soup.findAll(['h4', 'h5']):
if h.name == 'h4':
if current_section and current_articles:
feeds.append((current_section, current_articles))
current_section = self.tag_to_string(h)
self.log('\tFound section:', current_section)
current_articles = []
elif h.name == 'h5':
title = self.tag_to_string(h)
a = h.find('a', href=True)
if a is not None:
url = a.get('href')
if url.startswith('/'):
url = self.PREFIX + url
if title and url:
self.log('\t\tFound article:', title)
self.log('\t\t\t', url)
desc = ''
p = h.findNextSibling('p')
if p is not None:
desc = self.tag_to_string(p)
self.log('\t\t\t', desc)
current_articles.append({'title':title, 'url':url,
'date':'', 'description':desc})
return feeds
def postprocess_html(self, soup, first):
for x in soup.findAll(attrs={'class':'page-navigation'}):
x.extract()
if not first:
for x in soup.findAll(attrs={'class':'header-spacing'}):
x.extract()
return soup

View File

@ -17,7 +17,7 @@ class NYTimes(BasicNewsRecipe):
language = 'en'
description = 'Daily news from the New York Times (subscription version)'
timefmt = ''
timefmt = ' [%a, %b %d, %Y]'
needs_subscription = True
remove_tags_before = dict(id='article')
remove_tags_after = dict(id='article')
@ -44,6 +44,9 @@ class NYTimes(BasicNewsRecipe):
#open('/t/log.html', 'wb').write(raw)
return br
def short_title(self):
return 'NY Times'
def parse_index(self):
soup = self.index_to_soup('http://www.nytimes.com/pages/todayspaper/index.html')

View File

@ -0,0 +1,78 @@
from calibre.web.feeds.news import BasicNewsRecipe
class TheNewsRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'kwetal'
language = 'en_PK'
version = 1
title = u'The News'
publisher = u'Jang Group'
category = u'News, Pakistan'
description = u'English Newspaper from Pakistan'
use_embedded_content = False
remove_empty_feeds = True
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
encoding = 'iso-8859-1'
remove_tags = []
remove_tags.append(dict(name = 'img', attrs = {'src': 'images/thenews.gif'}))
remove_tags.append(dict(name = 'img', attrs = {'src': 'images/shim.gif'}))
# Feeds from http://thenews.com.pk/rss.asp
feeds = []
feeds.append((u'Latest Stories', u'http://www.thenews.com.pk/rss/thenews_updates.xml'))
feeds.append((u'Top Stories', u'http://www.thenews.com.pk/rss/thenews_topstories.xml'))
feeds.append((u'World News', u'http://www.thenews.com.pk/rss/thenews_world.xml'))
feeds.append((u'National News', u'http://www.thenews.com.pk/rss/thenews_national.xml'))
feeds.append((u'Business News', u'http://www.thenews.com.pk/rss/thenews_business.xml'))
feeds.append((u'Karachi News', u'http://www.thenews.com.pk/rss/thenews_karachi.xml'))
feeds.append((u'Lahore News', u'http://www.thenews.com.pk/rss/thenews_lahore.xml'))
feeds.append((u'Islamabad News', u'http://www.thenews.com.pk/rss/thenews_islamabad.xml'))
feeds.append((u'Peshawar News', u'http://www.thenews.com.pk/rss/thenews_peshawar.xml'))
feeds.append((u'Editorial', u'http://www.thenews.com.pk/rss/thenews_editorial.xml'))
feeds.append((u'Opinion', u'http://www.thenews.com.pk/rss/thenews_opinion.xml'))
feeds.append((u'Sports News', u'http://www.thenews.com.pk/rss/thenews_sports.xml'))
feeds.append((u'Newspost', u'http://www.thenews.com.pk/rss/thenews_newspost.xml'))
conversion_options = {'comments': description, 'tags': category, 'language': 'en',
'publisher': publisher, 'linearize_tables': True}
extra_css = '''
body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
.heading_txt {font-size: x-large; font-weight: bold; text-align: left;}
.small_txt {text-align: left;}
.dateline {font-size: x-small; color: #696969; margin-top: 1em; margin-bottom: 1em}
'''
def print_version(self, url):
ignore, sep, main = url.rpartition('/')
if main.startswith('updates.asp'):
return url.replace('updates.asp', 'print.asp')
elif main.startswith('top_story_detail.asp'):
return url.replace('top_story_detail.asp', 'print3.asp')
elif main.startswith('daily_detail.asp'):
return url.replace('daily_detail.asp', 'print1.asp')
else:
return None
def preprocess_html(self, soup):
for tr in soup.findAll('tr', attrs = {'bgcolor': True}):
del tr['bgcolor']
td = soup.find('td', attrs = {'class': 'small_txt', 'height': '20'})
if td:
del td['height']
td['class'] = 'dateline'
return soup

View File

@ -245,7 +245,7 @@ class LinuxFreeze(Command):
export MAGICK_CONFIGURE_PATH=$base/ImageMagick/config
export MAGICK_CODER_MODULE_PATH=$base/ImageMagick/modules-Q16/coders
export MAGICK_CODER_FILTER_PATH=$base/ImageMagick/modules-Q16/filter
export QT_PLUGIN_PATH=$base/qtplugins
export QT_PLUGIN_PATH=$base/qtplugins:$QT_PLUGIN_PATH
$loader "$@"
''')%exe)
os.chmod(path, 0755)

View File

@ -309,7 +309,7 @@ class Py2App(object):
@flush
def add_qt_frameworks(self):
info('\nAdding Qt Framework')
for f in ('QtCore', 'QtGui', 'QtXml', 'QtNetwork', 'QtSvg', 'QtWebkit',
for f in ('QtCore', 'QtGui', 'QtXml', 'QtNetwork', 'QtSvg', 'QtWebKit',
'QtXmlPatterns', 'phonon'):
self.add_qt_framework(f)
for d in glob.glob(join(SW, 'qt', 'plugins', '*')):

View File

@ -462,6 +462,7 @@ plugins += [
ILIAD,
IREXDR1000,
JETBOOK,
SHINEBOOK,
KINDLE,
KINDLE2,
KINDLE_DX,
@ -480,7 +481,6 @@ plugins += [
POCKETBOOK360,
GER2,
ITALICA,
SHINEBOOK,
ECLICTO,
DBOOK,
BOOX,

View File

@ -16,6 +16,7 @@ Windows PNP strings:
'''
from calibre.devices.usbms.driver import USBMS
from calibre.constants import iswindows
class EB600(USBMS):
@ -81,6 +82,19 @@ class SHINEBOOK(EB600):
VENDOR_NAME = 'LONGSHIN'
WINDOWS_MAIN_MEM = 'ESHINEBOOK'
MAIN_MEMORY_VOLUME_LABEL = 'ShineBook Main Memory'
STORAGE_CARD_VOLUME_LABEL = 'ShineBook Storage Card'
@classmethod
def can_handle(cls, dev, debug=False):
try:
if not iswindows:
return dev[4] == 'ShineBook'
except:
return True
class POCKETBOOK360(EB600):

View File

@ -1736,6 +1736,16 @@ class Main(MainWindow, Ui_MainWindow, DeviceGUI):
d.show()
self._modeless_dialogs.append(d)
return
if 'calibre.web.feeds.input.RecipeDisabled' in job.details:
msg = job.details
msg = msg[msg.find('calibre.web.feeds.input.RecipeDisabled:'):]
msg = msg.partition(':')[-1]
d = error_dialog(self, _('Recipe Disabled'),
'<p>%s</p>'%msg)
d.setModal(False)
d.show()
self._modeless_dialogs.append(d)
return
except:
pass
if job.killed:

View File

@ -81,7 +81,7 @@ Device Integration
What devices does |app| support?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
At the moment |app| has full support for the SONY PRS 300/500/505/600/700/900, Barnes & Noble Nook, Cybook Gen 3/Opus, Amazon Kindle 1/2/DX, Netronix EB600, Ectaco Jetbook, BeBook/BeBook Mini, Irex Illiad/DR1000, Foxit eSlick, PocketBook 360, Italica, eClicto, Iriver Story, Airis dBook, various Android phones and the iPhone. In addition, using the :guilabel:`Save to disk` function you can use it with any ebook reader that exports itself as a USB disk.
At the moment |app| has full support for the SONY PRS 300/500/505/600/700/900, Barnes & Noble Nook, Cybook Gen 3/Opus, Amazon Kindle 1/2/DX, Longshine ShineBook, Ectaco Jetbook, BeBook/BeBook Mini, Irex Illiad/DR1000, Foxit eSlick, PocketBook 360, Italica, eClicto, Iriver Story, Airis dBook, various Android phones and the iPhone. In addition, using the :guilabel:`Save to disk` function you can use it with any ebook reader that exports itself as a USB disk.
How can I help get my device supported in |app|?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@ -301,7 +301,7 @@ Your antivirus program is wrong. |app| is a completely open source product. You
How do I use purchased EPUB books with |app|?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Most purchased EPUB books have `DRM <http://wiki.mobileread.com/wiki/DRM>`_. This prevents |app| from opening them. You can still use |app| to store and transfer them to your SONY Reader. First, you must authorize your reader on a windows machine with Adobe Digital Editions. Once this is done, EPUB books transferred with |app| will work fine on your reader. Sometimes, the EPUB file itself is corrupted, in which case you should notify the e-book vendor.
Most purchased EPUB books have `DRM <http://wiki.mobileread.com/wiki/DRM>`_. This prevents |app| from opening them. You can still use |app| to store and transfer them to your SONY Reader. First, you must authorize your reader on a windows machine with Adobe Digital Editions. Once this is done, EPUB books transferred with |app| will work fine on your reader. When you purchase an epub book from a website, you will get an ".acsm" file. This file should be opened with Adobe Digital Editions, which will then download the actual ".epub" e-book. The e-book file will be stored in the folder "My Digital Editions", from where you can add it to |app|.
I want some feature added to |app|. What can I do?

View File

@ -73,6 +73,12 @@ def get_func(name):
return func, notification
def main():
from calibre.constants import isosx
if isosx and 'CALIBRE_WORKER_ADDRESS' not in os.environ:
# On some OS X computers launchd apparently tries to
# launch the last run process from the bundle
from calibre.gui2.main import main as gui_main
return gui_main(['calibre'])
address = cPickle.loads(unhexlify(os.environ['CALIBRE_WORKER_ADDRESS']))
key = unhexlify(os.environ['CALIBRE_WORKER_KEY'])
resultf = unhexlify(os.environ['CALIBRE_WORKER_RESULT'])

View File

@ -101,6 +101,7 @@ _extra_lang_codes = {
'en_IN' : _('English (IND)'),
'en_TH' : _('English (TH)'),
'en_CY' : _('English (CY)'),
'en_PK' : _('English (PK)'),
'de_AT' : _('German (AT)'),
'nl' : _('Dutch (NL)'),
'nl_BE' : _('Dutch (BE)'),

View File

@ -11,6 +11,9 @@ import os
from calibre.customize.conversion import InputFormatPlugin, OptionRecommendation
from calibre.constants import numeric_version
class RecipeDisabled(Exception):
pass
class RecipeInput(InputFormatPlugin):
name = 'Recipe Input'
@ -40,7 +43,7 @@ class RecipeInput(InputFormatPlugin):
'content.')),
OptionRecommendation(name='dont_download_recipe',
recommended_value=False,
help=_('Download latest version of builtin recipes')),
help=_('Do not download latest version of builtin recipes from the calibre server')),
OptionRecommendation(name='lrf', recommended_value=False,
help='Optimize fetching for subsequent conversion to LRF.'),
])
@ -83,6 +86,9 @@ class RecipeInput(InputFormatPlugin):
recipe_or_file)
ro = recipe(opts, log, self.report_progress)
disabled = getattr(ro, 'recipe_disabled', None)
if disabled is not None:
raise RecipeDisabled(disabled)
ro.download()
self.recipe_object = ro
for key, val in recipe.conversion_options.items():

View File

@ -270,11 +270,18 @@ class BasicNewsRecipe(Recipe):
.navbar {
font-family:monospace;
}
'''
'''
#: Set to a non empty string to disable this recipe
#: The string will be used as the disabled message
recipe_disabled = None
# See the built-in profiles for examples of these settings.
def short_title(self):
return self.title
def get_cover_url(self):
'''
Return a :term:`URL` to the cover image for this issue or `None`.
@ -886,7 +893,7 @@ class BasicNewsRecipe(Recipe):
def create_opf(self, feeds, dir=None):
if dir is None:
dir = self.output_dir
mi = MetaInformation(self.title + strftime(self.timefmt), [__appname__])
mi = MetaInformation(self.short_title() + strftime(self.timefmt), [__appname__])
mi.publisher = __appname__
mi.author_sort = __appname__
mi.publication_type = 'periodical:'+self.publication_type