mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Sync to trunk.
This commit is contained in:
John Schember
commit
e3aafa1789
@ -4,6 +4,104 @@
|
||||
# for important features/bug fixes.
|
||||
# Also, each release can have new and improved recipes.
|
||||
|
||||
- version: 0.6.51
|
||||
date: 2010-04-30
|
||||
|
||||
bug fixes:
|
||||
- title: "Fix regression that broke EPUB output in 0.6.50 when converting lists"
|
||||
|
||||
|
||||
- version: 0.6.50
|
||||
date: 2010-04-30
|
||||
|
||||
new features:
|
||||
- title: "Add merge book feature"
|
||||
type: major
|
||||
desc: >
|
||||
"You can now merge multiple books into a single book, by clicking the arrow next to the edit meta information button.
|
||||
Meta information from the books will be merged as well as individual book files in different formats"
|
||||
|
||||
- title: "Support for the Samsung Galaxy Spica and the Palm Pre"
|
||||
|
||||
- title: "Add a 'Go to' context menu to the ebook viewer"
|
||||
tickets: [1230]
|
||||
|
||||
- title: "Show an asterisk next to version number when user is using CALIBRE_DEVELOP_FROM"
|
||||
tickets: [5417]
|
||||
|
||||
- title: "Import ComicBookLover metadata from CBZ files"
|
||||
tickets: [5402]
|
||||
|
||||
- title: "Add keyboard shortcut for viewing a specific format"
|
||||
tickets: [5408]
|
||||
|
||||
- title: "EPUB Output: Add option to not use SVG for covers. Useful if you want to generate an EPUB for devices like the iPhone or JetBook Lite that don't support SVG covers"
|
||||
tickets: [5409]
|
||||
|
||||
- title: "In the book info display area, only show series and tags if there are any. Move comments to the bottom."
|
||||
tickets: [5391]
|
||||
|
||||
bug fixes:
|
||||
- title: "E-book viewer: Use the Qt API to set document padding during next page operation, instead of javascript."
|
||||
tickets: [5343]
|
||||
|
||||
- title: "E-book viewer: Handle self-closing heading tags in XHTML documents correctly."
|
||||
tickets: [5413]
|
||||
|
||||
- title: "Conversion pipeline: Ignore CSS pseudo selectors"
|
||||
tickets: [5337]
|
||||
|
||||
- title: "MOBI Input: Ignore form tags"
|
||||
tickets: [5378]
|
||||
|
||||
- title: "Handle a scheduled custom recipe being deleted gracefully"
|
||||
tickets: [5366]
|
||||
|
||||
- title: "ebook-convert: Don't rename PNG covers to JPG"
|
||||
tickets: [5379]
|
||||
|
||||
- title: "Conversion pipeline: Respect width and height attributes in addition to width and height in CSS"
|
||||
|
||||
- title: "Fix regression which broke the use of HTML files in the regexp testing wizard"
|
||||
tickets: [5341]
|
||||
|
||||
- title: "Fix match highlighting for multi-line regexps in the regexp testing wizard"
|
||||
tickets: [5414]
|
||||
|
||||
- title: "EPUB Output: Workaround Adobe Digital Editions bug in rendering of lists with a left margin set."
|
||||
tickets: [5415]
|
||||
|
||||
- title: "PRS 505/600/700/300 driver: Don't give an error message when editing metadata on SD card and cache directory does not exist"
|
||||
tickets: [5410]
|
||||
|
||||
- title: "When converting EPUB to EPUB multiple times and creating book jacket from metadata, if an existing book jacket is found,
|
||||
replace it. This will only work with EPUBs created with the current release onwards"
|
||||
|
||||
- title: "Correctly handle HTML in comments"
|
||||
tickets: [5237]
|
||||
|
||||
- title: "Kindle driver: When transferring files whose names start witha period, replace the period."
|
||||
tickets: [5367]
|
||||
|
||||
- title: "Conversion pipeline: When decoding XML (but not XHTML) if no encoding is specified, assume utf-8. Make entity conversion more robust. When splitting html handle ids with quotes in them correctly"
|
||||
|
||||
new recipes:
|
||||
- title: The Old New Thing, Berlingske, ABC, Ultima Hora, China Daily, Dani
|
||||
author: Darko Miletic
|
||||
|
||||
- title: Observa Digital
|
||||
author: yrvn
|
||||
|
||||
- title: "Bill O'Reilly and Sean Hannity"
|
||||
author: Rob Lammert
|
||||
|
||||
improved recipes:
|
||||
- PC Magazine
|
||||
- Reuters
|
||||
- Sueddeutsche Zeitung
|
||||
- "il Sole 24 Ore"
|
||||
- La Repubblica
|
||||
|
||||
- version: 0.6.49
|
||||
date: 2010-04-23
|
||||
|
||||
|
||||
BIN
resources/images/news/abc_py.png
Normal file
BIN
resources/images/news/abc_py.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 2.6 KiB |
BIN
resources/images/news/berlingske_dk.png
Normal file
BIN
resources/images/news/berlingske_dk.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 807 B |
BIN
resources/images/news/chinadaily.png
Normal file
BIN
resources/images/news/chinadaily.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 491 B |
BIN
resources/images/news/oldnewthing.png
Normal file
BIN
resources/images/news/oldnewthing.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 786 B |
BIN
resources/images/news/ultimahora.png
Normal file
BIN
resources/images/news/ultimahora.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 690 B |
49
resources/recipes/abc_py.recipe
Normal file
49
resources/recipes/abc_py.recipe
Normal file
@ -0,0 +1,49 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
abc.com.py
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class ABC_py(BasicNewsRecipe):
|
||||
title = 'ABC digital'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'Noticias de Paraguay y el resto del mundo'
|
||||
publisher = 'ABC'
|
||||
category = 'news, politics, Paraguay'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 200
|
||||
no_stylesheets = True
|
||||
encoding = 'cp1252'
|
||||
use_embedded_content = False
|
||||
language = 'es_PY'
|
||||
remove_empty_feeds = True
|
||||
publication_type = 'newspaper'
|
||||
extra_css = ' body{font-family: Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em} '
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : category
|
||||
, 'publisher' : publisher
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
remove_tags = [dict(name=['form','iframe','embed','object','link','base','table']),dict(attrs={'class':'toolbox'})]
|
||||
remove_tags_after = dict(attrs={'class':'date'})
|
||||
keep_only_tags = [dict(attrs={'class':'zcontent'})]
|
||||
|
||||
|
||||
feeds = [
|
||||
(u'Ultimo momento' , u'http://www.abc.com.py/ultimo-momento.xml' )
|
||||
,(u'Nacionales' , u'http://www.abc.com.py/nacionales.xml' )
|
||||
,(u'Internacionales' , u'http://www.abc.com.py/internacionales.xml' )
|
||||
,(u'Deportes' , u'http://www.abc.com.py/deportes.xml' )
|
||||
,(u'Espectaculos' , u'http://www.abc.com.py/espectaculos.xml' )
|
||||
,(u'Ciencia y Tecnologia', u'http://www.abc.com.py/ciencia-y-tecnologia.xml')
|
||||
]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
return soup
|
||||
59
resources/recipes/adnkronos.recipe
Normal file
59
resources/recipes/adnkronos.recipe
Normal file
@ -0,0 +1,59 @@
|
||||
#!/usr/bin/env python
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'Gabriele Marini, based on Darko Miletic'
|
||||
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
description = 'Italian daily newspaper - 02-05-2010'
|
||||
|
||||
'''
|
||||
http://www.adnkronos.com/
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Adnkronos(BasicNewsRecipe):
|
||||
__author__ = 'Gabriele Marini'
|
||||
description = 'News agency'
|
||||
cover_url = 'http://www.adnkronos.com/IGN6/img/popup_ign.jpg'
|
||||
title = u'Adnkronos'
|
||||
publisher = 'Adnkronos Group - ews agency'
|
||||
category = 'News, politics, culture, economy, general interest'
|
||||
|
||||
language = 'it'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 80
|
||||
use_embedded_content = False
|
||||
recursion = 10
|
||||
|
||||
remove_javascript = True
|
||||
def get_article_url(self, article):
|
||||
link = article.get('id', article.get('guid', None))
|
||||
return link
|
||||
|
||||
extra_css = ' .newsAbstract{font-style: italic} '
|
||||
keep_only_tags = [dict(name='div', attrs={'class':['breadCrumbs','newsTop','newsText']})
|
||||
]
|
||||
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':['leogoo','leogoo2']})
|
||||
]
|
||||
|
||||
|
||||
feeds = [
|
||||
(u'Prima Pagina', u'http://rss.adnkronos.com/RSS_PrimaPagina.xml'),
|
||||
(u'Ultima Ora', u'http://rss.adnkronos.com/RSS_Ultimora.xml'),
|
||||
(u'Politica', u'http://rss.adnkronos.com/RSS_Politica.xml'),
|
||||
(u'Esteri', u'http://rss.adnkronos.com/RSS_Esteri.xml'),
|
||||
(u'Cronoca', u'http://rss.adnkronos.com/RSS_Cronaca.xml'),
|
||||
(u'Economia', u'http://rss.adnkronos.com/RSS_Economia.xml'),
|
||||
(u'Finanza', u'http://rss.adnkronos.com/RSS_Finanza.xml'),
|
||||
(u'CyberNews', u'http://rss.adnkronos.com/RSS_CyberNews.xml'),
|
||||
(u'Spettacolo', u'http://rss.adnkronos.com/RSS_Spettacolo.xml'),
|
||||
(u'Cultura', u'http://rss.adnkronos.com/RSS_Cultura.xml'),
|
||||
(u'Sport', u'http://rss.adnkronos.com/RSS_Sport.xml'),
|
||||
(u'Sostenibilita', u'http://rss.adnkronos.com/RSS_Sostenibilita.xml'),
|
||||
(u'Salute', u'http://rss.adnkronos.com/RSS_Salute.xml')
|
||||
]
|
||||
|
||||
49
resources/recipes/berlingske_dk.recipe
Normal file
49
resources/recipes/berlingske_dk.recipe
Normal file
@ -0,0 +1,49 @@
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
berlingske.dk
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Berlingske_dk(BasicNewsRecipe):
|
||||
title = 'Berlingske Tidende'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'News from Denmark'
|
||||
publisher = 'berlingske.dk'
|
||||
category = 'news, politics, Denmark'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
remove_empty_feeds = True
|
||||
use_embedded_content = False
|
||||
publication_type = 'newspaper'
|
||||
encoding = 'utf8'
|
||||
language = 'da'
|
||||
masthead_url = 'http://www.berlingske.dk/sites/all/themes/bm/img/layout/masthead_bg.gif'
|
||||
extra_css = ' body{font-family: Arial,Helvetica,sans-serif } h1,.manchet,.byline{font-family: Cambria,Georgia,Times,"Times New Roman",serif } '
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : category
|
||||
, 'publisher': publisher
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
feeds = [
|
||||
(u'Breaking news' , u'http://www.berlingske.dk/breaking/rss' )
|
||||
,(u'Seneste nyt' , u'http://www.berlingske.dk/seneste/rss' )
|
||||
,(u'Topnyheder' , u'http://www.berlingske.dk/top/rss' )
|
||||
,(u'Danmark' , u'http://www.berlingske.dk/danmark/seneste/rss' )
|
||||
,(u'Verden' , u'http://www.berlingske.dk/verden/seneste/rss' )
|
||||
,(u'Klima' , u'http://www.berlingske.dk/klima/seneste/rss' )
|
||||
,(u'Debat' , u'http://www.berlingske.dk/debat/seneste/rss' )
|
||||
,(u'Koebenhavn' , u'http://www.berlingske.dk/koebenhavn/seneste/rss')
|
||||
,(u'Politik' , u'http://www.berlingske.dk/politik/seneste/rss' )
|
||||
,(u'Kultur' , u'http://www.berlingske.dk/kultur/seneste/rss' )
|
||||
]
|
||||
|
||||
keep_only_tags = [dict(attrs={'class':['first','pt-article']})]
|
||||
remove_tags = [dict(name=['object','link','base','iframe','embed'])]
|
||||
|
||||
48
resources/recipes/chinadaily.recipe
Normal file
48
resources/recipes/chinadaily.recipe
Normal file
@ -0,0 +1,48 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
www.chinadaily.com.cn
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Pagina12(BasicNewsRecipe):
|
||||
title = 'China Daily'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'Chinadaily.com.cn is the largest English portal in China, providing news, business information, BBS, learning materials.'
|
||||
publisher = 'China Daily Information Co.'
|
||||
category = 'news, politics, China'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 200
|
||||
no_stylesheets = True
|
||||
encoding = 'utf8'
|
||||
use_embedded_content = False
|
||||
language = 'en_CN'
|
||||
remove_empty_feeds = True
|
||||
publication_type = 'newsportal'
|
||||
masthead_url = 'http://www.chinadaily.com.cn/15421.files/chinadailylogo_e_20100301.jpg'
|
||||
extra_css = ' body{font-family: Arial,Helvetica,sans-serif } '
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : category
|
||||
, 'publisher' : publisher
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
remove_tags = [dict(name=['object','embed','iframe','table'])]
|
||||
keep_only_tags = [dict(attrs={'id':['Title_e','Content']})]
|
||||
|
||||
|
||||
feeds = [
|
||||
(u'China' , u'http://www.chinadaily.com.cn/rss/china_rss.xml' )
|
||||
,(u'Business', u'http://www.chinadaily.com.cn/rss/bizchina_rss.xml')
|
||||
,(u'World' , u'http://www.chinadaily.com.cn/rss/world_rss.xml' )
|
||||
,(u'Sports' , u'http://www.chinadaily.com.cn/rss/sports_rss.xml' )
|
||||
,(u'Opinions', u'http://www.chinadaily.com.cn/rss/opinion_rss.xml' )
|
||||
]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
return soup
|
||||
57
resources/recipes/el_observador.recipe
Normal file
57
resources/recipes/el_observador.recipe
Normal file
@ -0,0 +1,57 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = '2010, Yuri Alvarez<me at yurialvarez.com>'
|
||||
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
|
||||
'''
|
||||
observa.com.uy
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class ObservaDigital(BasicNewsRecipe):
|
||||
title = 'Observa Digital'
|
||||
__author__ = 'yrvn'
|
||||
description = 'Noticias de Uruguay'
|
||||
language = 'es'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
use_embedded_content = False
|
||||
recursion = 5
|
||||
encoding = 'utf8'
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
keep_only_tags = [dict(id=['contenido'])]
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'id':'contenedorVinculadas'}),
|
||||
dict(name='p', attrs={'id':'nota_firma'}),
|
||||
dict(name=['object','link'])
|
||||
]
|
||||
|
||||
extra_css = '''
|
||||
h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
|
||||
h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
|
||||
h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
|
||||
p {font-family:Arial,Helvetica,sans-serif;}
|
||||
'''
|
||||
feeds = [
|
||||
(u'Actualidad', u'http://www.observa.com.uy/RSS/actualidad.xml'),
|
||||
(u'Deportes', u'http://www.observa.com.uy/RSS/deportes.xml'),
|
||||
(u'Vida', u'http://www.observa.com.uy/RSS/vida.xml'),
|
||||
(u'Ciencia y Tecnologia', u'http://www.observa.com.uy/RSS/ciencia.xml')
|
||||
]
|
||||
|
||||
def get_cover_url(self):
|
||||
index = 'http://www.observa.com.uy/'
|
||||
soup = self.index_to_soup(index)
|
||||
for image in soup.findAll('img',alt=True):
|
||||
if image['alt'].startswith('Tapa El Observador'):
|
||||
return image['src'].rstrip('b.jpg') + '.jpg'
|
||||
return None
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
return soup
|
||||
60
resources/recipes/il_giornale.recipe
Normal file
60
resources/recipes/il_giornale.recipe
Normal file
@ -0,0 +1,60 @@
|
||||
#!/usr/bin/env python
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'Gabriele Marini, based on Darko Miletic'
|
||||
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
description = 'Italian daily newspaper - 19-04-2010'
|
||||
|
||||
'''
|
||||
http://www.ilgiornale.it/
|
||||
'''
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class IlGiornale(BasicNewsRecipe):
|
||||
__author__ = 'Marini Gabriele'
|
||||
description = 'Italian daily newspaper'
|
||||
|
||||
cover_url = 'http://www.ilgiornale.it/img_v1/logo.gif'
|
||||
title = u'Il Giornale'
|
||||
publisher = 'Il Giornale ON-LINE S.r.l.'
|
||||
category = 'News, politics, culture, economy, general interest'
|
||||
|
||||
language = 'it'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 50
|
||||
use_embedded_content = False
|
||||
recursion = 100
|
||||
|
||||
no_stylesheets = True
|
||||
conversion_options = {'linearize_tables':True}
|
||||
remove_javascript = True
|
||||
|
||||
|
||||
def get_article_url(self, article):
|
||||
return article.get('guid', article.get('id', None))
|
||||
|
||||
def print_version(self, url):
|
||||
raw = self.browser.open(url).read()
|
||||
soup = BeautifulSoup(raw.decode('utf8', 'replace'))
|
||||
all_print_tags = soup.find('div', {'style':'float:left; width:35%;'})
|
||||
print_link = all_print_tags.contents[1]
|
||||
if all_print_tags is None:
|
||||
return url
|
||||
return print_link['href']
|
||||
|
||||
|
||||
feeds = [
|
||||
(u'Ultime Notizie',u'http://www.ilgiornale.it/?RSS=S'),
|
||||
(u'All\'Interno', u'http://www.ilgiornale.it/la_s.pic1?SID=8&RSS=S'),
|
||||
(u'Esteri', u'http://www.ilgiornale.it/la_s.pic1?SID=6&RSS=S'),
|
||||
(u'Economia', u'http://www.ilgiornale.it/la_s.pic1?SID=5&RSS=S'),
|
||||
(u'Cultura', u'http://www.ilgiornale.it/la_s.pic1?SID=4&RSS=S'),
|
||||
(u'Spettacoli', u'http://www.ilgiornale.it/la_s.pic1?SID=14&RSS=S'),
|
||||
(u'Sport', u'http://www.ilgiornale.it/la_s.pic1?SID=15&RSS=S'),
|
||||
(u'Tech&Web', u'http://www.ilgiornale.it/la_s.pic1?SID=35&RSS=S'),
|
||||
(u'Edizione di Roma', u'http://www.ilgiornale.it/roma.pic1?SID=13&RSS=S'),
|
||||
(u'Edizione di Milano', u'http://www.ilgiornale.it/milano.pic1?SID=9&RSS=S'),
|
||||
(u'Edizione di Genova', u'http://www.ilgiornale.it/genova.pic1?SID=7&RSS=S')
|
||||
]
|
||||
56
resources/recipes/il_messaggero.recipe
Normal file
56
resources/recipes/il_messaggero.recipe
Normal file
@ -0,0 +1,56 @@
|
||||
#!/usr/bin/env python
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'Gabriele Marini, based on Darko Miletic'
|
||||
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
||||
description = 'Italian daily newspaper - v1.01 (04, January 2010)'
|
||||
|
||||
'''
|
||||
http://www.messaggero.it/
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class IlMessaggero(BasicNewsRecipe):
|
||||
__author__ = 'Gabriele Marini'
|
||||
description = 'Italian News'
|
||||
|
||||
cover_url = 'http://www.ilmessaggero.it/img_tst/logomsgr.gif'
|
||||
title = u'Il Messaggero'
|
||||
publisher = 'Caltagirone Editore'
|
||||
category = 'News, politics, culture, economy, general interest'
|
||||
|
||||
language = 'it'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
|
||||
oldest_article = 5
|
||||
max_articles_per_feed = 100
|
||||
use_embedded_content = False
|
||||
recursion = 10
|
||||
|
||||
remove_javascript = True
|
||||
|
||||
|
||||
keep_only_tags = [dict(name='h1', attrs={'class':'titoloLettura2'}),
|
||||
dict(name='h2', attrs={'class':'sottotitLettura'}),
|
||||
dict(name='span', attrs={'class':'testoArticoloG'})
|
||||
]
|
||||
|
||||
|
||||
|
||||
feeds = [
|
||||
(u'HomePage', u'http://www.ilmessaggero.it/rss/home.xml'),
|
||||
(u'Primo Piano', u'http://www.ilmessaggero.it/rss/initalia_primopiano.xml'),
|
||||
(u'Cronaca Bianca', u'http://www.ilmessaggero.it/rss/initalia_cronacabianca.xml'),
|
||||
(u'Cronaca Nera', u'http://www.ilmessaggero.it/rss/initalia_cronacanera.xml'),
|
||||
(u'Economia e Finanza', u'http://www.ilmessaggero.it/rss/economia.xml'),
|
||||
(u'Politica', u'http://www.ilmessaggero.it/rss/initalia_politica.xml'),
|
||||
(u'Scienza e Tecnologia', u'http://www.ilmessaggero.it/rss/scienza.xml'),
|
||||
(u'Cinema', u'http://www.ilmessaggero.it/rss.php?refresh_ce#'),
|
||||
(u'Viaggi', u'http://www.ilmessaggero.it/rss.php?refresh_ce#'),
|
||||
(u'Roma', u'http://www.ilmessaggero.it/rss/roma.xml'),
|
||||
(u'Cultura e Tendenze', u'http://www.ilmessaggero.it/rss/roma_culturaspet.xml'),
|
||||
(u'Sport', u'http://www.ilmessaggero.it/rss/sport.xml'),
|
||||
(u'Calcio', u'http://www.ilmessaggero.it/rss/sport_calcio.xml'),
|
||||
(u'Motori', u'http://www.ilmessaggero.it/rss/sport_motori.xml')
|
||||
]
|
||||
|
||||
@ -11,12 +11,13 @@ http://www.ilsole24ore.com/
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class ilsole(BasicNewsRecipe):
|
||||
class ilsole24Ore(BasicNewsRecipe):
|
||||
author = 'Lorenzo Vigentini & Edwin van Maastrigt'
|
||||
description = 'Financial news daily paper'
|
||||
|
||||
cover_url = 'http://www.ilsole24ore.com/img2009/header/t_logosole.gif'
|
||||
title = u'il Sole 24 Ore '
|
||||
cover_url = 'http://www.ilsole24ore.com/img2007/print_header.gif'
|
||||
|
||||
title = u'il Sole 24 Ore New'
|
||||
publisher = 'italiaNews'
|
||||
category = 'News, finance, economy, politics'
|
||||
|
||||
@ -35,12 +36,14 @@ class ilsole(BasicNewsRecipe):
|
||||
|
||||
def print_version(self, url):
|
||||
link, sep, params = url.rpartition('?')
|
||||
if link is None:
|
||||
return link.replace('_1.php', '_php')
|
||||
return link.replace('.shtml', '_PRN.shtml')
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'class':'txt'})
|
||||
]
|
||||
remove_tags = [dict(name='br')]
|
||||
# remove_tags = [dict(name='br')]
|
||||
|
||||
feeds = [
|
||||
(u'Prima pagina', u'http://www.ilsole24ore.com/rss/primapagina.xml'),
|
||||
@ -52,13 +55,14 @@ class ilsole(BasicNewsRecipe):
|
||||
(u'Tecnologia e business', u'http://www.ilsole24ore.com/rss/tecnologia-business.xml'),
|
||||
(u'Cultura e tempo libero', u'http://www.ilsole24ore.com/rss/tempolibero-cultura.xml'),
|
||||
(u'Sport', u'http://www.ilsole24ore.com/rss/sport.xml'),
|
||||
(u'Professionisti 24', u'http://www.ilsole24ore.com/rss/prof_home.xml')
|
||||
(u'Professionisti 24', u'http://www.ilsole24ore.com/rss/prof_home.xml'),
|
||||
(u'Ambiente e Sicurezza',u'http://www.ilsole24ore.com/rss/prof_as.xml')
|
||||
]
|
||||
|
||||
extra_css = '''
|
||||
html, body, table, tr, td, h1, h2, h3, h4, h5, h6, p, a, span, br, img {margin:0;padding:0;border:0;font-size:12px;font-family:Arial;}
|
||||
html, body, table, tr, td, h1, h2, h3, h4, h5, h6, p, a, span, br, img {margin:0;padding:0;border:0;font-size:12px;font-family:"Georgia","Times New Roman";}
|
||||
.linkHighlight {color:#0292c6;}
|
||||
.txt {border-bottom:1px solid #7c7c7c;padding-bottom:20px;text-align:justify;}
|
||||
.txt {border-bottom:1px solid #7c7c7c;padding-bottom:20px};text-align:justify;font-family:"serif"}
|
||||
.txt p {line-height:18px;}
|
||||
.txt span {line-height:22px;}
|
||||
.title h3 {color:#7b7b7b;}
|
||||
|
||||
@ -1,3 +1,4 @@
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class JerusalemPost(BasicNewsRecipe):
|
||||
@ -10,8 +11,6 @@ class JerusalemPost(BasicNewsRecipe):
|
||||
__author__ = 'Kovid Goyal'
|
||||
max_articles_per_feed = 10
|
||||
no_stylesheets = True
|
||||
remove_tags_before = {'class':'jp-grid-content'}
|
||||
remove_tags_after = {'id':'body_val'}
|
||||
|
||||
feeds = [ ('Front Page', 'http://www.jpost.com/servlet/Satellite?pagename=JPost/Page/RSS&cid=1123495333346'),
|
||||
('Israel News', 'http://www.jpost.com/servlet/Satellite?pagename=JPost/Page/RSS&cid=1178443463156'),
|
||||
@ -20,9 +19,24 @@ class JerusalemPost(BasicNewsRecipe):
|
||||
('Editorials', 'http://www.jpost.com/servlet/Satellite?pagename=JPost/Page/RSS&cid=1123495333211'),
|
||||
]
|
||||
|
||||
remove_tags = [
|
||||
dict(id=lambda x: x and 'ads.' in x),
|
||||
dict(attrs={'class':['printinfo', 'tt1']}),
|
||||
dict(onclick='DoPrint()'),
|
||||
dict(name='input'),
|
||||
]
|
||||
|
||||
conversion_options = {'linearize_tables':True}
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for x in soup.findAll(name=['form', 'input']):
|
||||
x.name = 'div'
|
||||
for x in soup.findAll('body', style=True):
|
||||
del x['style']
|
||||
for tag in soup.findAll('form'):
|
||||
tag.name = 'div'
|
||||
return soup
|
||||
|
||||
def print_version(self, url):
|
||||
m = re.search(r'(ID|id)=(\d+)', url)
|
||||
if m is not None:
|
||||
id_ = m.group(2)
|
||||
return 'http://www.jpost.com/LandedPages/PrintArticle.aspx?id=%s'%id_
|
||||
return url
|
||||
|
||||
|
||||
@ -10,7 +10,7 @@ http://www.repubblica.it/
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class LaRepublica(BasicNewsRecipe):
|
||||
class LaRepubblica(BasicNewsRecipe):
|
||||
author = 'Lorenzo Vigentini, based on Darko Miletic'
|
||||
description = 'Italian daily newspaper'
|
||||
|
||||
@ -54,21 +54,24 @@ class LaRepublica(BasicNewsRecipe):
|
||||
]
|
||||
|
||||
feeds = [
|
||||
(u'Repubblica Rilievo', u'http://www.repubblica.it/rss/homepage/rss2.0.xml'),
|
||||
(u'Repubblica Cronaca', u'http://www.repubblica.it/rss/cronaca/rss2.0.xml'),
|
||||
(u'Repubblica Esteri', u'http://www.repubblica.it/rss/esteri/rss2.0.xml'),
|
||||
(u'Repubblica Economia', u'http://www.repubblica.it/rss/economia/rss2.0.xml'),
|
||||
(u'Repubblica Politica', u'http://www.repubblica.it/rss/politica/rss2.0.xml'),
|
||||
(u'Repubblica Scienze', u'http://www.repubblica.it/rss/scienze/rss2.0.xml'),
|
||||
(u'Repubblica Tecnologia', u'http://www.repubblica.it/rss/tecnologia/rss2.0.xml'),
|
||||
(u'Repubblica Scuola e Universita', u'http://www.repubblica.it/rss/scuola_e_universita/rss2.0.xml'),
|
||||
(u'Repubblica Ambiente', u'http://www.repubblica.it/rss/ambiente/rss2.0.xml'),
|
||||
(u'Repubblica Cultura', u'http://www.repubblica.it/rss/spettacoli_e_cultura/rss2.0.xml'),
|
||||
(u'Repubblica Persone', u'http://www.repubblica.it/rss/persone/rss2.0.xml'),
|
||||
(u'Repubblica Sport', u'http://www.repubblica.it/rss/sport/rss2.0.xml'),
|
||||
(u'Repubblica Calcio', u'http://www.repubblica.it/rss/sport/calcio/rss2.0.xml'),
|
||||
(u'Repubblica Motori', u'http://www.repubblica.it/rss/motori/rss2.0.xml'),
|
||||
(u'Repubblica Roma', u'http://roma.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Repubblica Torino', u'http://torino.repubblica.it/rss/rss2.0.xml')
|
||||
(u'Rilievo', u'http://www.repubblica.it/rss/homepage/rss2.0.xml'),
|
||||
(u'Cronaca', u'http://www.repubblica.it/rss/cronaca/rss2.0.xml'),
|
||||
(u'Esteri', u'http://www.repubblica.it/rss/esteri/rss2.0.xml'),
|
||||
(u'Economia', u'http://www.repubblica.it/rss/economia/rss2.0.xml'),
|
||||
(u'Politica', u'http://www.repubblica.it/rss/politica/rss2.0.xml'),
|
||||
(u'Scienze', u'http://www.repubblica.it/rss/scienze/rss2.0.xml'),
|
||||
(u'Tecnologia', u'http://www.repubblica.it/rss/tecnologia/rss2.0.xml'),
|
||||
(u'Scuola e Universita', u'http://www.repubblica.it/rss/scuola_e_universita/rss2.0.xml'),
|
||||
(u'Ambiente', u'http://www.repubblica.it/rss/ambiente/rss2.0.xml'),
|
||||
(u'Cultura', u'http://www.repubblica.it/rss/spettacoli_e_cultura/rss2.0.xml'),
|
||||
(u'Persone', u'http://www.repubblica.it/rss/persone/rss2.0.xml'),
|
||||
(u'Sport', u'http://www.repubblica.it/rss/sport/rss2.0.xml'),
|
||||
(u'Calcio', u'http://www.repubblica.it/rss/sport/calcio/rss2.0.xml'),
|
||||
(u'Motori', u'http://www.repubblica.it/rss/motori/rss2.0.xml'),
|
||||
(u'Edizione Roma', u'http://roma.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Edizione Torino', u'http://torino.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Edizione Milano', u'feed://milano.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Edizione Napoli', u'feed://napoli.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Edizione Palermo', u'feed://palermo.repubblica.it/rss/rss2.0.xml')
|
||||
]
|
||||
|
||||
|
||||
34
resources/recipes/oldnewthing.recipe
Normal file
34
resources/recipes/oldnewthing.recipe
Normal file
@ -0,0 +1,34 @@
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
blogs.msdn.com/oldnewthing
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class OldNewThing(BasicNewsRecipe):
|
||||
title = 'The Old New Thing'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'Famous blog by Windows guru Raymond Chen'
|
||||
oldest_article = 15
|
||||
max_articles_per_feed = 100
|
||||
language = 'en'
|
||||
encoding = 'utf-8'
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
publication_type = 'blog'
|
||||
extra_css = ' body{font-family: Verdana,Arial,Helvetica,sans-serif} .code{font-family: "Lucida Console",monospace} '
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : 'blog, windows, microsoft, programming'
|
||||
, 'publisher': 'Raymond Chen'
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
remove_attributes = ['width','height']
|
||||
keep_only_tags = [dict(attrs={'class':['postsub','comment']})]
|
||||
|
||||
feeds = [(u'Posts', u'http://blogs.msdn.com/oldnewthing/rss.xml')]
|
||||
|
||||
36
resources/recipes/onionavclub.recipe
Normal file
36
resources/recipes/onionavclub.recipe
Normal file
@ -0,0 +1,36 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
'''
|
||||
bbc.co.uk
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class BBC(BasicNewsRecipe):
|
||||
title = u'The Onion AV Club'
|
||||
__author__ = 'Stephen Williams'
|
||||
description = 'Film, Television and Music Reviews'
|
||||
no_stylesheets = True
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'content'})
|
||||
]
|
||||
|
||||
remove_tags = [dict(name='div', attrs={'class':['footer','tools_horizontal']}),
|
||||
dict(name='div', attrs={'id':['tool_holder','elsewhere_on_avclub']})
|
||||
]
|
||||
extra_css = '.headline {font-size: x-large;} \n .fact { padding-top: 10pt }'
|
||||
|
||||
feeds = [
|
||||
('Interviews', 'http://www.avclub.com/feed/interview/'),
|
||||
('AV Club Daily', 'http://www.avclub.com/feed/daily'),
|
||||
('Film', 'http://www.avclub.com/feed/film/'),
|
||||
('Music', 'http://www.avclub.com/feed/music/'),
|
||||
('DVD', 'http://www.avclub.com/feed/dvd/'),
|
||||
('Books', 'http://www.avclub.com/feed/books/'),
|
||||
('Games', 'http://www.avclub.com/feed/games/'),
|
||||
('Interviews', 'http://www.avclub.com/feed/interview/'),
|
||||
]
|
||||
@ -9,8 +9,9 @@ __description__ = 'PCMag (www.pcmag.com) delivers authoritative, labs-based comp
|
||||
'''
|
||||
http://www.pcmag.com/
|
||||
'''
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from calibre.ebooks.BeautifulSoup import Comment
|
||||
|
||||
class pcMag(BasicNewsRecipe):
|
||||
__author__ = 'Lorenzo Vigentini'
|
||||
@ -33,9 +34,6 @@ class pcMag(BasicNewsRecipe):
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'id':'articleContent'})
|
||||
]
|
||||
|
||||
feeds = [
|
||||
(u'Tech Commentary from the Editors of PC Magazine', u'http://rssnewsapps.ziffdavis.com/PCMAG_commentary.xml'),
|
||||
@ -49,8 +47,13 @@ class pcMag(BasicNewsRecipe):
|
||||
(u'Technology News from Ziff Davis', u'http://rssnewsapps.ziffdavis.com/pcmagbreakingnews.xml')
|
||||
]
|
||||
|
||||
keep_only_tags = [dict(attrs={'class':'content-page'})]
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'id':['microAd','intellitxt','articleDeckTalkback','inlineDigg','underArticleLinks','w_talkback']}),
|
||||
dict(name='span', attrs={'id':['highlights_content','yahooBuzzBadge-48558872521263350499378']})
|
||||
]
|
||||
dict(attrs={'class':['control-side','comment','highlights_content','btn-holder','subscribe-panel',
|
||||
'grey-box comments-box']}),
|
||||
dict(id=['inlineDigg']),
|
||||
dict(text=lambda text:isinstance(text, Comment)),
|
||||
dict(name='img', width='1'),
|
||||
]
|
||||
preprocess_regexps = [(re.compile(r"<img '[^']+?'"), lambda m : '<img ')]
|
||||
|
||||
|
||||
@ -7,14 +7,31 @@ class Reuters(BasicNewsRecipe):
|
||||
|
||||
title = 'Reuters'
|
||||
description = 'Global news'
|
||||
__author__ = 'Kovid Goyal'
|
||||
__author__ = 'Kovid Goyal and Sujata Raman'
|
||||
use_embedded_content = False
|
||||
language = 'en'
|
||||
|
||||
max_articles_per_feed = 10
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
|
||||
|
||||
preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
|
||||
extra_css = '''
|
||||
body{font-family:arial,helvetica,sans;}
|
||||
h1{ font-size:larger ; font-weight:bold; }
|
||||
.byline{color:#006E97;font-size:x-small; font-weight:bold;}
|
||||
.location{font-size:x-small; font-weight:bold;}
|
||||
.timestamp{font-size:x-small; }
|
||||
'''
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'column2 gridPanel grid8'})]
|
||||
|
||||
|
||||
remove_tags = [dict(name='div', attrs={'id':['recommendedArticles','relatedNews','relatedVideo','relatedFactboxes']}),
|
||||
dict(name='p', attrs={'class':['relatedTopics']}),
|
||||
dict(name='a', attrs={'id':['fullSizeLink']}),
|
||||
dict(name='div', attrs={'class':['photoNav','relatedTopicButtons','articleComments','gridPanel grid8','footerHalf gridPanel grid1','gridPanel grid2','gridPanel grid3']}),]
|
||||
|
||||
preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
|
||||
[
|
||||
##(r'<HEAD>.*?</HEAD>' , lambda match : '<HEAD></HEAD>'),
|
||||
(r'<div id="apple-rss-sidebar-background">.*?<!-- start Entries -->', lambda match : ''),
|
||||
@ -24,10 +41,10 @@ class Reuters(BasicNewsRecipe):
|
||||
(r'<h3>Share:</h3>.*?</body>', lambda match : '<!-- END:: Shared Module id=36615 --></body>'),
|
||||
(r'<div id="atools" class="articleTools">.*?<div class="linebreak">', lambda match : '<div class="linebreak">'),
|
||||
]
|
||||
]
|
||||
|
||||
]
|
||||
|
||||
|
||||
|
||||
|
||||
feeds = [ ('Top Stories', 'http://feeds.reuters.com/reuters/topNews?format=xml'),
|
||||
('US News', 'http://feeds.reuters.com/reuters/domesticNews?format=xml'),
|
||||
('World News', 'http://feeds.reuters.com/reuters/worldNews?format=xml'),
|
||||
@ -37,6 +54,4 @@ class Reuters(BasicNewsRecipe):
|
||||
('Technology News', 'http://feeds.reuters.com/reuters/technologyNews?format=xml'),
|
||||
('Oddly Enough News', 'http://feeds.reuters.com/reuters/oddlyEnoughNews?format=xml')
|
||||
]
|
||||
|
||||
def print_version(self, url):
|
||||
return ('http://www.reuters.com/article/id' + url + '?sp=true')
|
||||
|
||||
|
||||
@ -5,9 +5,8 @@ __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
www.sueddeutsche.de/sz/
|
||||
'''
|
||||
|
||||
import urllib
|
||||
from calibre import strftime
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from calibre import strftime
|
||||
|
||||
class SueddeutcheZeitung(BasicNewsRecipe):
|
||||
title = 'Sueddeutche Zeitung'
|
||||
@ -20,12 +19,13 @@ class SueddeutcheZeitung(BasicNewsRecipe):
|
||||
encoding = 'cp1252'
|
||||
needs_subscription = True
|
||||
remove_empty_feeds = True
|
||||
delay = 2
|
||||
PREFIX = 'http://www.sueddeutsche.de'
|
||||
INDEX = PREFIX + strftime('/sz/%Y-%m-%d/')
|
||||
LOGIN = PREFIX + '/app/lbox/index.html'
|
||||
INDEX = PREFIX + '/app/epaper/textversion/'
|
||||
use_embedded_content = False
|
||||
masthead_url = 'http://pix.sueddeutsche.de/img/g_.gif'
|
||||
masthead_url = 'http://pix.sueddeutsche.de/img/layout/header/logo.gif'
|
||||
language = 'de'
|
||||
publication_type = 'newspaper'
|
||||
extra_css = ' body{font-family: Arial,Helvetica,sans-serif} '
|
||||
|
||||
conversion_options = {
|
||||
@ -40,49 +40,49 @@ class SueddeutcheZeitung(BasicNewsRecipe):
|
||||
|
||||
def get_browser(self):
|
||||
br = BasicNewsRecipe.get_browser()
|
||||
br.open(self.INDEX)
|
||||
if self.username is not None and self.password is not None:
|
||||
data = urllib.urlencode({ 'login_name':self.username
|
||||
,'login_passwort':self.password
|
||||
,'lboxaction':'doLogin'
|
||||
,'passtxt':'Passwort'
|
||||
,'referer':self.INDEX
|
||||
,'x':'22'
|
||||
,'y':'7'
|
||||
})
|
||||
br.open(self.LOGIN,data)
|
||||
br.open(self.INDEX)
|
||||
br.select_form(name='lbox')
|
||||
br['login_name' ] = self.username
|
||||
br['login_passwort'] = self.password
|
||||
br.submit()
|
||||
return br
|
||||
|
||||
remove_tags =[
|
||||
dict(attrs={'class':'hidePrint'})
|
||||
,dict(name=['link','object','embed','base','iframe'])
|
||||
]
|
||||
remove_tags_before = dict(name='h2')
|
||||
remove_tags_after = dict(attrs={'class':'author'})
|
||||
keep_only_tags = [dict(attrs={'class':'artikelBox'})]
|
||||
remove_tags_before = dict(attrs={'class':'artikelTitel'})
|
||||
remove_tags_after = dict(attrs={'class':'author'})
|
||||
|
||||
feeds = [
|
||||
(u'Politik' , INDEX + 'politik/' )
|
||||
,(u'Seite drei' , INDEX + 'seitedrei/' )
|
||||
,(u'Meinungsseite', INDEX + 'meinungsseite/')
|
||||
,(u'Wissen' , INDEX + 'wissen/' )
|
||||
,(u'Panorama' , INDEX + 'panorama/' )
|
||||
,(u'Feuilleton' , INDEX + 'feuilleton/' )
|
||||
,(u'Medien' , INDEX + 'medien/' )
|
||||
,(u'Wirtschaft' , INDEX + 'wirtschaft/' )
|
||||
,(u'Sport' , INDEX + 'sport/' )
|
||||
,(u'Bayern' , INDEX + 'bayern/' )
|
||||
,(u'Muenchen' , INDEX + 'muenchen/' )
|
||||
,(u'jetzt.de' , INDEX + 'jetzt.de/' )
|
||||
(u'Politik' , INDEX + 'Politik/' )
|
||||
,(u'Seite drei' , INDEX + 'Seite+drei/' )
|
||||
,(u'Meinungsseite', INDEX + 'Meinungsseite/')
|
||||
,(u'Wissen' , INDEX + 'Wissen/' )
|
||||
,(u'Panorama' , INDEX + 'Panorama/' )
|
||||
,(u'Feuilleton' , INDEX + 'Feuilleton/' )
|
||||
,(u'Medien' , INDEX + 'Medien/' )
|
||||
,(u'Wirtschaft' , INDEX + 'Wirtschaft/' )
|
||||
,(u'Sport' , INDEX + 'Sport/' )
|
||||
,(u'Bayern' , INDEX + 'Bayern/' )
|
||||
,(u'Muenchen' , INDEX + 'M%FCnchen/' )
|
||||
]
|
||||
|
||||
def parse_index(self):
|
||||
src = self.index_to_soup(self.INDEX)
|
||||
id = ''
|
||||
for itt in src.findAll('a',href=True):
|
||||
if itt['href'].startswith('/app/epaper/textversion/inhalt/'):
|
||||
id = itt['href'].rpartition('/inhalt/')[2]
|
||||
totalfeeds = []
|
||||
lfeeds = self.get_feeds()
|
||||
for feedobj in lfeeds:
|
||||
feedtitle, feedurl = feedobj
|
||||
self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
|
||||
articles = []
|
||||
soup = self.index_to_soup(feedurl)
|
||||
soup = self.index_to_soup(feedurl + id)
|
||||
tbl = soup.find(attrs={'class':'szprintd'})
|
||||
for item in tbl.findAll(name='td',attrs={'class':'topthema'}):
|
||||
atag = item.find(attrs={'class':'Titel'}).a
|
||||
@ -101,7 +101,3 @@ class SueddeutcheZeitung(BasicNewsRecipe):
|
||||
})
|
||||
totalfeeds.append((feedtitle, articles))
|
||||
return totalfeeds
|
||||
|
||||
def print_version(self, url):
|
||||
return url + 'print.html'
|
||||
|
||||
|
||||
52
resources/recipes/ultimahora.recipe
Normal file
52
resources/recipes/ultimahora.recipe
Normal file
@ -0,0 +1,52 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
ultimahora.com
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class UltimaHora_py(BasicNewsRecipe):
|
||||
title = 'Ultima Hora'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'Noticias de Paraguay y el resto del mundo'
|
||||
publisher = 'EDITORIAL EL PAIS S.A.'
|
||||
category = 'news, politics, Paraguay'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 200
|
||||
no_stylesheets = True
|
||||
encoding = 'cp1252'
|
||||
use_embedded_content = False
|
||||
language = 'es_PY'
|
||||
remove_empty_feeds = True
|
||||
publication_type = 'newspaper'
|
||||
masthead_url = 'http://www.ultimahora.com/imgs/uh-com.gif'
|
||||
extra_css = ' body{font-family: Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em} .sub_titulo_mediano,.TituloNota{font-family: Georgia,"Times New Roman",Times,serif} .sub_titulo_mediano{font-weight: bold} '
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : category
|
||||
, 'publisher' : publisher
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
remove_tags = [dict(name=['form','iframe','embed','object','link','base','table'])]
|
||||
keep_only_tags = [dict(attrs={'id':['nota_titulo','nota_copete','texto']})]
|
||||
|
||||
|
||||
feeds = [
|
||||
(u'Arte y Espectaculos' , u'http://www.ultimahora.com/adjuntos/rss/UHEspectaculos.xml' )
|
||||
,(u'Ciudad del Este' , u'http://www.ultimahora.com/adjuntos/rss/UHCDE.xml' )
|
||||
,(u'Deportes' , u'http://www.ultimahora.com/adjuntos/rss/UHDeportes.xml' )
|
||||
,(u'Ultimo momento' , u'http://www.ultimahora.com/adjuntos/rss/UltimoMomento.xml' )
|
||||
,(u'Nacionales' , u'http://www.ultimahora.com/adjuntos/rss/uh-rss-nacionales.xml' )
|
||||
,(u'Politica' , u'http://www.ultimahora.com/adjuntos/rss/uh-rss-politica.xml' )
|
||||
,(u'Sucesos' , u'http://www.ultimahora.com/adjuntos/rss/uh-rss-sucesos.xml' )
|
||||
,(u'Economia' , u'http://www.ultimahora.com/adjuntos/rss/uh-rss-economia.xml' )
|
||||
,(u'Ciencia y Tecnologia', u'http://www.ultimahora.com/adjuntos/rss/uh-rss-ciencia.xml' )
|
||||
]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
return soup
|
||||
@ -153,7 +153,7 @@ class LinuxFreeze(Command):
|
||||
sys.resources_location = os.path.join(DIR_NAME, 'resources')
|
||||
dfv = os.environ.get('CALIBRE_DEVELOP_FROM', None)
|
||||
if dfv and os.path.exists(dfv):
|
||||
sys.path.insert(0, dfv)
|
||||
sys.path.insert(0, os.path.abspath(dfv))
|
||||
|
||||
executables = %(executables)s
|
||||
|
||||
|
||||
@ -2,7 +2,7 @@ __license__ = 'GPL v3'
|
||||
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
__appname__ = 'calibre'
|
||||
__version__ = '0.6.49'
|
||||
__version__ = '0.6.51'
|
||||
__author__ = "Kovid Goyal <kovid@kovidgoyal.net>"
|
||||
|
||||
import re
|
||||
@ -56,9 +56,18 @@ if plugins is None:
|
||||
plugin_path = sys.extensions_location
|
||||
sys.path.insert(0, plugin_path)
|
||||
|
||||
for plugin in ['pictureflow', 'lzx', 'msdes', 'podofo', 'cPalmdoc',
|
||||
'fontconfig', 'pdfreflow', 'progress_indicator', 'chmlib',
|
||||
'chm_extra'] + \
|
||||
for plugin in [
|
||||
'pictureflow',
|
||||
'lzx',
|
||||
'msdes',
|
||||
'podofo',
|
||||
'cPalmdoc',
|
||||
'fontconfig',
|
||||
'pdfreflow',
|
||||
'progress_indicator',
|
||||
'chmlib',
|
||||
'chm_extra'
|
||||
] + \
|
||||
(['winutil'] if iswindows else []) + \
|
||||
(['usbobserver'] if isosx else []):
|
||||
try:
|
||||
|
||||
@ -7,7 +7,7 @@ import os
|
||||
import glob
|
||||
from calibre.customize import FileTypePlugin, MetadataReaderPlugin, MetadataWriterPlugin
|
||||
from calibre.constants import numeric_version
|
||||
from calibre.ebooks.metadata.archive import ArchiveExtract
|
||||
from calibre.ebooks.metadata.archive import ArchiveExtract, get_cbz_metadata
|
||||
|
||||
class HTML2ZIP(FileTypePlugin):
|
||||
name = 'HTML to ZIP'
|
||||
@ -97,6 +97,12 @@ class ComicMetadataReader(MetadataReaderPlugin):
|
||||
from calibre.ebooks.metadata import MetaInformation
|
||||
ret = extract_first(stream)
|
||||
mi = MetaInformation(None, None)
|
||||
stream.seek(0)
|
||||
if ftype == 'cbz':
|
||||
try:
|
||||
mi.smart_update(get_cbz_metadata(stream))
|
||||
except:
|
||||
pass
|
||||
if ret is not None:
|
||||
path, data = ret
|
||||
ext = os.path.splitext(path)[1][1:]
|
||||
@ -448,7 +454,7 @@ from calibre.devices.hanvon.driver import N516, EB511, ALEX
|
||||
from calibre.devices.edge.driver import EDGE
|
||||
from calibre.devices.teclast.driver import TECLAST_K3
|
||||
from calibre.devices.sne.driver import SNE
|
||||
from calibre.devices.misc import PALMPRE
|
||||
from calibre.devices.misc import PALMPRE, KOBO
|
||||
|
||||
from calibre.ebooks.metadata.fetch import GoogleBooks, ISBNDB, Amazon
|
||||
from calibre.library.catalog import CSV_XML, EPUB_MOBI
|
||||
@ -530,7 +536,8 @@ plugins += [
|
||||
EDGE,
|
||||
SNE,
|
||||
ALEX,
|
||||
PALMPRE
|
||||
PALMPRE,
|
||||
KOBO,
|
||||
]
|
||||
plugins += [x for x in list(locals().values()) if isinstance(x, type) and \
|
||||
x.__name__.endswith('MetadataReader')]
|
||||
|
||||
@ -4,6 +4,7 @@ __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
from itertools import izip
|
||||
from xml.sax.saxutils import escape
|
||||
|
||||
from calibre.customize import Plugin as _Plugin
|
||||
|
||||
@ -238,14 +239,14 @@ class OutputProfile(Plugin):
|
||||
|
||||
@classmethod
|
||||
def tags_to_string(cls, tags):
|
||||
return ', '.join(tags)
|
||||
return escape(', '.join(tags))
|
||||
|
||||
class iPadOutput(OutputProfile):
|
||||
|
||||
name = 'iPad'
|
||||
short_name = 'ipad'
|
||||
screen_size = (1024, 768)
|
||||
comic_screen_size = (1024, 768)
|
||||
screen_size = (768, 1024)
|
||||
comic_screen_size = (768, 1024)
|
||||
dpi = 132.0
|
||||
|
||||
class SonyReaderOutput(OutputProfile):
|
||||
@ -383,7 +384,8 @@ class KindleOutput(OutputProfile):
|
||||
|
||||
@classmethod
|
||||
def tags_to_string(cls, tags):
|
||||
return 'ttt '.join(tags)+'ttt '
|
||||
return u'%s <br/><span style="color: white">%s</span>' % (', '.join(tags),
|
||||
'ttt '.join(tags)+'ttt ')
|
||||
|
||||
class KindleDXOutput(OutputProfile):
|
||||
|
||||
@ -399,7 +401,8 @@ class KindleDXOutput(OutputProfile):
|
||||
|
||||
@classmethod
|
||||
def tags_to_string(cls, tags):
|
||||
return 'ttt '.join(tags)+'ttt '
|
||||
return u'%s <br/><span style="color: white">%s</span>' % (', '.join(tags),
|
||||
'ttt '.join(tags)+'ttt ')
|
||||
|
||||
class IlliadOutput(OutputProfile):
|
||||
|
||||
|
||||
@ -18,7 +18,8 @@ class ANDROID(USBMS):
|
||||
FORMATS = ['epub', 'pdf']
|
||||
|
||||
VENDOR_ID = {
|
||||
0x0bb4 : { 0x0c02 : [0x100], 0x0c01 : [0x100]},
|
||||
# HTC
|
||||
0x0bb4 : { 0x0c02 : [0x100], 0x0c01 : [0x100], 0x0ff9 : [0x0100]},
|
||||
|
||||
# Motorola
|
||||
0x22b8 : { 0x41d9 : [0x216], 0x2d67 : [0x100], 0x41db : [0x216]},
|
||||
@ -26,7 +27,7 @@ class ANDROID(USBMS):
|
||||
0x18d1 : { 0x4e11 : [0x0100, 0x226], 0x4e12: [0x0100, 0x226]},
|
||||
|
||||
# Samsung
|
||||
0x04e8 : { 0x681d : [0x0222]},
|
||||
0x04e8 : { 0x681d : [0x0222], 0x681c : [0x0222]},
|
||||
|
||||
# Acer
|
||||
0x502 : { 0x3203 : [0x0100]},
|
||||
|
||||
@ -62,7 +62,7 @@ class KINDLE(USBMS):
|
||||
|
||||
def filename_callback(self, fname, mi):
|
||||
if fname.startswith('.'):
|
||||
return fname[1:]
|
||||
return 'x'+fname[1:]
|
||||
return fname
|
||||
|
||||
def get_annotations(self, path_map):
|
||||
|
||||
@ -28,3 +28,24 @@ class PALMPRE(USBMS):
|
||||
|
||||
EBOOK_DIR_MAIN = 'E-books'
|
||||
|
||||
class KOBO(USBMS):
|
||||
|
||||
name = 'Kobo Reader Device Interface'
|
||||
gui_name = 'Kobo Reader'
|
||||
description = _('Communicate with the Kobo Reader')
|
||||
author = 'Kovid Goyal'
|
||||
|
||||
supported_platforms = ['windows', 'osx', 'linux']
|
||||
|
||||
# Ordered list of supported formats
|
||||
FORMATS = ['epub', 'pdf']
|
||||
|
||||
VENDOR_ID = [0x2237]
|
||||
PRODUCT_ID = [0x4161]
|
||||
BCD = [0x0110]
|
||||
|
||||
VENDOR_NAME = 'KOBO_INC'
|
||||
WINDOWS_MAIN_MEM = '.KOBOEREADER'
|
||||
|
||||
EBOOK_DIR_MAIN = 'e-books'
|
||||
|
||||
|
||||
@ -69,13 +69,15 @@ class PRS505(CLI, Device):
|
||||
|
||||
def write_cache(prefix):
|
||||
try:
|
||||
cachep = os.path.join(prefix, self.CACHE_XML)
|
||||
cachep = os.path.join(prefix, *(self.CACHE_XML.split('/')))
|
||||
if not os.path.exists(cachep):
|
||||
try:
|
||||
os.makedirs(os.path.dirname(cachep), mode=0777)
|
||||
except:
|
||||
time.sleep(5)
|
||||
os.makedirs(os.path.dirname(cachep), mode=0777)
|
||||
dname = os.path.dirname(cachep)
|
||||
if not os.path.exists(dname):
|
||||
try:
|
||||
os.makedirs(dname, mode=0777)
|
||||
except:
|
||||
time.sleep(5)
|
||||
os.makedirs(dname, mode=0777)
|
||||
with open(cachep, 'wb') as f:
|
||||
f.write(u'''<?xml version="1.0" encoding="UTF-8"?>
|
||||
<cache xmlns="http://www.kinoma.com/FskCache/1">
|
||||
@ -202,9 +204,11 @@ class PRS505(CLI, Device):
|
||||
|
||||
def write_card_prefix(prefix, listid):
|
||||
if prefix is not None and hasattr(booklists[listid], 'write'):
|
||||
if not os.path.exists(prefix):
|
||||
os.makedirs(prefix)
|
||||
with open(prefix + self.__class__.CACHE_XML, 'wb') as f:
|
||||
tgt = os.path.join(prefix, *(self.CACHE_XML.split('/')))
|
||||
base = os.path.dirname(tgt)
|
||||
if not os.path.exists(base):
|
||||
os.makedirs(base)
|
||||
with open(tgt, 'wb') as f:
|
||||
booklists[listid].write(f)
|
||||
write_card_prefix(self._card_a_prefix, 1)
|
||||
write_card_prefix(self._card_b_prefix, 2)
|
||||
|
||||
@ -25,6 +25,7 @@
|
||||
#include <stdio.h>
|
||||
|
||||
#include <CoreFoundation/CFNumber.h>
|
||||
#include <CoreServices/CoreServices.h>
|
||||
#include <IOKit/usb/IOUSBLib.h>
|
||||
#include <IOKit/IOCFPlugIn.h>
|
||||
#include <IOKit/IOKitLib.h>
|
||||
@ -52,6 +53,28 @@
|
||||
|
||||
#define NUKE(x) Py_XDECREF(x); x = NULL;
|
||||
|
||||
/* This function only works on 10.5 and later
|
||||
static PyObject* send2trash(PyObject *self, PyObject *args)
|
||||
{
|
||||
UInt8 *utf8_chars;
|
||||
FSRef fp;
|
||||
OSStatus op_result;
|
||||
|
||||
if (!PyArg_ParseTuple(args, "es", "utf-8", &utf8_chars)) {
|
||||
return NULL;
|
||||
}
|
||||
|
||||
FSPathMakeRefWithOptions(utf8_chars, kFSPathMakeRefDoNotFollowLeafSymlink, &fp, NULL);
|
||||
op_result = FSMoveObjectToTrashSync(&fp, NULL, kFSFileOperationDefaultOptions);
|
||||
PyMem_Free(utf8_chars);
|
||||
if (op_result != noErr) {
|
||||
PyErr_SetString(PyExc_OSError, GetMacOSStatusCommentString(op_result));
|
||||
return NULL;
|
||||
}
|
||||
Py_RETURN_NONE;
|
||||
}
|
||||
*/
|
||||
|
||||
static PyObject*
|
||||
usbobserver_get_iokit_string_property(io_service_t dev, CFStringRef prop) {
|
||||
CFTypeRef PropRef;
|
||||
|
||||
@ -676,7 +676,10 @@ OptionRecommendation(name='timestamp',
|
||||
if mi.cover:
|
||||
if mi.cover.startswith('http:') or mi.cover.startswith('https:'):
|
||||
mi.cover = self.download_cover(mi.cover)
|
||||
mi.cover_data = ('', open(mi.cover, 'rb').read())
|
||||
ext = mi.cover.rpartition('.')[-1].lower().strip()
|
||||
if ext not in ('png', 'jpg', 'jpeg'):
|
||||
ext = 'jpg'
|
||||
mi.cover_data = (ext, open(mi.cover, 'rb').read())
|
||||
mi.cover = None
|
||||
self.user_metadata = mi
|
||||
|
||||
|
||||
@ -81,12 +81,40 @@ class EPUBOutput(OutputFormatPlugin):
|
||||
OptionRecommendation(name='no_default_epub_cover', recommended_value=False,
|
||||
help=_('Normally, if the input file has no cover and you don\'t'
|
||||
' specify one, a default cover is generated with the title, '
|
||||
'authors, etc. This option disables the generation of this cover.')),
|
||||
'authors, etc. This option disables the generation of this cover.')
|
||||
),
|
||||
|
||||
OptionRecommendation(name='no_svg_cover', recommended_value=False,
|
||||
help=_('Do not use SVG for the book cover. Use this option if '
|
||||
'your EPUB is going to be used ona device that does not '
|
||||
'support SVG, like the iPhone or the JetBook Lite. '
|
||||
'Without this option, such devices will display the cover '
|
||||
'as a blank page.')
|
||||
),
|
||||
|
||||
])
|
||||
|
||||
recommendations = set([('pretty_print', True, OptionRecommendation.HIGH)])
|
||||
|
||||
NONSVG_TITLEPAGE_COVER = '''\
|
||||
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">
|
||||
<head>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
|
||||
<meta name="calibre:cover" content="true" />
|
||||
<title>Cover</title>
|
||||
<style type="text/css" title="override_css">
|
||||
@page {padding: 0pt; margin:0pt}
|
||||
body { text-align: center; padding:0pt; margin: 0pt; }
|
||||
div { padding:0pt; margin: 0pt; }
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<div>
|
||||
<img src="%s" alt="cover" style="height: 100%%" />
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
'''
|
||||
|
||||
TITLEPAGE_COVER = '''\
|
||||
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">
|
||||
@ -301,7 +329,9 @@ class EPUBOutput(OutputFormatPlugin):
|
||||
else:
|
||||
href = self.default_cover()
|
||||
if href is not None:
|
||||
tp = self.TITLEPAGE_COVER%unquote(href)
|
||||
templ = self.NONSVG_TITLEPAGE_COVER if self.opts.no_svg_cover \
|
||||
else self.TITLEPAGE_COVER
|
||||
tp = templ%unquote(href)
|
||||
id, href = m.generate('titlepage', 'titlepage.xhtml')
|
||||
item = m.add(id, href, guess_type('t.xhtml')[0],
|
||||
data=etree.fromstring(tp))
|
||||
@ -334,6 +364,12 @@ class EPUBOutput(OutputFormatPlugin):
|
||||
'''
|
||||
from calibre.ebooks.oeb.base import XPath, XHTML, OEB_STYLES, barename, urlunquote
|
||||
|
||||
stylesheet = None
|
||||
for item in self.oeb.manifest:
|
||||
if item.media_type.lower() in OEB_STYLES:
|
||||
stylesheet = item
|
||||
break
|
||||
|
||||
# ADE cries big wet tears when it encounters an invalid fragment
|
||||
# identifier in the NCX toc.
|
||||
frag_pat = re.compile(r'[-A-Za-z0-9_:.]+$')
|
||||
@ -430,11 +466,17 @@ class EPUBOutput(OutputFormatPlugin):
|
||||
elem.tail = special_chars.sub('', elem.tail)
|
||||
elem.tail = elem.tail.replace(u'\u2011', '-')
|
||||
|
||||
stylesheet = None
|
||||
for item in self.oeb.manifest:
|
||||
if item.media_type.lower() in OEB_STYLES:
|
||||
stylesheet = item
|
||||
break
|
||||
if stylesheet is not None:
|
||||
# ADE doesn't render lists correctly if they have left margins
|
||||
from cssutils.css import CSSRule
|
||||
for lb in XPath('//h:ul[@class]|//h:ol[@class]')(root):
|
||||
sel = '.'+lb.get('class')
|
||||
for rule in stylesheet.data.cssRules.rulesOfType(CSSRule.STYLE_RULE):
|
||||
if sel == rule.selectorList.selectorText:
|
||||
val = rule.style.removeProperty('margin-left')
|
||||
pval = rule.style.getProperty('padding-left')
|
||||
if val and not pval:
|
||||
rule.style.setProperty('padding-left', val)
|
||||
|
||||
if stylesheet is not None:
|
||||
stylesheet.data.add('a { color: inherit; text-decoration: inherit; '
|
||||
|
||||
@ -11,7 +11,7 @@ __docformat__ = 'restructuredtext en'
|
||||
Input plugin for HTML or OPF ebooks.
|
||||
'''
|
||||
|
||||
import os, re, sys, uuid
|
||||
import os, re, sys, uuid, tempfile
|
||||
from urlparse import urlparse, urlunparse
|
||||
from urllib import unquote
|
||||
from functools import partial
|
||||
@ -272,6 +272,7 @@ class HTMLInput(InputFormatPlugin):
|
||||
|
||||
def convert(self, stream, opts, file_ext, log,
|
||||
accelerators):
|
||||
self._is_case_sensitive = None
|
||||
basedir = os.getcwd()
|
||||
self.opts = opts
|
||||
|
||||
@ -290,6 +291,15 @@ class HTMLInput(InputFormatPlugin):
|
||||
return create_oebbook(log, stream.name, opts, self,
|
||||
encoding=opts.input_encoding)
|
||||
|
||||
def is_case_sensitive(self, path):
|
||||
if self._is_case_sensitive is not None:
|
||||
return self._is_case_sensitive
|
||||
if not path or not os.path.exists(path):
|
||||
return islinux or isfreebsd
|
||||
self._is_case_sensitive = os.path.exists(path.lower()) \
|
||||
and os.path.exists(path.upper())
|
||||
return self._is_case_sensitive
|
||||
|
||||
def create_oebbook(self, htmlpath, basedir, opts, log, mi):
|
||||
from calibre.ebooks.conversion.plumber import create_oebbook
|
||||
from calibre.ebooks.oeb.base import DirContainer, \
|
||||
@ -320,7 +330,6 @@ class HTMLInput(InputFormatPlugin):
|
||||
if not metadata.title:
|
||||
oeb.logger.warn('Title not specified')
|
||||
metadata.add('title', self.oeb.translate(__('Unknown')))
|
||||
|
||||
bookid = str(uuid.uuid4())
|
||||
metadata.add('identifier', bookid, id='uuid_id', scheme='uuid')
|
||||
for ident in metadata.identifier:
|
||||
@ -328,7 +337,6 @@ class HTMLInput(InputFormatPlugin):
|
||||
self.oeb.uid = metadata.identifier[0]
|
||||
break
|
||||
|
||||
|
||||
filelist = get_filelist(htmlpath, basedir, opts, log)
|
||||
filelist = [f for f in filelist if not f.is_binary]
|
||||
htmlfile_map = {}
|
||||
@ -345,14 +353,16 @@ class HTMLInput(InputFormatPlugin):
|
||||
|
||||
self.added_resources = {}
|
||||
self.log = log
|
||||
self.log('Normalizing filename cases')
|
||||
for path, href in htmlfile_map.items():
|
||||
if not (islinux or isfreebsd):
|
||||
if not self.is_case_sensitive(path):
|
||||
path = path.lower()
|
||||
self.added_resources[path] = href
|
||||
self.urlnormalize, self.DirContainer = urlnormalize, DirContainer
|
||||
self.urldefrag = urldefrag
|
||||
self.guess_type, self.BINARY_MIME = guess_type, BINARY_MIME
|
||||
|
||||
self.log('Rewriting HTML links')
|
||||
for f in filelist:
|
||||
path = f.path
|
||||
dpath = os.path.dirname(path)
|
||||
@ -417,7 +427,7 @@ class HTMLInput(InputFormatPlugin):
|
||||
if os.path.isdir(link):
|
||||
self.log.warn(link_, 'is a link to a directory. Ignoring.')
|
||||
return link_
|
||||
if not (islinux or isfreebsd):
|
||||
if not self.is_case_sensitive(tempfile.gettempdir()):
|
||||
link = link.lower()
|
||||
if link not in self.added_resources:
|
||||
bhref = os.path.basename(link)
|
||||
|
||||
@ -64,3 +64,45 @@ class ArchiveExtract(FileTypePlugin):
|
||||
of.write(zf.read(fname))
|
||||
return of.name
|
||||
|
||||
def get_comic_book_info(d, mi):
|
||||
series = d.get('series', '')
|
||||
if series.strip():
|
||||
mi.series = series
|
||||
if d.get('volume', -1) > -1:
|
||||
mi.series_index = float(d['volume'])
|
||||
if d.get('rating', -1) > -1:
|
||||
mi.rating = d['rating']
|
||||
for x in ('title', 'publisher'):
|
||||
y = d.get(x, '').strip()
|
||||
if y:
|
||||
setattr(mi, x, y)
|
||||
tags = d.get('tags', [])
|
||||
if tags:
|
||||
mi.tags = tags
|
||||
authors = []
|
||||
for credit in d.get('credits', []):
|
||||
if credit.get('role', '') in ('Writer', 'Artist', 'Cartoonist',
|
||||
'Creator'):
|
||||
x = credit.get('person', '')
|
||||
if x:
|
||||
x = ' '.join((reversed(x.split(', '))))
|
||||
authors.append(x)
|
||||
if authors:
|
||||
mi.authors = authors
|
||||
|
||||
|
||||
|
||||
def get_cbz_metadata(stream):
|
||||
from calibre.utils.zipfile import ZipFile
|
||||
from calibre.ebooks.metadata import MetaInformation
|
||||
import json
|
||||
|
||||
zf = ZipFile(stream)
|
||||
mi = MetaInformation(None, None)
|
||||
if zf.comment:
|
||||
m = json.loads(zf.comment)
|
||||
if hasattr(m, 'keys'):
|
||||
for cat in m.keys():
|
||||
if cat.startswith('ComicBookInfo'):
|
||||
get_comic_book_info(m[cat], mi)
|
||||
return mi
|
||||
|
||||
@ -61,7 +61,8 @@ class EXTHHeader(object):
|
||||
# last update time
|
||||
pass
|
||||
elif id == 503: # Long title
|
||||
if not title or title == _('Unknown'):
|
||||
if not title or title == _('Unknown') or \
|
||||
'USER_CONTENT' in title or title.startswith('dtp_'):
|
||||
try:
|
||||
title = content.decode(codec)
|
||||
except:
|
||||
@ -253,6 +254,8 @@ class MobiReader(object):
|
||||
stream = open(filename_or_stream, 'rb')
|
||||
|
||||
raw = stream.read()
|
||||
if raw.startswith('TPZ'):
|
||||
raise ValueError(_('This is an Amazon Topaz book. It cannot be processed.'))
|
||||
|
||||
self.header = raw[0:72]
|
||||
self.name = self.header[:32].replace('\x00', '')
|
||||
@ -260,7 +263,7 @@ class MobiReader(object):
|
||||
|
||||
self.ident = self.header[0x3C:0x3C + 8].upper()
|
||||
if self.ident not in ['BOOKMOBI', 'TEXTREAD']:
|
||||
raise MobiError('Unknown book type: %s' % self.ident)
|
||||
raise MobiError('Unknown book type: %s' % repr(self.ident))
|
||||
|
||||
self.sections = []
|
||||
self.section_headers = []
|
||||
@ -497,8 +500,8 @@ class MobiReader(object):
|
||||
if ':' in x:
|
||||
del tag.attrib[x]
|
||||
if tag.tag in ('country-region', 'place', 'placetype', 'placename',
|
||||
'state', 'city', 'street', 'address', 'content'):
|
||||
tag.tag = 'div' if tag.tag == 'content' else 'span'
|
||||
'state', 'city', 'street', 'address', 'content', 'form'):
|
||||
tag.tag = 'div' if tag.tag in ('content', 'form') else 'span'
|
||||
for key in tag.attrib.keys():
|
||||
tag.attrib.pop(key)
|
||||
continue
|
||||
|
||||
@ -294,6 +294,9 @@ def xml2str(root, pretty_print=False, strip_comments=False):
|
||||
def xml2unicode(root, pretty_print=False):
|
||||
return etree.tostring(root, pretty_print=pretty_print)
|
||||
|
||||
def xml2text(elem):
|
||||
return etree.tostring(elem, method='text', encoding=unicode, with_tail=False)
|
||||
|
||||
ASCII_CHARS = set(chr(x) for x in xrange(128))
|
||||
UNIBYTE_CHARS = set(chr(x) for x in xrange(256))
|
||||
URL_SAFE = set('ABCDEFGHIJKLMNOPQRSTUVWXYZ'
|
||||
@ -1187,7 +1190,8 @@ class Manifest(object):
|
||||
if item in self.ids:
|
||||
item = self.ids[item]
|
||||
del self.ids[item.id]
|
||||
del self.hrefs[item.href]
|
||||
if item.href in self.hrefs:
|
||||
del self.hrefs[item.href]
|
||||
self.items.remove(item)
|
||||
if item in self.oeb.spine:
|
||||
self.oeb.spine.remove(item)
|
||||
|
||||
@ -184,6 +184,8 @@ class EbookIterator(object):
|
||||
|
||||
if processed or plumber.input_fmt.lower() in ('pdb', 'pdf', 'rb') and \
|
||||
not hasattr(self.pathtoopf, 'manifest'):
|
||||
if hasattr(self.pathtoopf, 'manifest'):
|
||||
self.pathtoopf = write_oebbook(self.pathtoopf, self.base)
|
||||
self.pathtoopf = create_oebbook(self.log, self.pathtoopf, plumber.opts,
|
||||
plumber.input_plugin)
|
||||
if hasattr(self.pathtoopf, 'manifest'):
|
||||
|
||||
@ -96,6 +96,8 @@ class CSSSelector(etree.XPath):
|
||||
path = css_to_xpath(css)
|
||||
except UnicodeEncodeError: # Bug in css_to_xpath
|
||||
path = '/'
|
||||
except NotImplementedError: # Probably a subselect like :hover
|
||||
path = '/'
|
||||
path = self.LOCAL_NAME_RE.sub(r"local-name() = '", path)
|
||||
etree.XPath.__init__(self, path, namespaces=namespaces)
|
||||
self.css = css
|
||||
@ -526,7 +528,7 @@ class Style(object):
|
||||
base = parent.width
|
||||
else:
|
||||
base = self._profile.width
|
||||
if 'width' is self._element.attrib:
|
||||
if 'width' in self._element.attrib:
|
||||
width = self._element.attrib['width']
|
||||
elif 'width' in self._style:
|
||||
width = self._style['width']
|
||||
@ -534,6 +536,8 @@ class Style(object):
|
||||
result = base
|
||||
else:
|
||||
result = self._unit_convert(width, base=base)
|
||||
if isinstance(result, (unicode, str, bytes)):
|
||||
result = self._profile.width
|
||||
self._width = result
|
||||
return self._width
|
||||
|
||||
@ -547,7 +551,7 @@ class Style(object):
|
||||
base = parent.height
|
||||
else:
|
||||
base = self._profile.height
|
||||
if 'height' is self._element.attrib:
|
||||
if 'height' in self._element.attrib:
|
||||
height = self._element.attrib['height']
|
||||
elif 'height' in self._style:
|
||||
height = self._style['height']
|
||||
@ -555,6 +559,8 @@ class Style(object):
|
||||
result = base
|
||||
else:
|
||||
result = self._unit_convert(height, base=base)
|
||||
if isinstance(result, (unicode, str, bytes)):
|
||||
result = self._profile.height
|
||||
self._height = result
|
||||
return self._height
|
||||
|
||||
|
||||
@ -14,7 +14,7 @@ from lxml import etree
|
||||
|
||||
from calibre.ebooks.oeb.base import XPath, XPNSMAP
|
||||
from calibre import guess_type
|
||||
|
||||
from calibre.library.comments import comments_to_html
|
||||
class Jacket(object):
|
||||
'''
|
||||
Book jacket manipulation. Remove first image and insert comments at start of
|
||||
@ -25,6 +25,7 @@ class Jacket(object):
|
||||
<html xmlns="%(xmlns)s">
|
||||
<head>
|
||||
<title>%(title)s</title>
|
||||
<meta name="calibre-content" content="jacket"/>
|
||||
</head>
|
||||
<body>
|
||||
<div class="calibre_rescale_100">
|
||||
@ -83,7 +84,9 @@ class Jacket(object):
|
||||
comments = ''
|
||||
if not comments.strip():
|
||||
comments = ''
|
||||
comments = comments.replace('\r\n', '\n').replace('\n\n', '<br/><br/>')
|
||||
orig_comments = comments
|
||||
if comments:
|
||||
comments = comments_to_html(comments)
|
||||
series = '<b>Series: </b>' + escape(mi.series if mi.series else '')
|
||||
if mi.series and mi.series_index is not None:
|
||||
series += escape(' [%s]'%mi.format_series_index())
|
||||
@ -96,21 +99,41 @@ class Jacket(object):
|
||||
except:
|
||||
tags = []
|
||||
if tags:
|
||||
tags = '<b>Tags: </b>' + escape(self.opts.dest.tags_to_string(tags))
|
||||
tags = '<b>Tags: </b>' + self.opts.dest.tags_to_string(tags)
|
||||
else:
|
||||
tags = ''
|
||||
try:
|
||||
title = mi.title if mi.title else unicode(self.oeb.metadata.title[0])
|
||||
except:
|
||||
title = _('Unknown')
|
||||
html = self.JACKET_TEMPLATE%dict(xmlns=XPNSMAP['h'],
|
||||
title=escape(title), comments=escape(comments),
|
||||
|
||||
def generate_html(comments):
|
||||
return self.JACKET_TEMPLATE%dict(xmlns=XPNSMAP['h'],
|
||||
title=escape(title), comments=comments,
|
||||
jacket=escape(_('Book Jacket')), series=series,
|
||||
tags=tags, rating=self.get_rating(mi.rating))
|
||||
id, href = self.oeb.manifest.generate('jacket', 'jacket.xhtml')
|
||||
root = etree.fromstring(html)
|
||||
item = self.oeb.manifest.add(id, href, guess_type(href)[0], data=root)
|
||||
self.oeb.spine.insert(0, item, True)
|
||||
from calibre.ebooks.oeb.base import RECOVER_PARSER, XPath
|
||||
try:
|
||||
root = etree.fromstring(generate_html(comments), parser=RECOVER_PARSER)
|
||||
except:
|
||||
root = etree.fromstring(generate_html(escape(orig_comments)),
|
||||
parser=RECOVER_PARSER)
|
||||
jacket = XPath('//h:meta[@name="calibre-content" and @content="jacket"]')
|
||||
found = None
|
||||
for item in list(self.oeb.spine)[:4]:
|
||||
try:
|
||||
if jacket(item.data):
|
||||
found = item
|
||||
break
|
||||
except:
|
||||
continue
|
||||
if found is None:
|
||||
item = self.oeb.manifest.add(id, href, guess_type(href)[0], data=root)
|
||||
self.oeb.spine.insert(0, item, True)
|
||||
else:
|
||||
self.log('Found existing book jacket, replacing...')
|
||||
found.data = root
|
||||
|
||||
|
||||
def __call__(self, oeb, opts, metadata):
|
||||
|
||||
@ -8,6 +8,7 @@ __docformat__ = 'restructuredtext en'
|
||||
|
||||
import os
|
||||
from calibre.utils.date import isoformat, now
|
||||
from calibre import guess_type
|
||||
|
||||
def meta_info_to_oeb_metadata(mi, m, log):
|
||||
from calibre.ebooks.oeb.base import OPF
|
||||
@ -92,15 +93,16 @@ class MergeMetadata(object):
|
||||
scheme='uuid')
|
||||
self.oeb.uid = self.oeb.metadata.identifier[-1]
|
||||
|
||||
|
||||
|
||||
|
||||
def set_cover(self, mi, prefer_metadata_cover):
|
||||
cdata = ''
|
||||
cdata, ext = '', 'jpg'
|
||||
if mi.cover and os.access(mi.cover, os.R_OK):
|
||||
cdata = open(mi.cover, 'rb').read()
|
||||
ext = mi.cover.rpartition('.')[-1].lower().strip()
|
||||
elif mi.cover_data and mi.cover_data[-1]:
|
||||
cdata = mi.cover_data[1]
|
||||
ext = mi.cover_data[0]
|
||||
if ext not in ('png', 'jpg', 'jpeg'):
|
||||
ext = 'jpg'
|
||||
id = old_cover = None
|
||||
if 'cover' in self.oeb.guide:
|
||||
old_cover = self.oeb.guide['cover']
|
||||
@ -120,8 +122,8 @@ class MergeMetadata(object):
|
||||
self.oeb.manifest.add(id, old_cover.href, 'image/jpeg')
|
||||
return id
|
||||
if cdata:
|
||||
id, href = self.oeb.manifest.generate('cover', 'cover.jpg')
|
||||
self.oeb.manifest.add(id, href, 'image/jpeg', data=cdata)
|
||||
id, href = self.oeb.manifest.generate('cover', 'cover.'+ext)
|
||||
self.oeb.manifest.add(id, href, guess_type('cover.'+ext)[0], data=cdata)
|
||||
self.oeb.guide.add('cover', 'Cover', href)
|
||||
return id
|
||||
|
||||
|
||||
@ -5,7 +5,7 @@ __docformat__ = 'restructuredtext en'
|
||||
|
||||
'''
|
||||
Splitting of the XHTML flows. Splitting can happen on page boundaries or can be
|
||||
forces at "likely" locations to conform to size limitations. This transform
|
||||
forced at "likely" locations to conform to size limitations. This transform
|
||||
assumes a prior call to the flatcss transform.
|
||||
'''
|
||||
|
||||
@ -385,12 +385,18 @@ class FlowSplitter(object):
|
||||
raise SplitError(self.item.href, root)
|
||||
self.log.debug('\t\t\tSplit point:', split_point.tag, tree.getpath(split_point))
|
||||
|
||||
for t in self.do_split(tree, split_point, before):
|
||||
trees = self.do_split(tree, split_point, before)
|
||||
sizes = [len(tostring(t.getroot())) for t in trees]
|
||||
if min(sizes) < 5*1024:
|
||||
self.log.debug('\t\t\tSplit tree too small')
|
||||
self.split_to_size(tree)
|
||||
return
|
||||
|
||||
for t, size in zip(trees, sizes):
|
||||
r = t.getroot()
|
||||
if self.is_page_empty(r):
|
||||
continue
|
||||
size = len(tostring(r))
|
||||
if size <= self.max_flow_size:
|
||||
elif size <= self.max_flow_size:
|
||||
self.split_trees.append(t)
|
||||
self.log.debug(
|
||||
'\t\t\tCommitted sub-tree #%d (%d KB)'%(
|
||||
|
||||
@ -11,7 +11,7 @@ import re
|
||||
from lxml import etree
|
||||
from urlparse import urlparse
|
||||
|
||||
from calibre.ebooks.oeb.base import XPNSMAP, TOC, XHTML
|
||||
from calibre.ebooks.oeb.base import XPNSMAP, TOC, XHTML, xml2text
|
||||
from calibre.ebooks import ConversionError
|
||||
|
||||
def XPath(x):
|
||||
@ -79,8 +79,7 @@ class DetectStructure(object):
|
||||
page_break_before = 'display: block; page-break-before: always'
|
||||
page_break_after = 'display: block; page-break-after: always'
|
||||
for item, elem in self.detected_chapters:
|
||||
text = u' '.join([t.strip() for t in elem.xpath('descendant::text()')])
|
||||
text = text.strip()
|
||||
text = xml2text(elem).strip()
|
||||
self.log('\tDetected chapter:', text[:50])
|
||||
if chapter_mark == 'none':
|
||||
continue
|
||||
@ -120,8 +119,7 @@ class DetectStructure(object):
|
||||
if frag:
|
||||
href = '#'.join((href, frag))
|
||||
if not self.oeb.toc.has_href(href):
|
||||
text = u' '.join([t.strip() for t in \
|
||||
a.xpath('descendant::text()')])
|
||||
text = xml2text(a)
|
||||
text = text[:100].strip()
|
||||
if not self.oeb.toc.has_text(text):
|
||||
num += 1
|
||||
@ -135,7 +133,7 @@ class DetectStructure(object):
|
||||
|
||||
|
||||
def elem_to_link(self, item, elem, counter):
|
||||
text = u' '.join([t.strip() for t in elem.xpath('descendant::text()')])
|
||||
text = xml2text(elem)
|
||||
text = text[:100].strip()
|
||||
id = elem.get('id', 'calibre_toc_%d'%counter)
|
||||
elem.set('id', id)
|
||||
|
||||
@ -461,7 +461,7 @@ class FileDialog(QObject):
|
||||
|
||||
def get_files(self):
|
||||
if self.selected_files is None:
|
||||
return tuple(os.path.abspath(qstring_to_unicode(i)) for i in self.fd.selectedFiles())
|
||||
return tuple(os.path.abspath(unicode(i)) for i in self.fd.selectedFiles())
|
||||
return tuple(self.selected_files)
|
||||
|
||||
|
||||
|
||||
@ -17,7 +17,8 @@ class PluginWidget(Widget, Ui_Form):
|
||||
|
||||
def __init__(self, parent, get_option, get_help, db=None, book_id=None):
|
||||
Widget.__init__(self, parent, 'epub_output',
|
||||
['dont_split_on_page_breaks', 'flow_size', 'no_default_epub_cover']
|
||||
['dont_split_on_page_breaks', 'flow_size',
|
||||
'no_default_epub_cover', 'no_svg_cover']
|
||||
)
|
||||
self.db, self.book_id = db, book_id
|
||||
self.initialize_options(get_option, get_help, db, book_id)
|
||||
|
||||
@ -21,7 +21,7 @@
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="2" column="0">
|
||||
<item row="3" column="0">
|
||||
<widget class="QLabel" name="label">
|
||||
<property name="text">
|
||||
<string>Split files &larger than:</string>
|
||||
@ -31,7 +31,7 @@
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="2" column="1">
|
||||
<item row="3" column="1">
|
||||
<widget class="QSpinBox" name="opt_flow_size">
|
||||
<property name="suffix">
|
||||
<string> KB</string>
|
||||
@ -47,7 +47,7 @@
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="3" column="0">
|
||||
<item row="4" column="0">
|
||||
<spacer name="verticalSpacer">
|
||||
<property name="orientation">
|
||||
<enum>Qt::Vertical</enum>
|
||||
@ -67,6 +67,13 @@
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="2" column="0">
|
||||
<widget class="QCheckBox" name="opt_no_svg_cover">
|
||||
<property name="text">
|
||||
<string>No &SVG cover</string>
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
</layout>
|
||||
</widget>
|
||||
<resources/>
|
||||
|
||||
@ -71,7 +71,7 @@ class MetadataWidget(Widget, Ui_Form):
|
||||
self.author_sort.setText(mi.author_sort if mi.author_sort else '')
|
||||
self.tags.setText(', '.join(mi.tags if mi.tags else []))
|
||||
self.tags.update_tags_cache(self.db.all_tags())
|
||||
self.comment.setText(mi.comments if mi.comments else '')
|
||||
self.comment.setPlainText(mi.comments if mi.comments else '')
|
||||
if mi.series:
|
||||
self.series.setCurrentIndex(self.series.findText(mi.series))
|
||||
if mi.series_index is not None:
|
||||
|
||||
@ -7,41 +7,15 @@ __docformat__ = 'restructuredtext en'
|
||||
import re
|
||||
|
||||
from PyQt4.QtCore import SIGNAL, Qt
|
||||
from PyQt4.QtGui import QDialog, QWidget, QDialogButtonBox, QFileDialog, \
|
||||
QBrush, QSyntaxHighlighter, QTextCharFormat
|
||||
from PyQt4.QtGui import QDialog, QWidget, QDialogButtonBox, \
|
||||
QBrush, QTextCursor, QTextEdit
|
||||
|
||||
from calibre.gui2.convert.regex_builder_ui import Ui_RegexBuilder
|
||||
from calibre.gui2.convert.xexp_edit_ui import Ui_Form as Ui_Edit
|
||||
from calibre.gui2 import qstring_to_unicode
|
||||
from calibre.gui2 import error_dialog
|
||||
from calibre.gui2 import error_dialog, choose_files
|
||||
from calibre.ebooks.oeb.iterator import EbookIterator
|
||||
from calibre.gui2.dialogs.choose_format import ChooseFormatDialog
|
||||
|
||||
class RegexHighlighter(QSyntaxHighlighter):
|
||||
|
||||
def __init__(self, *args):
|
||||
QSyntaxHighlighter.__init__(self, *args)
|
||||
|
||||
self.regex = u''
|
||||
|
||||
def update_regex(self, regex):
|
||||
self.regex = regex
|
||||
self.rehighlight()
|
||||
|
||||
def highlightBlock(self, text):
|
||||
valid_regex = True
|
||||
text = qstring_to_unicode(text)
|
||||
format = QTextCharFormat()
|
||||
format.setBackground(QBrush(Qt.yellow))
|
||||
|
||||
if self.regex:
|
||||
try:
|
||||
for mo in re.finditer(self.regex, text):
|
||||
self.setFormat(mo.start(), mo.end() - mo.start(), format)
|
||||
except:
|
||||
valid_regex = False
|
||||
self.emit(SIGNAL('regex_valid(PyQt_PyObject)'), valid_regex)
|
||||
|
||||
class RegexBuilder(QDialog, Ui_RegexBuilder):
|
||||
|
||||
def __init__(self, db, book_id, regex, *args):
|
||||
@ -49,9 +23,7 @@ class RegexBuilder(QDialog, Ui_RegexBuilder):
|
||||
self.setupUi(self)
|
||||
|
||||
self.regex.setText(regex)
|
||||
self.regex_valid(True)
|
||||
self.highlighter = RegexHighlighter(self.preview.document())
|
||||
self.highlighter.update_regex(regex)
|
||||
self.regex_valid()
|
||||
|
||||
if not db or not book_id:
|
||||
self.button_box.addButton(QDialogButtonBox.Open)
|
||||
@ -62,19 +34,37 @@ class RegexBuilder(QDialog, Ui_RegexBuilder):
|
||||
self.connect(self.regex, SIGNAL('textChanged(QString)'), self.regex_valid)
|
||||
self.connect(self.test, SIGNAL('clicked()'), self.do_test)
|
||||
|
||||
def regex_valid(self, valid):
|
||||
regex = qstring_to_unicode(self.regex.text())
|
||||
def regex_valid(self):
|
||||
regex = unicode(self.regex.text())
|
||||
if regex:
|
||||
try:
|
||||
re.compile(regex)
|
||||
self.regex.setStyleSheet('QLineEdit { color: black; background-color: rgba(0,255,0,20%); }')
|
||||
except:
|
||||
self.regex.setStyleSheet('QLineEdit { color: black; background-color: rgb(255,0,0,20%); }')
|
||||
return False
|
||||
else:
|
||||
self.regex.setStyleSheet('QLineEdit { color: black; background-color: white; }')
|
||||
return True
|
||||
|
||||
def do_test(self):
|
||||
self.highlighter.update_regex(qstring_to_unicode(self.regex.text()))
|
||||
selections = []
|
||||
if self.regex_valid():
|
||||
text = unicode(self.preview.toPlainText())
|
||||
regex = unicode(self.regex.text())
|
||||
cursor = QTextCursor(self.preview.document())
|
||||
extsel = QTextEdit.ExtraSelection()
|
||||
extsel.cursor = cursor
|
||||
extsel.format.setBackground(QBrush(Qt.yellow))
|
||||
try:
|
||||
for match in re.finditer(regex, text):
|
||||
es = QTextEdit.ExtraSelection(extsel)
|
||||
es.cursor.setPosition(match.start(), QTextCursor.MoveAnchor)
|
||||
es.cursor.setPosition(match.end(), QTextCursor.KeepAnchor)
|
||||
selections.append(es)
|
||||
except:
|
||||
pass
|
||||
self.preview.setExtraSelections(selections)
|
||||
|
||||
def select_format(self, db, book_id):
|
||||
format = None
|
||||
@ -104,9 +94,10 @@ class RegexBuilder(QDialog, Ui_RegexBuilder):
|
||||
|
||||
def button_clicked(self, button):
|
||||
if button == self.button_box.button(QDialogButtonBox.Open):
|
||||
name = QFileDialog.getOpenFileName(self, _('Open book'), _('~'))
|
||||
if name:
|
||||
self.open_book(qstring_to_unicode(name))
|
||||
files = choose_files(self, 'regexp tester dialog', _('Open book'),
|
||||
select_only_single_file=True)
|
||||
if files:
|
||||
self.open_book(files[0])
|
||||
if button == self.button_box.button(QDialogButtonBox.Ok):
|
||||
self.accept()
|
||||
|
||||
|
||||
@ -11,6 +11,7 @@ from PyQt4.QtGui import QDialog, QPixmap, QGraphicsScene, QIcon, QDesktopService
|
||||
from calibre.gui2.dialogs.book_info_ui import Ui_BookInfo
|
||||
from calibre.gui2 import dynamic
|
||||
from calibre import fit_image
|
||||
from calibre.library.comments import comments_to_html
|
||||
|
||||
class BookInfo(QDialog, Ui_BookInfo):
|
||||
|
||||
@ -96,6 +97,8 @@ class BookInfo(QDialog, Ui_BookInfo):
|
||||
self.setWindowTitle(info[_('Title')])
|
||||
self.title.setText('<b>'+info.pop(_('Title')))
|
||||
comments = info.pop(_('Comments'), '')
|
||||
if comments:
|
||||
comments = comments_to_html(comments)
|
||||
if re.search(r'<[a-zA-Z]+>', comments) is None:
|
||||
lines = comments.splitlines()
|
||||
lines = [x if x.strip() else '<br><br>' for x in lines]
|
||||
|
||||
@ -180,27 +180,34 @@ class MetadataSingleDialog(ResizableDialog, Ui_MetadataSingleDialog):
|
||||
self.formats_changed = True
|
||||
|
||||
def get_selected_format_metadata(self):
|
||||
row = self.formats.currentRow()
|
||||
fmt = self.formats.item(row)
|
||||
if fmt is None:
|
||||
if self.formats.count() == 1:
|
||||
fmt = self.formats.item(0)
|
||||
if fmt is None:
|
||||
error_dialog(self, _('No format selected'),
|
||||
_('No format selected')).exec_()
|
||||
return None, None
|
||||
ext = fmt.ext.lower()
|
||||
if fmt.path is None:
|
||||
stream = self.db.format(self.row, ext, as_file=True)
|
||||
else:
|
||||
stream = open(fmt.path, 'r+b')
|
||||
old = prefs['read_file_metadata']
|
||||
if not old:
|
||||
prefs['read_file_metadata'] = True
|
||||
try:
|
||||
mi = get_metadata(stream, ext)
|
||||
return mi, ext
|
||||
except:
|
||||
error_dialog(self, _('Could not read metadata'),
|
||||
_('Could not read metadata from %s format')%ext).exec_()
|
||||
return None, None
|
||||
row = self.formats.currentRow()
|
||||
fmt = self.formats.item(row)
|
||||
if fmt is None:
|
||||
if self.formats.count() == 1:
|
||||
fmt = self.formats.item(0)
|
||||
if fmt is None:
|
||||
error_dialog(self, _('No format selected'),
|
||||
_('No format selected')).exec_()
|
||||
return None, None
|
||||
ext = fmt.ext.lower()
|
||||
if fmt.path is None:
|
||||
stream = self.db.format(self.row, ext, as_file=True)
|
||||
else:
|
||||
stream = open(fmt.path, 'r+b')
|
||||
try:
|
||||
mi = get_metadata(stream, ext)
|
||||
return mi, ext
|
||||
except:
|
||||
error_dialog(self, _('Could not read metadata'),
|
||||
_('Could not read metadata from %s format')%ext).exec_()
|
||||
return None, None
|
||||
finally:
|
||||
if old != prefs['read_file_metadata']:
|
||||
prefs['read_file_metadata'] = old
|
||||
|
||||
def set_metadata_from_format(self):
|
||||
mi, ext = self.get_selected_format_metadata()
|
||||
@ -231,7 +238,7 @@ class MetadataSingleDialog(ResizableDialog, Ui_MetadataSingleDialog):
|
||||
if mi.series_index is not None:
|
||||
self.series_index.setValue(float(mi.series_index))
|
||||
if mi.comments and mi.comments.strip():
|
||||
self.comments.setText(mi.comments)
|
||||
self.comments.setPlainText(mi.comments)
|
||||
|
||||
|
||||
def set_cover(self):
|
||||
@ -555,7 +562,7 @@ class MetadataSingleDialog(ResizableDialog, Ui_MetadataSingleDialog):
|
||||
title = qstring_to_unicode(self.title.text())
|
||||
try:
|
||||
author = string_to_authors(unicode(self.authors.text()))[0]
|
||||
except IndexError:
|
||||
except:
|
||||
author = ''
|
||||
publisher = qstring_to_unicode(self.publisher.currentText())
|
||||
if isbn or title or author or publisher:
|
||||
@ -590,7 +597,7 @@ class MetadataSingleDialog(ResizableDialog, Ui_MetadataSingleDialog):
|
||||
prefix = unicode(self.comments.toPlainText())
|
||||
if prefix:
|
||||
prefix += '\n'
|
||||
self.comments.setText(prefix + summ)
|
||||
self.comments.setPlainText(prefix + summ)
|
||||
if book.rating is not None:
|
||||
self.rating.setValue(int(book.rating))
|
||||
if book.tags:
|
||||
@ -654,7 +661,7 @@ class MetadataSingleDialog(ResizableDialog, Ui_MetadataSingleDialog):
|
||||
self.db.set_series(self.id,
|
||||
unicode(self.series.currentText()).strip(), notify=False)
|
||||
self.db.set_series_index(self.id, self.series_index.value(), notify=False)
|
||||
self.db.set_comment(self.id, qstring_to_unicode(self.comments.toPlainText()), notify=False)
|
||||
self.db.set_comment(self.id, unicode(self.comments.toPlainText()), notify=False)
|
||||
d = self.pubdate.date()
|
||||
d = qt_to_dt(d)
|
||||
self.db.set_pubdate(self.id, d, notify=False)
|
||||
|
||||
@ -220,6 +220,10 @@ class Scheduler(QObject):
|
||||
self.cac = QAction(QIcon(I('user_profile.svg')), _('Add a custom news source'), self)
|
||||
self.connect(self.cac, SIGNAL('triggered(bool)'), self.customize_feeds)
|
||||
self.news_menu.addAction(self.cac)
|
||||
self.news_menu.addSeparator()
|
||||
self.all_action = self.news_menu.addAction(
|
||||
_('Download all scheduled new sources'),
|
||||
self.download_all_scheduled)
|
||||
|
||||
self.timer = QTimer(self)
|
||||
self.timer.start(int(self.INTERVAL * 60000))
|
||||
@ -304,7 +308,11 @@ class Scheduler(QObject):
|
||||
if urn is not None:
|
||||
return self.download(urn)
|
||||
for urn in self.recipe_model.scheduled_urns():
|
||||
self.download(urn)
|
||||
if not self.download(urn):
|
||||
break
|
||||
|
||||
def download_all_scheduled(self):
|
||||
self.download_clicked(None)
|
||||
|
||||
def download(self, urn):
|
||||
self.lock.lock()
|
||||
@ -316,12 +324,13 @@ class Scheduler(QObject):
|
||||
'is active'))
|
||||
d.setModal(False)
|
||||
d.show()
|
||||
return
|
||||
return False
|
||||
self.internet_connection_failed = False
|
||||
doit = urn not in self.download_queue
|
||||
self.lock.unlock()
|
||||
if doit:
|
||||
self.do_download(urn)
|
||||
return True
|
||||
|
||||
def check(self):
|
||||
recipes = self.recipe_model.get_to_be_downloaded_recipes()
|
||||
|
||||
@ -777,7 +777,7 @@ class BooksView(TableView):
|
||||
self.setItemDelegateForColumn(cm.index('series'), self.series_delegate)
|
||||
|
||||
def set_context_menu(self, edit_metadata, send_to_device, convert, view,
|
||||
save, open_folder, book_details, merge, delete, similar_menu=None):
|
||||
save, open_folder, book_details, delete, similar_menu=None):
|
||||
self.setContextMenuPolicy(Qt.DefaultContextMenu)
|
||||
self.context_menu = QMenu(self)
|
||||
if edit_metadata is not None:
|
||||
@ -790,8 +790,6 @@ class BooksView(TableView):
|
||||
self.context_menu.addAction(save)
|
||||
if open_folder is not None:
|
||||
self.context_menu.addAction(open_folder)
|
||||
if merge is not None:
|
||||
self.context_menu.addAction(merge)
|
||||
if delete is not None:
|
||||
self.context_menu.addAction(delete)
|
||||
if book_details is not None:
|
||||
|
||||
@ -1379,5 +1379,5 @@ void PictureFlow::dataChanged() { d->dataChanged(); }
|
||||
void PictureFlow::emitcurrentChanged(int index) { emit currentChanged(index); }
|
||||
|
||||
int FlowImages::count() { return 0; }
|
||||
QImage FlowImages::image(int index) { return QImage(); }
|
||||
QString FlowImages::caption(int index) {return QString(); }
|
||||
QImage FlowImages::image(int index) { index=0; return QImage(); }
|
||||
QString FlowImages::caption(int index) {index=0; return QString(); }
|
||||
|
||||
@ -260,7 +260,10 @@ class ShortcutConfig(QWidget):
|
||||
self.view.setModel(model)
|
||||
self.delegate = Delegate()
|
||||
self.view.setItemDelegate(self.delegate)
|
||||
self.delegate.sizeHintChanged.connect(self.view.scrollTo)
|
||||
self.delegate.sizeHintChanged.connect(self.scrollTo)
|
||||
|
||||
def scrollTo(self, index):
|
||||
self.view.scrollTo(index)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
@ -11,6 +11,7 @@ from calibre.gui2.widgets import IMAGE_EXTENSIONS
|
||||
from calibre.gui2.progress_indicator import ProgressIndicator
|
||||
from calibre.gui2.notify import get_notifier
|
||||
from calibre.ebooks import BOOK_EXTENSIONS
|
||||
from calibre.library.comments import comments_to_html
|
||||
|
||||
class BookInfoDisplay(QWidget):
|
||||
|
||||
@ -91,9 +92,9 @@ class BookInfoDisplay(QWidget):
|
||||
WEIGHTS = collections.defaultdict(lambda : 100)
|
||||
WEIGHTS[_('Path')] = 0
|
||||
WEIGHTS[_('Formats')] = 1
|
||||
WEIGHTS[_('Comments')] = 2
|
||||
WEIGHTS[_('Series')] = 3
|
||||
WEIGHTS[_('Tags')] = 4
|
||||
WEIGHTS[_('Comments')] = 4
|
||||
WEIGHTS[_('Series')] = 2
|
||||
WEIGHTS[_('Tags')] = 3
|
||||
|
||||
def __init__(self, clear_message):
|
||||
QWidget.__init__(self)
|
||||
@ -127,10 +128,14 @@ class BookInfoDisplay(QWidget):
|
||||
keys.sort(cmp=lambda x, y: cmp(self.WEIGHTS[x], self.WEIGHTS[y]))
|
||||
for key in keys:
|
||||
txt = data[key]
|
||||
if not txt or not txt.strip() or txt == 'None':
|
||||
continue
|
||||
if isinstance(key, str):
|
||||
key = key.decode(preferred_encoding, 'replace')
|
||||
if isinstance(txt, str):
|
||||
txt = txt.decode(preferred_encoding, 'replace')
|
||||
if key == _('Comments'):
|
||||
txt = comments_to_html(txt)
|
||||
rows += u'<tr><td><b>%s:</b></td><td>%s</td></tr>'%(key, txt)
|
||||
self.book_data.setText(u'<table>'+rows+u'</table>')
|
||||
|
||||
|
||||
@ -242,8 +242,12 @@ class Main(MainWindow, Ui_MainWindow, DeviceGUI):
|
||||
####################### Vanity ########################
|
||||
self.vanity_template = _('<p>For help see the: <a href="%s">User Manual</a>'
|
||||
'<br>')%'http://calibre-ebook.com/user_manual'
|
||||
dv = os.environ.get('CALIBRE_DEVELOP_FROM', None)
|
||||
v = __version__
|
||||
if getattr(sys, 'frozen', False) and dv and os.path.abspath(dv) in sys.path:
|
||||
v += '*'
|
||||
self.vanity_template += _('<b>%s</b>: %s by <b>Kovid Goyal '
|
||||
'%%(version)s</b><br>%%(device)s</p>')%(__appname__, __version__)
|
||||
'%%(version)s</b><br>%%(device)s</p>')%(__appname__, v)
|
||||
self.latest_version = ' '
|
||||
self.vanity.setText(self.vanity_template%dict(version=' ', device=' '))
|
||||
self.device_info = ' '
|
||||
@ -350,7 +354,8 @@ class Main(MainWindow, Ui_MainWindow, DeviceGUI):
|
||||
|
||||
self.view_menu = QMenu()
|
||||
self.view_menu.addAction(_('View'))
|
||||
self.view_menu.addAction(_('View specific format'))
|
||||
ac = self.view_menu.addAction(_('View specific format'))
|
||||
ac.setShortcut(Qt.AltModifier+Qt.Key_V)
|
||||
self.action_view.setMenu(self.view_menu)
|
||||
|
||||
self.delete_menu = QMenu()
|
||||
@ -478,16 +483,15 @@ class Main(MainWindow, Ui_MainWindow, DeviceGUI):
|
||||
self.action_save,
|
||||
self.action_open_containing_folder,
|
||||
self.action_show_book_details,
|
||||
self.action_merge,
|
||||
self.action_del,
|
||||
similar_menu=similar_menu)
|
||||
|
||||
self.memory_view.set_context_menu(None, None, None,
|
||||
self.action_view, self.action_save, None, None, None, self.action_del)
|
||||
self.action_view, self.action_save, None, None, self.action_del)
|
||||
self.card_a_view.set_context_menu(None, None, None,
|
||||
self.action_view, self.action_save, None, None, None, self.action_del)
|
||||
self.action_view, self.action_save, None, None, self.action_del)
|
||||
self.card_b_view.set_context_menu(None, None, None,
|
||||
self.action_view, self.action_save, None, None, None, self.action_del)
|
||||
self.action_view, self.action_save, None, None, self.action_del)
|
||||
|
||||
QObject.connect(self.library_view,
|
||||
SIGNAL('files_dropped(PyQt_PyObject)'),
|
||||
@ -1669,7 +1673,7 @@ class Main(MainWindow, Ui_MainWindow, DeviceGUI):
|
||||
if src_book:
|
||||
fmt = os.path.splitext(src_book)[-1].replace('.', '').upper()
|
||||
with open(src_book, 'rb') as f:
|
||||
self.db.add_format(dest_id, fmt, f, index_is_id=True,
|
||||
self.library_view.model().db.add_format(dest_id, fmt, f, index_is_id=True,
|
||||
notify=False, replace=replace)
|
||||
|
||||
def books_to_merge(self, rows):
|
||||
@ -1684,7 +1688,7 @@ class Main(MainWindow, Ui_MainWindow, DeviceGUI):
|
||||
src_ids.append(id_)
|
||||
dbfmts = m.db.formats(id_, index_is_id=True)
|
||||
if dbfmts:
|
||||
for fmt in dbfmts:
|
||||
for fmt in dbfmts.split(','):
|
||||
src_books.append(m.db.format_abspath(id_, fmt,
|
||||
index_is_id=True))
|
||||
return [dest_id, src_books, src_ids]
|
||||
@ -2092,7 +2096,7 @@ class Main(MainWindow, Ui_MainWindow, DeviceGUI):
|
||||
return
|
||||
for row in rows:
|
||||
path = self.library_view.model().db.abspath(row.row())
|
||||
QDesktopServices.openUrl(QUrl('file:'+path))
|
||||
QDesktopServices.openUrl(QUrl.fromLocalFile(path))
|
||||
|
||||
|
||||
def view_book(self, triggered):
|
||||
|
||||
@ -7,10 +7,12 @@ __docformat__ = 'restructuredtext en'
|
||||
'''
|
||||
import os, math, re, glob, sys
|
||||
from base64 import b64encode
|
||||
from functools import partial
|
||||
|
||||
from PyQt4.Qt import QSize, QSizePolicy, QUrl, SIGNAL, Qt, QTimer, \
|
||||
QPainter, QPalette, QBrush, QFontDatabase, QDialog, \
|
||||
QColor, QPoint, QImage, QRegion, QVariant, QIcon, \
|
||||
QFont, pyqtSignature, QAction, QByteArray
|
||||
QFont, pyqtSignature, QAction, QByteArray, QMenu
|
||||
from PyQt4.QtWebKit import QWebPage, QWebView, QWebSettings
|
||||
|
||||
from calibre.utils.config import Config, StringConfig
|
||||
@ -392,13 +394,14 @@ class Document(QWebPage):
|
||||
return self.mainFrame().contentsSize().width() # offsetWidth gives inaccurate results
|
||||
|
||||
def set_bottom_padding(self, amount):
|
||||
padding = '%dpx'%amount
|
||||
try:
|
||||
old_padding = unicode(self.javascript('$("body").css("padding-bottom")').toString())
|
||||
except:
|
||||
old_padding = ''
|
||||
body = self.mainFrame().documentElement().findFirst('body')
|
||||
if body.isNull():
|
||||
return
|
||||
old_padding = unicode(body.styleProperty('padding-bottom',
|
||||
body.ComputedStyle)).strip()
|
||||
padding = u'%dpx'%amount
|
||||
if old_padding != padding:
|
||||
self.javascript('$("body").css("padding-bottom", "%s")' % padding)
|
||||
body.setStyleProperty('padding-bottom', padding + ' !important')
|
||||
|
||||
|
||||
class EntityDeclarationProcessor(object):
|
||||
@ -421,7 +424,7 @@ class DocumentView(QWebView):
|
||||
QWebView.__init__(self, *args)
|
||||
self.debug_javascript = False
|
||||
self.shortcuts = Shortcuts(SHORTCUTS, 'shortcuts/viewer')
|
||||
self.self_closing_pat = re.compile(r'<([a-z]+)\s+([^>]+)/>',
|
||||
self.self_closing_pat = re.compile(r'<([a-z1-6]+)\s+([^>]+)/>',
|
||||
re.IGNORECASE)
|
||||
self.setSizePolicy(QSizePolicy(QSizePolicy.Expanding, QSizePolicy.Expanding))
|
||||
self._size_hint = QSize(510, 680)
|
||||
@ -449,6 +452,50 @@ class DocumentView(QWebView):
|
||||
_('&Lookup in dictionary'), self)
|
||||
self.dictionary_action.setShortcut(Qt.CTRL+Qt.Key_L)
|
||||
self.dictionary_action.triggered.connect(self.lookup)
|
||||
self.goto_location_action = QAction(_('Go to...'), self)
|
||||
self.goto_location_menu = m = QMenu(self)
|
||||
self.goto_location_actions = a = {
|
||||
'Next Page': self.next_page,
|
||||
'Previous Page': self.previous_page,
|
||||
'Section Top' : partial(self.scroll_to, 0),
|
||||
'Document Top': self.goto_document_start,
|
||||
'Section Bottom':partial(self.scroll_to, 1),
|
||||
'Document Bottom': self.goto_document_end,
|
||||
'Next Section': self.goto_next_section,
|
||||
'Previous Section': self.goto_previous_section,
|
||||
}
|
||||
for name, key in [(_('Next Section'), 'Next Section'),
|
||||
(_('Previous Section'), 'Previous Section'),
|
||||
(None, None),
|
||||
(_('Document Start'), 'Document Top'),
|
||||
(_('Document End'), 'Document Bottom'),
|
||||
(None, None),
|
||||
(_('Section Start'), 'Section Top'),
|
||||
(_('Section End'), 'Section Bottom'),
|
||||
(None, None),
|
||||
(_('Next Page'), 'Next Page'),
|
||||
(_('Previous Page'), 'Previous Page')]:
|
||||
if key is None:
|
||||
m.addSeparator()
|
||||
else:
|
||||
m.addAction(name, a[key], self.shortcuts.get_sequences(key)[0])
|
||||
self.goto_location_action.setMenu(self.goto_location_menu)
|
||||
|
||||
def goto_next_section(self, *args):
|
||||
if self.manager is not None:
|
||||
self.manager.goto_next_section()
|
||||
|
||||
def goto_previous_section(self, *args):
|
||||
if self.manager is not None:
|
||||
self.manager.goto_previous_section()
|
||||
|
||||
def goto_document_start(self, *args):
|
||||
if self.manager is not None:
|
||||
self.manager.goto_start()
|
||||
|
||||
def goto_document_end(self, *args):
|
||||
if self.manager is not None:
|
||||
self.manager.goto_end()
|
||||
|
||||
@property
|
||||
def copy_action(self):
|
||||
@ -488,6 +535,8 @@ class DocumentView(QWebView):
|
||||
text = unicode(self.selectedText())
|
||||
if text:
|
||||
menu.insertAction(list(menu.actions())[0], self.dictionary_action)
|
||||
menu.addSeparator()
|
||||
menu.addAction(self.goto_location_action)
|
||||
menu.exec_(ev.globalPos())
|
||||
|
||||
def lookup(self, *args):
|
||||
@ -763,20 +812,9 @@ class DocumentView(QWebView):
|
||||
|
||||
def keyPressEvent(self, event):
|
||||
key = self.shortcuts.get_match(event)
|
||||
if key == 'Next Page':
|
||||
self.next_page()
|
||||
elif key == 'Previous Page':
|
||||
self.previous_page()
|
||||
elif key == 'Section Top':
|
||||
self.scroll_to(0)
|
||||
elif key == 'Document Top':
|
||||
if self.manager is not None:
|
||||
self.manager.goto_start()
|
||||
elif key == 'Section Bottom':
|
||||
self.scroll_to(1)
|
||||
elif key == 'Document Bottom':
|
||||
if self.manager is not None:
|
||||
self.manager.goto_end()
|
||||
func = self.goto_location_actions.get(key, None)
|
||||
if func is not None:
|
||||
func()
|
||||
elif key == 'Down':
|
||||
self.scroll_by(y=15)
|
||||
elif key == 'Up':
|
||||
@ -785,12 +823,6 @@ class DocumentView(QWebView):
|
||||
self.scroll_by(x=-15)
|
||||
elif key == 'Right':
|
||||
self.scroll_by(x=15)
|
||||
elif key == 'Next Section':
|
||||
if self.manager is not None:
|
||||
self.manager.goto_next_section()
|
||||
elif key == 'Previous Section':
|
||||
if self.manager is not None:
|
||||
self.manager.goto_previous_section()
|
||||
else:
|
||||
return QWebView.keyPressEvent(self, event)
|
||||
|
||||
|
||||
@ -822,7 +822,7 @@ def do_remove_custom_column(db, label, force):
|
||||
if not force:
|
||||
q = raw_input(_('You will lose all data in the column: %r.'
|
||||
' Are you sure (y/n)? ')%label)
|
||||
if q.lower().strip() != 'y':
|
||||
if q.lower().strip() != _('y'):
|
||||
return
|
||||
db.delete_custom_column(label=label)
|
||||
prints('Column %r removed.'%label)
|
||||
|
||||
114
src/calibre/library/comments.py
Normal file
114
src/calibre/library/comments.py
Normal file
@ -0,0 +1,114 @@
|
||||
#!/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 re
|
||||
|
||||
from calibre.constants import preferred_encoding
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag, NavigableString
|
||||
from calibre import prepare_string_for_xml
|
||||
|
||||
def comments_to_html(comments):
|
||||
'''
|
||||
Convert random comment text to normalized, xml-legal block of <p>s
|
||||
'plain text' returns as
|
||||
<p>plain text</p>
|
||||
|
||||
'plain text with <i>minimal</i> <b>markup</b>' returns as
|
||||
<p>plain text with <i>minimal</i> <b>markup</b></p>
|
||||
|
||||
'<p>pre-formatted text</p> returns untouched
|
||||
|
||||
'A line of text\n\nFollowed by a line of text' returns as
|
||||
<p>A line of text</p>
|
||||
<p>Followed by a line of text</p>
|
||||
|
||||
'A line of text.\nA second line of text.\rA third line of text' returns as
|
||||
<p>A line of text.<br />A second line of text.<br />A third line of text.</p>
|
||||
|
||||
'...end of a paragraph.Somehow the break was lost...' returns as
|
||||
<p>...end of a paragraph.</p>
|
||||
<p>Somehow the break was lost...</p>
|
||||
|
||||
Deprecated HTML returns as HTML via BeautifulSoup()
|
||||
|
||||
'''
|
||||
if not isinstance(comments, unicode):
|
||||
comments = comments.decode(preferred_encoding, 'replace')
|
||||
|
||||
# Hackish - ignoring sentences ending or beginning in numbers to avoid
|
||||
# confusion with decimal points.
|
||||
|
||||
# Explode lost CRs to \n\n
|
||||
for lost_cr in re.finditer('([a-z])([\.\?!])([A-Z])', comments):
|
||||
comments = comments.replace(lost_cr.group(),
|
||||
'%s%s\n\n%s' % (lost_cr.group(1),
|
||||
lost_cr.group(2),
|
||||
lost_cr.group(3)))
|
||||
|
||||
# Convert \n\n to <p>s
|
||||
if re.search('\n\n', comments):
|
||||
soup = BeautifulSoup()
|
||||
split_ps = comments.split(u'\n\n')
|
||||
tsc = 0
|
||||
for p in split_ps:
|
||||
pTag = Tag(soup,'p')
|
||||
pTag.insert(0,p)
|
||||
soup.insert(tsc,pTag)
|
||||
tsc += 1
|
||||
comments = soup.renderContents(None)
|
||||
|
||||
# Convert solo returns to <br />
|
||||
comments = re.sub('[\r\n]','<br />', comments)
|
||||
|
||||
# Convert two hyphens to emdash
|
||||
comments = re.sub('--', '—', comments)
|
||||
soup = BeautifulSoup(comments)
|
||||
result = BeautifulSoup()
|
||||
rtc = 0
|
||||
open_pTag = False
|
||||
|
||||
all_tokens = list(soup.contents)
|
||||
for token in all_tokens:
|
||||
if type(token) is NavigableString:
|
||||
if not open_pTag:
|
||||
pTag = Tag(result,'p')
|
||||
open_pTag = True
|
||||
ptc = 0
|
||||
pTag.insert(ptc,prepare_string_for_xml(token))
|
||||
ptc += 1
|
||||
|
||||
elif token.name in ['br','b','i','em']:
|
||||
if not open_pTag:
|
||||
pTag = Tag(result,'p')
|
||||
open_pTag = True
|
||||
ptc = 0
|
||||
pTag.insert(ptc, token)
|
||||
ptc += 1
|
||||
|
||||
else:
|
||||
if open_pTag:
|
||||
result.insert(rtc, pTag)
|
||||
rtc += 1
|
||||
open_pTag = False
|
||||
ptc = 0
|
||||
# Clean up NavigableStrings for xml
|
||||
sub_tokens = list(token.contents)
|
||||
for sub_token in sub_tokens:
|
||||
if type(sub_token) is NavigableString:
|
||||
sub_token.replaceWith(prepare_string_for_xml(sub_token))
|
||||
result.insert(rtc, token)
|
||||
rtc += 1
|
||||
|
||||
if open_pTag:
|
||||
result.insert(rtc, pTag)
|
||||
|
||||
paras = result.findAll('p')
|
||||
for p in paras:
|
||||
p['class'] = 'description'
|
||||
|
||||
return result.renderContents(encoding=None)
|
||||
|
||||
@ -27,7 +27,9 @@ FORMAT_ARG_DESCS = dict(
|
||||
'of the name use {author_sort[0]}'),
|
||||
tags=_('The tags'),
|
||||
series=_('The series'),
|
||||
series_index=_('The series number. To get leading zeros use {series_index:0>3s}'),
|
||||
series_index=_('The series number. '
|
||||
'To get leading zeros use {series_index:0>3s} or '
|
||||
'{series_index:>3s} for leading spaces'),
|
||||
rating=_('The rating'),
|
||||
isbn=_('The ISBN'),
|
||||
publisher=_('The publisher'),
|
||||
|
||||
@ -113,7 +113,7 @@ Metadata download plugins
|
||||
When :meth:`fetch` is called, the `self` object will have the following
|
||||
useful attributes (each of which may be None)::
|
||||
|
||||
title, author, publisher, isbn, log, verbose and extra
|
||||
title, book_author, publisher, isbn, log, verbose and extra
|
||||
|
||||
Use these attributes to construct the search query. extra is reserved for
|
||||
future use.
|
||||
|
||||
@ -19,12 +19,13 @@ __builtin__.__dict__['__'] = lambda s: s
|
||||
from calibre.constants import iswindows, preferred_encoding, plugins
|
||||
|
||||
_run_once = False
|
||||
winutil = winutilerror = None
|
||||
|
||||
if not _run_once:
|
||||
_run_once = True
|
||||
|
||||
################################################################################
|
||||
# Platform specific modules
|
||||
winutil = winutilerror = None
|
||||
if iswindows:
|
||||
winutil, winutilerror = plugins['winutil']
|
||||
if not winutil:
|
||||
|
||||
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
@ -106,6 +106,7 @@ _extra_lang_codes = {
|
||||
'en_SG' : _('English (Singapore)'),
|
||||
'en_YE' : _('English (Yemen)'),
|
||||
'en_IE' : _('English (Ireland)'),
|
||||
'es_PY' : _('Spanish (Paraguay)'),
|
||||
'de_AT' : _('German (AT)'),
|
||||
'nl' : _('Dutch (NL)'),
|
||||
'nl_BE' : _('Dutch (BE)'),
|
||||
|
||||
@ -183,10 +183,6 @@ class RecipeModel(QAbstractItemModel, SearchQueryParser):
|
||||
lang_map = {}
|
||||
self.all_urns = set([])
|
||||
self.showing_count = 0
|
||||
for x in self.scheduler_config.iter_recipes():
|
||||
urn = x.get('id')
|
||||
if ok(urn):
|
||||
factory(NewsItem, scheduled, urn, x.get('title'))
|
||||
for x in self.custom_recipe_collection:
|
||||
urn = x.get('id')
|
||||
self.all_urns.add(urn)
|
||||
@ -202,6 +198,13 @@ class RecipeModel(QAbstractItemModel, SearchQueryParser):
|
||||
lang_map[lang] = factory(NewsCategory, new_root, lang)
|
||||
factory(NewsItem, lang_map[lang], urn, x.get('title'))
|
||||
self.showing_count += 1
|
||||
for x in self.scheduler_config.iter_recipes():
|
||||
urn = x.get('id')
|
||||
if urn not in self.all_urns:
|
||||
self.scheduler_config.un_schedule_recipe(urn)
|
||||
continue
|
||||
if ok(urn):
|
||||
factory(NewsItem, scheduled, urn, x.get('title'))
|
||||
new_root.prune()
|
||||
new_root.sort()
|
||||
self.root = new_root
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user