mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
merge from trunk
This commit is contained in:
commit
483075e784
@ -12,7 +12,7 @@ class Noticias(BasicNewsRecipe):
|
||||
title = '180.com.uy'
|
||||
__author__ = 'Gustavo Azambuja'
|
||||
description = 'Noticias de Uruguay'
|
||||
language = 'es'
|
||||
language = 'es_UY'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
use_embedded_content = False
|
||||
recursion = 5
|
||||
|
@ -20,7 +20,7 @@ class SieteDias(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
encoding = 'utf-8'
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
|
||||
lang = 'es-AR'
|
||||
direction = 'ltr'
|
||||
|
@ -58,4 +58,4 @@ class Ambito(BasicNewsRecipe):
|
||||
del item['style']
|
||||
return soup
|
||||
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
|
@ -12,7 +12,7 @@ class AdvancedUserRecipe1290663986(BasicNewsRecipe):
|
||||
masthead_url = 'http://www.animalpolitico.com/wp-content/themes/animal_mu/images/logo.png'
|
||||
oldest_article = 1
|
||||
max_articles_per_feed = 100
|
||||
language = 'es'
|
||||
language = 'es_MX'
|
||||
|
||||
#feeds = [(u'Animal Politico', u'http://www.animalpolitico.com/feed/')]
|
||||
|
||||
|
@ -17,7 +17,7 @@ class Axxon_news(BasicNewsRecipe):
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = False
|
||||
use_embedded_content = False
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
encoding = 'utf-8'
|
||||
publication_type = 'magazine'
|
||||
INDEX = 'http://axxon.com.ar/rev/'
|
||||
|
@ -18,7 +18,7 @@ class Axxon_news(BasicNewsRecipe):
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = False
|
||||
use_embedded_content = False
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
|
||||
lang = 'es-AR'
|
||||
|
||||
|
53
resources/recipes/bbc_es.recipe
Normal file
53
resources/recipes/bbc_es.recipe
Normal file
@ -0,0 +1,53 @@
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'Luis Hernandez'
|
||||
__copyright__ = 'Luis Hernandez<tolyluis@gmail.com>'
|
||||
__version__ = 'v1.0'
|
||||
__date__ = '29 January 2011'
|
||||
|
||||
'''
|
||||
http://www.bbc.co.uk/mundo/
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1294946868(BasicNewsRecipe):
|
||||
|
||||
title = u'BBC Mundo'
|
||||
publisher = u'BBC'
|
||||
|
||||
__author__ = 'Luis Hernandez'
|
||||
description = 'BBC World for spanish readers'
|
||||
|
||||
cover_url = 'http://1.bp.blogspot.com/_NHiOjk_uZwU/TEYy7IJAdAI/AAAAAAAABP8/coAE-pJ7_5E/s1600/bbcmundo_h.png'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
|
||||
language = 'es'
|
||||
remove_empty_feeds = True
|
||||
encoding = 'UTF-8'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
|
||||
remove_tags_before = dict(name='div' , attrs={'class':['g-group']})
|
||||
remove_tags_after = dict(name='div' , attrs={'class':[' g-w8']})
|
||||
|
||||
remove_tags = [
|
||||
dict(name='ul', attrs={'class':['document-tools blq-clearfix','blq-clearfix']})
|
||||
,dict(name='div', attrs={'class':['box bx-quote-bubble','socialmedia-links','list li-carousel','list li-plain rolling-news','list li-plain','box bx-livestats','li-tab content','list li-relatedlinks','list li-relatedinternetlinks']})
|
||||
]
|
||||
|
||||
feeds = [
|
||||
(u'Portada' , u'http://www.bbc.co.uk/mundo/index.xml')
|
||||
,(u'Ultimas Noticias' , u'http://www.bbc.co.uk/mundo/ultimas_noticias/index.xml')
|
||||
,(u'Internacional' , u'http://www.bbc.co.uk/mundo/temas/internacional/index.xml')
|
||||
,(u'Economia' , u'http://www.bbc.co.uk/mundo/temas/economia/index.xml')
|
||||
,(u'America Latina' , u'http://www.bbc.co.uk/mundo/temas/america_latina/index.xml')
|
||||
,(u'Ciencia' , u'http://www.bbc.co.uk/mundo/temas/ciencia/index.xml')
|
||||
,(u'Salud' , u'http://www.bbc.co.uk/mundo/temas/salud/index.xml')
|
||||
,(u'Tecnologia' , u'http://www.bbc.co.uk/mundo/temas/tecnologia/index.xml')
|
||||
,(u'Cultura' , u'http://www.bbc.co.uk/mundo/temas/cultura/index.xml')
|
||||
]
|
||||
|
@ -12,7 +12,7 @@ class General(BasicNewsRecipe):
|
||||
title = 'bitacora.com.uy'
|
||||
__author__ = 'Gustavo Azambuja'
|
||||
description = 'Noticias de Uruguay'
|
||||
language = 'es'
|
||||
language = 'es_UY'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
use_embedded_content = False
|
||||
recursion = 5
|
||||
|
@ -20,7 +20,7 @@ class BsAsEconomico(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
encoding = 'utf-8'
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
|
||||
lang = 'es-AR'
|
||||
direction = 'ltr'
|
||||
|
@ -18,7 +18,7 @@ class Clarin(BasicNewsRecipe):
|
||||
use_embedded_content = False
|
||||
no_stylesheets = True
|
||||
encoding = 'utf8'
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
publication_type = 'newspaper'
|
||||
INDEX = 'http://www.clarin.com'
|
||||
masthead_url = 'http://www.clarin.com/static/CLAClarin/images/logo-clarin-print.jpg'
|
||||
|
@ -14,7 +14,7 @@ class CriticaDigital(BasicNewsRecipe):
|
||||
description = 'Noticias de Argentina'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
|
@ -11,7 +11,7 @@ class CubaDebate(BasicNewsRecipe):
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'Contra el Terorismo Mediatico'
|
||||
oldest_article = 15
|
||||
language = 'es'
|
||||
language = 'es_CU'
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
|
@ -16,7 +16,7 @@ class DeutscheWelle_es(BasicNewsRecipe):
|
||||
max_articles_per_feed = 100
|
||||
use_embedded_content = False
|
||||
no_stylesheets = True
|
||||
language = 'es'
|
||||
language = 'de_ES'
|
||||
publication_type = 'newsportal'
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.dw-world.de/skins/std/channel1/pics/dw_logo1024.gif'
|
||||
|
@ -20,7 +20,7 @@ class Diagonales(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
encoding = 'utf-8'
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
|
||||
lang = 'es-AR'
|
||||
direction = 'ltr'
|
||||
|
@ -20,7 +20,7 @@ class ElMercurio(BasicNewsRecipe):
|
||||
masthead_url = 'http://www.emol.com/especiales/logo_emol/logo_emol.gif'
|
||||
remove_javascript = True
|
||||
use_embedded_content = False
|
||||
language = 'es'
|
||||
language = 'es_CL'
|
||||
|
||||
|
||||
conversion_options = {
|
||||
|
@ -13,7 +13,7 @@ class ObservaDigital(BasicNewsRecipe):
|
||||
title = 'Observa Digital'
|
||||
__author__ = 'yrvn'
|
||||
description = 'Noticias de Uruguay'
|
||||
language = 'es'
|
||||
language = 'es_UY'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
use_embedded_content = False
|
||||
recursion = 5
|
||||
|
@ -14,7 +14,7 @@ class General(BasicNewsRecipe):
|
||||
description = 'Noticias de Uruguay y el resto del mundo'
|
||||
publisher = 'EL PAIS S.A.'
|
||||
category = 'news, politics, Uruguay'
|
||||
language = 'es'
|
||||
language = 'es_UY'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
use_embedded_content = False
|
||||
recursion = 2
|
||||
|
@ -20,7 +20,7 @@ class ElUniversal(BasicNewsRecipe):
|
||||
remove_javascript = True
|
||||
remove_empty_feeds = True
|
||||
publication_type = 'newspaper'
|
||||
language = 'es'
|
||||
language = 'es_MX'
|
||||
|
||||
extra_css = '''
|
||||
body{font-family:Arial,Helvetica,sans-serif}
|
||||
|
@ -20,7 +20,7 @@ class ElArgentino(BasicNewsRecipe):
|
||||
use_embedded_content = False
|
||||
encoding = 'utf8'
|
||||
cover_url = 'http://www.elargentino.com/TemplateWeb/MediosFooter/tapa_elargentino.png'
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
|
||||
|
||||
html2lrf_options = [
|
||||
|
@ -18,7 +18,7 @@ class ElComercio(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
encoding = 'utf-8'
|
||||
use_embedded_content = True
|
||||
language = 'es'
|
||||
language = 'es_EC'
|
||||
masthead_url = 'http://ww1.elcomercio.com/nv_images/headers/EC/logo_new_08.gif'
|
||||
extra_css = ' body{font-family: Arial,Verdana,sans-serif} img{margin-bottom: 1em} '
|
||||
|
||||
|
@ -13,7 +13,7 @@ class ElCronista(BasicNewsRecipe):
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'Noticias de Argentina'
|
||||
oldest_article = 2
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
|
@ -21,7 +21,7 @@ class ElTiempoHn(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
encoding = 'utf-8'
|
||||
language = 'es'
|
||||
language = 'es_HN'
|
||||
|
||||
lang = 'es-HN'
|
||||
direction = 'ltr'
|
||||
|
@ -18,7 +18,7 @@ class ElUniversal(BasicNewsRecipe):
|
||||
encoding = 'cp1252'
|
||||
publisher = 'El Universal'
|
||||
category = 'news, Caracas, Venezuela, world'
|
||||
language = 'es'
|
||||
language = 'es_VE'
|
||||
cover_url = strftime('http://static.eluniversal.com/%Y/%m/%d/portada.jpg')
|
||||
|
||||
conversion_options = {
|
||||
|
@ -3,7 +3,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
|
||||
class ElUniversalImpresaRecipe(BasicNewsRecipe):
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'kwetal'
|
||||
language = 'es'
|
||||
language = 'es_MX'
|
||||
version = 1
|
||||
|
||||
title = u'El Universal (Edici\u00F3n Impresa)'
|
||||
|
@ -17,7 +17,7 @@ class ElUniverso_Ecuador(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
encoding = 'utf8'
|
||||
use_embedded_content = False
|
||||
language = 'es'
|
||||
language = 'es_EC'
|
||||
remove_empty_feeds = True
|
||||
publication_type = 'newspaper'
|
||||
masthead_url = 'http://servicios2.eluniverso.com/versiones/v1/img/Hd/lg_ElUniverso.gif'
|
||||
|
@ -18,3 +18,6 @@ class EndgadgetJapan(BasicNewsRecipe):
|
||||
language = 'ja'
|
||||
encoding = 'utf-8'
|
||||
feeds = [(u'engadget', u'http://japanese.engadget.com/rss.xml')]
|
||||
|
||||
remove_tags_before = dict(name="div", attrs={'id':"content_wrap"})
|
||||
remove_tags_after = dict(name='h3', attrs={'id':'addcomments'})
|
||||
|
54
resources/recipes/explosm.recipe
Normal file
54
resources/recipes/explosm.recipe
Normal file
@ -0,0 +1,54 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
import re
|
||||
|
||||
class Explosm(BasicNewsRecipe):
|
||||
title = u'Explosm Rotated'
|
||||
__author__ = 'Andromeda Rabbit'
|
||||
description = 'Explosm'
|
||||
language = 'en'
|
||||
use_embedded_content = False
|
||||
no_stylesheets = True
|
||||
oldest_article = 24
|
||||
remove_javascript = True
|
||||
remove_empty_feeds = True
|
||||
max_articles_per_feed = 10
|
||||
|
||||
feeds = [
|
||||
(u'Explosm Feed', u'http://feeds.feedburner.com/Explosm')
|
||||
]
|
||||
|
||||
#match_regexps = [r'http://www.explosm.net/comics/.*']
|
||||
|
||||
keep_only_tags = [dict(name='img', attrs={'alt':'Cyanide and Happiness, a daily webcomic'})]
|
||||
remove_tags = [dict(name='div'), dict(name='span'), dict(name='table'), dict(name='br'), dict(name='nobr'), dict(name='a'), dict(name='b')]
|
||||
|
||||
extra_css = '''
|
||||
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
|
||||
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
|
||||
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
||||
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}'''
|
||||
|
||||
def get_cover_url(self):
|
||||
return 'http://cdn.shopify.com/s/files/1/0059/1872/products/cyanidetitle_large.jpg?1295846286'
|
||||
|
||||
def parse_feeds(self):
|
||||
feeds = BasicNewsRecipe.parse_feeds(self)
|
||||
|
||||
for curfeed in feeds:
|
||||
delList = []
|
||||
for a,curarticle in enumerate(curfeed.articles):
|
||||
if re.search(r'http://www.explosm.net/comics', curarticle.url) == None:
|
||||
delList.append(curarticle)
|
||||
if len(delList)>0:
|
||||
for d in delList:
|
||||
index = curfeed.articles.index(d)
|
||||
curfeed.articles[index:index+1] = []
|
||||
|
||||
return feeds
|
||||
|
||||
def skip_ad_pages(self, soup):
|
||||
# Skip ad pages served before actual article
|
||||
skip_tag = soup.find(name='img', attrs={'alt':'Cyanide and Happiness, a daily webcomic'})
|
||||
if skip_tag is None:
|
||||
return soup
|
||||
return None
|
@ -12,7 +12,7 @@ class General(BasicNewsRecipe):
|
||||
title = 'freeway.com.uy'
|
||||
__author__ = 'Gustavo Azambuja'
|
||||
description = 'Revista Freeway, Montevideo, Uruguay'
|
||||
language = 'es'
|
||||
language = 'es_UY'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
use_embedded_content = False
|
||||
recursion = 1
|
||||
|
@ -20,7 +20,7 @@ class Granma(BasicNewsRecipe):
|
||||
use_embedded_content = False
|
||||
encoding = 'cp1252'
|
||||
cover_url = 'http://www.granma.cubaweb.cu/imagenes/granweb229d.jpg'
|
||||
language = 'es'
|
||||
language = 'es_CU'
|
||||
|
||||
remove_javascript = True
|
||||
|
||||
|
@ -18,7 +18,7 @@ class iEco(BasicNewsRecipe):
|
||||
encoding = 'utf-8'
|
||||
publisher = 'Grupo Clarin'
|
||||
category = 'news, economia, mercados, bolsa de valores, finanzas, empresas, negocios, empleos, emprendedores, marketinguniversidades, tecnologia, agronegocios, noticias, informacion'
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
cover_url = 'http://www.ieco.clarin.com/static2/images/Tapa-PDF.gif'
|
||||
extra_css = ' #bd{font-family: sans-serif} '
|
||||
|
||||
|
@ -16,7 +16,7 @@ class Infobae(BasicNewsRecipe):
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
encoding = 'cp1252'
|
||||
masthead_url = 'http://www.infobae.com/imgs/header/header.gif'
|
||||
remove_javascript = True
|
||||
|
@ -20,7 +20,7 @@ class Juventudrebelde(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
encoding = 'cp1252'
|
||||
language = 'es'
|
||||
language = 'es_CU'
|
||||
|
||||
cover_url = strftime('http://www.juventudrebelde.cu/UserFiles/File/impreso/iportada-%Y-%m-%d.jpg')
|
||||
remove_javascript = True
|
||||
|
@ -50,4 +50,4 @@ class LaCuarta(BasicNewsRecipe):
|
||||
feeds = [(u'Noticias', u'http://lacuarta.cl/app/rss?sc=TEFDVUFSVEE=')]
|
||||
|
||||
|
||||
language = 'es'
|
||||
language = 'es_CL'
|
||||
|
@ -12,7 +12,7 @@ class General(BasicNewsRecipe):
|
||||
title = 'La Diaria'
|
||||
__author__ = 'Gustavo Azambuja'
|
||||
description = 'Noticias de Uruguay'
|
||||
language = 'es'
|
||||
language = 'es_UY'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
use_embedded_content = False
|
||||
recursion = 5
|
||||
|
@ -19,7 +19,7 @@ class LaJornada_mx(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
encoding = 'utf8'
|
||||
use_embedded_content = False
|
||||
language = 'es'
|
||||
language = 'es_MX'
|
||||
remove_empty_feeds = True
|
||||
cover_url = strftime("http://www.jornada.unam.mx/%Y/%m/%d/portada.pdf")
|
||||
masthead_url = 'http://www.jornada.unam.mx/v7.0/imagenes/la-jornada-trans.png'
|
||||
|
@ -18,7 +18,7 @@ class LaRazon_Bol(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
encoding = 'cp1252'
|
||||
use_embedded_content = False
|
||||
language = 'es'
|
||||
language = 'es_BO'
|
||||
publication_type = 'newspaper'
|
||||
delay = 1
|
||||
remove_empty_feeds = True
|
||||
|
@ -19,7 +19,7 @@ class LaSegunda(BasicNewsRecipe):
|
||||
encoding = 'cp1252'
|
||||
masthead_url = 'http://www.lasegunda.com/imagenes/logotipo_lasegunda_Oli.gif'
|
||||
remove_empty_feeds = True
|
||||
language = 'es'
|
||||
language = 'es_CL'
|
||||
extra_css = ' .titulonegritastop{font-size: xx-large; font-weight: bold} '
|
||||
|
||||
conversion_options = {
|
||||
|
@ -19,7 +19,7 @@ class LaMujerDeMiVida(BasicNewsRecipe):
|
||||
encoding = 'cp1252'
|
||||
publisher = 'La Mujer de mi Vida'
|
||||
category = 'literatura, critica, arte, ensayos'
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
|
||||
INDEX = 'http://www.lamujerdemivida.com.ar/'
|
||||
html2lrf_options = [
|
||||
|
@ -16,7 +16,7 @@ class Lanacion(BasicNewsRecipe):
|
||||
max_articles_per_feed = 100
|
||||
use_embedded_content = False
|
||||
no_stylesheets = True
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
publication_type = 'newspaper'
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.lanacion.com.ar/imgs/layout/logos/ln341x47.gif'
|
||||
|
@ -51,4 +51,4 @@ class LaNacionChile(BasicNewsRecipe):
|
||||
del item['style']
|
||||
return soup
|
||||
|
||||
language = 'es'
|
||||
language = 'es_CL'
|
||||
|
@ -21,7 +21,7 @@ class LaPrensa(BasicNewsRecipe):
|
||||
encoding = 'cp1252'
|
||||
# cover_url = 'http://www.laprensa.com.ar/imgs/logo.gif'
|
||||
remove_javascript = True
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
lang = 'es'
|
||||
|
||||
html2lrf_options = [
|
||||
|
@ -21,7 +21,7 @@ class LaPrensaHn(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
encoding = 'utf-8'
|
||||
language = 'es'
|
||||
language = 'es_HN'
|
||||
|
||||
lang = 'es-HN'
|
||||
direction = 'ltr'
|
||||
|
@ -22,7 +22,7 @@ class LaPrensa_ni(BasicNewsRecipe):
|
||||
use_embedded_content = False
|
||||
encoding = 'cp1252'
|
||||
remove_javascript = True
|
||||
language = 'es'
|
||||
language = 'es_NI'
|
||||
|
||||
months_es = ['enero','febrero','marzo','abril','mayo','junio','julio','agosto','septiembre','octubre','noviembre','diciembre']
|
||||
current_month = months_es[datetime.date.today().month - 1]
|
||||
|
@ -21,7 +21,7 @@ class LaTribuna(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
encoding = 'utf-8'
|
||||
language = 'es'
|
||||
language = 'es_HN'
|
||||
|
||||
lang = 'es-HN'
|
||||
direction = 'ltr'
|
||||
|
@ -9,6 +9,8 @@ __description__ = 'Canadian Paper '
|
||||
http://www.ledevoir.com/
|
||||
'''
|
||||
|
||||
import re
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class ledevoir(BasicNewsRecipe):
|
||||
@ -32,6 +34,8 @@ class ledevoir(BasicNewsRecipe):
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
|
||||
preprocess_regexps = [(re.compile(r'(title|alt)=".*?>.*?"', re.DOTALL), lambda m: '')]
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'id':'article'}),
|
||||
dict(name='ul', attrs={'id':'ariane'})
|
||||
|
@ -18,7 +18,7 @@ class LosTiempos_Bol(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
encoding = 'cp1252'
|
||||
use_embedded_content = False
|
||||
language = 'es'
|
||||
language = 'es_BO'
|
||||
publication_type = 'newspaper'
|
||||
delay = 1
|
||||
remove_empty_feeds = True
|
||||
|
@ -12,7 +12,7 @@ import datetime
|
||||
class Milenio(BasicNewsRecipe):
|
||||
title = u'Milenio-diario'
|
||||
__author__ = 'Bmsleight'
|
||||
language = 'es'
|
||||
language = 'es_MX'
|
||||
description = 'Milenio-diario'
|
||||
oldest_article = 10
|
||||
max_articles_per_feed = 100
|
||||
|
@ -20,7 +20,7 @@ class MiradasAlSur(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
encoding = 'utf-8'
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
|
||||
lang = 'es-AR'
|
||||
direction = 'ltr'
|
||||
|
@ -12,7 +12,7 @@ class Noticias(BasicNewsRecipe):
|
||||
title = 'Montevideo COMM'
|
||||
__author__ = 'Gustavo Azambuja'
|
||||
description = 'Noticias de Uruguay'
|
||||
language = 'es'
|
||||
language = 'es_UY'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
use_embedded_content = False
|
||||
recursion = 5
|
||||
|
@ -20,7 +20,7 @@ class Newsweek_Argentina(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
encoding = 'utf-8'
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
|
||||
lang = 'es-AR'
|
||||
direction = 'ltr'
|
||||
|
@ -12,7 +12,7 @@ class Noticias(BasicNewsRecipe):
|
||||
title = 'Observa Digital'
|
||||
__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
|
||||
description = 'Noticias desde Uruguay'
|
||||
language = 'es'
|
||||
language = 'es_UY'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
use_embedded_content = False
|
||||
recursion = 5
|
||||
|
@ -19,7 +19,7 @@ class Pagina12(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
encoding = 'cp1252'
|
||||
use_embedded_content = False
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
remove_empty_feeds = True
|
||||
publication_type = 'newspaper'
|
||||
masthead_url = 'http://www.pagina12.com.ar/commons/imgs/logo-home.gif'
|
||||
|
@ -17,7 +17,7 @@ class Perfil(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
encoding = 'cp1252'
|
||||
use_embedded_content = False
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.perfil.com/export/sites/diarioperfil/arte/10/logo_perfilcom_mm.gif'
|
||||
extra_css = """
|
||||
|
@ -13,7 +13,7 @@ class Reptantes(BasicNewsRecipe):
|
||||
description = u"cada vez que te haces acupuntura, tu muñeco vudú sufre en algún lado"
|
||||
oldest_article = 130
|
||||
max_articles_per_feed = 100
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
encoding = 'utf-8'
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
|
@ -12,7 +12,7 @@ class Noticias(BasicNewsRecipe):
|
||||
title = 'Revista Bla'
|
||||
__author__ = 'Gustavo Azambuja'
|
||||
description = 'Moda | Uruguay'
|
||||
language = 'es'
|
||||
language = 'es_UY'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
use_embedded_content = False
|
||||
recursion = 5
|
||||
|
@ -20,7 +20,7 @@ class Veintitres(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
encoding = 'utf-8'
|
||||
language = 'es'
|
||||
language = 'es_AR'
|
||||
|
||||
lang = 'es-AR'
|
||||
direction = 'ltr'
|
||||
|
@ -1,6 +1,6 @@
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>'
|
||||
|
||||
'''
|
||||
vijesti.me
|
||||
@ -18,12 +18,16 @@ class Vijesti(BasicNewsRecipe):
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 150
|
||||
no_stylesheets = True
|
||||
encoding = 'cp1250'
|
||||
encoding = 'utf8'
|
||||
use_embedded_content = False
|
||||
language = 'sr'
|
||||
publication_type = 'newspaper'
|
||||
masthead_url = 'http://www.vijesti.me/img/logo.gif'
|
||||
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
|
||||
extra_css = """
|
||||
@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
|
||||
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
|
||||
body{font-family: Georgia,"Times New Roman",Times,serif1,serif}
|
||||
.articledescription,.article,.chapter{font-family: sans1, sans-serif}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
@ -34,11 +38,11 @@ class Vijesti(BasicNewsRecipe):
|
||||
|
||||
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'mainnews'})]
|
||||
keep_only_tags = [dict(name='div', attrs={'id':['article_intro_text','article_text']})]
|
||||
|
||||
remove_tags = [dict(name=['object','link','embed','form'])]
|
||||
|
||||
feeds = [(u'Sve vijesti', u'http://www.vijesti.me/rss.php' )]
|
||||
feeds = [(u'Sve vijesti', u'http://www.vijesti.me/rss/' )]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
return self.adeify_images(soup)
|
||||
|
@ -360,6 +360,9 @@ class LinuxFreeze(Command):
|
||||
def main():
|
||||
try:
|
||||
sys.argv[0] = sys.calibre_basename
|
||||
dfv = os.environ.get('CALIBRE_DEVELOP_FROM', None)
|
||||
if dfv and os.path.exists(dfv):
|
||||
sys.path.insert(0, os.path.abspath(dfv))
|
||||
set_default_encoding()
|
||||
set_helper()
|
||||
set_qt_plugin_path()
|
||||
|
@ -21,6 +21,7 @@ from calibre.devices.usbms.driver import USBMS
|
||||
class EB600(USBMS):
|
||||
|
||||
name = 'Netronix EB600 Device Interface'
|
||||
gui_name = 'Netronix EB600'
|
||||
description = _('Communicate with the EB600 eBook reader.')
|
||||
author = 'Kovid Goyal'
|
||||
supported_platforms = ['windows', 'osx', 'linux']
|
||||
|
@ -53,7 +53,7 @@ def find_pages(dir, sort_on_mtime=False, verbose=False):
|
||||
prints('\t'+'\n\t'.join([os.path.basename(p) for p in pages]))
|
||||
return pages
|
||||
|
||||
class PageProcessor(list):
|
||||
class PageProcessor(list): # {{{
|
||||
'''
|
||||
Contains the actual image rendering logic. See :method:`render` and
|
||||
:method:`process_pages`.
|
||||
@ -111,6 +111,13 @@ class PageProcessor(list):
|
||||
|
||||
SCRWIDTH, SCRHEIGHT = self.opts.output_profile.comic_screen_size
|
||||
|
||||
try:
|
||||
if self.opts.comic_image_size:
|
||||
SCRWIDTH, SCRHEIGHT = map(int, [x.strip() for x in
|
||||
self.opts.comic_image_size.split('x')])
|
||||
except:
|
||||
pass # Ignore
|
||||
|
||||
if self.opts.keep_aspect_ratio:
|
||||
# Preserve the aspect ratio by adding border
|
||||
aspect = float(sizex) / float(sizey)
|
||||
@ -170,6 +177,7 @@ class PageProcessor(list):
|
||||
dest = dest[:-1]
|
||||
os.rename(dest+'8', dest)
|
||||
self.append(dest)
|
||||
# }}}
|
||||
|
||||
def render_pages(tasks, dest, opts, notification=lambda x, y: x):
|
||||
'''
|
||||
@ -291,7 +299,11 @@ class ComicInput(InputFormatPlugin):
|
||||
OptionRecommendation(name='no_process', recommended_value=False,
|
||||
help=_("Apply no processing to the image")),
|
||||
OptionRecommendation(name='dont_grayscale', recommended_value=False,
|
||||
help=_('Do not convert the image to grayscale (black and white)'))
|
||||
help=_('Do not convert the image to grayscale (black and white)')),
|
||||
OptionRecommendation(name='comic_image_size', recommended_value=None,
|
||||
help=_('Specify the image size as widthxheight pixels. Normally,'
|
||||
' an image size is automatically calculated from the output '
|
||||
'profile, this option overrides it.')),
|
||||
])
|
||||
|
||||
recommendations = set([
|
||||
|
@ -39,12 +39,15 @@ class LITInput(InputFormatPlugin):
|
||||
pre = body[0]
|
||||
from calibre.ebooks.txt.processor import convert_basic, preserve_spaces, \
|
||||
separate_paragraphs_single_line
|
||||
from calibre.ebooks.chardet import xml_to_unicode
|
||||
from lxml import etree
|
||||
import copy
|
||||
html = separate_paragraphs_single_line(pre.text)
|
||||
html = preserve_spaces(html)
|
||||
html = convert_basic(html).replace('<html>',
|
||||
'<html xmlns="%s">'%XHTML_NS)
|
||||
html = xml_to_unicode(html, strip_encoding_pats=True,
|
||||
resolve_entities=True)[0]
|
||||
root = etree.fromstring(html)
|
||||
body = XPath('//h:body')(root)
|
||||
pre.tag = XHTML('div')
|
||||
|
@ -488,7 +488,7 @@ class MobiReader(object):
|
||||
|
||||
|
||||
def remove_random_bytes(self, html):
|
||||
return re.sub('\x14|\x15|\x19|\x1c|\x1d|\xef|\x12|\x13|\xec|\x08',
|
||||
return re.sub('\x14|\x15|\x19|\x1c|\x1d|\xef|\x12|\x13|\xec|\x08|\x01|\x02|\x03|\x04|\x05|\x06|\x07',
|
||||
'', html)
|
||||
|
||||
def ensure_unit(self, raw, unit='px'):
|
||||
|
@ -83,6 +83,7 @@ class RTFInput(InputFormatPlugin):
|
||||
os.mkdir(debug_dir)
|
||||
debug_dir = 'rtfdebug'
|
||||
run_lev = 4
|
||||
self.log('Running RTFParser in debug mode')
|
||||
except:
|
||||
pass
|
||||
parser = ParseRtf(
|
||||
@ -230,22 +231,6 @@ class RTFInput(InputFormatPlugin):
|
||||
with open('styles.css', 'ab') as f:
|
||||
f.write(css)
|
||||
|
||||
# def preprocess(self, fname):
|
||||
# self.log('\tPreprocessing to convert unicode characters')
|
||||
# try:
|
||||
# data = open(fname, 'rb').read()
|
||||
# from calibre.ebooks.rtf.preprocess import RtfTokenizer, RtfTokenParser
|
||||
# tokenizer = RtfTokenizer(data)
|
||||
# tokens = RtfTokenParser(tokenizer.tokens)
|
||||
# data = tokens.toRTF()
|
||||
# fname = 'preprocessed.rtf'
|
||||
# with open(fname, 'wb') as f:
|
||||
# f.write(data)
|
||||
# except:
|
||||
# self.log.exception(
|
||||
# 'Failed to preprocess RTF to convert unicode sequences, ignoring...')
|
||||
# return fname
|
||||
|
||||
def convert_borders(self, doc):
|
||||
border_styles = []
|
||||
style_map = {}
|
||||
@ -280,8 +265,6 @@ class RTFInput(InputFormatPlugin):
|
||||
self.opts = options
|
||||
self.log = log
|
||||
self.log('Converting RTF to XML...')
|
||||
#Name of the preprocesssed RTF file
|
||||
# fname = self.preprocess(stream.name)
|
||||
try:
|
||||
xml = self.generate_xml(stream.name)
|
||||
except RtfInvalidCodeException, e:
|
||||
@ -335,3 +318,4 @@ class RTFInput(InputFormatPlugin):
|
||||
opf.render(open('metadata.opf', 'wb'))
|
||||
return os.path.abspath('metadata.opf')
|
||||
|
||||
|
||||
|
@ -24,14 +24,15 @@ from calibre.utils.magick.draw import save_cover_data_to, identify_data
|
||||
TAGS = {
|
||||
'b': '\\b',
|
||||
'del': '\\deleted',
|
||||
'h1': '\\b \\par \\pard \\hyphpar',
|
||||
'h2': '\\b \\par \\pard \\hyphpar',
|
||||
'h3': '\\b \\par \\pard \\hyphpar',
|
||||
'h4': '\\b \\par \\pard \\hyphpar',
|
||||
'h5': '\\b \\par \\pard \\hyphpar',
|
||||
'h6': '\\b \\par \\pard \\hyphpar',
|
||||
'li': '\\par \\pard \\hyphpar \t',
|
||||
'p': '\\par \\pard \\hyphpar \t',
|
||||
'h1': '\\s1 \\afs32',
|
||||
'h2': '\\s2 \\afs28',
|
||||
'h3': '\\s3 \\afs28',
|
||||
'h4': '\\s4 \\afs23',
|
||||
'h5': '\\s5 \\afs23',
|
||||
'h6': '\\s6 \\afs21',
|
||||
'i': '\\i',
|
||||
'li': '\t',
|
||||
'p': '\t',
|
||||
'sub': '\\sub',
|
||||
'sup': '\\super',
|
||||
'u': '\\ul',
|
||||
@ -39,15 +40,9 @@ TAGS = {
|
||||
|
||||
SINGLE_TAGS = {
|
||||
'br': '\n{\\line }\n',
|
||||
'div': '\n{\\line }\n',
|
||||
}
|
||||
|
||||
SINGLE_TAGS_END = {
|
||||
'div': '\n{\\line }\n',
|
||||
}
|
||||
|
||||
STYLES = [
|
||||
('display', {'block': '\\par \\pard \\hyphpar'}),
|
||||
('font-weight', {'bold': '\\b', 'bolder': '\\b'}),
|
||||
('font-style', {'italic': '\\i'}),
|
||||
('text-align', {'center': '\\qc', 'left': '\\ql', 'right': '\\qr'}),
|
||||
@ -55,6 +50,7 @@ STYLES = [
|
||||
]
|
||||
|
||||
BLOCK_TAGS = [
|
||||
'div',
|
||||
'p',
|
||||
'h1',
|
||||
'h2',
|
||||
@ -112,14 +108,16 @@ class RTFMLizer(object):
|
||||
stylizer = Stylizer(item.data, item.href, self.oeb_book,
|
||||
self.opts, self.opts.output_profile)
|
||||
output += self.dump_text(item.data.find(XHTML('body')), stylizer)
|
||||
output += '{\\page } '
|
||||
output += '{\\page }'
|
||||
for item in self.oeb_book.spine:
|
||||
self.log.debug('Converting %s to RTF markup...' % item.href)
|
||||
content = unicode(etree.tostring(item.data, encoding=unicode))
|
||||
content = self.remove_newlines(content)
|
||||
content = self.remove_tabs(content)
|
||||
content = etree.fromstring(content)
|
||||
stylizer = Stylizer(content, item.href, self.oeb_book, self.opts, self.opts.output_profile)
|
||||
output += self.dump_text(content.find(XHTML('body')), stylizer)
|
||||
output += '{\\page }'
|
||||
output += self.footer()
|
||||
output = self.insert_images(output)
|
||||
output = self.clean_text(output)
|
||||
@ -134,8 +132,23 @@ class RTFMLizer(object):
|
||||
|
||||
return text
|
||||
|
||||
def remove_tabs(self, text):
|
||||
self.log.debug('\Replace tabs with space for processing...')
|
||||
text = text.replace('\t', ' ')
|
||||
|
||||
return text
|
||||
|
||||
def header(self):
|
||||
return u'{\\rtf1{\\info{\\title %s}{\\author %s}}\\ansi\\ansicpg1252\\deff0\\deflang1033' % (self.oeb_book.metadata.title[0].value, authors_to_string([x.value for x in self.oeb_book.metadata.creator]))
|
||||
header = u'{\\rtf1{\\info{\\title %s}{\\author %s}}\\ansi\\ansicpg1252\\deff0\\deflang1033\n' % (self.oeb_book.metadata.title[0].value, authors_to_string([x.value for x in self.oeb_book.metadata.creator]))
|
||||
return header + \
|
||||
'{\\fonttbl{\\f0\\froman\\fprq2\\fcharset128 Times New Roman;}{\\f1\\froman\\fprq2\\fcharset128 Times New Roman;}{\\f2\\fswiss\\fprq2\\fcharset128 Arial;}{\\f3\\fnil\\fprq2\\fcharset128 Arial;}{\\f4\\fnil\\fprq2\\fcharset128 MS Mincho;}{\\f5\\fnil\\fprq2\\fcharset128 Tahoma;}{\\f6\\fnil\\fprq0\\fcharset128 Tahoma;}}\n' \
|
||||
'{\\stylesheet{\\ql \\li0\\ri0\\nowidctlpar\\wrapdefault\\faauto\\rin0\\lin0\\itap0 \\rtlch\\fcs1 \\af25\\afs24\\alang1033 \\ltrch\\fcs0 \\fs24\\lang1033\\langfe255\\cgrid\\langnp1033\\langfenp255 \\snext0 Normal;}\n' \
|
||||
'{\\s1\\ql \\li0\\ri0\\sb240\\sa120\\keepn\\nowidctlpar\\wrapdefault\\faauto\\outlinelevel0\\rin0\\lin0\\itap0 \\rtlch\\fcs1 \\ab\\af0\\afs32\\alang1033 \\ltrch\\fcs0 \\b\\fs32\\lang1033\\langfe255\\loch\\f1\\hich\\af1\\dbch\\af26\\cgrid\\langnp1033\\langfenp255 \\sbasedon15 \\snext16 \\slink21 heading 1;}\n' \
|
||||
'{\\s2\\ql \\li0\\ri0\\sb240\\sa120\\keepn\\nowidctlpar\\wrapdefault\\faauto\\outlinelevel1\\rin0\\lin0\\itap0 \\rtlch\\fcs1 \\ab\\ai\\af0\\afs28\\alang1033 \\ltrch\\fcs0 \\b\\i\\fs28\\lang1033\\langfe255\\loch\\f1\\hich\\af1\\dbch\\af26\\cgrid\\langnp1033\\langfenp255 \\sbasedon15 \\snext16 \\slink22 heading 2;}\n' \
|
||||
'{\\s3\\ql \\li0\\ri0\\sb240\\sa120\\keepn\\nowidctlpar\\wrapdefault\\faauto\\outlinelevel2\\rin0\\lin0\\itap0 \\rtlch\\fcs1 \\ab\\af0\\afs28\\alang1033 \\ltrch\\fcs0 \\b\\fs28\\lang1033\\langfe255\\loch\\f1\\hich\\af1\\dbch\\af26\\cgrid\\langnp1033\\langfenp255 \\sbasedon15 \\snext16 \\slink23 heading 3;}\n' \
|
||||
'{\\s4\\ql \\li0\\ri0\\sb240\\sa120\\keepn\\nowidctlpar\\wrapdefault\\faauto\\outlinelevel3\\rin0\\lin0\\itap0 \\rtlch\\fcs1 \\ab\\ai\\af0\\afs23\\alang1033 \\ltrch\\fcs0\\b\\i\\fs23\\lang1033\\langfe255\\loch\\f1\\hich\\af1\\dbch\\af26\\cgrid\\langnp1033\\langfenp255 \\sbasedon15 \\snext16 \\slink24 heading 4;}\n' \
|
||||
'{\\s5\\ql \\li0\\ri0\\sb240\\sa120\\keepn\\nowidctlpar\\wrapdefault\\faauto\\outlinelevel4\\rin0\\lin0\\itap0 \\rtlch\\fcs1 \\ab\\af0\\afs23\\alang1033 \\ltrch\\fcs0 \\b\\fs23\\lang1033\\langfe255\\loch\\f1\\hich\\af1\\dbch\\af26\\cgrid\\langnp1033\\langfenp255 \\sbasedon15 \\snext16 \\slink25 heading 5;}\n' \
|
||||
'{\\s6\\ql \\li0\\ri0\\sb240\\sa120\\keepn\\nowidctlpar\\wrapdefault\\faauto\\outlinelevel5\\rin0\\lin0\\itap0 \\rtlch\\fcs1 \\ab\\af0\\afs21\\alang1033 \\ltrch\\fcs0 \\b\\fs21\\lang1033\\langfe255\\loch\\f1\\hich\\af1\\dbch\\af26\\cgrid\\langnp1033\\langfenp255 \\sbasedon15 \\snext16 \\slink26 heading 6;}}\n'
|
||||
|
||||
def footer(self):
|
||||
return ' }'
|
||||
@ -170,19 +183,16 @@ class RTFMLizer(object):
|
||||
return (hex_string, width, height)
|
||||
|
||||
def clean_text(self, text):
|
||||
# Remove excess spaces at beginning and end of lines
|
||||
text = re.sub('(?m)^[ ]+', '', text)
|
||||
text = re.sub('(?m)[ ]+$', '', text)
|
||||
|
||||
# Remove excessive newlines
|
||||
#text = re.sub('%s{1,1}' % os.linesep, '%s%s' % (os.linesep, os.linesep), text)
|
||||
text = re.sub('%s{3,}' % os.linesep, '%s%s' % (os.linesep, os.linesep), text)
|
||||
|
||||
# Remove excessive spaces
|
||||
text = re.sub('[ ]{2,}', ' ', text)
|
||||
text = re.sub('\t{2,}', '\t', text)
|
||||
text = re.sub('\t ', '\t', text)
|
||||
|
||||
# Remove excessive line breaks
|
||||
text = re.sub(r'(\{\\line \}\s*){3,}', r'{\\line }{\\line }', text)
|
||||
#text = re.compile(r'(\{\\line \}\s*)+(?P<brackets>}*)\s*\{\\par').sub(lambda mo: r'%s{\\par' % mo.group('brackets'), text)
|
||||
|
||||
# Remove non-breaking spaces
|
||||
text = text.replace(u'\xa0', ' ')
|
||||
@ -222,7 +232,7 @@ class RTFMLizer(object):
|
||||
block_start = ''
|
||||
block_end = ''
|
||||
if 'block' not in tag_stack:
|
||||
block_start = '{\\par \\pard \\hyphpar '
|
||||
block_start = '{\\par\\pard\\hyphpar '
|
||||
block_end = '}'
|
||||
text += '%s SPECIAL_IMAGE-%s-REPLACE_ME %s' % (block_start, src, block_end)
|
||||
|
||||
@ -245,7 +255,7 @@ class RTFMLizer(object):
|
||||
tag_stack.append(style_tag)
|
||||
|
||||
# Proccess tags that contain text.
|
||||
if hasattr(elem, 'text') and elem.text != None and elem.text.strip() != '':
|
||||
if hasattr(elem, 'text') and elem.text:
|
||||
text += txt2rtf(elem.text)
|
||||
|
||||
for item in elem:
|
||||
@ -254,16 +264,15 @@ class RTFMLizer(object):
|
||||
for i in range(0, tag_count):
|
||||
end_tag = tag_stack.pop()
|
||||
if end_tag != 'block':
|
||||
if tag in BLOCK_TAGS:
|
||||
text += u'\\par\\pard\\plain\\hyphpar}'
|
||||
else:
|
||||
text += u'}'
|
||||
|
||||
single_tag_end = SINGLE_TAGS_END.get(tag, None)
|
||||
if single_tag_end:
|
||||
text += single_tag_end
|
||||
|
||||
if hasattr(elem, 'tail') and elem.tail != None and elem.tail.strip() != '':
|
||||
if hasattr(elem, 'tail') and elem.tail:
|
||||
if 'block' in tag_stack:
|
||||
text += '%s' % txt2rtf(elem.tail)
|
||||
else:
|
||||
text += '{\\par \\pard \\hyphpar %s}' % txt2rtf(elem.tail)
|
||||
text += '{\\par\\pard\\hyphpar %s}' % txt2rtf(elem.tail)
|
||||
|
||||
return text
|
||||
|
@ -238,6 +238,8 @@ class ParseRtf:
|
||||
bug_handler = RtfInvalidCodeException,
|
||||
)
|
||||
enc = 'cp' + encode_obj.get_codepage()
|
||||
if enc == 'cp10000':
|
||||
enc = 'mac_roman'
|
||||
msg = 'Exception in token processing'
|
||||
if check_encoding_obj.check_encoding(self.__file, enc):
|
||||
file_name = self.__file if isinstance(self.__file, str) \
|
||||
|
@ -16,7 +16,9 @@
|
||||
# #
|
||||
#########################################################################
|
||||
import sys, os, tempfile, re
|
||||
|
||||
from calibre.ebooks.rtf2xml import copy
|
||||
|
||||
class Colors:
|
||||
"""
|
||||
Change lines with color info from color numbers to the actual color names.
|
||||
@ -40,8 +42,10 @@ class Colors:
|
||||
self.__file = in_file
|
||||
self.__copy = copy
|
||||
self.__bug_handler = bug_handler
|
||||
self.__line = 0
|
||||
self.__write_to = tempfile.mktemp()
|
||||
self.__run_level = run_level
|
||||
|
||||
def __initiate_values(self):
|
||||
"""
|
||||
Initiate all values.
|
||||
@ -61,6 +65,7 @@ class Colors:
|
||||
self.__color_num = 1
|
||||
self.__line_color_exp = re.compile(r'bdr-color_:(\d+)')
|
||||
# cw<bd<bor-par-to<nu<bdr-hair__|bdr-li-wid:0.50|bdr-sp-wid:1.00|bdr-color_:2
|
||||
|
||||
def __before_color_func(self, line):
|
||||
"""
|
||||
Requires:
|
||||
@ -76,6 +81,7 @@ class Colors:
|
||||
if self.__token_info == 'mi<mk<clrtbl-beg':
|
||||
self.__state = 'in_color_table'
|
||||
self.__write_obj.write(line)
|
||||
|
||||
def __default_color_func(self, line):
|
||||
"""
|
||||
Requires:
|
||||
@ -87,6 +93,7 @@ class Colors:
|
||||
"""
|
||||
hex_num = line[-3:-1]
|
||||
self.__color_string += hex_num
|
||||
|
||||
def __blue_func(self, line):
|
||||
"""
|
||||
Requires:
|
||||
@ -109,6 +116,7 @@ class Colors:
|
||||
)
|
||||
self.__color_num += 1
|
||||
self.__color_string = '#'
|
||||
|
||||
def __in_color_func(self, line):
|
||||
"""
|
||||
Requires:
|
||||
@ -127,12 +135,13 @@ class Colors:
|
||||
self.__state = 'after_color_table'
|
||||
else:
|
||||
action = self.__state_dict.get(self.__token_info)
|
||||
if action == None:
|
||||
if action is None:
|
||||
sys.stderr.write('in module colors.py\n'
|
||||
'function is self.__in_color_func\n'
|
||||
'no action for %s' % self.__token_info
|
||||
)
|
||||
action(line)
|
||||
|
||||
def __after_color_func(self, line):
|
||||
"""
|
||||
Check the to see if it contains color info. If it does, extract the
|
||||
@ -180,6 +189,7 @@ class Colors:
|
||||
else:
|
||||
self.__write_obj.write(line)
|
||||
# cw<bd<bor-par-to<nu<bdr-hair__|bdr-li-wid:0.50|bdr-sp-wid:1.00|bdr-color_:2
|
||||
|
||||
def __sub_from_line_color(self, match_obj):
|
||||
num = match_obj.group(1)
|
||||
try:
|
||||
@ -191,25 +201,27 @@ class Colors:
|
||||
else:
|
||||
return 'bdr-color_:no-value'
|
||||
hex_num = self.__figure_num(num)
|
||||
return_value = 'bdr-color_:%s' % hex_num
|
||||
return return_value
|
||||
return 'bdr-color_:%s' % hex_num
|
||||
|
||||
def __figure_num(self, num):
|
||||
if num == 0:
|
||||
hex_num = 'false'
|
||||
else:
|
||||
hex_num = self.__color_dict.get(num)
|
||||
if hex_num == None:
|
||||
if self.__run_level > 3:
|
||||
msg = 'no value in self.__color_dict for key %s\n' % num
|
||||
raise self.__bug_hanlder, msg
|
||||
if hex_num == None:
|
||||
if hex_num is None:
|
||||
hex_num = '0'
|
||||
if self.__run_level > 5:
|
||||
msg = 'no value in self.__color_dict' \
|
||||
'for key %s at line %d\n' % (num, self.__line)
|
||||
raise self.__bug_handler, msg
|
||||
return hex_num
|
||||
|
||||
def __do_nothing_func(self, line):
|
||||
"""
|
||||
Bad RTF will have text in the color table
|
||||
"""
|
||||
pass
|
||||
|
||||
def convert_colors(self):
|
||||
"""
|
||||
Requires:
|
||||
@ -226,20 +238,16 @@ class Colors:
|
||||
info, and substitute the number with the hex number.
|
||||
"""
|
||||
self.__initiate_values()
|
||||
read_obj = open(self.__file, 'r')
|
||||
self.__write_obj = open(self.__write_to, 'w')
|
||||
line_to_read = 1
|
||||
while line_to_read:
|
||||
line_to_read = read_obj.readline()
|
||||
line = line_to_read
|
||||
with open(self.__file, 'r') as read_obj:
|
||||
with open(self.__write_to, 'w') as self.__write_obj:
|
||||
for line in read_obj:
|
||||
self.__line+=1
|
||||
self.__token_info = line[:16]
|
||||
action = self.__state_dict.get(self.__state)
|
||||
if action == None:
|
||||
sys.stderr.write('no no matching state in module fonts.py\n')
|
||||
if action is None:
|
||||
sys.stderr.write('no matching state in module fonts.py\n')
|
||||
sys.stderr.write(self.__state + '\n')
|
||||
action(line)
|
||||
read_obj.close()
|
||||
self.__write_obj.close()
|
||||
copy_obj = copy.Copy(bug_handler = self.__bug_handler)
|
||||
if self.__copy:
|
||||
copy_obj.copy_file(self.__write_to, "color.data")
|
||||
|
@ -33,13 +33,13 @@ class ConvertToTags:
|
||||
self.__copy = copy
|
||||
self.__dtd_path = dtd_path
|
||||
self.__no_dtd = no_dtd
|
||||
if encoding != 'mac_roman':
|
||||
self.__encoding = 'cp' + encoding
|
||||
else:
|
||||
if encoding == 'mac_roman':
|
||||
self.__encoding = 'mac_roman'
|
||||
self.__indent = indent
|
||||
self.__run_level = run_level
|
||||
self.__write_to = tempfile.mktemp()
|
||||
self.__convert_utf = False
|
||||
|
||||
def __initiate_values(self):
|
||||
"""
|
||||
@ -213,7 +213,8 @@ class ConvertToTags:
|
||||
if not check_encoding_obj.check_encoding(self.__file, verbose=False):
|
||||
self.__write_obj.write('<?xml version="1.0" encoding="US-ASCII" ?>')
|
||||
elif not check_encoding_obj.check_encoding(self.__file, self.__encoding):
|
||||
self.__write_obj.write('<?xml version="1.0" encoding="%s" ?>' % self.__encoding)
|
||||
self.__write_obj.write('<?xml version="1.0" encoding="UTF-8" ?>')
|
||||
self.__convert_utf = True
|
||||
else:
|
||||
self.__write_obj.write('<?xml version="1.0" encoding="US-ASCII" ?>')
|
||||
sys.stderr.write('Bad RTF encoding, revert to US-ASCII chars and'
|
||||
@ -253,7 +254,7 @@ class ConvertToTags:
|
||||
an empty tag function.
|
||||
"""
|
||||
self.__initiate_values()
|
||||
self.__write_obj = open(self.__write_to, 'w')
|
||||
with open(self.__write_to, 'w') as self.__write_obj:
|
||||
self.__write_dec()
|
||||
with open(self.__file, 'r') as read_obj:
|
||||
for line in read_obj:
|
||||
@ -262,6 +263,19 @@ class ConvertToTags:
|
||||
if action is not None:
|
||||
action(line)
|
||||
self.__write_obj.close()
|
||||
#convert all encodings to UTF8 to avoid unsupported encodings in lxml
|
||||
if self.__convert_utf:
|
||||
copy_obj = copy.Copy(bug_handler = self.__bug_handler)
|
||||
copy_obj.rename(self.__write_to, self.__file)
|
||||
with open(self.__file, 'r') as read_obj:
|
||||
with open(self.__write_to, 'w') as write_obj:
|
||||
file = read_obj.read()
|
||||
try:
|
||||
file = file.decode(self.__encoding)
|
||||
write_obj.write(file.encode('utf-8'))
|
||||
except:
|
||||
sys.stderr.write('Conversion to UTF-8 is not possible,'
|
||||
' encoding should be very carefully checked')
|
||||
copy_obj = copy.Copy(bug_handler = self.__bug_handler)
|
||||
if self.__copy:
|
||||
copy_obj.copy_file(self.__write_to, "convert_to_tags.data")
|
||||
|
@ -75,12 +75,16 @@ class DefaultEncoding:
|
||||
self._encoding()
|
||||
self.__datafetched = True
|
||||
code_page = 'ansicpg' + self.__code_page
|
||||
if self.__code_page == '10000':
|
||||
self.__code_page = 'mac_roman'
|
||||
return self.__platform, code_page, self.__default_num
|
||||
|
||||
def get_codepage(self):
|
||||
if not self.__datafetched:
|
||||
self._encoding()
|
||||
self.__datafetched = True
|
||||
if self.__code_page == '10000':
|
||||
self.__code_page = 'mac_roman'
|
||||
return self.__code_page
|
||||
|
||||
def get_platform(self):
|
||||
|
@ -16,7 +16,9 @@
|
||||
# #
|
||||
#########################################################################
|
||||
import sys, os, tempfile
|
||||
|
||||
from calibre.ebooks.rtf2xml import copy
|
||||
|
||||
class Fonts:
|
||||
"""
|
||||
Change lines with font info from font numbers to the actual font names.
|
||||
@ -45,6 +47,7 @@ class Fonts:
|
||||
self.__default_font_num = default_font_num
|
||||
self.__write_to = tempfile.mktemp()
|
||||
self.__run_level = run_level
|
||||
|
||||
def __initiate_values(self):
|
||||
"""
|
||||
Initiate all values.
|
||||
@ -67,6 +70,7 @@ class Fonts:
|
||||
self.__font_table = {}
|
||||
# individual font written
|
||||
self.__wrote_ind_font = 0
|
||||
|
||||
def __default_func(self, line):
|
||||
"""
|
||||
Requires:
|
||||
@ -79,6 +83,7 @@ class Fonts:
|
||||
if self.__token_info == 'mi<mk<fonttb-beg':
|
||||
self.__state = 'font_table'
|
||||
self.__write_obj.write(line)
|
||||
|
||||
def __font_table_func(self, line):
|
||||
"""
|
||||
Requires:
|
||||
@ -101,6 +106,7 @@ class Fonts:
|
||||
self.__font_num = self.__default_font_num
|
||||
self.__text_line = ''
|
||||
##self.__write_obj.write(line)
|
||||
|
||||
def __font_in_table_func(self, line):
|
||||
"""
|
||||
Requires:
|
||||
@ -138,6 +144,7 @@ class Fonts:
|
||||
elif self.__token_info == 'mi<mk<fonttb-end':
|
||||
self.__found_end_font_table_func()
|
||||
self.__state = 'after_font_table'
|
||||
|
||||
def __found_end_font_table_func(self):
|
||||
"""
|
||||
Required:
|
||||
@ -150,7 +157,8 @@ class Fonts:
|
||||
if not self.__wrote_ind_font:
|
||||
self.__write_obj.write(
|
||||
'mi<tg<empty-att_'
|
||||
'<font-in-table<name>Times<num>0\n' )
|
||||
'<font-in-table<name>Times<num>0\n')
|
||||
|
||||
def __after_font_table_func(self, line):
|
||||
"""
|
||||
Required:
|
||||
@ -169,7 +177,7 @@ class Fonts:
|
||||
if self.__token_info == 'cw<ci<font-style':
|
||||
font_num = line[20:-1]
|
||||
font_name = self.__font_table.get(font_num)
|
||||
if font_name == None:
|
||||
if font_name is None:
|
||||
if self.__run_level > 3:
|
||||
msg = 'no value for %s in self.__font_table\n' % font_num
|
||||
raise self.__bug_handler, msg
|
||||
@ -182,6 +190,7 @@ class Fonts:
|
||||
)
|
||||
else:
|
||||
self.__write_obj.write(line)
|
||||
|
||||
def convert_fonts(self):
|
||||
"""
|
||||
Required:
|
||||
@ -197,20 +206,15 @@ class Fonts:
|
||||
info. Substitute a font name for a font number.
|
||||
"""
|
||||
self.__initiate_values()
|
||||
read_obj = open(self.__file, 'r')
|
||||
self.__write_obj = open(self.__write_to, 'w')
|
||||
line_to_read = 1
|
||||
while line_to_read:
|
||||
line_to_read = read_obj.readline()
|
||||
line = line_to_read
|
||||
with open(self.__file, 'r') as read_obj:
|
||||
with open(self.__write_to, 'w') as self.__write_obj:
|
||||
for line in read_obj:
|
||||
self.__token_info = line[:16]
|
||||
action = self.__state_dict.get(self.__state)
|
||||
if action == None:
|
||||
sys.stderr.write('no no matching state in module fonts.py\n')
|
||||
sys.stderr.write(self.__state + '\n')
|
||||
if action is None:
|
||||
sys.stderr.write('no matching state in module fonts.py\n' \
|
||||
+ self.__state + '\n')
|
||||
action(line)
|
||||
read_obj.close()
|
||||
self.__write_obj.close()
|
||||
default_font_name = self.__font_table.get(self.__default_font_num)
|
||||
if not default_font_name:
|
||||
default_font_name = 'Not Defined'
|
||||
|
@ -43,7 +43,7 @@ class GetCharMap:
|
||||
def get_char_map(self, map):
|
||||
if map == 'ansicpg0':
|
||||
map = 'ansicpg1250'
|
||||
if map in ('ansicpg10000', '10000'):
|
||||
if map == 'ansicpg10000':
|
||||
map = 'mac_roman'
|
||||
found_map = False
|
||||
map_dict = {}
|
||||
|
@ -126,12 +126,6 @@ class Tokenize:
|
||||
tokens = re.split(self.__splitexp, input_file)
|
||||
#remove empty tokens and \n
|
||||
return filter(lambda x: len(x) > 0 and x != '\n', tokens)
|
||||
#input_file = re.sub(self.__utf_exp, self.__from_ms_to_utf8, input_file)
|
||||
# line = re.sub( self.__neg_utf_exp, self.__neg_unicode_func, line)
|
||||
# this is for older RTF
|
||||
#line = re.sub(self.__par_exp, '\\par ', line)
|
||||
#return filter(lambda x: len(x) > 0, \
|
||||
#(self.__remove_line.sub('', x) for x in tokens))
|
||||
|
||||
def __compile_expressions(self):
|
||||
SIMPLE_RPL = {
|
||||
@ -160,7 +154,7 @@ class Tokenize:
|
||||
}
|
||||
self.__replace_spchar = MReplace(SIMPLE_RPL)
|
||||
#add ;? in case of char following \u
|
||||
self.__ms_hex_exp = re.compile(r"\\\'([0-9a-fA-F]{2})") #r"\\\'(..)"
|
||||
self.__ms_hex_exp = re.compile(r"\\\'([0-9a-fA-F]{2})")
|
||||
self.__utf_exp = re.compile(r"\\u(-?\d{3,6}) ?")
|
||||
self.__bin_exp = re.compile(r"(?:\\bin(-?\d{0,10})[\n ]+)[01\n]+")
|
||||
#manage upr/ud situations
|
||||
@ -172,14 +166,21 @@ class Tokenize:
|
||||
self.__splitexp = re.compile(r"(\\[{}]|\n|\\[^\s\\{}&]+(?:[ \t\r\f\v])?)")
|
||||
#this is for old RTF
|
||||
self.__par_exp = re.compile(r'\\\n+')
|
||||
# self.__par_exp = re.compile(r'\\$')
|
||||
#handle cw using a digit as argument and without space as delimiter
|
||||
self.__cwdigit_exp = re.compile(r"(\\[a-zA-Z]+[\-0-9]+)([^0-9 \\]+)")
|
||||
#self.__bin_exp = re.compile(r"\\bin(-?\d{1,8}) {0,1}")
|
||||
#self.__utf_exp = re.compile(r"^\\u(-?\d{3,6})")
|
||||
#self.__splitexp = re.compile(r"(\\[\\{}]|{|}|\n|\\[^\s\\{}&]+(?:\s)?)")
|
||||
#self.__remove_line = re.compile(r'\n+')
|
||||
#self.__mixed_exp = re.compile(r"(\\[a-zA-Z]+\d+)(\D+)")
|
||||
##self.num_exp = re.compile(r"(\*|:|[a-zA-Z]+)(.*)")
|
||||
|
||||
def __correct_spliting(self, token):
|
||||
match_obj = re.search(self.__cwdigit_exp, token)
|
||||
if match_obj is None:
|
||||
return token
|
||||
else:
|
||||
return '%s\n%s' % (match_obj.group(1), match_obj.group(2))
|
||||
|
||||
def tokenize(self):
|
||||
"""Main class for handling other methods. Reads the file \
|
||||
, uses method self.sub_reg to make basic substitutions,\
|
||||
@ -195,6 +196,8 @@ class Tokenize:
|
||||
tokens = map(self.__unicode_process, tokens)
|
||||
#remove empty items created by removing \uc
|
||||
tokens = filter(lambda x: len(x) > 0, tokens)
|
||||
#handles bothersome cases
|
||||
tokens = map(self.__correct_spliting, tokens)
|
||||
|
||||
#write
|
||||
with open(self.__write_to, 'wb') as write_obj:
|
||||
@ -203,8 +206,6 @@ class Tokenize:
|
||||
copy_obj = copy.Copy(bug_handler = self.__bug_handler)
|
||||
if self.__copy:
|
||||
copy_obj.copy_file(self.__write_to, "tokenize.data")
|
||||
# if self.__out_file:
|
||||
# self.__file = self.__out_file
|
||||
copy_obj.rename(self.__write_to, self.__file)
|
||||
os.remove(self.__write_to)
|
||||
|
||||
|
@ -22,7 +22,7 @@ class PluginWidget(Widget, Ui_Form):
|
||||
['colors', 'dont_normalize', 'keep_aspect_ratio', 'right2left',
|
||||
'despeckle', 'no_sort', 'no_process', 'landscape',
|
||||
'dont_sharpen', 'disable_trim', 'wide', 'output_format',
|
||||
'dont_grayscale']
|
||||
'dont_grayscale', 'comic_image_size']
|
||||
)
|
||||
self.db, self.book_id = db, book_id
|
||||
for x in get_option('output_format').option.choices:
|
||||
|
@ -7,7 +7,7 @@
|
||||
<x>0</x>
|
||||
<y>0</y>
|
||||
<width>599</width>
|
||||
<height>345</height>
|
||||
<height>398</height>
|
||||
</rect>
|
||||
</property>
|
||||
<property name="windowTitle">
|
||||
@ -37,70 +37,70 @@
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="3" column="0">
|
||||
<item row="4" column="0">
|
||||
<widget class="QCheckBox" name="opt_dont_normalize">
|
||||
<property name="text">
|
||||
<string>Disable &normalize</string>
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="4" column="0">
|
||||
<item row="5" column="0">
|
||||
<widget class="QCheckBox" name="opt_keep_aspect_ratio">
|
||||
<property name="text">
|
||||
<string>Keep &aspect ratio</string>
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="5" column="0">
|
||||
<item row="6" column="0">
|
||||
<widget class="QCheckBox" name="opt_dont_sharpen">
|
||||
<property name="text">
|
||||
<string>Disable &Sharpening</string>
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="6" column="0">
|
||||
<item row="7" column="0">
|
||||
<widget class="QCheckBox" name="opt_disable_trim">
|
||||
<property name="text">
|
||||
<string>Disable &Trimming</string>
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="7" column="0">
|
||||
<item row="8" column="0">
|
||||
<widget class="QCheckBox" name="opt_wide">
|
||||
<property name="text">
|
||||
<string>&Wide</string>
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="8" column="0">
|
||||
<item row="9" column="0">
|
||||
<widget class="QCheckBox" name="opt_landscape">
|
||||
<property name="text">
|
||||
<string>&Landscape</string>
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="9" column="0">
|
||||
<item row="10" column="0">
|
||||
<widget class="QCheckBox" name="opt_right2left">
|
||||
<property name="text">
|
||||
<string>&Right to left</string>
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="10" column="0">
|
||||
<item row="11" column="0">
|
||||
<widget class="QCheckBox" name="opt_no_sort">
|
||||
<property name="text">
|
||||
<string>Don't so&rt</string>
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="11" column="0">
|
||||
<item row="12" column="0">
|
||||
<widget class="QCheckBox" name="opt_despeckle">
|
||||
<property name="text">
|
||||
<string>De&speckle</string>
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="13" column="0">
|
||||
<item row="14" column="0">
|
||||
<spacer name="verticalSpacer">
|
||||
<property name="orientation">
|
||||
<enum>Qt::Vertical</enum>
|
||||
@ -120,7 +120,7 @@
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="12" column="0">
|
||||
<item row="13" column="0">
|
||||
<widget class="QLabel" name="label">
|
||||
<property name="text">
|
||||
<string>&Output format:</string>
|
||||
@ -130,7 +130,7 @@
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="12" column="1">
|
||||
<item row="13" column="1">
|
||||
<widget class="QComboBox" name="opt_output_format"/>
|
||||
</item>
|
||||
<item row="1" column="0">
|
||||
@ -140,6 +140,19 @@
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="3" column="0">
|
||||
<widget class="QLabel" name="label_2">
|
||||
<property name="text">
|
||||
<string>Override image &size:</string>
|
||||
</property>
|
||||
<property name="buddy">
|
||||
<cstring>opt_comic_image_size</cstring>
|
||||
</property>
|
||||
</widget>
|
||||
</item>
|
||||
<item row="3" column="1">
|
||||
<widget class="QLineEdit" name="opt_comic_image_size"/>
|
||||
</item>
|
||||
</layout>
|
||||
</widget>
|
||||
<resources/>
|
||||
|
@ -687,7 +687,7 @@ class DeviceMixin(object): # {{{
|
||||
except:
|
||||
pass
|
||||
if not self.device_error_dialog.isVisible():
|
||||
self.device_error_dialog.setDetailedText(job.details)
|
||||
self.device_error_dialog.set_details(job.details)
|
||||
self.device_error_dialog.show()
|
||||
|
||||
# Device connected {{{
|
||||
@ -838,9 +838,9 @@ class DeviceMixin(object): # {{{
|
||||
format_count[f] = 1
|
||||
for f in self.device_manager.device.settings().format_map:
|
||||
if f in format_count.keys():
|
||||
formats.append((f, _('%i of %i Books' % (format_count[f], len(rows))), True if f in aval_out_formats else False))
|
||||
formats.append((f, _('%i of %i Books') % (format_count[f], len(rows))), True if f in aval_out_formats else False)
|
||||
elif f in aval_out_formats:
|
||||
formats.append((f, _('0 of %i Books' % len(rows)), True))
|
||||
formats.append((f, _('0 of %i Books') % len(rows)), True)
|
||||
d = ChooseFormatDeviceDialog(self, _('Choose format to send to device'), formats)
|
||||
if d.exec_() != QDialog.Accepted:
|
||||
return
|
||||
|
@ -7,7 +7,7 @@ import os, shutil
|
||||
|
||||
from PyQt4.Qt import QDialog, QVBoxLayout, QHBoxLayout, QTreeWidget, QLabel, \
|
||||
QPushButton, QDialogButtonBox, QApplication, QTreeWidgetItem, \
|
||||
QLineEdit, Qt, QProgressBar, QSize, QTimer
|
||||
QLineEdit, Qt, QProgressBar, QSize, QTimer, QIcon, QTextEdit
|
||||
|
||||
from calibre.gui2.dialogs.confirm_delete import confirm
|
||||
from calibre.library.check_library import CheckLibrary, CHECKS
|
||||
@ -16,7 +16,7 @@ from calibre import prints, as_unicode
|
||||
from calibre.ptempfile import PersistentTemporaryFile
|
||||
from calibre.library.sqlite import DBThread, OperationalError
|
||||
|
||||
class DBCheck(QDialog):
|
||||
class DBCheck(QDialog): # {{{
|
||||
|
||||
def __init__(self, parent, db):
|
||||
QDialog.__init__(self, parent)
|
||||
@ -74,6 +74,7 @@ class DBCheck(QDialog):
|
||||
self.reject()
|
||||
|
||||
def start_load(self):
|
||||
try:
|
||||
self.conn.close()
|
||||
self.pb.setMaximum(self.count)
|
||||
self.pb.setValue(0)
|
||||
@ -89,6 +90,11 @@ class DBCheck(QDialog):
|
||||
self.conn.commit()
|
||||
|
||||
QTimer.singleShot(0, self.do_one_load)
|
||||
except Exception, e:
|
||||
import traceback
|
||||
self.error = (as_unicode(e), traceback.format_exc())
|
||||
self.reject()
|
||||
|
||||
|
||||
def do_one_load(self):
|
||||
if self.rejected:
|
||||
@ -128,7 +134,7 @@ class DBCheck(QDialog):
|
||||
def reject(self):
|
||||
self.rejected = True
|
||||
QDialog.reject(self)
|
||||
|
||||
# }}}
|
||||
|
||||
class Item(QTreeWidgetItem):
|
||||
pass
|
||||
@ -140,9 +146,70 @@ class CheckLibraryDialog(QDialog):
|
||||
self.db = db
|
||||
|
||||
self.setWindowTitle(_('Check Library -- Problems Found'))
|
||||
self.setWindowIcon(QIcon(I('debug.png')))
|
||||
|
||||
self._layout = QVBoxLayout(self)
|
||||
self.setLayout(self._layout)
|
||||
self._tl = QHBoxLayout()
|
||||
self._layout = QVBoxLayout()
|
||||
self.setLayout(self._tl)
|
||||
self._tl.addLayout(self._layout)
|
||||
self.helpw = QTextEdit(self)
|
||||
self._tl.addWidget(self.helpw)
|
||||
self.helpw.setReadOnly(True)
|
||||
self.helpw.setText(_('''\
|
||||
<h1>Help</h1>
|
||||
|
||||
<p>calibre stores the list of your books and their metadata in a
|
||||
database. The actual book files and covers are stored as normal
|
||||
files in the calibre library folder. The database contains a list of the files
|
||||
and covers belonging to each book entry. This tool checks that the
|
||||
actual files in the library folder on your computer match the
|
||||
information in the database.</p>
|
||||
|
||||
<p>The result of each type of check is shown to the left. The various
|
||||
checks are:
|
||||
</p>
|
||||
<ul>
|
||||
<li><b>Invalid titles</b>: These are files and folders appearing
|
||||
in the library where books titles should, but that do not have the
|
||||
correct form to be a book title.</li>
|
||||
<li><b>Extra titles</b>: These are extra files in your calibre
|
||||
library that appear to be correctly-formed titles, but have no corresponding
|
||||
entries in the database</li>
|
||||
<li><b>Invalid authors</b>: These are files appearing
|
||||
in the library where only author folders should be.</li>
|
||||
<li><b>Extra authors</b>: These are folders in the
|
||||
calibre library that appear to be authors but that do not have entries
|
||||
in the database</li>
|
||||
<li><b>Missing book formats</b>: These are book formats that are in
|
||||
the database but have no corresponding format file in the book's folder.
|
||||
<li><b>Extra book formats</b>: These are book format files found in
|
||||
the book's folder but not in the database.
|
||||
<li><b>Unknown files in books</b>: These are extra files in the
|
||||
folder of each book that do not correspond to a known format or cover
|
||||
file.</li>
|
||||
<li><b>Missing cover files</b>: These represent books that are marked
|
||||
in the database as having covers but the actual cover files are
|
||||
missing.</li>
|
||||
<li><b>Cover files not in database</b>: These are books that have
|
||||
cover files but are marked as not having covers in the database.</li>
|
||||
<li><b>Folder raising exception</b>: These represent folders in the
|
||||
calibre library that could not be processed/understood by this
|
||||
tool.</li>
|
||||
</ul>
|
||||
|
||||
<p>There are two kinds of automatic fixes possible: <i>Delete
|
||||
marked</i> and <i>Fix marked</i>.</p>
|
||||
<p><i>Delete marked</i> is used to remove extra files/folders/covers that
|
||||
have no entries in the database. Check the box next to the item you want
|
||||
to delete. Use with caution.</p>
|
||||
<p><i>Fix marked</i> is applicable only to covers (the two lines marked
|
||||
'fixable'). In the case of missing cover files, checking the fixable
|
||||
box and pushing this button will remove the cover mark from the
|
||||
database for all the files in that category. In the case of extra
|
||||
cover files, checking the fixable box and pushing this button will
|
||||
add the cover mark to the database for all the files in that
|
||||
category.</p>
|
||||
'''))
|
||||
|
||||
self.log = QTreeWidget(self)
|
||||
self.log.itemChanged.connect(self.item_changed)
|
||||
@ -193,7 +260,7 @@ class CheckLibraryDialog(QDialog):
|
||||
self._layout.addLayout(h)
|
||||
|
||||
self._layout.addWidget(self.bbox)
|
||||
self.resize(750, 500)
|
||||
self.resize(950, 500)
|
||||
self.bbox.setEnabled(True)
|
||||
|
||||
def do_exec(self):
|
||||
@ -341,5 +408,6 @@ class CheckLibraryDialog(QDialog):
|
||||
|
||||
if __name__ == '__main__':
|
||||
app = QApplication([])
|
||||
d = CheckLibraryDialog()
|
||||
from calibre.library import db
|
||||
d = CheckLibraryDialog(None, db())
|
||||
d.exec_()
|
||||
|
@ -45,7 +45,6 @@ class MessageBox(QDialog, Ui_Dialog):
|
||||
self.ctc_button.clicked.connect(self.copy_to_clipboard)
|
||||
|
||||
|
||||
if det_msg:
|
||||
self.show_det_msg = _('Show &details')
|
||||
self.hide_det_msg = _('Hide &details')
|
||||
self.det_msg_toggle = self.bb.addButton(self.show_det_msg, self.bb.ActionRole)
|
||||
@ -53,7 +52,6 @@ class MessageBox(QDialog, Ui_Dialog):
|
||||
self.det_msg_toggle.setToolTip(
|
||||
_('Show detailed information about this error'))
|
||||
|
||||
|
||||
self.copy_action = QAction(self)
|
||||
self.addAction(self.copy_action)
|
||||
self.copy_action.setShortcuts(QKeySequence.Copy)
|
||||
@ -66,10 +64,14 @@ class MessageBox(QDialog, Ui_Dialog):
|
||||
else:
|
||||
self.bb.button(self.bb.Ok).setDefault(True)
|
||||
|
||||
if not det_msg:
|
||||
self.det_msg_toggle.setVisible(False)
|
||||
|
||||
self.do_resize()
|
||||
|
||||
|
||||
def toggle_det_msg(self, *args):
|
||||
vis = self.det_msg.isVisible()
|
||||
vis = unicode(self.det_msg_toggle.text()) == self.hide_det_msg
|
||||
self.det_msg_toggle.setText(self.show_det_msg if vis else
|
||||
self.hide_det_msg)
|
||||
self.det_msg.setVisible(not vis)
|
||||
@ -100,6 +102,15 @@ class MessageBox(QDialog, Ui_Dialog):
|
||||
self.bb.button(self.bb.Ok).setFocus(Qt.OtherFocusReason)
|
||||
return ret
|
||||
|
||||
def set_details(self, msg):
|
||||
if not msg:
|
||||
msg = ''
|
||||
self.det_msg.setPlainText(msg)
|
||||
self.det_msg_toggle.setText(self.show_det_msg)
|
||||
self.det_msg_toggle.setVisible(bool(msg))
|
||||
self.det_msg.setVisible(False)
|
||||
self.do_resize()
|
||||
|
||||
if __name__ == '__main__':
|
||||
app = QApplication([])
|
||||
from calibre.gui2 import question_dialog
|
||||
|
@ -21,7 +21,7 @@ class DBRestore(QDialog):
|
||||
self.l = QVBoxLayout()
|
||||
self.setLayout(self.l)
|
||||
self.l1 = QLabel('<b>'+_('Restoring database from backups, do not'
|
||||
' interrupt, this will happen in two stages')+'...')
|
||||
' interrupt, this will happen in three stages')+'...')
|
||||
self.setWindowTitle(_('Restoring database'))
|
||||
self.l.addWidget(self.l1)
|
||||
self.pb = QProgressBar(self)
|
||||
@ -104,7 +104,7 @@ def restore_database(db, parent=None):
|
||||
else:
|
||||
if r.errors_occurred:
|
||||
warning_dialog(parent, _('Success'),
|
||||
_('Restoring the database succeeded with some warnings',
|
||||
_('Restoring the database succeeded with some warnings'
|
||||
' click Show details to see the details.'),
|
||||
det_msg=r.report, show=True)
|
||||
else:
|
||||
|
@ -266,7 +266,7 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
|
||||
|
||||
def add_plugin(self):
|
||||
path = choose_files(self, 'add a plugin dialog', _('Add plugin'),
|
||||
filters=[(_('Plugins'), ['zip'])], all_files=False,
|
||||
filters=[(_('Plugins') + ' (*.zip)', ['zip'])], all_files=False,
|
||||
select_only_single_file=True)
|
||||
if not path:
|
||||
return
|
||||
|
@ -275,7 +275,7 @@ def generate_catalog(parent, dbspec, ids, device_manager, db):
|
||||
|
||||
if device_manager.is_device_connected:
|
||||
device = device_manager.device
|
||||
connected_device['name'] = device.gui_name
|
||||
connected_device['name'] = device.get_gui_name()
|
||||
try:
|
||||
storage = []
|
||||
if device._main_prefix:
|
||||
|
@ -232,6 +232,7 @@ class BIBTEX(CatalogPlugin): # {{{
|
||||
help = _('The fields to output when cataloging books in the '
|
||||
'database. Should be a comma-separated list of fields.\n'
|
||||
'Available fields: %s.\n'
|
||||
'plus user-created custom fields.\n'
|
||||
'Example: %s=title,authors,tags\n'
|
||||
"Default: '%%default'\n"
|
||||
"Applies to: BIBTEX output format")%(', '.join(FIELDS),
|
||||
@ -269,7 +270,7 @@ class BIBTEX(CatalogPlugin): # {{{
|
||||
dest = 'bib_cit',
|
||||
action = None,
|
||||
help = _('The template for citation creation from database fields.\n'
|
||||
' Should be a template with {} enclosed fields.\n'
|
||||
'Should be a template with {} enclosed fields.\n'
|
||||
'Available fields: %s.\n'
|
||||
"Default: '%%default'\n"
|
||||
"Applies to: BIBTEX output format")%', '.join(TEMPLATE_ALLOWED_FIELDS)),
|
||||
@ -344,7 +345,7 @@ class BIBTEX(CatalogPlugin): # {{{
|
||||
if field == 'authors' :
|
||||
bibtex_entry.append(u'author = "%s"' % bibtexdict.bibtex_author_format(item))
|
||||
|
||||
elif field in ['title', 'publisher', 'cover', 'uuid',
|
||||
elif field in ['title', 'publisher', 'cover', 'uuid', 'ondevice',
|
||||
'author_sort', 'series'] :
|
||||
bibtex_entry.append(u'%s = "%s"' % (field, bibtexdict.utf8ToBibtex(item)))
|
||||
|
||||
@ -378,7 +379,7 @@ class BIBTEX(CatalogPlugin): # {{{
|
||||
if calibre_files:
|
||||
files = [u':%s:%s' % (format, format.rpartition('.')[2].upper())\
|
||||
for format in item]
|
||||
bibtex_entry.append(u'files = "%s"' % u', '.join(files))
|
||||
bibtex_entry.append(u'file = "%s"' % u', '.join(files))
|
||||
|
||||
elif field == 'series_index' :
|
||||
bibtex_entry.append(u'volume = "%s"' % int(item))
|
||||
@ -474,6 +475,8 @@ class BIBTEX(CatalogPlugin): # {{{
|
||||
if opts.verbose:
|
||||
opts_dict = vars(opts)
|
||||
log("%s(): Generating %s" % (self.name,self.fmt))
|
||||
if opts.connected_device['is_device_connected']:
|
||||
log(" connected_device: %s" % opts.connected_device['name'])
|
||||
if opts_dict['search_text']:
|
||||
log(" --search='%s'" % opts_dict['search_text'])
|
||||
|
||||
@ -548,6 +551,7 @@ class BIBTEX(CatalogPlugin): # {{{
|
||||
as outfile:
|
||||
#File header
|
||||
nb_entries = len(data)
|
||||
|
||||
#check in book strict if all is ok else throw a warning into log
|
||||
if bib_entry == 'book' :
|
||||
nb_books = len(filter(check_entry_book_valid, data))
|
||||
@ -555,6 +559,11 @@ class BIBTEX(CatalogPlugin): # {{{
|
||||
log(" WARNING: only %d entries in %d are book compatible" % (nb_books, nb_entries))
|
||||
nb_entries = nb_books
|
||||
|
||||
# If connected device, add 'On Device' values to data
|
||||
if opts.connected_device['is_device_connected'] and 'ondevice' in fields:
|
||||
for entry in data:
|
||||
entry['ondevice'] = db.catalog_plugin_on_device_temp_mapping[entry['id']]['ondevice']
|
||||
|
||||
outfile.write(u'%%%Calibre catalog\n%%%{0} entries in catalog\n\n'.format(nb_entries))
|
||||
outfile.write(u'@preamble{"This catalog of %d entries was generated by calibre on %s"}\n\n'
|
||||
% (nb_entries, nowf().strftime("%A, %d. %B %Y %H:%M").decode(preferred_encoding)))
|
||||
|
@ -30,8 +30,8 @@ CHECKS = [('invalid_titles', _('Invalid titles'), True, False),
|
||||
('missing_formats', _('Missing book formats'), False, False),
|
||||
('extra_formats', _('Extra book formats'), True, False),
|
||||
('extra_files', _('Unknown files in books'), True, False),
|
||||
('missing_covers', _('Missing covers in books'), False, True),
|
||||
('extra_covers', _('Extra covers in books'), True, True),
|
||||
('missing_covers', _('Missing covers files'), False, True),
|
||||
('extra_covers', _('Cover files not in database'), True, True),
|
||||
('failed_folders', _('Folders raising exception'), False, False)
|
||||
]
|
||||
|
||||
|
@ -1549,7 +1549,9 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
|
||||
elif mi.cover is not None:
|
||||
if os.access(mi.cover, os.R_OK):
|
||||
with lopen(mi.cover, 'rb') as f:
|
||||
doit(self.set_cover, id, f, commit=False)
|
||||
raw = f.read()
|
||||
if raw:
|
||||
doit(self.set_cover, id, raw, commit=False)
|
||||
if mi.tags:
|
||||
doit(self.set_tags, id, mi.tags, notify=False, commit=False)
|
||||
if mi.comments:
|
||||
|
@ -141,7 +141,7 @@ class Restore(Thread):
|
||||
sizes = [os.path.getsize(os.path.join(dirpath, x)) for x in formats]
|
||||
names = [os.path.splitext(x)[0] for x in formats]
|
||||
opf = os.path.join(dirpath, 'metadata.opf')
|
||||
mi = OPF(opf).to_book_metadata()
|
||||
mi = OPF(opf, basedir=dirpath).to_book_metadata()
|
||||
timestamp = os.path.getmtime(opf)
|
||||
path = os.path.relpath(dirpath, self.src_library_path).replace(os.sep,
|
||||
'/')
|
||||
|
@ -295,7 +295,9 @@ e-ink screen :)
|
||||
Note that in the case of the Kindle, there is a way to manipulate collections via USB,
|
||||
but it requires that the Kindle be rebooted *every time* it is disconnected from the computer, for the
|
||||
changes to the collections to be recognized. As such, it is unlikely that
|
||||
any |app| developers will ever feel motivated enough to support it.
|
||||
any |app| developers will ever feel motivated enough to support it. There is however, a |app| plugin
|
||||
that allows you to create collections on your Kindle from the |app| metadata. It is available
|
||||
`here <http://www.mobileread.com/forums/showthread.php?t=118635>`_.
|
||||
|
||||
Library Management
|
||||
------------------
|
||||
|
File diff suppressed because it is too large
Load Diff
@ -112,6 +112,16 @@ _extra_lang_codes = {
|
||||
'en_IE' : _('English (Ireland)'),
|
||||
'en_CN' : _('English (China)'),
|
||||
'es_PY' : _('Spanish (Paraguay)'),
|
||||
'es_UY' : _('Spanish (Uruguay)'),
|
||||
'es_AR' : _('Spanish (Argentina)'),
|
||||
'es_MX' : _('Spanish (Mexico)'),
|
||||
'es_CU' : _('Spanish (Cuba)'),
|
||||
'es_CL' : _('Spanish (Chile)'),
|
||||
'es_EC' : _('Spanish (Ecuador)'),
|
||||
'es_HN' : _('Spanish (Honduras)'),
|
||||
'es_VE' : _('Spanish (Venezuela)'),
|
||||
'es_BO' : _('Spanish (Bolivia)'),
|
||||
'es_NI' : _('Spanish (Nicaragua)'),
|
||||
'de_AT' : _('German (AT)'),
|
||||
'fr_BE' : _('French (BE)'),
|
||||
'nl' : _('Dutch (NL)'),
|
||||
|
Loading…
x
Reference in New Issue
Block a user