mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
[Sync] Sync with trunk. r6766
This commit is contained in:
Li Fanxi
commit
fec3cb8375
158
Changelog.yaml
158
Changelog.yaml
@ -4,6 +4,164 @@
|
||||
# for important features/bug fixes.
|
||||
# Also, each release can have new and improved recipes.
|
||||
|
||||
- version: 0.7.26
|
||||
date: 2010-10-30
|
||||
|
||||
new features:
|
||||
- title: "Check library: Allow wildcards in ignore names field"
|
||||
|
||||
bug fixes:
|
||||
- title: "Fix regression in 0.7.25 that broke reading metadata from filenames."
|
||||
|
||||
- title: "Fix regression in 0.7.25 that caused original files to be mistakenly removed when adding books recursively"
|
||||
|
||||
- title: "Fix long series/publisher causing edit metadata in bulk dialog to become very large"
|
||||
tickets: [7332]
|
||||
|
||||
- title: "Only add SONY periodical code to downloaded news if output profile is set to one of the SONY reader profiles. This is needed because the ever delightful Stanza crashes and burns when an EPUB has the periodical code"
|
||||
|
||||
improved recipes:
|
||||
- El Periodico
|
||||
- New Zealand Herald
|
||||
|
||||
new recipes:
|
||||
- title: "Taggeschau.de"
|
||||
author: "Florian Andreas Pfaff"
|
||||
|
||||
- title: "Gamespot Reviews"
|
||||
author: "Marc Tonsing"
|
||||
|
||||
- version: 0.7.25
|
||||
date: 2010-10-29
|
||||
|
||||
new features:
|
||||
- title: "Add support for the SONY periodical format."
|
||||
description: "This means that news downloaded by calibre and sent to a newer SONY device (350/650/900) should appear in the Periodicals section and have the special periodicals navigation user interface"
|
||||
type: major
|
||||
|
||||
- title: "Content server: Make the new browsing interface the default. The old interface can be accessed at /old"
|
||||
|
||||
- title: "Content server: Allow running of content server as a WSGI application within another server. Add tutorial for this to the User Manual."
|
||||
|
||||
- title: "Support for the Pico Life reader, Kobo Wifi and HTC Aria"
|
||||
|
||||
- title: "Content server: Add a new --url-prefix command line option to ease the use of the server with a reverse proxy"
|
||||
|
||||
- title: "New social metadata plugin for Amazon that does not rely on AWS. Since Amazon broke AWS, it is recommended you upgrade to this version if you use metadata from Amazon"
|
||||
|
||||
- title: "Add a tweak to specify the fonts used when geenrating the default cover"
|
||||
|
||||
- title: "Add an output profile for generic Tablet devices"
|
||||
tickets: [7289]
|
||||
|
||||
- title: "SONY driver: Allow sorting of collections by arbitrary field via a new tweak."
|
||||
|
||||
- title: "Content server: Make /mobile a little prettier"
|
||||
|
||||
- title: "Add button to 'Library Check' to automatically delete spurious files and folders"
|
||||
|
||||
bug fixes:
|
||||
- title: "FB2 Input: Lots of love. Handle stylesheets and style attributes. Make parsinf malformed FB2 files more robust."
|
||||
tickets: [7219, 7230]
|
||||
|
||||
- title: "Fix auto send of news to device with multiple calibre libraries. The fix means that if you have any pending news to be sent, it will be ignored after the update. Future news downloads will once again be automatically sent to the device."
|
||||
|
||||
- title: "MOBI Output: Conversion of super/sub scripts now handles nested tags."
|
||||
tickets: [7264]
|
||||
|
||||
- title: "Conversion pipeline: Fix parsing of XML encoding declarations."
|
||||
tickets: [7328]
|
||||
|
||||
- title: "Pandigital (Kobo): Upload thumbnails to correct location"
|
||||
tickets: [7165]
|
||||
|
||||
- title: "Fix auto emailed news with non asci characters in title not being deliverd to Kindle"
|
||||
tickets: [7322]
|
||||
|
||||
- title: "Read metadata only after on import plugins have run when adding books to GUI"
|
||||
tickets: [7245]
|
||||
|
||||
- title: "Various fixes for bugs caused by non ascii temporary paths on windows with non UTF-8 filesystem encodings"
|
||||
tickets: [7288]
|
||||
|
||||
- title: "Various fixes/enhancements to SNB Output"
|
||||
|
||||
- title: "Allow Tag editor in edit metadata dialog to be used even if tags have been changed"
|
||||
tickets: [7298]
|
||||
|
||||
- title: "Fix crash on some OS X machines when Preferences->Conversion->Output is clicked"
|
||||
|
||||
- title: "MOBI indexing: Fix last entry missing sometimes"
|
||||
tickets: [6595]
|
||||
|
||||
- title: "Fix regression causing books to be deselected after sending to device"
|
||||
tickets: [7271]
|
||||
|
||||
- title: "Conversion pipeline: Fix rescaling of GIF images not working"
|
||||
tickets: [7306]
|
||||
|
||||
- title: "Update PDF metadata/conversion libraries in windows build"
|
||||
|
||||
- title: "Fix timezone bug when searching on date fields"
|
||||
tickets: [7300]
|
||||
|
||||
- title: "Fix regression that caused the viewr to crash if the main application is closed"
|
||||
tickets: [7276]
|
||||
|
||||
- title: "Fix bug causing a spurious metadata.opf file to be written at the root of the calibre library when adding books"
|
||||
|
||||
- title: "Use the same title casing algorithm in all places"
|
||||
|
||||
- title: "Fix bulk edit of dual state boolean custom columns"
|
||||
|
||||
- title: "Increase image size for comics in Kindle DX profile for better conversion of comics to PDF"
|
||||
|
||||
- title: "Fix restore db to not dies when conflicting custom columns are encountered and report conflicting columns errors. Fix exceptions when referencing invalid _index fields."
|
||||
|
||||
- title: "Fix auto merge books not respecting article sort tweak"
|
||||
tickets: [7147]
|
||||
|
||||
- title: "Linux device drivers: Fix udisks based ejecting for devices with multiple nodes"
|
||||
|
||||
- title: "Linux device mounting: Mount the drive with the lowest kernel name as main memory"
|
||||
|
||||
- title: "Fix use of numeric fields in templates"
|
||||
|
||||
- title: "EPUB Input: Handle EPUB files with multiple OPF files."
|
||||
tickets: [7229]
|
||||
|
||||
- title: "Setting EPUB metadata: Fix date format. Fix language being overwritten by und when unspecified. Fix empty ISBN identifier being created"
|
||||
|
||||
- title: "Fix cannot delete a Series listing from List view also dismiss fetch metadata dialog when no metadata found automatically"
|
||||
tickets: [7221, 7220]
|
||||
|
||||
- title: "Content server: Handle switch library in GUI gracefully"
|
||||
|
||||
- title: "calibre-server: Use cherrypy implementation of --pidfile and --daemonize"
|
||||
|
||||
new recipes:
|
||||
- title: "Ming Pao"
|
||||
author: "Eddie Lau"
|
||||
|
||||
- title: "lenta.ru"
|
||||
author: "Nikolai Kotchetkov"
|
||||
|
||||
- title: "frazpc.pl"
|
||||
author: "Tomasz Dlugosz"
|
||||
|
||||
- title: "Perfil and The Economic Collapse Blog"
|
||||
author: "Darko Miletic"
|
||||
|
||||
- title: "STNN"
|
||||
author: "Larry Chan"
|
||||
|
||||
improved recipes:
|
||||
- CubaDebate
|
||||
- El Pais
|
||||
- Fox News
|
||||
- New Scientist
|
||||
- The Economic Times of India
|
||||
|
||||
- version: 0.7.24
|
||||
date: 2010-10-17
|
||||
|
||||
|
||||
@ -208,6 +208,8 @@ h2.library_name {
|
||||
|
||||
}
|
||||
|
||||
.toplevel li a { text-decoration: none; }
|
||||
|
||||
.toplevel li img {
|
||||
vertical-align: middle;
|
||||
margin-right: 1em;
|
||||
@ -261,9 +263,16 @@ h2.library_name {
|
||||
|
||||
}
|
||||
|
||||
.category div.category-item span.href { display: none }
|
||||
.category div.category-item a { text-decoration: none; color: inherit; }
|
||||
|
||||
#groups span.load_href { display: none }
|
||||
#groups a.load_href {
|
||||
text-decoration: none;
|
||||
color: inherit;
|
||||
font-size: medium;
|
||||
font-weight: normal;
|
||||
padding: 0;
|
||||
padding-left: 0.5em;
|
||||
}
|
||||
|
||||
#groups h3 {
|
||||
font-weight: bold;
|
||||
|
||||
@ -116,7 +116,7 @@ function toplevel() {
|
||||
$(".sort_select").hide();
|
||||
|
||||
$(".toplevel li").click(function() {
|
||||
var href = $(this).children("span.url").text();
|
||||
var href = $(this).children("a").attr('href');
|
||||
window.location = href;
|
||||
});
|
||||
|
||||
@ -133,7 +133,7 @@ function render_error(msg) {
|
||||
// Category feed {{{
|
||||
|
||||
function category_clicked() {
|
||||
var href = $(this).find("span.href").html();
|
||||
var href = $(this).find("a").attr('href');
|
||||
window.location = href;
|
||||
}
|
||||
|
||||
@ -151,7 +151,7 @@ function category() {
|
||||
|
||||
change: function(event, ui) {
|
||||
if (ui.newContent) {
|
||||
var href = ui.newContent.children("span.load_href").html();
|
||||
var href = ui.newContent.prev().children("a.load_href").attr('href');
|
||||
ui.newContent.children(".loading").show();
|
||||
if (href) {
|
||||
$.ajax({
|
||||
|
||||
3385
resources/content_server/read/monocle.js
Normal file
3385
resources/content_server/read/monocle.js
Normal file
File diff suppressed because it is too large
Load Diff
BIN
resources/images/news/perfil.png
Normal file
BIN
resources/images/news/perfil.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 781 B |
@ -2,7 +2,7 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
||||
__copyright__ = '30 October 2010, Jordi Balcells based on an earlier recipe by Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
elperiodico.cat
|
||||
'''
|
||||
@ -12,8 +12,8 @@ from calibre.ebooks.BeautifulSoup import Tag
|
||||
|
||||
class ElPeriodico_cat(BasicNewsRecipe):
|
||||
title = 'El Periodico de Catalunya'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'Noticias desde Catalunya'
|
||||
__author__ = 'Jordi Balcells/Darko Miletic'
|
||||
description = 'Noticies des de Catalunya'
|
||||
publisher = 'elperiodico.cat'
|
||||
category = 'news, politics, Spain, Catalunya'
|
||||
oldest_article = 2
|
||||
@ -33,15 +33,25 @@ class ElPeriodico_cat(BasicNewsRecipe):
|
||||
|
||||
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
|
||||
|
||||
feeds = [(u"Tota l'edició", u'http://www.elperiodico.cat/rss.asp?id=46')]
|
||||
feeds = [(u'Portada', u'http://www.elperiodico.cat/ca/rss/rss_portada.xml'),
|
||||
(u'Internacional', u'http://www.elperiodico.cat/ca/rss/internacional/rss.xml'),
|
||||
(u'Societat', u'http://www.elperiodico.cat/ca/rss/societat/rss.xml'),
|
||||
(u'Ci\xe8ncia i tecnologia', u'http://www.elperiodico.cat/ca/rss/ciencia-i-tecnologia/rss.xml'),
|
||||
(u'Esports', u'http://www.elperiodico.cat/ca/rss/esports/rss.xml'),
|
||||
(u'Gent', u'http://www.elperiodico.cat/ca/rss/gent/rss.xml'),
|
||||
(u'Opini\xf3', u'http://www.elperiodico.cat/ca/rss/opinio/rss.xml'),
|
||||
(u'Pol\xedtica', u'http://www.elperiodico.cat/ca/rss/politica/rss.xml'),
|
||||
(u'Barcelona', u'http://www.elperiodico.cat/ca/rss/barcelona/rss.xml'),
|
||||
(u'Economia', u'http://www.elperiodico.cat/ca/rss/economia/rss.xml'),
|
||||
(u'Cultura i espectacles', u'http://www.elperiodico.cat/ca/rss/cultura-i-espectacles/rss.xml'),
|
||||
(u'Tele', u'http://www.elperiodico.cat/ca/rss/tele/rss.xml')]
|
||||
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'noticia'})]
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'titularnoticia'}),
|
||||
dict(name='div', attrs={'class':'noticia_completa'})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name=['object','link','script'])
|
||||
,dict(name='ul',attrs={'class':'herramientasDeNoticia'})
|
||||
,dict(name='div', attrs={'id':'inferiores'})
|
||||
remove_tags = [dict(name='div', attrs={'class':['opcionb','opcionb last','columna_noticia']}),
|
||||
dict(name='span', attrs={'class':'opcionesnoticia'})
|
||||
]
|
||||
|
||||
def print_version(self, url):
|
||||
|
||||
@ -2,17 +2,17 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
||||
__copyright__ = '30 October 2010, Jordi Balcells based on an earlier recipe by Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
elperiodico.com
|
||||
elperiodico.cat
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from calibre.ebooks.BeautifulSoup import Tag
|
||||
|
||||
class ElPeriodico_esp(BasicNewsRecipe):
|
||||
class ElPeriodico_cat(BasicNewsRecipe):
|
||||
title = 'El Periodico de Catalunya'
|
||||
__author__ = 'Darko Miletic'
|
||||
__author__ = 'Jordi Balcells/Darko Miletic'
|
||||
description = 'Noticias desde Catalunya'
|
||||
publisher = 'elperiodico.com'
|
||||
category = 'news, politics, Spain, Catalunya'
|
||||
@ -33,15 +33,25 @@ class ElPeriodico_esp(BasicNewsRecipe):
|
||||
|
||||
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
|
||||
|
||||
feeds = [(u"Toda la edición", u'http://www.elperiodico.com/rss.asp?id=46')]
|
||||
feeds = [(u'Portada', u'http://www.elperiodico.com/es/rss/rss_portada.xml'),
|
||||
(u'Internacional', u'http://elperiodico.com/es/rss/internacional/rss.xml'),
|
||||
(u'Sociedad', u'http://elperiodico.com/es/rss/sociedad/rss.xml'),
|
||||
(u'Ciencia y Tecnolog\xeda', u'http://elperiodico.com/es/rss/ciencia-y-tecnologia/rss.xml'),
|
||||
(u'Deportes', u'http://elperiodico.com/es/rss/deportes/rss.xml'),
|
||||
(u'Gente', u'http://elperiodico.com/es/rss/gente/rss.xml'),
|
||||
(u'Opini\xf3n', u'http://elperiodico.com/es/rss/opinion/rss.xml'),
|
||||
(u'Pol\xedtica', u'http://elperiodico.com/es/rss/politica/rss.xml'),
|
||||
(u'Barcelona', u'http://elperiodico.com/es/rss/barcelona/rss.xml'),
|
||||
(u'Econom\xeda', u'http://elperiodico.com/es/rss/economia/rss.xml'),
|
||||
(u'Cultura y espect\xe1culos', u'http://elperiodico.com/es/rss/cultura-y-espectaculos/rss.xml'),
|
||||
(u'Tele', u'http://elperiodico.com/es/rss/cultura-y-espectaculos/rss.xml')]
|
||||
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'noticia'})]
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'titularnoticia'}),
|
||||
dict(name='div', attrs={'class':'noticia_completa'})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name=['object','link','script'])
|
||||
,dict(name='ul',attrs={'class':'herramientasDeNoticia'})
|
||||
,dict(name='div', attrs={'id':'inferiores'})
|
||||
remove_tags = [dict(name='div', attrs={'class':['opcionb','opcionb last','columna_noticia']}),
|
||||
dict(name='span', attrs={'class':'opcionesnoticia'})
|
||||
]
|
||||
|
||||
def print_version(self, url):
|
||||
|
||||
41
resources/recipes/gamespot.recipe
Normal file
41
resources/recipes/gamespot.recipe
Normal file
@ -0,0 +1,41 @@
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = u'Marc T\xf6nsing'
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class GamespotCom(BasicNewsRecipe):
|
||||
|
||||
title = u'Gamespot.com Reviews'
|
||||
description = 'review articles from gamespot.com'
|
||||
language = 'en'
|
||||
__author__ = u'Marc T\xf6nsing'
|
||||
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 40
|
||||
remove_empty_feeds = True
|
||||
no_stylesheets = True
|
||||
no_javascript = True
|
||||
|
||||
feeds = [
|
||||
('PC Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=5'),
|
||||
('XBOX 360 Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1029'),
|
||||
('Wii Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1031'),
|
||||
('PlayStation 3 Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1028'),
|
||||
('PlayStation 2 Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=7'),
|
||||
('PlayStation Portable Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1024'),
|
||||
('Nintendo DS Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1026'),
|
||||
('iPhone Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1049'),
|
||||
]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':'top_bar'}),
|
||||
dict(name='div', attrs={'class':'video_embed'})
|
||||
]
|
||||
|
||||
def get_cover_url(self):
|
||||
return 'http://image.gamespotcdn.net/gamespot/shared/gs5/gslogo_bw.gif'
|
||||
|
||||
def get_article_url(self, article):
|
||||
return article.get('link') + '?print=1'
|
||||
|
||||
|
||||
177
resources/recipes/lenta_ru.recipe
Normal file
177
resources/recipes/lenta_ru.recipe
Normal file
@ -0,0 +1,177 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
'''
|
||||
Lenta.ru
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.feedparser import parse
|
||||
from calibre.ebooks.BeautifulSoup import Tag
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
import re
|
||||
|
||||
class LentaRURecipe(BasicNewsRecipe):
|
||||
title = u'Lenta.ru: \u041d\u043e\u0432\u043e\u0441\u0442\u0438'
|
||||
__author__ = 'Nikolai Kotchetkov'
|
||||
publisher = 'lenta.ru'
|
||||
category = 'news, Russia'
|
||||
description = u'''\u0415\u0436\u0435\u0434\u043d\u0435\u0432\u043d\u0430\u044f
|
||||
\u0438\u043d\u0442\u0435\u0440\u043d\u0435\u0442-\u0433\u0430\u0437\u0435\u0442\u0430.
|
||||
\u041d\u043e\u0432\u043e\u0441\u0442\u0438 \u0441\u043e
|
||||
\u0432\u0441\u0435\u0433\u043e \u043c\u0438\u0440\u0430 \u043d\u0430
|
||||
\u0440\u0443\u0441\u0441\u043a\u043e\u043c
|
||||
\u044f\u0437\u044b\u043a\u0435'''
|
||||
description = u'Ежедневная интернет-газета. Новости со всего мира на русском языке'
|
||||
oldest_article = 3
|
||||
max_articles_per_feed = 100
|
||||
|
||||
masthead_url = u'http://img.lenta.ru/i/logowrambler.gif'
|
||||
cover_url = u'http://img.lenta.ru/i/logowrambler.gif'
|
||||
|
||||
#Add feed names if you want them to be sorted (feeds of this list appear first)
|
||||
sortOrder = [u'_default', u'В России', u'б.СССР', u'В мире']
|
||||
|
||||
encoding = 'cp1251'
|
||||
language = 'ru'
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
recursions = 0
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : category
|
||||
, 'publisher' : publisher
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
|
||||
keep_only_tags = [dict(name='td', attrs={'class':['statya','content']})]
|
||||
|
||||
remove_tags_after = [dict(name='p', attrs={'class':'links'}), dict(name='div', attrs={'id':'readers-block'})]
|
||||
|
||||
remove_tags = [dict(name='table', attrs={'class':['vrezka','content']}), dict(name='div', attrs={'class':'b240'}), dict(name='div', attrs={'id':'readers-block'}), dict(name='p', attrs={'class':'links'})]
|
||||
|
||||
feeds = [u'http://lenta.ru/rss/']
|
||||
|
||||
extra_css = 'h1 {font-size: 1.2em; margin: 0em 0em 0em 0em;} h2 {font-size: 1.0em; margin: 0em 0em 0em 0em;} h3 {font-size: 0.8em; margin: 0em 0em 0em 0em;}'
|
||||
|
||||
def parse_index(self):
|
||||
try:
|
||||
feedData = parse(self.feeds[0])
|
||||
if not feedData:
|
||||
raise NotImplementedError
|
||||
self.log("parse_index: Feed loaded successfully.")
|
||||
if feedData.feed.has_key('title'):
|
||||
self.title = feedData.feed.title
|
||||
self.log("parse_index: Title updated to: ", self.title)
|
||||
if feedData.feed.has_key('image'):
|
||||
self.log("HAS IMAGE!!!!")
|
||||
|
||||
def get_virtual_feed_articles(feed):
|
||||
if feeds.has_key(feed):
|
||||
return feeds[feed][1]
|
||||
self.log("Adding new feed: ", feed)
|
||||
articles = []
|
||||
feeds[feed] = (feed, articles)
|
||||
return articles
|
||||
|
||||
feeds = {}
|
||||
|
||||
#Iterate feed items and distribute articles using tags
|
||||
for item in feedData.entries:
|
||||
link = item.get('link', '');
|
||||
title = item.get('title', '');
|
||||
if '' == link or '' == title:
|
||||
continue
|
||||
article = {'title':title, 'url':link, 'description':item.get('description', ''), 'date':item.get('date', ''), 'content':''};
|
||||
if not item.has_key('tags'):
|
||||
get_virtual_feed_articles('_default').append(article)
|
||||
continue
|
||||
for tag in item.tags:
|
||||
addedToDefault = False
|
||||
term = tag.get('term', '')
|
||||
if '' == term:
|
||||
if (not addedToDefault):
|
||||
get_virtual_feed_articles('_default').append(article)
|
||||
continue
|
||||
get_virtual_feed_articles(term).append(article)
|
||||
|
||||
#Get feed list
|
||||
#Select sorted feeds first of all
|
||||
result = []
|
||||
for feedName in self.sortOrder:
|
||||
if (not feeds.has_key(feedName)): continue
|
||||
result.append(feeds[feedName])
|
||||
del feeds[feedName]
|
||||
result = result + feeds.values()
|
||||
|
||||
return result
|
||||
|
||||
except Exception, err:
|
||||
self.log(err)
|
||||
raise NotImplementedError
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
return self.adeify_images(soup)
|
||||
|
||||
def postprocess_html(self, soup, first_fetch):
|
||||
#self.log('Original: ', soup.prettify())
|
||||
|
||||
contents = Tag(soup, 'div')
|
||||
|
||||
#Extract tags with given attributes
|
||||
extractElements = {'div' : [{'id' : 'readers-block'}]}
|
||||
|
||||
#Remove all elements that were not extracted before
|
||||
for tag, attrs in extractElements.iteritems():
|
||||
for attr in attrs:
|
||||
garbage = soup.findAll(tag, attr)
|
||||
if garbage:
|
||||
for pieceOfGarbage in garbage:
|
||||
pieceOfGarbage.extract()
|
||||
|
||||
#Find article text using header
|
||||
#and add all elements to contents
|
||||
element = soup.find({'h1' : True, 'h2' : True})
|
||||
if (element):
|
||||
element.name = 'h1'
|
||||
while element:
|
||||
nextElement = element.nextSibling
|
||||
element.extract()
|
||||
contents.insert(len(contents.contents), element)
|
||||
element = nextElement
|
||||
|
||||
#Place article date after header
|
||||
dates = soup.findAll(text=re.compile('\d{2}\.\d{2}\.\d{4}, \d{2}:\d{2}:\d{2}'))
|
||||
if dates:
|
||||
for date in dates:
|
||||
for string in date:
|
||||
parent = date.parent
|
||||
if (parent and isinstance(parent, Tag) and 'div' == parent.name and 'dt' == parent['class']):
|
||||
#Date div found
|
||||
parent.extract()
|
||||
parent['style'] = 'font-size: 0.5em; color: gray; font-family: monospace;'
|
||||
contents.insert(1, parent)
|
||||
break
|
||||
|
||||
#Place article picture after date
|
||||
pic = soup.find('img')
|
||||
if pic:
|
||||
picDiv = Tag(soup, 'div')
|
||||
picDiv['style'] = 'width: 100%; text-align: center;'
|
||||
pic.extract()
|
||||
picDiv.insert(0, pic)
|
||||
title = pic.get('title', None)
|
||||
if title:
|
||||
titleDiv = Tag(soup, 'div')
|
||||
titleDiv['style'] = 'font-size: 0.5em;'
|
||||
titleDiv.insert(0, title)
|
||||
picDiv.insert(1, titleDiv)
|
||||
contents.insert(2, picDiv)
|
||||
|
||||
body = soup.find('td', {'class':['statya','content']})
|
||||
if body:
|
||||
body.replaceWith(contents)
|
||||
|
||||
#self.log('Result: ', soup.prettify())
|
||||
return soup
|
||||
|
||||
@ -1,53 +1,79 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>'
|
||||
__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010, Louis Gesbert <meta at antislash dot info>'
|
||||
'''
|
||||
Mediapart
|
||||
'''
|
||||
|
||||
import re, string
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
||||
from calibre.ebooks.BeautifulSoup import Tag
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Mediapart(BasicNewsRecipe):
|
||||
title = 'Mediapart'
|
||||
__author__ = 'Mathieu Godlewski <mathieu at godlewski.fr>'
|
||||
__author__ = 'Mathieu Godlewski'
|
||||
description = 'Global news in french from online newspapers'
|
||||
oldest_article = 7
|
||||
language = 'fr'
|
||||
needs_subscription = True
|
||||
|
||||
max_articles_per_feed = 50
|
||||
no_stylesheets = True
|
||||
|
||||
html2lrf_options = ['--base-font-size', '10']
|
||||
cover_url = 'http://www.mediapart.fr/sites/all/themes/mediapart/mediapart/images/annonce.jpg'
|
||||
|
||||
feeds = [
|
||||
('Les articles', 'http://www.mediapart.fr/articles/feed'),
|
||||
]
|
||||
|
||||
preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE|re.DOTALL), i[1]) for i in
|
||||
[
|
||||
(r'<div class="print-title">([^>]+)</div>', lambda match : '<h2>'+match.group(1)+'</h2>'),
|
||||
(r'<p>Mediapart\.fr</p>', lambda match : ''),
|
||||
(r'<p[^>]*>[\s]*</p>', lambda match : ''),
|
||||
(r'<p><a href="[^\.]+\.pdf">[^>]*</a></p>', lambda match : ''),
|
||||
# -- print-version has poor quality on this website, better do the conversion ourselves
|
||||
#
|
||||
# preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE|re.DOTALL), i[1]) for i in
|
||||
# [
|
||||
# (r'<div class="print-title">([^>]+)</div>', lambda match : '<h2>'+match.group(1)+'</h2>'),
|
||||
# (r'<span class=\'auteur_staff\'>[^>]+<a title=\'[^\']*\'[^>]*>([^<]*)</a>[^<]*</span>',
|
||||
# lambda match : '<i>'+match.group(1)+'</i>'),
|
||||
# (r'\'', lambda match: '’'),
|
||||
# ]
|
||||
# ]
|
||||
#
|
||||
# remove_tags = [ dict(name='div', attrs={'class':'print-source_url'}),
|
||||
# dict(name='div', attrs={'class':'print-links'}),
|
||||
# dict(name='img', attrs={'src':'entete_article.png'}),
|
||||
# dict(name='br') ]
|
||||
#
|
||||
# def print_version(self, url):
|
||||
# raw = self.browser.open(url).read()
|
||||
# soup = BeautifulSoup(raw.decode('utf8', 'replace'))
|
||||
# div = soup.find('div', {'id':re.compile('node-\d+')})
|
||||
# if div is None:
|
||||
# return None
|
||||
# article_id = string.replace(div['id'], 'node-', '')
|
||||
# if article_id is None:
|
||||
# return None
|
||||
# return 'http://www.mediapart.fr/print/'+article_id
|
||||
|
||||
# -- Non-print version [dict(name='div', attrs={'class':'advert'})]
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='h1', attrs={'class':'title'}),
|
||||
dict(name='div', attrs={'class':'page_papier_detail'}),
|
||||
]
|
||||
]
|
||||
|
||||
remove_tags = [ dict(name='div', attrs={'class':'print-source_url'}),
|
||||
dict(name='div', attrs={'class':'print-links'}),
|
||||
dict(name='img', attrs={'src':'entete_article.png'}),
|
||||
]
|
||||
def preprocess_html(self,soup):
|
||||
for title in soup.findAll('div', {'class':'titre'}):
|
||||
tag = Tag(soup, 'h3')
|
||||
title.replaceWith(tag)
|
||||
tag.insert(0,title)
|
||||
return soup
|
||||
|
||||
# -- Handle login
|
||||
|
||||
def get_browser(self):
|
||||
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['name'] = self.username
|
||||
br['pass'] = self.password
|
||||
br.submit()
|
||||
return br
|
||||
|
||||
def print_version(self, url):
|
||||
raw = self.browser.open(url).read()
|
||||
soup = BeautifulSoup(raw.decode('utf8', 'replace'))
|
||||
div = soup.find('div', {'class':'node node-type-article'})
|
||||
if div is None:
|
||||
return None
|
||||
article_id = string.replace(div['id'], 'node-', '')
|
||||
if article_id is None:
|
||||
return None
|
||||
return 'http://www.mediapart.fr/print/'+article_id
|
||||
|
||||
@ -1,74 +1,43 @@
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
import re
|
||||
|
||||
class NewZealandHerald(BasicNewsRecipe):
|
||||
|
||||
title = 'New Zealand Herald'
|
||||
__author__ = 'Krittika Goyal'
|
||||
__author__ = 'Kovid Goyal'
|
||||
description = 'Daily news'
|
||||
timefmt = ' [%d %b, %Y]'
|
||||
language = 'en_NZ'
|
||||
oldest_article = 2.5
|
||||
|
||||
no_stylesheets = True
|
||||
remove_tags_before = dict(name='div', attrs={'class':'contentContainer left eight'})
|
||||
remove_tags_after = dict(name='div', attrs={'class':'callToAction'})
|
||||
remove_tags = [
|
||||
dict(name='iframe'),
|
||||
dict(name='div', attrs={'class':['sectionHeader', 'tools','callToAction', 'contentContainer right two nopad relatedColumn']}),
|
||||
#dict(name='div', attrs={'id':['shareContainer']}),
|
||||
#dict(name='form', attrs={'onsubmit':"return verifySearch(this.w,'Keyword, citation, or #author')"}),
|
||||
#dict(name='table', attrs={'cellspacing':'0'}),
|
||||
feeds = [
|
||||
('Business',
|
||||
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000003.xml'),
|
||||
('World',
|
||||
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000002.xml'),
|
||||
('National',
|
||||
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000001.xml'),
|
||||
('Entertainment',
|
||||
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_001501119.xml'),
|
||||
('Travel',
|
||||
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000007.xml'),
|
||||
('Opinion',
|
||||
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000466.xml'),
|
||||
('Life & Style',
|
||||
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000006.xml'),
|
||||
('Technology'
|
||||
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000005.xml'),
|
||||
('Sport',
|
||||
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000004.xml'),
|
||||
('Motoring',
|
||||
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000009.xml'),
|
||||
('Property',
|
||||
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000008.xml'),
|
||||
]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
table = soup.find('table')
|
||||
if table is not None:
|
||||
table.extract()
|
||||
return soup
|
||||
|
||||
#TO GET ARTICLES IN SECTION
|
||||
def nz_parse_section(self, url):
|
||||
soup = self.index_to_soup(url)
|
||||
div = soup.find(attrs={'class':'col-300 categoryList'})
|
||||
date = div.find(attrs={'class':'link-list-heading'})
|
||||
|
||||
current_articles = []
|
||||
for x in date.findAllNext(attrs={'class':['linkList', 'link-list-heading']}):
|
||||
if x.get('class') == 'link-list-heading': break
|
||||
for li in x.findAll('li'):
|
||||
a = li.find('a', href=True)
|
||||
if a is None:
|
||||
continue
|
||||
title = self.tag_to_string(a)
|
||||
url = a.get('href', False)
|
||||
if not url or not title:
|
||||
continue
|
||||
if url.startswith('/'):
|
||||
url = 'http://www.nzherald.co.nz'+url
|
||||
self.log('\t\tFound article:', title)
|
||||
self.log('\t\t\t', url)
|
||||
current_articles.append({'title': title, 'url':url,
|
||||
'description':'', 'date':''})
|
||||
|
||||
return current_articles
|
||||
|
||||
|
||||
# To GET SECTIONS
|
||||
def parse_index(self):
|
||||
feeds = []
|
||||
for title, url in [
|
||||
('National',
|
||||
'http://www.nzherald.co.nz/nz/news/headlines.cfm?c_id=1'),
|
||||
('World',
|
||||
'http://www.nzherald.co.nz/world/news/headlines.cfm?c_id=2'),
|
||||
('Politics',
|
||||
'http://www.nzherald.co.nz/politics/news/headlines.cfm?c_id=280'),
|
||||
('Crime',
|
||||
'http://www.nzherald.co.nz/crime/news/headlines.cfm?c_id=30'),
|
||||
('Environment',
|
||||
'http://www.nzherald.co.nz/environment/news/headlines.cfm?c_id=39'),
|
||||
]:
|
||||
articles = self.nz_parse_section(url)
|
||||
if articles:
|
||||
feeds.append((title, articles))
|
||||
return feeds
|
||||
def print_version(self, url):
|
||||
m = re.search(r'objectid=(\d+)', url)
|
||||
if m is None:
|
||||
return url
|
||||
return 'http://www.nzherald.co.nz/news/print.cfm?pnum=1&objectid=' + m.group(1)
|
||||
|
||||
|
||||
66
resources/recipes/perfil.recipe
Normal file
66
resources/recipes/perfil.recipe
Normal file
@ -0,0 +1,66 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
perfil.com
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Perfil(BasicNewsRecipe):
|
||||
title = 'Perfil'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'Noticias de Argentina y el resto del mundo'
|
||||
publisher = 'perfil.com'
|
||||
category = 'news, politics, Argentina'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 200
|
||||
no_stylesheets = True
|
||||
encoding = 'cp1252'
|
||||
use_embedded_content = False
|
||||
language = 'es'
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.perfil.com/export/sites/diarioperfil/arte/10/logo_perfilcom_mm.gif'
|
||||
extra_css = """
|
||||
body{font-family: Arial,Helvetica,sans-serif }
|
||||
.seccion{border-bottom: 1px dotted #666666; text-transform: uppercase; font-size: x-large}
|
||||
.foto1 h1{font-size: x-small}
|
||||
h1{font-family: Georgia,"Times New Roman",serif}
|
||||
img{margin-bottom: 0.4em}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : category
|
||||
, 'publisher' : publisher
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
remove_tags = [
|
||||
dict(name=['iframe','embed','object','base','meta','link'])
|
||||
,dict(name='a', attrs={'href':'#comentarios'})
|
||||
,dict(name='div', attrs={'class':'foto3'})
|
||||
,dict(name='img', attrs={'alt':'ampliar'})
|
||||
]
|
||||
keep_only_tags=[dict(attrs={'class':['bd468a','cuerpoSuperior']})]
|
||||
remove_attributes=['onload','lang','width','height','border']
|
||||
|
||||
feeds = [
|
||||
(u'Ultimo momento' , u'http://www.perfil.com/rss/ultimomomento.xml')
|
||||
,(u'Politica' , u'http://www.perfil.com/rss/politica.xml' )
|
||||
,(u'Policia' , u'http://www.perfil.com/rss/policia.xml' )
|
||||
,(u'Internacionales', u'http://www.perfil.com/rss/internacional.xml')
|
||||
,(u'Economia' , u'http://www.perfil.com/rss/economia.xml' )
|
||||
,(u'Deportes' , u'http://www.perfil.com/rss/deportes.xml' )
|
||||
,(u'Opinion' , u'http://www.perfil.com/rss/columnistas.xml' )
|
||||
,(u'Sociedad' , u'http://www.perfil.com/rss/sociedad.xml' )
|
||||
,(u'Cultura' , u'http://www.perfil.com/rss/cultura.xml' )
|
||||
,(u'Espectaculos' , u'http://www.perfil.com/rss/espectaculos.xml' )
|
||||
,(u'Ciencia' , u'http://www.perfil.com/rss/ciencia.xml' )
|
||||
,(u'Salud' , u'http://www.perfil.com/rss/salud.xml' )
|
||||
,(u'Tecnologia' , u'http://www.perfil.com/rss/tecnologia.xml' )
|
||||
]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
return soup
|
||||
53
resources/recipes/rue89.recipe
Normal file
53
resources/recipes/rue89.recipe
Normal file
@ -0,0 +1,53 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Louis Gesbert <meta at antislash dot info>'
|
||||
'''
|
||||
Rue89
|
||||
'''
|
||||
|
||||
__author__ = '2010, Louis Gesbert <meta at antislash dot info>'
|
||||
|
||||
import re
|
||||
from calibre.ebooks.BeautifulSoup import Tag
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Rue89(BasicNewsRecipe):
|
||||
title = 'Rue89'
|
||||
__author__ = 'Louis Gesbert'
|
||||
description = 'Popular free french news website'
|
||||
title = u'Rue89'
|
||||
language = 'fr'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 50
|
||||
|
||||
feeds = [(u'La Une', u'http://www.rue89.com/homepage/feed')]
|
||||
|
||||
no_stylesheets = True
|
||||
|
||||
preprocess_regexps = [
|
||||
(re.compile(r'<(/?)h2>', re.IGNORECASE|re.DOTALL),
|
||||
lambda match : '<'+match.group(1)+'h3>'),
|
||||
(re.compile(r'<div class="print-title">([^>]+)</div>', re.IGNORECASE|re.DOTALL),
|
||||
lambda match : '<h2>'+match.group(1)+'</h2>'),
|
||||
(re.compile(r'<img[^>]+src="[^"]*/numeros/(\d+)[^0-9.">]*.gif"[^>]*/>', re.IGNORECASE|re.DOTALL),
|
||||
lambda match : '<span style="font-family: Sans-serif; color: red; font-size:24pt; padding=2pt;">'+match.group(1)+'</span>'),
|
||||
(re.compile(r'\''), lambda match: '’'),
|
||||
]
|
||||
|
||||
def preprocess_html(self,soup):
|
||||
body = Tag(soup, 'body')
|
||||
title = soup.find('h1', {'class':'title'})
|
||||
content = soup.find('div', {'class':'content'})
|
||||
soup.body.replaceWith(body)
|
||||
body.insert(0, title)
|
||||
body.insert(1, content)
|
||||
return soup
|
||||
|
||||
remove_tags = [ #dict(name='div', attrs={'class':'print-source_url'}),
|
||||
#dict(name='div', attrs={'class':'print-links'}),
|
||||
#dict(name='img', attrs={'class':'print-logo'}),
|
||||
dict(name='div', attrs={'class':'content_top'}),
|
||||
dict(name='div', attrs={'id':'sidebar-left'}), ]
|
||||
|
||||
# -- print-version has poor quality on this website, better do the conversion ourselves
|
||||
# def print_version(self, url):
|
||||
# return re.sub('^.*-([0-9]+)$', 'http://www.rue89.com/print/\\1',url)
|
||||
24
resources/recipes/taggeschau_de.recipe
Normal file
24
resources/recipes/taggeschau_de.recipe
Normal file
@ -0,0 +1,24 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Tagesschau(BasicNewsRecipe):
|
||||
title = 'Tagesschau'
|
||||
description = 'Nachrichten der ARD'
|
||||
publisher = 'ARD'
|
||||
language = 'de_DE'
|
||||
|
||||
__author__ = 'Florian Andreas Pfaff'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
|
||||
feeds = [('Tagesschau', 'http://www.tagesschau.de/xml/rss2')]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':['linksZumThema schmal','teaserBox','boxMoreLinks','directLinks','teaserBox boxtext','fPlayer','zitatBox breit flashaudio']}),
|
||||
dict(name='div',
|
||||
attrs={'id':['socialBookmarks','seitenanfang']}),
|
||||
dict(name='ul',
|
||||
attrs={'class':['directLinks','directLinks weltatlas']}),
|
||||
dict(name='strong', attrs={'class':['boxTitle inv','inv']})
|
||||
]
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'centerCol'})]
|
||||
@ -30,23 +30,40 @@
|
||||
<title>
|
||||
<xsl:value-of select="fb:description/fb:title-info/fb:book-title"/>
|
||||
</title>
|
||||
<style type="text/x-oeb1-css">
|
||||
A { color : #0002CC }
|
||||
A:HOVER { color : #BF0000 }
|
||||
BODY { background-color : #FEFEFE; color : #000000; font-family : Verdana, Geneva, Arial, Helvetica, sans-serif; text-align : justify }
|
||||
H1{ font-size : 160%; font-style : normal; font-weight : bold; text-align : left; border : 1px solid Black; background-color : #E7E7E7; margin-left : 0px; page-break-before : always; }
|
||||
H2{ font-size : 130%; font-style : normal; font-weight : bold; text-align : left; background-color : #EEEEEE; border : 1px solid Gray; page-break-before : always; }
|
||||
H3{ font-size : 110%; font-style : normal; font-weight : bold; text-align : left; background-color : #F1F1F1; border : 1px solid Silver;}
|
||||
H4{ font-size : 100%; font-style : normal; font-weight : bold; text-align : left; border : 1px solid Gray; background-color : #F4F4F4;}
|
||||
H5{ font-size : 100%; font-style : italic; font-weight : bold; text-align : left; border : 1px solid Gray; background-color : #F4F4F4;}
|
||||
H6{ font-size : 100%; font-style : italic; font-weight : normal; text-align : left; border : 1px solid Gray; background-color : #F4F4F4;}
|
||||
SMALL{ font-size : 80% }
|
||||
BLOCKQUOTE{ margin-left :4em; margin-top:1em; margin-right:0.2em;}
|
||||
HR{ color : Black }
|
||||
DIV{font-family : "Times New Roman", Times, serif; text-align : justify}
|
||||
UL{margin-left: 0}
|
||||
.epigraph{width:50%; margin-left : 35%;}
|
||||
<style type="text/css">
|
||||
a { color : #0002CC }
|
||||
|
||||
a:hover { color : #BF0000 }
|
||||
|
||||
body { background-color : #FEFEFE; color : #000000; font-family : Verdana, Geneva, Arial, Helvetica, sans-serif; text-align : justify }
|
||||
|
||||
h1{ font-size : 160%; font-style : normal; font-weight : bold; text-align : left; border : 1px solid Black; background-color : #E7E7E7; margin-left : 0px; page-break-before : always; }
|
||||
|
||||
h2{ font-size : 130%; font-style : normal; font-weight : bold; text-align : left; background-color : #EEEEEE; border : 1px solid Gray; page-break-before : always; }
|
||||
|
||||
h3{ font-size : 110%; font-style : normal; font-weight : bold; text-align : left; background-color : #F1F1F1; border : 1px solid Silver;}
|
||||
|
||||
h4{ font-size : 100%; font-style : normal; font-weight : bold; text-align : left; border : 1px solid Gray; background-color : #F4F4F4;}
|
||||
|
||||
h5{ font-size : 100%; font-style : italic; font-weight : bold; text-align : left; border : 1px solid Gray; background-color : #F4F4F4;}
|
||||
|
||||
h6{ font-size : 100%; font-style : italic; font-weight : normal; text-align : left; border : 1px solid Gray; background-color : #F4F4F4;}
|
||||
|
||||
small { font-size : 80% }
|
||||
|
||||
blockquote { margin-left :4em; margin-top:1em; margin-right:0.2em;}
|
||||
|
||||
hr { color : Black }
|
||||
|
||||
div {font-family : "Times New Roman", Times, serif; text-align : justify}
|
||||
|
||||
ul {margin-left: 0}
|
||||
|
||||
.epigraph{width:50%; margin-left : 35%;}
|
||||
|
||||
div.paragraph { text-align: justify; text-indent: 2em; }
|
||||
</style>
|
||||
<link rel="stylesheet" type="text/css" href="inline-styles.css" />
|
||||
</head>
|
||||
<body>
|
||||
<xsl:for-each select="fb:description/fb:title-info/fb:annotation">
|
||||
@ -136,12 +153,13 @@
|
||||
</xsl:choose>
|
||||
</xsl:variable>
|
||||
<xsl:if test="$section_has_title = 'None'">
|
||||
<a name="TOC_{generate-id()}" />
|
||||
<xsl:if test="@id">
|
||||
<xsl:element name="a">
|
||||
<xsl:attribute name="name"><xsl:value-of select="@id"/></xsl:attribute>
|
||||
</xsl:element>
|
||||
</xsl:if>
|
||||
<div id="TOC_{generate-id()}">
|
||||
<xsl:if test="@id">
|
||||
<xsl:element name="a">
|
||||
<xsl:attribute name="id"><xsl:value-of select="@id"/></xsl:attribute>
|
||||
</xsl:element>
|
||||
</xsl:if>
|
||||
</div>
|
||||
</xsl:if>
|
||||
<xsl:apply-templates>
|
||||
<xsl:with-param name="section_toc_id" select="$section_has_title" />
|
||||
@ -160,13 +178,13 @@
|
||||
</xsl:if>
|
||||
<xsl:if test="$section_toc_id != 'None'">
|
||||
<xsl:element name="a">
|
||||
<xsl:attribute name="name">TOC_<xsl:value-of select="$section_toc_id"/></xsl:attribute>
|
||||
<xsl:attribute name="id">TOC_<xsl:value-of select="$section_toc_id"/></xsl:attribute>
|
||||
</xsl:element>
|
||||
</xsl:if>
|
||||
<a name="TOC_{generate-id()}"></a>
|
||||
<xsl:if test="@id">
|
||||
<xsl:element name="a">
|
||||
<xsl:attribute name="name"><xsl:value-of select="@id"/></xsl:attribute>
|
||||
<xsl:attribute name="id"><xsl:value-of select="@id"/></xsl:attribute>
|
||||
</xsl:element>
|
||||
</xsl:if>
|
||||
<xsl:apply-templates/>
|
||||
@ -176,7 +194,7 @@
|
||||
<xsl:element name="h6">
|
||||
<xsl:if test="@id">
|
||||
<xsl:element name="a">
|
||||
<xsl:attribute name="name"><xsl:value-of select="@id"/></xsl:attribute>
|
||||
<xsl:attribute name="id"><xsl:value-of select="@id"/></xsl:attribute>
|
||||
</xsl:element>
|
||||
</xsl:if>
|
||||
<xsl:apply-templates/>
|
||||
@ -207,11 +225,18 @@
|
||||
</xsl:template>
|
||||
<!-- p -->
|
||||
<xsl:template match="fb:p">
|
||||
<div align="justify"><xsl:if test="@id">
|
||||
<xsl:element name="div">
|
||||
<xsl:attribute name="class">paragraph</xsl:attribute>
|
||||
<xsl:if test="@id">
|
||||
<xsl:element name="a">
|
||||
<xsl:attribute name="name"><xsl:value-of select="@id"/></xsl:attribute>
|
||||
</xsl:element>
|
||||
</xsl:if>    <xsl:apply-templates/></div>
|
||||
</xsl:if>
|
||||
<xsl:if test="@style">
|
||||
<xsl:attribute name="style"><xsl:value-of select="@style"/></xsl:attribute>
|
||||
</xsl:if>
|
||||
<xsl:apply-templates/>
|
||||
</xsl:element>
|
||||
</xsl:template>
|
||||
<!-- strong -->
|
||||
<xsl:template match="fb:strong">
|
||||
|
||||
@ -20,20 +20,4 @@ function setup_image_scaling_handlers() {
|
||||
});
|
||||
}
|
||||
|
||||
function extract_svged_images() {
|
||||
$("svg").each(function() {
|
||||
var children = $(this).children("img");
|
||||
if (children.length == 1) {
|
||||
var img = $(children[0]);
|
||||
var href = img.attr('xlink:href');
|
||||
if (href != undefined) {
|
||||
$(this).replaceWith('<div style="text-align:center; margin: 0; padding: 0"><img style="height: 98%" alt="SVG Image" src="' + href +'"></img></div>');
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
$(document).ready(function() {
|
||||
//extract_svged_images();
|
||||
});
|
||||
|
||||
|
||||
@ -8,7 +8,7 @@ __docformat__ = 'restructuredtext en'
|
||||
|
||||
__all__ = [
|
||||
'pot', 'translations', 'get_translations', 'iso639',
|
||||
'build', 'build_pdf2xml',
|
||||
'build', 'build_pdf2xml', 'server',
|
||||
'gui',
|
||||
'develop', 'install',
|
||||
'resources',
|
||||
@ -35,6 +35,9 @@ from setup.extensions import Build, BuildPDF2XML
|
||||
build = Build()
|
||||
build_pdf2xml = BuildPDF2XML()
|
||||
|
||||
from setup.server import Server
|
||||
server = Server()
|
||||
|
||||
from setup.install import Develop, Install, Sdist
|
||||
develop = Develop()
|
||||
install = Install()
|
||||
|
||||
102
setup/server.py
Normal file
102
setup/server.py
Normal file
@ -0,0 +1,102 @@
|
||||
#!/usr/bin/env python
|
||||
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import subprocess, tempfile, os, time, sys
|
||||
from threading import RLock
|
||||
|
||||
from setup import Command
|
||||
|
||||
try:
|
||||
from pyinotify import WatchManager, ThreadedNotifier, EventsCodes, ProcessEvent
|
||||
except:
|
||||
wm = None
|
||||
else:
|
||||
wm = WatchManager()
|
||||
flags = EventsCodes.ALL_FLAGS
|
||||
mask = flags['IN_MODIFY']
|
||||
|
||||
class ProcessEvents(ProcessEvent):
|
||||
|
||||
def __init__(self, command):
|
||||
ProcessEvent.__init__(self)
|
||||
self.command = command
|
||||
|
||||
def process_default(self, event):
|
||||
name = getattr(event,
|
||||
'name', None)
|
||||
if name and os.path.splitext(name)[1] == '.py':
|
||||
print
|
||||
print name, 'changed'
|
||||
self.command.kill_server()
|
||||
self.command.launch_server()
|
||||
print self.command.prompt,
|
||||
sys.stdout.flush()
|
||||
|
||||
|
||||
class Server(Command):
|
||||
|
||||
description = 'Run the calibre server in development mode conveniently'
|
||||
|
||||
MONOCLE_PATH = '../monocle'
|
||||
|
||||
def rebuild_monocole(self):
|
||||
subprocess.check_call(['sprocketize', '-C', self.MONOCLE_PATH,
|
||||
'-I', 'src', 'src/monocle.js'],
|
||||
stdout=open('resources/content_server/read/monocle.js', 'wb'))
|
||||
|
||||
def launch_server(self):
|
||||
print 'Starting server...\n'
|
||||
with self.lock:
|
||||
self.rebuild_monocole()
|
||||
self.server_proc = p = subprocess.Popen(['calibre-server', '--develop'],
|
||||
stderr=subprocess.STDOUT, stdout=self.server_log)
|
||||
time.sleep(0.2)
|
||||
if p.poll() is not None:
|
||||
print 'Starting server failed'
|
||||
raise SystemExit(1)
|
||||
return p
|
||||
|
||||
def kill_server(self):
|
||||
print 'Killing server...\n'
|
||||
if self.server_proc is not None:
|
||||
with self.lock:
|
||||
if self.server_proc.poll() is None:
|
||||
self.server_proc.terminate()
|
||||
while self.server_proc.poll() is None:
|
||||
time.sleep(0.1)
|
||||
|
||||
def watch(self):
|
||||
if wm is not None:
|
||||
self.notifier = ThreadedNotifier(wm, ProcessEvents(self))
|
||||
self.notifier.start()
|
||||
self.wdd = wm.add_watch(os.path.abspath('src'), mask, rec=True)
|
||||
|
||||
def run(self, opts):
|
||||
self.lock = RLock()
|
||||
tdir = tempfile.gettempdir()
|
||||
logf = os.path.join(tdir, 'calibre-server.log')
|
||||
self.server_log = open(logf, 'ab')
|
||||
self.prompt = 'Press Enter to kill/restart server. Ctrl+C to quit: '
|
||||
print 'Server log available at:', logf
|
||||
print
|
||||
self.watch()
|
||||
|
||||
while True:
|
||||
self.launch_server()
|
||||
try:
|
||||
raw_input(self.prompt)
|
||||
except:
|
||||
print
|
||||
self.kill_server()
|
||||
break
|
||||
else:
|
||||
self.kill_server()
|
||||
print
|
||||
|
||||
if hasattr(self, 'notifier'):
|
||||
self.notifier.stop()
|
||||
|
||||
@ -2,7 +2,7 @@ __license__ = 'GPL v3'
|
||||
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
__appname__ = 'calibre'
|
||||
__version__ = '0.7.24'
|
||||
__version__ = '0.7.26'
|
||||
__author__ = "Kovid Goyal <kovid@kovidgoyal.net>"
|
||||
|
||||
import re
|
||||
|
||||
@ -292,7 +292,7 @@ class RTFMetadataReader(MetadataReaderPlugin):
|
||||
def get_metadata(self, stream, ftype):
|
||||
from calibre.ebooks.metadata.rtf import get_metadata
|
||||
return get_metadata(stream)
|
||||
|
||||
|
||||
class SNBMetadataReader(MetadataReaderPlugin):
|
||||
|
||||
name = 'Read SNB metadata'
|
||||
@ -471,7 +471,8 @@ from calibre.devices.iriver.driver import IRIVER_STORY
|
||||
from calibre.devices.binatone.driver import README
|
||||
from calibre.devices.hanvon.driver import N516, EB511, ALEX, AZBOOKA, THEBOOK
|
||||
from calibre.devices.edge.driver import EDGE
|
||||
from calibre.devices.teclast.driver import TECLAST_K3, NEWSMY, IPAPYRUS, SOVOS
|
||||
from calibre.devices.teclast.driver import TECLAST_K3, NEWSMY, IPAPYRUS, \
|
||||
SOVOS, PICO
|
||||
from calibre.devices.sne.driver import SNE
|
||||
from calibre.devices.misc import PALMPRE, AVANT, SWEEX, PDNOVEL, KOGAN, \
|
||||
GEMEI, VELOCITYMICRO, PDNOVEL_KOBO
|
||||
@ -572,6 +573,7 @@ plugins += [
|
||||
ELONEX,
|
||||
TECLAST_K3,
|
||||
NEWSMY,
|
||||
PICO,
|
||||
IPAPYRUS,
|
||||
SOVOS,
|
||||
EDGE,
|
||||
|
||||
@ -259,6 +259,9 @@ class OutputProfile(Plugin):
|
||||
#: Number of ems that the left margin of a blockquote is rendered as
|
||||
mobi_ems_per_blockquote = 1.0
|
||||
|
||||
#: Special periodical formatting needed in EPUB
|
||||
epub_periodical_format = None
|
||||
|
||||
@classmethod
|
||||
def tags_to_string(cls, tags):
|
||||
return escape(', '.join(tags))
|
||||
@ -439,6 +442,9 @@ class SonyReaderOutput(OutputProfile):
|
||||
fsizes = [7.5, 9, 10, 12, 15.5, 20, 22, 24]
|
||||
unsupported_unicode_chars = [u'\u201f', u'\u201b']
|
||||
|
||||
epub_periodical_format = 'sony'
|
||||
#periodical_date_in_title = False
|
||||
|
||||
|
||||
class KoboReaderOutput(OutputProfile):
|
||||
|
||||
@ -561,6 +567,8 @@ class CybookOpusOutput(SonyReaderOutput):
|
||||
fbase = 16
|
||||
fsizes = [12, 12, 14, 16, 18, 20, 22, 24]
|
||||
|
||||
epub_periodical_format = None
|
||||
|
||||
class KindleOutput(OutputProfile):
|
||||
|
||||
name = 'Kindle'
|
||||
|
||||
@ -117,6 +117,12 @@ class PDNOVEL_KOBO(PDNOVEL):
|
||||
|
||||
EBOOK_DIR_MAIN = 'eBooks/Kobo'
|
||||
|
||||
def upload_cover(self, path, filename, metadata, filepath):
|
||||
coverdata = getattr(metadata, 'thumbnail', None)
|
||||
if coverdata and coverdata[2]:
|
||||
with open(os.path.join(path, '.thumbnail', filename+'.jpg'), 'wb') as coverfile:
|
||||
coverfile.write(coverdata[2])
|
||||
|
||||
|
||||
class VELOCITYMICRO(USBMS):
|
||||
name = 'VelocityMicro device interface'
|
||||
|
||||
@ -41,6 +41,15 @@ class NEWSMY(TECLAST_K3):
|
||||
WINDOWS_MAIN_MEM = 'NEWSMY'
|
||||
WINDOWS_CARD_A_MEM = 'USBDISK____SD'
|
||||
|
||||
class PICO(NEWSMY):
|
||||
name = 'Pico device interface'
|
||||
gui_name = 'Pico'
|
||||
description = _('Communicate with the Pico reader.')
|
||||
|
||||
WINDOWS_MAIN_MEM = 'USBDISK__USER'
|
||||
EBOOK_DIR_MAIN = 'Books'
|
||||
FORMATS = ['EPUB', 'FB2', 'TXT', 'LRC', 'PDB', 'PDF', 'HTML', 'WTXT']
|
||||
|
||||
class IPAPYRUS(TECLAST_K3):
|
||||
|
||||
name = 'iPapyrus device interface'
|
||||
|
||||
@ -30,9 +30,9 @@ def detect(aBuf):
|
||||
|
||||
# Added by Kovid
|
||||
ENCODING_PATS = [
|
||||
re.compile(r'<\?[^<>]+encoding=[\'"](.*?)[\'"][^<>]*>',
|
||||
re.compile(r'<\?[^<>]+encoding\s*=\s*[\'"](.*?)[\'"][^<>]*>',
|
||||
re.IGNORECASE),
|
||||
re.compile(r'''<meta\s+?[^<>]+?content=['"][^'"]*?charset=([-a-z0-9]+)[^'"]*?['"][^<>]*>''',
|
||||
re.compile(r'''<meta\s+?[^<>]+?content\s*=\s*['"][^'"]*?charset=([-a-z0-9]+)[^'"]*?['"][^<>]*>''',
|
||||
re.IGNORECASE)
|
||||
]
|
||||
ENTITY_PATTERN = re.compile(r'&(\S+?);')
|
||||
|
||||
@ -187,9 +187,10 @@ class EPUBOutput(OutputFormatPlugin):
|
||||
metadata_xml = None
|
||||
extra_entries = []
|
||||
if self.is_periodical:
|
||||
from calibre.ebooks.epub.periodical import sony_metadata
|
||||
metadata_xml, atom_xml = sony_metadata(oeb)
|
||||
extra_entries = [('atom.xml', 'application/atom+xml', atom_xml)]
|
||||
if self.opts.output_profile.epub_periodical_format == 'sony':
|
||||
from calibre.ebooks.epub.periodical import sony_metadata
|
||||
metadata_xml, atom_xml = sony_metadata(oeb)
|
||||
extra_entries = [('atom.xml', 'application/atom+xml', atom_xml)]
|
||||
oeb_output = plugin_for_output_format('oeb')
|
||||
oeb_output.convert(oeb, tdir, input_plugin, opts, log)
|
||||
opf = [x for x in os.listdir(tdir) if x.endswith('.opf')][0]
|
||||
|
||||
@ -40,14 +40,35 @@ class FB2Input(InputFormatPlugin):
|
||||
accelerators):
|
||||
from calibre.ebooks.metadata.opf2 import OPFCreator
|
||||
from calibre.ebooks.metadata.meta import get_metadata
|
||||
from calibre.ebooks.oeb.base import XLINK_NS
|
||||
from calibre.ebooks.oeb.base import XLINK_NS, XHTML_NS, RECOVER_PARSER
|
||||
NAMESPACES = {'f':FB2NS, 'l':XLINK_NS}
|
||||
log.debug('Parsing XML...')
|
||||
raw = stream.read()
|
||||
raw = stream.read().replace('\0', '')
|
||||
try:
|
||||
doc = etree.fromstring(raw)
|
||||
except etree.XMLSyntaxError:
|
||||
doc = etree.fromstring(raw.replace('& ', '&'))
|
||||
try:
|
||||
doc = etree.fromstring(raw, parser=RECOVER_PARSER)
|
||||
except:
|
||||
doc = etree.fromstring(raw.replace('& ', '&'),
|
||||
parser=RECOVER_PARSER)
|
||||
stylesheets = doc.xpath('//*[local-name() = "stylesheet" and @type="text/css"]')
|
||||
css = ''
|
||||
for s in stylesheets:
|
||||
css += etree.tostring(s, encoding=unicode, method='text',
|
||||
with_tail=False) + '\n\n'
|
||||
if css:
|
||||
import cssutils, logging
|
||||
parser = cssutils.CSSParser(fetcher=None,
|
||||
log=logging.getLogger('calibre.css'))
|
||||
|
||||
XHTML_CSS_NAMESPACE = '@namespace "%s";\n' % XHTML_NS
|
||||
text = XHTML_CSS_NAMESPACE + css
|
||||
log.debug('Parsing stylesheet...')
|
||||
stylesheet = parser.parseString(text)
|
||||
stylesheet.namespaces['h'] = XHTML_NS
|
||||
css = unicode(stylesheet.cssText).replace('h|style', 'h|span')
|
||||
css = re.sub(r'name\s*=\s*', 'class=', css)
|
||||
self.extract_embedded_content(doc)
|
||||
log.debug('Converting XML to HTML...')
|
||||
ss = open(P('templates/fb2.xsl'), 'rb').read()
|
||||
@ -63,7 +84,9 @@ class FB2Input(InputFormatPlugin):
|
||||
for img in result.xpath('//img[@src]'):
|
||||
src = img.get('src')
|
||||
img.set('src', self.binary_map.get(src, src))
|
||||
open('index.xhtml', 'wb').write(transform.tostring(result))
|
||||
index = transform.tostring(result)
|
||||
open('index.xhtml', 'wb').write(index)
|
||||
open('inline-styles.css', 'wb').write(css)
|
||||
stream.seek(0)
|
||||
mi = get_metadata(stream, 'fb2')
|
||||
if not mi.title:
|
||||
|
||||
@ -282,15 +282,22 @@ class HTMLInput(InputFormatPlugin):
|
||||
basedir = os.getcwd()
|
||||
self.opts = opts
|
||||
|
||||
fname = None
|
||||
if hasattr(stream, 'name'):
|
||||
basedir = os.path.dirname(stream.name)
|
||||
fname = os.path.basename(stream.name)
|
||||
|
||||
if file_ext != 'opf':
|
||||
if opts.dont_package:
|
||||
raise ValueError('The --dont-package option is not supported for an HTML input file')
|
||||
from calibre.ebooks.metadata.html import get_metadata
|
||||
oeb = self.create_oebbook(stream.name, basedir, opts, log,
|
||||
get_metadata(stream))
|
||||
mi = get_metadata(stream)
|
||||
if fname:
|
||||
from calibre.ebooks.metadata.meta import metadata_from_filename
|
||||
fmi = metadata_from_filename(fname)
|
||||
fmi.smart_update(mi)
|
||||
mi = fmi
|
||||
oeb = self.create_oebbook(stream.name, basedir, opts, log, mi)
|
||||
return oeb
|
||||
|
||||
from calibre.ebooks.conversion.plumber import create_oebbook
|
||||
|
||||
@ -92,10 +92,14 @@ def get_metadata(br, asin, mi):
|
||||
' @class="emptyClear" or @href]'):
|
||||
c.getparent().remove(c)
|
||||
desc = html.tostring(desc, method='html', encoding=unicode).strip()
|
||||
desc = re.sub(r' class=[^>]+>', '>', desc)
|
||||
# remove all attributes from tags
|
||||
desc = re.sub(r'<([a-zA-Z0-9]+)\s[^>]+>', r'<\1>', desc)
|
||||
# Collapse whitespace
|
||||
desc = re.sub('\n+', '\n', desc)
|
||||
desc = re.sub(' +', ' ', desc)
|
||||
# Remove the notice about text referring to out of print editions
|
||||
desc = re.sub(r'(?s)<em>--This text ref.*?</em>', '', desc)
|
||||
# Remove comments
|
||||
desc = re.sub(r'(?s)<!--.*?-->', '', desc)
|
||||
mi.comments = desc
|
||||
|
||||
|
||||
@ -22,7 +22,8 @@ def get_metadata(stream):
|
||||
'xlink':XLINK_NS})
|
||||
tostring = lambda x : etree.tostring(x, method='text',
|
||||
encoding=unicode).strip()
|
||||
root = etree.fromstring(stream.read())
|
||||
parser = etree.XMLParser(recover=True, no_network=True)
|
||||
root = etree.fromstring(stream.read(), parser=parser)
|
||||
authors, author_sort = [], None
|
||||
for au in XPath('//fb2:author')(root):
|
||||
fname = lname = author = None
|
||||
|
||||
@ -12,7 +12,7 @@ import os, time, sys, shutil
|
||||
|
||||
from calibre.utils.ipc.job import ParallelJob
|
||||
from calibre.utils.ipc.server import Server
|
||||
from calibre.ptempfile import PersistentTemporaryDirectory
|
||||
from calibre.ptempfile import PersistentTemporaryDirectory, TemporaryDirectory
|
||||
from calibre import prints
|
||||
from calibre.constants import filesystem_encoding
|
||||
|
||||
@ -21,51 +21,76 @@ def debug(*args):
|
||||
prints(*args)
|
||||
sys.stdout.flush()
|
||||
|
||||
def read_metadata_(task, tdir, notification=lambda x,y:x):
|
||||
def serialize_metadata_for(formats, tdir, id_):
|
||||
from calibre.ebooks.metadata.meta import metadata_from_formats
|
||||
from calibre.ebooks.metadata.opf2 import metadata_to_opf
|
||||
mi = metadata_from_formats(formats)
|
||||
mi.cover = None
|
||||
cdata = None
|
||||
if mi.cover_data:
|
||||
cdata = mi.cover_data[-1]
|
||||
mi.cover_data = None
|
||||
if not mi.application_id:
|
||||
mi.application_id = '__calibre_dummy__'
|
||||
with open(os.path.join(tdir, '%s.opf'%id_), 'wb') as f:
|
||||
f.write(metadata_to_opf(mi))
|
||||
if cdata:
|
||||
with open(os.path.join(tdir, str(id_)), 'wb') as f:
|
||||
f.write(cdata)
|
||||
|
||||
def read_metadata_(task, tdir, notification=lambda x,y:x):
|
||||
with TemporaryDirectory() as mdir:
|
||||
do_read_metadata(task, tdir, mdir, notification)
|
||||
|
||||
def do_read_metadata(task, tdir, mdir, notification):
|
||||
from calibre.customize.ui import run_plugins_on_import
|
||||
for x in task:
|
||||
try:
|
||||
id, formats = x
|
||||
id_, formats = x
|
||||
except:
|
||||
continue
|
||||
try:
|
||||
if isinstance(formats, basestring): formats = [formats]
|
||||
mi = metadata_from_formats(formats)
|
||||
mi.cover = None
|
||||
cdata = None
|
||||
if mi.cover_data:
|
||||
cdata = mi.cover_data[-1]
|
||||
mi.cover_data = None
|
||||
if not mi.application_id:
|
||||
mi.application_id = '__calibre_dummy__'
|
||||
with open(os.path.join(tdir, '%s.opf'%id), 'wb') as f:
|
||||
f.write(metadata_to_opf(mi))
|
||||
if cdata:
|
||||
with open(os.path.join(tdir, str(id)), 'wb') as f:
|
||||
f.write(cdata)
|
||||
import_map = {}
|
||||
fmts, metadata_fmts = [], []
|
||||
for format in formats:
|
||||
mfmt = format
|
||||
name, ext = os.path.splitext(os.path.basename(format))
|
||||
nfp = run_plugins_on_import(format)
|
||||
if nfp is None:
|
||||
nfp = format
|
||||
nfp = os.path.abspath(nfp)
|
||||
if not nfp or nfp == format or not os.access(nfp, os.R_OK):
|
||||
nfp = None
|
||||
else:
|
||||
# Ensure that the filename is preserved so that
|
||||
# reading metadata from filename is not broken
|
||||
nfp = os.path.abspath(nfp)
|
||||
nfext = os.path.splitext(nfp)[1]
|
||||
mfmt = os.path.join(mdir, name + nfext)
|
||||
shutil.copyfile(nfp, mfmt)
|
||||
metadata_fmts.append(mfmt)
|
||||
fmts.append(nfp)
|
||||
|
||||
serialize_metadata_for(metadata_fmts, tdir, id_)
|
||||
|
||||
for format, nfp in zip(formats, fmts):
|
||||
if not nfp:
|
||||
continue
|
||||
if isinstance(nfp, unicode):
|
||||
nfp.encode(filesystem_encoding)
|
||||
x = lambda j : os.path.abspath(os.path.normpath(os.path.normcase(j)))
|
||||
if x(nfp) != x(format) and os.access(nfp, os.R_OK|os.W_OK):
|
||||
fmt = os.path.splitext(format)[1].replace('.', '').lower()
|
||||
nfmt = os.path.splitext(nfp)[1].replace('.', '').lower()
|
||||
dest = os.path.join(tdir, '%s.%s'%(id, nfmt))
|
||||
dest = os.path.join(tdir, '%s.%s'%(id_, nfmt))
|
||||
shutil.copyfile(nfp, dest)
|
||||
import_map[fmt] = dest
|
||||
os.remove(nfp)
|
||||
if import_map:
|
||||
with open(os.path.join(tdir, str(id)+'.import'), 'wb') as f:
|
||||
with open(os.path.join(tdir, str(id_)+'.import'), 'wb') as f:
|
||||
for fmt, nfp in import_map.items():
|
||||
f.write(fmt+':'+nfp+'\n')
|
||||
notification(0.5, id)
|
||||
notification(0.5, id_)
|
||||
except:
|
||||
import traceback
|
||||
with open(os.path.join(tdir, '%s.error'%id), 'wb') as f:
|
||||
with open(os.path.join(tdir, '%s.error'%id_), 'wb') as f:
|
||||
f.write(traceback.format_exc())
|
||||
|
||||
class Progress(object):
|
||||
|
||||
@ -27,6 +27,8 @@ TABLE_TAGS = set(['table', 'tr', 'td', 'th', 'caption'])
|
||||
SPECIAL_TAGS = set(['hr', 'br'])
|
||||
CONTENT_TAGS = set(['img', 'hr', 'br'])
|
||||
|
||||
NOT_VTAGS = HEADER_TAGS | NESTABLE_TAGS | TABLE_TAGS | SPECIAL_TAGS | \
|
||||
CONTENT_TAGS
|
||||
PAGE_BREAKS = set(['always', 'left', 'right'])
|
||||
|
||||
COLLAPSE = re.compile(r'[ \t\r\n\v]+')
|
||||
@ -57,8 +59,6 @@ class FormatState(object):
|
||||
self.indent = 0.
|
||||
self.fsize = 3
|
||||
self.ids = set()
|
||||
self.valign = 'baseline'
|
||||
self.nest = False
|
||||
self.italic = False
|
||||
self.bold = False
|
||||
self.strikethrough = False
|
||||
@ -76,7 +76,6 @@ class FormatState(object):
|
||||
and self.italic == other.italic \
|
||||
and self.bold == other.bold \
|
||||
and self.href == other.href \
|
||||
and self.valign == other.valign \
|
||||
and self.preserve == other.preserve \
|
||||
and self.family == other.family \
|
||||
and self.bgcolor == other.bgcolor \
|
||||
@ -224,7 +223,6 @@ class MobiMLizer(object):
|
||||
return
|
||||
if not pstate or istate != pstate:
|
||||
inline = para
|
||||
valign = istate.valign
|
||||
fsize = istate.fsize
|
||||
href = istate.href
|
||||
if not href:
|
||||
@ -234,19 +232,8 @@ class MobiMLizer(object):
|
||||
else:
|
||||
inline = etree.SubElement(inline, XHTML('a'), href=href)
|
||||
bstate.anchor = inline
|
||||
if valign == 'super':
|
||||
parent = inline
|
||||
if istate.nest and bstate.inline is not None:
|
||||
parent = bstate.inline
|
||||
istate.nest = False
|
||||
inline = etree.SubElement(parent, XHTML('sup'))
|
||||
elif valign == 'sub':
|
||||
parent = inline
|
||||
if istate.nest and bstate.inline is not None:
|
||||
parent = bstate.inline
|
||||
istate.nest = False
|
||||
inline = etree.SubElement(parent, XHTML('sub'))
|
||||
elif fsize != 3:
|
||||
|
||||
if fsize != 3:
|
||||
inline = etree.SubElement(inline, XHTML('font'),
|
||||
size=str(fsize))
|
||||
if istate.family == 'monospace':
|
||||
@ -279,7 +266,8 @@ class MobiMLizer(object):
|
||||
else:
|
||||
inline.append(item)
|
||||
|
||||
def mobimlize_elem(self, elem, stylizer, bstate, istates):
|
||||
def mobimlize_elem(self, elem, stylizer, bstate, istates,
|
||||
ignore_valign=False):
|
||||
if not isinstance(elem.tag, basestring) \
|
||||
or namespace(elem.tag) != XHTML_NS:
|
||||
return
|
||||
@ -351,15 +339,6 @@ class MobiMLizer(object):
|
||||
istate.family = 'sans-serif'
|
||||
else:
|
||||
istate.family = 'serif'
|
||||
valign = style['vertical-align']
|
||||
if valign in ('super', 'text-top') or asfloat(valign) > 0:
|
||||
istate.nest = istate.valign in ('sub', 'super')
|
||||
istate.valign = 'super'
|
||||
elif valign == 'sub' or asfloat(valign) < 0:
|
||||
istate.nest = istate.valign in ('sub', 'super')
|
||||
istate.valign = 'sub'
|
||||
else:
|
||||
istate.valign = 'baseline'
|
||||
if 'id' in elem.attrib:
|
||||
istate.ids.add(elem.attrib['id'])
|
||||
if 'name' in elem.attrib:
|
||||
@ -407,6 +386,30 @@ class MobiMLizer(object):
|
||||
text = None
|
||||
else:
|
||||
text = COLLAPSE.sub(' ', elem.text)
|
||||
valign = style['vertical-align']
|
||||
not_baseline = valign in ('super', 'sub', 'text-top',
|
||||
'text-bottom')
|
||||
vtag = 'sup' if valign in ('super', 'text-top') else 'sub'
|
||||
if not_baseline and not ignore_valign and tag not in NOT_VTAGS and not isblock:
|
||||
nroot = etree.Element(XHTML('html'), nsmap=MOBI_NSMAP)
|
||||
vbstate = BlockState(etree.SubElement(nroot, XHTML('body')))
|
||||
vbstate.para = etree.SubElement(vbstate.body, XHTML('p'))
|
||||
self.mobimlize_elem(elem, stylizer, vbstate, istates,
|
||||
ignore_valign=True)
|
||||
if len(istates) > 0:
|
||||
istates.pop()
|
||||
if len(istates) == 0:
|
||||
istates.append(FormatState())
|
||||
at_start = bstate.para is None
|
||||
if at_start:
|
||||
self.mobimlize_content('span', '', bstate, istates)
|
||||
parent = bstate.para if bstate.inline is None else bstate.inline
|
||||
if parent is not None:
|
||||
vtag = etree.SubElement(parent, XHTML(vtag))
|
||||
for child in vbstate.para:
|
||||
vtag.append(child)
|
||||
return
|
||||
|
||||
if text or tag in CONTENT_TAGS or tag in NESTABLE_TAGS:
|
||||
self.mobimlize_content(tag, text, bstate, istates)
|
||||
for child in elem:
|
||||
@ -421,6 +424,8 @@ class MobiMLizer(object):
|
||||
tail = COLLAPSE.sub(' ', child.tail)
|
||||
if tail:
|
||||
self.mobimlize_content(tag, tail, bstate, istates)
|
||||
|
||||
|
||||
if bstate.content and style['page-break-after'] in PAGE_BREAKS:
|
||||
bstate.pbreak = True
|
||||
if isblock:
|
||||
|
||||
@ -31,17 +31,17 @@ class SNBOutput(OutputFormatPlugin):
|
||||
'the line will be broken at the space after and will exceed the '
|
||||
'specified value. Also, there is a minimum of 25 characters. '
|
||||
'Use 0 to disable line splitting.')),
|
||||
OptionRecommendation(name='insert_empty_line',
|
||||
OptionRecommendation(name='snb_insert_empty_line',
|
||||
recommended_value=False, level=OptionRecommendation.LOW,
|
||||
help=_('Speicfy whether or not to insert an empty line between '
|
||||
help=_('Specify whether or not to insert an empty line between '
|
||||
'two paragraphs.')),
|
||||
OptionRecommendation(name='indent_first_line',
|
||||
OptionRecommendation(name='snb_indent_first_line',
|
||||
recommended_value=True, level=OptionRecommendation.LOW,
|
||||
help=_('Speicfy whether or not to insert two space characters '
|
||||
help=_('Specify whether or not to insert two space characters '
|
||||
'to indent the first line of each paragraph.')),
|
||||
OptionRecommendation(name='hide_chapter_name',
|
||||
OptionRecommendation(name='snb_hide_chapter_name',
|
||||
recommended_value=False, level=OptionRecommendation.LOW,
|
||||
help=_('Speicfy whether or not to hide the chapter title for each '
|
||||
help=_('Specify whether or not to hide the chapter title for each '
|
||||
'chapter. Useful for image-only output (eg. comics).')),
|
||||
])
|
||||
|
||||
|
||||
@ -90,7 +90,7 @@ class SNBMLizer(object):
|
||||
snbcTree = etree.Element("snbc")
|
||||
snbcHead = etree.SubElement(snbcTree, "head")
|
||||
etree.SubElement(snbcHead, "title").text = subtitle
|
||||
if self.opts and self.opts.hide_chapter_name:
|
||||
if self.opts and self.opts.snb_hide_chapter_name:
|
||||
etree.SubElement(snbcHead, "hidetitle").text = u"true"
|
||||
etree.SubElement(snbcTree, "body")
|
||||
trees[subitem] = snbcTree
|
||||
@ -120,13 +120,13 @@ class SNBMLizer(object):
|
||||
subitem = line[len(CALIBRE_SNB_BM_TAG):]
|
||||
bodyTree = trees[subitem].find(".//body")
|
||||
else:
|
||||
if self.opts and self.opts.indent_first_line:
|
||||
if self.opts and self.opts.snb_indent_first_line:
|
||||
prefix = u'\u3000\u3000'
|
||||
else:
|
||||
prefix = u''
|
||||
etree.SubElement(bodyTree, "text").text = \
|
||||
etree.CDATA(unicode(prefix + line))
|
||||
if self.opts and self.opts.insert_empty_line:
|
||||
if self.opts and self.opts.snb_insert_empty_line:
|
||||
etree.SubElement(bodyTree, "text").text = \
|
||||
etree.CDATA(u'')
|
||||
|
||||
|
||||
@ -18,7 +18,8 @@ class PluginWidget(Widget, Ui_Form):
|
||||
|
||||
def __init__(self, parent, get_option, get_help, db=None, book_id=None):
|
||||
Widget.__init__(self, parent,
|
||||
['insert_empty_line', 'indent_first_line', 'hide_chapter_name',])
|
||||
['snb_insert_empty_line', 'snb_indent_first_line',
|
||||
'snb_hide_chapter_name',])
|
||||
self.db, self.book_id = db, book_id
|
||||
self.initialize_options(get_option, get_help, db, book_id)
|
||||
|
||||
|
||||
@ -28,21 +28,21 @@
|
||||
</spacer>
|
||||
</item>
|
||||
<item row="3" column="0">
|
||||
<widget class="QCheckBox" name="opt_hide_chapter_name">
|
||||
<widget class="QCheckBox" name="opt_snb_hide_chapter_name">
|
||||
<property name="text">
|
||||
<string>Hide chapter name</string>
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="2" column="0">
|
||||
<widget class="QCheckBox" name="opt_indent_first_line">
|
||||
<widget class="QCheckBox" name="opt_snb_indent_first_line">
|
||||
<property name="text">
|
||||
<string>Insert space before the first line for each paragraph</string>
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="1" column="0">
|
||||
<widget class="QCheckBox" name="opt_insert_empty_line">
|
||||
<widget class="QCheckBox" name="opt_snb_insert_empty_line">
|
||||
<property name="text">
|
||||
<string>Insert empty line between paragraphs</string>
|
||||
</property>
|
||||
|
||||
@ -489,7 +489,7 @@ class DeviceMenu(QMenu): # {{{
|
||||
for actions, desc in (
|
||||
(basic_actions, ''),
|
||||
(delete_actions, _('Send and delete from library')),
|
||||
(specific_actions, _('Send specific format'))
|
||||
(specific_actions, _('Send specific format to'))
|
||||
):
|
||||
mdest = menu
|
||||
if actions is not basic_actions:
|
||||
@ -1029,7 +1029,7 @@ class DeviceMixin(object): # {{{
|
||||
to_s = [account]
|
||||
subjects = [_('News:')+' '+mi.title]
|
||||
texts = [_('Attached is the')+' '+mi.title]
|
||||
attachment_names = [mi.title+os.path.splitext(attachment)[1]]
|
||||
attachment_names = [ascii_filename(mi.title)+os.path.splitext(attachment)[1]]
|
||||
attachments = [attachment]
|
||||
jobnames = ['%s:%s'%(id, mi.title)]
|
||||
remove = [id] if config['delete_news_from_library_on_upload']\
|
||||
|
||||
@ -55,12 +55,16 @@ class CheckLibraryDialog(QDialog):
|
||||
h.addWidget(ln)
|
||||
self.name_ignores = QLineEdit()
|
||||
self.name_ignores.setText(db.prefs.get('check_library_ignore_names', ''))
|
||||
self.name_ignores.setToolTip(
|
||||
_('Enter comma-separated standard file name wildcards, such as synctoy*.dat'))
|
||||
ln.setBuddy(self.name_ignores)
|
||||
h.addWidget(self.name_ignores)
|
||||
le = QLabel(_('Extensions to ignore'))
|
||||
h.addWidget(le)
|
||||
self.ext_ignores = QLineEdit()
|
||||
self.ext_ignores.setText(db.prefs.get('check_library_ignore_extensions', ''))
|
||||
self.ext_ignores.setToolTip(
|
||||
_('Enter comma-separated extensions without a leading dot. Used only in book folders'))
|
||||
le.setBuddy(self.ext_ignores)
|
||||
h.addWidget(self.ext_ignores)
|
||||
self._layout.addLayout(h)
|
||||
|
||||
@ -571,6 +571,10 @@ class MetadataBulkDialog(QDialog, Ui_MetadataBulkDialog):
|
||||
self.initalize_authors()
|
||||
self.initialize_series()
|
||||
self.initialize_publisher()
|
||||
for x in ('authors', 'publisher', 'series'):
|
||||
x = getattr(self, x)
|
||||
x.setSizeAdjustPolicy(x.AdjustToMinimumContentsLengthWithIcon)
|
||||
x.setMinimumContentsLength(25)
|
||||
|
||||
def initalize_authors(self):
|
||||
all_authors = self.db.all_authors()
|
||||
|
||||
@ -678,6 +678,19 @@ nothing should be put between the original text and the inserted text</string>
|
||||
<item row="8" column="2">
|
||||
<widget class="QLineEdit" name="test_result"/>
|
||||
</item>
|
||||
<item row="25" column="0" colspan="2">
|
||||
<spacer name="verticalSpacer_2">
|
||||
<property name="orientation">
|
||||
<enum>Qt::Vertical</enum>
|
||||
</property>
|
||||
<property name="sizeHint" stdset="0">
|
||||
<size>
|
||||
<width>20</width>
|
||||
<height>5</height>
|
||||
</size>
|
||||
</property>
|
||||
</spacer>
|
||||
</item>
|
||||
</layout>
|
||||
</widget>
|
||||
</widget>
|
||||
|
||||
@ -2,7 +2,7 @@ __license__ = 'GPL v3'
|
||||
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
''' Code to manage ebook library'''
|
||||
|
||||
def db():
|
||||
def db(path=None):
|
||||
from calibre.library.database2 import LibraryDatabase2
|
||||
from calibre.utils.config import prefs
|
||||
return LibraryDatabase2(prefs['library_path'])
|
||||
return LibraryDatabase2(path if path else prefs['library_path'])
|
||||
|
||||
@ -5,7 +5,7 @@ __license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import re, os, traceback
|
||||
import re, os, traceback, fnmatch
|
||||
|
||||
from calibre import isbytestring
|
||||
from calibre.constants import filesystem_encoding
|
||||
@ -66,13 +66,19 @@ class CheckLibrary(object):
|
||||
return self.failed_folders or self.mismatched_dirs or \
|
||||
self.conflicting_custom_cols or self.failed_restores
|
||||
|
||||
def ignore_name(self, filename):
|
||||
for filespec in self.ignore_names:
|
||||
if fnmatch.fnmatch(filename, filespec):
|
||||
return True
|
||||
return False;
|
||||
|
||||
def scan_library(self, name_ignores, extension_ignores):
|
||||
self.ignore_names = frozenset(name_ignores)
|
||||
self.ignore_ext = frozenset(['.'+ e for e in extension_ignores])
|
||||
|
||||
lib = self.src_library_path
|
||||
for auth_dir in os.listdir(lib):
|
||||
if auth_dir in self.ignore_names or auth_dir == 'metadata.db':
|
||||
if self.ignore_name(auth_dir) or auth_dir == 'metadata.db':
|
||||
continue
|
||||
auth_path = os.path.join(lib, auth_dir)
|
||||
# First check: author must be a directory
|
||||
@ -85,7 +91,7 @@ class CheckLibrary(object):
|
||||
# Look for titles in the author directories
|
||||
found_titles = False
|
||||
for title_dir in os.listdir(auth_path):
|
||||
if title_dir in self.ignore_names:
|
||||
if self.ignore_name(title_dir):
|
||||
continue
|
||||
title_path = os.path.join(auth_path, title_dir)
|
||||
db_path = os.path.join(auth_dir, title_dir)
|
||||
|
||||
@ -28,11 +28,13 @@ from calibre.library.server.browse import BrowseServer
|
||||
|
||||
class DispatchController(object): # {{{
|
||||
|
||||
def __init__(self, prefix):
|
||||
def __init__(self, prefix, wsgi=False):
|
||||
self.dispatcher = cherrypy.dispatch.RoutesDispatcher()
|
||||
self.funcs = []
|
||||
self.seen = set([])
|
||||
self.prefix = prefix if prefix else ''
|
||||
if wsgi:
|
||||
self.prefix = ''
|
||||
|
||||
def __call__(self, name, route, func, **kwargs):
|
||||
if name in self.seen:
|
||||
@ -96,7 +98,9 @@ class LibraryServer(ContentServer, MobileServer, XMLServer, OPDSServer, Cache,
|
||||
|
||||
server_name = __appname__ + '/' + __version__
|
||||
|
||||
def __init__(self, db, opts, embedded=False, show_tracebacks=True):
|
||||
def __init__(self, db, opts, embedded=False, show_tracebacks=True,
|
||||
wsgi=False):
|
||||
self.is_wsgi = bool(wsgi)
|
||||
self.opts = opts
|
||||
self.embedded = embedded
|
||||
self.state_callback = None
|
||||
@ -114,35 +118,47 @@ class LibraryServer(ContentServer, MobileServer, XMLServer, OPDSServer, Cache,
|
||||
self.set_database(db)
|
||||
|
||||
cherrypy.config.update({
|
||||
'log.screen' : opts.develop,
|
||||
'engine.autoreload_on' : opts.develop,
|
||||
'tools.log_headers.on' : opts.develop,
|
||||
'checker.on' : opts.develop,
|
||||
'request.show_tracebacks': show_tracebacks,
|
||||
'server.socket_host' : listen_on,
|
||||
'server.socket_port' : opts.port,
|
||||
'server.socket_timeout' : opts.timeout, #seconds
|
||||
'server.thread_pool' : opts.thread_pool, # number of threads
|
||||
})
|
||||
if embedded:
|
||||
'log.screen' : opts.develop,
|
||||
'engine.autoreload_on' : getattr(opts,
|
||||
'auto_reload', False),
|
||||
'tools.log_headers.on' : opts.develop,
|
||||
'checker.on' : opts.develop,
|
||||
'request.show_tracebacks': show_tracebacks,
|
||||
'server.socket_host' : listen_on,
|
||||
'server.socket_port' : opts.port,
|
||||
'server.socket_timeout' : opts.timeout, #seconds
|
||||
'server.thread_pool' : opts.thread_pool, # number of threads
|
||||
})
|
||||
if embedded or wsgi:
|
||||
cherrypy.config.update({'engine.SIGHUP' : None,
|
||||
'engine.SIGTERM' : None,})
|
||||
self.config = {'global': {
|
||||
'tools.gzip.on' : True,
|
||||
'tools.gzip.mime_types': ['text/html', 'text/plain', 'text/xml', 'text/javascript', 'text/css'],
|
||||
}}
|
||||
if opts.password:
|
||||
self.config['/'] = {
|
||||
'tools.digest_auth.on' : True,
|
||||
'tools.digest_auth.realm' : (_('Password to access your calibre library. Username is ') + opts.username.strip()).encode('ascii', 'replace'),
|
||||
'tools.digest_auth.users' : {opts.username.strip():opts.password.strip()},
|
||||
}
|
||||
|
||||
|
||||
self.config = {}
|
||||
self.is_running = False
|
||||
self.exception = None
|
||||
self.setup_loggers()
|
||||
cherrypy.engine.bonjour.subscribe()
|
||||
if not wsgi:
|
||||
self.setup_loggers()
|
||||
cherrypy.engine.bonjour.subscribe()
|
||||
self.config['global'] = {
|
||||
'tools.gzip.on' : True,
|
||||
'tools.gzip.mime_types': ['text/html', 'text/plain',
|
||||
'text/xml', 'text/javascript', 'text/css'],
|
||||
}
|
||||
if opts.password:
|
||||
self.config['/'] = {
|
||||
'tools.digest_auth.on' : True,
|
||||
'tools.digest_auth.realm' : (
|
||||
_('Password to access your calibre library. Username is ')
|
||||
+ opts.username.strip()),
|
||||
'tools.digest_auth.users' : {opts.username.strip():opts.password.strip()},
|
||||
}
|
||||
|
||||
self.__dispatcher__ = DispatchController(self.opts.url_prefix, wsgi)
|
||||
for x in self.__class__.__bases__:
|
||||
if hasattr(x, 'add_routes'):
|
||||
x.add_routes(self, self.__dispatcher__)
|
||||
root_conf = self.config.get('/', {})
|
||||
root_conf['request.dispatch'] = self.__dispatcher__.dispatcher
|
||||
self.config['/'] = root_conf
|
||||
|
||||
def set_database(self, db):
|
||||
self.db = db
|
||||
@ -183,14 +199,6 @@ class LibraryServer(ContentServer, MobileServer, XMLServer, OPDSServer, Cache,
|
||||
|
||||
def start(self):
|
||||
self.is_running = False
|
||||
d = DispatchController(self.opts.url_prefix)
|
||||
for x in self.__class__.__bases__:
|
||||
if hasattr(x, 'add_routes'):
|
||||
x.add_routes(self, d)
|
||||
root_conf = self.config.get('/', {})
|
||||
root_conf['request.dispatch'] = d.dispatcher
|
||||
self.config['/'] = root_conf
|
||||
|
||||
cherrypy.tree.mount(root=None, config=self.config)
|
||||
try:
|
||||
try:
|
||||
|
||||
@ -123,9 +123,10 @@ def get_category_items(category, items, restriction, datatype, prefix): # {{{
|
||||
|
||||
def item(i):
|
||||
templ = (u'<div title="{4}" class="category-item">'
|
||||
'<div class="category-name">{0}</div><div>{1}</div>'
|
||||
'<div>{2}'
|
||||
'<span class="href">{5}{3}</span></div></div>')
|
||||
'<div class="category-name">'
|
||||
'<a href="{5}{3}" title="{4}">{0}</a></div>'
|
||||
'<div>{1}</div>'
|
||||
'<div>{2}</div></div>')
|
||||
rating, rstring = render_rating(i.avg_rating, prefix)
|
||||
name = xml(i.name)
|
||||
if datatype == 'rating':
|
||||
@ -142,7 +143,7 @@ def get_category_items(category, items, restriction, datatype, prefix): # {{{
|
||||
q = category
|
||||
href = '/browse/matches/%s/%s'%(quote(q), quote(id_))
|
||||
return templ.format(xml(name), rating,
|
||||
xml(desc), xml(href), rstring, prefix)
|
||||
xml(desc), xml(href, True), rstring, prefix)
|
||||
|
||||
items = list(map(item, items))
|
||||
return '\n'.join(['<div class="category-container">'] + items + ['</div>'])
|
||||
@ -335,9 +336,10 @@ class BrowseServer(object):
|
||||
icon = 'blank.png'
|
||||
cats.append((meta['name'], category, icon))
|
||||
|
||||
cats = [('<li title="{2} {0}"><img src="{3}{src}" alt="{0}" />'
|
||||
cats = [('<li><a title="{2} {0}" href="/browse/category/{1}"> </a>'
|
||||
'<img src="{3}{src}" alt="{0}" />'
|
||||
'<span class="label">{0}</span>'
|
||||
'<span class="url">{3}/browse/category/{1}</span></li>')
|
||||
'</li>')
|
||||
.format(xml(x, True), xml(quote(y)), xml(_('Browse books by')),
|
||||
self.opts.url_prefix, src='/browse/icon/'+z)
|
||||
for x, y, z in cats]
|
||||
@ -393,14 +395,15 @@ class BrowseServer(object):
|
||||
for x in sorted(starts):
|
||||
category_groups[x] = len([y for y in items if
|
||||
getter(y).upper().startswith(x)])
|
||||
items = [(u'<h3 title="{0}">{0} <span>[{2}]</span></h3><div>'
|
||||
items = [(u'<h3 title="{0}"><a class="load_href" title="{0}"'
|
||||
u' href="{4}{3}"><strong>{0}</strong> [{2}]</a></h3><div>'
|
||||
u'<div class="loaded" style="display:none"></div>'
|
||||
u'<div class="loading"><img alt="{1}" src="{4}/static/loading.gif" /><em>{1}</em></div>'
|
||||
u'<span class="load_href">{4}{3}</span></div>').format(
|
||||
u'</div>').format(
|
||||
xml(s, True),
|
||||
xml(_('Loading, please wait'))+'…',
|
||||
unicode(c),
|
||||
xml(u'/browse/category_group/%s/%s'%(category, s)),
|
||||
xml(u'/browse/category_group/%s/%s'%(category, s), True),
|
||||
self.opts.url_prefix)
|
||||
for s, c in category_groups.items()]
|
||||
items = '\n\n'.join(items)
|
||||
@ -460,13 +463,14 @@ class BrowseServer(object):
|
||||
@Endpoint()
|
||||
def browse_catalog(self, category=None, category_sort=None):
|
||||
'Entry point for top-level, categories and sub-categories'
|
||||
prefix = '' if self.is_wsgi else self.opts.url_prefix
|
||||
if category == None:
|
||||
ans = self.browse_toplevel()
|
||||
elif category == 'newest':
|
||||
raise cherrypy.InternalRedirect(self.opts.url_prefix +
|
||||
raise cherrypy.InternalRedirect(prefix +
|
||||
'/browse/matches/newest/dummy')
|
||||
elif category == 'allbooks':
|
||||
raise cherrypy.InternalRedirect(self.opts.url_prefix +
|
||||
raise cherrypy.InternalRedirect(prefix +
|
||||
'/browse/matches/allbooks/dummy')
|
||||
else:
|
||||
ans = self.browse_category(category, category_sort)
|
||||
@ -562,7 +566,8 @@ class BrowseServer(object):
|
||||
if not val:
|
||||
val = ''
|
||||
args[key] = xml(val, True)
|
||||
fname = ascii_filename(args['title']) + ' - ' + ascii_filename(args['authors'])
|
||||
fname = quote(ascii_filename(args['title']) + ' - ' +
|
||||
ascii_filename(args['authors']))
|
||||
return args, fmt, fmts, fname
|
||||
|
||||
@Endpoint(mimetype='application/json; charset=utf-8')
|
||||
|
||||
@ -70,10 +70,10 @@ class ContentServer(object):
|
||||
id = id.rpartition('_')[-1].partition('.')[0]
|
||||
match = re.search(r'\d+', id)
|
||||
if not match:
|
||||
raise cherrypy.HTTPError(400, 'id:%s not an integer'%id)
|
||||
raise cherrypy.HTTPError(404, 'id:%s not an integer'%id)
|
||||
id = int(match.group())
|
||||
if not self.db.has_id(id):
|
||||
raise cherrypy.HTTPError(400, 'id:%d does not exist in database'%id)
|
||||
raise cherrypy.HTTPError(404, 'id:%d does not exist in database'%id)
|
||||
if what == 'thumb' or what.startswith('thumb_'):
|
||||
try:
|
||||
width, height = map(int, what.split('_')[1:])
|
||||
|
||||
@ -24,6 +24,17 @@ def stop_threaded_server(server):
|
||||
server.exit()
|
||||
server.thread = None
|
||||
|
||||
def create_wsgi_app(path_to_library=None, prefix=''):
|
||||
'WSGI entry point'
|
||||
from calibre.library import db
|
||||
cherrypy.config.update({'environment': 'embedded'})
|
||||
db = db(path_to_library)
|
||||
parser = option_parser()
|
||||
opts, args = parser.parse_args(['calibre-server'])
|
||||
opts.url_prefix = prefix
|
||||
server = LibraryServer(db, opts, wsgi=True, show_tracebacks=True)
|
||||
return cherrypy.Application(server, script_name=None, config=server.config)
|
||||
|
||||
def option_parser():
|
||||
parser = config().option_parser('%prog '+ _(
|
||||
'''[options]
|
||||
@ -47,6 +58,9 @@ The OPDS interface is advertised via BonJour automatically.
|
||||
help=_('Specifies a restriction to be used for this invocation. '
|
||||
'This option overrides any per-library settings specified'
|
||||
' in the GUI'))
|
||||
parser.add_option('--auto-reload', default=False, action='store_true',
|
||||
help=_('Auto reload server when source code changes. May not'
|
||||
' work in all environments.'))
|
||||
return parser
|
||||
|
||||
|
||||
|
||||
@ -7,6 +7,7 @@ __docformat__ = 'restructuredtext en'
|
||||
|
||||
import re, os
|
||||
import __builtin__
|
||||
from urllib import quote
|
||||
|
||||
import cherrypy
|
||||
from lxml import html
|
||||
@ -115,13 +116,13 @@ def build_index(books, num, search, sort, order, start, total, url_base, CKEYS,
|
||||
|
||||
data = TD()
|
||||
for fmt in book['formats'].split(','):
|
||||
a = ascii_filename(book['authors'])
|
||||
t = ascii_filename(book['title'])
|
||||
a = quote(ascii_filename(book['authors']))
|
||||
t = quote(ascii_filename(book['title']))
|
||||
s = SPAN(
|
||||
A(
|
||||
fmt.lower(),
|
||||
href=prefix+'/get/%s/%s-%s_%d.%s' % (fmt, a, t,
|
||||
book['id'], fmt)
|
||||
book['id'], fmt.lower())
|
||||
),
|
||||
CLASS('button'))
|
||||
s.tail = u''
|
||||
|
||||
@ -36,6 +36,7 @@ FileTypePlugin
|
||||
|
||||
.. _pluginsMetadataPlugin:
|
||||
|
||||
|
||||
Metadata plugins
|
||||
-------------------
|
||||
|
||||
@ -50,7 +51,6 @@ Metadata plugins
|
||||
:members:
|
||||
:member-order: bysource
|
||||
|
||||
.. _pluginsMetadataSource:
|
||||
|
||||
Catalog plugins
|
||||
----------------
|
||||
@ -60,6 +60,7 @@ Catalog plugins
|
||||
:members:
|
||||
:member-order: bysource
|
||||
|
||||
.. _pluginsMetadataSource:
|
||||
|
||||
Metadata download plugins
|
||||
--------------------------
|
||||
|
||||
108
src/calibre/manual/server.rst
Normal file
108
src/calibre/manual/server.rst
Normal file
@ -0,0 +1,108 @@
|
||||
.. include:: global.rst
|
||||
|
||||
.. _servertutorial:
|
||||
|
||||
Integrating the |app| content server into other servers
|
||||
==========================================================
|
||||
|
||||
Here, we will show you how to integrate the |app| content server into another server. The most common reason for this is to make use of SSL or more sophisticated authentication. There are two main techniques: Running the |app| content server as a standalone process and using a reverse proxy to connect it with your main server or running the content server in process in your main server with WSGI. The examples below are all for Apache 2.x on linux, but should be easily adaptable to other platforms.
|
||||
|
||||
.. contents:: Contents
|
||||
:depth: 2
|
||||
:local:
|
||||
|
||||
.. note:: This only applies to calibre releases >= 0.7.25
|
||||
|
||||
Using a reverse proxy
|
||||
-----------------------
|
||||
|
||||
This is the simplest approach as it allows you to use the binary calibre install with no external dependencies/system integration requirements.
|
||||
|
||||
First start the |app| content server as shown below::
|
||||
|
||||
calibre-server --url-prefix /calibre --port 8080
|
||||
|
||||
Now suppose you are using Apache as your main server. First enable the proxy modules in apache, by adding the following to :file:`httpd.conf`::
|
||||
|
||||
LoadModule proxy_module modules/mod_proxy.so
|
||||
LoadModule proxy_http_module modules/mod_proxy_http.so
|
||||
|
||||
The exact technique for enabling the proxy modules will vary depending on your Apache installation. Once you have the proxy modules enabled, add the following rules to httpd.conf (or if you are using virtual hosts to the conf file for the virtual host in question::
|
||||
|
||||
RewriteEngine on
|
||||
RewriteRule ^/calibre/(.*) http://localhost:8080/calibre/$1 [proxy]
|
||||
RewriteRule ^/calibre http://localhost:8080 [proxy]
|
||||
|
||||
That's all, you will now be able to access the |app| Content Server under the /calibre URL in your apache server.
|
||||
|
||||
.. note:: If you are willing to devote an entire VirtualHost to the content server, then there is no need to use --url-prefix and RewriteRule, instead just use the ProxyPass directive.
|
||||
|
||||
In process
|
||||
------------
|
||||
|
||||
The calibre content server can be run directly, in process, inside a host server like Apache using the WSGI framework.
|
||||
|
||||
.. note:: For this to work, all the dependencies needed by calibre must be installed on your system. On linux, this can be achieved fairly easily by installing the distribution provided calibre package (provided it is up to date).
|
||||
|
||||
First, we have to create a WSGI *adapter* for the calibre content server. Here is a template you can use for the purpose. Replace the paths as directed in the comments
|
||||
|
||||
.. code-block:: python
|
||||
|
||||
# WSGI script file to run calibre content server as a WSGI app
|
||||
|
||||
import sys, os
|
||||
|
||||
|
||||
# You can get the paths referenced here by running
|
||||
# calibre-debug --paths
|
||||
# on your server
|
||||
|
||||
# The first entry from CALIBRE_PYTHON_PATH
|
||||
sys.path.insert(0, '/home/kovid/work/calibre/src')
|
||||
|
||||
# CALIBRE_RESOURCES_PATH
|
||||
sys.resources_location = '/home/kovid/work/calibre/resources'
|
||||
|
||||
# CALIBRE_EXTENSIONS_PATH
|
||||
sys.extensions_location = '/home/kovid/work/calibre/src/calibre/plugins'
|
||||
|
||||
# Path to directory containing calibre executables
|
||||
sys.executables_location = '/usr/bin'
|
||||
|
||||
# Path to a directory for which the server has read/write permissions
|
||||
# calibre config will be stored here
|
||||
os.environ['CALIBRE_CONFIG_DIRECTORY'] = '/var/www/localhost/calibre-config'
|
||||
|
||||
del sys
|
||||
del os
|
||||
|
||||
from calibre.library.server.main import create_wsgi_app
|
||||
application = create_wsgi_app(
|
||||
# The mount point of this WSGI application (i.e. the first argument to
|
||||
# the WSGIScriptAlias directive). Set to empty string is mounted at /
|
||||
prefix='/calibre',
|
||||
|
||||
# Path to the calibre library to be served
|
||||
# The server process must have write permission for all files/dirs
|
||||
# in this directory or BAD things will happen
|
||||
path_to_library='/home/kovid/documents/demo library'
|
||||
)
|
||||
|
||||
del create_wsgi_app
|
||||
|
||||
Save this adapter as :file:`calibre-wsgi-adpater.py` somewhere your server will have access to it.
|
||||
|
||||
Let's suppose that we want to use WSGI in Apache. First enable WSGI in Apache by adding the following to :file:`httpd.conf`::
|
||||
|
||||
LoadModule proxy_module modules/mod_wsgi.so
|
||||
|
||||
The exact technique for enabling the wsgi module will vary depending on your Apache installation. Once you have the proxy modules enabled, add the following rules to httpd.conf (or if you are using virtual hosts to the conf file for the virtual host in question::
|
||||
|
||||
WSGIScriptAlias /calibre /var/www/localhost/cgi-bin/calibre-wsgi-adapter.py
|
||||
|
||||
Change the path to :file:`calibre-wsgi-adapter.py` to wherever you saved it previously (make sure Apache has access to it).
|
||||
|
||||
That's all, you will now be able to access the |app| Content Server under the /calibre URL in your apache server.
|
||||
|
||||
.. note:: For more help with using mod_wsgi in Apache, see `mod_wsgi <http://code.google.com/p/modwsgi/wiki/WhereToGetHelp>`_.
|
||||
|
||||
@ -16,4 +16,5 @@ Here you will find tutorials to get you started using |app|'s more advanced feat
|
||||
template_lang
|
||||
regexp
|
||||
portable
|
||||
server
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@ -583,7 +583,7 @@ class BasicNewsRecipe(Recipe):
|
||||
self.title = unicode(self.title, 'utf-8', 'replace')
|
||||
|
||||
self.debug = options.verbose > 1
|
||||
self.output_dir = os.getcwd()
|
||||
self.output_dir = os.path.abspath(os.getcwdu())
|
||||
self.verbose = options.verbose
|
||||
self.test = options.test
|
||||
self.username = options.username
|
||||
@ -594,7 +594,6 @@ class BasicNewsRecipe(Recipe):
|
||||
if self.touchscreen:
|
||||
self.template_css += self.output_profile.touchscreen_news_css
|
||||
|
||||
self.output_dir = os.path.abspath(self.output_dir)
|
||||
if options.test:
|
||||
self.max_articles_per_feed = 2
|
||||
self.simultaneous_downloads = min(4, self.simultaneous_downloads)
|
||||
@ -958,6 +957,8 @@ class BasicNewsRecipe(Recipe):
|
||||
self.log.error(_('Could not download cover: %s')%str(err))
|
||||
self.log.debug(traceback.format_exc())
|
||||
else:
|
||||
if not cu:
|
||||
return
|
||||
cdata = None
|
||||
if os.access(cu, os.R_OK):
|
||||
cdata = open(cu, 'rb').read()
|
||||
@ -988,6 +989,7 @@ class BasicNewsRecipe(Recipe):
|
||||
self.cover_path = cpath
|
||||
|
||||
def download_cover(self):
|
||||
self.cover_path = None
|
||||
try:
|
||||
self._download_cover()
|
||||
except:
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user