mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Merge
This commit is contained in:
Sengian
commit
bbdb113a2c
@ -4,6 +4,7 @@ src/calibre/plugins
|
||||
resources/images.qrc
|
||||
src/calibre/manual/.build/
|
||||
src/calibre/manual/cli/
|
||||
src/calibre/manual/template_ref.rst
|
||||
build
|
||||
dist
|
||||
docs
|
||||
@ -31,3 +32,4 @@ nbproject/
|
||||
.pydevproject
|
||||
.settings/
|
||||
*.DS_Store
|
||||
calibre_plugins/
|
||||
|
||||
@ -478,7 +478,7 @@
|
||||
type: major
|
||||
description : >
|
||||
"You can now save your frequently used searches and access them with a single click. For details
|
||||
see http://calibre-ebook.com/user_manual/gui.html#search-sort"
|
||||
see http://manual.calibre-ebook.com/gui.html#search-sort"
|
||||
|
||||
- title: "Add searching by date/published date"
|
||||
tickets: [5244]
|
||||
|
||||
202
Changelog.yaml
202
Changelog.yaml
@ -19,6 +19,202 @@
|
||||
# new recipes:
|
||||
# - title:
|
||||
|
||||
- version: 0.8.4
|
||||
date: 2011-06-03
|
||||
|
||||
new features:
|
||||
- title: "New and much simpler interface for specifying column coloring via Preferences->Look & Feel->Column Coloring"
|
||||
|
||||
- title: "Driver for Trekstor eBook Player 5M, Samsung Galaxy SII I9100, Motorola Defy and miBuk GAMMA 6.2"
|
||||
tickets: [792091, 791216]
|
||||
|
||||
- title: "Get Books: Add EpubBud, WH Smits and E-book Shoppe stores"
|
||||
|
||||
- title: "When deleting 'all formats except ...', do not delete if it leaves a book with no formats"
|
||||
|
||||
- title: "Change default toolbar to make it a little more new user friendly. The icons have been re-arranged and now the text is always visiblke by default. You can change that in Preferences->Look & Feeel and Preferences->Toolbar"
|
||||
|
||||
- title: "Windows installer: Remember and use previous settings for installing desktop icons, adding to path, etc. This makes the installer a little slower, complaints should go to Microsoft."
|
||||
|
||||
- title: "Template language: Add str_in_list and on_device formatter functions. Make debugging templates a little easier"
|
||||
|
||||
- title: "Allow the user to specify formatting for number type custom columns"
|
||||
|
||||
bug fixes:
|
||||
- title: "Fix typo in NOOK TSR driver that prevented it from working on windows"
|
||||
|
||||
- title: "Fix quotes in identifiers causing Tag Browser to be blank."
|
||||
tickets: [791044]
|
||||
|
||||
- title: "Speedup auto complete when there are lots of items (>2500) the downside being that non ASCII characters are not sorted correctly. The threshold can be controlled via Preferences->Tweaks"
|
||||
tickets: [792191]
|
||||
|
||||
- title: "RTF Output: Fix handling of curly brackets"
|
||||
tickets: [791805]
|
||||
|
||||
- title: "Fix searching in Get Books not working with non ASCII characters"
|
||||
tickets: [791788]
|
||||
|
||||
- title: "Fix excessive memory consumption when moving very large files during a metadata change"
|
||||
tickets: [791806]
|
||||
|
||||
- title: "Fix series index being overwritten even when series is turned off in bulk metadata download"
|
||||
tickets: [789990]
|
||||
|
||||
- title: "Fix regression in templates where id and other non standard fields no longer worked."
|
||||
|
||||
- title: "EPUB Output: Fix crash caused by ids with non-ascii characters in them"
|
||||
|
||||
- title: "Try to preserve the timestamps of files in a ZIP container"
|
||||
|
||||
- title: "After adding books always select the most recently added book."
|
||||
tickets: [789343]
|
||||
|
||||
improved recipes:
|
||||
- bild.de
|
||||
- CNN
|
||||
- BBC News (fast)
|
||||
- Dilema Veche
|
||||
|
||||
new recipes:
|
||||
- title: Metro UK
|
||||
author: Dave Asbury
|
||||
|
||||
- title: Alt om Herning and Version2.dk
|
||||
author: Rasmus Lauritsen
|
||||
|
||||
- title: Observatorul cultural
|
||||
author: song2
|
||||
|
||||
|
||||
- version: 0.8.3
|
||||
date: 2011-05-27
|
||||
|
||||
new features:
|
||||
- title: "Allow the coloring of columns in the book list."
|
||||
description: "You can either create a custom column with a fixed set of values and assign a color to each value, or you can use the calibre template language to color any column in arbitrarily powerful ways. For example, you can have the title appear in red if the book has a particular tag."
|
||||
type: major
|
||||
|
||||
- title: "Support for the Nook Simple Reader"
|
||||
|
||||
- title: "Get Books, new stores: Virtualo, lulu.net"
|
||||
|
||||
- title: "A store chooser dialog for Get Books (click the little preferences icon at the bottom of the Get Books screen)."
|
||||
|
||||
- title: "Add a merge_lists, and, or, not template functions to the calibre template language"
|
||||
|
||||
- title: "EPUB Output: Change any white-space:pre declarations in the CSS to pre-wrap to accomodate readers that cannot scroll horizontally."
|
||||
tickets: [786722]
|
||||
|
||||
- title: "Windows installer: Remember and use previous installation folder when upgrading. Note that this will work for future upgrades, after this one."
|
||||
|
||||
bug fixes:
|
||||
- title: "MOBI Output: Fix hidden tags with id attributes also hiding their trailing text"
|
||||
tickets: [788570]
|
||||
|
||||
- title: "Fix switching from one news source to another via a search not saving changes to the scheduling of the first source"
|
||||
tickets: [774849]
|
||||
|
||||
- title: "Dont allow user to use non email usernames when setting up Hotmail or Gmail accounts"
|
||||
|
||||
- title: "Amazon metadata download: Use separate identifiers for country specific downloads so that the links to Amazon in the Book details panel work when downloading metadata from country specific amazon websites."
|
||||
tickets: [786146]
|
||||
|
||||
- title: "Nicer error message when user attempts to set title/author via Edit metadata dialog and one of the files is open in another program."
|
||||
|
||||
- title: "Fix {id} not working in send to device templates"
|
||||
|
||||
- title: "Windows: If creating a bytestring temp dir fails, create a unicode one and hope the rest of calibre can handle it"
|
||||
|
||||
- title: "Get Books: Fix some results from Amazon missing."
|
||||
tickets: [785962]
|
||||
|
||||
improved recipes:
|
||||
- Kathermini
|
||||
- Faz.net
|
||||
- The Washington Post
|
||||
- El Mundo
|
||||
- Marca
|
||||
- The Nation
|
||||
|
||||
new recipes:
|
||||
- title: Various German news sources
|
||||
author: schuster
|
||||
|
||||
- title: "George R. R. Martin's Blog"
|
||||
author: Darko Miletic
|
||||
|
||||
- title: "Focus (DE) and National Geographic"
|
||||
auhtor: Anonymous
|
||||
|
||||
|
||||
|
||||
- version: 0.8.2
|
||||
date: 2011-05-20
|
||||
|
||||
new features:
|
||||
- title: "Various new ebook sources added to Get Books: Google Books, O'Reilly, archive.org, some Polish ebooks stores, etc."
|
||||
|
||||
- title: "Amazon metadata download: Allow user to configure Amazon plugin to use any of the US, UK, German, French and Italian Amazon websites"
|
||||
|
||||
- title: "When deleting large numbers of books, give the user the option to skip the Recycle Bin, since sending lots of files to the recycle bin can be very slow."
|
||||
tickets: [784987]
|
||||
|
||||
- title: "OS X: The unified title+toolbar was disabled as it had various bugs. If you really want it you can turn it on again via Preferences->Tweaks, but be aware that you will see problems like the calibre windowd being too wide, weird animations when a device is detected, etc."
|
||||
|
||||
- title: "Add a tweak that controls what words are treated as suffixes when generating an author sort string from an author name."
|
||||
|
||||
- title: "Get Books: Store last few searches in history"
|
||||
|
||||
bug fixes:
|
||||
- title: "Fix a crash when a device is connected/disconnected while a modal dialog opened from the toolbar is visible"
|
||||
tickets: [780484]
|
||||
|
||||
- title: "Fix incorrect results from ebooks.com when searching via Get Books"
|
||||
|
||||
- title: "Metadata plugboards: Add prioritization scheme to allow for using different settings for different locations"
|
||||
tickets: [783229]
|
||||
|
||||
- title: "Fix manage authors dialog too wide"
|
||||
tickets: [783065]
|
||||
|
||||
- title: "Fix multiple bracket types in author names not handled correctly when generating author sort string"
|
||||
tickets: [782551]
|
||||
|
||||
- title: "MOBI Input: Don't error out when detecting TOC structure if one of the elements has an invalid margin unit"
|
||||
|
||||
- title: "More fixes for japanese language calibre on windows"
|
||||
tickets: [782408]
|
||||
|
||||
- title: "Linux binaries: Always use either Cleanlook or Plastique styles for the GUI if no style can be loaded from the host computer"
|
||||
|
||||
improved recipes:
|
||||
- Newsweek
|
||||
- Economist
|
||||
- Dvhn
|
||||
- United Daily
|
||||
- Dagens Nyheter
|
||||
- GoComics
|
||||
- faz.net
|
||||
- golem.de
|
||||
|
||||
new recipes:
|
||||
- title: National Geographic
|
||||
author: gagsays
|
||||
|
||||
- title: Various German news sources
|
||||
author: schuster
|
||||
|
||||
- title: Dilema Veche
|
||||
author: Silviu Cotoara
|
||||
|
||||
- title: "Glamour, Good to Know, Good Housekeeping and Men's Health"
|
||||
author: Anonymous
|
||||
|
||||
- title: "Financial Sense and iProfessional"
|
||||
author: Darko Miletic
|
||||
|
||||
|
||||
- version: 0.8.1
|
||||
date: 2011-05-13
|
||||
|
||||
@ -456,7 +652,7 @@
|
||||
- title: "FB2 Output: Option to set the FB2 genre explicitly."
|
||||
tickets: [743178]
|
||||
|
||||
- title: "Plugin developers: calibre now has a new plugin API, see http://calibre-ebook.com/user_manual/creating_plugins.html. Your existing plugins should continue to work, but it would be good to test them to make sure."
|
||||
- title: "Plugin developers: calibre now has a new plugin API, see http://manual.calibre-ebook.com/creating_plugins.html. Your existing plugins should continue to work, but it would be good to test them to make sure."
|
||||
|
||||
bug fixes:
|
||||
- title: "Fix text color in the search bar set to black instead of the system font color"
|
||||
@ -841,7 +1037,7 @@
|
||||
|
||||
new features:
|
||||
- title: "Tag Browser: Support the creation of nested User Categories"
|
||||
description: "See http://calibre-ebook.com/user_manual/gui.html#tag-browser for details"
|
||||
description: "See http://manual.calibre-ebook.com/gui.html#tag-browser for details"
|
||||
type: major
|
||||
|
||||
- title: "Disable Kent District Library plugin to download series information. The website could not handle the load calibre's 2 million users put on it. You can manually re-enable it if you really want series information, but it is very slow"
|
||||
@ -3714,7 +3910,7 @@
|
||||
type: major
|
||||
description: >
|
||||
"You can now change the icons used in the User Interface and other static resources. Details on how to
|
||||
do this are at: http://calibre-ebook.com/user_manual/customize.html#overriding-icons-templates-etcetera"
|
||||
do this are at: http://manual.calibre-ebook.com/customize.html#overriding-icons-templates-etcetera"
|
||||
|
||||
- title: "Split the 'Send to device' button into two buttons, 'Connect/share' and 'Send to device'. The new 'Send to device' button will now only be available when a device is connected."
|
||||
|
||||
|
||||
2
INSTALL
2
INSTALL
@ -3,7 +3,7 @@ calibre supports installation from source, only on Linux.
|
||||
Note that you *do not* need to install from source to hack on
|
||||
the calibre source code. To get started with calibre development,
|
||||
use a normal calibre install and follow the instructions at
|
||||
http://calibre-ebook.com/user_manual/develop.html
|
||||
http://manual.calibre-ebook.com/develop.html
|
||||
|
||||
On Linux, there are two kinds of installation from source possible.
|
||||
Note that both kinds require lots of dependencies as well as a
|
||||
|
||||
4
README
4
README
@ -6,8 +6,8 @@ reading. It is cross platform, running on Linux, Windows and OS X.
|
||||
|
||||
For screenshots: https://calibre-ebook.com/demo
|
||||
|
||||
For installation/usage instructions please see
|
||||
http://calibre-ebook.com/user_manual
|
||||
For usage instructions please see
|
||||
http://manual.calibre-ebook.com
|
||||
|
||||
For source code access:
|
||||
bzr branch lp:calibre
|
||||
|
||||
BIN
icons/favicon.ico
Normal file
BIN
icons/favicon.ico
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 158 KiB |
42
recipes/aachener_nachrichten.recipe
Normal file
42
recipes/aachener_nachrichten.recipe
Normal file
@ -0,0 +1,42 @@
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
class AdvancedUserRecipe(BasicNewsRecipe):
|
||||
|
||||
title = u'Aachener Nachrichten'
|
||||
__author__ = 'schuster'
|
||||
oldest_article = 1
|
||||
max_articles_per_feed = 100
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
remove_javascript = True
|
||||
cover_url = 'http://www.an-online.de/einwaage/images/an_logo.png'
|
||||
masthead_url = 'http://www.an-online.de/einwaage/images/an_logo.png'
|
||||
extra_css = '''
|
||||
.fliesstext_detail:{margin-bottom:10%;}
|
||||
.headline_1:{margin-bottom:25%;}
|
||||
b{font-family:Arial,Helvetica,sans-serif; font-weight:200;font-size:large;}
|
||||
a{font-family:Arial,Helvetica,sans-serif; font-weight:400;font-size:large;}
|
||||
ll{font-family:Arial,Helvetica,sans-serif; font-weight:100;font-size:large;}
|
||||
h4{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
|
||||
img {min-width:300px; max-width:600px; min-height:300px; max-height:800px}
|
||||
dd{font-family:Arial,Helvetica,sans-serif;font-size:large;}
|
||||
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
|
||||
'''
|
||||
|
||||
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='span', attrs={'class':['fliesstext_detail', 'headline_1', 'autor_detail']}),
|
||||
dict(id=['header-logo'])
|
||||
]
|
||||
|
||||
feeds = [(u'Euregio', u'http://www.an-online.de/an/rss/Euregio.xml'),
|
||||
(u'Aachen', u'http://www.an-online.de/an/rss/Aachen.xml'),
|
||||
(u'Nordkreis', u'http://www.an-online.de/an/rss/Nordkreis.xml'),
|
||||
(u'Düren', u'http://www.an-online.de/an/rss/Dueren.xml'),
|
||||
(u'Eiffel', u'http://www.an-online.de/an/rss/Eifel.xml'),
|
||||
(u'Eschweiler', u'http://www.an-online.de/an/rss/Eschweiler.xml'),
|
||||
(u'Geilenkirchen', u'http://www.an-online.de/an/rss/Geilenkirchen.xml'),
|
||||
(u'Heinsberg', u'http://www.an-online.de/an/rss/Heinsberg.xml'),
|
||||
(u'Jülich', u'http://www.an-online.de/an/rss/Juelich.xml'),
|
||||
(u'Stolberg', u'http://www.an-online.de/an/rss/Stolberg.xml'),
|
||||
(u'Ratgebenr', u'http://www.an-online.de/an/rss/Ratgeber.xml')]
|
||||
43
recipes/alt_om_herning.recipe
Normal file
43
recipes/alt_om_herning.recipe
Normal file
@ -0,0 +1,43 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Rasmus Lauritsen <rasmus at lauritsen.info>'
|
||||
'''
|
||||
aoh.dk
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class aoh_dk(BasicNewsRecipe):
|
||||
title = 'Alt om Herning'
|
||||
__author__ = 'Rasmus Lauritsen'
|
||||
description = 'Nyheder fra Herning om omegn'
|
||||
publisher = 'Mediehuset Herning Folkeblad'
|
||||
category = 'news, local, Denmark'
|
||||
oldest_article = 14
|
||||
max_articles_per_feed = 50
|
||||
no_stylesheets = True
|
||||
delay = 1
|
||||
encoding = 'utf8'
|
||||
use_embedded_content = False
|
||||
language = 'da'
|
||||
extra_css = """ body{font-family: Verdana,Arial,sans-serif }
|
||||
img{margin-bottom: 0.4em}
|
||||
.txtContent,.stamp{font-size: small}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : category
|
||||
, 'publisher' : publisher
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
feeds = [(u'All news', u'http://aoh.dk/rss.xml')]
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='h1')
|
||||
,dict(name='span', attrs={'class':['frontpage_body']})
|
||||
]
|
||||
|
||||
remove_tags = [
|
||||
dict(name=['object','link'])
|
||||
]
|
||||
@ -1,27 +1,30 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
__copyright__ = '2010 - 2011, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
news.bbc.co.uk
|
||||
'''
|
||||
import re
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
|
||||
class BBC(BasicNewsRecipe):
|
||||
title = 'BBC News (fast)'
|
||||
__author__ = 'Darko Miletic, Starson17'
|
||||
description = 'News from UK. A much faster version that does not download pictures'
|
||||
description = 'Visit BBC News for up-to-the-minute news, breaking news, video, audio and feature stories. BBC News provides trusted World and UK news as well as local and regional perspectives. Also entertainment, business, science, technology and health news.'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
#delay = 1
|
||||
use_embedded_content = False
|
||||
encoding = 'utf8'
|
||||
publisher = 'BBC'
|
||||
category = 'news, UK, world'
|
||||
language = 'en_GB'
|
||||
publication_type = 'newsportal'
|
||||
extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif } .introduction{font-weight: bold} .story-feature{display: block; padding: 0; border: 1px solid; width: 40%; font-size: small} .story-feature h2{text-align: center; text-transform: uppercase} '
|
||||
preprocess_regexps = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')]
|
||||
masthead_url = 'http://news.bbcimg.co.uk/img/1_0_1/cream/hi/news/news-blocks.gif'
|
||||
extra_css = """
|
||||
body{ font-family: Verdana,Helvetica,Arial,sans-serif }
|
||||
.introduction{font-weight: bold}
|
||||
.story-feature{display: block; padding: 0; border: 1px solid; width: 40%; font-size: small}
|
||||
.story-feature h2{text-align: center; text-transform: uppercase}
|
||||
"""
|
||||
conversion_options = {
|
||||
'comments' : description
|
||||
,'tags' : category
|
||||
@ -31,31 +34,54 @@ class BBC(BasicNewsRecipe):
|
||||
}
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'class':['layout-block-a layout-block']})
|
||||
,dict(attrs={'class':['story-body','storybody']})
|
||||
dict(name='div', attrs={'class':['layout-block-a layout-block']})
|
||||
,dict(attrs={'class':['story-body','storybody']})
|
||||
,dict(attrs={'id':['meta-information','story-body']})
|
||||
]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':['story-feature related narrow', 'share-help', 'embedded-hyper', \
|
||||
'story-feature wide ', 'story-feature narrow']})
|
||||
, dict(name=['img'])
|
||||
]
|
||||
dict(name='div', attrs={'class':['story-feature related narrow', \
|
||||
'share-help', 'embedded-hyper', \
|
||||
'story-feature wide ', \
|
||||
'story-feature narrow', \
|
||||
'hidden','story-actions', \
|
||||
'embedded-hyper']})
|
||||
,dict(name=['img','meta','link','object','embed','iframe','base'])
|
||||
,dict(attrs={'class':['hidden','videoInStoryC']})
|
||||
,dict(attrs={'id':['bbccom_sponsor_section','toggle-controls', \
|
||||
'toggle-images','toggle-title']})
|
||||
]
|
||||
|
||||
remove_attributes = ['width','height']
|
||||
remove_attributes = ['width','height','xmlns:og','lang','clear']
|
||||
|
||||
feeds = [
|
||||
('News Front Page', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/front_page/rss.xml'),
|
||||
('Science/Nature', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/science/nature/rss.xml'),
|
||||
('Technology', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/technology/rss.xml'),
|
||||
('Entertainment', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/entertainment/rss.xml'),
|
||||
('Magazine', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/uk_news/magazine/rss.xml'),
|
||||
('Business', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/business/rss.xml'),
|
||||
('Health', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/health/rss.xml'),
|
||||
('Americas', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/americas/rss.xml'),
|
||||
('Europe', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/europe/rss.xml'),
|
||||
('South Asia', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/south_asia/rss.xml'),
|
||||
('UK', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/uk_news/rss.xml'),
|
||||
('Asia-Pacific', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/asia-pacific/rss.xml'),
|
||||
('Africa', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/africa/rss.xml'),
|
||||
('Top Stories' , 'http://feeds.bbci.co.uk/news/rss.xml' ),
|
||||
('Science/Environment', 'http://feeds.bbci.co.uk/news/science_and_environment/rss.xml'),
|
||||
('Technology' , 'http://feeds.bbci.co.uk/news/technology/rss.xml' ),
|
||||
('Entertainment/Arts' , 'http://feeds.bbci.co.uk/news/entertainment_and_arts/rss.xml' ),
|
||||
('Magazine' , 'http://feeds.bbci.co.uk/news/magazine/rss.xml' ),
|
||||
('Business' , 'http://feeds.bbci.co.uk/news/business/rss.xml' ),
|
||||
('Politics' , 'http://feeds.bbci.co.uk/news/politics/rss.xml' ),
|
||||
('Health' , 'http://feeds.bbci.co.uk/news/health/rss.xml' ),
|
||||
('US&Canada' , 'http://feeds.bbci.co.uk/news/world/us_and_canada/rss.xml' ),
|
||||
('Latin America' , 'http://feeds.bbci.co.uk/news/world/latin_america/rss.xml' ),
|
||||
('Europe' , 'http://feeds.bbci.co.uk/news/world/europe/rss.xml' ),
|
||||
('South Asia' , 'http://feeds.bbci.co.uk/news/world/south_asia/rss.xml' ),
|
||||
('England' , 'http://feeds.bbci.co.uk/news/england/rss.xml' ),
|
||||
('Asia-Pacific' , 'http://feeds.bbci.co.uk/news/world/asia_pacific/rss.xml' ),
|
||||
('Africa' , 'http://feeds.bbci.co.uk/news/world/africa/rss.xml' )
|
||||
]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
for item in soup.findAll('left'):
|
||||
item.name='span'
|
||||
for item in soup.findAll('a'):
|
||||
if item.string is not None:
|
||||
str = item.string
|
||||
item.replaceWith(str)
|
||||
else:
|
||||
str = self.tag_to_string(item)
|
||||
item.replaceWith(str)
|
||||
return soup
|
||||
|
||||
74
recipes/bild_de.recipe
Normal file
74
recipes/bild_de.recipe
Normal file
@ -0,0 +1,74 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
|
||||
|
||||
title = u'Bild.de'
|
||||
__author__ = 'schuster'
|
||||
oldest_article = 1
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
remove_javascript = True
|
||||
|
||||
# get cover from myspace
|
||||
cover_url = 'http://a3.l3-images.myspacecdn.com/images02/56/0232f842170b4d349779f8379c27e073/l.jpg'
|
||||
masthead_url = 'http://a3.l3-images.myspacecdn.com/images02/56/0232f842170b4d349779f8379c27e073/l.jpg'
|
||||
|
||||
# set what to fetch on the site
|
||||
remove_tags_before = dict(name = 'h2', attrs={'id':'cover'})
|
||||
remove_tags_after = dict(name ='div', attrs={'class':'back'})
|
||||
|
||||
|
||||
# remove things on the site that we don't want
|
||||
remove_tags = [dict(name='div', attrs={'class':'credit'}),
|
||||
dict(name='div', attrs={'class':'index'}),
|
||||
dict(name='div', attrs={'id':'zstart31'}),
|
||||
dict(name='div', attrs={'class':'hentry'}),
|
||||
dict(name='div', attrs={'class':'back'}),
|
||||
dict(name='div', attrs={'class':'pagination'}),
|
||||
dict(name='div', attrs={'class':'header'}),
|
||||
dict(name='div', attrs={'class':'element floatL'}),
|
||||
dict(name='div', attrs={'class':'stWrap'})
|
||||
]
|
||||
|
||||
# thanx to kiklop74 for code (see sticky thread -> Recipes - Re-usable code)
|
||||
# this one removes a lot of direct-link's
|
||||
def preprocess_html(self, soup):
|
||||
for alink in soup.findAll('a'):
|
||||
if alink.string is not None:
|
||||
tstr = alink.string
|
||||
alink.replaceWith(tstr)
|
||||
return soup
|
||||
|
||||
# remove the ad's
|
||||
filter_regexps = [r'.\.smartadserver\.com']
|
||||
def skip_ad_pages(self, soup):
|
||||
return None
|
||||
|
||||
#get the real url behind .feedsportal.com and fetch the artikels
|
||||
def get_article_url(self, article):
|
||||
return article.get('id', article.get('guid', None))
|
||||
|
||||
#list of the rss source from www.bild.de
|
||||
feeds = [(u'Überblick', u'http://rss.bild.de/bild.xml'),
|
||||
(u'News', u'http://rss.bild.de/bild-news.xml'),
|
||||
(u'Politik', u'http://rss.bild.de/bild-politik.xml'),
|
||||
(u'Unterhaltung', u'http://rss.bild.de/bild-unterhaltung.xml'),
|
||||
(u'Sport', u'http://rss.bild.de/bild-sport.xml'),
|
||||
(u'Lifestyle', u'http://rss.bild.de/bild-lifestyle.xml'),
|
||||
(u'Ratgeber', u'http://rss.bild.de/bild-ratgeber.xml'),
|
||||
(u'Reg. - Berlin', u'http://rss.bild.de/bild-berlin.xml'),
|
||||
(u'Reg. - Bremen', u'http://rss.bild.de/bild-bremen.xml'),
|
||||
(u'Reg. - Dresden', u'http://rss.bild.de/bild-dresden.xml'),
|
||||
(u'Reg. - Düsseldorf', u'http://rss.bild.de/bild-duesseldorf.xml'),
|
||||
(u'Reg. - Frankfurt-Main', u'http://rss.bild.de/bild-frankfurt-main.xml'),
|
||||
(u'Reg. - Hamburg', u'http://rss.bild.de/bild-hamburg.xml'),
|
||||
(u'Reg. - Hannover', u'http://rss.bild.de/bild-hannover.xml'),
|
||||
(u'Reg. - Köln', u'http://rss.bild.de/bild-koeln.xml'),
|
||||
(u'Reg. - Leipzig', u'http://rss.bild.de/bild-leipzig.xml'),
|
||||
(u'Reg. - München', u'http://rss.bild.de/bild-muenchen.xml'),
|
||||
(u'Reg. - Ruhrgebiet', u'http://rss.bild.de/bild-ruhrgebiet.xml'),
|
||||
(u'Reg. - Stuttgart', u'http://rss.bild.de/bild-stuttgart.xml')
|
||||
]
|
||||
|
||||
33
recipes/borse_online.recipe
Normal file
33
recipes/borse_online.recipe
Normal file
@ -0,0 +1,33 @@
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
|
||||
|
||||
title = u'Börse-online'
|
||||
__author__ = 'schuster'
|
||||
oldest_article = 1
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
remove_javascript = True
|
||||
cover_url = 'http://www.dpv.de/images/1995/source.gif'
|
||||
masthead_url = 'http://www.zeitschriften-cover.de/cover/boerse-online-cover-januar-2010-x1387.jpg'
|
||||
extra_css = '''
|
||||
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
|
||||
h4{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
|
||||
img {min-width:300px; max-width:600px; min-height:300px; max-height:800px}
|
||||
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
||||
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
|
||||
'''
|
||||
remove_tags_bevor = [dict(name='h3')]
|
||||
remove_tags_after = [dict(name='div', attrs={'class':'artikelfuss'})]
|
||||
remove_tags = [dict(attrs={'class':['moduleTopNav', 'moduleHeaderNav', 'text', 'blau', 'poll1150']}),
|
||||
dict(id=['newsletterlayer', 'newsletterlayerClose', 'newsletterlayer_body', 'newsletterarray_error', 'newsletterlayer_emailadress', 'newsletterlayer_submit', 'kommentar']),
|
||||
dict(name=['h2', 'Gesamtranking', 'h3',''])]
|
||||
|
||||
def print_version(self, url):
|
||||
return url.replace('.html#nv=rss', '.html?mode=print')
|
||||
|
||||
|
||||
|
||||
feeds = [(u'Börsennachrichten', u'http://www.boerse-online.de/rss/')]
|
||||
|
||||
61
recipes/capital_de.recipe
Normal file
61
recipes/capital_de.recipe
Normal file
@ -0,0 +1,61 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
class AdvancedUserRecipe1305470859(BasicNewsRecipe):
|
||||
title = u'Capital.de'
|
||||
language = 'de'
|
||||
__author__ = 'schuster'
|
||||
oldest_article =7
|
||||
max_articles_per_feed = 35
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
use_embedded_content = False
|
||||
masthead_url = 'http://www.wirtschaftsmedien-shop.de/media/stores/wirtschaftsmedien/capital/teaser_large_abo.jpg'
|
||||
cover_url = 'http://d1kb9jvg6ylufe.cloudfront.net/WebsiteCMS/de/unternehmen/linktipps/mainColumn/08/image/DE_Capital_bis20mm_SW.jpg'
|
||||
|
||||
extra_css = '''
|
||||
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
|
||||
h4{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
|
||||
img {min-width:300px; max-width:600px; min-height:300px; max-height:800px}
|
||||
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
||||
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
|
||||
'''
|
||||
def print_version(self, url):
|
||||
return url.replace ('nv=rss#utm_source=rss2&utm_medium=rss_feed&utm_campaign=/', 'mode=print')
|
||||
remove_tags_bevor = [dict(name='td', attrs={'class':'textcell'})]
|
||||
remove_tags_after = [dict(name='div', attrs={'class':'artikelsplit'})]
|
||||
|
||||
feeds = [ (u'Wirtschaftsmagazin', u'http://www.capital.de/rss/'),
|
||||
(u'Unternehmen', u'http://www.capital.de/rss/unternehmen'),
|
||||
(u'Finanz & Geldanlage', u'http://www.capital.de/rss/finanzen/geldanlage')]
|
||||
|
||||
def append_page(self, soup, appendtag, position):
|
||||
pager = soup.find('div',attrs={'class':'artikelsplit'})
|
||||
if pager:
|
||||
nexturl = self.INDEX + pager.a['href']
|
||||
soup2 = self.index_to_soup(nexturl)
|
||||
texttag = soup2.find('div', attrs={'class':'printable'})
|
||||
for it in texttag.findAll(style=True):
|
||||
del it['style']
|
||||
newpos = len(texttag.contents)
|
||||
self.append_page(soup2,texttag,newpos)
|
||||
texttag.extract()
|
||||
appendtag.insert(position,texttag)
|
||||
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
for item in soup.findAll('div', attrs={'class':'artikelsplit'}):
|
||||
item.extract()
|
||||
self.append_page(soup, soup.body, 3)
|
||||
pager = soup.find('div',attrs={'class':'artikelsplit'})
|
||||
if pager:
|
||||
pager.extract()
|
||||
return self.adeify_images(soup)
|
||||
|
||||
|
||||
|
||||
remove_tags = [dict(attrs={'class':['navSeitenAlle', 'kommentieren', 'teaserheader', 'teasercontent', 'info', 'zwischenhead', 'artikelsplit']}),
|
||||
dict(id=['topNav', 'mainNav', 'subNav', 'socialmedia', 'footerRahmen', 'gatrixx_marktinformationen', 'pager', 'weitere']),
|
||||
dict(span=['ratingtext', 'Gesamtranking', 'h3','']),
|
||||
dict(rel=['canonical'])]
|
||||
|
||||
@ -3,71 +3,39 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
'''
|
||||
Profile to download CNN
|
||||
'''
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
||||
|
||||
class CNN(BasicNewsRecipe):
|
||||
|
||||
title = 'CNN'
|
||||
description = 'Global news'
|
||||
timefmt = ' [%d %b %Y]'
|
||||
__author__ = 'Krittika Goyal and Sujata Raman'
|
||||
__author__ = 'Kovid Goyal'
|
||||
language = 'en'
|
||||
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
oldest_article = 15
|
||||
recursions = 1
|
||||
match_regexps = [r'http://sportsillustrated.cnn.com/.*/[1-9].html']
|
||||
#recursions = 1
|
||||
#match_regexps = [r'http://sportsillustrated.cnn.com/.*/[1-9].html']
|
||||
max_articles_per_feed = 25
|
||||
|
||||
extra_css = '''
|
||||
.cnn_strycntntlft{font-family :Arial,Helvetica,sans-serif;}
|
||||
h2{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
|
||||
.cnnTxtCmpnt{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
|
||||
.cnnTMcontent{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#575757}
|
||||
.storytext{font-family :Arial,Helvetica,sans-serif; font-size:small}
|
||||
.storybyline{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#575757}
|
||||
.credit{font-family :Arial,Helvetica,sans-serif; font-size:xx-small; color:#575757}
|
||||
.storyBrandingBanner{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#575757}
|
||||
.storytimestamp{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#575757}
|
||||
.timestamp{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#575757}
|
||||
.cnn_strytmstmp{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#666666;}
|
||||
.cnn_stryimg640caption{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#666666;}
|
||||
.cnn_strylccimg300cntr{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#666666;}
|
||||
.cnn_stryichgfcpt{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#666666;}
|
||||
.cnnByline{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#666666;}
|
||||
.cnn_bulletbin cnnStryHghLght{ font-size:xx-small;}
|
||||
.subhead p{font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
|
||||
.cnnStoryContent{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
|
||||
.cnnContentContainer{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
|
||||
.col1{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#666666;}
|
||||
.col3{color:#333333; font-family :Arial,Helvetica,sans-serif; font-size:x-small;font-weight:bold;}
|
||||
.cnnInlineT1Caption{font-family :Arial,Helvetica,sans-serif; font-size:x-small;font-weight:bold;}
|
||||
.cnnInlineT1Credit{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#333333;}
|
||||
.col10{color:#5A637E;}
|
||||
.cnnInlineRailBulletList{color:black;}
|
||||
.cnnLine0{font-family :Arial,Helvetica,sans-serif; color:#666666;font-weight:bold;}
|
||||
.cnnTimeStamp{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#333333;}
|
||||
.galleryhedDek{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#575757;}
|
||||
.galleryWidgetHeader{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#004276;}
|
||||
.article-content{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
|
||||
.cnnRecapStory{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
|
||||
h1{font-family :Arial,Helvetica,sans-serif; font-size:x-large}
|
||||
.captionname{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#575757;}
|
||||
inStoryIE{{font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
|
||||
'''
|
||||
|
||||
#remove_tags_before = dict(name='h1', attrs={'class':'heading'})
|
||||
#remove_tags_after = dict(name='td', attrs={'class':'newptool1'})
|
||||
remove_tags = [
|
||||
dict(name='iframe'),
|
||||
dict(name='div', attrs={'class':['cnnEndOfStory', 'cnnShareThisItem', 'cnn_strylctcntr cnn_strylctcqrelt', 'cnnShareBoxContent', 'cnn_strybtmcntnt', 'cnn_strycntntrgt']}),
|
||||
dict(name='div', attrs={'id':['IEContainer', 'clickIncludeBox']}),
|
||||
#dict(name='ul', attrs={'class':'article-tools'}),
|
||||
#dict(name='ul', attrs={'class':'articleTools'}),
|
||||
preprocess_regexps = [
|
||||
(re.compile(r'<!--\[if.*if\]-->', re.DOTALL), lambda m: ''),
|
||||
(re.compile(r'<script.*?</script>', re.DOTALL), lambda m: ''),
|
||||
(re.compile(r'<style.*?</style>', re.DOTALL), lambda m: ''),
|
||||
]
|
||||
|
||||
keep_only_tags = [dict(id='cnnContentContainer')]
|
||||
remove_tags = [
|
||||
{'class':['cnn_strybtntools', 'cnn_strylftcntnt',
|
||||
'cnn_strybtntools', 'cnn_strybtntoolsbttm', 'cnn_strybtmcntnt',
|
||||
'cnn_strycntntrgt']},
|
||||
]
|
||||
|
||||
|
||||
feeds = [
|
||||
('Top News', 'http://rss.cnn.com/rss/cnn_topstories.rss'),
|
||||
('World', 'http://rss.cnn.com/rss/cnn_world.rss'),
|
||||
@ -84,15 +52,8 @@ class CNN(BasicNewsRecipe):
|
||||
('Offbeat', 'http://rss.cnn.com/rss/cnn_offbeat.rss'),
|
||||
('Most Popular', 'http://rss.cnn.com/rss/cnn_mostpopular.rss')
|
||||
]
|
||||
def preprocess_html(self, soup):
|
||||
story = soup.find(name='div', attrs={'class':'cnnBody_Left'})
|
||||
if story is None:
|
||||
story = soup.find(name='div', attrs={'id':'cnnContentContainer'})
|
||||
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
|
||||
body = soup.find(name='body')
|
||||
body.insert(0, story)
|
||||
else:
|
||||
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
|
||||
body = soup.find(name='body')
|
||||
body.insert(0, story)
|
||||
return soup
|
||||
|
||||
def get_article_url(self, article):
|
||||
ans = BasicNewsRecipe.get_article_url(self, article)
|
||||
return ans.partition('?')[0]
|
||||
|
||||
|
||||
34
recipes/cosmopolitan_de.recipe
Normal file
34
recipes/cosmopolitan_de.recipe
Normal file
@ -0,0 +1,34 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1305567197(BasicNewsRecipe):
|
||||
title = u'Cosmopolitan.de'
|
||||
__author__ = 'schuster'
|
||||
oldest_article = 7
|
||||
language = 'de'
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_javascript = True
|
||||
cover_url = 'http://www.cosmopolitan.com/cm/shared/site_images/print_this/cosmopolitan_logo.gif'
|
||||
remove_tags_before = dict(name = 'h1', attrs={'class':'artikel'})
|
||||
remove_tags_after = dict(name ='div', attrs={'class':'morePages'})
|
||||
extra_css = '''
|
||||
h2{font-family:Arial,Helvetica,sans-serif; font-size: x-small;}
|
||||
h1{ font-family:Arial,Helvetica,sans-serif; font-size:x-large; font-weight:bold;}
|
||||
'''
|
||||
remove_tags = [ dict(id='strong'),
|
||||
dict(title='strong'),
|
||||
dict(name='span'),
|
||||
dict(name='li', attrs={'class':'large'}),
|
||||
dict(name='ul', attrs={'class':'articleImagesPortrait clearfix'}),
|
||||
dict(name='p', attrs={'class':'external'}),
|
||||
dict(name='a', attrs={'target':'_blank'}),]
|
||||
feeds = [ (u'Komplett', u'http://www.cosmopolitan.de/rss/allgemein.xml'),
|
||||
(u'Mode', u'http://www.cosmopolitan.de/rss/mode.xml'),
|
||||
(u'Beauty', u'http://www.cosmopolitan.de/rss/beauty.xml'),
|
||||
(u'Liebe&Sex', u'http://www.cosmopolitan.de/rss/liebe.xml'),
|
||||
(u'Psychologie', u'http://www.cosmopolitan.de/rss/psychologie.xml'),
|
||||
(u'Job&Karriere', u'http://www.cosmopolitan.de/rss/job.xml'),
|
||||
(u'Lifestyle', u'http://www.cosmopolitan.de/rss/lifestyle.xml'),
|
||||
(u'Shopping', u'http://www.cosmopolitan.de/rss/shopping.xml'),
|
||||
(u'Bildergalerien', u'http://www.cosmopolitan.de/rss/bildgalerien.xml')]
|
||||
71
recipes/dilemaveche.recipe
Normal file
71
recipes/dilemaveche.recipe
Normal file
@ -0,0 +1,71 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class DilemaVeche(BasicNewsRecipe):
|
||||
title = u'Dilema Veche' # apare vinerea, mai pe dupa-masa,depinde de Luiza cred (care se semneaza ca fiind creatorul fiecarui articol in feed-ul RSS)
|
||||
__author__ = 'song2' # inspirat din scriptul pentru Le Monde. Inspired from the Le Monde script
|
||||
description = '"Sint vechi, domnule!" (I.L. Caragiale)'
|
||||
publisher = 'Adevarul Holding'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 200
|
||||
encoding = 'utf8'
|
||||
language = 'ro'
|
||||
masthead_url = 'http://www.dilemaveche.ro/sites/all/themes/dilema/theme/dilema_two/layouter/dilema_two_homepage/logo.png'
|
||||
publication_type = 'magazine'
|
||||
feeds = [
|
||||
('Editoriale si opinii - Situatiunea', 'http://www.dilemaveche.ro/taxonomy/term/37/0/feed'),
|
||||
('Editoriale si opinii - Pe ce lume traim', 'http://www.dilemaveche.ro/taxonomy/term/38/0/feed'),
|
||||
('Editoriale si opinii - Bordeie si obiceie', 'http://www.dilemaveche.ro/taxonomy/term/44/0/feed'),
|
||||
('Editoriale si opinii - Talc Show', 'http://www.dilemaveche.ro/taxonomy/term/44/0/feed'),
|
||||
('Tema saptamanii', 'http://www.dilemaveche.ro/taxonomy/term/19/0/feed'),
|
||||
('La zi in cultura - Dilema va recomanda', 'http://www.dilemaveche.ro/taxonomy/term/58/0/feed'),
|
||||
('La zi in cultura - Carte', 'http://www.dilemaveche.ro/taxonomy/term/14/0/feed'),
|
||||
('La zi in cultura - Film', 'http://www.dilemaveche.ro/taxonomy/term/13/0/feed'),
|
||||
('La zi in cultura - Muzica', 'http://www.dilemaveche.ro/taxonomy/term/1341/0/feed'),
|
||||
('La zi in cultura - Arte performative', 'http://www.dilemaveche.ro/taxonomy/term/1342/0/feed'),
|
||||
('La zi in cultura - Arte vizuale', 'http://www.dilemaveche.ro/taxonomy/term/1512/0/feed'),
|
||||
('Societate - Ieri cu vedere spre azi', 'http://www.dilemaveche.ro/taxonomy/term/15/0/feed'),
|
||||
('Societate - Din polul opus', 'http://www.dilemaveche.ro/taxonomy/term/41/0/feed'),
|
||||
('Societate - Mass comedia', 'http://www.dilemaveche.ro/taxonomy/term/43/0/feed'),
|
||||
('Societate - La singular si la plural', 'http://www.dilemaveche.ro/taxonomy/term/42/0/feed'),
|
||||
('Oameni si idei - Educatie', 'http://www.dilemaveche.ro/taxonomy/term/46/0/feed'),
|
||||
('Oameni si idei - Polemici si dezbateri', 'http://www.dilemaveche.ro/taxonomy/term/48/0/feed'),
|
||||
('Oameni si idei - Stiinta si tehnologie', 'http://www.dilemaveche.ro/taxonomy/term/46/0/feed'),
|
||||
('Dileme on-line', 'http://www.dilemaveche.ro/taxonomy/term/005/0/feed')
|
||||
]
|
||||
remove_tags_before = dict(name='div',attrs={'class':'spacer_10'})
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':'art_related_left'}),
|
||||
dict(name='div', attrs={'class':'controale'}),
|
||||
dict(name='div', attrs={'class':'simple_overlay'}),
|
||||
]
|
||||
remove_tags_after = [dict(id='facebookLike')]
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
remove_empty_feeds = True
|
||||
extra_css = """
|
||||
body{font-family: Georgia,Times,serif }
|
||||
img{margin-bottom: 0.4em; display:block}
|
||||
"""
|
||||
def get_cover_url(self):
|
||||
cover_url = None
|
||||
soup = self.index_to_soup('http://dilemaveche.ro')
|
||||
link_item = soup.find('div',attrs={'class':'box_dr_pdf_picture'})
|
||||
if link_item and link_item.a:
|
||||
cover_url = link_item.a['href']
|
||||
br = BasicNewsRecipe.get_browser()
|
||||
try:
|
||||
br.open(cover_url)
|
||||
except: #daca nu gaseste pdf-ul
|
||||
self.log("\nPDF indisponibil")
|
||||
link_item = soup.find('div',attrs={'class':'box_dr_pdf_picture'})
|
||||
if link_item and link_item.img:
|
||||
cover_url = link_item.img['src']
|
||||
br = BasicNewsRecipe.get_browser()
|
||||
try:
|
||||
br.open(cover_url)
|
||||
except: #daca nu gaseste nici imaginea mica mica
|
||||
print('Mama lor de nenorociti! nu este nici pdf nici imagine')
|
||||
cover_url ='http://www.dilemaveche.ro/sites/all/themes/dilema/theme/dilema_two/layouter/dilema_two_homepage/logo.png'
|
||||
return cover_url
|
||||
cover_margins = (10, 15, '#ffffff')
|
||||
|
||||
@ -37,7 +37,7 @@ class DN_se(BasicNewsRecipe):
|
||||
,(u'Kultur' , u'http://www.dn.se/kultur-rss' )
|
||||
]
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'article'})]
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'article-content'})]
|
||||
remove_tags_before = dict(name='h1')
|
||||
remove_tags_after = dict(name='div',attrs={'id':'byline'})
|
||||
remove_tags = [
|
||||
|
||||
@ -1,19 +1,21 @@
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1302341394(BasicNewsRecipe):
|
||||
title = u'DvhN'
|
||||
oldest_article = 1
|
||||
__author__ = 'Reijndert'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 200
|
||||
|
||||
__author__ = 'Reijndert'
|
||||
no_stylesheets = True
|
||||
cover_url = 'http://www.dvhn.nl/template/Dagblad_v2.0/gfx/logo_DvhN.gif'
|
||||
cover_url = 'http://members.home.nl/apm.de.haas/calibre/DvhN.jpg'
|
||||
language = 'nl'
|
||||
country = 'NL'
|
||||
version = 1
|
||||
publisher = u'Dagblad van het Noorden'
|
||||
category = u'Nieuws'
|
||||
description = u'Nieuws uit Noord Nederland'
|
||||
timefmt = ' %Y-%m-%d (%a)'
|
||||
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'fullPicture'})
|
||||
@ -21,11 +23,26 @@ class AdvancedUserRecipe1302341394(BasicNewsRecipe):
|
||||
]
|
||||
|
||||
remove_tags = [
|
||||
dict(name=['object','link','iframe','base'])
|
||||
,dict(name='span',attrs={'class':'copyright'})
|
||||
dict(name='span',attrs={'class':'location'})
|
||||
]
|
||||
|
||||
feeds = [(u'Drenthe', u'http://www.dvhn.nl/nieuws/drenthe/index.jsp?service=rss'), (u'Groningen', u'http://www.dvhn.nl/nieuws/groningen/index.jsp?service=rss'), (u'Nederland', u'http://www.dvhn.nl/nieuws/nederland/index.jsp?service=rss'), (u'Wereld', u'http://www.dvhn.nl/nieuws/wereld/index.jsp?service=rss'), (u'Economie', u'http://www.dvhn.nl/nieuws/economie/index.jsp?service=rss'), (u'Sport', u'http://www.dvhn.nl/nieuws/sport/index.jsp?service=rss'), (u'Cultuur', u'http://www.dvhn.nl/nieuws/kunst/index.jsp?service=rss'), (u'24 Uur', u'http://www.dvhn.nl/nieuws/24uurdvhn/index.jsp?service=rss&selectiontype=last24hours')]
|
||||
preprocess_regexps = [
|
||||
(re.compile(r'<a.*?>'), lambda h1: '')
|
||||
,(re.compile(r'</a>'), lambda h2: '')
|
||||
,(re.compile(r'Word vriend van Dagblad van het Noorden op Facebook'), lambda h3: '')
|
||||
,(re.compile(r'Volg Dagblad van het Noorden op Twitter'), lambda h3: '')
|
||||
]
|
||||
|
||||
|
||||
feeds = [(u'Drenthe', u'http://www.dvhn.nl/nieuws/drenthe/index.jsp?service=rss')
|
||||
, (u'Groningen', u'http://www.dvhn.nl/nieuws/groningen/index.jsp?service=rss')
|
||||
, (u'Nederland', u'http://www.dvhn.nl/nieuws/nederland/index.jsp?service=rss')
|
||||
, (u'Wereld', u'http://www.dvhn.nl/nieuws/wereld/index.jsp?service=rss')
|
||||
, (u'Economie', u'http://www.dvhn.nl/nieuws/economie/index.jsp?service=rss')
|
||||
, (u'Sport', u'http://www.dvhn.nl/nieuws/sport/index.jsp?service=rss')
|
||||
, (u'Cultuur', u'http://www.dvhn.nl/nieuws/kunst/index.jsp?service=rss')
|
||||
, (u'24 Uur', u'http://www.dvhn.nl/nieuws/24uurdvhn/index.jsp?service=rss&selectiontype=last24hours')
|
||||
]
|
||||
|
||||
extra_css = '''
|
||||
body {font-family: verdana, arial, helvetica, geneva, sans-serif;}
|
||||
|
||||
@ -20,7 +20,7 @@ class Economist(BasicNewsRecipe):
|
||||
INDEX = 'http://www.economist.com/printedition'
|
||||
description = ('Global news and current affairs from a European'
|
||||
' perspective. Best downloaded on Friday mornings (GMT)')
|
||||
|
||||
extra_css = '.headline {font-size: x-large;} \n h2 { font-size: small; } \n h1 { font-size: medium; }'
|
||||
oldest_article = 7.0
|
||||
cover_url = 'http://www.economist.com/images/covers/currentcoverus_large.jpg'
|
||||
remove_tags = [
|
||||
|
||||
@ -14,7 +14,7 @@ class Economist(BasicNewsRecipe):
|
||||
description = ('Global news and current affairs from a European'
|
||||
' perspective. Best downloaded on Friday mornings (GMT).'
|
||||
' Much slower than the print edition based version.')
|
||||
|
||||
extra_css = '.headline {font-size: x-large;} \n h2 { font-size: small; } \n h1 { font-size: medium; }'
|
||||
oldest_article = 7.0
|
||||
cover_url = 'http://www.economist.com/images/covers/currentcoverus_large.jpg'
|
||||
remove_tags = [
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
||||
__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
elmundo.es
|
||||
'''
|
||||
@ -10,15 +10,24 @@ from calibre.web.feeds.news import BasicNewsRecipe
|
||||
class ElMundo(BasicNewsRecipe):
|
||||
title = 'El Mundo'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'News from Spain'
|
||||
publisher = 'El Mundo'
|
||||
description = 'Lider de informacion en espaniol'
|
||||
publisher = 'Unidad Editorial Informacion General S.L.U.'
|
||||
category = 'news, politics, Spain'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
encoding = 'iso8859_15'
|
||||
language = 'es'
|
||||
language = 'es_ES'
|
||||
masthead_url = 'http://estaticos03.elmundo.es/elmundo/iconos/v4.x/v4.01/bg_h1.png'
|
||||
publication_type = 'newspaper'
|
||||
extra_css = """
|
||||
body{font-family: Arial,Helvetica,sans-serif}
|
||||
.metadata_noticia{font-size: small}
|
||||
h1,h2,h3,h4,h5,h6,.subtitulo {color: #3F5974}
|
||||
.hora{color: red}
|
||||
.update{color: gray}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comments' : description
|
||||
@ -30,22 +39,31 @@ class ElMundo(BasicNewsRecipe):
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'noticia'})]
|
||||
remove_tags_before = dict(attrs={'class':['titular','antetitulo'] })
|
||||
remove_tags_after = dict(name='div' , attrs={'id':['desarrollo_noticia','tamano']})
|
||||
|
||||
remove_attributes = ['lang','border']
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':['herramientas','publicidad_google']})
|
||||
,dict(name='div', attrs={'id':'modulo_multimedia' })
|
||||
,dict(name='ul', attrs={'class':'herramientas' })
|
||||
,dict(name=['object','link'])
|
||||
,dict(name=['object','link','embed','iframe','base','meta'])
|
||||
]
|
||||
|
||||
feeds = [
|
||||
(u'Portada' , u'http://rss.elmundo.es/rss/descarga.htm?data2=4' )
|
||||
,(u'Deportes' , u'http://rss.elmundo.es/rss/descarga.htm?data2=14')
|
||||
,(u'Economia' , u'http://rss.elmundo.es/rss/descarga.htm?data2=7' )
|
||||
,(u'Espana' , u'http://rss.elmundo.es/rss/descarga.htm?data2=8' )
|
||||
,(u'Internacional' , u'http://rss.elmundo.es/rss/descarga.htm?data2=9' )
|
||||
,(u'Cultura' , u'http://rss.elmundo.es/rss/descarga.htm?data2=6' )
|
||||
,(u'Ciencia/Ecologia', u'http://rss.elmundo.es/rss/descarga.htm?data2=5' )
|
||||
,(u'Comunicacion' , u'http://rss.elmundo.es/rss/descarga.htm?data2=26')
|
||||
,(u'Television' , u'http://rss.elmundo.es/rss/descarga.htm?data2=76')
|
||||
(u'Portada' , u'http://estaticos.elmundo.es/elmundo/rss/portada.xml' )
|
||||
,(u'Deportes' , u'http://estaticos.elmundo.es/elmundodeporte/rss/portada.xml')
|
||||
,(u'Economia' , u'http://estaticos.elmundo.es/elmundo/rss/economia.xml' )
|
||||
,(u'Espana' , u'http://estaticos.elmundo.es/elmundo/rss/espana.xml' )
|
||||
,(u'Internacional' , u'http://estaticos.elmundo.es/elmundo/rss/internacional.xml' )
|
||||
,(u'Cultura' , u'http://estaticos.elmundo.es/elmundo/rss/cultura.xml' )
|
||||
,(u'Ciencia/Ecologia', u'http://estaticos.elmundo.es/elmundo/rss/ciencia.xml' )
|
||||
,(u'Comunicacion' , u'http://estaticos.elmundo.es/elmundo/rss/comunicacion.xml' )
|
||||
,(u'Television' , u'http://estaticos.elmundo.es/elmundo/rss/television.xml' )
|
||||
]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
return soup
|
||||
|
||||
def get_article_url(self, article):
|
||||
return article.get('guid', None)
|
||||
|
||||
|
||||
72
recipes/express_de.recipe
Normal file
72
recipes/express_de.recipe
Normal file
@ -0,0 +1,72 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
|
||||
|
||||
title = u'Express.de'
|
||||
__author__ = 'schuster'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 50
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
extra_css = '''
|
||||
h2{font-family:Arial,Helvetica,sans-serif; font-size: x-small;}
|
||||
h1{ font-family:Arial,Helvetica,sans-serif; font-size:x-large; font-weight:bold;}
|
||||
'''
|
||||
remove_javascript = True
|
||||
remove_tags_befor = [dict(name='div', attrs={'class':'Datum'})]
|
||||
remove_tags_after = [dict(name='div', attrs={'class':'MoreNews'})]
|
||||
|
||||
remove_tags = [dict(id='kalaydo'),
|
||||
dict(id='Header'),
|
||||
dict(id='Searchline'),
|
||||
dict(id='MainNav'),
|
||||
dict(id='Logo'),
|
||||
dict(id='MainLinkSpacer'),
|
||||
dict(id='MainLinks'),
|
||||
dict(id='ContainerPfad'), #neu
|
||||
dict(title='Diese Seite Bookmarken'),
|
||||
|
||||
dict(name='span'),
|
||||
dict(name='div', attrs={'class':'spacer_leftneu'}),
|
||||
dict(name='div', attrs={'class':'button kalaydologo'}),
|
||||
dict(name='div', attrs={'class':'button stellenneu'}),
|
||||
dict(name='div', attrs={'class':'button autoneu'}),
|
||||
dict(name='div', attrs={'class':'button immobilienneu'}),
|
||||
dict(name='div', attrs={'class':'button kleinanzeigen'}),
|
||||
dict(name='div', attrs={'class':'button tiereneu'}),
|
||||
dict(name='div', attrs={'class':'button ferienwohnungen'}),
|
||||
dict(name='div', attrs={'class':'button inserierenneu'}),
|
||||
dict(name='div', attrs={'class':'spacer_rightneu'}),
|
||||
dict(name='div', attrs={'class':'spacer_rightcorner'}),
|
||||
dict(name='div', attrs={'class':'HeaderMetaNav'}),
|
||||
dict(name='div', attrs={'class':'HeaderSearchOption'}),
|
||||
dict(name='div', attrs={'class':'HeaderSearch'}),
|
||||
dict(name='div', attrs={'class':'sbutton'}),
|
||||
dict(name='div', attrs={'class':'active'}),
|
||||
dict(name='div', attrs={'class':'MoreNews'}), #neu
|
||||
dict(name='div', attrs={'class':'ContentBoxSubline'}) #neu
|
||||
]
|
||||
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for alink in soup.findAll('a'):
|
||||
if alink.string is not None:
|
||||
tstr = alink.string
|
||||
alink.replaceWith(tstr)
|
||||
return soup
|
||||
|
||||
feeds = [(u'Top-Themen', u'http://www.express.de/home/-/2126/2126/-/view/asFeed/-/index.xml'),
|
||||
(u'Regional - Köln', u'http://www.express.de/regional/koeln/-/2856/2856/-/view/asFeed/-/index.xml'),
|
||||
(u'Regional - Bonn', u'http://www.express.de/regional/bonn/-/2860/2860/-/view/asFeed/-/index.xml'),
|
||||
(u'Regional - Düsseldorf', u'http://www.express.de/regional/duesseldorf/-/2858/2858/-/view/asFeed/-/index.xml'),
|
||||
(u'Regional - Region', u'http://www.express.de/regional/-/2178/2178/-/view/asFeed/-/index.xml'),
|
||||
(u'Sport-News', u'http://www.express.de/sport/-/2176/2176/-/view/asFeed/-/index.xml'),
|
||||
(u'Fussball-News', u'http://www.express.de/sport/fussball/-/3186/3186/-/view/asFeed/-/index.xml'),
|
||||
(u'1.FC Köln News', u'http://www.express.de/sport/fussball/fc-koeln/-/3192/3192/-/view/asFeed/-/index.xml'),
|
||||
(u'Alemannia Aachen News', u'http://www.express.de/sport/fussball/alemannia/-/3290/3290/-/view/asFeed/-/index.xml'),
|
||||
(u'Borussia M~Gladbach', u'http://www.express.de/sport/fussball/gladbach/-/3286/3286/-/view/asFeed/-/index.xml'),
|
||||
(u'Fortuna D~Dorf', u'http://www.express.de/sport/fussball/fortuna/-/3292/3292/-/view/asFeed/-/index.xml'),
|
||||
(u'Basketball News', u'http://www.express.de/sport/basketball/-/3190/3190/-/view/asFeed/-/index.xml'),
|
||||
(u'Big Brother', u'http://www.express.de/news/promi-show/big-brother/-/2402/2402/-/view/asFeed/-/index.xml'),
|
||||
]
|
||||
|
||||
@ -1,16 +1,16 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2008-2009, Kovid Goyal <kovid at kovidgoyal.net>, Darko Miletic <darko at gmail.com>'
|
||||
__copyright__ = '2008-2011, Kovid Goyal <kovid at kovidgoyal.net>, Darko Miletic <darko at gmail.com>'
|
||||
'''
|
||||
Profile to download FAZ.net
|
||||
Profile to download FAZ.NET
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class FazNet(BasicNewsRecipe):
|
||||
title = 'FAZ NET'
|
||||
title = 'FAZ.NET'
|
||||
__author__ = 'Kovid Goyal, Darko Miletic'
|
||||
description = 'Frankfurter Allgemeine Zeitung'
|
||||
publisher = 'FAZ Electronic Media GmbH'
|
||||
publisher = 'Frankfurter Allgemeine Zeitung GmbH'
|
||||
category = 'news, politics, Germany'
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
@ -32,15 +32,27 @@ class FazNet(BasicNewsRecipe):
|
||||
|
||||
remove_tags = [
|
||||
dict(name=['object','link','embed','base'])
|
||||
,dict(name='div', attrs={'class':['LinkBoxModulSmall','ModulVerlagsInfo']})
|
||||
,dict(name='div',
|
||||
attrs={'class':['LinkBoxModulSmall','ModulVerlagsInfo',
|
||||
'ArtikelServices', 'ModulLesermeinungenFooter',
|
||||
'ModulArtikelServices', 'BoxTool Aufklappen_Grau',
|
||||
'SocialMediaUnten', ]}),
|
||||
dict(id=['KurzLinkMenu', 'ArtikelServicesMenu']),
|
||||
]
|
||||
|
||||
|
||||
feeds = [ ('FAZ.NET', 'http://www.faz.net/s/Rub/Tpl~Epartner~SRss_.xml') ]
|
||||
|
||||
def print_version(self, url):
|
||||
article, sep, rest = url.partition('?')
|
||||
return article.replace('.html', '~Afor~Eprint.html')
|
||||
feeds = [
|
||||
('FAZ.NET Aktuell', 'http://www.faz.net/s/RubF3CE08B362D244869BE7984590CB6AC1/Tpl~Epartner~SRss_.xml'),
|
||||
('Politik', 'http://www.faz.net/s/RubA24ECD630CAE40E483841DB7D16F4211/Tpl~Epartner~SRss_.xml'),
|
||||
('Wirtschaft', 'http://www.faz.net/s/RubC9401175958F4DE28E143E68888825F6/Tpl~Epartner~SRss_.xml'),
|
||||
('Feuilleton', 'http://www.faz.net/s/RubCC21B04EE95145B3AC877C874FB1B611/Tpl~Epartner~SRss_.xml'),
|
||||
('Sport', 'http://www.faz.net/s/Rub9F27A221597D4C39A82856B0FE79F051/Tpl~Epartner~SRss_.xml'),
|
||||
('Gesellschaft', 'http://www.faz.net/s/Rub02DBAA63F9EB43CEB421272A670A685C/Tpl~Epartner~SRss_.xml'),
|
||||
('Finanzen', 'http://www.faz.net/s/Rub4B891837ECD14082816D9E088A2D7CB4/Tpl~Epartner~SRss_.xml'),
|
||||
('Wissen', 'http://www.faz.net/s/Rub7F4BEE0E0C39429A8565089709B70C44/Tpl~Epartner~SRss_.xml'),
|
||||
('Reise', 'http://www.faz.net/s/RubE2FB5CA667054BDEA70FB3BC45F8D91C/Tpl~Epartner~SRss_.xml'),
|
||||
('Technik & Motor', 'http://www.faz.net/s/Rub01E4D53776494844A85FDF23F5707AD8/Tpl~Epartner~SRss_.xml'),
|
||||
('Beruf & Chance', 'http://www.faz.net/s/RubB1E10A8367E8446897468EDAA6EA0504/Tpl~Epartner~SRss_.xml')
|
||||
]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>'
|
||||
|
||||
48
recipes/focus_de.recipe
Normal file
48
recipes/focus_de.recipe
Normal file
@ -0,0 +1,48 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1305567197(BasicNewsRecipe):
|
||||
title = u'Focus (DE)'
|
||||
__author__ = 'Anonymous'
|
||||
language = 'de'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_javascript = True
|
||||
|
||||
def print_version(self, url):
|
||||
return url + '?drucken=1'
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'id':['article']}) ]
|
||||
|
||||
remove_tags = [dict(name='div', attrs={'class':'sidebar'}),
|
||||
dict(name='div', attrs={'class':'commentForm'}),
|
||||
dict(name='div', attrs={'class':'comment clearfix oid-3534591 open'}),
|
||||
dict(name='div', attrs={'class':'similarityBlock'}),
|
||||
dict(name='div', attrs={'class':'footer'}),
|
||||
dict(name='div', attrs={'class':'getMoreComments'}),
|
||||
dict(name='div', attrs={'class':'moreComments'}),
|
||||
dict(name='div', attrs={'class':'ads'}),
|
||||
dict(name='div', attrs={'class':'articleContent'}),
|
||||
|
||||
|
||||
]
|
||||
remove_tags_after = [
|
||||
dict(name='div',attrs={'class':['commentForm','title', 'actions clearfix']})
|
||||
]
|
||||
|
||||
|
||||
feeds = [ (u'Eilmeldungen', u'http://rss2.focus.de/c/32191/f/533875/index.rss'),
|
||||
(u'Auto-News', u'http://rss2.focus.de/c/32191/f/443320/index.rss'),
|
||||
(u'Digital-News', u'http://rss2.focus.de/c/32191/f/443315/index.rss'),
|
||||
(u'Finanzen-News', u'http://rss2.focus.de/c/32191/f/443317/index.rss'),
|
||||
(u'Gesundheit-News', u'http://rss2.focus.de/c/32191/f/443314/index.rss'),
|
||||
(u'Immobilien-News', u'http://rss2.focus.de/c/32191/f/443318/index.rss'),
|
||||
(u'Kultur-News', u'http://rss2.focus.de/c/32191/f/443321/index.rss'),
|
||||
(u'Panorama-News', u'http://rss2.focus.de/c/32191/f/533877/index.rss'),
|
||||
(u'Politik-News', u'http://rss2.focus.de/c/32191/f/443313/index.rss'),
|
||||
(u'Reisen-News', u'http://rss2.focus.de/c/32191/f/443316/index.rss'),
|
||||
(u'Sport-News', u'http://rss2.focus.de/c/32191/f/443319/index.rss'),
|
||||
(u'Wissen-News', u'http://rss2.focus.de/c/32191/f/533876/index.rss'),
|
||||
]
|
||||
35
recipes/frankfurter_rundschau.recipe
Normal file
35
recipes/frankfurter_rundschau.recipe
Normal file
@ -0,0 +1,35 @@
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
class AdvancedUserRecipe(BasicNewsRecipe):
|
||||
|
||||
title = u'Frankfurter Rundschau'
|
||||
__author__ = 'schuster'
|
||||
oldest_article = 1
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
remove_javascript = True
|
||||
cover_url = 'http://www.fr-online.de/image/view/-/1474018/data/823538/-/logo.png'
|
||||
extra_css = '''
|
||||
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
|
||||
h4{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
|
||||
img {min-width:300px; max-width:600px; min-height:300px; max-height:800px}
|
||||
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
||||
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
|
||||
'''
|
||||
|
||||
feeds = [(u'Startseite', u'http://www.fr-online.de/home/-/1472778/1472778/-/view/asFeed/-/index.xml'),
|
||||
(u'Politik', u'http://www.fr-online.de/politik/-/1472596/1472596/-/view/asFeed/-/index.xml'),
|
||||
(u'Meinungen', u'http://www.fr-online.de/politik/meinung/-/1472602/1472602/-/view/asFeed/-/index.xml'),
|
||||
(u'Wirtschaft', u'http://www.fr-online.de/wirtschaft/-/1472780/1472780/-/view/asFeed/-/index.xml'),
|
||||
(u'Sport', u'http://www.fr-online.de/sport/-/1472784/1472784/-/view/asFeed/-/index.xml'),
|
||||
(u'Kultur', u'http://www.fr-online.de/kultur/-/1472786/1472786/-/view/asFeed/-/index.xml'),
|
||||
(u'Panorama', u'http://www.fr-online.de/panorama/-/1472782/1472782/-/view/asFeed/-/index.xml'),
|
||||
(u'Digital', u'http://www.fr-online.de/digital/-/1472406/1472406/-/view/asFeed/-/index.xml'),
|
||||
(u'Wissenschaft', u'http://www.fr-online.de/wissenschaft/-/1472788/1472788/-/view/asFeed/-/index.xml')
|
||||
]
|
||||
|
||||
|
||||
def print_version(self, url):
|
||||
return url.replace('index.html', 'view/printVersion/-/index.html')
|
||||
|
||||
38
recipes/glamour.recipe
Normal file
38
recipes/glamour.recipe
Normal file
@ -0,0 +1,38 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1305547242(BasicNewsRecipe):
|
||||
title = u'Glamour (US)'
|
||||
oldest_article = 21
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
language = 'en'
|
||||
remove_javascript = True
|
||||
__author__ = 'Anonymous'
|
||||
remove_tags = [dict(name='div', attrs={'class':'articles_footer', 'class':'printoptions'})]
|
||||
|
||||
def print_version(self, url):
|
||||
return url + '?printable=true'
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for alink in soup.findAll('a'):
|
||||
if alink.string is not None:
|
||||
tstr = alink.string
|
||||
alink.replaceWith(tstr)
|
||||
return soup
|
||||
|
||||
feeds = [ (u'All Fashion', u'http://feeds.glamour.com/glamour/all_fashion'),
|
||||
(u'All Beauty', u'http://feeds.glamour.com/glamour/all_beauty'),
|
||||
(u'All Sex, Love & Life', u'http://feeds.glamour.com/glamour/sex_love_life'),
|
||||
(u'All Health & Fitness', u'http://feeds.glamour.com/glamour/health_fitness'),
|
||||
(u'Shopping', u'http://feeds.glamour.com/glamour/shopping'),
|
||||
(u'Slaves to Fashion blog', u'http://feeds.glamour.com/glamour/slavestofashion'),
|
||||
(u'The Girls in the Beauty Department', u'http://feeds.glamour.com/glamour/thegirlsinthebeautydepartment'),
|
||||
(u'Smitten blog', u'http://feeds.glamour.com/glamour/smitten'),
|
||||
(u'Save the Date', u'http://feeds.feedburner.com/glamour/save-the-date'),
|
||||
(u'Single-ish blog', u'http://feeds.glamour.com/glamour/glamoursingle-ish'),
|
||||
(u'Save the Date', u'http://feeds.feedburner.com/glamour/save-the-date'),
|
||||
(u'Vitamin G blog', u'http://feeds.glamour.com/glamour/vitamin-g'),
|
||||
(u'Margarita Shapes Up blog', u'http://feeds.glamour.com/glamour/margaritashapesup'),
|
||||
(u'Little Miss Fortune blog', u'http://feeds.glamour.com/glamour/little-miss-fortune'),
|
||||
]
|
||||
@ -6,13 +6,13 @@ __copyright__ = 'Copyright 2010 Starson17'
|
||||
www.gocomics.com
|
||||
'''
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
import mechanize
|
||||
import mechanize, re
|
||||
|
||||
class GoComics(BasicNewsRecipe):
|
||||
title = 'GoComics'
|
||||
__author__ = 'Starson17'
|
||||
__version__ = '1.03'
|
||||
__date__ = '09 October 2010'
|
||||
__version__ = '1.05'
|
||||
__date__ = '19 may 2011'
|
||||
description = u'200+ Comics - Customize for more days/comics: Defaults to 7 days, 25 comics - 20 general, 5 editorial.'
|
||||
category = 'news, comics'
|
||||
language = 'en'
|
||||
@ -20,6 +20,7 @@ class GoComics(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
cover_url = 'http://paulbuckley14059.files.wordpress.com/2008/06/calvin-and-hobbes.jpg'
|
||||
remove_attributes = ['style']
|
||||
|
||||
####### USER PREFERENCES - COMICS, IMAGE SIZE AND NUMBER OF COMICS TO RETRIEVE ########
|
||||
# num_comics_to_get - I've tried up to 99 on Calvin&Hobbes
|
||||
@ -40,6 +41,8 @@ class GoComics(BasicNewsRecipe):
|
||||
|
||||
remove_tags = [dict(name='a', attrs={'class':['beginning','prev','cal','next','newest']}),
|
||||
dict(name='div', attrs={'class':['tag-wrapper']}),
|
||||
dict(name='a', attrs={'href':re.compile(r'.*mutable_[0-9]+', re.IGNORECASE)}),
|
||||
dict(name='img', attrs={'src':re.compile(r'.*mutable_[0-9]+', re.IGNORECASE)}),
|
||||
dict(name='ul', attrs={'class':['share-nav','feature-nav']}),
|
||||
]
|
||||
|
||||
|
||||
@ -1,83 +1,70 @@
|
||||
#!/usr/bin/env python
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
class golem_ger(BasicNewsRecipe):
|
||||
title = u'Golem.de'
|
||||
language = 'de'
|
||||
__author__ = 'Kovid Goyal'
|
||||
__author__ = 'schuster'
|
||||
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
language = 'de'
|
||||
lang = 'de-DE'
|
||||
no_stylesheets = True
|
||||
encoding = 'iso-8859-1'
|
||||
recursions = 1
|
||||
match_regexps = [r'http://www.golem.de/.*.html']
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='h1', attrs={'class':'artikelhead'}),
|
||||
dict(name='p', attrs={'class':'teaser'}),
|
||||
dict(name='div', attrs={'class':'artikeltext'}),
|
||||
dict(name='h2', attrs={'id':'artikelhead'}),
|
||||
]
|
||||
|
||||
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'id':['similarContent','topContentWrapper','storycarousel','aboveFootPromo','comments','toolbar','breadcrumbs','commentlink','sidebar','rightColumn']}),
|
||||
dict(name='div', attrs={'class':['gg_embeddedSubText','gg_embeddedIndex gg_solid','gg_toOldGallery','golemGallery']}),
|
||||
dict(name='img', attrs={'class':['gg_embedded','gg_embeddedIconRight gg_embeddedIconFS gg_cursorpointer']}),
|
||||
dict(name='td', attrs={'class':['xsmall']}),
|
||||
]
|
||||
|
||||
|
||||
# remove_tags_after = [
|
||||
# dict(name='div', attrs={'id':['contentad2']})
|
||||
# ]
|
||||
|
||||
|
||||
feeds = [
|
||||
(u'Golem.de', u'http://rss.golem.de/rss.php?feed=ATOM1.0'),
|
||||
(u'Audio/Video', u'http://rss.golem.de/rss.php?tp=av&feed=RSS2.0'),
|
||||
(u'Foto', u'http://rss.golem.de/rss.php?tp=foto&feed=RSS2.0'),
|
||||
(u'Games', u'http://rss.golem.de/rss.php?tp=games&feed=RSS2.0'),
|
||||
(u'Internet', u'http://rss.golem.de/rss.php?tp=inet&feed=RSS1.0'),
|
||||
(u'Mobil', u'http://rss.golem.de/rss.php?tp=mc&feed=ATOM1.0'),
|
||||
(u'Internet', u'http://rss.golem.de/rss.php?tp=inet&feed=RSS1.0'),
|
||||
(u'Politik/Recht', u'http://rss.golem.de/rss.php?tp=pol&feed=ATOM1.0'),
|
||||
(u'Desktop-Applikationen', u'http://rss.golem.de/rss.php?tp=apps&feed=RSS2.0'),
|
||||
(u'Software-Entwicklung', u'http://rss.golem.de/rss.php?tp=dev&feed=RSS2.0'),
|
||||
(u'Wirtschaft', u'http://rss.golem.de/rss.php?tp=wirtschaft&feed=RSS2.0'),
|
||||
(u'Hardware', u'http://rss.golem.de/rss.php?r=hw&feed=RSS2.0'),
|
||||
(u'Software', u'http://rss.golem.de/rss.php?r=sw&feed=RSS2.0'),
|
||||
(u'Networld', u'http://rss.golem.de/rss.php?r=nw&feed=RSS2.0'),
|
||||
(u'Entertainment', u'http://rss.golem.de/rss.php?r=et&feed=RSS2.0'),
|
||||
(u'TK', u'http://rss.golem.de/rss.php?r=tk&feed=RSS2.0'),
|
||||
(u'E-Commerce', u'http://rss.golem.de/rss.php?r=ec&feed=RSS2.0'),
|
||||
(u'Unternehmen/Maerkte', u'http://rss.golem.de/rss.php?r=wi&feed=RSS2.0')
|
||||
]
|
||||
|
||||
|
||||
|
||||
|
||||
feeds = [
|
||||
(u'Golem.de', u'http://rss.golem.de/rss.php?feed=ATOM1.0'),
|
||||
(u'Mobil', u'http://rss.golem.de/rss.php?tp=mc&feed=feed=RSS2.0'),
|
||||
(u'OSS', u'http://rss.golem.de/rss.php?tp=oss&feed=RSS2.0'),
|
||||
(u'Politik/Recht', u'http://rss.golem.de/rss.php?tp=pol&feed=RSS2.0'),
|
||||
(u'Desktop-Applikationen', u'http://rss.golem.de/rss.php?tp=apps&feed=RSS2.0'),
|
||||
(u'Software-Entwicklung', u'http://rss.golem.de/rss.php?tp=dev&feed=RSS2.0'),
|
||||
]
|
||||
|
||||
|
||||
max_articles_per_feed = 10
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
cover_url = 'http://www.e-energy.de/images/logo_golem.jpg'
|
||||
masthead_url = 'http://www.golem.de/staticrl/images/logo.png'
|
||||
extra_css = '''
|
||||
h1 {color:#0066CC;font-family:Arial,Helvetica,sans-serif; font-size:30px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; line-height:20px;margin-bottom:2 em;}
|
||||
h2 {color:#4D4D4D;font-family:Arial,Helvetica,sans-serif; font-size:22px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; line-height:16px; }
|
||||
h3 {color:#4D4D4D;font-family:Arial,Helvetica,sans-serif; font-size:x-small; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:normal; line-height:5px;}
|
||||
h4 {color:#333333; font-family:Arial,Helvetica,sans-serif;font-size:13px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; line-height:13px; }
|
||||
h5 {color:#333333; font-family:Arial,Helvetica,sans-serif; font-size:11px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; line-height:11px; text-transform:uppercase;}
|
||||
.teaser {font-style:italic;font-size:12pt;margin-bottom:15pt;}
|
||||
.xsmall{font-style:italic;font-size:x-small;}
|
||||
.td{font-style:italic;font-size:x-small;}
|
||||
img {align:left;}
|
||||
h2{font-family:Arial,Helvetica,sans-serif; font-size: x-small;}
|
||||
h1{ font-family:Arial,Helvetica,sans-serif; font-size:x-large; font-weight:bold;}
|
||||
|
||||
'''
|
||||
remove_javascript = True
|
||||
remove_tags_befor = [dict(name='header', attrs={'class':'cluster-header'})]
|
||||
remove_tags_after = [dict(name='p', attrs={'class':'meta'})]
|
||||
remove_tags = [dict(rel='nofollow'),
|
||||
dict(name='header', attrs={'id':'header'}),
|
||||
dict(name='div', attrs={'class':'dh1'}),
|
||||
dict(name='label', attrs={'class':'implied'}),
|
||||
dict(name='section', attrs={'id':'comments'}),
|
||||
dict(name='li', attrs={'class':'gg_prebackcounterItem'}),
|
||||
dict(name='li', attrs={'class':'gg_prebackcounterItem gg_embeddedIndexCounter'}),
|
||||
dict(name='img', attrs={'class':'gg_embeddedIconRight gg_embeddedIconFS gg_cursorpointer'}),
|
||||
dict(name='div', attrs={'target':'_blank'})
|
||||
]
|
||||
|
||||
def get_browser(self, *args, **kwargs):
|
||||
from calibre import browser
|
||||
kwargs['user_agent'] = 'mozilla'
|
||||
return browser(*args, **kwargs)
|
||||
|
||||
def get_article_url(self, article):
|
||||
return article.get('id', article.get('guid', None))
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for alink in soup.findAll('a'):
|
||||
if alink.string is not None:
|
||||
tstr = alink.string
|
||||
alink.replaceWith(tstr)
|
||||
return soup
|
||||
|
||||
feeds = [(u'Audio/Video', u'http://rss.golem.de/rss.php?tp=av&feed=RSS2.0'),
|
||||
(u'Foto', u'http://rss.golem.de/rss.php?tp=foto&feed=RSS2.0'),
|
||||
(u'Games', u'http://rss.golem.de/rss.php?tp=games&feed=RSS2.0'),
|
||||
(u'Handy', u'http://rss.golem.de/rss.php?tp=handy&feed=RSS2.0'),
|
||||
(u'Internet', u'http://rss.golem.de/rss.php?tp=inet&feed=RSS2.0'),
|
||||
(u'Mobile', u'http://rss.golem.de/rss.php?tp=mc&feed=RSS2.0'),
|
||||
(u'OSS', u'http://rss.golem.de/rss.php?tp=oss&feed=RSS2.0'),
|
||||
(u'Politik/Recht', u'http://rss.golem.de/rss.php?tp=pol&feed=RSS2.0'),
|
||||
(u'Security', u'http://rss.golem.de/rss.php?tp=sec&feed=RSS2.0'),
|
||||
(u'Desktop-Applikationen', u'http://rss.golem.de/rss.php?tp=apps&feed=RSS2.0'),
|
||||
(u'Software-Entwicklung', u'http://rss.golem.de/rss.php?tp=dev&feed=RSS2.0'),
|
||||
(u'Wirtschaft', u'http://rss.golem.de/rss.php?tp=wirtschaft&feed=RSS2.0'),
|
||||
(u'Hardware', u'http://rss.golem.de/rss.php?r=hw&feed=RSS2.0'),
|
||||
(u'Software', u'http://rss.golem.de/rss.php?r=sw&feed=RSS2.0'),
|
||||
(u'Networld', u'http://rss.golem.de/rss.php?r=nw&feed=RSS2.0'),
|
||||
(u'Entertainment', u'http://rss.golem.de/rss.php?r=et&feed=RSS2.0'),
|
||||
(u'TK', u'http://rss.golem.de/rss.php?r=tk&feed=RSS2.0'),
|
||||
(u'Wirtschaft', u'http://rss.golem.de/rss.php?r=wi&feed=RSS2.0'),
|
||||
(u'E-Commerce', u'http://rss.golem.de/rss.php?r=ec&feed=RSS2.0')
|
||||
|
||||
]
|
||||
|
||||
|
||||
31
recipes/good_house_keeping.recipe
Normal file
31
recipes/good_house_keeping.recipe
Normal file
@ -0,0 +1,31 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1305547242(BasicNewsRecipe):
|
||||
title = u'Good House Keeping'
|
||||
language = 'en'
|
||||
__author__ = 'Anonymous'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_javascript = True
|
||||
|
||||
def print_version(self,url):
|
||||
segments = url.split('/')
|
||||
printURL = '/'.join(segments[0:3]) + '/print-this/' + '/'.join(segments[4:])
|
||||
return printURL
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for alink in soup.findAll('a'):
|
||||
if alink.string is not None:
|
||||
tstr = alink.string
|
||||
alink.replaceWith(tstr)
|
||||
return soup
|
||||
|
||||
feeds = [ (u'Recipes & Entertaining', u'http://www.goodhousekeeping.com/food/food-rss/?src=rss'),
|
||||
(u'Home & House', u'http://www.goodhousekeeping.com/home/home-rss/?src=rss'),
|
||||
(u'Diet & Health', u'http://www.goodhousekeeping.com/health/health-rss/?src=rss'),
|
||||
(u'Beauty & Style', u'http://www.goodhousekeeping.com/beauty/beauty-rss/?src=rss'),
|
||||
(u'Family & Pets', u'http://www.goodhousekeeping.com/family/family-rss/?src=rss'),
|
||||
(u'Saving Money', u'http://www.goodhousekeeping.com/money/money-rss/?src=rss'),
|
||||
]
|
||||
32
recipes/good_to_know.recipe
Normal file
32
recipes/good_to_know.recipe
Normal file
@ -0,0 +1,32 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1305547242(BasicNewsRecipe):
|
||||
title = u'Good to Know (uk)'
|
||||
oldest_article = 14
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_javascript = True
|
||||
__author__ = 'Anonymous'
|
||||
language = 'en_GB'
|
||||
remove_tags = [dict(name='div', attrs={'class':'articles_footer', 'class':'printoptions'})]
|
||||
|
||||
def print_version(self, url):
|
||||
return url + '/print/1'
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for alink in soup.findAll('a'):
|
||||
if alink.string is not None:
|
||||
tstr = alink.string
|
||||
alink.replaceWith(tstr)
|
||||
return soup
|
||||
|
||||
feeds = [ (u'Family Conception Advice', u'http://www.goodtoknow.co.uk/feeds/family.rss'),
|
||||
(u'Family Health Advice', u'http://www.goodtoknow.co.uk/feeds/health.rss'),
|
||||
(u'Diet Advice', u'http://www.goodtoknow.co.uk/feeds/diet.rss'),
|
||||
(u'Food Advice', u'http://www.goodtoknow.co.uk/feeds/food.rss'),
|
||||
(u'Sex Advice', u'http://www.goodtoknow.co.uk/feeds/sex.rss'),
|
||||
(u'Easy Exercise', u'http://www.goodtoknow.co.uk/feeds/easyexercise.rss'),
|
||||
(u'Recipes', u'http://www.goodtoknow.co.uk/feeds/recipes.rss'),
|
||||
(u'Food Quick-tips', u'http://www.goodtoknow.co.uk/feeds/foodquicktips.rss'),
|
||||
]
|
||||
36
recipes/grrm.recipe
Normal file
36
recipes/grrm.recipe
Normal file
@ -0,0 +1,36 @@
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
grrm.livejournal.com
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class NotABlog(BasicNewsRecipe):
|
||||
title = 'Not A Blog - George R.R. Martin'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'George R.R. Martin'
|
||||
oldest_article = 15
|
||||
max_articles_per_feed = 100
|
||||
language = 'en'
|
||||
encoding = 'utf-8'
|
||||
no_stylesheets = True
|
||||
use_embedded_content = True
|
||||
publication_type = 'blog'
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : 'sf, fantasy, game of thrones'
|
||||
, 'publisher': 'George R.R. Martin'
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
feeds = [(u'Posts', u'http://grrm.livejournal.com/data/rss')]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
return self.adeify_images(soup)
|
||||
|
||||
|
||||
@ -87,7 +87,13 @@ class Guardian(BasicNewsRecipe):
|
||||
idx = soup.find('div', id='book-index')
|
||||
for s in idx.findAll('strong', attrs={'class':'book'}):
|
||||
a = s.find('a', href=True)
|
||||
yield (self.tag_to_string(a), a['href'])
|
||||
section_title = self.tag_to_string(a)
|
||||
if not section_title in self.ignore_sections:
|
||||
prefix = ''
|
||||
if section_title != 'Main section':
|
||||
prefix = section_title + ': '
|
||||
for subsection in s.parent.findAll('a', attrs={'class':'book-section'}):
|
||||
yield (prefix + self.tag_to_string(subsection), subsection['href'])
|
||||
|
||||
def find_articles(self, url):
|
||||
soup = self.index_to_soup(url)
|
||||
@ -114,10 +120,7 @@ class Guardian(BasicNewsRecipe):
|
||||
try:
|
||||
feeds = []
|
||||
for title, href in self.find_sections():
|
||||
if not title in self.ignore_sections:
|
||||
feeds.append((title, list(self.find_articles(href))))
|
||||
feeds.append((title, list(self.find_articles(href))))
|
||||
return feeds
|
||||
except:
|
||||
raise NotImplementedError
|
||||
|
||||
|
||||
|
||||
52
recipes/heise_online.recipe
Normal file
52
recipes/heise_online.recipe
Normal file
@ -0,0 +1,52 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
class AdvancedUserRecipe(BasicNewsRecipe):
|
||||
|
||||
title = 'Heise-online'
|
||||
description = 'News vom Heise-Verlag'
|
||||
__author__ = 'schuster'
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 35
|
||||
rescale_images = True
|
||||
remove_empty_feeds = True
|
||||
timeout = 5
|
||||
no_stylesheets = True
|
||||
|
||||
|
||||
remove_tags_after = dict(name ='p', attrs={'class':'editor'})
|
||||
remove_tags = [dict(id='navi_top_container'),
|
||||
dict(id='navi_bottom'),
|
||||
dict(id='mitte_rechts'),
|
||||
dict(id='navigation'),
|
||||
dict(id='subnavi'),
|
||||
dict(id='social_bookmarks'),
|
||||
dict(id='permalink'),
|
||||
dict(id='content_foren'),
|
||||
dict(id='seiten_navi'),
|
||||
dict(id='adbottom'),
|
||||
dict(id='sitemap')]
|
||||
|
||||
feeds = [
|
||||
('Newsticker', 'http://www.heise.de/newsticker/heise.rdf'),
|
||||
('Auto', 'http://www.heise.de/autos/rss/news.rdf'),
|
||||
('Foto ', 'http://www.heise.de/foto/rss/news-atom.xml'),
|
||||
('Mac&i', 'http://www.heise.de/mac-and-i/news.rdf'),
|
||||
('Mobile ', 'http://www.heise.de/mobil/newsticker/heise-atom.xml'),
|
||||
('Netz ', 'http://www.heise.de/netze/rss/netze-atom.xml'),
|
||||
('Open ', 'http://www.heise.de/open/news/news-atom.xml'),
|
||||
('Resale ', 'http://www.heise.de/resale/rss/resale.rdf'),
|
||||
('Security ', 'http://www.heise.de/security/news/news-atom.xml'),
|
||||
('C`t', 'http://www.heise.de/ct/rss/artikel-atom.xml'),
|
||||
('iX', 'http://www.heise.de/ix/news/news.rdf'),
|
||||
('Mach-flott', 'http://www.heise.de/mach-flott/rss/mach-flott-atom.xml'),
|
||||
('Blog: Babel-Bulletin', 'http://www.heise.de/developer/rss/babel-bulletin/blog.rdf'),
|
||||
('Blog: Der Dotnet-Doktor', 'http://www.heise.de/developer/rss/dotnet-doktor/blog.rdf'),
|
||||
('Blog: Bernds Management-Welt', 'http://www.heise.de/developer/rss/bernds-management-welt/blog.rdf'),
|
||||
('Blog: IT conversation', 'http://www.heise.de/developer/rss/world-of-it/blog.rdf'),
|
||||
('Blog: Kais bewegtes Web', 'http://www.heise.de/developer/rss/kais-bewegtes-web/blog.rdf')
|
||||
]
|
||||
|
||||
def print_version(self, url):
|
||||
return url + '?view=print'
|
||||
|
||||
BIN
recipes/icons/dilemaveche.png
Normal file
BIN
recipes/icons/dilemaveche.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 558 B |
Binary file not shown.
|
Before Width: | Height: | Size: 550 B After Width: | Height: | Size: 1.1 KiB |
BIN
recipes/icons/marca.png
Normal file
BIN
recipes/icons/marca.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 293 B |
BIN
recipes/icons/natgeo.png
Normal file
BIN
recipes/icons/natgeo.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 247 B |
BIN
recipes/icons/osnews_pl.png
Normal file
BIN
recipes/icons/osnews_pl.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1006 B |
BIN
recipes/icons/rmf24_opinie.png
Normal file
BIN
recipes/icons/rmf24_opinie.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 722 B |
BIN
recipes/icons/swiatkindle.png
Normal file
BIN
recipes/icons/swiatkindle.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 425 B |
BIN
recipes/icons/the_nation.png
Normal file
BIN
recipes/icons/the_nation.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 925 B |
BIN
recipes/icons/wash_post.png
Normal file
BIN
recipes/icons/wash_post.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.1 KiB |
32
recipes/impulse_de.recipe
Normal file
32
recipes/impulse_de.recipe
Normal file
@ -0,0 +1,32 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
class AdvancedUserRecipe1305470859(BasicNewsRecipe):
|
||||
title = u'Impulse.de'
|
||||
language = 'de'
|
||||
__author__ = 'schuster'
|
||||
oldest_article =14
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
use_embedded_content = False
|
||||
cover_url = 'http://www.bvk.de/files/image/bilder/Logo%20Impulse.jpg'
|
||||
|
||||
extra_css = '''
|
||||
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
|
||||
h4{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
|
||||
img {min-width:300px; max-width:600px; min-height:300px; max-height:800px}
|
||||
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
||||
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
|
||||
'''
|
||||
def print_version(self, url):
|
||||
return url.replace ('#utm_source=rss2&utm_medium=rss_feed&utm_campaign=/', '?mode=print')
|
||||
remove_tags_bevor = [dict(name='h1', attrs={'class':'h2'})]
|
||||
remove_tags_after = [dict(name='div', attrs={'class':'artikelfuss'})]
|
||||
|
||||
feeds = [ (u'impulstest', u'http://www.impulse.de/rss/')]
|
||||
|
||||
|
||||
remove_tags = [dict(attrs={'class':['navSeitenAlle', 'kommentieren', 'teaserheader', 'teasercontent', 'info', 'zwischenhead', 'kasten_artikel']}),
|
||||
dict(id=['metaNav', 'impKopf', 'impTopNav', 'impSubNav', 'footerRahmen', 'gatrixx_marktinformationen', 'pager', 'weitere', 'socialmedia', 'rating_open']),
|
||||
dict(span=['ratingtext', 'Gesamtranking', 'h3','']),
|
||||
dict(rel=['canonical'])]
|
||||
|
||||
@ -3,8 +3,9 @@ from calibre.web.feeds.news import BasicNewsRecipe
|
||||
class AdvancedUserRecipe1295262156(BasicNewsRecipe):
|
||||
title = u'kath.net'
|
||||
__author__ = 'Bobus'
|
||||
description = u'Katholische Nachrichten'
|
||||
oldest_article = 7
|
||||
language = 'en'
|
||||
language = 'de'
|
||||
max_articles_per_feed = 100
|
||||
|
||||
feeds = [(u'kath.net', u'http://www.kath.net/2005/xml/index.xml')]
|
||||
|
||||
@ -5,14 +5,16 @@ class Kathimerini(BasicNewsRecipe):
|
||||
__author__ = 'Pan'
|
||||
description = 'News from Greece'
|
||||
max_articles_per_feed = 100
|
||||
oldest_article = 100
|
||||
oldest_article = 100
|
||||
publisher = 'Kathimerini'
|
||||
category = 'news, GR'
|
||||
language = 'el'
|
||||
encoding = 'windows-1253'
|
||||
conversion_options = { 'linearize_tables': True}
|
||||
no_stylesheets = True
|
||||
remove_tags_before = dict(name='td',attrs={'class':'news'})
|
||||
remove_tags_after = dict(name='td',attrs={'class':'news'})
|
||||
remove_attributes = ['width', 'src','header','footer']
|
||||
remove_tags_before = dict(name='td',attrs={'class':'news'})
|
||||
remove_tags_after = dict(name='td',attrs={'class':'news'})
|
||||
remove_attributes = ['width', 'src','header','footer']
|
||||
|
||||
feeds = [(u'\u03a0\u03bf\u03bb\u03b9\u03c4\u03b9\u03ba\u03ae',
|
||||
'http://wk.kathimerini.gr/xml_files/politics.xml'),
|
||||
@ -34,4 +36,3 @@ class Kathimerini(BasicNewsRecipe):
|
||||
def print_version(self, url):
|
||||
return url.replace('http://news.kathimerini.gr/4dcgi/', 'http://news.kathimerini.gr/4dcgi/4dcgi/')
|
||||
|
||||
|
||||
|
||||
@ -1,14 +1,11 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
||||
__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
www.marca.com
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from calibre.ebooks.BeautifulSoup import Tag
|
||||
|
||||
class Marca(BasicNewsRecipe):
|
||||
title = 'Marca'
|
||||
@ -22,35 +19,30 @@ class Marca(BasicNewsRecipe):
|
||||
use_embedded_content = False
|
||||
delay = 1
|
||||
encoding = 'iso-8859-15'
|
||||
language = 'es'
|
||||
language = 'es_ES'
|
||||
publication_type = 'newsportal'
|
||||
masthead_url = 'http://estaticos.marca.com/deporte/img/v3.0/img_marca-com.png'
|
||||
extra_css = """
|
||||
body{font-family: Tahoma,Geneva,sans-serif}
|
||||
h1,h2,h3,h4,h5,h6{font-family: 'LatoBlack',Tahoma,Geneva,sans-serif}
|
||||
.cab_articulo h4 {font-family: Georgia,"Times New Roman",Times,serif}
|
||||
.antetitulo{text-transform: uppercase}
|
||||
"""
|
||||
|
||||
direction = 'ltr'
|
||||
feeds = [(u'Portada', u'http://estaticos.marca.com/rss/portada.xml')]
|
||||
|
||||
html2lrf_options = [
|
||||
'--comment' , description
|
||||
, '--category' , category
|
||||
, '--publisher', publisher
|
||||
]
|
||||
|
||||
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
|
||||
|
||||
feeds = [(u'Portada', u'http://rss.marca.com/rss/descarga.htm?data2=425')]
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':['cab_articulo','col_izq']})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name=['object','link','script'])
|
||||
,dict(name='div', attrs={'class':['colC','peu']})
|
||||
,dict(name='div', attrs={'class':['utilidades estirar','bloque_int_corr estirar']})
|
||||
keep_only_tags = [dict(name='div', attrs={'class':['cab_articulo','cuerpo_articulo']})]
|
||||
remove_attributes = ['lang']
|
||||
remove_tags = [
|
||||
dict(name=['object','link','script','embed','iframe','meta','base'])
|
||||
,dict(name='div', attrs={'class':'tabs'})
|
||||
]
|
||||
|
||||
remove_tags_after = [dict(name='div', attrs={'class':'bloque_int_corr estirar'})]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
soup.html['dir' ] = self.direction
|
||||
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
|
||||
soup.head.insert(0,mcharset)
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
return soup
|
||||
|
||||
def get_article_url(self, article):
|
||||
return article.get('guid', None)
|
||||
|
||||
|
||||
24
recipes/max_planck.recipe
Normal file
24
recipes/max_planck.recipe
Normal file
@ -0,0 +1,24 @@
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
|
||||
|
||||
title = u'Max-Planck-Inst.'
|
||||
__author__ = 'schuster'
|
||||
oldest_article = 30
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
remove_javascript = True
|
||||
|
||||
remove_tags = [dict(attrs={'class':['box_url', 'print_kontakt']}),
|
||||
dict(id=['skiplinks'])]
|
||||
|
||||
|
||||
|
||||
def print_version(self, url):
|
||||
split_url = url.split("/")
|
||||
print_url = 'http://www.mpg.de/print/' + split_url[3]
|
||||
return print_url
|
||||
|
||||
feeds = [(u'Forschung', u'http://www.mpg.de/de/forschung.rss')]
|
||||
|
||||
@ -71,7 +71,7 @@ class Mediapart(BasicNewsRecipe):
|
||||
br = BasicNewsRecipe.get_browser()
|
||||
if self.username is not None and self.password is not None:
|
||||
br.open('http://www.mediapart.fr/')
|
||||
br.select_form(nr=1)
|
||||
br.select_form(nr=0)
|
||||
br['name'] = self.username
|
||||
br['pass'] = self.password
|
||||
br.submit()
|
||||
|
||||
10
recipes/mens_health.recipe
Normal file
10
recipes/mens_health.recipe
Normal file
@ -0,0 +1,10 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1305636254(BasicNewsRecipe):
|
||||
title = u'Mens Health (US)'
|
||||
language = 'en'
|
||||
__author__ = 'Anonymous'
|
||||
oldest_article = 14
|
||||
max_articles_per_feed = 100
|
||||
|
||||
feeds = [(u'News', u'http://blogs.menshealth.com/health-headlines/feed')]
|
||||
29
recipes/metro_uk.recipe
Normal file
29
recipes/metro_uk.recipe
Normal file
@ -0,0 +1,29 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
class AdvancedUserRecipe1306097511(BasicNewsRecipe):
|
||||
title = u'Metro UK'
|
||||
|
||||
no_stylesheets = True
|
||||
oldest_article = 1
|
||||
max_articles_per_feed = 200
|
||||
|
||||
__author__ = 'Dave Asbury'
|
||||
language = 'en_GB'
|
||||
simultaneous_downloads= 3
|
||||
|
||||
masthead_url = 'http://e-edition.metro.co.uk/images/metro_logo.gif'
|
||||
|
||||
keep_only_tags = [
|
||||
dict(attrs={'class':['img-cnt figure']}),
|
||||
dict(attrs={'class':['art-img']}),
|
||||
dict(name='h1'),
|
||||
dict(name='h2', attrs={'class':'h2'}),
|
||||
dict(name='div', attrs={'class':'art-lft'})
|
||||
]
|
||||
remove_tags = [dict(name='div', attrs={'class':[ 'metroCommentFormWrap',
|
||||
'commentForm', 'metroCommentInnerWrap',
|
||||
'art-rgt','pluck-app pluck-comm','news m12 clrd clr-l p5t', 'flt-r' ]})]
|
||||
|
||||
feeds = [
|
||||
(u'News', u'http://www.metro.co.uk/rss/news/'), (u'Money', u'http://www.metro.co.uk/rss/money/'), (u'Sport', u'http://www.metro.co.uk/rss/sport/'), (u'Film', u'http://www.metro.co.uk/rss/metrolife/film/'), (u'Music', u'http://www.metro.co.uk/rss/metrolife/music/'), (u'TV', u'http://www.metro.co.uk/rss/tv/'), (u'Showbiz', u'http://www.metro.co.uk/rss/showbiz/'), (u'Weird News', u'http://www.metro.co.uk/rss/weird/'), (u'Travel', u'http://www.metro.co.uk/rss/travel/'), (u'Lifestyle', u'http://www.metro.co.uk/rss/lifestyle/'), (u'Books', u'http://www.metro.co.uk/rss/lifestyle/books/'), (u'Food', u'http://www.metro.co.uk/rss/lifestyle/restaurants/')]
|
||||
|
||||
|
||||
71
recipes/natgeo.recipe
Normal file
71
recipes/natgeo.recipe
Normal file
@ -0,0 +1,71 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, gagsays <gagsays at gmail dot com>'
|
||||
'''
|
||||
nationalgeographic.com
|
||||
'''
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
class NatGeo(BasicNewsRecipe):
|
||||
title = u'National Geographic'
|
||||
description = 'Daily news articles from The National Geographic'
|
||||
language = 'en'
|
||||
oldest_article = 20
|
||||
max_articles_per_feed = 25
|
||||
encoding = 'utf8'
|
||||
publisher = 'nationalgeographic.com'
|
||||
category = 'science, nat geo'
|
||||
__author__ = 'gagsays'
|
||||
masthead_url = 'http://s.ngeo.com/wpf/sites/themes/global/i/presentation/ng_logo_small.png'
|
||||
description = 'Inspiring people to care about the planet since 1888'
|
||||
timefmt = ' [%a, %d %b, %Y]'
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
|
||||
extra_css = '''
|
||||
body {color: #000000;font-size: medium;}
|
||||
h1 {color: #222222; font-size: large; font-weight:lighter; text-decoration:none; text-align: center;font-family:Georgia,Times New Roman,Times,serif;}
|
||||
h2 {color: #454545; font-size: small; font-weight:lighter; text-decoration:none; text-align: justify; font-style:italic;font-family :Georgia,Times New Roman,Times,serif;}
|
||||
h3 {color: #555555; font-size: small; font-style:italic; margin-top: 10px;}
|
||||
img{margin-bottom: 0.25em;display:block;margin-left: auto;margin-right: auto;}
|
||||
a:link,a,.a,href {text-decoration: none;color: #000000;}
|
||||
.caption{color: #000000;font-size: xx-small;text-align: justify;font-weight:normal;}
|
||||
.credit{color: #555555;font-size: xx-small;text-align: left;font-weight:lighter;}
|
||||
p.author,p.publication{color: #000000;font-size: xx-small;text-align: left;display:inline;}
|
||||
p.publication_time{color: #000000;font-size: xx-small;text-align: right;text-decoration: underline;}
|
||||
p {margin-bottom: 0;}
|
||||
p + p {text-indent: 1.5em;margin-top: 0;}
|
||||
.hidden{display:none;}
|
||||
#page_head{text-transform:uppercase;}
|
||||
'''
|
||||
|
||||
def parse_feeds (self):
|
||||
feeds = BasicNewsRecipe.parse_feeds(self)
|
||||
for feed in feeds:
|
||||
for article in feed.articles[:]:
|
||||
if 'Presented' in article.title or 'Pictures' in article.title:
|
||||
feed.articles.remove(article)
|
||||
return feeds
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for alink in soup.findAll('a'):
|
||||
if alink.string is not None:
|
||||
tstr = alink.string
|
||||
alink.replaceWith(tstr)
|
||||
return soup
|
||||
|
||||
remove_tags_before = dict(id='page_head')
|
||||
keep_only_tags = [
|
||||
dict(name='div',attrs={'id':['page_head','content_mainA']})
|
||||
]
|
||||
remove_tags_after = [
|
||||
dict(name='div',attrs={'class':['article_text','promo_collection']})
|
||||
]
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':['aside','primary full_width']})
|
||||
,dict(name='div', attrs={'id':['header_search','navigation_mainB_wrap']})
|
||||
]
|
||||
feeds = [
|
||||
(u'Daily News', u'http://feeds.nationalgeographic.com/ng/News/News_Main')
|
||||
]
|
||||
|
||||
25
recipes/national_geographic_de.recipe
Normal file
25
recipes/national_geographic_de.recipe
Normal file
@ -0,0 +1,25 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1305567197(BasicNewsRecipe):
|
||||
title = u'National Geographic (DE)'
|
||||
__author__ = 'Anonymous'
|
||||
language = 'de'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 1000
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_javascript = True
|
||||
cover_url = 'http://www.nationalgeographic.de/images/national-geographic-logo.jpg'
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'class':['contentbox_no_top_border']}) ]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':'related'}),
|
||||
dict(name='li', attrs={'class':'first'}),
|
||||
dict(name='div', attrs={'class':'extrasbox_inner'}),
|
||||
|
||||
]
|
||||
|
||||
feeds = [ (u'National Geographic', u'http://feeds.nationalgeographic.de/ng-neueste-artikel'),
|
||||
|
||||
]
|
||||
@ -11,6 +11,20 @@ class Newsweek(BasicNewsRecipe):
|
||||
|
||||
BASE_URL = 'http://www.newsweek.com'
|
||||
|
||||
topics = {
|
||||
'Culture' : '/tag/culture.html',
|
||||
'Business' : '/tag/business.html',
|
||||
'Society' : '/tag/society.html',
|
||||
'Science' : '/tag/science.html',
|
||||
'Education' : '/tag/education.html',
|
||||
'Politics' : '/tag/politics.html',
|
||||
'Health' : '/tag/health.html',
|
||||
'World' : '/tag/world.html',
|
||||
'Nation' : '/tag/nation.html',
|
||||
'Technology' : '/tag/technology.html',
|
||||
'Game Changers' : '/tag/game-changers.html',
|
||||
}
|
||||
|
||||
keep_only_tags = dict(name='article', attrs={'class':'article-text'})
|
||||
remove_tags = [dict(attrs={'data-dartad':True})]
|
||||
remove_attributes = ['property']
|
||||
@ -21,14 +35,10 @@ class Newsweek(BasicNewsRecipe):
|
||||
return soup
|
||||
|
||||
def newsweek_sections(self):
|
||||
return [
|
||||
('Nation', 'http://www.newsweek.com/tag/nation.html'),
|
||||
('Society', 'http://www.newsweek.com/tag/society.html'),
|
||||
('Culture', 'http://www.newsweek.com/tag/culture.html'),
|
||||
('World', 'http://www.newsweek.com/tag/world.html'),
|
||||
('Politics', 'http://www.newsweek.com/tag/politics.html'),
|
||||
('Business', 'http://www.newsweek.com/tag/business.html'),
|
||||
]
|
||||
for topic_name, topic_url in self.topics.iteritems():
|
||||
yield (topic_name,
|
||||
self.BASE_URL+topic_url)
|
||||
|
||||
|
||||
def newsweek_parse_section_page(self, soup):
|
||||
for article in soup.findAll('article', about=True,
|
||||
@ -59,7 +69,11 @@ class Newsweek(BasicNewsRecipe):
|
||||
for section, shref in self.newsweek_sections():
|
||||
self.log('Processing section', section, shref)
|
||||
articles = []
|
||||
soups = [self.index_to_soup(shref)]
|
||||
try:
|
||||
soups = [self.index_to_soup(shref)]
|
||||
except:
|
||||
self.log.warn('Section %s not found, skipping'%section)
|
||||
continue
|
||||
na = soups[0].find('a', rel='next')
|
||||
if na:
|
||||
soups.append(self.index_to_soup(self.BASE_URL+na['href']))
|
||||
|
||||
29
recipes/ngz.recipe
Normal file
29
recipes/ngz.recipe
Normal file
@ -0,0 +1,29 @@
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
|
||||
|
||||
title = u'NGZ-online'
|
||||
__author__ = 'schuster'
|
||||
remove_tags_before = dict(id='bu')
|
||||
remove_tags_after = dict(id='noblock')
|
||||
remove_tags = [dict(attrs={'class':['articleTools', 'post-tools', 'side_tool', 'nextArticleLink clearfix', 'liketext']}),
|
||||
dict(id=['footer', 'toolsRight', 'articleInline', 'navigation', 'archive', 'side_search', 'blog_sidebar', 'side_tool', 'side_index', 'Verlinken', 'vorheriger', 'LESERKOMMENTARE', 'bei facebook', 'bei twitter', 'Schreiben Sie jetzt Ihre Meinung:', 'Thema', 'Ihr Beitrag', 'Ihr Name', 'Ich möchte über weitere Lesermeinungen zu diesem Artikel per E-Mail informiert werden.', 'banneroben', 'bannerrechts', 'inserieren', 'stellen', 'auto', 'immobilien', 'kleinanzeige', 'tiere', 'ferienwohnung', 'NGZ Card', 'Mediengruppe RP', 'Werben', 'Newsletter', 'Wetter', 'RSS', 'Abo', 'Anzeigen', 'Redaktion', 'Schulprojekte', 'Gast', 'Mein NGZ', 'Nachrichten', 'Sport', 'Wirtschaft', 'Stadt-Infos', 'Bilderserien', 'Bookmarken', 'del.icio.us', 'Mister Wong', 'YiGG', 'Webnews', 'Shortnews', 'Twitter', 'Newsider', 'Facebook', 'StudiVZ/MeinVZ', 'Versenden', 'Drucken']),
|
||||
dict(name=['script', 'noscript', 'style'])]
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
remove_javascript = True
|
||||
cover_url = 'http://www.rhein-kreis-neuss-macht-sport.de/sport/includes/bilder/ngz_logo.jpg'
|
||||
|
||||
def print_version(self, url):
|
||||
return url + '?ot=de.circit.rpo.PopupPageLayout.ot'
|
||||
feeds = [
|
||||
(u'Grevenbroich', u'http://www.ngz-online.de/app/feed/rss/grevenbroich'),
|
||||
(u'Kreis Neuss', u'http://www.ngz-online.de/app/feed/rss/rheinkreisneuss'),
|
||||
(u'Dormagen', u'http://www.ngz-online.de/app/feed/rss/dormagen'),
|
||||
(u'J\xfcchen', u'http://www.ngz-online.de/app/feed/rss/juechen'),
|
||||
(u'Rommerskirchen', u'http://www.ngz-online.de/app/feed/rss/rommerskirchen')
|
||||
|
||||
]
|
||||
|
||||
64
recipes/observatorul_cultural.recipe
Normal file
64
recipes/observatorul_cultural.recipe
Normal file
@ -0,0 +1,64 @@
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
coverpage = None
|
||||
|
||||
class ObservatorulCultural(BasicNewsRecipe):
|
||||
title = u'Observatorul cultural'
|
||||
__author__ = 'song2' #prelucrat dupa un script de http://www.thenowhereman.com
|
||||
encoding = 'utf-8'
|
||||
language = 'ro'
|
||||
publication_type = 'magazine'
|
||||
description = 'Spiritul critic in acţiune\n'
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
masthead_url='http://www.observatorcultural.ro/userfiles/article/sigla%20Observator%20cultural_02231058.JPG'
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'class':'detaliuArticol'})]
|
||||
remove_tags = [dict(name='div', attrs={'class':'comentariiArticol'}),
|
||||
dict(name='div', attrs={'class':'postComment'}),
|
||||
dict(name='div', attrs={'class':'utileArticol'}),
|
||||
dict(name='p', attrs={'class':'butonComenteaza'}),
|
||||
dict(name='h5'),
|
||||
dict(name='div', attrs={'style':'margin-top: 0px; padding-top: 0px;'})
|
||||
]
|
||||
def parse_index(self):
|
||||
soup = self.index_to_soup('http://www.observatorcultural.ro/Arhiva*-archive.html')
|
||||
issueTag = soup.find('a', href=re.compile("observatorcultural.ro\/Numarul"))
|
||||
issueURL = issueTag['href']
|
||||
print issueURL;
|
||||
issueSoup = self.index_to_soup(issueURL)
|
||||
feeds = []
|
||||
stories = []
|
||||
for categorie in issueSoup.findAll('dl',attrs={'class':'continutArhive'}):
|
||||
categ=self.tag_to_string(categorie.find('dt'))
|
||||
for story in categorie.findAll('dd'):
|
||||
title=[]
|
||||
for bucatele in story.findAll('a'):
|
||||
title.append(bucatele)
|
||||
if len(title)==1: #daca articolul nu are autor
|
||||
stories.append({
|
||||
'title' : self.tag_to_string(title[0]),
|
||||
'url' : title[0]['href'],
|
||||
'date' : '',
|
||||
'author' : ''})
|
||||
else: # daca articolul are autor len(title)=2
|
||||
stories.append({
|
||||
'title' : self.tag_to_string(title[1]),
|
||||
'url' :title[1]['href'],
|
||||
'date' : '',
|
||||
'author' : self.tag_to_string(title[0])})
|
||||
print(self.tag_to_string(title[0]))
|
||||
if 'Editorial' in categ:
|
||||
global coverpage
|
||||
coverpage=title[1]['href'] # am luat link-ul spre editorial
|
||||
feeds.append((categ,stories))
|
||||
stories = []
|
||||
print feeds
|
||||
return feeds
|
||||
#procedura de luat coperta
|
||||
def get_cover_url(self):
|
||||
soup = self.index_to_soup(coverpage)
|
||||
link_item = soup.find('a',attrs={'rel':'lightbox'}) # caut imaginea textului
|
||||
a=''
|
||||
cover_url = a.join(link_item.img['src'].split('_details_'))
|
||||
return cover_url
|
||||
35
recipes/polizeipress_de.recipe
Normal file
35
recipes/polizeipress_de.recipe
Normal file
@ -0,0 +1,35 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe(BasicNewsRecipe):
|
||||
|
||||
title = u'Polizeipresse - Deutschland'
|
||||
__author__ = 'schuster'
|
||||
description = 'Tagesaktuelle "Polizeiberichte" aus ganz Deutschland (bis auf Ortsebene).' 'Um deinen Ort/Stadt/Kreis usw. einzubinden, gehe auf "http://www.presseportal.de/polizeipresse/" und suche im oberen "Suchfeld" nach dem Namen.' 'Oberhalb der Suchergebnisse (Folgen:) auf den üblichen link zu den RSS-Feeds klicken und den RSS-link im Rezept unter "feeds" eintragen wie üblich.' 'Die Auswahl von Orten kann vereinfacht werden wenn man den Suchbegriff wie folgt eingibt:' '"Stadt-Ort".'
|
||||
oldest_article = 21
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
remove_javascript = True
|
||||
masthead_url = 'http://www.alt-heliservice.de/images/34_BPOL_Logo_4C_g_schutzbereich.jpg'
|
||||
cover_url = 'http://berlinstadtservice.de/buerger/Bundespolizei-Logo.png'
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'id':'logo'}),
|
||||
dict(name='div', attrs={'id':'origin'}),
|
||||
dict(name='pre', attrs={'class':'xml_contact'})]
|
||||
|
||||
def print_version(self,url):
|
||||
segments = url.split('/')
|
||||
printURL = 'http://www.presseportal.de/print.htx?nr=' + '/'.join(segments[5:6]) + '&type=polizei'
|
||||
return printURL
|
||||
|
||||
feeds = [(u'Frimmerdorf', u'http://www.presseportal.de/rss/rss2_vts.htx?q=Grevenbroich-frimmersdorf&w=public_service'),
|
||||
(u'Neurath', u'http://www.presseportal.de/rss/rss2_vts.htx?q=Grevenbroich-neurath&w=public_service'),
|
||||
(u'Gustorf', u'http://www.presseportal.de/rss/rss2_vts.htx?q=Grevenbroich-gustorf&w=public_service'),
|
||||
(u'Neuenhausen', u'http://www.presseportal.de/rss/rss2_vts.htx?q=Grevenbroich-neuenhausen&w=public_service'),
|
||||
(u'Wevelinghoven', u'http://www.presseportal.de/rss/rss2_vts.htx?q=Grevenbroich-Wevelinghoven&w=public_service'),
|
||||
(u'Grevenbroich ges.', u'http://www.presseportal.de/rss/rss2_vts.htx?q=grevenbroich&w=public_service'),
|
||||
(u'Kreis Neuss ges.', u'http://www.presseportal.de/rss/rss2_vts.htx?q=Rhein-Kreis+Neuss&w=public_service'),
|
||||
]
|
||||
|
||||
22
recipes/pro_physik.recipe
Normal file
22
recipes/pro_physik.recipe
Normal file
@ -0,0 +1,22 @@
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
|
||||
|
||||
title = u'Pro Physik'
|
||||
__author__ = 'schuster'
|
||||
oldest_article = 4
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
remove_javascript = True
|
||||
cover_url = 'http://www.pro-physik.de/Phy/images/site/prophysik_logo1.jpg'
|
||||
|
||||
|
||||
def print_version(self, url):
|
||||
return url.replace('leadArticle.do', 'print.do')
|
||||
|
||||
|
||||
feeds = [(u'Hightech', u'http://www.pro-physik.de/Phy/hightechfeed.xml'),
|
||||
(u'Forschung', u'http://www.pro-physik.de/Phy/forschungfeed.xml'),
|
||||
(u'Magazin', u'http://www.pro-physik.de/Phy/magazinfeed.xml')]
|
||||
|
||||
55
recipes/rheinische_post.recipe
Normal file
55
recipes/rheinische_post.recipe
Normal file
@ -0,0 +1,55 @@
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
class AdvancedUserRecipe(BasicNewsRecipe):
|
||||
|
||||
title = u'RP-online'
|
||||
__author__ = 'schuster'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
remove_javascript = True
|
||||
masthead_url = 'http://www.die-zeitungen.de/uploads/pics/LOGO_RP_ONLINE_01.jpg'
|
||||
cover_url = 'http://www.manroland.com/com/pressinfo_images/com/RheinischePost_Logo_300dpi.jpg'
|
||||
extra_css = '''
|
||||
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
|
||||
h4{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
|
||||
img {min-width:300px; max-width:600px; min-height:300px; max-height:800px}
|
||||
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
||||
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
|
||||
'''
|
||||
remove_tags_before = dict(id='article_content')
|
||||
remove_tags_after = dict(id='article_content')
|
||||
remove_tags = [dict(attrs={'class':['goodies', 'left', 'right', 'clear-all', 'teaser anzeigenwerbung', 'lesermeinung', 'goodiebox', 'goodiebox 1', 'goodiebox 2', 'goodiebox 3', 'boxframe', 'link']}),
|
||||
dict(id=['click_Fotos_link']),
|
||||
dict(name=['script', 'noscript', 'style', '_top', 'click_Fotos_link'])]
|
||||
|
||||
feeds = [ (u'Top-News', u'http://www.ngz-online.de/app/feed/rss/topnews'),
|
||||
(u'Politik', u'http://www.ngz-online.de/app/feed/rss/politik'),
|
||||
(u'Wirtschaft', u'http://www.ngz-online.de/app/feed/rss/wirtschaft'),
|
||||
(u'Panorama', u'http://www.ngz-online.de/app/feed/rss/panorama'),
|
||||
(u'Sport', u'http://www.ngz-online.de/app/feed/rss/sport'),
|
||||
(u'Tour de France', u'http://www.ngz-online.de/app/feed/rss/tourdefrance'),
|
||||
(u'Fußball', u'http://www.ngz-online.de/app/feed/rss/fussball'),
|
||||
(u'Fußball BuLi', u'http://www.ngz-online.de/app/feed/rss/bundesliga'),
|
||||
(u'Formel 1', u'http://www.ngz-online.de/app/feed/rss/formel1'),
|
||||
(u'US-Sport', u'http://www.ngz-online.de/app/feed/rss/us-sports'),
|
||||
(u'Boxen', u'http://www.ngz-online.de/app/feed/rss/boxen'),
|
||||
(u'Eishockey', u'http://www.ngz-online.de/app/feed/rss/eishockey'),
|
||||
(u'Basketball', u'http://www.ngz-online.de/app/feed/rss/basketball'),
|
||||
(u'Handball', u'http://www.ngz-online.de/app/feed/rss/handball'),
|
||||
(u'Motorsport', u'http://www.ngz-online.de/app/feed/rss/motorsport'),
|
||||
(u'Tennis', u'http://www.ngz-online.de/app/feed/rss/tennis'),
|
||||
(u'Radsport', u'http://www.ngz-online.de/app/feed/rss/radsport'),
|
||||
(u'Kultur', u'http://www.ngz-online.de/app/feed/rss/kultur'),
|
||||
(u'Gesellschaft', u'http://www.ngz-online.de/app/feed/rss/gesellschaft'),
|
||||
(u'Wissenschaft', u'http://www.ngz-online.de/app/feed/rss/wissen'),
|
||||
(u'Gesundheit', u'http://www.ngz-online.de/app/feed/rss/gesundheit'),
|
||||
(u'Digitale Welt', u'http://www.ngz-online.de/app/feed/rss/digitale'),
|
||||
(u'Auto & Mobil', u'http://www.ngz-online.de/app/feed/rss/auto'),
|
||||
(u'Reise & Welt', u'http://www.ngz-online.de/app/feed/rss/reise'),
|
||||
(u'Beruf & Karriere', u'http://www.ngz-online.de/app/feed/rss/beruf'),
|
||||
(u'Herzrasen', u'http://www.ngz-online.de/app/feed/rss/herzrasen'),
|
||||
(u'About a Boy', u'http://www.ngz-online.de/app/feed/rss/about_a_boy'),
|
||||
|
||||
]
|
||||
@ -1,52 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'Mori'
|
||||
__version__ = 'v. 0.1'
|
||||
'''
|
||||
www.runa.pl/blog
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
import re
|
||||
|
||||
class FantazmatyRecipe(BasicNewsRecipe):
|
||||
__author__ = 'Mori'
|
||||
language = 'pl'
|
||||
|
||||
title = u'Fantazmaty'
|
||||
publisher = u'Agencja Wydawnicza Runa'
|
||||
description = u'Blog Agencji Wydawniczej Runa'
|
||||
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
encoding = 'utf-8'
|
||||
|
||||
oldest_article = 100
|
||||
max_articles_per_feed = 100
|
||||
|
||||
extra_css = '''
|
||||
img{float: left; padding-right: 10px; padding-bottom: 5px;}
|
||||
'''
|
||||
|
||||
feeds = [
|
||||
(u'Fantazmaty', u'http://www.runa.pl/blog/rss.xml')
|
||||
]
|
||||
|
||||
remove_tags = [
|
||||
dict(name = 'div', attrs = {'class' : 'path'}),
|
||||
dict(name = 'div', attrs = {'class' : 'drdot'}),
|
||||
dict(name = 'div', attrs = {'class' : 'picture'})
|
||||
]
|
||||
|
||||
remove_tags_after = [
|
||||
dict(name = 'div', attrs = {'class' : 'content'})
|
||||
]
|
||||
|
||||
preprocess_regexps = [
|
||||
(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
|
||||
[
|
||||
(r'<body>.*?<div id="primary"', lambda match: '<body><div id="primary"'),
|
||||
(r'<!--.*?-->', lambda match: '')
|
||||
]
|
||||
]
|
||||
28
recipes/spektrum.recipe
Normal file
28
recipes/spektrum.recipe
Normal file
@ -0,0 +1,28 @@
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
|
||||
title = u'Spektrum (der Wissenschaft)'
|
||||
__author__ = 'schuster'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
language = 'de'
|
||||
cover_url = 'http://upload.wikimedia.org/wikipedia/de/3/3b/Spektrum_der_Wissenschaft_Logo.svg'
|
||||
|
||||
remove_tags = [dict(attrs={'class':['hauptnaviPkt gainlayout', 'hauptnaviButton', 'suchButton', 'suchbegriffKasten', 'loginButton', 'subnavigation', 'artikelInfoLeiste gainlayout', 'artikelTools', 'nurLetzteSeite', 'link', 'boxUnterArtikel', 'leserbriefeBlock', 'boxTitel', 'boxInhalt', 'sehrklein', 'boxabstand', 'werbeboxinhalt', 'rbabstand', 'bildlinks', 'rechtebox', 'denkmalbox', 'denkmalfrage']}),
|
||||
dict(id=['pflip', 'verlagsleiste', 'bereich', 'bannerVertikal', 'headerLogoLink', 'kopf', 'topNavi', 'headerSchnellsuche', 'headerSchnellsucheWarten', 'navigation', 'navigationL', 'navigationR', 'inhalt', 'rechtespalte', 'sdwboxenshop', 'shopboxen', 'fuss']),
|
||||
dict(name=['naservice'])]
|
||||
|
||||
def print_version(self,url):
|
||||
newurl = url.replace('artikel/', 'sixcms/detail.php?id=')
|
||||
return newurl + '&_druckversion=1'
|
||||
|
||||
|
||||
|
||||
feeds = [(u'Spektrum der Wissenschaft', u'http://www.spektrum.de/artikel/982623'),
|
||||
(u'SpektrumDirekt', u'http://www.spektrumdirekt.de/artikel/996406'),
|
||||
(u'Sterne und Weltraum', u'http://www.astronomie-heute.de/artikel/865248'),
|
||||
(u'Gehirn & Geist', u'http://www.gehirn-und-geist.de/artikel/982626'),
|
||||
(u'epoc', u'http://www.epoc.de/artikel/982625')
|
||||
|
||||
]
|
||||
|
||||
filter_regexps = [r'ads\.doubleclick\.net']
|
||||
24
recipes/technology_review_de.recipe
Normal file
24
recipes/technology_review_de.recipe
Normal file
@ -0,0 +1,24 @@
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
|
||||
|
||||
title = u'Technology Review'
|
||||
__author__ = 'schuster'
|
||||
remove_tags_before = dict(id='keywords')
|
||||
remove_tags_after = dict(id='kommentar')
|
||||
remove_tags = [dict(attrs={'class':['navi_oben_pvg', 'navi_oben_tarifr', 'navi_oben_itm', 'navi_oben_eve', 'navi_oben_whi', 'navi_oben_abo', 'navi_oben_shop', 'navi_top_logo', 'navi_top_abschnitt', 'first']}),
|
||||
dict(id=['footer', 'toolsRight', 'articleInline', 'navigation', 'archive', 'side_search', 'blog_sidebar', 'side_tool', 'side_index']),
|
||||
dict(name=['script', 'noscript', 'style'])]
|
||||
oldest_article = 4
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
language = 'de'
|
||||
remove_javascript = True
|
||||
|
||||
def print_version(self, url):
|
||||
return url + '?view=print'
|
||||
|
||||
|
||||
feeds = [
|
||||
(u'Technik News', u'http://www.heise.de/tr/news-atom.xml') ]
|
||||
|
||||
@ -49,6 +49,7 @@ class TelegraphUK(BasicNewsRecipe):
|
||||
(u'UK News' , u'http://www.telegraph.co.uk/news/uknews/rss' )
|
||||
,(u'World News' , u'http://www.telegraph.co.uk/news/worldnews/rss' )
|
||||
,(u'Politics' , u'http://www.telegraph.co.uk/news/newstopics/politics/rss' )
|
||||
,(u'Finance' , u'http://www.telegraph.co.uk/finance/rss' )
|
||||
,(u'Technology News', u'http://www.telegraph.co.uk/scienceandtechnology/technology/technologynews/rss' )
|
||||
,(u'UK News' , u'http://www.telegraph.co.uk/scienceandtechnology/technology/technologyreviews/rss')
|
||||
,(u'Science News' , u'http://www.telegraph.co.uk/scienceandtechnology/science/sciencenews/rss' )
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2008 - 2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
__copyright__ = '2008 - 2011, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
thenation.com
|
||||
'''
|
||||
@ -16,10 +16,17 @@ class Thenation(BasicNewsRecipe):
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
language = 'en'
|
||||
use_embedded_content = False
|
||||
delay = 1
|
||||
masthead_url = 'http://www.thenation.com/sites/default/themes/thenation/images/logo-main.gif'
|
||||
exra_css = ' body{font-family: Arial,Helvetica,sans-serif;} .print-created{font-size: small;} .caption{display: block; font-size: x-small;} '
|
||||
use_embedded_content = False
|
||||
delay = 1
|
||||
masthead_url = 'http://www.thenation.com/sites/default/themes/thenation/images/logo-main.gif'
|
||||
login_url = 'http://www.thenation.com/user?destination=%3Cfront%3E'
|
||||
publication_type = 'magazine'
|
||||
needs_subscription = 'optional'
|
||||
exra_css = """
|
||||
body{font-family: Arial,Helvetica,sans-serif;}
|
||||
.print-created{font-size: small;}
|
||||
.caption{display: block; font-size: x-small;}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
@ -28,13 +35,30 @@ class Thenation(BasicNewsRecipe):
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
keep_only_tags = [ dict(attrs={'class':['print-title','print-created','print-content','print-links']}) ]
|
||||
remove_tags = [dict(name='link')]
|
||||
keep_only_tags = [dict(attrs={'class':['print-title','print-created','print-content','print-links']})]
|
||||
remove_tags = [dict(name=['link','iframe','base','meta','object','embed'])]
|
||||
remove_attributes = ['lang']
|
||||
|
||||
feeds = [(u"Editor's Picks", u'http://www.thenation.com/rss/editors_picks')]
|
||||
feeds = [(u"Articles", u'http://www.thenation.com/rss/articles')]
|
||||
|
||||
def print_version(self, url):
|
||||
return url.replace('.thenation.com/','.thenation.com/print/')
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
return self.adeify_images(soup)
|
||||
def get_browser(self):
|
||||
br = BasicNewsRecipe.get_browser()
|
||||
br.open('http://www.thenation.com/')
|
||||
if self.username is not None and self.password is not None:
|
||||
br.open(self.login_url)
|
||||
br.select_form(nr=1)
|
||||
br['name'] = self.username
|
||||
br['pass'] = self.password
|
||||
br.submit()
|
||||
return br
|
||||
|
||||
def get_cover_url(self):
|
||||
soup = self.index_to_soup('http://www.thenation.com/issue/')
|
||||
item = soup.find('div',attrs={'id':'cover-wrapper'})
|
||||
if item:
|
||||
return item.img['src']
|
||||
return None
|
||||
|
||||
@ -10,8 +10,8 @@ import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Time(BasicNewsRecipe):
|
||||
recipe_disabled = ('This recipe has been disabled as TIME no longer'
|
||||
' publish complete articles on the web.')
|
||||
#recipe_disabled = ('This recipe has been disabled as TIME no longer'
|
||||
# ' publish complete articles on the web.')
|
||||
title = u'Time'
|
||||
__author__ = 'Kovid Goyal and Sujata Raman'
|
||||
description = 'Weekly magazine'
|
||||
|
||||
@ -14,6 +14,7 @@ class UnitedDaily(BasicNewsRecipe):
|
||||
(u'生活', u'http://udn.com/udnrss/life.xml'),
|
||||
(u'綜合', u'http://udn.com/udnrss/education.xml'),
|
||||
(u'意見評論', u'http://udn.com/udnrss/opinion.xml'),
|
||||
(u'校園博覽會', u'http://mag.udn.com/udnrss/campus_rss.xml'),
|
||||
(u'大台北', u'http://udn.com/udnrss/local_taipei.xml'),
|
||||
(u'桃竹苗', u'http://udn.com/udnrss/local_tyhcml.xml'),
|
||||
(u'中彰投', u'http://udn.com/udnrss/local_tcchnt.xml'),
|
||||
@ -21,15 +22,21 @@ class UnitedDaily(BasicNewsRecipe):
|
||||
(u'高屏離島', u'http://udn.com/udnrss/local_ksptisland.xml'),
|
||||
(u'基宜花東', u'http://udn.com/udnrss/local_klilhltt.xml'),
|
||||
(u'台灣百寶鄉', u'http://udn.com/udnrss/local_oddlyenough.xml'),
|
||||
(u'台灣人物', u'http://mag.udn.com/udnrss/people_rss.xml'),
|
||||
(u'兩岸要聞', u'http://udn.com/udnrss/mainland.xml'),
|
||||
(u'國際焦點', u'http://udn.com/udnrss/international.xml'),
|
||||
(u'台商經貿', u'http://udn.com/udnrss/financechina.xml'),
|
||||
(u'國際財經', u'http://udn.com/udnrss/financeworld.xml'),
|
||||
(u'全球觀察', u'http://mag.udn.com/udnrss/world_rss.xml'),
|
||||
(u'財經焦點', u'http://udn.com/udnrss/financesfocus.xml'),
|
||||
(u'股市要聞', u'http://udn.com/udnrss/stock.xml'),
|
||||
(u'股市快訊', u'http://udn.com/udnrss/stklatest.xml'),
|
||||
(u'稅務法務', u'http://udn.com/udnrss/tax.xml'),
|
||||
(u'房市情報', u'http://udn.com/udnrss/houses.xml'),
|
||||
(u'個人理財', u'http://mag.udn.com/udnrss/wealth_rss.xml'),
|
||||
(u'研究報告', u'http://mag.udn.com/udnrss/report_rss.xml'),
|
||||
(u'基金', u'http://mag.udn.com/udnrss/fund_rss.xml'),
|
||||
(u'理財會客室', u'http://mag.udn.com/udnrss/m_forum_rss.xml'),
|
||||
(u'棒球', u'http://udn.com/udnrss/baseball.xml'),
|
||||
(u'籃球', u'http://udn.com/udnrss/basketball.xml'),
|
||||
(u'體壇動態', u'http://udn.com/udnrss/sportsfocus.xml'),
|
||||
@ -40,19 +47,24 @@ class UnitedDaily(BasicNewsRecipe):
|
||||
(u'電影世界', u'http://udn.com/udnrss/movie.xml'),
|
||||
(u'流行音樂', u'http://udn.com/udnrss/music.xml'),
|
||||
(u'觀點專題', u'http://udn.com/udnrss/starssubject.xml'),
|
||||
(u'消費流行', u'http://mag.udn.com/udnrss/happylife_rss.xml'),
|
||||
(u'食樂指南', u'http://udn.com/udnrss/food.xml'),
|
||||
(u'數位資訊', u'http://mag.udn.com/udnrss/digital_rss.xml'),
|
||||
(u'折扣好康', u'http://udn.com/udnrss/shopping.xml'),
|
||||
(u'發燒車訊', u'http://mag.udn.com/udnrss/car_rss.xml'),
|
||||
(u'醫藥新聞', u'http://udn.com/udnrss/health.xml'),
|
||||
(u'家婦繽紛', u'http://udn.com/udnrss/benfen.xml'),
|
||||
(u'談星論命', u'http://udn.com/udnrss/astrology.xml'),
|
||||
(u'文化副刊', u'http://udn.com/udnrss/reading.xml'),
|
||||
(u'旅遊休閒', u'http://travel.udn.com/udnrss/travel_rss.xml'),
|
||||
(u'健康醫藥', u'http://mag.udn.com/udnrss/life_rss.xml'),
|
||||
]
|
||||
|
||||
extra_css = '''div[id='story_title'] {font-size:200%; font-weight:bold;}'''
|
||||
extra_css = '''div[id='story_title'] {font-size:200%; font-weight:bold;} td[class='story_title'] {font-size:200%; font-weight:bold;} td[class='story_title'] td[class='story_title']>div {font-size:200%; font-weight:bold;}'''
|
||||
|
||||
__author__ = 'Eddie Lau'
|
||||
__version__ = '1.0'
|
||||
language = 'zh'
|
||||
__version__ = '1.1'
|
||||
language = 'zh-TW'
|
||||
publisher = 'United Daily News Group'
|
||||
description = 'United Daily (Taiwan)'
|
||||
category = 'News, Chinese, Taiwan'
|
||||
@ -63,5 +75,12 @@ class UnitedDaily(BasicNewsRecipe):
|
||||
conversion_options = {'linearize_tables':True}
|
||||
masthead_url = 'http://udn.com/NEWS/2004/images/logo_udn.gif'
|
||||
cover_url = 'http://udn.com/NEWS/2004/images/logo_udn.gif'
|
||||
keep_only_tags = [dict(name='div', attrs={'id':['story_title','story_author', 'story']})]
|
||||
keep_only_tags = [dict(name='td', attrs={'class':['story_title']}),
|
||||
dict(name='div', attrs={'id':['story_title']}),
|
||||
dict(name='td', attrs={'class':['story_author']}),
|
||||
dict(name='div', attrs={'id':['story_author']}),
|
||||
dict(name='td', attrs={'class':['story']}),
|
||||
dict(name='div', attrs={'id':['story']}),
|
||||
]
|
||||
remove_tags = [dict(name='div', attrs={'id':['mvouter']})]
|
||||
|
||||
|
||||
64
recipes/version2.recipe
Normal file
64
recipes/version2.recipe
Normal file
@ -0,0 +1,64 @@
|
||||
import re
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Rasmus Lauritsen <rasmus at lauritsen.info>'
|
||||
'''
|
||||
version2.dk
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class version2(BasicNewsRecipe):
|
||||
title = 'Version2.dk'
|
||||
__author__ = 'Rasmus Lauritsen'
|
||||
description = 'IT News'
|
||||
publisher = 'version2.dk'
|
||||
category = 'news, IT, hardware, software, Denmark'
|
||||
oldest_article = 14
|
||||
max_articles_per_feed = 50
|
||||
no_stylesheets = True
|
||||
remove_empty_feeds = True
|
||||
use_embedded_content = False
|
||||
encoding = 'iso-8859-1'
|
||||
language = 'da'
|
||||
|
||||
extra_css = """
|
||||
body {font-family: "Verdana",Times,serif}
|
||||
.articleauthor{color: #9F9F9F;
|
||||
font-family: Arial, sans-serif;
|
||||
font-size: small;
|
||||
text-transform: uppercase}
|
||||
.rubric,.dd,h6#credit{color: #CD0021;
|
||||
font-family: Arial, sans-serif;
|
||||
font-size: small;
|
||||
text-transform: uppercase}
|
||||
.descender:first-letter{display: inline; font-size: xx-large; font-weight: bold}
|
||||
.dd,h6#credit{color: gray}
|
||||
.c{display: block}
|
||||
.caption,h2#articleintro{font-style: italic}
|
||||
.caption{font-size: small}
|
||||
"""
|
||||
|
||||
preprocess_regexps = [ (re.compile(r'</?a[^>]*>'),lambda match: ''),
|
||||
(re.compile(r'<span[^>]*article-link-id.*?<br\s*\/?><br\s*\/?>'), lambda match: '')]
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'article'})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='p',attrs={'class':'meta links'}),
|
||||
dict(name='div',attrs={'class':'float-right'}),
|
||||
dict(name='span',attrs={'class':'article-link-id'})
|
||||
]
|
||||
|
||||
feeds = [
|
||||
(u'Seneste nyheder' , u'http://www.version2.dk/feeds/nyheder')
|
||||
,(u'Forretningssoftware' , u'http://www.version2.dk/feeds/forretningssoftware')
|
||||
,(u'Internet & styresystemer' , u'http://www.version2.dk/feeds/styresystemer')
|
||||
,(u'It-arkitektur' , u'http://www.version2.dk/feeds/it-arkitektur')
|
||||
,(u'It-styring & outsourcing' , u'http://www.version2.dk/feeds/it-styring')
|
||||
,(u'Job & karriere' , u'http://www.version2.dk/feeds/karriere')
|
||||
,(u'Mobil it & tele' , u'http://www.version2.dk/feeds/tele')
|
||||
,(u'Server/storage & netværk' , u'http://www.version2.dk/feeds/server-storage')
|
||||
,(u'Sikkerhed' , u'http://www.version2.dk/feeds/sikkerhed')
|
||||
,(u'Softwareudvikling' , u'http://www.version2.dk/feeds/softwareudvikling')
|
||||
]
|
||||
@ -1,64 +1,75 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
www.washingtonpost.com
|
||||
'''
|
||||
|
||||
from calibre import strftime
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class TheWashingtonPost(BasicNewsRecipe):
|
||||
title = 'The Washington Post'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'Leading source for news, video and opinion on politics, business, world and national news, science, travel, entertainment and more. Our local coverage includes reporting on education, crime, weather, traffic, real estate, jobs and cars for DC, Maryland and Virginia. Offering award-winning opinion writing, entertainment information and restaurant reviews.'
|
||||
publisher = 'The Washington Post Company'
|
||||
category = 'news, politics, USA'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 200
|
||||
no_stylesheets = True
|
||||
encoding = 'utf8'
|
||||
delay = 1
|
||||
use_embedded_content = False
|
||||
language = 'en'
|
||||
remove_empty_feeds = True
|
||||
publication_type = 'newspaper'
|
||||
masthead_url = 'http://www.washingtonpost.com/rw/sites/twpweb/img/logos/twp_logo_300.gif'
|
||||
cover_url = strftime('http://www.washingtonpost.com/rw/WashingtonPost/Content/Epaper/%Y-%m-%d/Ax1.pdf')
|
||||
extra_css = """
|
||||
body{font-family: Georgia,serif }
|
||||
"""
|
||||
|
||||
class WashingtonPost(BasicNewsRecipe):
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : category
|
||||
, 'publisher' : publisher
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
title = 'Washington Post'
|
||||
description = 'US political news'
|
||||
__author__ = 'Kovid Goyal'
|
||||
use_embedded_content = False
|
||||
max_articles_per_feed = 20
|
||||
language = 'en'
|
||||
encoding = 'utf-8'
|
||||
keep_only_tags = [dict(attrs={'id':['content','entryhead','entrytext']})]
|
||||
remove_tags = [
|
||||
dict(name=['meta','link','iframe','base'])
|
||||
,dict(attrs={'id':'multimedia-leaf-page'})
|
||||
]
|
||||
remove_attributes= ['lang','property','epochtime','datetitle','pagetype','contenttype','comparetime']
|
||||
|
||||
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
|
||||
feeds = [
|
||||
('Politics', 'http://www.washingtonpost.com/rss/politics'),
|
||||
('Nation', 'http://www.washingtonpost.com/rss/national'),
|
||||
('World', 'http://www.washingtonpost.com/rss/world'),
|
||||
('Business', 'http://www.washingtonpost.com/rss/business'),
|
||||
('Lifestyle', 'http://www.washingtonpost.com/rss/lifestyle'),
|
||||
('Sports', 'http://www.washingtonpost.com/rss/sports'),
|
||||
('Redskins', 'http://www.washingtonpost.com/rss/sports/redskins'),
|
||||
('Opinions', 'http://www.washingtonpost.com/rss/opinions'),
|
||||
('Entertainment', 'http://www.washingtonpost.com/rss/entertainment'),
|
||||
('Local', 'http://www.washingtonpost.com/rss/local'),
|
||||
('Investigations',
|
||||
'http://www.washingtonpost.com/rss/investigations'),
|
||||
]
|
||||
|
||||
remove_tags = [
|
||||
{'class':lambda x: x and 'article-toolbar' in x},
|
||||
{'class':lambda x: x and 'quick-comments' in x},
|
||||
{'class':lambda x: x and 'tweet' in x},
|
||||
{'class':lambda x: x and 'article-related' in x},
|
||||
{'class':lambda x: x and 'hidden' in x.split()},
|
||||
{'class':lambda x: x and 'also-read' in x.split()},
|
||||
{'class':lambda x: x and 'partners-content' in x.split()},
|
||||
{'class':['module share', 'module ads', 'comment-vars', 'hidden',
|
||||
'share-icons-wrap', 'comments', 'flipper']},
|
||||
{'id':['right-rail', 'save-and-share']},
|
||||
{'width':'1', 'height':'1'},
|
||||
|
||||
]
|
||||
|
||||
keep_only_tags = dict(id=['content', 'article'])
|
||||
|
||||
def get_article_url(self, *args):
|
||||
ans = BasicNewsRecipe.get_article_url(self, *args)
|
||||
ans = ans.rpartition('?')[0]
|
||||
if ans.endswith('_video.html'):
|
||||
return None
|
||||
if 'ads.pheedo.com' in ans:
|
||||
return None
|
||||
#if not ans.endswith('_blog.html'):
|
||||
# return None
|
||||
return ans
|
||||
|
||||
(u'World' , u'http://feeds.washingtonpost.com/rss/world' )
|
||||
,(u'National' , u'http://feeds.washingtonpost.com/rss/national' )
|
||||
,(u'White House' , u'http://feeds.washingtonpost.com/rss/politics/whitehouse' )
|
||||
,(u'Business' , u'http://feeds.washingtonpost.com/rss/business' )
|
||||
,(u'Opinions' , u'http://feeds.washingtonpost.com/rss/opinions' )
|
||||
,(u'Investigations' , u'http://feeds.washingtonpost.com/rss/investigations' )
|
||||
,(u'Local' , u'http://feeds.washingtonpost.com/rss/local' )
|
||||
,(u'Entertainment' , u'http://feeds.washingtonpost.com/rss/entertainment' )
|
||||
,(u'Sports' , u'http://feeds.washingtonpost.com/rss/sports' )
|
||||
,(u'Redskins' , u'http://feeds.washingtonpost.com/rss/sports/redskins' )
|
||||
,(u'Special Reports', u'http://feeds.washingtonpost.com/rss/national/special-reports')
|
||||
]
|
||||
|
||||
def print_version(self, url):
|
||||
return url.replace('_story.html', '_singlePage.html')
|
||||
if '_story.html' in url:
|
||||
return url.replace('_story.html','_print.html')
|
||||
return url
|
||||
|
||||
def get_article_url(self, article):
|
||||
link = BasicNewsRecipe.get_article_url(self,article)
|
||||
if not 'washingtonpost.com' in link:
|
||||
self.log('Skipping adds:', link)
|
||||
return None
|
||||
for it in ['_video.html','_gallery.html','_links.html']:
|
||||
if it in link:
|
||||
self.log('Skipping non-article:', link)
|
||||
return None
|
||||
return link
|
||||
|
||||
|
||||
@ -82,7 +82,7 @@ class ZAOBAO(BasicNewsRecipe):
|
||||
return soup
|
||||
|
||||
def parse_feeds(self):
|
||||
self.log_debug(_('ZAOBAO overrided parse_feeds()'))
|
||||
self.log(_('ZAOBAO overrided parse_feeds()'))
|
||||
parsed_feeds = BasicNewsRecipe.parse_feeds(self)
|
||||
|
||||
for id, obj in enumerate(self.INDEXES):
|
||||
@ -99,7 +99,7 @@ class ZAOBAO(BasicNewsRecipe):
|
||||
a_title = self.tag_to_string(a)
|
||||
date = ''
|
||||
description = ''
|
||||
self.log_debug(_('adding %s at %s')%(a_title,a_url))
|
||||
self.log(_('adding %s at %s')%(a_title,a_url))
|
||||
articles.append({
|
||||
'title':a_title,
|
||||
'date':date,
|
||||
@ -110,23 +110,23 @@ class ZAOBAO(BasicNewsRecipe):
|
||||
pfeeds = feeds_from_index([(title, articles)], oldest_article=self.oldest_article,
|
||||
max_articles_per_feed=self.max_articles_per_feed)
|
||||
|
||||
self.log_debug(_('adding %s to feed')%(title))
|
||||
self.log(_('adding %s to feed')%(title))
|
||||
for feed in pfeeds:
|
||||
self.log_debug(_('adding feed: %s')%(feed.title))
|
||||
self.log(_('adding feed: %s')%(feed.title))
|
||||
feed.description = self.DESC_SENSE
|
||||
parsed_feeds.append(feed)
|
||||
for a, article in enumerate(feed):
|
||||
self.log_debug(_('added article %s from %s')%(article.title, article.url))
|
||||
self.log_debug(_('added feed %s')%(feed.title))
|
||||
self.log(_('added article %s from %s')%(article.title, article.url))
|
||||
self.log(_('added feed %s')%(feed.title))
|
||||
|
||||
for i, feed in enumerate(parsed_feeds):
|
||||
# workaorund a strange problem: Somethimes the xml encoding is not apllied correctly by parse()
|
||||
weired_encoding_detected = False
|
||||
if not isinstance(feed.description, unicode) and self.encoding and feed.description:
|
||||
self.log_debug(_('Feed %s is not encoded correctly, manually replace it')%(feed.title))
|
||||
self.log(_('Feed %s is not encoded correctly, manually replace it')%(feed.title))
|
||||
feed.description = feed.description.decode(self.encoding, 'replace')
|
||||
elif feed.description.find(self.DESC_SENSE) == -1 and self.encoding and feed.description:
|
||||
self.log_debug(_('Feed %s is weired encoded, manually redo all')%(feed.title))
|
||||
self.log(_('Feed %s is weired encoded, manually redo all')%(feed.title))
|
||||
feed.description = feed.description.encode('cp1252', 'replace').decode(self.encoding, 'replace')
|
||||
weired_encoding_detected = True
|
||||
|
||||
@ -148,7 +148,7 @@ class ZAOBAO(BasicNewsRecipe):
|
||||
article.text_summary = article.text_summary.encode('cp1252', 'replace').decode(self.encoding, 'replace')
|
||||
|
||||
if article.title == "Untitled article":
|
||||
self.log_debug(_('Removing empty article %s from %s')%(article.title, article.url))
|
||||
self.log(_('Removing empty article %s from %s')%(article.title, article.url))
|
||||
# remove the article
|
||||
feed.articles[a:a+1] = []
|
||||
return parsed_feeds
|
||||
|
||||
@ -37,18 +37,23 @@ series_index_auto_increment = 'next'
|
||||
# Can be either True or False
|
||||
authors_completer_append_separator = False
|
||||
|
||||
|
||||
#: Author sort name algorithm
|
||||
# The algorithm used to copy author to author_sort
|
||||
# Possible values are:
|
||||
# invert: use "fn ln" -> "ln, fn" (the default algorithm)
|
||||
# invert: use "fn ln" -> "ln, fn"
|
||||
# copy : copy author to author_sort without modification
|
||||
# comma : use 'copy' if there is a ',' in the name, otherwise use 'invert'
|
||||
# nocomma : "fn ln" -> "ln fn" (without the comma)
|
||||
# When this tweak is changed, the author_sort values stored with each author
|
||||
# must be recomputed by right-clicking on an author in the left-hand tags pane,
|
||||
# selecting 'manage authors', and pressing 'Recalculate all author sort values'.
|
||||
# The author name suffixes are words that are ignored when they occur at the
|
||||
# end of an author name. The case of the suffix is ignored and trailing
|
||||
# periods are automatically handled.
|
||||
author_sort_copy_method = 'comma'
|
||||
author_name_suffixes = ('Jr', 'Sr', 'Inc', 'Ph.D', 'Phd',
|
||||
'MD', 'M.D', 'I', 'II', 'III', 'IV',
|
||||
'Junior', 'Senior')
|
||||
|
||||
#: Use author sort in Tag Browser
|
||||
# Set which author field to display in the tags pane (the list of authors,
|
||||
@ -65,6 +70,15 @@ author_sort_copy_method = 'comma'
|
||||
# categories_use_field_for_author_name = 'author_sort'
|
||||
categories_use_field_for_author_name = 'author'
|
||||
|
||||
#: Completion sort order: choose when to change from lexicographic to ASCII-like
|
||||
# Calibre normally uses locale-dependent lexicographic ordering when showing
|
||||
# completion values. This means that the sort order is correct for the user's
|
||||
# language. However, this can be slow. Performance is improved by switching to
|
||||
# ascii ordering. This tweak controls when that switch happens. Set it to zero
|
||||
# to always use ascii ordering. Set it to something larger than zero to switch
|
||||
# to ascii ordering for performance reasons.
|
||||
completion_change_to_ascii_sorting = 2500
|
||||
|
||||
#: Control partitioning of Tag Browser
|
||||
# When partitioning the tags browser, the format of the subcategory label is
|
||||
# controlled by a template: categories_collapsed_name_template if sorting by
|
||||
@ -87,7 +101,6 @@ categories_collapsed_name_template = r'{first.sort:shorten(4,,0)} - {last.sort:s
|
||||
categories_collapsed_rating_template = r'{first.avg_rating:4.2f:ifempty(0)} - {last.avg_rating:4.2f:ifempty(0)}'
|
||||
categories_collapsed_popularity_template = r'{first.count:d} - {last.count:d}'
|
||||
|
||||
|
||||
#: Specify columns to sort the booklist by on startup
|
||||
# Provide a set of columns to be sorted on when calibre starts
|
||||
# The argument is None if saved sort history is to be used
|
||||
@ -238,17 +251,14 @@ sony_collection_name_template='{value}{category:| (|)}'
|
||||
# Default: empty (no rules), so no collection attributes are named.
|
||||
sony_collection_sorting_rules = []
|
||||
|
||||
|
||||
#: Control how tags are applied when copying books to another library
|
||||
# Set this to True to ensure that tags in 'Tags to add when adding
|
||||
# a book' are added when copying books to another library
|
||||
add_new_book_tags_when_importing_books = False
|
||||
|
||||
|
||||
#: Set the maximum number of tags to show per book in the content server
|
||||
max_content_server_tags_shown=5
|
||||
|
||||
|
||||
#: Set custom metadata fields that the content server will or will not display.
|
||||
# content_server_will_display is a list of custom fields to be displayed.
|
||||
# content_server_wont_display is a list of custom fields not to be displayed.
|
||||
@ -290,7 +300,6 @@ generate_cover_foot_font = None
|
||||
# Example: doubleclick_on_library_view = 'do_nothing'
|
||||
doubleclick_on_library_view = 'open_viewer'
|
||||
|
||||
|
||||
#: Language to use when sorting.
|
||||
# Setting this tweak will force sorting to use the
|
||||
# collating order for the specified language. This might be useful if you run
|
||||
@ -345,3 +354,11 @@ send_news_to_device_location = "main"
|
||||
# work on all operating systems)
|
||||
server_listen_on = '0.0.0.0'
|
||||
|
||||
#: Unified toolbar on OS X
|
||||
# If you enable this option and restart calibre, the toolbar will be 'unified'
|
||||
# with the titlebar as is normal for OS X applications. However, doing this has
|
||||
# various bugs, for instance the minimum width of the toolbar becomes twice
|
||||
# what it should be and it causes other random bugs on some systems, so turn it
|
||||
# on at your own risk!
|
||||
unified_title_toolbar_on_osx = False
|
||||
|
||||
|
||||
@ -1,34 +1,43 @@
|
||||
{
|
||||
"contains": "def evaluate(self, formatter, kwargs, mi, locals,\n val, test, value_if_present, value_if_not):\n if re.search(test, val):\n return value_if_present\n else:\n return value_if_not\n",
|
||||
"and": "def evaluate(self, formatter, kwargs, mi, locals, *args):\n i = 0\n while i < len(args):\n if not args[i]:\n return ''\n i += 1\n return '1'\n",
|
||||
"contains": "def evaluate(self, formatter, kwargs, mi, locals,\n val, test, value_if_present, value_if_not):\n if re.search(test, val, flags=re.I):\n return value_if_present\n else:\n return value_if_not\n",
|
||||
"divide": "def evaluate(self, formatter, kwargs, mi, locals, x, y):\n x = float(x if x else 0)\n y = float(y if y else 0)\n return unicode(x / y)\n",
|
||||
"uppercase": "def evaluate(self, formatter, kwargs, mi, locals, val):\n return val.upper()\n",
|
||||
"strcat": "def evaluate(self, formatter, kwargs, mi, locals, *args):\n i = 0\n res = ''\n for i in range(0, len(args)):\n res += args[i]\n return res\n",
|
||||
"substr": "def evaluate(self, formatter, kwargs, mi, locals, str_, start_, end_):\n return str_[int(start_): len(str_) if int(end_) == 0 else int(end_)]\n",
|
||||
"in_list": "def evaluate(self, formatter, kwargs, mi, locals, val, sep, pat, fv, nfv):\n l = [v.strip() for v in val.split(sep) if v.strip()]\n if l:\n for v in l:\n if re.search(pat, v, flags=re.I):\n return fv\n return nfv\n",
|
||||
"not": "def evaluate(self, formatter, kwargs, mi, locals, *args):\n i = 0\n while i < len(args):\n if args[i]:\n return '1'\n i += 1\n return ''\n",
|
||||
"ifempty": "def evaluate(self, formatter, kwargs, mi, locals, val, value_if_empty):\n if val:\n return val\n else:\n return value_if_empty\n",
|
||||
"booksize": "def evaluate(self, formatter, kwargs, mi, locals):\n if mi.book_size is not None:\n try:\n return str(mi.book_size)\n except:\n pass\n return ''\n",
|
||||
"select": "def evaluate(self, formatter, kwargs, mi, locals, val, key):\n if not val:\n return ''\n vals = [v.strip() for v in val.split(',')]\n for v in vals:\n if v.startswith(key+':'):\n return v[len(key)+1:]\n return ''\n",
|
||||
"field": "def evaluate(self, formatter, kwargs, mi, locals, name):\n return formatter.get_value(name, [], kwargs)\n",
|
||||
"strcmp": "def evaluate(self, formatter, kwargs, mi, locals, x, y, lt, eq, gt):\n v = strcmp(x, y)\n if v < 0:\n return lt\n if v == 0:\n return eq\n return gt\n",
|
||||
"first_non_empty": "def evaluate(self, formatter, kwargs, mi, locals, *args):\n i = 0\n while i < len(args):\n if args[i]:\n return args[i]\n i += 1\n return ''\n",
|
||||
"re": "def evaluate(self, formatter, kwargs, mi, locals, val, pattern, replacement):\n return re.sub(pattern, replacement, val, flags=re.I)\n",
|
||||
"subtract": "def evaluate(self, formatter, kwargs, mi, locals, x, y):\n x = float(x if x else 0)\n y = float(y if y else 0)\n return unicode(x - y)\n",
|
||||
"list_item": "def evaluate(self, formatter, kwargs, mi, locals, val, index, sep):\n if not val:\n return ''\n index = int(index)\n val = val.split(sep)\n try:\n return val[index]\n except:\n return ''\n",
|
||||
"shorten": "def evaluate(self, formatter, kwargs, mi, locals,\n val, leading, center_string, trailing):\n l = max(0, int(leading))\n t = max(0, int(trailing))\n if len(val) > l + len(center_string) + t:\n return val[0:l] + center_string + ('' if t == 0 else val[-t:])\n else:\n return val\n",
|
||||
"re": "def evaluate(self, formatter, kwargs, mi, locals, val, pattern, replacement):\n return re.sub(pattern, replacement, val)\n",
|
||||
"field": "def evaluate(self, formatter, kwargs, mi, locals, name):\n return formatter.get_value(name, [], kwargs)\n",
|
||||
"add": "def evaluate(self, formatter, kwargs, mi, locals, x, y):\n x = float(x if x else 0)\n y = float(y if y else 0)\n return unicode(x + y)\n",
|
||||
"lookup": "def evaluate(self, formatter, kwargs, mi, locals, val, *args):\n if len(args) == 2: # here for backwards compatibility\n if val:\n return formatter.vformat('{'+args[0].strip()+'}', [], kwargs)\n else:\n return formatter.vformat('{'+args[1].strip()+'}', [], kwargs)\n if (len(args) % 2) != 1:\n raise ValueError(_('lookup requires either 2 or an odd number of arguments'))\n i = 0\n while i < len(args):\n if i + 1 >= len(args):\n return formatter.vformat('{' + args[i].strip() + '}', [], kwargs)\n if re.search(args[i], val):\n return formatter.vformat('{'+args[i+1].strip() + '}', [], kwargs)\n i += 2\n",
|
||||
"lookup": "def evaluate(self, formatter, kwargs, mi, locals, val, *args):\n if len(args) == 2: # here for backwards compatibility\n if val:\n return formatter.vformat('{'+args[0].strip()+'}', [], kwargs)\n else:\n return formatter.vformat('{'+args[1].strip()+'}', [], kwargs)\n if (len(args) % 2) != 1:\n raise ValueError(_('lookup requires either 2 or an odd number of arguments'))\n i = 0\n while i < len(args):\n if i + 1 >= len(args):\n return formatter.vformat('{' + args[i].strip() + '}', [], kwargs)\n if re.search(args[i], val, flags=re.I):\n return formatter.vformat('{'+args[i+1].strip() + '}', [], kwargs)\n i += 2\n",
|
||||
"template": "def evaluate(self, formatter, kwargs, mi, locals, template):\n template = template.replace('[[', '{').replace(']]', '}')\n return formatter.__class__().safe_format(template, kwargs, 'TEMPLATE', mi)\n",
|
||||
"print": "def evaluate(self, formatter, kwargs, mi, locals, *args):\n print args\n return None\n",
|
||||
"merge_lists": "def evaluate(self, formatter, kwargs, mi, locals, list1, list2, separator):\n l1 = [l.strip() for l in list1.split(separator) if l.strip()]\n l2 = [l.strip() for l in list2.split(separator) if l.strip()]\n lcl1 = set([icu_lower(l) for l in l1])\n res = []\n for i in l1:\n res.append(i)\n for i in l2:\n if icu_lower(i) not in lcl1:\n res.append(i)\n return ', '.join(sorted(res, key=sort_key))\n",
|
||||
"str_in_list": "def evaluate(self, formatter, kwargs, mi, locals, val, sep, str, fv, nfv):\n l = [v.strip() for v in val.split(sep) if v.strip()]\n c = [v.strip() for v in str.split(sep) if v.strip()]\n if l:\n for v in l:\n for t in c:\n if strcmp(t, v) == 0:\n return fv\n return nfv\n",
|
||||
"titlecase": "def evaluate(self, formatter, kwargs, mi, locals, val):\n return titlecase(val)\n",
|
||||
"subitems": "def evaluate(self, formatter, kwargs, mi, locals, val, start_index, end_index):\n if not val:\n return ''\n si = int(start_index)\n ei = int(end_index)\n items = [v.strip() for v in val.split(',')]\n rv = set()\n for item in items:\n component = item.split('.')\n try:\n if ei == 0:\n rv.add('.'.join(component[si:]))\n else:\n rv.add('.'.join(component[si:ei]))\n except:\n pass\n return ', '.join(sorted(rv, key=sort_key))\n",
|
||||
"sublist": "def evaluate(self, formatter, kwargs, mi, locals, val, start_index, end_index, sep):\n if not val:\n return ''\n si = int(start_index)\n ei = int(end_index)\n val = val.split(sep)\n try:\n if ei == 0:\n return sep.join(val[si:])\n else:\n return sep.join(val[si:ei])\n except:\n return ''\n",
|
||||
"test": "def evaluate(self, formatter, kwargs, mi, locals, val, value_if_set, value_not_set):\n if val:\n return value_if_set\n else:\n return value_not_set\n",
|
||||
"eval": "def evaluate(self, formatter, kwargs, mi, locals, template):\n from formatter import eval_formatter\n template = template.replace('[[', '{').replace(']]', '}')\n return eval_formatter.safe_format(template, locals, 'EVAL', None)\n",
|
||||
"multiply": "def evaluate(self, formatter, kwargs, mi, locals, x, y):\n x = float(x if x else 0)\n y = float(y if y else 0)\n return unicode(x * y)\n",
|
||||
"format_date": "def evaluate(self, formatter, kwargs, mi, locals, val, format_string):\n if not val:\n return ''\n try:\n dt = parse_date(val)\n s = format_date(dt, format_string)\n except:\n s = 'BAD DATE'\n return s\n",
|
||||
"format_date": "def evaluate(self, formatter, kwargs, mi, locals, val, format_string):\n if not val or val == 'None':\n return ''\n try:\n dt = parse_date(val)\n s = format_date(dt, format_string)\n except:\n s = 'BAD DATE'\n return s\n",
|
||||
"capitalize": "def evaluate(self, formatter, kwargs, mi, locals, val):\n return capitalize(val)\n",
|
||||
"identifier_in_list": "def evaluate(self, formatter, kwargs, mi, locals, val, ident, fv, nfv):\n l = [v.strip() for v in val.split(',') if v.strip()]\n (id, _, regexp) = ident.partition(':')\n if not id:\n return nfv\n id += ':'\n if l:\n for v in l:\n if v.startswith(id):\n if not regexp or re.search(regexp, v[len(id):], flags=re.I):\n return fv\n return nfv\n",
|
||||
"count": "def evaluate(self, formatter, kwargs, mi, locals, val, sep):\n return unicode(len(val.split(sep)))\n",
|
||||
"lowercase": "def evaluate(self, formatter, kwargs, mi, locals, val):\n return val.lower()\n",
|
||||
"strcmp": "def evaluate(self, formatter, kwargs, mi, locals, x, y, lt, eq, gt):\n v = strcmp(x, y)\n if v < 0:\n return lt\n if v == 0:\n return eq\n return gt\n",
|
||||
"switch": "def evaluate(self, formatter, kwargs, mi, locals, val, *args):\n if (len(args) % 2) != 1:\n raise ValueError(_('switch requires an odd number of arguments'))\n i = 0\n while i < len(args):\n if i + 1 >= len(args):\n return args[i]\n if re.search(args[i], val):\n return args[i+1]\n i += 2\n",
|
||||
"substr": "def evaluate(self, formatter, kwargs, mi, locals, str_, start_, end_):\n return str_[int(start_): len(str_) if int(end_) == 0 else int(end_)]\n",
|
||||
"or": "def evaluate(self, formatter, kwargs, mi, locals, *args):\n i = 0\n while i < len(args):\n if args[i]:\n return '1'\n i += 1\n return ''\n",
|
||||
"switch": "def evaluate(self, formatter, kwargs, mi, locals, val, *args):\n if (len(args) % 2) != 1:\n raise ValueError(_('switch requires an odd number of arguments'))\n i = 0\n while i < len(args):\n if i + 1 >= len(args):\n return args[i]\n if re.search(args[i], val, flags=re.I):\n return args[i+1]\n i += 2\n",
|
||||
"ondevice": "def evaluate(self, formatter, kwargs, mi, locals):\n if mi.ondevice_col:\n return _('Yes')\n return ''\n",
|
||||
"assign": "def evaluate(self, formatter, kwargs, mi, locals, target, value):\n locals[target] = value\n return value\n",
|
||||
"raw_field": "def evaluate(self, formatter, kwargs, mi, locals, name):\n return unicode(getattr(mi, name, None))\n",
|
||||
"cmp": "def evaluate(self, formatter, kwargs, mi, locals, x, y, lt, eq, gt):\n x = float(x if x else 0)\n y = float(y if y else 0)\n if x < y:\n return lt\n if x == y:\n return eq\n return gt\n"
|
||||
"cmp": "def evaluate(self, formatter, kwargs, mi, locals, x, y, lt, eq, gt):\n x = float(x if x and x != 'None' else 0)\n y = float(y if y and y != 'None' else 0)\n if x < y:\n return lt\n if x == y:\n return eq\n return gt\n"
|
||||
}
|
||||
@ -12,7 +12,9 @@ is64bit = platform.architecture()[0] == '64bit'
|
||||
iswindows = re.search('win(32|64)', sys.platform)
|
||||
isosx = 'darwin' in sys.platform
|
||||
isfreebsd = 'freebsd' in sys.platform
|
||||
islinux = not isosx and not iswindows and not isfreebsd
|
||||
isnetbsd = 'netbsd' in sys.platform
|
||||
isbsd = isnetbsd or isfreebsd
|
||||
islinux = not isosx and not iswindows and not isbsd
|
||||
SRC = os.path.abspath('src')
|
||||
sys.path.insert(0, SRC)
|
||||
sys.resources_location = os.path.join(os.path.dirname(SRC), 'resources')
|
||||
|
||||
@ -11,7 +11,7 @@ from distutils import sysconfig
|
||||
|
||||
from PyQt4.pyqtconfig import QtGuiModuleMakefile
|
||||
|
||||
from setup import Command, islinux, isfreebsd, isosx, SRC, iswindows
|
||||
from setup import Command, islinux, isfreebsd, isbsd, isosx, SRC, iswindows
|
||||
from setup.build_environment import fc_inc, fc_lib, chmlib_inc_dirs, \
|
||||
fc_error, poppler_libs, poppler_lib_dirs, poppler_inc_dirs, podofo_inc, \
|
||||
podofo_lib, podofo_error, poppler_error, pyqt, OSX_SDK, NMAKE, \
|
||||
@ -21,7 +21,7 @@ from setup.build_environment import fc_inc, fc_lib, chmlib_inc_dirs, \
|
||||
jpg_lib_dirs, chmlib_lib_dirs, sqlite_inc_dirs, icu_inc_dirs, \
|
||||
icu_lib_dirs
|
||||
MT
|
||||
isunix = islinux or isosx or isfreebsd
|
||||
isunix = islinux or isosx or isbsd
|
||||
|
||||
make = 'make' if isunix else NMAKE
|
||||
|
||||
@ -205,7 +205,7 @@ if islinux:
|
||||
ldflags.append('-lpython'+sysconfig.get_python_version())
|
||||
|
||||
|
||||
if isfreebsd:
|
||||
if isbsd:
|
||||
cflags.append('-pthread')
|
||||
ldflags.append('-shared')
|
||||
cflags.append('-I'+sysconfig.get_python_inc())
|
||||
|
||||
@ -8,7 +8,7 @@ __docformat__ = 'restructuredtext en'
|
||||
|
||||
import sys, os, textwrap, subprocess, shutil, tempfile, atexit, stat, shlex
|
||||
|
||||
from setup import Command, islinux, isfreebsd, basenames, modules, functions, \
|
||||
from setup import Command, islinux, isfreebsd, isbsd, basenames, modules, functions, \
|
||||
__appname__, __version__
|
||||
|
||||
HEADER = '''\
|
||||
@ -116,7 +116,7 @@ class Develop(Command):
|
||||
|
||||
|
||||
def pre_sub_commands(self, opts):
|
||||
if not (islinux or isfreebsd):
|
||||
if not (islinux or isbsd):
|
||||
self.info('\nSetting up a source based development environment is only '
|
||||
'supported on linux. On other platforms, see the User Manual'
|
||||
' for help with setting up a development environment.')
|
||||
@ -156,7 +156,7 @@ class Develop(Command):
|
||||
self.warn('Failed to compile mount helper. Auto mounting of',
|
||||
' devices will not work')
|
||||
|
||||
if not isfreebsd and os.geteuid() != 0:
|
||||
if not isbsd and os.geteuid() != 0:
|
||||
return self.warn('Must be run as root to compile mount helper. Auto '
|
||||
'mounting of devices will not work.')
|
||||
src = os.path.join(self.SRC, 'calibre', 'devices', 'linux_mount_helper.c')
|
||||
@ -168,7 +168,7 @@ class Develop(Command):
|
||||
ret = p.wait()
|
||||
if ret != 0:
|
||||
return warn()
|
||||
if not isfreebsd:
|
||||
if not isbsd:
|
||||
os.chown(dest, 0, 0)
|
||||
os.chmod(dest, stat.S_ISUID|stat.S_ISGID|stat.S_IRUSR|stat.S_IWUSR|\
|
||||
stat.S_IXUSR|stat.S_IXGRP|stat.S_IXOTH)
|
||||
|
||||
@ -32,7 +32,6 @@ class Win32(VMInstaller):
|
||||
FREEZE_TEMPLATE = 'python -OO setup.py {freeze_command} --no-ice'
|
||||
INSTALLER_EXT = 'msi'
|
||||
SHUTDOWN_CMD = ['shutdown.exe', '-s', '-f', '-t', '0']
|
||||
BUILD_BUILD = ['python setup.py kakasi',] + VMInstaller.BUILD_BUILD
|
||||
|
||||
def download_installer(self):
|
||||
installer = self.installer()
|
||||
|
||||
@ -17,6 +17,7 @@
|
||||
IncludeMaximum="yes"
|
||||
OnlyDetect="no"
|
||||
Language="1033"
|
||||
MigrateFeatures="yes"
|
||||
Property="OLDPRODUCTFOUND"/>
|
||||
<UpgradeVersion Minimum="{version}"
|
||||
IncludeMinimum="no"
|
||||
@ -26,6 +27,11 @@
|
||||
</Upgrade>
|
||||
<CustomAction Id="PreventDowngrading" Error="Newer version already installed."/>
|
||||
|
||||
<Property Id="APPLICATIONFOLDER">
|
||||
<RegistrySearch Id='calibreInstDir' Type='raw'
|
||||
Root='HKLM' Key="Software\{app}\Installer" Name="InstallPath" />
|
||||
</Property>
|
||||
|
||||
<Directory Id='TARGETDIR' Name='SourceDir'>
|
||||
<Merge Id="VCRedist" SourceFile="{crt_msm}" DiskId="1" Language="0"/>
|
||||
<Directory Id='ProgramFilesFolder' Name='PFiles'>
|
||||
@ -43,6 +49,9 @@
|
||||
<Environment Id='UpdatePath' Name='PATH' Action='set' System='yes' Part='last' Value='[APPLICATIONFOLDER]' />
|
||||
<RegistryValue Root="HKCU" Key="Software\Microsoft\{app}" Name="system_path_updated" Type="integer" Value="1" KeyPath="yes"/>
|
||||
</Component>
|
||||
<Component Id="RememberInstallDir" Guid="*">
|
||||
<RegistryValue Root="HKLM" Key="Software\{app}\Installer" Name="InstallPath" Type="string" Value="[APPLICATIONFOLDER]" KeyPath="yes"/>
|
||||
</Component>
|
||||
</DirectoryRef>
|
||||
|
||||
<DirectoryRef Id="ApplicationProgramsFolder">
|
||||
@ -61,7 +70,7 @@
|
||||
WorkingDirectory="APPLICATIONROOTDIRECTORY" />
|
||||
<util:InternetShortcut Id="OnlineDocumentationShortcut"
|
||||
Name="User Manual" Type="url"
|
||||
Target="http://calibre-ebook.com/user_manual"/>
|
||||
Target="http://manual.calibre-ebook.com"/>
|
||||
<util:InternetShortcut Id="GetInvolvedS"
|
||||
Name="Get Involved" Type="url"
|
||||
Target="http://calibre-ebook.com/get-involved"/>
|
||||
@ -87,7 +96,8 @@
|
||||
ConfigurableDirectory="APPLICATIONFOLDER">
|
||||
|
||||
<Feature Id="MainApplication" Title="Program Files" Level="1"
|
||||
Description="All the files need to run {app}" Absent="disallow">
|
||||
Description="All the files needed to run {app}" Absent="disallow">
|
||||
<ComponentRef Id="RememberInstallDir"/>
|
||||
</Feature>
|
||||
|
||||
<Feature Id="VCRedist" Title="Visual C++ 8.0 Runtime" AllowAdvertise="no" Display="hidden" Level="1">
|
||||
@ -115,7 +125,7 @@
|
||||
<Property Id="ARPPRODUCTICON" Value="main_icon" />
|
||||
|
||||
<Condition
|
||||
Message="This application is only supported on Windows XP SP2, or higher.">
|
||||
Message="This application is only supported on Windows XP SP3, or higher.">
|
||||
<![CDATA[Installed OR (VersionNT >= 501)]]>
|
||||
</Condition>
|
||||
<InstallExecuteSequence>
|
||||
|
||||
@ -187,7 +187,6 @@ msgstr ""
|
||||
|
||||
'''%dict(appname=__appname__, version=version, year=time.strftime('%Y'))
|
||||
|
||||
|
||||
def usage(code, msg=''):
|
||||
print >> sys.stderr, __doc__ % globals()
|
||||
if msg:
|
||||
|
||||
@ -6,10 +6,10 @@ __license__ = 'GPL v3'
|
||||
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import os, cPickle, re, anydbm, shutil, marshal, zipfile, glob
|
||||
import os, cPickle, re, shutil, marshal, zipfile, glob
|
||||
from zlib import compress
|
||||
|
||||
from setup import Command, basenames, __appname__, iswindows
|
||||
from setup import Command, basenames, __appname__
|
||||
|
||||
def get_opts_from_parser(parser):
|
||||
def do_opt(opt):
|
||||
@ -34,12 +34,12 @@ class Kakasi(Command):
|
||||
self.records = {}
|
||||
src = self.j(self.KAKASI_PATH, 'kakasidict.utf8')
|
||||
dest = self.j(self.RESOURCES, 'localization',
|
||||
'pykakasi','kanwadict2.db')
|
||||
'pykakasi','kanwadict2.pickle')
|
||||
base = os.path.dirname(dest)
|
||||
if not os.path.exists(base):
|
||||
os.makedirs(base)
|
||||
|
||||
if self.newer(dest, src) or iswindows:
|
||||
if self.newer(dest, src):
|
||||
self.info('\tGenerating Kanwadict')
|
||||
|
||||
for line in open(src, "r"):
|
||||
@ -50,7 +50,7 @@ class Kakasi(Command):
|
||||
dest = self.j(self.RESOURCES, 'localization',
|
||||
'pykakasi','itaijidict2.pickle')
|
||||
|
||||
if self.newer(dest, src) or iswindows:
|
||||
if self.newer(dest, src):
|
||||
self.info('\tGenerating Itaijidict')
|
||||
self.mkitaiji(src, dest)
|
||||
|
||||
@ -58,7 +58,7 @@ class Kakasi(Command):
|
||||
dest = self.j(self.RESOURCES, 'localization',
|
||||
'pykakasi','kanadict2.pickle')
|
||||
|
||||
if self.newer(dest, src) or iswindows:
|
||||
if self.newer(dest, src):
|
||||
self.info('\tGenerating kanadict')
|
||||
self.mkkanadict(src, dest)
|
||||
|
||||
@ -75,7 +75,7 @@ class Kakasi(Command):
|
||||
continue
|
||||
pair = re.sub(r'\\u([0-9a-fA-F]{4})', lambda x:unichr(int(x.group(1),16)), line)
|
||||
dic[pair[0]] = pair[1]
|
||||
cPickle.dump(dic, open(dst, 'w'), protocol=-1) #pickle
|
||||
cPickle.dump(dic, open(dst, 'wb'), protocol=-1) #pickle
|
||||
|
||||
def mkkanadict(self, src, dst):
|
||||
dic = {}
|
||||
@ -87,7 +87,7 @@ class Kakasi(Command):
|
||||
continue
|
||||
(alpha, kana) = line.split(' ')
|
||||
dic[kana] = alpha
|
||||
cPickle.dump(dic, open(dst, 'w'), protocol=-1) #pickle
|
||||
cPickle.dump(dic, open(dst, 'wb'), protocol=-1) #pickle
|
||||
|
||||
def parsekdict(self, line):
|
||||
line = line.decode("utf-8").strip()
|
||||
@ -115,16 +115,11 @@ class Kakasi(Command):
|
||||
self.records[key][kanji]=[(yomi, tail)]
|
||||
|
||||
def kanwaout(self, out):
|
||||
try:
|
||||
# Needed as otherwise anydbm tries to create a gdbm db when the db
|
||||
# created on Unix is found
|
||||
os.remove(out)
|
||||
except:
|
||||
pass
|
||||
dic = anydbm.open(out, 'n')
|
||||
for (k, v) in self.records.iteritems():
|
||||
dic[k] = compress(marshal.dumps(v))
|
||||
dic.close()
|
||||
with open(out, 'wb') as f:
|
||||
dic = {}
|
||||
for k, v in self.records.iteritems():
|
||||
dic[k] = compress(marshal.dumps(v))
|
||||
cPickle.dump(dic, f, -1)
|
||||
|
||||
def clean(self):
|
||||
kakasi = self.j(self.RESOURCES, 'localization', 'pykakasi')
|
||||
|
||||
@ -85,7 +85,7 @@ class Translations(POT):
|
||||
|
||||
def mo_file(self, po_file):
|
||||
locale = os.path.splitext(os.path.basename(po_file))[0]
|
||||
return locale, os.path.join(self.DEST, locale, 'LC_MESSAGES', 'messages.mo')
|
||||
return locale, os.path.join(self.DEST, locale, 'messages.mo')
|
||||
|
||||
|
||||
def run(self, opts):
|
||||
@ -94,9 +94,8 @@ class Translations(POT):
|
||||
base = os.path.dirname(dest)
|
||||
if not os.path.exists(base):
|
||||
os.makedirs(base)
|
||||
if self.newer(dest, f):
|
||||
self.info('\tCompiling translations for', locale)
|
||||
subprocess.check_call(['msgfmt', '-o', dest, f])
|
||||
self.info('\tCompiling translations for', locale)
|
||||
subprocess.check_call(['msgfmt', '-o', dest, f])
|
||||
if locale in ('en_GB', 'nds', 'te', 'yi'):
|
||||
continue
|
||||
pycountry = self.j(sysconfig.get_python_lib(), 'pycountry',
|
||||
@ -123,6 +122,16 @@ class Translations(POT):
|
||||
shutil.copy2(f, dest)
|
||||
|
||||
self.write_stats()
|
||||
self.freeze_locales()
|
||||
|
||||
def freeze_locales(self):
|
||||
zf = self.DEST + '.zip'
|
||||
from calibre import CurrentDir
|
||||
from calibre.utils.zipfile import ZipFile, ZIP_DEFLATED
|
||||
with ZipFile(zf, 'w', ZIP_DEFLATED) as zf:
|
||||
with CurrentDir(self.DEST):
|
||||
zf.add_dir('.')
|
||||
shutil.rmtree(self.DEST)
|
||||
|
||||
@property
|
||||
def stats(self):
|
||||
|
||||
@ -16,7 +16,7 @@ from setup import Command, __version__, installer_name, __appname__
|
||||
PREFIX = "/var/www/calibre-ebook.com"
|
||||
DOWNLOADS = PREFIX+"/htdocs/downloads"
|
||||
BETAS = DOWNLOADS +'/betas'
|
||||
USER_MANUAL = PREFIX+'/htdocs/user_manual'
|
||||
USER_MANUAL = '/var/www/localhost/htdocs/'
|
||||
HTML2LRF = "calibre/ebooks/lrf/html/demo"
|
||||
TXT2LRF = "src/calibre/ebooks/lrf/txt/demo"
|
||||
MOBILEREAD = 'ftp://dev.mobileread.com/calibre/'
|
||||
@ -365,7 +365,7 @@ class UploadUserManual(Command): # {{{
|
||||
self.build_plugin_example(x)
|
||||
|
||||
check_call(' '.join(['scp', '-r', 'src/calibre/manual/.build/html/*',
|
||||
'divok:%s'%USER_MANUAL]), shell=True)
|
||||
'bugs:%s'%USER_MANUAL]), shell=True)
|
||||
# }}}
|
||||
|
||||
class UploadDemo(Command): # {{{
|
||||
|
||||
@ -12,10 +12,10 @@ from functools import partial
|
||||
warnings.simplefilter('ignore', DeprecationWarning)
|
||||
|
||||
|
||||
from calibre.constants import (iswindows, isosx, islinux, isfreebsd, isfrozen,
|
||||
preferred_encoding, __appname__, __version__, __author__,
|
||||
win32event, win32api, winerror, fcntl,
|
||||
filesystem_encoding, plugins, config_dir)
|
||||
from calibre.constants import (iswindows, isosx, islinux, isfrozen,
|
||||
isbsd, preferred_encoding, __appname__, __version__, __author__,
|
||||
win32event, win32api, winerror, fcntl,
|
||||
filesystem_encoding, plugins, config_dir)
|
||||
from calibre.startup import winutil, winutilerror
|
||||
|
||||
if False and islinux and not getattr(sys, 'frozen', False):
|
||||
@ -31,7 +31,7 @@ if False:
|
||||
# Prevent pyflakes from complaining
|
||||
winutil, winutilerror, __appname__, islinux, __version__
|
||||
fcntl, win32event, isfrozen, __author__
|
||||
winerror, win32api, isfreebsd
|
||||
winerror, win32api, isbsd
|
||||
|
||||
_mt_inited = False
|
||||
def _init_mimetypes():
|
||||
@ -630,6 +630,24 @@ def human_readable(size):
|
||||
size = size[:-2]
|
||||
return size + " " + suffix
|
||||
|
||||
def remove_bracketed_text(src,
|
||||
brackets={u'(':u')', u'[':u']', u'{':u'}'}):
|
||||
from collections import Counter
|
||||
counts = Counter()
|
||||
buf = []
|
||||
src = force_unicode(src)
|
||||
rmap = dict([(v, k) for k, v in brackets.iteritems()])
|
||||
for char in src:
|
||||
if char in brackets:
|
||||
counts[char] += 1
|
||||
elif char in rmap:
|
||||
idx = rmap[char]
|
||||
if counts[idx] > 0:
|
||||
counts[idx] -= 1
|
||||
elif sum(counts.itervalues()) < 1:
|
||||
buf.append(char)
|
||||
return u''.join(buf)
|
||||
|
||||
if isosx:
|
||||
import glob, shutil
|
||||
fdir = os.path.expanduser('~/.fonts')
|
||||
|
||||
@ -4,7 +4,7 @@ __license__ = 'GPL v3'
|
||||
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
__appname__ = u'calibre'
|
||||
numeric_version = (0, 8, 1)
|
||||
numeric_version = (0, 8, 4)
|
||||
__version__ = u'.'.join(map(unicode, numeric_version))
|
||||
__author__ = u"Kovid Goyal <kovid@kovidgoyal.net>"
|
||||
|
||||
@ -27,7 +27,9 @@ iswindows = 'win32' in _plat or 'win64' in _plat
|
||||
isosx = 'darwin' in _plat
|
||||
isnewosx = isosx and getattr(sys, 'new_app_bundle', False)
|
||||
isfreebsd = 'freebsd' in _plat
|
||||
islinux = not(iswindows or isosx or isfreebsd)
|
||||
isnetbsd = 'netbsd' in _plat
|
||||
isbsd = isfreebsd or isnetbsd
|
||||
islinux = not(iswindows or isosx or isbsd)
|
||||
isfrozen = hasattr(sys, 'frozen')
|
||||
isunix = isosx or islinux
|
||||
|
||||
|
||||
@ -607,10 +607,25 @@ class StoreBase(Plugin): # {{{
|
||||
supported_platforms = ['windows', 'osx', 'linux']
|
||||
author = 'John Schember'
|
||||
type = _('Store')
|
||||
# Information about the store. Should be in the primary language
|
||||
# of the store. This should not be translatable when set by
|
||||
# a subclass.
|
||||
description = _('An ebook store.')
|
||||
minimum_calibre_version = (0, 8, 0)
|
||||
version = (1, 0, 1)
|
||||
|
||||
actual_plugin = None
|
||||
|
||||
# Does the store only distribute ebooks without DRM.
|
||||
drm_free_only = False
|
||||
# This is the 2 letter country code for the corporate
|
||||
# headquarters of the store.
|
||||
headquarters = ''
|
||||
# All formats the store distributes ebooks in.
|
||||
formats = []
|
||||
# Is this store on an affiliate program?
|
||||
affiliate = False
|
||||
|
||||
def load_actual_plugin(self, gui):
|
||||
'''
|
||||
This method must return the actual interface action plugin object.
|
||||
|
||||
@ -1,4 +1,5 @@
|
||||
import os.path
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
|
||||
@ -593,7 +594,7 @@ from calibre.devices.iliad.driver import ILIAD
|
||||
from calibre.devices.irexdr.driver import IREXDR1000, IREXDR800
|
||||
from calibre.devices.jetbook.driver import JETBOOK, MIBUK, JETBOOK_MINI
|
||||
from calibre.devices.kindle.driver import KINDLE, KINDLE2, KINDLE_DX
|
||||
from calibre.devices.nook.driver import NOOK, NOOK_COLOR
|
||||
from calibre.devices.nook.driver import NOOK, NOOK_COLOR, NOOK_TSR
|
||||
from calibre.devices.prs505.driver import PRS505
|
||||
from calibre.devices.user_defined.driver import USER_DEFINED
|
||||
from calibre.devices.android.driver import ANDROID, S60
|
||||
@ -692,8 +693,7 @@ plugins += [
|
||||
KINDLE,
|
||||
KINDLE2,
|
||||
KINDLE_DX,
|
||||
NOOK,
|
||||
NOOK_COLOR,
|
||||
NOOK, NOOK_COLOR, NOOK_TSR,
|
||||
PRS505,
|
||||
ANDROID,
|
||||
S60,
|
||||
@ -854,6 +854,17 @@ class ActionStore(InterfaceActionBase):
|
||||
author = 'John Schember'
|
||||
actual_plugin = 'calibre.gui2.actions.store:StoreAction'
|
||||
|
||||
def customization_help(self, gui=False):
|
||||
return 'Customize the behavior of the store search.'
|
||||
|
||||
def config_widget(self):
|
||||
from calibre.gui2.store.config.store import config_widget as get_cw
|
||||
return get_cw()
|
||||
|
||||
def save_settings(self, config_widget):
|
||||
from calibre.gui2.store.config.store import save_settings as save
|
||||
save(config_widget)
|
||||
|
||||
plugins += [ActionAdd, ActionFetchAnnotations, ActionGenerateCatalog,
|
||||
ActionConvert, ActionDelete, ActionEditMetadata, ActionView,
|
||||
ActionFetchNews, ActionSaveToDisk, ActionShowBookDetails,
|
||||
@ -1094,121 +1105,353 @@ plugins += [LookAndFeel, Behavior, Columns, Toolbar, Search, InputOptions,
|
||||
# Store plugins {{{
|
||||
class StoreAmazonKindleStore(StoreBase):
|
||||
name = 'Amazon Kindle'
|
||||
description = _('Kindle books from Amazon')
|
||||
description = u'Kindle books from Amazon.'
|
||||
actual_plugin = 'calibre.gui2.store.amazon_plugin:AmazonKindleStore'
|
||||
|
||||
headquarters = 'US'
|
||||
formats = ['KINDLE']
|
||||
affiliate = True
|
||||
|
||||
class StoreAmazonDEKindleStore(StoreBase):
|
||||
name = 'Amazon DE Kindle'
|
||||
description = _('Kindle eBooks')
|
||||
author = 'Charles Haley'
|
||||
description = u'Kindle Bücher von Amazon.'
|
||||
actual_plugin = 'calibre.gui2.store.amazon_de_plugin:AmazonDEKindleStore'
|
||||
|
||||
headquarters = 'DE'
|
||||
formats = ['KINDLE']
|
||||
affiliate = True
|
||||
|
||||
class StoreAmazonUKKindleStore(StoreBase):
|
||||
name = 'Amazon UK Kindle'
|
||||
description = _('Kindle books from Amazon.uk')
|
||||
author = 'Charles Haley'
|
||||
description = u'Kindle books from Amazon\'s UK web site. Also, includes French language ebooks.'
|
||||
actual_plugin = 'calibre.gui2.store.amazon_uk_plugin:AmazonUKKindleStore'
|
||||
|
||||
headquarters = 'UK'
|
||||
formats = ['KINDLE']
|
||||
affiliate = True
|
||||
|
||||
class StoreArchiveOrgStore(StoreBase):
|
||||
name = 'Archive.org'
|
||||
description = u'An Internet library offering permanent access for researchers, historians, scholars, people with disabilities, and the general public to historical collections that exist in digital format.'
|
||||
actual_plugin = 'calibre.gui2.store.archive_org_plugin:ArchiveOrgStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'US'
|
||||
formats = ['DAISY', 'DJVU', 'EPUB', 'MOBI', 'PDF', 'TXT']
|
||||
|
||||
class StoreBaenWebScriptionStore(StoreBase):
|
||||
name = 'Baen WebScription'
|
||||
description = _('Ebooks for readers.')
|
||||
description = u'Sci-Fi & Fantasy brought to you by Jim Baen.'
|
||||
actual_plugin = 'calibre.gui2.store.baen_webscription_plugin:BaenWebScriptionStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'US'
|
||||
formats = ['EPUB', 'LIT', 'LRF', 'MOBI', 'RB', 'RTF', 'ZIP']
|
||||
|
||||
class StoreBNStore(StoreBase):
|
||||
name = 'Barnes and Noble'
|
||||
description = _('Books, Textbooks, eBooks, Toys, Games and More.')
|
||||
description = u'The world\'s largest book seller. As the ultimate destination for book lovers, Barnes & Noble.com offers an incredible array of content.'
|
||||
actual_plugin = 'calibre.gui2.store.bn_plugin:BNStore'
|
||||
|
||||
headquarters = 'US'
|
||||
formats = ['NOOK']
|
||||
affiliate = True
|
||||
|
||||
class StoreBeamEBooksDEStore(StoreBase):
|
||||
name = 'Beam EBooks DE'
|
||||
description = _('der eBook Shop')
|
||||
author = 'Charles Haley'
|
||||
description = u'Bei uns finden Sie: Tausende deutschsprachige eBooks; Alle eBooks ohne hartes DRM; PDF, ePub und Mobipocket Format; Sofortige Verfügbarkeit - 24 Stunden am Tag; Günstige Preise; eBooks für viele Lesegeräte, PC,Mac und Smartphones; Viele Gratis eBooks'
|
||||
actual_plugin = 'calibre.gui2.store.beam_ebooks_de_plugin:BeamEBooksDEStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'DE'
|
||||
formats = ['EPUB', 'MOBI', 'PDF']
|
||||
affiliate = True
|
||||
|
||||
class StoreBeWriteStore(StoreBase):
|
||||
name = 'BeWrite Books'
|
||||
description = _('Publishers of fine books.')
|
||||
description = u'Publishers of fine books. Highly selective and editorially driven. Does not offer: books for children or exclusively YA, erotica, swords-and-sorcery fantasy and space-opera-style science fiction. All other genres are represented.'
|
||||
actual_plugin = 'calibre.gui2.store.bewrite_plugin:BeWriteStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'US'
|
||||
formats = ['EPUB', 'MOBI', 'PDF']
|
||||
|
||||
class StoreDieselEbooksStore(StoreBase):
|
||||
name = 'Diesel eBooks'
|
||||
description = _('World Famous eBook Store.')
|
||||
description = u'Instant access to over 2.4 million titles from hundreds of publishers including Harlequin, HarperCollins, John Wiley & Sons, McGraw-Hill, Simon & Schuster and Random House.'
|
||||
actual_plugin = 'calibre.gui2.store.diesel_ebooks_plugin:DieselEbooksStore'
|
||||
|
||||
headquarters = 'US'
|
||||
formats = ['EPUB', 'PDF']
|
||||
affiliate = True
|
||||
|
||||
class StoreEbookscomStore(StoreBase):
|
||||
name = 'eBooks.com'
|
||||
description = _('The digital bookstore.')
|
||||
description = u'Sells books in multiple electronic formats in all categories. Technical infrastructure is cutting edge, robust and scalable, with servers in the US and Europe.'
|
||||
actual_plugin = 'calibre.gui2.store.ebooks_com_plugin:EbookscomStore'
|
||||
|
||||
headquarters = 'US'
|
||||
formats = ['EPUB', 'LIT', 'MOBI', 'PDF']
|
||||
affiliate = True
|
||||
|
||||
class StoreEPubBuyDEStore(StoreBase):
|
||||
name = 'EPUBBuy DE'
|
||||
description = _('EPUBReaders eBook Shop')
|
||||
author = 'Charles Haley'
|
||||
description = u'Bei EPUBBuy.com finden Sie ausschliesslich eBooks im weitverbreiteten EPUB-Format und ohne DRM. So haben Sie die freie Wahl, wo Sie Ihr eBook lesen: Tablet, eBook-Reader, Smartphone oder einfach auf Ihrem PC. So macht eBook-Lesen Spaß!'
|
||||
actual_plugin = 'calibre.gui2.store.epubbuy_de_plugin:EPubBuyDEStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'DE'
|
||||
formats = ['EPUB']
|
||||
affiliate = True
|
||||
|
||||
class StoreEBookShoppeUKStore(StoreBase):
|
||||
name = 'ebookShoppe UK'
|
||||
author = u'Charles Haley'
|
||||
description = u'We made this website in an attempt to offer the widest range of UK eBooks possible across and as many formats as we could manage.'
|
||||
actual_plugin = 'calibre.gui2.store.ebookshoppe_uk_plugin:EBookShoppeUKStore'
|
||||
|
||||
headquarters = 'UK'
|
||||
formats = ['EPUB', 'PDF']
|
||||
affiliate = True
|
||||
|
||||
class StoreEHarlequinStore(StoreBase):
|
||||
name = 'eHarlequin'
|
||||
description = _('entertain, enrich, inspire.')
|
||||
description = u'A global leader in series romance and one of the world\'s leading publishers of books for women. Offers women a broad range of reading from romance to bestseller fiction, from young adult novels to erotic literature, from nonfiction to fantasy, from African-American novels to inspirational romance, and more.'
|
||||
actual_plugin = 'calibre.gui2.store.eharlequin_plugin:EHarlequinStore'
|
||||
|
||||
headquarters = 'CA'
|
||||
formats = ['EPUB', 'PDF']
|
||||
affiliate = True
|
||||
|
||||
class StoreEpubBudStore(StoreBase):
|
||||
name = 'ePub Bud'
|
||||
description = 'Well, it\'s pretty much just "YouTube for Children\'s eBooks. A not-for-profit organization devoted to brining self published childrens books to the world.'
|
||||
actual_plugin = 'calibre.gui2.store.epubbud_plugin:EpubBudStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'US'
|
||||
formats = ['EPUB']
|
||||
|
||||
class StoreFeedbooksStore(StoreBase):
|
||||
name = 'Feedbooks'
|
||||
description = _('Read anywhere.')
|
||||
description = u'Feedbooks is a cloud publishing and distribution service, connected to a large ecosystem of reading systems and social networks. Provides a variety of genres from independent and classic books.'
|
||||
actual_plugin = 'calibre.gui2.store.feedbooks_plugin:FeedbooksStore'
|
||||
|
||||
headquarters = 'FR'
|
||||
formats = ['EPUB', 'MOBI', 'PDF']
|
||||
|
||||
class StoreFoylesUKStore(StoreBase):
|
||||
name = 'Foyles UK'
|
||||
description = _('Foyles of London, online')
|
||||
author = 'Charles Haley'
|
||||
description = u'Foyles of London\'s ebook store. Provides extensive range covering all subjects.'
|
||||
actual_plugin = 'calibre.gui2.store.foyles_uk_plugin:FoylesUKStore'
|
||||
|
||||
headquarters = 'UK'
|
||||
formats = ['EPUB', 'PDF']
|
||||
affiliate = True
|
||||
|
||||
class StoreGandalfStore(StoreBase):
|
||||
name = 'Gandalf'
|
||||
author = u'Tomasz Długosz'
|
||||
description = u'Księgarnia internetowa Gandalf.'
|
||||
actual_plugin = 'calibre.gui2.store.gandalf_plugin:GandalfStore'
|
||||
|
||||
headquarters = 'PL'
|
||||
formats = ['EPUB', 'PDF']
|
||||
|
||||
class StoreGoogleBooksStore(StoreBase):
|
||||
name = 'Google Books'
|
||||
description = u'Google Books'
|
||||
actual_plugin = 'calibre.gui2.store.google_books_plugin:GoogleBooksStore'
|
||||
|
||||
headquarters = 'US'
|
||||
formats = ['EPUB', 'PDF', 'TXT']
|
||||
|
||||
class StoreGutenbergStore(StoreBase):
|
||||
name = 'Project Gutenberg'
|
||||
description = _('The first producer of free ebooks.')
|
||||
description = u'The first producer of free ebooks. Free in the United States because their copyright has expired. They may not be free of copyright in other countries. Readers outside of the United States must check the copyright laws of their countries before downloading or redistributing our ebooks.'
|
||||
actual_plugin = 'calibre.gui2.store.gutenberg_plugin:GutenbergStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'US'
|
||||
formats = ['EPUB', 'HTML', 'MOBI', 'PDB', 'TXT']
|
||||
|
||||
class StoreKoboStore(StoreBase):
|
||||
name = 'Kobo'
|
||||
description = _('eReading: anytime. anyplace.')
|
||||
description = u'With over 2.3 million eBooks to browse we have engaged readers in over 200 countries in Kobo eReading. Our eBook listings include New York Times Bestsellers, award winners, classics and more!'
|
||||
actual_plugin = 'calibre.gui2.store.kobo_plugin:KoboStore'
|
||||
|
||||
headquarters = 'CA'
|
||||
formats = ['EPUB']
|
||||
affiliate = True
|
||||
|
||||
class StoreLegimiStore(StoreBase):
|
||||
name = 'Legimi'
|
||||
author = u'Tomasz Długosz'
|
||||
description = u'Tanie oraz darmowe ebooki, egazety i blogi w formacie EPUB, wprost na Twój e-czytnik, iPhone, iPad, Android i komputer'
|
||||
actual_plugin = 'calibre.gui2.store.legimi_plugin:LegimiStore'
|
||||
|
||||
headquarters = 'PL'
|
||||
formats = ['EPUB']
|
||||
|
||||
class StoreManyBooksStore(StoreBase):
|
||||
name = 'ManyBooks'
|
||||
description = _('The best ebooks at the best price: free!')
|
||||
description = u'Public domain and creative commons works from many sources.'
|
||||
actual_plugin = 'calibre.gui2.store.manybooks_plugin:ManyBooksStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'US'
|
||||
formats = ['EPUB', 'FB2', 'JAR', 'LIT', 'LRF', 'MOBI', 'PDB', 'PDF', 'RB', 'RTF', 'TCR', 'TXT', 'ZIP']
|
||||
|
||||
class StoreMobileReadStore(StoreBase):
|
||||
name = 'MobileRead'
|
||||
description = _('Ebooks handcrafted with the utmost care')
|
||||
description = u'Ebooks handcrafted with the utmost care.'
|
||||
actual_plugin = 'calibre.gui2.store.mobileread.mobileread_plugin:MobileReadStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'CH'
|
||||
formats = ['EPUB', 'IMP', 'LRF', 'LIT', 'MOBI', 'PDF']
|
||||
|
||||
class StoreNextoStore(StoreBase):
|
||||
name = 'Nexto'
|
||||
author = u'Tomasz Długosz'
|
||||
description = u'Największy w Polsce sklep internetowy z audiobookami mp3, ebookami pdf oraz prasą do pobrania on-line.'
|
||||
actual_plugin = 'calibre.gui2.store.nexto_plugin:NextoStore'
|
||||
|
||||
headquarters = 'PL'
|
||||
formats = ['EPUB', 'PDF']
|
||||
affiliate = True
|
||||
|
||||
class StoreOpenLibraryStore(StoreBase):
|
||||
name = 'Open Library'
|
||||
description = _('One web page for every book.')
|
||||
description = u'One web page for every book ever published. The goal is to be a true online library. Over 20 million records from a variety of large catalogs as well as single contributions, with more on the way.'
|
||||
actual_plugin = 'calibre.gui2.store.open_library_plugin:OpenLibraryStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'US'
|
||||
formats = ['DAISY', 'DJVU', 'EPUB', 'MOBI', 'PDF', 'TXT']
|
||||
|
||||
class StoreOReillyStore(StoreBase):
|
||||
name = 'OReilly'
|
||||
description = u'Programming and tech ebooks from OReilly.'
|
||||
actual_plugin = 'calibre.gui2.store.oreilly_plugin:OReillyStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'US'
|
||||
formats = ['APK', 'DAISY', 'EPUB', 'MOBI', 'PDF']
|
||||
|
||||
class StorePragmaticBookshelfStore(StoreBase):
|
||||
name = 'Pragmatic Bookshelf'
|
||||
description = u'The Pragmatic Bookshelf\'s collection of programming and tech books avaliable as ebooks.'
|
||||
actual_plugin = 'calibre.gui2.store.pragmatic_bookshelf_plugin:PragmaticBookshelfStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'US'
|
||||
formats = ['EPUB', 'MOBI', 'PDF']
|
||||
|
||||
class StoreSmashwordsStore(StoreBase):
|
||||
name = 'Smashwords'
|
||||
description = _('Your ebook. Your way.')
|
||||
description = u'An ebook publishing and distribution platform for ebook authors, publishers and readers. Covers many genres and formats.'
|
||||
actual_plugin = 'calibre.gui2.store.smashwords_plugin:SmashwordsStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'US'
|
||||
formats = ['EPUB', 'HTML', 'LRF', 'MOBI', 'PDB', 'RTF', 'TXT']
|
||||
affiliate = True
|
||||
|
||||
class StoreVirtualoStore(StoreBase):
|
||||
name = 'Virtualo'
|
||||
author = u'Tomasz Długosz'
|
||||
description = u'Księgarnia internetowa, która oferuje bezpieczny i szeroki dostęp do książek w formie cyfrowej.'
|
||||
actual_plugin = 'calibre.gui2.store.virtualo_plugin:VirtualoStore'
|
||||
|
||||
headquarters = 'PL'
|
||||
formats = ['EPUB', 'PDF']
|
||||
|
||||
class StoreWaterstonesUKStore(StoreBase):
|
||||
name = 'Waterstones UK'
|
||||
description = _('Feel every word')
|
||||
author = 'Charles Haley'
|
||||
description = u'Waterstone\'s mission is to be the leading Bookseller on the High Street and online providing customers the widest choice, great value and expert advice from a team passionate about Bookselling.'
|
||||
actual_plugin = 'calibre.gui2.store.waterstones_uk_plugin:WaterstonesUKStore'
|
||||
|
||||
headquarters = 'UK'
|
||||
formats = ['EPUB', 'PDF']
|
||||
|
||||
class StoreWeightlessBooksStore(StoreBase):
|
||||
name = 'Weightless Books'
|
||||
description = '(e)Books That Don\'t Weigh You Down'
|
||||
description = u'An independent DRM-free ebooksite devoted to ebooks of all sorts.'
|
||||
actual_plugin = 'calibre.gui2.store.weightless_books_plugin:WeightlessBooksStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'US'
|
||||
formats = ['EPUB', 'HTML', 'LIT', 'MOBI', 'PDF']
|
||||
|
||||
class StoreWHSmithUKStore(StoreBase):
|
||||
name = 'WH Smith UK'
|
||||
author = 'Charles Haley'
|
||||
description = u"Shop for savings on Books, discounted Magazine subscriptions and great prices on Stationery, Toys & Games"
|
||||
actual_plugin = 'calibre.gui2.store.whsmith_uk_plugin:WHSmithUKStore'
|
||||
|
||||
headquarters = 'UK'
|
||||
formats = ['EPUB', 'PDF']
|
||||
|
||||
class StoreWizardsTowerBooksStore(StoreBase):
|
||||
name = 'Wizards Tower Books'
|
||||
description = 'Wizard\'s Tower Press'
|
||||
description = u'A science fiction and fantasy publisher. Concentrates mainly on making out-of-print works available once more as e-books, and helping other small presses exploit the e-book market. Also publishes a small number of limited-print-run anthologies with a view to encouraging diversity in the science fiction and fantasy field.'
|
||||
actual_plugin = 'calibre.gui2.store.wizards_tower_books_plugin:WizardsTowerBooksStore'
|
||||
|
||||
plugins += [StoreAmazonKindleStore, StoreAmazonDEKindleStore, StoreAmazonUKKindleStore,
|
||||
StoreBaenWebScriptionStore, StoreBNStore,
|
||||
StoreBeamEBooksDEStore, StoreBeWriteStore,
|
||||
StoreDieselEbooksStore, StoreEbookscomStore, StoreEPubBuyDEStore,
|
||||
StoreEHarlequinStore, StoreFeedbooksStore,
|
||||
StoreFoylesUKStore, StoreGutenbergStore, StoreKoboStore, StoreManyBooksStore,
|
||||
StoreMobileReadStore, StoreOpenLibraryStore, StoreSmashwordsStore,
|
||||
StoreWaterstonesUKStore, StoreWeightlessBooksStore, StoreWizardsTowerBooksStore]
|
||||
drm_free_only = True
|
||||
headquarters = 'UK'
|
||||
formats = ['EPUB', 'MOBI']
|
||||
|
||||
class StoreWoblinkStore(StoreBase):
|
||||
name = 'Woblink'
|
||||
author = u'Tomasz Długosz'
|
||||
description = u'Czytanie zdarza się wszędzie!'
|
||||
actual_plugin = 'calibre.gui2.store.woblink_plugin:WoblinkStore'
|
||||
|
||||
headquarters = 'PL'
|
||||
formats = ['EPUB']
|
||||
|
||||
plugins += [
|
||||
StoreArchiveOrgStore,
|
||||
StoreAmazonKindleStore,
|
||||
StoreAmazonDEKindleStore,
|
||||
StoreAmazonUKKindleStore,
|
||||
StoreBaenWebScriptionStore,
|
||||
StoreBNStore,
|
||||
StoreBeamEBooksDEStore,
|
||||
StoreBeWriteStore,
|
||||
StoreDieselEbooksStore,
|
||||
StoreEbookscomStore,
|
||||
StoreEBookShoppeUKStore,
|
||||
StoreEPubBuyDEStore,
|
||||
StoreEHarlequinStore,
|
||||
StoreEpubBudStore,
|
||||
StoreFeedbooksStore,
|
||||
StoreFoylesUKStore,
|
||||
StoreGandalfStore,
|
||||
StoreGoogleBooksStore,
|
||||
StoreGutenbergStore,
|
||||
StoreKoboStore,
|
||||
StoreLegimiStore,
|
||||
StoreManyBooksStore,
|
||||
StoreMobileReadStore,
|
||||
StoreNextoStore,
|
||||
StoreOpenLibraryStore,
|
||||
StoreOReillyStore,
|
||||
StorePragmaticBookshelfStore,
|
||||
StoreSmashwordsStore,
|
||||
StoreVirtualoStore,
|
||||
StoreWaterstonesUKStore,
|
||||
StoreWeightlessBooksStore,
|
||||
StoreWHSmithUKStore,
|
||||
StoreWizardsTowerBooksStore,
|
||||
StoreWoblinkStore
|
||||
]
|
||||
|
||||
# }}}
|
||||
|
||||
@ -216,9 +216,26 @@ def store_plugins():
|
||||
customization = config['plugin_customization']
|
||||
for plugin in _initialized_plugins:
|
||||
if isinstance(plugin, Store):
|
||||
if not is_disabled(plugin):
|
||||
plugin.site_customization = customization.get(plugin.name, '')
|
||||
yield plugin
|
||||
plugin.site_customization = customization.get(plugin.name, '')
|
||||
yield plugin
|
||||
|
||||
def available_store_plugins():
|
||||
for plugin in store_plugins():
|
||||
if not is_disabled(plugin):
|
||||
yield plugin
|
||||
|
||||
def stores():
|
||||
stores = set([])
|
||||
for plugin in store_plugins():
|
||||
stores.add(plugin.name)
|
||||
return stores
|
||||
|
||||
def available_stores():
|
||||
stores = set([])
|
||||
for plugin in available_store_plugins():
|
||||
stores.add(plugin.name)
|
||||
return stores
|
||||
|
||||
# }}}
|
||||
|
||||
# Metadata read/write {{{
|
||||
|
||||
@ -52,6 +52,8 @@ class ANDROID(USBMS):
|
||||
0x04e8 : { 0x681d : [0x0222, 0x0223, 0x0224, 0x0400],
|
||||
0x681c : [0x0222, 0x0224, 0x0400],
|
||||
0x6640 : [0x0100],
|
||||
0x685e : [0x0400],
|
||||
0x6860 : [0x0400],
|
||||
0x6877 : [0x0400],
|
||||
},
|
||||
|
||||
@ -59,7 +61,7 @@ class ANDROID(USBMS):
|
||||
0x0489 : { 0xc001 : [0x0226], 0xc004 : [0x0226], },
|
||||
|
||||
# Acer
|
||||
0x502 : { 0x3203 : [0x0100]},
|
||||
0x502 : { 0x3203 : [0x0100, 0x224]},
|
||||
|
||||
# Dell
|
||||
0x413c : { 0xb007 : [0x0100, 0x0224, 0x0226]},
|
||||
@ -109,10 +111,12 @@ class ANDROID(USBMS):
|
||||
'SGH-T849', '_MB300', 'A70S', 'S_ANDROID', 'A101IT', 'A70H',
|
||||
'IDEOS_TABLET', 'MYTOUCH_4G', 'UMS_COMPOSITE', 'SCH-I800_CARD',
|
||||
'7', 'A956', 'A955', 'A43', 'ANDROID_PLATFORM', 'TEGRA_2',
|
||||
'MB860', 'MULTI-CARD', 'MID7015A', 'INCREDIBLE', 'A7EB', 'STREAK']
|
||||
'MB860', 'MULTI-CARD', 'MID7015A', 'INCREDIBLE', 'A7EB', 'STREAK',
|
||||
'MB525']
|
||||
WINDOWS_CARD_A_MEM = ['ANDROID_PHONE', 'GT-I9000_CARD', 'SGH-I897',
|
||||
'FILE-STOR_GADGET', 'SGH-T959', 'SAMSUNG_ANDROID', 'GT-P1000_CARD',
|
||||
'A70S', 'A101IT', '7', 'INCREDIBLE', 'A7EB', 'SGH-T849_CARD']
|
||||
'A70S', 'A101IT', '7', 'INCREDIBLE', 'A7EB', 'SGH-T849_CARD',
|
||||
'__UMS_COMPOSITE']
|
||||
|
||||
OSX_MAIN_MEM = 'Android Device Main Memory'
|
||||
|
||||
|
||||
@ -941,7 +941,7 @@ class ITUNES(DriverBase):
|
||||
# declared in use_plugboard_ext and a device name of ITUNES
|
||||
if DEBUG:
|
||||
self.log.info("ITUNES.set_plugboard()")
|
||||
#self.log.info(' using plugboard %s' % plugboards)
|
||||
#self.log.info(' plugboard: %s' % plugboards)
|
||||
self.plugboards = plugboards
|
||||
self.plugboard_func = pb_func
|
||||
|
||||
@ -1052,7 +1052,6 @@ class ITUNES(DriverBase):
|
||||
'title': metadata[i].title,
|
||||
'uuid': metadata[i].uuid }
|
||||
|
||||
|
||||
# Report progress
|
||||
if self.report_progress is not None:
|
||||
self.report_progress((i+1)/file_count, _('%d of %d') % (i+1, file_count))
|
||||
@ -2393,6 +2392,16 @@ class ITUNES(DriverBase):
|
||||
self.iTunes.Windows[0].Minimized = True
|
||||
self.initial_status = 'launched'
|
||||
|
||||
try:
|
||||
# Pre-emptive test to confirm functional iTunes automation interface
|
||||
foo = self.iTunes.Version
|
||||
foo
|
||||
except:
|
||||
self.iTunes = None
|
||||
raise OpenFeedback('Unable to connect to iTunes.\n' +
|
||||
' iTunes automation interface non-responsive, ' +
|
||||
'recommend reinstalling iTunes')
|
||||
|
||||
# Read the current storage path for iTunes media from the XML file
|
||||
media_dir = ''
|
||||
string = None
|
||||
@ -2744,7 +2753,6 @@ class ITUNES(DriverBase):
|
||||
# Update metadata from plugboard
|
||||
# If self.plugboard is None (no transforms), original metadata is returned intact
|
||||
metadata_x = self._xform_metadata_via_plugboard(metadata, this_book.format)
|
||||
|
||||
if isosx:
|
||||
if lb_added:
|
||||
lb_added.name.set(metadata_x.title)
|
||||
@ -2754,8 +2762,7 @@ class ITUNES(DriverBase):
|
||||
lb_added.description.set("%s %s" % (self.description_prefix,strftime('%Y-%m-%d %H:%M:%S')))
|
||||
lb_added.enabled.set(True)
|
||||
lb_added.sort_artist.set(icu_title(metadata_x.author_sort))
|
||||
lb_added.sort_name.set(metadata.title_sort)
|
||||
|
||||
lb_added.sort_name.set(metadata_x.title_sort)
|
||||
|
||||
if db_added:
|
||||
db_added.name.set(metadata_x.title)
|
||||
@ -2765,7 +2772,7 @@ class ITUNES(DriverBase):
|
||||
db_added.description.set("%s %s" % (self.description_prefix,strftime('%Y-%m-%d %H:%M:%S')))
|
||||
db_added.enabled.set(True)
|
||||
db_added.sort_artist.set(icu_title(metadata_x.author_sort))
|
||||
db_added.sort_name.set(metadata.title_sort)
|
||||
db_added.sort_name.set(metadata_x.title_sort)
|
||||
|
||||
if metadata_x.comments:
|
||||
if lb_added:
|
||||
@ -2785,6 +2792,7 @@ class ITUNES(DriverBase):
|
||||
|
||||
# Set genre from series if available, else first alpha tag
|
||||
# Otherwise iTunes grabs the first dc:subject from the opf metadata
|
||||
# If title_sort applied in plugboard, that overrides using series/index as title_sort
|
||||
if metadata_x.series and self.settings().extra_customization[self.USE_SERIES_AS_CATEGORY]:
|
||||
if DEBUG:
|
||||
self.log.info(" ITUNES._update_iTunes_metadata()")
|
||||
@ -2796,7 +2804,9 @@ class ITUNES(DriverBase):
|
||||
fraction = index-integer
|
||||
series_index = '%04d%s' % (integer, str('%0.4f' % fraction).lstrip('0'))
|
||||
if lb_added:
|
||||
lb_added.sort_name.set("%s %s" % (self.title_sorter(metadata_x.series), series_index))
|
||||
# If no title_sort plugboard tweak, create sort_name from series/index
|
||||
if metadata.title_sort == metadata_x.title_sort:
|
||||
lb_added.sort_name.set("%s %s" % (self.title_sorter(metadata_x.series), series_index))
|
||||
lb_added.episode_ID.set(metadata_x.series)
|
||||
lb_added.episode_number.set(metadata_x.series_index)
|
||||
|
||||
@ -2810,7 +2820,9 @@ class ITUNES(DriverBase):
|
||||
break
|
||||
|
||||
if db_added:
|
||||
db_added.sort_name.set("%s %s" % (self.title_sorter(metadata_x.series), series_index))
|
||||
# If no title_sort plugboard tweak, create sort_name from series/index
|
||||
if metadata.title_sort == metadata_x.title_sort:
|
||||
db_added.sort_name.set("%s %s" % (self.title_sorter(metadata_x.series), series_index))
|
||||
db_added.episode_ID.set(metadata_x.series)
|
||||
db_added.episode_number.set(metadata_x.series_index)
|
||||
|
||||
@ -2845,7 +2857,7 @@ class ITUNES(DriverBase):
|
||||
lb_added.Description = ("%s %s" % (self.description_prefix,strftime('%Y-%m-%d %H:%M:%S')))
|
||||
lb_added.Enabled = True
|
||||
lb_added.SortArtist = icu_title(metadata_x.author_sort)
|
||||
lb_added.SortName = metadata.title_sort
|
||||
lb_added.SortName = metadata_x.title_sort
|
||||
|
||||
if db_added:
|
||||
db_added.Name = metadata_x.title
|
||||
@ -2855,7 +2867,7 @@ class ITUNES(DriverBase):
|
||||
db_added.Description = ("%s %s" % (self.description_prefix,strftime('%Y-%m-%d %H:%M:%S')))
|
||||
db_added.Enabled = True
|
||||
db_added.SortArtist = icu_title(metadata_x.author_sort)
|
||||
db_added.SortName = metadata.title_sort
|
||||
db_added.SortName = metadata_x.title_sort
|
||||
|
||||
if metadata_x.comments:
|
||||
if lb_added:
|
||||
@ -2888,7 +2900,9 @@ class ITUNES(DriverBase):
|
||||
fraction = index-integer
|
||||
series_index = '%04d%s' % (integer, str('%0.4f' % fraction).lstrip('0'))
|
||||
if lb_added:
|
||||
lb_added.SortName = "%s %s" % (self.title_sorter(metadata_x.series), series_index)
|
||||
# If no title_sort plugboard tweak, create sort_name from series/index
|
||||
if metadata.title_sort == metadata_x.title_sort:
|
||||
lb_added.SortName = "%s %s" % (self.title_sorter(metadata_x.series), series_index)
|
||||
lb_added.EpisodeID = metadata_x.series
|
||||
|
||||
try:
|
||||
@ -2914,7 +2928,9 @@ class ITUNES(DriverBase):
|
||||
break
|
||||
|
||||
if db_added:
|
||||
db_added.SortName = "%s %s" % (self.title_sorter(metadata_x.series), series_index)
|
||||
# If no title_sort plugboard tweak, create sort_name from series/index
|
||||
if metadata.title_sort == metadata_x.title_sort:
|
||||
db_added.SortName = "%s %s" % (self.title_sorter(metadata_x.series), series_index)
|
||||
db_added.EpisodeID = metadata_x.series
|
||||
|
||||
try:
|
||||
@ -2975,11 +2991,13 @@ class ITUNES(DriverBase):
|
||||
newmi.publisher if book.publisher != newmi.publisher else ''))
|
||||
self.log.info(" tags: %s %s" % (book.tags, ">>> %s" %
|
||||
newmi.tags if book.tags != newmi.tags else ''))
|
||||
else:
|
||||
self.log(" matching plugboard not found")
|
||||
|
||||
else:
|
||||
newmi = book
|
||||
return newmi
|
||||
|
||||
|
||||
class ITUNES_ASYNC(ITUNES):
|
||||
'''
|
||||
This subclass allows the user to interact directly with iTunes via a menu option
|
||||
@ -3014,6 +3032,8 @@ class ITUNES_ASYNC(ITUNES):
|
||||
pythoncom.CoInitialize()
|
||||
self._launch_iTunes()
|
||||
except:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
raise UserFeedback('unable to launch iTunes', details=None, level=UserFeedback.WARN)
|
||||
finally:
|
||||
pythoncom.CoUninitialize()
|
||||
|
||||
@ -35,8 +35,8 @@ class EB600(USBMS):
|
||||
PRODUCT_ID = [0x1688]
|
||||
BCD = [0x110]
|
||||
|
||||
VENDOR_NAME = 'NETRONIX'
|
||||
WINDOWS_MAIN_MEM = 'EBOOK'
|
||||
VENDOR_NAME = ['NETRONIX', 'WOLDER']
|
||||
WINDOWS_MAIN_MEM = ['EBOOK', 'MIBUK_GAMMA_6.2']
|
||||
WINDOWS_CARD_A_MEM = 'EBOOK'
|
||||
|
||||
OSX_MAIN_MEM = 'EB600 Internal Storage Media'
|
||||
@ -95,9 +95,8 @@ class POCKETBOOK360(EB600):
|
||||
|
||||
FORMATS = ['epub', 'fb2', 'prc', 'mobi', 'pdf', 'djvu', 'rtf', 'chm', 'txt']
|
||||
|
||||
VENDOR_NAME = 'PHILIPS'
|
||||
WINDOWS_MAIN_MEM = 'MASS_STORGE'
|
||||
WINDOWS_CARD_A_MEM = 'MASS_STORGE'
|
||||
VENDOR_NAME = ['PHILIPS', '__POCKET']
|
||||
WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = ['MASS_STORGE', 'BOOK_USB_STORAGE']
|
||||
|
||||
OSX_MAIN_MEM = 'Philips Mass Storge Media'
|
||||
OSX_CARD_A_MEM = 'Philips Mass Storge Media'
|
||||
|
||||
@ -8,10 +8,10 @@ from ctypes import cdll, POINTER, byref, pointer, Structure as _Structure, \
|
||||
c_ubyte, c_ushort, c_int, c_char, c_void_p, c_byte, c_uint
|
||||
from errno import EBUSY, ENOMEM
|
||||
|
||||
from calibre import iswindows, isosx, isfreebsd, load_library
|
||||
from calibre import iswindows, isosx, isbsd, load_library
|
||||
|
||||
_libusb_name = 'libusb'
|
||||
PATH_MAX = 511 if iswindows else 1024 if (isosx or isfreebsd) else 4096
|
||||
PATH_MAX = 511 if iswindows else 1024 if (isosx or isbsd) else 4096
|
||||
if iswindows:
|
||||
class Structure(_Structure):
|
||||
_pack_ = 1
|
||||
|
||||
@ -224,13 +224,16 @@ class TREKSTOR(USBMS):
|
||||
FORMATS = ['epub', 'txt', 'pdf']
|
||||
|
||||
VENDOR_ID = [0x1e68]
|
||||
PRODUCT_ID = [0x0041, 0x0042]
|
||||
PRODUCT_ID = [0x0041, 0x0042,
|
||||
0x003e # This is for the EBOOK_PLAYER_5M https://bugs.launchpad.net/bugs/792091
|
||||
]
|
||||
BCD = [0x0002]
|
||||
|
||||
EBOOK_DIR_MAIN = 'Ebooks'
|
||||
|
||||
VENDOR_NAME = 'TREKSTOR'
|
||||
WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = 'EBOOK_PLAYER_7'
|
||||
WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = ['EBOOK_PLAYER_7',
|
||||
'EBOOK_PLAYER_5M']
|
||||
|
||||
class EEEREADER(USBMS):
|
||||
|
||||
@ -269,8 +272,8 @@ class NEXTBOOK(USBMS):
|
||||
|
||||
EBOOK_DIR_MAIN = ''
|
||||
|
||||
VENDOR_NAME = 'NEXT2'
|
||||
WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = '1.0.14'
|
||||
VENDOR_NAME = ['NEXT2', 'BK7005']
|
||||
WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = ['1.0.14', 'PLAYER']
|
||||
SUPPORTS_SUB_DIRS = True
|
||||
THUMBNAIL_HEIGHT = 120
|
||||
|
||||
|
||||
@ -107,3 +107,19 @@ class NOOK_COLOR(NOOK):
|
||||
|
||||
return filepath
|
||||
|
||||
def upload_cover(self, path, filename, metadata, filepath):
|
||||
pass
|
||||
|
||||
class NOOK_TSR(NOOK):
|
||||
gui_name = _('Nook Simple')
|
||||
description = _('Communicate with the Nook TSR eBook reader.')
|
||||
|
||||
PRODUCT_ID = [0x003]
|
||||
BCD = [0x216]
|
||||
|
||||
EBOOK_DIR_MAIN = EBOOK_DIR_CARD_A = 'My Files/Books'
|
||||
WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = 'EBOOK_DISK'
|
||||
|
||||
def upload_cover(self, path, filename, metadata, filepath):
|
||||
pass
|
||||
|
||||
|
||||
@ -204,7 +204,8 @@ class CollectionsBookList(BookList):
|
||||
elif fm['datatype'] == 'text' and fm['is_multiple']:
|
||||
val = orig_val
|
||||
elif fm['datatype'] == 'composite' and fm['is_multiple']:
|
||||
val = [v.strip() for v in val.split(fm['is_multiple'])]
|
||||
val = [v.strip() for v in
|
||||
val.split(fm['is_multiple']['ui_to_list'])]
|
||||
else:
|
||||
val = [val]
|
||||
|
||||
|
||||
@ -926,8 +926,8 @@ class Device(DeviceConfig, DevicePlugin):
|
||||
if not isinstance(template, unicode):
|
||||
template = template.decode('utf-8')
|
||||
app_id = str(getattr(mdata, 'application_id', ''))
|
||||
# The db id will be in the created filename
|
||||
extra_components = get_components(template, mdata, fname,
|
||||
id_ = mdata.get('id', fname)
|
||||
extra_components = get_components(template, mdata, id_,
|
||||
timefmt=opts.send_timefmt, length=maxlen-len(app_id)-1)
|
||||
if not extra_components:
|
||||
extra_components.append(sanitize(self.filename_callback(fname,
|
||||
|
||||
@ -40,7 +40,7 @@ To get help on them specify the input and output file and then use the -h \
|
||||
option.
|
||||
|
||||
For full documentation of the conversion system see
|
||||
''') + 'http://calibre-ebook.com/user_manual/conversion.html'
|
||||
''') + 'http://manual.calibre-ebook.com/conversion.html'
|
||||
|
||||
HEURISTIC_OPTIONS = ['markup_chapter_headings',
|
||||
'italicize_common_cases', 'fix_indents',
|
||||
|
||||
@ -101,7 +101,7 @@ class Container(object):
|
||||
return None
|
||||
return existing[0]
|
||||
|
||||
def add_name_to_manifest(self, name):
|
||||
def add_name_to_manifest(self, name, mt=None):
|
||||
item = self.manifest_item_for_name(name)
|
||||
if item is not None:
|
||||
return
|
||||
@ -109,11 +109,27 @@ class Container(object):
|
||||
item = manifest.makeelement('{%s}item'%OPF_NS, nsmap={'opf':OPF_NS},
|
||||
href=self.name_to_href(name, posixpath.dirname(self.opf_name)),
|
||||
id=self.generate_manifest_id())
|
||||
mt = guess_type(posixpath.basename(name))[0]
|
||||
if not mt:
|
||||
mt = guess_type(posixpath.basename(name))[0]
|
||||
if not mt:
|
||||
mt = 'application/octest-stream'
|
||||
item.set('media-type', mt)
|
||||
manifest.append(item)
|
||||
self.fix_tail(item)
|
||||
|
||||
def fix_tail(self, item):
|
||||
'''
|
||||
Designed only to work with self closing elements after item has
|
||||
just been inserted/appended
|
||||
'''
|
||||
parent = item.getparent()
|
||||
idx = parent.index(item)
|
||||
if idx == 0:
|
||||
item.tail = parent.text
|
||||
else:
|
||||
item.tail = parent[idx-1].tail
|
||||
if idx == len(parent)-1:
|
||||
parent[idx-1].tail = parent.text
|
||||
|
||||
def generate_manifest_id(self):
|
||||
items = self.opf.xpath('//opf:manifest/opf:item[@id]',
|
||||
|
||||
@ -413,6 +413,13 @@ class EPUBOutput(OutputFormatPlugin):
|
||||
rule.style.removeProperty('margin-left')
|
||||
# padding-left breaks rendering in webkit and gecko
|
||||
rule.style.removeProperty('padding-left')
|
||||
# Change whitespace:pre to pre-line to accommodate readers that
|
||||
# cannot scroll horizontally
|
||||
for rule in stylesheet.data.cssRules.rulesOfType(CSSRule.STYLE_RULE):
|
||||
style = rule.style
|
||||
ws = style.getPropertyValue('white-space')
|
||||
if ws == 'pre':
|
||||
style.setProperty('white-space', 'pre-wrap')
|
||||
|
||||
# }}}
|
||||
|
||||
|
||||
@ -20,7 +20,7 @@ from itertools import izip
|
||||
from calibre.customize.conversion import InputFormatPlugin
|
||||
from calibre.ebooks.chardet import xml_to_unicode
|
||||
from calibre.customize.conversion import OptionRecommendation
|
||||
from calibre.constants import islinux, isfreebsd, iswindows
|
||||
from calibre.constants import islinux, isbsd, iswindows
|
||||
from calibre import unicode_path, as_unicode
|
||||
from calibre.utils.localization import get_lang
|
||||
from calibre.utils.filenames import ascii_filename
|
||||
@ -302,7 +302,7 @@ class HTMLInput(InputFormatPlugin):
|
||||
if getattr(self, '_is_case_sensitive', None) is not None:
|
||||
return self._is_case_sensitive
|
||||
if not path or not os.path.exists(path):
|
||||
return islinux or isfreebsd
|
||||
return islinux or isbsd
|
||||
self._is_case_sensitive = not (os.path.exists(path.lower()) \
|
||||
and os.path.exists(path.upper()))
|
||||
return self._is_case_sensitive
|
||||
|
||||
@ -10,7 +10,7 @@ import os, sys, re
|
||||
from urllib import unquote, quote
|
||||
from urlparse import urlparse
|
||||
|
||||
from calibre import relpath, guess_type
|
||||
from calibre import relpath, guess_type, remove_bracketed_text
|
||||
|
||||
from calibre.utils.config import tweaks
|
||||
|
||||
@ -27,20 +27,37 @@ def authors_to_string(authors):
|
||||
else:
|
||||
return ''
|
||||
|
||||
_bracket_pat = re.compile(r'[\[({].*?[})\]]')
|
||||
def author_to_author_sort(author):
|
||||
def author_to_author_sort(author, method=None):
|
||||
if not author:
|
||||
return ''
|
||||
method = tweaks['author_sort_copy_method']
|
||||
if method == 'copy' or (method == 'comma' and ',' in author):
|
||||
return u''
|
||||
sauthor = remove_bracketed_text(author).strip()
|
||||
tokens = sauthor.split()
|
||||
if len(tokens) < 2:
|
||||
return author
|
||||
author = _bracket_pat.sub('', author).strip()
|
||||
tokens = author.split()
|
||||
if tokens and tokens[-1] not in ('Inc.', 'Inc'):
|
||||
tokens = tokens[-1:] + tokens[:-1]
|
||||
if len(tokens) > 1 and method != 'nocomma':
|
||||
tokens[0] += ','
|
||||
return ' '.join(tokens)
|
||||
if method is None:
|
||||
method = tweaks['author_sort_copy_method']
|
||||
if method == u'copy':
|
||||
return author
|
||||
suffixes = set([x.lower() for x in tweaks['author_name_suffixes']])
|
||||
suffixes |= set([x+u'.' for x in suffixes])
|
||||
|
||||
last = tokens[-1].lower()
|
||||
suffix = None
|
||||
if last in suffixes:
|
||||
suffix = tokens[-1]
|
||||
tokens = tokens[:-1]
|
||||
|
||||
if method == u'comma' and u',' in u''.join(tokens):
|
||||
return author
|
||||
|
||||
atokens = tokens[-1:] + tokens[:-1]
|
||||
if suffix:
|
||||
atokens.append(suffix)
|
||||
|
||||
if method != u'nocomma' and len(atokens) > 1:
|
||||
atokens[0] += u','
|
||||
|
||||
return u' '.join(atokens)
|
||||
|
||||
def authors_to_sort_string(authors):
|
||||
return ' & '.join(map(author_to_author_sort, authors))
|
||||
|
||||
@ -41,27 +41,34 @@ field_metadata = FieldMetadata()
|
||||
|
||||
class SafeFormat(TemplateFormatter):
|
||||
|
||||
def get_value(self, key, args, kwargs):
|
||||
def get_value(self, orig_key, args, kwargs):
|
||||
if not orig_key:
|
||||
return ''
|
||||
orig_key = orig_key.lower()
|
||||
key = orig_key
|
||||
if key != 'title_sort' and key not in TOP_LEVEL_IDENTIFIERS:
|
||||
key = field_metadata.search_term_to_field_key(key)
|
||||
if key is None or (self.book and
|
||||
key not in self.book.all_field_keys()):
|
||||
if hasattr(self.book, orig_key):
|
||||
key = orig_key
|
||||
else:
|
||||
raise ValueError(_('Value: unknown field ') + orig_key)
|
||||
try:
|
||||
key = key.lower()
|
||||
if key != 'title_sort' and key not in TOP_LEVEL_IDENTIFIERS:
|
||||
key = field_metadata.search_term_to_field_key(key)
|
||||
b = self.book.get_user_metadata(key, False)
|
||||
if b and b['datatype'] == 'int' and self.book.get(key, 0) == 0:
|
||||
v = ''
|
||||
elif b and b['datatype'] == 'float' and self.book.get(key, 0.0) == 0.0:
|
||||
v = ''
|
||||
else:
|
||||
v = self.book.format_field(key, series_with_index=False)[1]
|
||||
if v is None:
|
||||
return ''
|
||||
if v == '':
|
||||
return ''
|
||||
return v
|
||||
except:
|
||||
if DEBUG:
|
||||
traceback.print_exc()
|
||||
return key
|
||||
b = None
|
||||
if b and b['datatype'] == 'int' and self.book.get(key, 0) == 0:
|
||||
v = ''
|
||||
elif b and b['datatype'] == 'float' and self.book.get(key, 0.0) == 0.0:
|
||||
v = ''
|
||||
else:
|
||||
v = self.book.format_field(key, series_with_index=False)[1]
|
||||
if v is None:
|
||||
return ''
|
||||
if v == '':
|
||||
return ''
|
||||
return v
|
||||
|
||||
composite_formatter = SafeFormat()
|
||||
|
||||
@ -75,7 +82,7 @@ class Metadata(object):
|
||||
Metadata from custom columns should be accessed via the get() method,
|
||||
passing in the lookup name for the column, for example: "#mytags".
|
||||
|
||||
Use the :meth:`is_null` method to test if a filed is null.
|
||||
Use the :meth:`is_null` method to test if a field is null.
|
||||
|
||||
This object also has functions to format fields into strings.
|
||||
|
||||
@ -106,7 +113,7 @@ class Metadata(object):
|
||||
|
||||
def is_null(self, field):
|
||||
'''
|
||||
Return True if the value of filed is null in this object.
|
||||
Return True if the value of field is null in this object.
|
||||
'null' means it is unknown or evaluates to False. So a title of
|
||||
_('Unknown') is null or a language of 'und' is null.
|
||||
|
||||
@ -614,10 +621,7 @@ class Metadata(object):
|
||||
orig_res = res
|
||||
datatype = cmeta['datatype']
|
||||
if datatype == 'text' and cmeta['is_multiple']:
|
||||
if cmeta['display'].get('is_names', False):
|
||||
res = u' & '.join(res)
|
||||
else:
|
||||
res = u', '.join(sorted(res, key=sort_key))
|
||||
res = cmeta['is_multiple']['list_to_ui'].join(res)
|
||||
elif datatype == 'series' and series_with_index:
|
||||
if self.get_extra(key) is not None:
|
||||
res = res + \
|
||||
@ -628,6 +632,12 @@ class Metadata(object):
|
||||
res = _('Yes') if res else _('No')
|
||||
elif datatype == 'rating':
|
||||
res = res/2.0
|
||||
elif datatype in ['int', 'float']:
|
||||
try:
|
||||
fmt = cmeta['display'].get('number_format', None)
|
||||
res = fmt.format(res)
|
||||
except:
|
||||
pass
|
||||
return (name, unicode(res), orig_res, cmeta)
|
||||
|
||||
# convert top-level ids into their value
|
||||
@ -655,7 +665,7 @@ class Metadata(object):
|
||||
elif datatype == 'text' and fmeta['is_multiple']:
|
||||
if isinstance(res, dict):
|
||||
res = [k + ':' + v for k,v in res.items()]
|
||||
res = u', '.join(sorted(res, key=sort_key))
|
||||
res = fmeta['is_multiple']['list_to_ui'].join(sorted(res, key=sort_key))
|
||||
elif datatype == 'series' and series_with_index:
|
||||
res = res + ' [%s]'%self.format_series_index()
|
||||
elif datatype == 'datetime':
|
||||
|
||||
@ -5,8 +5,7 @@ Created on 4 Jun 2010
|
||||
'''
|
||||
|
||||
from base64 import b64encode, b64decode
|
||||
import json
|
||||
import traceback
|
||||
import json, traceback
|
||||
|
||||
from calibre.ebooks.metadata.book import SERIALIZABLE_FIELDS
|
||||
from calibre.constants import filesystem_encoding, preferred_encoding
|
||||
@ -69,6 +68,40 @@ def object_to_unicode(obj, enc=preferred_encoding):
|
||||
return ans
|
||||
return obj
|
||||
|
||||
def encode_is_multiple(fm):
|
||||
if fm.get('is_multiple', None):
|
||||
# migrate is_multiple back to a character
|
||||
fm['is_multiple2'] = fm.get('is_multiple', {})
|
||||
dt = fm.get('datatype', None)
|
||||
if dt == 'composite':
|
||||
fm['is_multiple'] = ','
|
||||
else:
|
||||
fm['is_multiple'] = '|'
|
||||
else:
|
||||
fm['is_multiple'] = None
|
||||
fm['is_multiple2'] = {}
|
||||
|
||||
def decode_is_multiple(fm):
|
||||
im = fm.get('is_multiple2', None)
|
||||
if im:
|
||||
fm['is_multiple'] = im
|
||||
del fm['is_multiple2']
|
||||
else:
|
||||
# Must migrate the is_multiple from char to dict
|
||||
im = fm.get('is_multiple', {})
|
||||
if im:
|
||||
dt = fm.get('datatype', None)
|
||||
if dt == 'composite':
|
||||
im = {'cache_to_list': ',', 'ui_to_list': ',',
|
||||
'list_to_ui': ', '}
|
||||
elif fm.get('display', {}).get('is_names', False):
|
||||
im = {'cache_to_list': '|', 'ui_to_list': '&',
|
||||
'list_to_ui': ', '}
|
||||
else:
|
||||
im = {'cache_to_list': '|', 'ui_to_list': ',',
|
||||
'list_to_ui': ', '}
|
||||
fm['is_multiple'] = im
|
||||
|
||||
class JsonCodec(object):
|
||||
|
||||
def __init__(self):
|
||||
@ -93,9 +126,10 @@ class JsonCodec(object):
|
||||
def encode_metadata_attr(self, book, key):
|
||||
if key == 'user_metadata':
|
||||
meta = book.get_all_user_metadata(make_copy=True)
|
||||
for k in meta:
|
||||
if meta[k]['datatype'] == 'datetime':
|
||||
meta[k]['#value#'] = datetime_to_string(meta[k]['#value#'])
|
||||
for fm in meta.itervalues():
|
||||
if fm['datatype'] == 'datetime':
|
||||
fm['#value#'] = datetime_to_string(fm['#value#'])
|
||||
encode_is_multiple(fm)
|
||||
return meta
|
||||
if key in self.field_metadata:
|
||||
datatype = self.field_metadata[key]['datatype']
|
||||
@ -135,9 +169,10 @@ class JsonCodec(object):
|
||||
if key == 'classifiers':
|
||||
key = 'identifiers'
|
||||
if key == 'user_metadata':
|
||||
for k in value:
|
||||
if value[k]['datatype'] == 'datetime':
|
||||
value[k]['#value#'] = string_to_datetime(value[k]['#value#'])
|
||||
for fm in value.itervalues():
|
||||
if fm['datatype'] == 'datetime':
|
||||
fm['#value#'] = string_to_datetime(fm['#value#'])
|
||||
decode_is_multiple(fm)
|
||||
return value
|
||||
elif key in self.field_metadata:
|
||||
if self.field_metadata[key]['datatype'] == 'datetime':
|
||||
|
||||
@ -7,7 +7,7 @@ __docformat__ = 'restructuredtext en'
|
||||
lxml based OPF parser.
|
||||
'''
|
||||
|
||||
import re, sys, unittest, functools, os, uuid, glob, cStringIO, json
|
||||
import re, sys, unittest, functools, os, uuid, glob, cStringIO, json, copy
|
||||
from urllib import unquote
|
||||
from urlparse import urlparse
|
||||
|
||||
@ -453,10 +453,13 @@ class TitleSortField(MetadataField):
|
||||
|
||||
def serialize_user_metadata(metadata_elem, all_user_metadata, tail='\n'+(' '*8)):
|
||||
from calibre.utils.config import to_json
|
||||
from calibre.ebooks.metadata.book.json_codec import object_to_unicode
|
||||
from calibre.ebooks.metadata.book.json_codec import (object_to_unicode,
|
||||
encode_is_multiple)
|
||||
|
||||
for name, fm in all_user_metadata.items():
|
||||
try:
|
||||
fm = copy.copy(fm)
|
||||
encode_is_multiple(fm)
|
||||
fm = object_to_unicode(fm)
|
||||
fm = json.dumps(fm, default=to_json, ensure_ascii=False)
|
||||
except:
|
||||
@ -575,6 +578,7 @@ class OPF(object): # {{{
|
||||
self._user_metadata_ = {}
|
||||
temp = Metadata('x', ['x'])
|
||||
from calibre.utils.config import from_json
|
||||
from calibre.ebooks.metadata.book.json_codec import decode_is_multiple
|
||||
elems = self.root.xpath('//*[name() = "meta" and starts-with(@name,'
|
||||
'"calibre:user_metadata:") and @content]')
|
||||
for elem in elems:
|
||||
@ -585,6 +589,7 @@ class OPF(object): # {{{
|
||||
fm = elem.get('content')
|
||||
try:
|
||||
fm = json.loads(fm, object_hook=from_json)
|
||||
decode_is_multiple(fm)
|
||||
temp.set_user_metadata(name, fm)
|
||||
except:
|
||||
prints('Failed to read user metadata:', name)
|
||||
|
||||
@ -29,7 +29,7 @@ class Worker(Thread): # Get details {{{
|
||||
Get book details from amazons book page in a separate thread
|
||||
'''
|
||||
|
||||
def __init__(self, url, result_queue, browser, log, relevance, plugin, timeout=20):
|
||||
def __init__(self, url, result_queue, browser, log, relevance, domain, plugin, timeout=20):
|
||||
Thread.__init__(self)
|
||||
self.daemon = True
|
||||
self.url, self.result_queue = url, result_queue
|
||||
@ -37,11 +37,12 @@ class Worker(Thread): # Get details {{{
|
||||
self.relevance, self.plugin = relevance, plugin
|
||||
self.browser = browser.clone_browser()
|
||||
self.cover_url = self.amazon_id = self.isbn = None
|
||||
self.domain = self.plugin.domain
|
||||
self.domain = domain
|
||||
|
||||
months = {
|
||||
'de': {
|
||||
1 : ['jän'],
|
||||
2 : ['februar'],
|
||||
3 : ['märz'],
|
||||
5 : ['mai'],
|
||||
6 : ['juni'],
|
||||
@ -199,7 +200,8 @@ class Worker(Thread): # Get details {{{
|
||||
return
|
||||
|
||||
mi = Metadata(title, authors)
|
||||
mi.set_identifier('amazon', asin)
|
||||
idtype = 'amazon' if self.domain == 'com' else 'amazon_'+self.domain
|
||||
mi.set_identifier(idtype, asin)
|
||||
self.amazon_id = asin
|
||||
|
||||
try:
|
||||
@ -404,12 +406,30 @@ class Amazon(Source):
|
||||
'country\'s Amazon website.'), choices=AMAZON_DOMAINS),
|
||||
)
|
||||
|
||||
def get_domain_and_asin(self, identifiers):
|
||||
for key, val in identifiers.iteritems():
|
||||
key = key.lower()
|
||||
if key in ('amazon', 'asin'):
|
||||
return 'com', val
|
||||
if key.startswith('amazon_'):
|
||||
domain = key.split('_')[-1]
|
||||
if domain and domain in self.AMAZON_DOMAINS:
|
||||
return domain, val
|
||||
return None, None
|
||||
|
||||
def get_book_url(self, identifiers): # {{{
|
||||
asin = identifiers.get('amazon', None)
|
||||
if asin is None:
|
||||
asin = identifiers.get('asin', None)
|
||||
if asin:
|
||||
return ('amazon', asin, 'http://amzn.com/%s'%asin)
|
||||
domain, asin = self.get_domain_and_asin(identifiers)
|
||||
if domain and asin:
|
||||
url = None
|
||||
if domain == 'com':
|
||||
url = 'http://amzn.com/'+asin
|
||||
elif domain == 'uk':
|
||||
url = 'http://www.amazon.co.uk/dp/'+asin
|
||||
else:
|
||||
url = 'http://www.amazon.%s/dp/%s'%(domain, asin)
|
||||
if url:
|
||||
idtype = 'amazon' if self.domain == 'com' else 'amazon_'+self.domain
|
||||
return (idtype, asin, url)
|
||||
# }}}
|
||||
|
||||
@property
|
||||
@ -420,8 +440,14 @@ class Amazon(Source):
|
||||
|
||||
return domain
|
||||
|
||||
def create_query(self, log, title=None, authors=None, identifiers={}): # {{{
|
||||
domain = self.domain
|
||||
def create_query(self, log, title=None, authors=None, identifiers={}, # {{{
|
||||
domain=None):
|
||||
if domain is None:
|
||||
domain = self.domain
|
||||
|
||||
idomain, asin = self.get_domain_and_asin(identifiers)
|
||||
if idomain is not None:
|
||||
domain = idomain
|
||||
|
||||
# See the amazon detailed search page to get all options
|
||||
q = { 'search-alias' : 'aps',
|
||||
@ -433,7 +459,6 @@ class Amazon(Source):
|
||||
else:
|
||||
q['sort'] = 'relevancerank'
|
||||
|
||||
asin = identifiers.get('amazon', None)
|
||||
isbn = check_isbn(identifiers.get('isbn', None))
|
||||
|
||||
if asin is not None:
|
||||
@ -456,23 +481,22 @@ class Amazon(Source):
|
||||
if not ('field-keywords' in q or 'field-isbn' in q or
|
||||
('field-title' in q)):
|
||||
# Insufficient metadata to make an identify query
|
||||
return None
|
||||
return None, None
|
||||
|
||||
latin1q = dict([(x.encode('latin1', 'ignore'), y.encode('latin1',
|
||||
'ignore')) for x, y in
|
||||
q.iteritems()])
|
||||
udomain = domain
|
||||
if domain == 'uk':
|
||||
domain = 'co.uk'
|
||||
url = 'http://www.amazon.%s/s/?'%domain + urlencode(latin1q)
|
||||
return url
|
||||
udomain = 'co.uk'
|
||||
url = 'http://www.amazon.%s/s/?'%udomain + urlencode(latin1q)
|
||||
return url, domain
|
||||
|
||||
# }}}
|
||||
|
||||
def get_cached_cover_url(self, identifiers): # {{{
|
||||
url = None
|
||||
asin = identifiers.get('amazon', None)
|
||||
if asin is None:
|
||||
asin = identifiers.get('asin', None)
|
||||
domain, asin = self.get_domain_and_asin(identifiers)
|
||||
if asin is None:
|
||||
isbn = identifiers.get('isbn', None)
|
||||
if isbn is not None:
|
||||
@ -489,7 +513,7 @@ class Amazon(Source):
|
||||
Note this method will retry without identifiers automatically if no
|
||||
match is found with identifiers.
|
||||
'''
|
||||
query = self.create_query(log, title=title, authors=authors,
|
||||
query, domain = self.create_query(log, title=title, authors=authors,
|
||||
identifiers=identifiers)
|
||||
if query is None:
|
||||
log.error('Insufficient metadata to construct query')
|
||||
@ -549,7 +573,8 @@ class Amazon(Source):
|
||||
r'//div[@id="Results"]/descendant::td[starts-with(@id, "search:Td:")]'):
|
||||
for a in td.xpath(r'descendant::td[@class="dataColumn"]/descendant::a[@href]/span[@class="srTitle"]/..'):
|
||||
title = tostring(a, method='text', encoding=unicode).lower()
|
||||
if 'bulk pack' not in title:
|
||||
if ('bulk pack' not in title and '[audiobook]' not in
|
||||
title and '[audio cd]' not in title):
|
||||
matches.append(a.get('href'))
|
||||
break
|
||||
|
||||
@ -570,7 +595,7 @@ class Amazon(Source):
|
||||
log.error('No matches found with query: %r'%query)
|
||||
return
|
||||
|
||||
workers = [Worker(url, result_queue, br, log, i, self) for i, url in
|
||||
workers = [Worker(url, result_queue, br, log, i, domain, self) for i, url in
|
||||
enumerate(matches)]
|
||||
|
||||
for w in workers:
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
x
Reference in New Issue
Block a user