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

New recipe for De Volksrant by acidzebra, updated recipe for The Chicago Tribune. Add the the CyBook Opus to the welcome wizard. Fix #3146 (More formats for Bebook/lBook etc)

Browse Source
This commit is contained in:
Kovid Goyal 2009-08-13 11:16:27 -06:00
parent 1f349f330e
commit 30735c5885
7 changed files with 83 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/calibre/customize/profiles.py
View File

@ -270,7 +270,7 @@ class CybookG3Output(OutputProfile):
fbase = 16
fsizes = [12, 12, 14, 16, 18, 20, 22, 24]
class CybookOpusOutput(OutputProfile):
class CybookOpusOutput(SonyReaderOutput):
author = 'John Schember'
name = 'Cybook Opus'
@ -278,7 +278,6 @@ class CybookOpusOutput(OutputProfile):
description = _('This profile is intended for the Cybook Opus.')
# Screen size is a best guess
screen_size = (600, 800)
dpi = 200
fbase = 16
fsizes = [12, 12, 14, 16, 18, 20, 22, 24]

2
src/calibre/devices/bebook/driver.py
View File

@ -20,7 +20,7 @@ class BEBOOK(USBMS):
supported_platforms = ['windows', 'osx', 'linux']
# Ordered list of supported formats
FORMATS = ['mobi', 'epub', 'pdf', 'rtf', 'txt']
FORMATS = ['mobi', 'epub', 'fb2', 'lit', 'prc', 'pdf', 'rtf', 'txt']
VENDOR_ID = [0x0525]
PRODUCT_ID = [0x8803, 0x6803]

2
src/calibre/gui2/__init__.py
View File

@ -181,7 +181,7 @@ def question_dialog(parent, title, msg, det_msg=''):
return d.exec_() == QMessageBox.Yes
def info_dialog(parent, title, msg, det_msg='', show=False):
d = MessageBox(QMessageBox.Information, title, msg, QMessageBox.NoButton,
d = MessageBox(QMessageBox.Information, title, msg, QMessageBox.Ok,
parent, det_msg)
d.setIconPixmap(QPixmap(':/images/dialog_information.svg'))
if show:

1
src/calibre/gui2/wizard/__init__.py
View File

@ -104,6 +104,7 @@ class CybookOpus(CybookG3):
name = 'Cybook Opus'
output_format = 'EPUB'
output_profile = 'cybook_opus'
id = 'cybook_opus'
class BeBook(Device):

1
src/calibre/web/feeds/recipes/__init__.py
View File

@ -53,6 +53,7 @@ recipe_modules = ['recipe_' + r for r in (
'gva_be', 'hln', 'tijd', 'degentenaar', 'inquirer_net', 'uncrate',
'fastcompany', 'accountancyage', 'laprensa_hn', 'latribuna',
'eltiempo_hn', 'slate', 'tnxm', 'bbcvietnamese', 'vnexpress',
'volksrant', 'theeconomictimes_india',
)]

76
src/calibre/web/feeds/recipes/recipe_chicago_tribune.py
View File

@ -12,14 +12,35 @@ from threading import RLock
class ChicagoTribune(BasicNewsRecipe):
title = 'Chicago Tribune'
__author__ = 'Kovid Goyal'
__author__ = 'Kovid Goyal and Sujata Raman'
description = 'Politics, local and business news from Chicago'
language = _('English')
use_embedded_content = False
articles_are_obfuscated = True
remove_tags_before = dict(name='h1')
obfuctation_lock = RLock()
no_stylesheets = True
remove_javascript = True
keep_only_tags = [dict(name='div', attrs={'class':["story","entry-asset asset hentry"]}),
dict(name='div', attrs={'id':["pagebody","story","maincontentcontainer"]}),
]
remove_tags_after = [ {'class':['photo_article',]} ]
remove_tags = [{'id':["moduleArticleTools","content-bottom","rail","articleRelates module","toolSet","relatedrailcontent","div-wrapper","beta","atp-comments","footer"]},
{'class':["clearfix","relatedTitle","articleRelates module","asset-footer","tools","comments","featurePromo","featurePromo fp-topjobs brownBackground","clearfix fullSpan brownBackground","curvedContent"]},
dict(name='font',attrs={'id':["cr-other-headlines"]})]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
.byline {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
.date {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
.copyright {font-family:Arial,Helvetica,sans-serif;font-size:xx-small;text-align:center}
.story{font-family:Arial,Helvetica,sans-serif;font-size:small;}
.entry-asset asset hentry{font-family:Arial,Helvetica,sans-serif;font-size:small;}
.pagebody{font-family:Arial,Helvetica,sans-serif;font-size:small;}
.maincontentcontainer{font-family:Arial,Helvetica,sans-serif;font-size:small;}
.story-body{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
feeds = [
('Latest news', 'http://feeds.chicagotribune.com/chicagotribune/news/'),
('Local news', 'http://feeds.chicagotribune.com/chicagotribune/news/local/'),
@ -28,14 +49,14 @@ class ChicagoTribune(BasicNewsRecipe):
('Most E-mailed stories', 'http://feeds.chicagotribune.com/chicagotribune/email/'),
('Opinion', 'http://feeds.chicagotribune.com/chicagotribune/opinion/'),
('Off Topic', 'http://feeds.chicagotribune.com/chicagotribune/offtopic/'),
('Politics', 'http://feeds.chicagotribune.com/chicagotribune/politics/'),
('Special Reports', 'http://feeds.chicagotribune.com/chicagotribune/special/'),
('Religion News', 'http://feeds.chicagotribune.com/chicagotribune/religion/'),
#('Politics', 'http://feeds.chicagotribune.com/chicagotribune/politics/'),
#('Special Reports', 'http://feeds.chicagotribune.com/chicagotribune/special/'),
#('Religion News', 'http://feeds.chicagotribune.com/chicagotribune/religion/'),
('Business news', 'http://feeds.chicagotribune.com/chicagotribune/business/'),
('Jobs and Careers', 'http://feeds.chicagotribune.com/chicagotribune/career/'),
('Local scene', 'http://feeds.chicagotribune.com/chicagohomes/localscene/'),
('Phil Rosenthal', 'http://feeds.chicagotribune.com/chicagotribune/rosenthal/'),
('Tech Buzz', 'http://feeds.chicagotribune.com/chicagotribune/techbuzz/'),
#('Tech Buzz', 'http://feeds.chicagotribune.com/chicagotribune/techbuzz/'),
('Your Money', 'http://feeds.chicagotribune.com/chicagotribune/yourmoney/'),
('Jon Hilkevitch - Getting around', 'http://feeds.chicagotribune.com/chicagotribune/gettingaround/'),
('Jon Yates - What\'s your problem?', 'http://feeds.chicagotribune.com/chicagotribune/problem/'),
@ -44,39 +65,30 @@ class ChicagoTribune(BasicNewsRecipe):
('Sports', 'http://feeds.chicagotribune.com/chicagotribune/sports/'),
('Arts and Architecture', 'http://feeds.chicagotribune.com/chicagotribune/arts/'),
('Books', 'http://feeds.chicagotribune.com/chicagotribune/books/'),
('Magazine', 'http://feeds.chicagotribune.com/chicagotribune/magazine/'),
#('Magazine', 'http://feeds.chicagotribune.com/chicagotribune/magazine/'),
('Movies', 'http://feeds.chicagotribune.com/chicagotribune/movies/'),
('Music', 'http://feeds.chicagotribune.com/chicagotribune/movies/'),
('Music', 'http://feeds.chicagotribune.com/chicagotribune/music/'),
('TV', 'http://feeds.chicagotribune.com/chicagotribune/tv/'),
('Hypertext', 'http://feeds.chicagotribune.com/chicagotribune/hypertext/'),
('iPhone Blog', 'http://feeds.feedburner.com/redeye/iphoneblog'),
('Julie\'s Health Club', 'http://feeds.chicagotribune.com/chicagotribune_julieshealthclub/'),
]
temp_files = []
def get_article_url(self, article):
print article.get('feedburner_origlink', article.get('guid', article.get('link')))
return article.get('feedburner_origlink', article.get('guid', article.get('link')))
def get_obfuscated_article(self, url):
with self.obfuctation_lock:
soup = self.index_to_soup(url)
img = soup.find('img', alt='Print')
if img is not None:
a = img.parent.find('a', href=True)
purl = urlparse(url)
xurl = urlunparse(purl[:2] + (a['href'], '', '', ''))
soup = self.index_to_soup(xurl)
for img in soup.findAll('img', src=True):
if img['src'].startswith('/'):
img['src'] = urlunparse(purl[:2]+(img['src'], '', '', ''))
html = unicode(soup)
else:
h1 = soup.find(id='page-title')
body = soup.find(attrs={'class':re.compile('asset-content')})
html = u'<html><head/><body>%s</body></html>'%(unicode(h1)+unicode(body))
self.temp_files.append(PersistentTemporaryFile('_chicago_tribune.xhtml'))
self.temp_files[-1].write(html.encode('utf-8'))
self.temp_files[-1].close()
return self.temp_files[-1].name
def postprocess_html(self, soup, first_fetch):
for t in soup.findAll(['table', 'tr', 'td']):
t.name = 'div'
for tag in soup.findAll('form', dict(attrs={'name':["comments_form"]})):
tag.extract()
for tag in soup.findAll('font', dict(attrs={'id':["cr-other-headlines"]})):
tag.extract()
return soup

34
src/calibre/web/feeds/recipes/recipe_volksrant.py Normal file
View File

@ -0,0 +1,34 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import with_statement
__license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1249039563(BasicNewsRecipe):
title = u'De Volkskrant'
__author__ = 'acidzebra'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
language = _('Dutch')
keep_only_tags = [dict(name='div', attrs={'id':'leftColumnArticle'}) ]
remove_tags = [
dict(name='div',attrs={'class':'article_tools'}),
dict(name='div',attrs={'id':'article_tools'}),
dict(name='div',attrs={'class':'articletools'}),
dict(name='div',attrs={'id':'articletools'}),
dict(name='div',attrs={'id':'myOverlay'}),
dict(name='div',attrs={'id':'trackback'}),
dict(name='div',attrs={'id':'googleBanner'}),
dict(name='div',attrs={'id':'article_headlines'}),
]
extra_css = '''
body{font-family:Arial,Helvetica,sans-serif; font-size:small;}
h1{font-size:large;}
'''
feeds = [(u'Laatste Nieuws', u'http://volkskrant.nl/rss/laatstenieuws.rss'), (u'Binnenlands nieuws', u'http://volkskrant.nl/rss/nederland.rss'), (u'Buitenlands nieuws', u'http://volkskrant.nl/rss/internationaal.rss'), (u'Economisch nieuws', u'http://volkskrant.nl/rss/economie.rss'), (u'Sportnieuws', u'http://volkskrant.nl/rss/sport.rss'), (u'Kunstnieuws', u'http://volkskrant.nl/rss/kunst.rss'), (u'Wetenschapsnieuws', u'http://feeds.feedburner.com/DeVolkskrantWetenschap'), (u'Technologienieuws', u'http://feeds.feedburner.com/vkmedia')]