mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-07 10:14:46 -04:00
Sync to trunk
This commit is contained in:
Alex Stanev
commit
c4714d5a82
@ -1,5 +1,4 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from calibre.web.feeds import Feed
|
||||
|
||||
@ -46,4 +45,3 @@ class GC_gl(BasicNewsRecipe):
|
||||
}
|
||||
newArticles.append(newArt)
|
||||
masterFeed.append((feed.title,newArticles))
|
||||
|
||||
|
||||
BIN
recipes/icons/losandes.png
Normal file
BIN
recipes/icons/losandes.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 285 B |
@ -1,4 +1,3 @@
|
||||
from calibre import strftime
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1299694372(BasicNewsRecipe):
|
||||
@ -9,14 +8,24 @@ class AdvancedUserRecipe1299694372(BasicNewsRecipe):
|
||||
oldest_article = 365
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'id':'text_controls_toggle'})
|
||||
,dict(name='script')
|
||||
,dict(name='div', attrs={'id':'text_controls'})
|
||||
,dict(name='div', attrs={'id':'editing_controls'})
|
||||
,dict(name='div', attrs={'class':'bar bottom'})
|
||||
]
|
||||
use_embedded_content = False
|
||||
needs_subscription = True
|
||||
INDEX = u'http://www.instapaper.com'
|
||||
LOGIN = INDEX + u'/user/login'
|
||||
|
||||
|
||||
|
||||
feeds = [(u'Instapaper Unread', u'http://www.instapaper.com/u'), (u'Instapaper Starred', u'http://www.instapaper.com/starred')]
|
||||
feeds = [
|
||||
(u'Instapaper Unread', u'http://www.instapaper.com/u'),
|
||||
(u'Instapaper Starred', u'http://www.instapaper.com/starred')
|
||||
]
|
||||
|
||||
def get_browser(self):
|
||||
br = BasicNewsRecipe.get_browser()
|
||||
@ -37,18 +46,20 @@ class AdvancedUserRecipe1299694372(BasicNewsRecipe):
|
||||
self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
|
||||
articles = []
|
||||
soup = self.index_to_soup(feedurl)
|
||||
for item in soup.findAll('div', attrs={'class':'titleRow'}):
|
||||
description = self.tag_to_string(item.div)
|
||||
for item in soup.findAll('div', attrs={'class':'cornerControls'}):
|
||||
#description = self.tag_to_string(item.div)
|
||||
atag = item.a
|
||||
if atag and atag.has_key('href'):
|
||||
url = atag['href']
|
||||
title = self.tag_to_string(atag)
|
||||
date = strftime(self.timefmt)
|
||||
articles.append({
|
||||
'title' :title
|
||||
,'date' :date
|
||||
,'url' :url
|
||||
,'description':description
|
||||
'url' :url
|
||||
})
|
||||
totalfeeds.append((feedtitle, articles))
|
||||
return totalfeeds
|
||||
|
||||
def print_version(self, url):
|
||||
return 'http://www.instapaper.com' + url
|
||||
|
||||
def populate_article_metadata(self, article, soup, first):
|
||||
article.title = soup.find('title').contents[0].strip()
|
||||
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
import urllib2
|
||||
import urllib2, re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class JBPress(BasicNewsRecipe):
|
||||
@ -40,3 +40,12 @@ class JBPress(BasicNewsRecipe):
|
||||
def print_version(self, url):
|
||||
url = urllib2.urlopen(url).geturl() # resolve redirect.
|
||||
return url.replace('/-/', '/print/')
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
# remove breadcrumb
|
||||
h3s = soup.findAll('h3')
|
||||
for h3 in h3s:
|
||||
if re.compile('^JBpress>').match(h3.string):
|
||||
h3.extract()
|
||||
return soup
|
||||
|
||||
|
||||
78
recipes/losandes.recipe
Normal file
78
recipes/losandes.recipe
Normal file
@ -0,0 +1,78 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
www.losandes.com.ar
|
||||
'''
|
||||
|
||||
from calibre import strftime
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class LosAndes(BasicNewsRecipe):
|
||||
title = 'Los Andes'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'Noticias de Mendoza, Argentina y el resto del mundo'
|
||||
publisher = 'Los Andes'
|
||||
category = 'news, politics, Argentina'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 200
|
||||
no_stylesheets = True
|
||||
encoding = 'cp1252'
|
||||
use_embedded_content = False
|
||||
language = 'es_AR'
|
||||
remove_empty_feeds = True
|
||||
publication_type = 'newspaper'
|
||||
masthead_url = 'http://www.losandes.com.ar/graficos/losandes.png'
|
||||
extra_css = """
|
||||
body{font-family: Arial,Helvetica,sans-serif }
|
||||
h1,h2{font-family: "Times New Roman",Times,serif}
|
||||
.fechaNota{font-weight: bold; color: gray}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : category
|
||||
, 'publisher' : publisher
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
remove_tags = [
|
||||
dict(name=['meta','link'])
|
||||
,dict(attrs={'class':['cabecera', 'url']})
|
||||
]
|
||||
remove_tags_before=dict(attrs={'class':'cabecera'})
|
||||
remove_tags_after=dict(attrs={'class':'url'})
|
||||
|
||||
|
||||
feeds = [
|
||||
(u'Ultimas Noticias' , u'http://www.losandes.com.ar/servicios/rss.asp?r=78' )
|
||||
,(u'Politica' , u'http://www.losandes.com.ar/servicios/rss.asp?r=68' )
|
||||
,(u'Economia nacional' , u'http://www.losandes.com.ar/servicios/rss.asp?r=65' )
|
||||
,(u'Economia internacional' , u'http://www.losandes.com.ar/servicios/rss.asp?r=505')
|
||||
,(u'Internacionales' , u'http://www.losandes.com.ar/servicios/rss.asp?r=66' )
|
||||
,(u'Turismo' , u'http://www.losandes.com.ar/servicios/rss.asp?r=502')
|
||||
,(u'Fincas' , u'http://www.losandes.com.ar/servicios/rss.asp?r=504')
|
||||
,(u'Isha nos habla' , u'http://www.losandes.com.ar/servicios/rss.asp?r=562')
|
||||
,(u'Estilo' , u'http://www.losandes.com.ar/servicios/rss.asp?r=81' )
|
||||
,(u'Cultura' , u'http://www.losandes.com.ar/servicios/rss.asp?r=503')
|
||||
,(u'Policiales' , u'http://www.losandes.com.ar/servicios/rss.asp?r=70' )
|
||||
,(u'Deportes' , u'http://www.losandes.com.ar/servicios/rss.asp?r=69' )
|
||||
,(u'Sociedad' , u'http://www.losandes.com.ar/servicios/rss.asp?r=67' )
|
||||
,(u'Opinion' , u'http://www.losandes.com.ar/servicios/rss.asp?r=80' )
|
||||
,(u'Editorial' , u'http://www.losandes.com.ar/servicios/rss.asp?r=76' )
|
||||
,(u'Mirador' , u'http://www.losandes.com.ar/servicios/rss.asp?r=79' )
|
||||
]
|
||||
|
||||
def print_version(self, url):
|
||||
artid = url.rpartition('.')[0].rpartition('-')[2]
|
||||
return "http://www.losandes.com.ar/includes/modulos/imprimir.asp?tipo=noticia&id=" + artid
|
||||
|
||||
def get_cover_url(self):
|
||||
month = strftime("%m").lstrip('0')
|
||||
day = strftime("%d").lstrip('0')
|
||||
year = strftime("%Y")
|
||||
return "http://www.losandes.com.ar/fotografias/fotosnoticias/" + year + "/" + month + "/" + day + "/th_tapa.jpg"
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
return soup
|
||||
44
recipes/luns_a_venres.recipe
Normal file
44
recipes/luns_a_venres.recipe
Normal file
@ -0,0 +1,44 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class LV_gl(BasicNewsRecipe):
|
||||
title = u'De Luns a Venres (RSS)'
|
||||
__author__ = u'Susana Sotelo Docío'
|
||||
description = u'O gratuíto galego'
|
||||
publisher = u'Galiciaé'
|
||||
category = u'news'
|
||||
encoding = 'utf-8'
|
||||
language = 'gl'
|
||||
direction = 'ltr'
|
||||
cover_url = 'http://lv.galiciae.com/new_estilos/lv/logo.gif'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 200
|
||||
center_navbar = False
|
||||
|
||||
feeds = [
|
||||
(u'Galicia', u'http://lv.galiciae.com/cache/rss/sec_galicia_gl.rss'),
|
||||
(u'Cultura', u'http://lv.galiciae.com/cache/rss/sec_cultura_gl.rss'),
|
||||
(u'Mundo', u'http://lv.galiciae.com/cache/rss/sec_mundo_gl.rss'),
|
||||
(u'Cidadanía', u'http://lv.galiciae.com/cache/rss/sec_ciudadania_gl.rss'),
|
||||
(u'Tecnoloxía', u'http://lv.galiciae.com/cache/rss/sec_tecnologia_gl.rss'),
|
||||
(u'España', u'http://lv.galiciae.com/cache/rss/sec_espana_gl.rss'),
|
||||
(u'Deportes', u'http://lv.galiciae.com/cache/rss/sec_deportes_gl.rss'),
|
||||
(u'Economía', u'http://lv.galiciae.com/cache/rss/sec_economia_gl.rss'),
|
||||
(u'Lercheo', u'http://lv.galiciae.com/cache/rss/sec_gente_gl.rss'),
|
||||
(u'Medio ambiente', u'http://lv.galiciae.com/cache/rss/sec_medioambiente_gl.rss'),
|
||||
(u'España/Mundo', u'http://lv.galiciae.com/cache/rss/sec_espanamundo_gl.rss'),
|
||||
(u'Sociedade', u'http://lv.galiciae.com/cache/rss/sec_sociedad_gl.rss'),
|
||||
(u'Ciencia', u'http://lv.galiciae.com/cache/rss/sec_ciencia_gl.rss'),
|
||||
(u'Motor', u'http://lv.galiciae.com/cache/rss/sec_motor_gl.rss'),
|
||||
(u'Coches', u'http://lv.galiciae.com/cache/rss/sec_coches_gl.rss'),
|
||||
(u'Motos', u'http://lv.galiciae.com/cache/rss/sec_motos_gl.rss'),
|
||||
(u'Industriais', u'http://lv.galiciae.com/cache/rss/sec_industriales_gl.rss')
|
||||
]
|
||||
|
||||
extra_css = u' p{text-align:left} '
|
||||
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\nencoding="' + encoding + '"\ntags="' + category + '"\noverride_css=" p {text-align:left; text-indent: 0cm} "'
|
||||
|
||||
def print_version(self, url):
|
||||
url += '?imprimir&lang=gl'
|
||||
return url
|
||||
|
||||
@ -1,11 +1,10 @@
|
||||
EMAILADDRESS = 'hoge@foobar.co.jp'
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class NBOnline(BasicNewsRecipe):
|
||||
title = u'Nikkei Business Online'
|
||||
language = 'ja'
|
||||
description = u'Nikkei Business Online New articles. PLEASE NOTE: You need to edit EMAILADDRESS line of this "nbonline.recipe" file to set your e-mail address which is needed when login. (file is in "Calibre2/resources/recipes" directory.)'
|
||||
description = u'Nikkei Business Online.\u6CE8\uFF1A\u30E6\u30FC\u30B6\u30FC\u540D\u306Bemail\u30A2\u30C9\u30EC\u30B9\u3068\u30E6\u30FC\u30B6\u30FC\u540D\u3092\u30BB\u30DF\u30B3\u30ED\u30F3\u3067\u533A\u5207\u3063\u3066\u5165\u308C\u3066\u304F\u3060\u3055\u3044\u3002\u4F8B\uFF1Aemail@address.jp;username . PLEASE NOTE: You need to put your email address and username into username filed separeted by ; (semi-colon).'
|
||||
__author__ = 'Ado Nishimura'
|
||||
needs_subscription = True
|
||||
oldest_article = 7
|
||||
@ -23,8 +22,8 @@ class NBOnline(BasicNewsRecipe):
|
||||
if self.username is not None and self.password is not None:
|
||||
br.open('https://signon.nikkeibp.co.jp/front/login/?ct=p&ts=nbo')
|
||||
br.select_form(name='loginActionForm')
|
||||
br['email'] = EMAILADDRESS
|
||||
br['userId'] = self.username
|
||||
br['email'] = self.username.split(';')[0]
|
||||
br['userId'] = self.username.split(';')[1]
|
||||
br['password'] = self.password
|
||||
br.submit()
|
||||
return br
|
||||
|
||||
@ -11,6 +11,7 @@
|
||||
<link rel="stylesheet" type="text/css" href="{prefix}/static/browse/browse.css" />
|
||||
<link type="text/css" href="{prefix}/static/jquery_ui/css/humanity-custom/jquery-ui-1.8.5.custom.css" rel="stylesheet" />
|
||||
<link rel="stylesheet" type="text/css" href="{prefix}/static/jquery.multiselect.css" />
|
||||
<link rel="apple-touch-icon" href="/static/calibre.png" />
|
||||
|
||||
<script type="text/javascript" src="{prefix}/static/jquery.js"></script>
|
||||
<script type="text/javascript" src="{prefix}/static/jquery.corner.js"></script>
|
||||
|
||||
@ -1181,6 +1181,16 @@ class StoreBeWriteStore(StoreBase):
|
||||
headquarters = 'US'
|
||||
formats = ['EPUB', 'MOBI', 'PDF']
|
||||
|
||||
class StoreBookotekaStore(StoreBase):
|
||||
name = 'Bookoteka'
|
||||
author = u'Tomasz Długosz'
|
||||
description = u'E-booki w Bookotece dostępne są w formacie EPUB oraz PDF. Publikacje sprzedawane w Bookotece są objęte prawami autorskimi. Zobowiązaliśmy się chronić te prawa, ale bez ograniczania dostępu do książki użytkownikowi, który nabył ją w legalny sposób. Dlatego też Bookoteka stosuje tak zwany „watermarking transakcyjny” czyli swego rodzaju znaki wodne.'
|
||||
actual_plugin = 'calibre.gui2.store.stores.bookoteka_plugin:BookotekaStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'PL'
|
||||
formats = ['EPUB', 'PDF']
|
||||
|
||||
class StoreChitankaStore(StoreBase):
|
||||
name = u'Моята библиотека'
|
||||
author = 'Alex Stanev'
|
||||
@ -1218,16 +1228,16 @@ class StoreEbookscomStore(StoreBase):
|
||||
formats = ['EPUB', 'LIT', 'MOBI', 'PDF']
|
||||
affiliate = True
|
||||
|
||||
class StoreEPubBuyDEStore(StoreBase):
|
||||
name = 'EPUBBuy DE'
|
||||
author = 'Charles Haley'
|
||||
description = u'Bei EPUBBuy.com finden Sie ausschliesslich eBooks im weitverbreiteten EPUB-Format und ohne DRM. So haben Sie die freie Wahl, wo Sie Ihr eBook lesen: Tablet, eBook-Reader, Smartphone oder einfach auf Ihrem PC. So macht eBook-Lesen Spaß!'
|
||||
actual_plugin = 'calibre.gui2.store.stores.epubbuy_de_plugin:EPubBuyDEStore'
|
||||
|
||||
drm_free_only = True
|
||||
headquarters = 'DE'
|
||||
formats = ['EPUB']
|
||||
affiliate = True
|
||||
#class StoreEPubBuyDEStore(StoreBase):
|
||||
# name = 'EPUBBuy DE'
|
||||
# author = 'Charles Haley'
|
||||
# description = u'Bei EPUBBuy.com finden Sie ausschliesslich eBooks im weitverbreiteten EPUB-Format und ohne DRM. So haben Sie die freie Wahl, wo Sie Ihr eBook lesen: Tablet, eBook-Reader, Smartphone oder einfach auf Ihrem PC. So macht eBook-Lesen Spaß!'
|
||||
# actual_plugin = 'calibre.gui2.store.stores.epubbuy_de_plugin:EPubBuyDEStore'
|
||||
#
|
||||
# drm_free_only = True
|
||||
# headquarters = 'DE'
|
||||
# formats = ['EPUB']
|
||||
# affiliate = True
|
||||
|
||||
class StoreEBookShoppeUKStore(StoreBase):
|
||||
name = 'ebookShoppe UK'
|
||||
@ -1465,12 +1475,13 @@ plugins += [
|
||||
StoreBNStore,
|
||||
StoreBeamEBooksDEStore,
|
||||
StoreBeWriteStore,
|
||||
StoreBookotekaStore,
|
||||
StoreChitankaStore,
|
||||
StoreDieselEbooksStore,
|
||||
StoreEbookNLStore,
|
||||
StoreEbookscomStore,
|
||||
StoreEBookShoppeUKStore,
|
||||
StoreEPubBuyDEStore,
|
||||
# StoreEPubBuyDEStore,
|
||||
StoreEHarlequinStore,
|
||||
StoreEpubBudStore,
|
||||
StoreFeedbooksStore,
|
||||
|
||||
@ -131,7 +131,7 @@ class AZBOOKA(ALEX):
|
||||
description = _('Communicate with the Azbooka')
|
||||
|
||||
VENDOR_NAME = 'LINUX'
|
||||
WINDOWS_MAIN_MEM = 'FILE-STOR_GADGET'
|
||||
WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = 'FILE-STOR_GADGET'
|
||||
|
||||
MAIN_MEMORY_VOLUME_LABEL = 'Azbooka Internal Memory'
|
||||
|
||||
|
||||
@ -303,6 +303,9 @@ class CSSPreProcessor(object):
|
||||
class HTMLPreProcessor(object):
|
||||
|
||||
PREPROCESS = [
|
||||
# Remove huge block of contiguous spaces as they slow down
|
||||
# the following regexes pretty badly
|
||||
(re.compile(r'\s{10000,}'), lambda m: ''),
|
||||
# Some idiotic HTML generators (Frontpage I'm looking at you)
|
||||
# Put all sorts of crap into <head>. This messes up lxml
|
||||
(re.compile(r'<head[^>]*>\n*(.*?)\n*</head>', re.IGNORECASE|re.DOTALL),
|
||||
|
||||
@ -7,9 +7,13 @@ __license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import struct, datetime, sys, os
|
||||
import struct, datetime, sys, os, shutil
|
||||
from collections import OrderedDict
|
||||
from calibre.utils.date import utc_tz
|
||||
from calibre.ebooks.mobi.langcodes import main_language, sub_language
|
||||
from calibre.ebooks.mobi.writer2.utils import (decode_hex_number, decint,
|
||||
get_trailing_data)
|
||||
from calibre.utils.magick.draw import identify_data
|
||||
|
||||
# PalmDB {{{
|
||||
class PalmDOCAttributes(object):
|
||||
@ -275,6 +279,8 @@ class MOBIHeader(object): # {{{
|
||||
self.drm_flags = bin(struct.unpack(b'>I', self.raw[176:180])[0])
|
||||
self.has_extra_data_flags = self.length >= 232 and len(self.raw) >= 232+16
|
||||
self.has_fcis_flis = False
|
||||
self.has_multibytes = self.has_indexing_bytes = self.has_uncrossable_breaks = False
|
||||
self.extra_data_flags = 0
|
||||
if self.has_extra_data_flags:
|
||||
self.unknown4 = self.raw[180:192]
|
||||
self.first_content_record, self.last_content_record = \
|
||||
@ -284,8 +290,11 @@ class MOBIHeader(object): # {{{
|
||||
self.flis_count) = struct.unpack(b'>IIII',
|
||||
self.raw[200:216])
|
||||
self.unknown6 = self.raw[216:240]
|
||||
self.extra_data_flags = bin(struct.unpack(b'>I',
|
||||
self.raw[240:244])[0])
|
||||
self.extra_data_flags = struct.unpack(b'>I',
|
||||
self.raw[240:244])[0]
|
||||
self.has_multibytes = bool(self.extra_data_flags & 0b1)
|
||||
self.has_indexing_bytes = bool(self.extra_data_flags & 0b10)
|
||||
self.has_uncrossable_breaks = bool(self.extra_data_flags & 0b100)
|
||||
self.primary_index_record, = struct.unpack(b'>I',
|
||||
self.raw[244:248])
|
||||
|
||||
@ -346,7 +355,10 @@ class MOBIHeader(object): # {{{
|
||||
ans.append('FLIS number: %d'% self.flis_number)
|
||||
ans.append('FLIS count: %d'% self.flis_count)
|
||||
ans.append('Unknown6: %r'% self.unknown6)
|
||||
ans.append('Extra data flags: %r'%self.extra_data_flags)
|
||||
ans.append(('Extra data flags: %s (has multibyte: %s) '
|
||||
'(has indexing: %s) (has uncrossable breaks: %s)')%(
|
||||
bin(self.extra_data_flags), self.has_multibytes,
|
||||
self.has_indexing_bytes, self.has_uncrossable_breaks ))
|
||||
ans.append('Primary index record (null value: %d): %d'%(0xffffffff,
|
||||
self.primary_index_record))
|
||||
|
||||
@ -368,21 +380,20 @@ class TagX(object): # {{{
|
||||
def __init__(self, raw, control_byte_count):
|
||||
self.tag = ord(raw[0])
|
||||
self.num_values = ord(raw[1])
|
||||
self.bmask = ord(raw[2])
|
||||
self.bitmask = bin(self.bmask)
|
||||
self.bitmask = ord(raw[2])
|
||||
# End of file = 1 iff last entry
|
||||
# When it is 1 all others are 0
|
||||
self.eof = ord(raw[3])
|
||||
|
||||
self.is_eof = (self.eof == 1 and self.tag == 0 and self.num_values == 0
|
||||
and self.bmask == 0)
|
||||
and self.bitmask == 0)
|
||||
|
||||
def __repr__(self):
|
||||
return 'TAGX(tag=%02d, num_values=%d, bitmask=%r (%d), eof=%d)' % (self.tag,
|
||||
self.num_values, self.bitmask, self.bmask, self.eof)
|
||||
return 'TAGX(tag=%02d, num_values=%d, bitmask=%r, eof=%d)' % (self.tag,
|
||||
self.num_values, bin(self.bitmask), self.eof)
|
||||
# }}}
|
||||
|
||||
class PrimaryIndexRecord(object): # {{{
|
||||
class IndexHeader(object): # {{{
|
||||
|
||||
def __init__(self, record):
|
||||
self.record = record
|
||||
@ -413,7 +424,7 @@ class PrimaryIndexRecord(object): # {{{
|
||||
self.ordt_start, = struct.unpack('>I', raw[40:44])
|
||||
self.ligt_start, = struct.unpack('>I', raw[44:48])
|
||||
self.num_of_ligt_entries, = struct.unpack('>I', raw[48:52])
|
||||
self.num_of_ctoc_blocks, = struct.unpack('>I', raw[52:56])
|
||||
self.num_of_cncx_blocks, = struct.unpack('>I', raw[52:56])
|
||||
self.unknown2 = raw[56:180]
|
||||
self.tagx_offset, = struct.unpack(b'>I', raw[180:184])
|
||||
if self.tagx_offset != self.header_length:
|
||||
@ -435,11 +446,11 @@ class PrimaryIndexRecord(object): # {{{
|
||||
self.tagx_control_byte_count))
|
||||
if self.tagx_entries and not self.tagx_entries[-1].is_eof:
|
||||
raise ValueError('TAGX last entry is not EOF')
|
||||
self.tagx_entries = self.tagx_entries[:-1]
|
||||
|
||||
idxt0_pos = self.header_length+self.tagx_header_length
|
||||
last_name_len, = struct.unpack(b'>B', raw[idxt0_pos])
|
||||
count_pos = idxt0_pos+1+last_name_len
|
||||
last_num = int(raw[idxt0_pos+1:count_pos], 16)
|
||||
last_num, consumed = decode_hex_number(raw[idxt0_pos:])
|
||||
count_pos = idxt0_pos + consumed
|
||||
self.ncx_count, = struct.unpack(b'>H', raw[count_pos:count_pos+2])
|
||||
|
||||
if last_num != self.ncx_count - 1:
|
||||
@ -457,9 +468,12 @@ class PrimaryIndexRecord(object): # {{{
|
||||
def __str__(self):
|
||||
ans = ['*'*20 + ' Index Header '+ '*'*20]
|
||||
a = ans.append
|
||||
def u(w):
|
||||
a('Unknown: %r (%d bytes) (All zeros: %r)'%(w,
|
||||
len(w), not bool(w.replace(b'\0', b'')) ))
|
||||
|
||||
a('Header length: %d'%self.header_length)
|
||||
a('Unknown1: %r (%d bytes) (All zeros: %r)'%(self.unknown1,
|
||||
len(self.unknown1), not bool(self.unknown1.replace(b'\0', '')) ))
|
||||
u(self.unknown1)
|
||||
a('Index Type: %s (%d)'%(self.index_type_desc, self.index_type))
|
||||
a('Offset to IDXT start: %d'%self.idxt_start)
|
||||
a('Number of index records: %d'%self.index_count)
|
||||
@ -471,12 +485,10 @@ class PrimaryIndexRecord(object): # {{{
|
||||
a('ORDT start: %d'%self.ordt_start)
|
||||
a('LIGT start: %d'%self.ligt_start)
|
||||
a('Number of LIGT entries: %d'%self.num_of_ligt_entries)
|
||||
a('Number of CTOC blocks: %d'%self.num_of_ctoc_blocks)
|
||||
a('Unknown2: %r (%d bytes) (All zeros: %r)'%(self.unknown2,
|
||||
len(self.unknown2), not bool(self.unknown2.replace(b'\0', '')) ))
|
||||
a('Number of cncx blocks: %d'%self.num_of_cncx_blocks)
|
||||
u(self.unknown2)
|
||||
a('TAGX offset: %d'%self.tagx_offset)
|
||||
a('Unknown3: %r (%d bytes) (All zeros: %r)'%(self.unknown3,
|
||||
len(self.unknown3), not bool(self.unknown3.replace(b'\0', '')) ))
|
||||
u(self.unknown3)
|
||||
a('\n\n')
|
||||
a('*'*20 + ' TAGX Header (%d bytes)'%self.tagx_header_length+ '*'*20)
|
||||
a('Header length: %d'%self.tagx_header_length)
|
||||
@ -488,6 +500,354 @@ class PrimaryIndexRecord(object): # {{{
|
||||
return '\n'.join(ans)
|
||||
# }}}
|
||||
|
||||
class Tag(object): # {{{
|
||||
|
||||
'''
|
||||
Index entries are a collection of tags. Each tag is represented by this
|
||||
class.
|
||||
'''
|
||||
|
||||
TAG_MAP = {
|
||||
1: ('offset', 'Offset in HTML'),
|
||||
2: ('size', 'Size in HTML'),
|
||||
3: ('label_offset', 'Offset to label in CNCX'),
|
||||
4: ('depth', 'Depth of this entry in TOC'),
|
||||
|
||||
# The remaining tag types have to be interpreted subject to the type
|
||||
# of index entry they are present in
|
||||
}
|
||||
|
||||
INTERPRET_MAP = {
|
||||
'subchapter': {
|
||||
5 : ('Parent chapter index', 'parent_index')
|
||||
},
|
||||
|
||||
'article' : {
|
||||
5 : ('Class offset in cncx', 'class_offset'),
|
||||
21 : ('Parent section index', 'parent_index'),
|
||||
22 : ('Description offset in cncx', 'desc_offset'),
|
||||
23 : ('Author offset in cncx', 'author_offset'),
|
||||
},
|
||||
|
||||
'chapter_with_subchapters' : {
|
||||
22 : ('First subchapter index', 'first_subchapter_index'),
|
||||
23 : ('Last subchapter index', 'last_subchapter_index'),
|
||||
},
|
||||
|
||||
'periodical' : {
|
||||
5 : ('Class offset in cncx', 'class_offset'),
|
||||
22 : ('First section index', 'first_section_index'),
|
||||
23 : ('Last section index', 'last_section_index'),
|
||||
},
|
||||
|
||||
'section' : {
|
||||
5 : ('Class offset in cncx', 'class_offset'),
|
||||
21 : ('Periodical index', 'periodical_index'),
|
||||
22 : ('First article index', 'first_article_index'),
|
||||
23 : ('Last article index', 'last_article_index'),
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def __init__(self, tagx, vals, entry_type, cncx):
|
||||
self.value = vals if len(vals) > 1 else vals[0]
|
||||
self.entry_type = entry_type
|
||||
self.cncx_value = None
|
||||
if tagx.tag in self.TAG_MAP:
|
||||
self.attr, self.desc = self.TAG_MAP[tagx.tag]
|
||||
else:
|
||||
try:
|
||||
td = self.INTERPRET_MAP[entry_type]
|
||||
except:
|
||||
raise ValueError('Unknown entry type: %s'%entry_type)
|
||||
try:
|
||||
self.desc, self.attr = td[tagx.tag]
|
||||
except:
|
||||
raise ValueError('Unknown tag: %d for entry type: %s'%(
|
||||
tagx.tag, entry_type))
|
||||
if '_offset' in self.attr:
|
||||
self.cncx_value = cncx[self.value]
|
||||
|
||||
def __str__(self):
|
||||
if self.cncx_value is not None:
|
||||
return '%s : %r [%r]'%(self.desc, self.value, self.cncx_value)
|
||||
return '%s : %r'%(self.desc, self.value)
|
||||
|
||||
# }}}
|
||||
|
||||
class IndexEntry(object): # {{{
|
||||
|
||||
'''
|
||||
The index is made up of entries, each of which is represented by an
|
||||
instance of this class. Index entries typically point to offsets int eh
|
||||
HTML, specify HTML sizes and point to text strings in the CNCX that are
|
||||
used in the navigation UI.
|
||||
'''
|
||||
|
||||
TYPES = {
|
||||
# Present in book type files
|
||||
0x0f : 'chapter',
|
||||
0x6f : 'chapter_with_subchapters',
|
||||
0x1f : 'subchapter',
|
||||
# Present in periodicals
|
||||
0xdf : 'periodical',
|
||||
0xff : 'section',
|
||||
0x3f : 'article',
|
||||
}
|
||||
|
||||
def __init__(self, ident, entry_type, raw, cncx, tagx_entries):
|
||||
self.index = ident
|
||||
self.raw = raw
|
||||
self.tags = []
|
||||
|
||||
try:
|
||||
self.entry_type = self.TYPES[entry_type]
|
||||
except KeyError:
|
||||
raise ValueError('Unknown Index Entry type: %s'%hex(entry_type))
|
||||
|
||||
expected_tags = [tag for tag in tagx_entries if tag.bitmask &
|
||||
entry_type]
|
||||
|
||||
for tag in expected_tags:
|
||||
vals = []
|
||||
for i in range(tag.num_values):
|
||||
if not raw:
|
||||
raise ValueError('Index entry does not match TAGX header')
|
||||
val, consumed = decint(raw)
|
||||
raw = raw[consumed:]
|
||||
vals.append(val)
|
||||
self.tags.append(Tag(tag, vals, self.entry_type, cncx))
|
||||
|
||||
@property
|
||||
def label(self):
|
||||
for tag in self.tags:
|
||||
if tag.attr == 'label_offset':
|
||||
return tag.cncx_value
|
||||
return ''
|
||||
|
||||
def __str__(self):
|
||||
ans = ['Index Entry(index=%s, entry_type=%s, length=%d)'%(
|
||||
self.index, self.entry_type, len(self.tags))]
|
||||
for tag in self.tags:
|
||||
ans.append('\t'+str(tag))
|
||||
return '\n'.join(ans)
|
||||
|
||||
# }}}
|
||||
|
||||
class IndexRecord(object): # {{{
|
||||
|
||||
'''
|
||||
Represents all indexing information in the MOBI, apart from indexing info
|
||||
in the trailing data of the text records.
|
||||
'''
|
||||
|
||||
def __init__(self, record, index_header, cncx):
|
||||
self.record = record
|
||||
raw = self.record.raw
|
||||
if raw[:4] != b'INDX':
|
||||
raise ValueError('Invalid Primary Index Record')
|
||||
|
||||
u = struct.unpack
|
||||
|
||||
self.header_length, = u('>I', raw[4:8])
|
||||
self.unknown1 = raw[8:12]
|
||||
self.header_type, = u('>I', raw[12:16])
|
||||
self.unknown2 = raw[16:20]
|
||||
self.idxt_offset, self.idxt_count = u(b'>II', raw[20:28])
|
||||
if self.idxt_offset < 192:
|
||||
raise ValueError('Unknown Index record structure')
|
||||
self.unknown3 = raw[28:36]
|
||||
self.unknown4 = raw[36:192] # Should be 156 bytes
|
||||
|
||||
self.index_offsets = []
|
||||
indices = raw[self.idxt_offset:]
|
||||
if indices[:4] != b'IDXT':
|
||||
raise ValueError("Invalid IDXT index table")
|
||||
indices = indices[4:]
|
||||
for i in range(self.idxt_count):
|
||||
off, = u(b'>H', indices[i*2:(i+1)*2])
|
||||
self.index_offsets.append(off-192)
|
||||
|
||||
indxt = raw[192:self.idxt_offset]
|
||||
self.indices = []
|
||||
for i, off in enumerate(self.index_offsets):
|
||||
try:
|
||||
next_off = self.index_offsets[i+1]
|
||||
except:
|
||||
next_off = len(indxt)
|
||||
index, consumed = decode_hex_number(indxt[off:])
|
||||
entry_type = ord(indxt[off+consumed])
|
||||
self.indices.append(IndexEntry(index, entry_type,
|
||||
indxt[off+consumed+1:next_off], cncx, index_header.tagx_entries))
|
||||
|
||||
|
||||
def __str__(self):
|
||||
ans = ['*'*20 + ' Index Record (%d bytes) '%len(self.record.raw)+ '*'*20]
|
||||
a = ans.append
|
||||
def u(w):
|
||||
a('Unknown: %r (%d bytes) (All zeros: %r)'%(w,
|
||||
len(w), not bool(w.replace(b'\0', b'')) ))
|
||||
a('Header length: %d'%self.header_length)
|
||||
u(self.unknown1)
|
||||
a('Header Type: %d'%self.header_type)
|
||||
u(self.unknown2)
|
||||
a('IDXT Offset: %d'%self.idxt_offset)
|
||||
a('IDXT Count: %d'%self.idxt_count)
|
||||
u(self.unknown3)
|
||||
u(self.unknown4)
|
||||
a('Index offsets: %r'%self.index_offsets)
|
||||
a('\nIndex Entries:')
|
||||
for entry in self.indices:
|
||||
a(str(entry)+'\n')
|
||||
|
||||
return '\n'.join(ans)
|
||||
|
||||
# }}}
|
||||
|
||||
class CNCX(object) : # {{{
|
||||
|
||||
'''
|
||||
Parses the records that contain the compiled NCX (all strings from the
|
||||
NCX). Presents a simple offset : string mapping interface to access the
|
||||
data.
|
||||
'''
|
||||
|
||||
def __init__(self, records, codec):
|
||||
self.records = OrderedDict()
|
||||
pos = 0
|
||||
for record in records:
|
||||
raw = record.raw
|
||||
while pos < len(raw):
|
||||
length, consumed = decint(raw[pos:])
|
||||
if length > 0:
|
||||
self.records[pos] = raw[pos+consumed:pos+consumed+length].decode(
|
||||
codec)
|
||||
pos += consumed+length
|
||||
|
||||
def __getitem__(self, offset):
|
||||
return self.records.get(offset)
|
||||
|
||||
def __str__(self):
|
||||
ans = ['*'*20 + ' cncx (%d strings) '%len(self.records)+ '*'*20]
|
||||
for k, v in self.records.iteritems():
|
||||
ans.append('%10d : %s'%(k, v))
|
||||
return '\n'.join(ans)
|
||||
|
||||
|
||||
# }}}
|
||||
|
||||
class TextRecord(object): # {{{
|
||||
|
||||
def __init__(self, idx, record, extra_data_flags, decompress, index_record,
|
||||
doc_type):
|
||||
self.trailing_data, self.raw = get_trailing_data(record.raw, extra_data_flags)
|
||||
self.raw = decompress(self.raw)
|
||||
if 0 in self.trailing_data:
|
||||
self.trailing_data['multibyte_overlap'] = self.trailing_data.pop(0)
|
||||
if 1 in self.trailing_data:
|
||||
self.trailing_data['indexing'] = self.trailing_data.pop(1)
|
||||
if 2 in self.trailing_data:
|
||||
self.trailing_data['uncrossable_breaks'] = self.trailing_data.pop(2)
|
||||
|
||||
self.idx = idx
|
||||
|
||||
if 'indexing' in self.trailing_data and index_record is not None:
|
||||
self.interpret_indexing(doc_type, index_record.indices)
|
||||
|
||||
def interpret_indexing(self, doc_type, indices):
|
||||
raw = self.trailing_data['indexing']
|
||||
ident, consumed = decint(raw)
|
||||
raw = raw[consumed:]
|
||||
entry_type = ident & 0b111
|
||||
index_entry_idx = ident >> 3
|
||||
index_entry = None
|
||||
for i in indices:
|
||||
if i.index == index_entry_idx:
|
||||
index_entry = i.label
|
||||
break
|
||||
self.trailing_data['interpreted_indexing'] = (
|
||||
'Type: %s, Index Entry: %s'%(entry_type, index_entry))
|
||||
if doc_type == 2: # Book
|
||||
self.interpret_book_indexing(raw, entry_type)
|
||||
|
||||
def interpret_book_indexing(self, raw, entry_type):
|
||||
arg1, consumed = decint(raw)
|
||||
raw = raw[consumed:]
|
||||
if arg1 != 0:
|
||||
raise ValueError('TBS index entry has unknown arg1: %d'%
|
||||
arg1)
|
||||
if entry_type == 2:
|
||||
desc = ('This record has only a single starting or a single'
|
||||
' ending point')
|
||||
if raw:
|
||||
raise ValueError('TBS index entry has unknown extra bytes:'
|
||||
' %r'%raw)
|
||||
elif entry_type == 3:
|
||||
desc = ('This record is spanned by a single node (i.e. it'
|
||||
' has no start or end points)')
|
||||
arg2, consumed = decint(raw)
|
||||
if arg2 != 0:
|
||||
raise ValueError('TBS index entry has unknown arg2: %d'%
|
||||
arg2)
|
||||
elif entry_type == 6:
|
||||
if len(raw) != 1:
|
||||
raise ValueError('TBS index entry has unknown extra bytes:'
|
||||
' %r'%raw)
|
||||
num = ord(raw[0])
|
||||
# An unmatched starting or ending point each contributes 1 to
|
||||
# this count. A matched pair of starting and ending points
|
||||
# together contribute 1 to this count. Note that you can only
|
||||
# ever have either 1 unmatched start point or 1 unmatched end
|
||||
# point, never both (logically impossible).
|
||||
desc = ('This record has %d starting/ending points and/or complete'
|
||||
' nodes.')%num
|
||||
else:
|
||||
raise ValueError('Unknown TBS index entry type: %d for book'%entry_type)
|
||||
self.trailing_data['interpreted_indexing'] += ' :: ' + desc
|
||||
|
||||
def dump(self, folder):
|
||||
name = '%06d'%self.idx
|
||||
with open(os.path.join(folder, name+'.txt'), 'wb') as f:
|
||||
f.write(self.raw)
|
||||
with open(os.path.join(folder, name+'.trailing_data'), 'wb') as f:
|
||||
for k, v in self.trailing_data.iteritems():
|
||||
raw = '%s : %r\n\n'%(k, v)
|
||||
f.write(raw.encode('utf-8'))
|
||||
|
||||
# }}}
|
||||
|
||||
class ImageRecord(object): # {{{
|
||||
|
||||
def __init__(self, idx, record, fmt):
|
||||
self.raw = record.raw
|
||||
self.fmt = fmt
|
||||
self.idx = idx
|
||||
|
||||
def dump(self, folder):
|
||||
name = '%06d'%self.idx
|
||||
with open(os.path.join(folder, name+'.'+self.fmt), 'wb') as f:
|
||||
f.write(self.raw)
|
||||
|
||||
# }}}
|
||||
|
||||
class BinaryRecord(object): # {{{
|
||||
|
||||
def __init__(self, idx, record):
|
||||
self.raw = record.raw
|
||||
sig = self.raw[:4]
|
||||
name = '%06d'%idx
|
||||
if sig in (b'FCIS', b'FLIS', b'SRCS'):
|
||||
name += '-' + sig.decode('ascii')
|
||||
elif sig == b'\xe9\x8e\r\n':
|
||||
name += '-' + 'EOF'
|
||||
self.name = name
|
||||
|
||||
def dump(self, folder):
|
||||
with open(os.path.join(folder, self.name+'.bin'), 'wb') as f:
|
||||
f.write(self.raw)
|
||||
|
||||
# }}}
|
||||
|
||||
class MOBIFile(object): # {{{
|
||||
|
||||
def __init__(self, stream):
|
||||
@ -516,10 +876,59 @@ class MOBIFile(object): # {{{
|
||||
|
||||
self.mobi_header = MOBIHeader(self.records[0])
|
||||
|
||||
self.primary_index_record = None
|
||||
if 'huff' in self.mobi_header.compression.lower():
|
||||
huffrecs = [r.raw for r in
|
||||
xrange(self.mobi_header.huffman_record_offset,
|
||||
self.mobi_header.huffman_record_offset +
|
||||
self.mobi_header.huffman_record_count)]
|
||||
from calibre.ebooks.mobi.huffcdic import HuffReader
|
||||
huffs = HuffReader(huffrecs)
|
||||
decompress = huffs.decompress
|
||||
elif 'palmdoc' in self.mobi_header.compression.lower():
|
||||
from calibre.ebooks.compression.palmdoc import decompress_doc
|
||||
decompress = decompress_doc
|
||||
else:
|
||||
decompress = lambda x: x
|
||||
|
||||
self.index_header = self.index_record = None
|
||||
self.indexing_record_nums = set()
|
||||
pir = self.mobi_header.primary_index_record
|
||||
if pir != 0xffffffff:
|
||||
self.primary_index_record = PrimaryIndexRecord(self.records[pir])
|
||||
self.index_header = IndexHeader(self.records[pir])
|
||||
self.cncx = CNCX(self.records[
|
||||
pir+2:pir+2+self.index_header.num_of_cncx_blocks],
|
||||
self.index_header.index_encoding)
|
||||
self.index_record = IndexRecord(self.records[pir+1],
|
||||
self.index_header, self.cncx)
|
||||
self.indexing_record_nums = set(xrange(pir,
|
||||
pir+2+self.index_header.num_of_cncx_blocks))
|
||||
|
||||
|
||||
ntr = self.mobi_header.number_of_text_records
|
||||
fntbr = self.mobi_header.first_non_book_record
|
||||
fii = self.mobi_header.first_image_index
|
||||
if fntbr == 0xffffffff:
|
||||
fntbr = len(self.records)
|
||||
self.text_records = [TextRecord(r, self.records[r],
|
||||
self.mobi_header.extra_data_flags, decompress, self.index_record,
|
||||
self.mobi_header.type_raw) for r in xrange(1,
|
||||
min(len(self.records), ntr+1))]
|
||||
self.image_records, self.binary_records = [], []
|
||||
for i in xrange(fntbr, len(self.records)):
|
||||
if i in self.indexing_record_nums:
|
||||
continue
|
||||
r = self.records[i]
|
||||
fmt = None
|
||||
if i >= fii and r.raw[:4] not in (b'FLIS', b'FCIS', b'SRCS',
|
||||
b'\xe9\x8e\r\n'):
|
||||
try:
|
||||
width, height, fmt = identify_data(r.raw)
|
||||
except:
|
||||
pass
|
||||
if fmt is not None:
|
||||
self.image_records.append(ImageRecord(i, r, fmt))
|
||||
else:
|
||||
self.binary_records.append(BinaryRecord(i, r))
|
||||
|
||||
|
||||
def print_header(self, f=sys.stdout):
|
||||
@ -533,18 +942,33 @@ class MOBIFile(object): # {{{
|
||||
print (str(self.mobi_header).encode('utf-8'), file=f)
|
||||
# }}}
|
||||
|
||||
def inspect_mobi(path_or_stream):
|
||||
def inspect_mobi(path_or_stream, prefix='decompiled'):
|
||||
stream = (path_or_stream if hasattr(path_or_stream, 'read') else
|
||||
open(path_or_stream, 'rb'))
|
||||
f = MOBIFile(stream)
|
||||
ddir = 'debug_' + os.path.splitext(os.path.basename(stream.name))[0]
|
||||
if not os.path.exists(ddir):
|
||||
ddir = prefix + '_' + os.path.splitext(os.path.basename(stream.name))[0]
|
||||
try:
|
||||
shutil.rmtree(ddir)
|
||||
except:
|
||||
pass
|
||||
os.mkdir(ddir)
|
||||
with open(os.path.join(ddir, 'header.txt'), 'wb') as out:
|
||||
f.print_header(f=out)
|
||||
if f.primary_index_record is not None:
|
||||
with open(os.path.join(ddir, 'primary_index_record.txt'), 'wb') as out:
|
||||
print(str(f.primary_index_record), file=out)
|
||||
if f.index_header is not None:
|
||||
with open(os.path.join(ddir, 'index.txt'), 'wb') as out:
|
||||
print(str(f.index_header), file=out)
|
||||
print('\n\n', file=out)
|
||||
print(str(f.cncx).encode('utf-8'), file=out)
|
||||
print('\n\n', file=out)
|
||||
print(str(f.index_record), file=out)
|
||||
|
||||
for tdir, attr in [('text', 'text_records'), ('images', 'image_records'),
|
||||
('binary', 'binary_records')]:
|
||||
tdir = os.path.join(ddir, tdir)
|
||||
os.mkdir(tdir)
|
||||
for rec in getattr(f, attr):
|
||||
rec.dump(tdir)
|
||||
|
||||
print ('Debug data saved to:', ddir)
|
||||
|
||||
def main():
|
||||
|
||||
@ -933,6 +933,9 @@ class MobiReader(object):
|
||||
continue
|
||||
processed_records.append(i)
|
||||
data = self.sections[i][0]
|
||||
if data[:4] in (b'FLIS', b'FCIS', b'SRCS', b'\xe9\x8e\r\n'):
|
||||
# A FLIS, FCIS, SRCS or EOF record, ignore
|
||||
continue
|
||||
buf = cStringIO.StringIO(data)
|
||||
image_index += 1
|
||||
try:
|
||||
|
||||
@ -1260,11 +1260,11 @@ class MobiWriter(object):
|
||||
data = compress_doc(data)
|
||||
record = StringIO()
|
||||
record.write(data)
|
||||
|
||||
# Marshall's utf-8 break code.
|
||||
if WRITE_PBREAKS :
|
||||
# Write trailing muti-byte sequence if any
|
||||
record.write(overlap)
|
||||
record.write(pack('>B', len(overlap)))
|
||||
|
||||
if WRITE_PBREAKS :
|
||||
nextra = 0
|
||||
pbreak = 0
|
||||
running = offset
|
||||
@ -1642,6 +1642,61 @@ class MobiWriter(object):
|
||||
for record in self._records:
|
||||
self._write(record)
|
||||
|
||||
def _clean_text_value(self, text):
|
||||
if text is not None and text.strip() :
|
||||
text = text.strip()
|
||||
if not isinstance(text, unicode):
|
||||
text = text.decode('utf-8', 'replace')
|
||||
text = normalize(text).encode('utf-8')
|
||||
else :
|
||||
text = "(none)".encode('utf-8')
|
||||
return text
|
||||
|
||||
def _compute_offset_length(self, i, node, entries) :
|
||||
h = node.href
|
||||
if h not in self._id_offsets:
|
||||
self._oeb.log.warning('Could not find TOC entry:', node.title)
|
||||
return -1, -1
|
||||
|
||||
offset = self._id_offsets[h]
|
||||
length = None
|
||||
# Calculate length based on next entry's offset
|
||||
for sibling in entries[i+1:]:
|
||||
h2 = sibling.href
|
||||
if h2 in self._id_offsets:
|
||||
offset2 = self._id_offsets[h2]
|
||||
if offset2 > offset:
|
||||
length = offset2 - offset
|
||||
break
|
||||
if length is None:
|
||||
length = self._content_length - offset
|
||||
return offset, length
|
||||
|
||||
def _establish_document_structure(self) :
|
||||
documentType = None
|
||||
try :
|
||||
klass = self._ctoc_map[0]['klass']
|
||||
except :
|
||||
klass = None
|
||||
|
||||
if klass == 'chapter' or klass == None :
|
||||
documentType = 'book'
|
||||
if self.opts.verbose > 2 :
|
||||
self._oeb.logger.info("Adding a MobiBook to self._MobiDoc")
|
||||
self._MobiDoc.documentStructure = MobiBook()
|
||||
|
||||
elif klass == 'periodical' :
|
||||
documentType = klass
|
||||
if self.opts.verbose > 2 :
|
||||
self._oeb.logger.info("Adding a MobiPeriodical to self._MobiDoc")
|
||||
self._MobiDoc.documentStructure = MobiPeriodical(self._MobiDoc.getNextNode())
|
||||
self._MobiDoc.documentStructure.startAddress = self._anchor_offset_kindle
|
||||
else :
|
||||
raise NotImplementedError('_establish_document_structure: unrecognized klass: %s' % klass)
|
||||
return documentType
|
||||
|
||||
# Index {{{
|
||||
|
||||
def _generate_index(self):
|
||||
self._oeb.log('Generating INDX ...')
|
||||
self._primary_index_record = None
|
||||
@ -1815,276 +1870,7 @@ class MobiWriter(object):
|
||||
open(os.path.join(t, n+'.bin'), 'wb').write(self._records[-(i+1)])
|
||||
self._oeb.log.debug('Index records dumped to', t)
|
||||
|
||||
def _clean_text_value(self, text):
|
||||
if text is not None and text.strip() :
|
||||
text = text.strip()
|
||||
if not isinstance(text, unicode):
|
||||
text = text.decode('utf-8', 'replace')
|
||||
text = normalize(text).encode('utf-8')
|
||||
else :
|
||||
text = "(none)".encode('utf-8')
|
||||
return text
|
||||
|
||||
def _add_to_ctoc(self, ctoc_str, record_offset):
|
||||
# Write vwilen + string to ctoc
|
||||
# Return offset
|
||||
# Is there enough room for this string in the current ctoc record?
|
||||
if 0xfbf8 - self._ctoc.tell() < 2 + len(ctoc_str):
|
||||
# flush this ctoc, start a new one
|
||||
# print "closing ctoc_record at 0x%X" % self._ctoc.tell()
|
||||
# print "starting new ctoc with '%-50.50s ...'" % ctoc_str
|
||||
# pad with 00
|
||||
pad = 0xfbf8 - self._ctoc.tell()
|
||||
# print "padding %d bytes of 00" % pad
|
||||
self._ctoc.write('\0' * (pad))
|
||||
self._ctoc_records.append(self._ctoc.getvalue())
|
||||
self._ctoc.truncate(0)
|
||||
self._ctoc_offset += 0x10000
|
||||
record_offset = self._ctoc_offset
|
||||
|
||||
offset = self._ctoc.tell() + record_offset
|
||||
self._ctoc.write(decint(len(ctoc_str), DECINT_FORWARD) + ctoc_str)
|
||||
return offset
|
||||
|
||||
def _add_flat_ctoc_node(self, node, ctoc, title=None):
|
||||
# Process 'chapter' or 'article' nodes only, force either to 'chapter'
|
||||
t = node.title if title is None else title
|
||||
t = self._clean_text_value(t)
|
||||
self._last_toc_entry = t
|
||||
|
||||
# Create an empty dictionary for this node
|
||||
ctoc_name_map = {}
|
||||
|
||||
# article = chapter
|
||||
if node.klass == 'article' :
|
||||
ctoc_name_map['klass'] = 'chapter'
|
||||
else :
|
||||
ctoc_name_map['klass'] = node.klass
|
||||
|
||||
# Add title offset to name map
|
||||
ctoc_name_map['titleOffset'] = self._add_to_ctoc(t, self._ctoc_offset)
|
||||
self._chapterCount += 1
|
||||
|
||||
# append this node's name_map to map
|
||||
self._ctoc_map.append(ctoc_name_map)
|
||||
|
||||
return
|
||||
|
||||
def _add_structured_ctoc_node(self, node, ctoc, title=None):
|
||||
# Process 'periodical', 'section' and 'article'
|
||||
|
||||
# Fetch the offset referencing the current ctoc_record
|
||||
if node.klass is None :
|
||||
return
|
||||
t = node.title if title is None else title
|
||||
t = self._clean_text_value(t)
|
||||
self._last_toc_entry = t
|
||||
|
||||
# Create an empty dictionary for this node
|
||||
ctoc_name_map = {}
|
||||
|
||||
# Add the klass of this node
|
||||
ctoc_name_map['klass'] = node.klass
|
||||
|
||||
if node.klass == 'chapter':
|
||||
# Add title offset to name map
|
||||
ctoc_name_map['titleOffset'] = self._add_to_ctoc(t, self._ctoc_offset)
|
||||
self._chapterCount += 1
|
||||
|
||||
elif node.klass == 'periodical' :
|
||||
# Add title offset
|
||||
ctoc_name_map['titleOffset'] = self._add_to_ctoc(t, self._ctoc_offset)
|
||||
|
||||
# Look for existing class entry 'periodical' in _ctoc_map
|
||||
for entry in self._ctoc_map:
|
||||
if entry['klass'] == 'periodical':
|
||||
# Use the pre-existing instance
|
||||
ctoc_name_map['classOffset'] = entry['classOffset']
|
||||
break
|
||||
else :
|
||||
continue
|
||||
else:
|
||||
# class names should always be in CNCX 0 - no offset
|
||||
ctoc_name_map['classOffset'] = self._add_to_ctoc(node.klass, 0)
|
||||
|
||||
self._periodicalCount += 1
|
||||
|
||||
elif node.klass == 'section' :
|
||||
# Add title offset
|
||||
ctoc_name_map['titleOffset'] = self._add_to_ctoc(t, self._ctoc_offset)
|
||||
|
||||
# Look for existing class entry 'section' in _ctoc_map
|
||||
for entry in self._ctoc_map:
|
||||
if entry['klass'] == 'section':
|
||||
# Use the pre-existing instance
|
||||
ctoc_name_map['classOffset'] = entry['classOffset']
|
||||
break
|
||||
else :
|
||||
continue
|
||||
else:
|
||||
# class names should always be in CNCX 0 - no offset
|
||||
ctoc_name_map['classOffset'] = self._add_to_ctoc(node.klass, 0)
|
||||
|
||||
self._sectionCount += 1
|
||||
|
||||
elif node.klass == 'article' :
|
||||
# Add title offset/title
|
||||
ctoc_name_map['titleOffset'] = self._add_to_ctoc(t, self._ctoc_offset)
|
||||
|
||||
# Look for existing class entry 'article' in _ctoc_map
|
||||
for entry in self._ctoc_map:
|
||||
if entry['klass'] == 'article':
|
||||
ctoc_name_map['classOffset'] = entry['classOffset']
|
||||
break
|
||||
else :
|
||||
continue
|
||||
else:
|
||||
# class names should always be in CNCX 0 - no offset
|
||||
ctoc_name_map['classOffset'] = self._add_to_ctoc(node.klass, 0)
|
||||
|
||||
# Add description offset/description
|
||||
if node.description :
|
||||
d = self._clean_text_value(node.description)
|
||||
ctoc_name_map['descriptionOffset'] = self._add_to_ctoc(d, self._ctoc_offset)
|
||||
else :
|
||||
ctoc_name_map['descriptionOffset'] = None
|
||||
|
||||
# Add author offset/attribution
|
||||
if node.author :
|
||||
a = self._clean_text_value(node.author)
|
||||
ctoc_name_map['authorOffset'] = self._add_to_ctoc(a, self._ctoc_offset)
|
||||
else :
|
||||
ctoc_name_map['authorOffset'] = None
|
||||
|
||||
self._articleCount += 1
|
||||
|
||||
else :
|
||||
raise NotImplementedError( \
|
||||
'writer._generate_ctoc.add_node: title: %s has unrecognized klass: %s, playOrder: %d' % \
|
||||
(node.title, node.klass, node.play_order))
|
||||
|
||||
# append this node's name_map to map
|
||||
self._ctoc_map.append(ctoc_name_map)
|
||||
|
||||
def _generate_ctoc(self):
|
||||
# Generate the compiled TOC strings
|
||||
# Each node has 1-4 CTOC entries:
|
||||
# Periodical (0xDF)
|
||||
# title, class
|
||||
# Section (0xFF)
|
||||
# title, class
|
||||
# Article (0x3F)
|
||||
# title, class, description, author
|
||||
# Chapter (0x0F)
|
||||
# title, class
|
||||
# nb: Chapters don't actually have @class, so we synthesize it
|
||||
# in reader._toc_from_navpoint
|
||||
|
||||
toc = self._oeb.toc
|
||||
reduced_toc = []
|
||||
self._ctoc_map = [] # per node dictionary of {class/title/desc/author} offsets
|
||||
self._last_toc_entry = None
|
||||
#ctoc = StringIO()
|
||||
self._ctoc = StringIO()
|
||||
|
||||
# Track the individual node types
|
||||
self._periodicalCount = 0
|
||||
self._sectionCount = 0
|
||||
self._articleCount = 0
|
||||
self._chapterCount = 0
|
||||
|
||||
#first = True
|
||||
|
||||
if self._conforming_periodical_toc :
|
||||
self._oeb.logger.info('Generating structured CTOC ...')
|
||||
for (child) in toc.iter():
|
||||
if self.opts.verbose > 2 :
|
||||
self._oeb.logger.info(" %s" % child)
|
||||
self._add_structured_ctoc_node(child, self._ctoc)
|
||||
#first = False
|
||||
|
||||
else :
|
||||
self._oeb.logger.info('Generating flat CTOC ...')
|
||||
previousOffset = -1
|
||||
currentOffset = 0
|
||||
for (i, child) in enumerate(toc.iterdescendants()):
|
||||
# Only add chapters or articles at depth==1
|
||||
# no class defaults to 'chapter'
|
||||
if child.klass is None : child.klass = 'chapter'
|
||||
if (child.klass == 'article' or child.klass == 'chapter') and child.depth() == 1 :
|
||||
if self.opts.verbose > 2 :
|
||||
self._oeb.logger.info("adding (klass:%s depth:%d) %s to flat ctoc" % \
|
||||
(child.klass, child.depth(), child) )
|
||||
|
||||
# Test to see if this child's offset is the same as the previous child's
|
||||
# offset, skip it
|
||||
h = child.href
|
||||
|
||||
if h is None:
|
||||
self._oeb.logger.warn(' Ignoring TOC entry with no href:',
|
||||
child.title)
|
||||
continue
|
||||
if h not in self._id_offsets:
|
||||
self._oeb.logger.warn(' Ignoring missing TOC entry:',
|
||||
unicode(child))
|
||||
continue
|
||||
|
||||
currentOffset = self._id_offsets[h]
|
||||
# print "_generate_ctoc: child offset: 0x%X" % currentOffset
|
||||
|
||||
if currentOffset != previousOffset :
|
||||
self._add_flat_ctoc_node(child, self._ctoc)
|
||||
reduced_toc.append(child)
|
||||
previousOffset = currentOffset
|
||||
else :
|
||||
self._oeb.logger.warn(" Ignoring redundant href: %s in '%s'" % (h, child.title))
|
||||
|
||||
else :
|
||||
if self.opts.verbose > 2 :
|
||||
self._oeb.logger.info("skipping class: %s depth %d at position %d" % \
|
||||
(child.klass, child.depth(),i))
|
||||
|
||||
# Update the TOC with our edited version
|
||||
self._oeb.toc.nodes = reduced_toc
|
||||
|
||||
# Instantiate a MobiDocument(mobitype)
|
||||
if (not self._periodicalCount and not self._sectionCount and not self._articleCount) or \
|
||||
not self.opts.mobi_periodical :
|
||||
mobiType = 0x002
|
||||
elif self._periodicalCount:
|
||||
pt = None
|
||||
if self._oeb.metadata.publication_type:
|
||||
x = unicode(self._oeb.metadata.publication_type[0]).split(':')
|
||||
if len(x) > 1:
|
||||
pt = x[1]
|
||||
mobiType = {'newspaper':0x101}.get(pt, 0x103)
|
||||
else :
|
||||
raise NotImplementedError('_generate_ctoc: Unrecognized document structured')
|
||||
|
||||
self._MobiDoc = MobiDocument(mobiType)
|
||||
|
||||
if self.opts.verbose > 2 :
|
||||
structType = 'book'
|
||||
if mobiType > 0x100 :
|
||||
structType = 'flat periodical' if mobiType == 0x102 else 'structured periodical'
|
||||
self._oeb.logger.info("Instantiating a %s MobiDocument of type 0x%X" % (structType, mobiType ) )
|
||||
if mobiType > 0x100 :
|
||||
self._oeb.logger.info("periodicalCount: %d sectionCount: %d articleCount: %d"% \
|
||||
(self._periodicalCount, self._sectionCount, self._articleCount) )
|
||||
else :
|
||||
self._oeb.logger.info("chapterCount: %d" % self._chapterCount)
|
||||
|
||||
# Apparently the CTOC must end with a null byte
|
||||
self._ctoc.write('\0')
|
||||
|
||||
ctoc = self._ctoc.getvalue()
|
||||
rec_count = len(self._ctoc_records)
|
||||
self._oeb.logger.info(" CNCX utilization: %d %s %.0f%% full" % \
|
||||
(rec_count + 1, 'records, last record' if rec_count else 'record,',
|
||||
len(ctoc)/655) )
|
||||
|
||||
return align_block(ctoc)
|
||||
|
||||
# Index nodes {{{
|
||||
def _write_periodical_node(self, indxt, indices, index, offset, length, count, firstSection, lastSection) :
|
||||
pos = 0xc0 + indxt.tell()
|
||||
indices.write(pack('>H', pos)) # Save the offset for IDXTIndices
|
||||
@ -2176,48 +1962,8 @@ class MobiWriter(object):
|
||||
indxt.write(decint(self._ctoc_map[index]['titleOffset'], DECINT_FORWARD)) # vwi title offset in CNCX
|
||||
indxt.write(decint(0, DECINT_FORWARD)) # unknown byte
|
||||
|
||||
def _compute_offset_length(self, i, node, entries) :
|
||||
h = node.href
|
||||
if h not in self._id_offsets:
|
||||
self._oeb.log.warning('Could not find TOC entry:', node.title)
|
||||
return -1, -1
|
||||
# }}}
|
||||
|
||||
offset = self._id_offsets[h]
|
||||
length = None
|
||||
# Calculate length based on next entry's offset
|
||||
for sibling in entries[i+1:]:
|
||||
h2 = sibling.href
|
||||
if h2 in self._id_offsets:
|
||||
offset2 = self._id_offsets[h2]
|
||||
if offset2 > offset:
|
||||
length = offset2 - offset
|
||||
break
|
||||
if length is None:
|
||||
length = self._content_length - offset
|
||||
return offset, length
|
||||
|
||||
def _establish_document_structure(self) :
|
||||
documentType = None
|
||||
try :
|
||||
klass = self._ctoc_map[0]['klass']
|
||||
except :
|
||||
klass = None
|
||||
|
||||
if klass == 'chapter' or klass == None :
|
||||
documentType = 'book'
|
||||
if self.opts.verbose > 2 :
|
||||
self._oeb.logger.info("Adding a MobiBook to self._MobiDoc")
|
||||
self._MobiDoc.documentStructure = MobiBook()
|
||||
|
||||
elif klass == 'periodical' :
|
||||
documentType = klass
|
||||
if self.opts.verbose > 2 :
|
||||
self._oeb.logger.info("Adding a MobiPeriodical to self._MobiDoc")
|
||||
self._MobiDoc.documentStructure = MobiPeriodical(self._MobiDoc.getNextNode())
|
||||
self._MobiDoc.documentStructure.startAddress = self._anchor_offset_kindle
|
||||
else :
|
||||
raise NotImplementedError('_establish_document_structure: unrecognized klass: %s' % klass)
|
||||
return documentType
|
||||
|
||||
def _generate_section_indices(self, child, currentSection, myPeriodical, myDoc ) :
|
||||
sectionTitles = list(child.iter())[1:]
|
||||
@ -2495,6 +2241,270 @@ class MobiWriter(object):
|
||||
last_name, c = self._add_periodical_structured_articles(myDoc, indxt, indices)
|
||||
|
||||
return align_block(indxt.getvalue()), c, align_block(indices.getvalue()), last_name
|
||||
# }}}
|
||||
|
||||
# CTOC {{{
|
||||
def _add_to_ctoc(self, ctoc_str, record_offset):
|
||||
# Write vwilen + string to ctoc
|
||||
# Return offset
|
||||
# Is there enough room for this string in the current ctoc record?
|
||||
if 0xfbf8 - self._ctoc.tell() < 2 + len(ctoc_str):
|
||||
# flush this ctoc, start a new one
|
||||
# print "closing ctoc_record at 0x%X" % self._ctoc.tell()
|
||||
# print "starting new ctoc with '%-50.50s ...'" % ctoc_str
|
||||
# pad with 00
|
||||
pad = 0xfbf8 - self._ctoc.tell()
|
||||
# print "padding %d bytes of 00" % pad
|
||||
self._ctoc.write('\0' * (pad))
|
||||
self._ctoc_records.append(self._ctoc.getvalue())
|
||||
self._ctoc.truncate(0)
|
||||
self._ctoc_offset += 0x10000
|
||||
record_offset = self._ctoc_offset
|
||||
|
||||
offset = self._ctoc.tell() + record_offset
|
||||
self._ctoc.write(decint(len(ctoc_str), DECINT_FORWARD) + ctoc_str)
|
||||
return offset
|
||||
|
||||
def _add_flat_ctoc_node(self, node, ctoc, title=None):
|
||||
# Process 'chapter' or 'article' nodes only, force either to 'chapter'
|
||||
t = node.title if title is None else title
|
||||
t = self._clean_text_value(t)
|
||||
self._last_toc_entry = t
|
||||
|
||||
# Create an empty dictionary for this node
|
||||
ctoc_name_map = {}
|
||||
|
||||
# article = chapter
|
||||
if node.klass == 'article' :
|
||||
ctoc_name_map['klass'] = 'chapter'
|
||||
else :
|
||||
ctoc_name_map['klass'] = node.klass
|
||||
|
||||
# Add title offset to name map
|
||||
ctoc_name_map['titleOffset'] = self._add_to_ctoc(t, self._ctoc_offset)
|
||||
self._chapterCount += 1
|
||||
|
||||
# append this node's name_map to map
|
||||
self._ctoc_map.append(ctoc_name_map)
|
||||
|
||||
return
|
||||
|
||||
def _add_structured_ctoc_node(self, node, ctoc, title=None):
|
||||
# Process 'periodical', 'section' and 'article'
|
||||
|
||||
# Fetch the offset referencing the current ctoc_record
|
||||
if node.klass is None :
|
||||
return
|
||||
t = node.title if title is None else title
|
||||
t = self._clean_text_value(t)
|
||||
self._last_toc_entry = t
|
||||
|
||||
# Create an empty dictionary for this node
|
||||
ctoc_name_map = {}
|
||||
|
||||
# Add the klass of this node
|
||||
ctoc_name_map['klass'] = node.klass
|
||||
|
||||
if node.klass == 'chapter':
|
||||
# Add title offset to name map
|
||||
ctoc_name_map['titleOffset'] = self._add_to_ctoc(t, self._ctoc_offset)
|
||||
self._chapterCount += 1
|
||||
|
||||
elif node.klass == 'periodical' :
|
||||
# Add title offset
|
||||
ctoc_name_map['titleOffset'] = self._add_to_ctoc(t, self._ctoc_offset)
|
||||
|
||||
# Look for existing class entry 'periodical' in _ctoc_map
|
||||
for entry in self._ctoc_map:
|
||||
if entry['klass'] == 'periodical':
|
||||
# Use the pre-existing instance
|
||||
ctoc_name_map['classOffset'] = entry['classOffset']
|
||||
break
|
||||
else :
|
||||
continue
|
||||
else:
|
||||
# class names should always be in CNCX 0 - no offset
|
||||
ctoc_name_map['classOffset'] = self._add_to_ctoc(node.klass, 0)
|
||||
|
||||
self._periodicalCount += 1
|
||||
|
||||
elif node.klass == 'section' :
|
||||
# Add title offset
|
||||
ctoc_name_map['titleOffset'] = self._add_to_ctoc(t, self._ctoc_offset)
|
||||
|
||||
# Look for existing class entry 'section' in _ctoc_map
|
||||
for entry in self._ctoc_map:
|
||||
if entry['klass'] == 'section':
|
||||
# Use the pre-existing instance
|
||||
ctoc_name_map['classOffset'] = entry['classOffset']
|
||||
break
|
||||
else :
|
||||
continue
|
||||
else:
|
||||
# class names should always be in CNCX 0 - no offset
|
||||
ctoc_name_map['classOffset'] = self._add_to_ctoc(node.klass, 0)
|
||||
|
||||
self._sectionCount += 1
|
||||
|
||||
elif node.klass == 'article' :
|
||||
# Add title offset/title
|
||||
ctoc_name_map['titleOffset'] = self._add_to_ctoc(t, self._ctoc_offset)
|
||||
|
||||
# Look for existing class entry 'article' in _ctoc_map
|
||||
for entry in self._ctoc_map:
|
||||
if entry['klass'] == 'article':
|
||||
ctoc_name_map['classOffset'] = entry['classOffset']
|
||||
break
|
||||
else :
|
||||
continue
|
||||
else:
|
||||
# class names should always be in CNCX 0 - no offset
|
||||
ctoc_name_map['classOffset'] = self._add_to_ctoc(node.klass, 0)
|
||||
|
||||
# Add description offset/description
|
||||
if node.description :
|
||||
d = self._clean_text_value(node.description)
|
||||
ctoc_name_map['descriptionOffset'] = self._add_to_ctoc(d, self._ctoc_offset)
|
||||
else :
|
||||
ctoc_name_map['descriptionOffset'] = None
|
||||
|
||||
# Add author offset/attribution
|
||||
if node.author :
|
||||
a = self._clean_text_value(node.author)
|
||||
ctoc_name_map['authorOffset'] = self._add_to_ctoc(a, self._ctoc_offset)
|
||||
else :
|
||||
ctoc_name_map['authorOffset'] = None
|
||||
|
||||
self._articleCount += 1
|
||||
|
||||
else :
|
||||
raise NotImplementedError( \
|
||||
'writer._generate_ctoc.add_node: title: %s has unrecognized klass: %s, playOrder: %d' % \
|
||||
(node.title, node.klass, node.play_order))
|
||||
|
||||
# append this node's name_map to map
|
||||
self._ctoc_map.append(ctoc_name_map)
|
||||
|
||||
def _generate_ctoc(self):
|
||||
# Generate the compiled TOC strings
|
||||
# Each node has 1-4 CTOC entries:
|
||||
# Periodical (0xDF)
|
||||
# title, class
|
||||
# Section (0xFF)
|
||||
# title, class
|
||||
# Article (0x3F)
|
||||
# title, class, description, author
|
||||
# Chapter (0x0F)
|
||||
# title, class
|
||||
# nb: Chapters don't actually have @class, so we synthesize it
|
||||
# in reader._toc_from_navpoint
|
||||
|
||||
toc = self._oeb.toc
|
||||
reduced_toc = []
|
||||
self._ctoc_map = [] # per node dictionary of {class/title/desc/author} offsets
|
||||
self._last_toc_entry = None
|
||||
#ctoc = StringIO()
|
||||
self._ctoc = StringIO()
|
||||
|
||||
# Track the individual node types
|
||||
self._periodicalCount = 0
|
||||
self._sectionCount = 0
|
||||
self._articleCount = 0
|
||||
self._chapterCount = 0
|
||||
|
||||
#first = True
|
||||
|
||||
if self._conforming_periodical_toc :
|
||||
self._oeb.logger.info('Generating structured CTOC ...')
|
||||
for (child) in toc.iter():
|
||||
if self.opts.verbose > 2 :
|
||||
self._oeb.logger.info(" %s" % child)
|
||||
self._add_structured_ctoc_node(child, self._ctoc)
|
||||
#first = False
|
||||
|
||||
else :
|
||||
self._oeb.logger.info('Generating flat CTOC ...')
|
||||
previousOffset = -1
|
||||
currentOffset = 0
|
||||
for (i, child) in enumerate(toc.iterdescendants()):
|
||||
# Only add chapters or articles at depth==1
|
||||
# no class defaults to 'chapter'
|
||||
if child.klass is None : child.klass = 'chapter'
|
||||
if (child.klass == 'article' or child.klass == 'chapter') and child.depth() == 1 :
|
||||
if self.opts.verbose > 2 :
|
||||
self._oeb.logger.info("adding (klass:%s depth:%d) %s to flat ctoc" % \
|
||||
(child.klass, child.depth(), child) )
|
||||
|
||||
# Test to see if this child's offset is the same as the previous child's
|
||||
# offset, skip it
|
||||
h = child.href
|
||||
|
||||
if h is None:
|
||||
self._oeb.logger.warn(' Ignoring TOC entry with no href:',
|
||||
child.title)
|
||||
continue
|
||||
if h not in self._id_offsets:
|
||||
self._oeb.logger.warn(' Ignoring missing TOC entry:',
|
||||
unicode(child))
|
||||
continue
|
||||
|
||||
currentOffset = self._id_offsets[h]
|
||||
# print "_generate_ctoc: child offset: 0x%X" % currentOffset
|
||||
|
||||
if currentOffset != previousOffset :
|
||||
self._add_flat_ctoc_node(child, self._ctoc)
|
||||
reduced_toc.append(child)
|
||||
previousOffset = currentOffset
|
||||
else :
|
||||
self._oeb.logger.warn(" Ignoring redundant href: %s in '%s'" % (h, child.title))
|
||||
|
||||
else :
|
||||
if self.opts.verbose > 2 :
|
||||
self._oeb.logger.info("skipping class: %s depth %d at position %d" % \
|
||||
(child.klass, child.depth(),i))
|
||||
|
||||
# Update the TOC with our edited version
|
||||
self._oeb.toc.nodes = reduced_toc
|
||||
|
||||
# Instantiate a MobiDocument(mobitype)
|
||||
if (not self._periodicalCount and not self._sectionCount and not self._articleCount) or \
|
||||
not self.opts.mobi_periodical :
|
||||
mobiType = 0x002
|
||||
elif self._periodicalCount:
|
||||
pt = None
|
||||
if self._oeb.metadata.publication_type:
|
||||
x = unicode(self._oeb.metadata.publication_type[0]).split(':')
|
||||
if len(x) > 1:
|
||||
pt = x[1]
|
||||
mobiType = {'newspaper':0x101}.get(pt, 0x103)
|
||||
else :
|
||||
raise NotImplementedError('_generate_ctoc: Unrecognized document structured')
|
||||
|
||||
self._MobiDoc = MobiDocument(mobiType)
|
||||
|
||||
if self.opts.verbose > 2 :
|
||||
structType = 'book'
|
||||
if mobiType > 0x100 :
|
||||
structType = 'flat periodical' if mobiType == 0x102 else 'structured periodical'
|
||||
self._oeb.logger.info("Instantiating a %s MobiDocument of type 0x%X" % (structType, mobiType ) )
|
||||
if mobiType > 0x100 :
|
||||
self._oeb.logger.info("periodicalCount: %d sectionCount: %d articleCount: %d"% \
|
||||
(self._periodicalCount, self._sectionCount, self._articleCount) )
|
||||
else :
|
||||
self._oeb.logger.info("chapterCount: %d" % self._chapterCount)
|
||||
|
||||
# Apparently the CTOC must end with a null byte
|
||||
self._ctoc.write('\0')
|
||||
|
||||
ctoc = self._ctoc.getvalue()
|
||||
rec_count = len(self._ctoc_records)
|
||||
self._oeb.logger.info(" CNCX utilization: %d %s %.0f%% full" % \
|
||||
(rec_count + 1, 'records, last record' if rec_count else 'record,',
|
||||
len(ctoc)/655) )
|
||||
|
||||
return align_block(ctoc)
|
||||
|
||||
# }}}
|
||||
|
||||
class HTMLRecordData(object):
|
||||
""" A data structure containing indexing/navigation data for an HTML record """
|
||||
|
||||
@ -15,10 +15,10 @@ from calibre.ebooks import normalize
|
||||
from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
|
||||
from calibre.ebooks.mobi.writer2.serializer import Serializer
|
||||
from calibre.ebooks.compression.palmdoc import compress_doc
|
||||
from calibre.utils.magick.draw import Image, save_cover_data_to, thumbnail
|
||||
from calibre.ebooks.mobi.langcodes import iana2mobi
|
||||
from calibre.utils.filenames import ascii_filename
|
||||
from calibre.ebooks.mobi.writer2 import PALMDOC, UNCOMPRESSED
|
||||
from calibre.ebooks.mobi.writer2.utils import (rescale_image, encint)
|
||||
|
||||
EXTH_CODES = {
|
||||
'creator': 100,
|
||||
@ -41,87 +41,10 @@ WRITE_UNCROSSABLE_BREAKS = False
|
||||
|
||||
RECORD_SIZE = 0x1000 # 4096
|
||||
|
||||
IMAGE_MAX_SIZE = 10 * 1024 * 1024
|
||||
|
||||
MAX_THUMB_SIZE = 16 * 1024
|
||||
MAX_THUMB_DIMEN = (180, 240)
|
||||
|
||||
# Almost like the one for MS LIT, but not quite.
|
||||
DECINT_FORWARD = 0
|
||||
DECINT_BACKWARD = 1
|
||||
|
||||
def decint(value, direction):
|
||||
'''
|
||||
Some parts of the Mobipocket format encode data as variable-width integers.
|
||||
These integers are represented big-endian with 7 bits per byte in bits 1-7.
|
||||
They may be either forward-encoded, in which case only the LSB has bit 8 set,
|
||||
or backward-encoded, in which case only the MSB has bit 8 set.
|
||||
For example, the number 0x11111 would be represented forward-encoded as:
|
||||
|
||||
0x04 0x22 0x91
|
||||
|
||||
And backward-encoded as:
|
||||
|
||||
0x84 0x22 0x11
|
||||
|
||||
This function encodes the integer ``value`` as a variable width integer and
|
||||
returns the bytestring corresponding to it.
|
||||
'''
|
||||
# Encode vwi
|
||||
byts = bytearray()
|
||||
while True:
|
||||
b = value & 0x7f
|
||||
value >>= 7
|
||||
byts.append(b)
|
||||
if value == 0:
|
||||
break
|
||||
if direction == DECINT_FORWARD:
|
||||
byts[0] |= 0x80
|
||||
elif direction == DECINT_BACKWARD:
|
||||
byts[-1] |= 0x80
|
||||
return bytes(byts)
|
||||
|
||||
def rescale_image(data, maxsizeb=IMAGE_MAX_SIZE, dimen=None):
|
||||
'''
|
||||
Convert image setting all transparent pixels to white and changing format
|
||||
to JPEG. Ensure the resultant image has a byte size less than
|
||||
maxsizeb.
|
||||
|
||||
If dimen is not None, generate a thumbnail of width=dimen, height=dimen
|
||||
|
||||
Returns the image as a bytestring
|
||||
'''
|
||||
if dimen is not None:
|
||||
data = thumbnail(data, width=dimen, height=dimen,
|
||||
compression_quality=90)[-1]
|
||||
else:
|
||||
# Replace transparent pixels with white pixels and convert to JPEG
|
||||
data = save_cover_data_to(data, 'img.jpg', return_data=True)
|
||||
if len(data) <= maxsizeb:
|
||||
return data
|
||||
orig_data = data
|
||||
img = Image()
|
||||
quality = 95
|
||||
|
||||
img.load(data)
|
||||
while len(data) >= maxsizeb and quality >= 10:
|
||||
quality -= 5
|
||||
img.set_compression_quality(quality)
|
||||
data = img.export('jpg')
|
||||
if len(data) <= maxsizeb:
|
||||
return data
|
||||
orig_data = data
|
||||
|
||||
scale = 0.9
|
||||
while len(data) >= maxsizeb and scale >= 0.05:
|
||||
img = Image()
|
||||
img.load(orig_data)
|
||||
w, h = img.size
|
||||
img.size = (int(scale*w), int(scale*h))
|
||||
img.set_compression_quality(quality)
|
||||
data = img.export('jpg')
|
||||
scale -= 0.05
|
||||
return data
|
||||
|
||||
class MobiWriter(object):
|
||||
COLLAPSE_RE = re.compile(r'[ \t\r\n\v]+')
|
||||
|
||||
@ -243,13 +166,13 @@ class MobiWriter(object):
|
||||
# the next record.
|
||||
while breaks and (breaks[0] - offset) < RECORD_SIZE:
|
||||
pbreak = (breaks.pop(0) - running) >> 3
|
||||
encoded = decint(pbreak, DECINT_FORWARD)
|
||||
encoded = encint(pbreak)
|
||||
record.write(encoded)
|
||||
running += pbreak << 3
|
||||
nextra += len(encoded)
|
||||
lsize = 1
|
||||
while True:
|
||||
size = decint(nextra + lsize, DECINT_BACKWARD)
|
||||
size = encint(nextra + lsize, forward=False)
|
||||
if len(size) == lsize:
|
||||
break
|
||||
lsize += 1
|
||||
|
||||
177
src/calibre/ebooks/mobi/writer2/utils.py
Normal file
177
src/calibre/ebooks/mobi/writer2/utils.py
Normal file
@ -0,0 +1,177 @@
|
||||
#!/usr/bin/env python
|
||||
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
|
||||
from __future__ import (unicode_literals, division, absolute_import,
|
||||
print_function)
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import struct
|
||||
from collections import OrderedDict
|
||||
|
||||
from calibre.utils.magick.draw import Image, save_cover_data_to, thumbnail
|
||||
|
||||
IMAGE_MAX_SIZE = 10 * 1024 * 1024
|
||||
|
||||
def decode_hex_number(raw):
|
||||
'''
|
||||
Return a variable length number encoded using hexadecimal encoding. These
|
||||
numbers have the first byte which tells the number of bytes that follow.
|
||||
The bytes that follow are simply the hexadecimal representation of the
|
||||
number.
|
||||
|
||||
:param raw: Raw binary data as a bytestring
|
||||
|
||||
:return: The number and the number of bytes from raw that the number
|
||||
occupies
|
||||
'''
|
||||
length, = struct.unpack(b'>B', raw[0])
|
||||
raw = raw[1:1+length]
|
||||
consumed = length+1
|
||||
return int(raw, 16), consumed
|
||||
|
||||
def encode_number_as_hex(num):
|
||||
'''
|
||||
Encode num as a variable length encoded hexadecimal number. Returns the
|
||||
bytestring containing the encoded number. These
|
||||
numbers have the first byte which tells the number of bytes that follow.
|
||||
The bytes that follow are simply the hexadecimal representation of the
|
||||
number.
|
||||
'''
|
||||
num = bytes(hex(num)[2:])
|
||||
ans = bytearray(num)
|
||||
ans.insert(0, len(num))
|
||||
return bytes(ans)
|
||||
|
||||
def encint(value, forward=True):
|
||||
'''
|
||||
Some parts of the Mobipocket format encode data as variable-width integers.
|
||||
These integers are represented big-endian with 7 bits per byte in bits 1-7.
|
||||
They may be either forward-encoded, in which case only the first byte has bit 8 set,
|
||||
or backward-encoded, in which case only the last byte has bit 8 set.
|
||||
For example, the number 0x11111 = 0b10001000100010001 would be represented
|
||||
forward-encoded as:
|
||||
|
||||
0x04 0x22 0x91 = 0b100 0b100010 0b10010001
|
||||
|
||||
And backward-encoded as:
|
||||
|
||||
0x84 0x22 0x11 = 0b10000100 0b100010 0b10001
|
||||
|
||||
This function encodes the integer ``value`` as a variable width integer and
|
||||
returns the bytestring corresponding to it.
|
||||
|
||||
If forward is True the bytes returned are suitable for prepending to the
|
||||
output buffer, otherwise they must be append to the output buffer.
|
||||
'''
|
||||
# Encode vwi
|
||||
byts = bytearray()
|
||||
while True:
|
||||
b = value & 0b01111111
|
||||
value >>= 7 # shift value to the right by 7 bits
|
||||
byts.append(b)
|
||||
if value == 0:
|
||||
break
|
||||
byts[0 if forward else -1] |= 0b10000000
|
||||
byts.reverse()
|
||||
return bytes(byts)
|
||||
|
||||
def decint(raw, forward=True):
|
||||
'''
|
||||
Read a variable width integer from the bytestring raw and return the
|
||||
integer and the number of bytes read. If forward is True bytes are read
|
||||
from the start of raw, otherwise from the end of raw.
|
||||
|
||||
This function is the inverse of encint above, see its docs for more
|
||||
details.
|
||||
'''
|
||||
val = 0
|
||||
byts = bytearray()
|
||||
for byte in raw if forward else reversed(raw):
|
||||
bnum = ord(byte)
|
||||
byts.append(bnum & 0b01111111)
|
||||
if bnum & 0b10000000:
|
||||
break
|
||||
if not forward:
|
||||
byts.reverse()
|
||||
for byte in byts:
|
||||
val <<= 7 # Shift value to the left by 7 bits
|
||||
val |= byte
|
||||
|
||||
return val, len(byts)
|
||||
|
||||
def test_decint(num):
|
||||
for d in (True, False):
|
||||
raw = encint(num, forward=d)
|
||||
sz = len(raw)
|
||||
if (num, sz) != decint(raw, forward=d):
|
||||
raise ValueError('Failed for num %d, forward=%r: %r != %r' % (
|
||||
num, d, (num, sz), decint(raw, forward=d)))
|
||||
|
||||
def rescale_image(data, maxsizeb=IMAGE_MAX_SIZE, dimen=None):
|
||||
'''
|
||||
Convert image setting all transparent pixels to white and changing format
|
||||
to JPEG. Ensure the resultant image has a byte size less than
|
||||
maxsizeb.
|
||||
|
||||
If dimen is not None, generate a thumbnail of width=dimen, height=dimen
|
||||
|
||||
Returns the image as a bytestring
|
||||
'''
|
||||
if dimen is not None:
|
||||
data = thumbnail(data, width=dimen, height=dimen,
|
||||
compression_quality=90)[-1]
|
||||
else:
|
||||
# Replace transparent pixels with white pixels and convert to JPEG
|
||||
data = save_cover_data_to(data, 'img.jpg', return_data=True)
|
||||
if len(data) <= maxsizeb:
|
||||
return data
|
||||
orig_data = data
|
||||
img = Image()
|
||||
quality = 95
|
||||
|
||||
img.load(data)
|
||||
while len(data) >= maxsizeb and quality >= 10:
|
||||
quality -= 5
|
||||
img.set_compression_quality(quality)
|
||||
data = img.export('jpg')
|
||||
if len(data) <= maxsizeb:
|
||||
return data
|
||||
orig_data = data
|
||||
|
||||
scale = 0.9
|
||||
while len(data) >= maxsizeb and scale >= 0.05:
|
||||
img = Image()
|
||||
img.load(orig_data)
|
||||
w, h = img.size
|
||||
img.size = (int(scale*w), int(scale*h))
|
||||
img.set_compression_quality(quality)
|
||||
data = img.export('jpg')
|
||||
scale -= 0.05
|
||||
return data
|
||||
|
||||
def get_trailing_data(record, extra_data_flags):
|
||||
'''
|
||||
Given a text record as a bytestring and the extra data flags from the MOBI
|
||||
header, return the trailing data as a dictionary, mapping bit number to
|
||||
data as bytestring. Also returns the record - all trailing data.
|
||||
|
||||
:return: Trailing data, record - trailing data
|
||||
'''
|
||||
data = OrderedDict()
|
||||
for i in xrange(16, -1, -1):
|
||||
flag = 2**i
|
||||
if flag & extra_data_flags:
|
||||
if i == 0:
|
||||
# Only the first two bits are used for the size since there can
|
||||
# never be more than 3 trailing multibyte chars
|
||||
sz = (ord(record[-1]) & 0b11) + 1
|
||||
consumed = 1
|
||||
else:
|
||||
sz, consumed = decint(record, forward=False)
|
||||
if sz > consumed:
|
||||
data[i] = record[-sz:-consumed]
|
||||
record = record[:-sz]
|
||||
return data, record
|
||||
|
||||
@ -163,6 +163,8 @@ class OEBReader(object):
|
||||
if item.media_type in check:
|
||||
try:
|
||||
item.data
|
||||
except KeyboardInterrupt:
|
||||
raise
|
||||
except:
|
||||
self.logger.exception('Failed to parse content in %s'%
|
||||
item.href)
|
||||
@ -186,8 +188,13 @@ class OEBReader(object):
|
||||
href, _ = urldefrag(href)
|
||||
if not href:
|
||||
continue
|
||||
try:
|
||||
href = item.abshref(urlnormalize(href))
|
||||
scheme = urlparse(href).scheme
|
||||
except:
|
||||
self.oeb.log.exception(
|
||||
'Skipping invalid href: %r'%href)
|
||||
continue
|
||||
if not scheme and href not in known:
|
||||
new.add(href)
|
||||
elif item.media_type in OEB_STYLES:
|
||||
|
||||
@ -47,15 +47,19 @@ def meta_info_to_oeb_metadata(mi, m, log, override_input_metadata=False):
|
||||
m.add('series', mi.series)
|
||||
elif override_input_metadata:
|
||||
m.clear('series')
|
||||
if not mi.is_null('isbn'):
|
||||
identifiers = mi.get_identifiers()
|
||||
set_isbn = False
|
||||
for typ, val in identifiers.iteritems():
|
||||
has = False
|
||||
if typ.lower() == 'isbn':
|
||||
set_isbn = True
|
||||
for x in m.identifier:
|
||||
if x.scheme.lower() == 'isbn':
|
||||
x.content = mi.isbn
|
||||
if x.scheme.lower() == typ.lower():
|
||||
x.content = val
|
||||
has = True
|
||||
if not has:
|
||||
m.add('identifier', mi.isbn, scheme='ISBN')
|
||||
elif override_input_metadata:
|
||||
m.add('identifier', val, scheme=typ.upper())
|
||||
if override_input_metadata and not set_isbn:
|
||||
m.filter('identifier', lambda x: x.scheme.lower() == 'isbn')
|
||||
if not mi.is_null('language'):
|
||||
m.clear('language')
|
||||
|
||||
@ -47,7 +47,10 @@ class ManifestTrimmer(object):
|
||||
item.data is not None:
|
||||
hrefs = [r[2] for r in iterlinks(item.data)]
|
||||
for href in hrefs:
|
||||
try:
|
||||
href = item.abshref(urlnormalize(href))
|
||||
except:
|
||||
continue
|
||||
if href in oeb.manifest.hrefs:
|
||||
found = oeb.manifest.hrefs[href]
|
||||
if found not in used:
|
||||
|
||||
@ -7,8 +7,8 @@ __docformat__ = 'restructuredtext en'
|
||||
import re, os
|
||||
|
||||
from PyQt4.QtCore import SIGNAL, Qt, pyqtSignal
|
||||
from PyQt4.QtGui import QDialog, QWidget, QDialogButtonBox, \
|
||||
QBrush, QTextCursor, QTextEdit
|
||||
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
|
||||
@ -16,6 +16,7 @@ from calibre.gui2 import error_dialog, choose_files
|
||||
from calibre.ebooks.oeb.iterator import EbookIterator
|
||||
from calibre.ebooks.conversion.preprocess import HTMLPreProcessor
|
||||
from calibre.gui2.dialogs.choose_format import ChooseFormatDialog
|
||||
from calibre.constants import iswindows
|
||||
|
||||
class RegexBuilder(QDialog, Ui_RegexBuilder):
|
||||
|
||||
@ -134,8 +135,18 @@ class RegexBuilder(QDialog, Ui_RegexBuilder):
|
||||
_('Cannot build regex using the GUI builder without a book.'),
|
||||
show=True)
|
||||
return False
|
||||
try:
|
||||
fpath = db.format(book_id, format, index_is_id=True,
|
||||
as_path=True)
|
||||
except OSError:
|
||||
if iswindows:
|
||||
import traceback
|
||||
error_dialog(self, _('Could not open file'),
|
||||
_('Could not open the file, do you have it open in'
|
||||
' another program?'), show=True,
|
||||
det_msg=traceback.format_exc())
|
||||
return False
|
||||
raise
|
||||
try:
|
||||
self.open_book(fpath)
|
||||
finally:
|
||||
|
||||
@ -4,3 +4,4 @@ or asked not to be included in the store integration.
|
||||
* Borders (http://www.borders.com/).
|
||||
* Indigo (http://www.chapters.indigo.ca/).
|
||||
* Libraria Rizzoli (http://libreriarizzoli.corriere.it/).
|
||||
* EPubBuy DE: reason: too much traffic for too little sales
|
||||
|
||||
78
src/calibre/gui2/store/stores/bookoteka_plugin.py
Normal file
78
src/calibre/gui2/store/stores/bookoteka_plugin.py
Normal file
@ -0,0 +1,78 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from __future__ import (unicode_literals, division, absolute_import, print_function)
|
||||
|
||||
__license__ = 'GPL 3'
|
||||
__copyright__ = '2011, Tomasz Długosz <tomek3d@gmail.com>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import re
|
||||
import urllib
|
||||
from contextlib import closing
|
||||
|
||||
from lxml import html
|
||||
|
||||
from PyQt4.Qt import QUrl
|
||||
|
||||
from calibre import browser, url_slash_cleaner
|
||||
from calibre.gui2 import open_url
|
||||
from calibre.gui2.store import StorePlugin
|
||||
from calibre.gui2.store.basic_config import BasicStoreConfig
|
||||
from calibre.gui2.store.search_result import SearchResult
|
||||
from calibre.gui2.store.web_store_dialog import WebStoreDialog
|
||||
|
||||
class BookotekaStore(BasicStoreConfig, StorePlugin):
|
||||
|
||||
def open(self, parent=None, detail_item=None, external=False):
|
||||
|
||||
url = 'http://bookoteka.pl/ebooki'
|
||||
detail_url = None
|
||||
|
||||
if detail_item:
|
||||
detail_url = detail_item
|
||||
|
||||
if external or self.config.get('open_external', False):
|
||||
open_url(QUrl(url_slash_cleaner(detail_url if detail_url else url)))
|
||||
else:
|
||||
d = WebStoreDialog(self.gui, url, parent, detail_url)
|
||||
d.setWindowTitle(self.name)
|
||||
d.set_tags(self.config.get('tags', ''))
|
||||
d.exec_()
|
||||
|
||||
def search(self, query, max_results=10, timeout=60):
|
||||
url = 'http://bookoteka.pl/list?search=' + urllib.quote_plus(query) + '&cat=1&hp=1&type=1'
|
||||
|
||||
br = browser()
|
||||
|
||||
counter = max_results
|
||||
with closing(br.open(url, timeout=timeout)) as f:
|
||||
doc = html.fromstring(f.read())
|
||||
for data in doc.xpath('//li[@class="EBOOK"]'):
|
||||
if counter <= 0:
|
||||
break
|
||||
|
||||
id = ''.join(data.xpath('.//a[@class="item_link"]/@href'))
|
||||
if not id:
|
||||
continue
|
||||
|
||||
cover_url = ''.join(data.xpath('.//a[@class="item_link"]/@style'))
|
||||
cover_url = re.sub(r'.*\(', '', cover_url)
|
||||
cover_url = re.sub(r'\).*', '', cover_url)
|
||||
title = ''.join(data.xpath('.//div[@class="shelf_title"]/a/text()'))
|
||||
author = ''.join(data.xpath('.//div[@class="shelf_authors"]/text()'))
|
||||
price = ''.join(data.xpath('.//span[@class="EBOOK"]/text()'))
|
||||
price = price.replace('.', ',')
|
||||
formats = ', '.join(data.xpath('.//a[@class="fancybox protected"]/text()'))
|
||||
|
||||
counter -= 1
|
||||
|
||||
s = SearchResult()
|
||||
s.cover_url = 'http://bookoteka.pl' + cover_url
|
||||
s.title = title.strip()
|
||||
s.author = author.strip()
|
||||
s.price = price
|
||||
s.detail_item = 'http://bookoteka.pl' + id.strip()
|
||||
s.drm = SearchResult.DRM_UNLOCKED
|
||||
s.formats = formats.strip()
|
||||
|
||||
yield s
|
||||
@ -153,12 +153,22 @@ def build_index(books, num, search, sort, order, start, total, url_base, CKEYS,
|
||||
bookt.append(TR(thumbnail, data))
|
||||
# }}}
|
||||
|
||||
body.append(HR())
|
||||
body.append(DIV(
|
||||
A(_('Switch to the full interface (non-mobile interface)'),
|
||||
href="/browse",
|
||||
style="text-decoration: none; color: blue",
|
||||
title=_('The full interface gives you many more features, '
|
||||
'but it may not work well on a small screen')),
|
||||
style="text-align:center"))
|
||||
return HTML(
|
||||
HEAD(
|
||||
TITLE(__appname__ + ' Library'),
|
||||
LINK(rel='icon', href='http://calibre-ebook.com/favicon.ico',
|
||||
type='image/x-icon'),
|
||||
LINK(rel='stylesheet', type='text/css', href=prefix+'/mobile/style.css')
|
||||
LINK(rel='stylesheet', type='text/css',
|
||||
href=prefix+'/mobile/style.css'),
|
||||
LINK(rel='apple-touch-icon', href="/static/calibre.png")
|
||||
), # End head
|
||||
body
|
||||
) # End html
|
||||
|
||||
@ -211,9 +211,9 @@ calibre-dev.bat::
|
||||
Debugging tips
|
||||
----------------
|
||||
|
||||
Running |app| code in a python debugger is not easy unless you install from source on Linux. However, Python is a
|
||||
Python is a
|
||||
dynamically typed language with excellent facilities for introspection. Kovid wrote the core |app| code without once
|
||||
using a debugger. There are two main strategies to debug |app| code:
|
||||
using a debugger. There are many strategies to debug |app| code:
|
||||
|
||||
Using an interactive python interpreter
|
||||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
@ -240,6 +240,12 @@ Similarly, you can start the ebook-viewer as::
|
||||
|
||||
calibre-debug -w /path/to/file/to/be/viewed
|
||||
|
||||
Using the debugger in PyDev
|
||||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
It is possible to get the debugger in PyDev working with the |app| development environment,
|
||||
see the `forum thread <http://www.mobileread.com/forums/showthread.php?t=143208>`_.
|
||||
|
||||
Executing arbitrary scripts in the |app| python environment
|
||||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
|
||||
@ -405,9 +405,9 @@ To those of you that claim that you need access to the filesystem to so that you
|
||||
|
||||
If you are worried that someday |app| will cease to be developed, leaving all your books marooned in its folder structure, explore the powerful "Save to Disk" feature in |app| that lets you export all your files into a folder structure of arbitrary complexity based on their metadata.
|
||||
|
||||
Since I keep getting asked why there are numbers at the end of the title folder name, the reason is for *robustness*. That number is the id number of the book record in the |app| database. The presence of the number allows you to have multiple records with the same title and author names. More importantly, it is part of what allows |app| to magically regenerate the database with all metadata if the database file gets corrupted. Given that |app|'s mission is to get you to stop storing metadata in filenames and stop using the filesystem to find things, the increased robustness afforded by the id numbers is well worth the uglier folder names.
|
||||
Finally, the reason there are numbers at the end of every title folder, is for *robustness*. That number is the id number of the book record in the |app| database. The presence of the number allows you to have multiple records with the same title and author names. It is also part of what allows |app| to magically regenerate the database with all metadata if the database file gets corrupted. Given that |app|'s mission is to get you to stop storing metadata in filenames and stop using the filesystem to find things, the increased robustness afforded by the id numbers is well worth the uglier folder names.
|
||||
|
||||
Finally, if you are irrevocably wedded to using the filesystem to store your metadata, feel free to patch your local copy of |app| to use whatever storage scheme you like. But, do not bother me with requests to change the directory structure, **they will be ignored**.
|
||||
If you are still not convinced, then I'm afraid |app| is not for you. Look elsewhere for your book cataloguing needs. Just so we're clear, **this is not going to change**. Kindly do not contact us in an attempt to get us to change this.
|
||||
|
||||
Why doesn't |app| have a column for foo?
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user