Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Pull from trunk

Browse Source
This commit is contained in:
Kovid Goyal 2009-02-07 14:08:35 -08:00
commit cbdf0ea09e
49 changed files with 1014 additions and 418 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
installer/windows/calibre/calibre.mpi
View File

@ -299,7 +299,6 @@ File ::2BCD9281-2CBC-CF0D-0E12-2CE11F6ED758 -name comic2epub.exe.local -parent 8
File ::EDE6F457-C83F-C5FA-9AF4-38FDFF17D929 -name PIL._imagingtk.pyd -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::09D0906E-3611-3DB7-32CF-A140585694A7 -name win32pdh.pyd -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::4C84F0DC-7157-0C90-2062-180139B03E25 -name IM_MOD_RL_rgb_.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::F402F507-87C5-BDB1-80AE-AD3FF4A4BCE7 -name bzrlib._patiencediff_c.pyd -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::A732EDE7-4796-241F-BECA-68E59F88F8AF -name lrs2lrf.exe -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::69072379-7D16-B9F7-9F39-3E6403C48267 -name IM_MOD_RL_xbm_.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::FBD11D98-D1E7-5DD9-BF02-01CE92518859 -name IM_MOD_RL_otb_.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
@ -365,7 +364,6 @@ File ::26741B21-C241-E100-8BB1-8B679BC3E662 -name configure.xml -parent 8E5D85A4
File ::7D491E89-C6D3-1E6E-F4BD-8E55260FE33E -name libexpat.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::A4910EB3-0F1C-F6F0-CD2D-16A64BBAA92B -name calibre-fontconfig.exe.local -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::8711327A-716D-B162-6AC6-2FB4AD071266 -name fb22lrf.exe -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::0FDD3A7A-31F3-8089-CE32-D80EAA6F62B2 -name bzrlib._btree_serializer_c.pyd -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::476CB977-5155-D56F-26CA-EB243AEBBA99 -name unrar.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::2DA1CC8D-AF5C-3B03-2060-301DFE0356CC -name mobi2oeb.exe.local -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::2E2A9EDA-5386-444E-8479-557386794552 -name IM_MOD_RL_uil_.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
@ -487,7 +485,6 @@ File ::AA761ACD-B728-2324-AA75-B20A2A79F125 -name lrf2lrs.exe -parent 8E5D85A4-7
File ::95434C76-22F5-B9CE-6194-6E1B1EE3232D -name IM_MOD_RL_info_.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::AAF45D03-322F-5553-63A7-312DB754A20B -name _ctypes.pyd -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::C3D351CA-A8D8-AB35-55D9-5AACF8DB37D1 -name python26.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::2F90B52F-A728-2CA4-5688-0283674695B7 -name _elementtree.pyd -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::B50B66A1-FB65-FAD5-1DD7-E894ACC07464 -name QtSvg4.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::906FF13D-D993-7192-7EA5-6D15A5A24BFB -name CORE_RL_png_.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
File ::5D368661-6BF0-D6AF-7C1A-87646864EB4B -name delegates.xml -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
@ -552,7 +549,7 @@ SetupType ::D9ADE41C-B744-690C-2CED-CF826BF03D2E -setup Install -active Yes -pla
InstallComponent 3EA07B17-04D8-6508-B535-96CC7173B49A -setup Install -type pane -conditions D7F585DB-0DEC-A94E-DAB0-94D558D82764 -title {Welcome Screen} -component Welcome -command insert -active Yes -parent StandardInstall
Condition D7F585DB-0DEC-A94E-DAB0-94D558D82764 -active Yes -parent 3EA07B17-04D8-6508-B535-96CC7173B49A -title {Execute Script Condition} -component ExecuteScriptCondition -TreeObject::id D7F585DB-0DEC-A94E-DAB0-94D558D82764
InstallComponent 7CCDA4BB-861C-C21E-3011-E93DB58F07D6 -setup Install -type action -conditions ADBCD53E-C9A6-A3CA-1AAC-0DB0CE84F71E -title {Check for Previous Install} -component CheckForPreviousInstall -command reorder -active Yes -parent 3EA07B17-04D8-6508-B535-96CC7173B49A
InstallComponent 7CCDA4BB-861C-C21E-3011-E93DB58F07D6 -setup Install -type action -conditions ADBCD53E-C9A6-A3CA-1AAC-0DB0CE84F71E -title {Check for Previous Install} -component CheckForPreviousInstall -command insert -active Yes -parent 3EA07B17-04D8-6508-B535-96CC7173B49A
Condition ADBCD53E-C9A6-A3CA-1AAC-0DB0CE84F71E -active Yes -parent 7CCDA4BB-861C-C21E-3011-E93DB58F07D6 -title {Execute Script Condition} -component ExecuteScriptCondition -TreeObject::id ADBCD53E-C9A6-A3CA-1AAC-0DB0CE84F71E
InstallComponent 580ACF2C-517F-5E48-9DEF-7DAEFBA59FDD -setup Install -type action -conditions 6DE3B369-9D6B-6BC1-4EA0-2C54ECE159EB -title {Set Virtual Text} -component SetVirtualText -command insert -active Yes -parent 3EA07B17-04D8-6508-B535-96CC7173B49A
Condition 6DE3B369-9D6B-6BC1-4EA0-2C54ECE159EB -active Yes -parent 580ACF2C-517F-5E48-9DEF-7DAEFBA59FDD -title {String Is Condition} -component StringIsCondition -TreeObject::id 6DE3B369-9D6B-6BC1-4EA0-2C54ECE159EB

2
installer/windows/freeze.py
View File

@ -12,7 +12,7 @@ LIBUNRAR = 'C:\\Program Files\\UnrarDLL\\unrar.dll'
PDFTOHTML = 'C:\\pdftohtml\\pdftohtml.exe'
IMAGEMAGICK_DIR = 'C:\\ImageMagick'
FONTCONFIG_DIR = 'C:\\fontconfig'
VC90 = r'C:\Program Files\Microsoft Visual Studio 9.0\VC\redist\x86\Microsoft.VC90.CRT'
VC90 = r'C:\VC90.CRT'
import sys, os, py2exe, shutil, zipfile, glob, subprocess, re
from distutils.core import setup

2
src/calibre/__init__.py
View File

@ -21,6 +21,8 @@ import mechanize
mimetypes.add_type('application/epub+zip', '.epub')
mimetypes.add_type('text/x-sony-bbeb+xml', '.lrs')
mimetypes.add_type('application/xhtml+xml', '.xhtml')
mimetypes.add_type('image/svg+xml', '.svg')
mimetypes.add_type('application/x-sony-bbeb', '.lrf')
mimetypes.add_type('application/x-dtbncx+xml', '.ncx')
mimetypes.add_type('application/adobe-page-template+xml', '.xpgt')

2
src/calibre/constants.py
View File

@ -2,7 +2,7 @@ __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
__appname__ = 'calibre'
__version__ = '0.4.133'
__version__ = '0.4.134'
__author__ = "Kovid Goyal <kovid@kovidgoyal.net>"
'''
Various run time constants.

2
src/calibre/ebooks/html.py
View File

@ -467,7 +467,7 @@ class Parser(PreProcessor, LoggingInterface):
if self.htmlfile.is_binary:
raise ValueError('Not a valid HTML file: '+self.htmlfile.path)
src = open(self.htmlfile.path, 'rb').read().decode(self.htmlfile.encoding, 'replace').strip()
src = src.replace('\x00', '')
src = src.replace('\x00', '').replace('\r', ' ')
src = self.preprocess(src)
# lxml chokes on unicode input when it contains encoding declarations
for pat in ENCODING_PATS:

20
src/calibre/ebooks/oeb/base.py
View File

@ -48,34 +48,34 @@ XPNSMAP = {
DC_PREFIXES = ('d11', 'd10', 'd09')
def XML(name):
def XML(name):
return '{%s}%s' % (XML_NS, name)
def XHTML(name):
def XHTML(name):
return '{%s}%s' % (XHTML_NS, name)
def OPF(name):
def OPF(name):
return '{%s}%s' % (OPF2_NS, name)
def DC(name):
def DC(name):
return '{%s}%s' % (DC11_NS, name)
def XSI(name):
def XSI(name):
return '{%s}%s' % (XSI_NS, name)
def DCTERMS(name):
def DCTERMS(name):
return '{%s}%s' % (DCTERMS_NS, name)
def NCX(name):
def NCX(name):
return '{%s}%s' % (NCX_NS, name)
def SVG(name):
def SVG(name):
return '{%s}%s' % (SVG_NS, name)
def XLINK(name):
def XLINK(name):
return '{%s}%s' % (XLINK_NS, name)
def CALIBRE(name):
def CALIBRE(name):
return '{%s}%s' % (CALIBRE_NS, name)
def LINK_SELECTORS():

17
src/calibre/ebooks/oeb/stylizer.py
View File

@ -17,6 +17,7 @@ import types
import re
import copy
from itertools import izip
from xml.dom import SyntaxErr as CSSSyntaxError
import cssutils
from cssutils.css import CSSStyleRule, CSSPageRule, CSSStyleDeclaration, \
CSSValueList, cssproperties
@ -288,15 +289,19 @@ class Style(object):
def _update_cssdict(self, cssdict):
self._style.update(cssdict)
def _apply_style_attr(self):
attrib = self._element.attrib
if 'style' in attrib:
css = attrib['style'].split(';')
css = filter(None, map(lambda x: x.strip(), css))
if 'style' not in attrib:
return
css = attrib['style'].split(';')
css = filter(None, (x.strip() for x in css))
try:
style = CSSStyleDeclaration('; '.join(css))
self._style.update(self._stylizer.flatten_style(style))
except CSSSyntaxError:
return
self._style.update(self._stylizer.flatten_style(style))
def _has_parent(self):
return (self._element.getparent() is not None)

BIN
src/calibre/gui2/images/news/starbulletin.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 983 B

9
src/calibre/gui2/main.py
View File

@ -369,13 +369,14 @@ class Main(MainWindow, Ui_MainWindow):
if r == QSystemTrayIcon.Trigger:
if self.isVisible():
for window in QApplication.topLevelWidgets():
if isinstance(window, (MainWindow, QDialog)):
if isinstance(window, (MainWindow, QDialog)) and window.isVisible():
window.hide()
setattr(window, '__systray_minimized', True)
else:
for window in QApplication.topLevelWidgets():
if isinstance(window, (MainWindow, QDialog)):
if window not in (self.device_error_dialog, self.jobs_dialog):
window.show()
if getattr(window, '__systray_minimized', False):
window.show()
setattr(window, '__systray_minimized', False)
def do_default_sync(self, checked):

1
src/calibre/web/feeds/recipes/__init__.py
View File

@ -27,6 +27,7 @@ recipe_modules = ['recipe_' + r for r in (
'shacknews', 'teleread', 'granma', 'juventudrebelde', 'juventudrebelde_english',
'la_tercera', 'el_mercurio_chile', 'la_cuarta', 'lanacion_chile', 'la_segunda',
'jb_online', 'estadao', 'o_globo', 'vijesti', 'elmundo', 'the_oz',
'honoluluadvertiser', 'starbulletin', 'exiled',
)]
import re, imp, inspect, time, os

40
src/calibre/web/feeds/recipes/recipe_ambito.py
View File

@ -1,31 +1,38 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
ambito.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class Ambito(BasicNewsRecipe):
title = 'Ambito.com'
__author__ = 'Darko Miletic'
description = 'Informacion Libre las 24 horas'
description = 'Informacion Libre las 24 horas'
publisher = 'Ambito.com'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'iso--8859-1'
language = _('Spanish')
encoding = 'iso-8859-1'
cover_url = 'http://www.ambito.com/img/logo_.jpg'
remove_javascript = True
use_embedded_content = False
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Argentina'
, '--publisher' , title
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'align':'justify'})]
remove_tags = [dict(name=['object','link'])]
feeds = [
(u'Principales Noticias', u'http://www.ambito.com/rss/noticiasp.asp' )
@ -43,3 +50,12 @@ class Ambito(BasicNewsRecipe):
def print_version(self, url):
return url.replace('http://www.ambito.com/noticia.asp?','http://www.ambito.com/noticias/imprimir.asp?')
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="es-AR"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

37
src/calibre/web/feeds/recipes/recipe_b92.py
View File

@ -7,25 +7,33 @@ b92.net
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class B92(BasicNewsRecipe):
title = u'B92'
title = 'B92'
__author__ = 'Darko Miletic'
language = _('Serbian')
description = 'Dnevne vesti iz Srbije i sveta'
oldest_article = 7
oldest_article = 2
publisher = 'B92.net'
category = 'news, politics, Serbia'
max_articles_per_feed = 100
remove_javascript = True
no_stylesheets = True
use_embedded_content = False
cover_url = 'http://static.b92.net/images/fp/logo.gif'
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
keep_only_tags = [ dict(name='div', attrs={'class':'sama_vest'}) ]
html2lrf_options = [
'--comment', description
, '--base-font-size', '10'
, '--category', 'news, Serbia'
, '--publisher', 'B92'
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
feeds = [
(u'Vesti', u'http://www.b92.net/info/rss/vesti.xml')
@ -44,3 +52,16 @@ class B92(BasicNewsRecipe):
if biz:
nurl = 'http://www.b92.net/mobilni/biz/index.php?nav_id=' + article_id
return nurl
def preprocess_html(self, soup):
soup.html['xml:lang'] = 'sr-Latn'
soup.html['lang'] = 'sr-Latn'
mtag = '<meta http-equiv="Content-Language" content="sr-Latn"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(name='img',align=True):
del item['align']
item.insert(0,'<br /><br />')
return soup
language = _('Serbian')

44
src/calibre/web/feeds/recipes/recipe_blic.py
View File

@ -5,31 +5,49 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
blic.rs
'''
import string,re
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Blic(BasicNewsRecipe):
title = u'Blic'
__author__ = 'Darko Miletic'
description = 'Blic.rs online verzija najtiraznije novine u Srbiji donosi najnovije vesti iz Srbije i sveta, komentare, politicke analize, poslovne i ekonomske vesti, vesti iz regiona, intervjue, informacije iz kulture, reportaze, pokriva sve sportske dogadjaje, detaljan tv program, nagradne igre, zabavu, fenomenalni Blic strip, dnevni horoskop, arhivu svih dogadjaja'
oldest_article = 7
__author__ = u'Darko Miletic'
description = u'Blic.co.yu online verzija najtiraznije novine u Srbiji donosi najnovije vesti iz Srbije i sveta, komentare, politicke analize, poslovne i ekonomske vesti, vesti iz regiona, intervjue, informacije iz kulture, reportaze, pokriva sve sportske dogadjaje, detaljan tv program, nagradne igre, zabavu, fenomenalni Blic strip, dnevni horoskop, arhivu svih dogadjaja'
publisher = 'RINGIER d.o.o.'
category = 'news, politics, Serbia'
oldest_article = 2
max_articles_per_feed = 100
remove_javascript = True
no_stylesheets = True
use_embedded_content = False
cover_url = 'http://www.blic.rs/resources/images/header_back_tile.png'
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
html2lrf_options = [
'--comment', description
, '--base-font-size', '10'
, '--category', 'news, Serbia'
, '--publisher', 'Blic'
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
keep_only_tags = [ dict(name='div', attrs={'class':'single_news'}) ]
keep_only_tags = [dict(name='div', attrs={'class':'single_news'})]
feeds = [ (u'Vesti', u'http://www.blic.rs/rssall.php')]
feeds = [(u'Vesti', u'http://www.blic.rs/rssall.php')]
remove_tags = [dict(name=['object','link'])]
def print_version(self, url):
start_url, question, rest_url = url.partition('?')
return u'http://www.blic.rs/_print.php?' + rest_url
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="sr-Latn"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Serbian')

29
src/calibre/web/feeds/recipes/recipe_clarin.py
View File

@ -1,31 +1,35 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
clarin.com
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class Clarin(BasicNewsRecipe):
title = 'Clarin'
__author__ = 'Darko Miletic'
description = 'Noticias de Argentina y mundo'
publisher = 'Grupo Clarin'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 100
language = _('Spanish')
use_embedded_content = False
no_stylesheets = True
cover_url = strftime('http://www.clarin.com/diario/%Y/%m/%d/portada.jpg')
remove_javascript = True
html2lrf_options = [
'--comment', description
, '--base-font-size', '10'
, '--category', 'news, Argentina'
, '--publisher', 'Grupo Clarin'
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
remove_tags = [
dict(name='a' , attrs={'class':'Imp' })
@ -49,3 +53,12 @@ class Clarin(BasicNewsRecipe):
rest = artl.partition('-0')[-1]
lmain = rest.partition('.')[0]
return 'http://www.servicios.clarin.com/notas/jsp/clarin/v9/notas/imprimir.jsp?pagid=' + lmain
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="es-AR"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

48
src/calibre/web/feeds/recipes/recipe_danas.py
View File

@ -5,37 +5,47 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
danas.rs
'''
import string,re
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Danas(BasicNewsRecipe):
title = 'Danas'
title = u'Danas'
__author__ = 'Darko Miletic'
description = 'Dnevne novine sa vestima iz sveta, politike, ekonomije, kulture, sporta, Beograda, Novog Sada i cele Srbije.'
description = 'Vesti'
publisher = 'Danas d.o.o.'
category = 'news, politics, Serbia'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
no_stylesheets = False
remove_javascript = True
use_embedded_content = False
cover_url = 'http://www.danas.rs/images/basic/danas.gif'
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
html2lrf_options = [
'--comment', description
, '--base-font-size', '10'
, '--category', 'news, Serbia'
, '--publisher', 'Danas'
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
keep_only_tags = [ dict(name='div', attrs={'id':'left'}) ]
keep_only_tags = [dict(name='div', attrs={'id':'left'})]
remove_tags = [
dict(name='div', attrs={'class':'width_1_4' })
,dict(name='div', attrs={'class':'metaClanka' })
,dict(name='div', attrs={'id':'comments' })
,dict(name='div', attrs={'class':'baner' })
,dict(name='div', attrs={'class':'slikaClanka'})
dict(name='div', attrs={'class':['width_1_4','metaClanka','baner']})
,dict(name='div', attrs={'id':'comments'})
,dict(name=['object','link'])
]
feeds = [(u'Vesti', u'http://www.danas.rs/rss/rss.asp')]
feeds = [ (u'Vesti', u'http://www.danas.rs/rss/rss.asp')]
def print_version(self, url):
return url + '&action=print'
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="sr-Latn"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Serbian')

2
src/calibre/web/feeds/recipes/recipe_de_standaard.py
View File

@ -9,7 +9,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class DeStandaard(BasicNewsRecipe):
title = u'De Standaard'
__author__ = u'Darko Miletic'
language = _('French')
language = _('Dutch')
description = u'News from Belgium'
oldest_article = 7
max_articles_per_feed = 100

1
src/calibre/web/feeds/recipes/recipe_demorgen_be.py
View File

@ -13,6 +13,7 @@ class DeMorganBe(BasicNewsRecipe):
__author__ = u'Darko Miletic'
description = u'News from Belgium'
oldest_article = 7
language = _('Dutch')
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False

29
src/calibre/web/feeds/recipes/recipe_el_mercurio_chile.py
View File

@ -5,31 +5,36 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
emol.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class ElMercurio(BasicNewsRecipe):
title = 'El Mercurio online'
language = _('Spanish')
__author__ = 'Darko Miletic'
description = 'El sitio de noticias online de Chile'
description = 'El sitio de noticias online de Chile'
publisher = 'El Mercurio'
category = 'news, politics, Chile'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
cover_url = 'http://www.emol.com/especiales/logo_emol/logo_emol.gif'
remove_javascript = True
use_embedded_content = False
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Chile'
, '--publisher' , title
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [
dict(name='div', attrs={'class':'despliegue-txt_750px'})
,dict(name='div', attrs={'id':'div_cuerpo_participa'})
]
remove_tags = [
dict(name='div', attrs={'class':'contenedor_despliegue-col-left300'})
@ -45,4 +50,12 @@ class ElMercurio(BasicNewsRecipe):
,(u'Tecnologia', u'http://www.emol.com/rss20/rss.asp?canal=5')
,(u'La Musica', u'http://www.emol.com/rss20/rss.asp?canal=7')
]
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="es-CL"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

27
src/calibre/web/feeds/recipes/recipe_elargentino.py
View File

@ -1,30 +1,34 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
elargentino.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class ElArgentino(BasicNewsRecipe):
title = 'ElArgentino.com'
__author__ = 'Darko Miletic'
description = 'Informacion Libre las 24 horas'
language = _('Spanish')
description = 'Informacion Libre las 24 horas'
publisher = 'ElArgentino.com'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 100
remove_javascript = True
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
cover_url = 'http://www.elargentino.com/TemplateWeb/MediosFooter/tapa_elargentino.png'
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Argentina'
, '--publisher' , 'ElArgentino.com'
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
remove_tags = [
dict(name='div', attrs={'id':'noprint' })
@ -50,7 +54,10 @@ class ElArgentino(BasicNewsRecipe):
return u'http://www.elargentino.com/Impresion.aspx?Id=' + article_id
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8">'
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8">\n<meta http-equiv="Content-Language" content="es-AR"/>\n'
soup.head.insert(0,mtag)
soup.prettify()
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

40
src/calibre/web/feeds/recipes/recipe_elmundo.py
View File

@ -6,41 +6,55 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
elmundo.es
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class ElMundo(BasicNewsRecipe):
title = 'El Mundo'
__author__ = 'Darko Miletic'
description = 'News from Spain'
language = _('Spanish')
publisher = 'El Mundo'
category = 'news, politics, Spain'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'iso8859_15'
cover_url = 'http://estaticos02.cache.el-mundo.net/papel/imagenes/v2.0/logoverde.gif'
remove_javascript = True
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Spain'
, '--publisher' , title
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'class':'noticia'})]
keep_only_tags = [
dict(name='div', attrs={'id':['bloqueprincipal','noticia']})
,dict(name='div', attrs={'class':['contenido_noticia_01']})
]
remove_tags = [
dict(name='div', attrs={'class':['herramientas','publicidad_google','video','herramientasarriba','contenido_noticia_02']})
dict(name='div', attrs={'class':['herramientas','publicidad_google']})
,dict(name='div', attrs={'id':'modulo_multimedia' })
,dict(name=['object','script','link', 'a'])
,dict(name='ul', attrs={'class':'herramientas'})
,dict(name='ul', attrs={'class':'herramientas' })
,dict(name=['object','link'])
]
feeds = [
(u'Portada' , u'http://rss.elmundo.es/rss/descarga.htm?data2=4' )
,(u'Television' , u'http://rss.elmundo.es/rss/descarga.htm?data2=76')
,(u'Espana' , u'http://rss.elmundo.es/rss/descarga.htm?data2=8' )
,(u'Internacional' , u'http://rss.elmundo.es/rss/descarga.htm?data2=9' )
,(u'Cultura' , u'http://rss.elmundo.es/rss/descarga.htm?data2=6' )
,(u'Ciencia/Ecologia', u'http://rss.elmundo.es/rss/descarga.htm?data2=5' )
,(u'Comunicacion' , u'http://rss.elmundo.es/rss/descarga.htm?data2=26')
,(u'Television' , u'http://rss.elmundo.es/rss/descarga.htm?data2=76')
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

25
src/calibre/web/feeds/recipes/recipe_estadao.py
View File

@ -6,26 +6,29 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
estadao.com.br
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class Estadao(BasicNewsRecipe):
title = 'O Estado de S. Paulo'
__author__ = 'Darko Miletic'
description = 'News from Brasil'
language = _('Spanish')
description = 'News from Brasil in Portugese'
publisher = 'O Estado de S. Paulo'
category = 'news, politics, Brasil'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
cover_url = 'http://www.estadao.com.br/img/logo_estadao.png'
remove_javascript = True
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Brasil'
, '--publisher' , title
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'id':'c1'})]
@ -52,4 +55,8 @@ class Estadao(BasicNewsRecipe):
ifr = soup.find('iframe')
if ifr:
ifr.extract()
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Portugese')

51
src/calibre/web/feeds/recipes/recipe_exiled.py Normal file
View File

@ -0,0 +1,51 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
exiledonline.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Exiled(BasicNewsRecipe):
title = 'Exiled Online'
__author__ = 'Darko Miletic'
description = "Mankind's only alternative since 1997 - Formerly known as The eXile"
publisher = 'Exiled Online'
language = _('English')
category = 'news, politics, international'
oldest_article = 15
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
remove_javascript = True
cover_url = 'http://exiledonline.com/wp-content/themes/exiledonline_theme/images/header-sm.gif'
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher' , publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'id':'main'})]
remove_tags = [
dict(name=['object','link'])
,dict(name='div', attrs={'class':'info'})
,dict(name='div', attrs={'id':['comments','navig']})
]
feeds = [(u'Articles', u'http://exiledonline.com/feed/' )]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
mtag = '\n<meta http-equiv="Content-Language" content="en"/>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8">\n'
soup.head.insert(0,mtag)
return soup

33
src/calibre/web/feeds/recipes/recipe_granma.py
View File

@ -7,27 +7,30 @@ granma.cubaweb.cu
'''
import urllib
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class Granma(BasicNewsRecipe):
title = 'Diario Granma'
__author__ = 'Darko Miletic'
language = _('Spanish')
description = 'Organo oficial del Comite Central del Partido Comunista de Cuba'
publisher = 'Granma'
category = 'news, politics, Cuba'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
cover_url = 'http://www.granma.cubaweb.cu/imagenes/granweb229d.jpg'
remove_javascript = True
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Cuba'
, '--publisher' , title
'--comment', description
, '--category', category
, '--publisher', publisher
, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='table', attrs={'height':'466'})]
@ -35,9 +38,15 @@ class Granma(BasicNewsRecipe):
def preprocess_html(self, soup):
del soup.body.table['style']
rtag = soup.find('td', attrs={'height':'458'})
if rtag:
del rtag['style']
mtag = '<meta http-equiv="Content-Language" content="es-CU"/>'
soup.head.insert(0,mtag)
for item in soup.findAll('table'):
if item.has_key('width'):
del item['width']
if item.has_key('height'):
del item['height']
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

136
src/calibre/web/feeds/recipes/recipe_harpers_full.py
View File

@ -1,62 +1,80 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
harpers.org - paid subscription/ printed issue articles
This recipe only get's article's published in text format
images and pdf's are ignored
'''
from calibre import strftime
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
harpers.org - paid subscription/ printed issue articles
This recipe only get's article's published in text format
images and pdf's are ignored
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Harpers_full(BasicNewsRecipe):
title = u"Harper's Magazine - articles from printed edition"
__author__ = u'Darko Miletic'
description = u"Harper's Magazine: Founded June 1850."
language = _('English')
oldest_article = 30
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
simultaneous_downloads = 1
delay = 1
needs_subscription = True
INDEX = strftime('http://www.harpers.org/archive/%Y/%m')
LOGIN = 'http://www.harpers.org'
cover_url = strftime('http://www.harpers.org/media/pages/%Y/%m/gif/0001.gif')
keep_only_tags = [ dict(name='div', attrs={'id':'cached'}) ]
remove_tags = [
dict(name='table', attrs={'class':'rcnt'})
,dict(name='table', attrs={'class':'rcnt topline'})
]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None:
br.open(self.LOGIN)
br.select_form(nr=1)
br['handle' ] = self.username
br['password'] = self.password
br.submit()
return br
class Harpers_full(BasicNewsRecipe):
title = u"Harper's Magazine - articles from printed edition"
__author__ = u'Darko Miletic'
description = u"Harper's Magazine: Founded June 1850."
publisher = "Harpers's"
category = 'news, politics, USA'
oldest_article = 30
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
simultaneous_downloads = 1
delay = 1
needs_subscription = True
INDEX = strftime('http://www.harpers.org/archive/%Y/%m')
LOGIN = 'http://www.harpers.org'
cover_url = strftime('http://www.harpers.org/media/pages/%Y/%m/gif/0001.gif')
remove_javascript = True
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [ dict(name='div', attrs={'id':'cached'}) ]
remove_tags = [
dict(name='table', attrs={'class':'rcnt'})
,dict(name='table', attrs={'class':'rcnt topline'})
]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None:
br.open(self.LOGIN)
br.select_form(nr=1)
br['handle' ] = self.username
br['password'] = self.password
br.submit()
return br
def parse_index(self):
articles = []
print 'Processing ' + self.INDEX
soup = self.index_to_soup(self.INDEX)
for item in soup.findAll('div', attrs={'class':'title'}):
text_link = item.parent.find('img',attrs={'alt':'Text'})
if text_link:
url = self.LOGIN + item.a['href']
title = item.a.contents[0]
date = strftime(' %B %Y')
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description':''
})
return [(soup.head.title.string, articles)]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup
def parse_index(self):
articles = []
print 'Processing ' + self.INDEX
soup = self.index_to_soup(self.INDEX)
for item in soup.findAll('div', attrs={'class':'title'}):
text_link = item.parent.find('img',attrs={'alt':'Text'})
if text_link:
url = self.LOGIN + item.a['href']
title = item.a.contents[0]
date = strftime(' %B %Y')
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description':''
})
return [(soup.head.title.string, articles)]
language = _('English')

58
src/calibre/web/feeds/recipes/recipe_honoluluadvertiser.py Normal file
View File

@ -0,0 +1,58 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
honoluluadvertiser.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Honoluluadvertiser(BasicNewsRecipe):
title = 'Honolulu Advertiser'
__author__ = 'Darko Miletic'
description = "Latest national and local Hawaii sports news from The Honolulu Advertiser."
publisher = 'Honolulu Advertiser'
category = 'news, Honolulu, Hawaii'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
remove_javascript = True
cover_url = 'http://www.honoluluadvertiser.com/graphics/branding.gif'
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher' , publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='td')]
remove_tags = [dict(name=['object','link'])]
feeds = [
(u'Breaking news', u'http://www.honoluluadvertiser.com/apps/pbcs.dll/section?Category=RSS01&MIME=XML' )
,(u'Local news', u'http://www.honoluluadvertiser.com/apps/pbcs.dll/section?Category=RSS02&MIME=XML' )
,(u'Sports', u'http://www.honoluluadvertiser.com/apps/pbcs.dll/section?Category=RSS03&MIME=XML' )
,(u'Island life', u'http://www.honoluluadvertiser.com/apps/pbcs.dll/section?Category=RSS05&MIME=XML' )
,(u'Entertainment', u'http://www.honoluluadvertiser.com/apps/pbcs.dll/section?Category=RSS06&MIME=XML' )
,(u'Business', u'http://www.honoluluadvertiser.com/apps/pbcs.dll/section?Category=RSS04&MIME=XML' )
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
mtag = '\n<meta http-equiv="Content-Language" content="en"/>\n'
soup.head.insert(0,mtag)
return soup
def print_version(self, url):
ubody, sep, rest = url.rpartition('/-1/')
root, sep2, article_id = ubody.partition('/article/')
return u'http://www.honoluluadvertiser.com/apps/pbcs.dll/article?AID=/' + article_id + '&template=printart'

41
src/calibre/web/feeds/recipes/recipe_infobae.py
View File

@ -1,34 +1,36 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
infobae.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class Infobae(BasicNewsRecipe):
title = 'Infobae.com'
__author__ = 'Darko Miletic'
description = 'Informacion Libre las 24 horas'
description = 'Informacion Libre las 24 horas'
publisher = 'Infobae.com'
category = 'news, politics, Argentina'
oldest_article = 2
language = _('Spanish')
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'iso-8859-1'
cover_url = 'http://www.infobae.com/imgs/header/header.gif'
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Argentina'
, '--publisher' , 'Infobae.com'
]
remove_javascript = True
feeds = [
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
feeds = [
(u'Noticias' , u'http://www.infobae.com/adjuntos/html/RSS/hoy.xml' )
,(u'Salud' , u'http://www.infobae.com/adjuntos/html/RSS/salud.xml' )
,(u'Tecnologia', u'http://www.infobae.com/adjuntos/html/RSS/tecnologia.xml')
@ -37,5 +39,14 @@ class Infobae(BasicNewsRecipe):
def print_version(self, url):
main, sep, article_part = url.partition('contenidos/')
article_id, rsep, rrest = article_part.partition('-')
article_id, rsep, rrest = article_part.partition('-')
return u'http://www.infobae.com/notas/nota_imprimir.php?Idx=' + article_id
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8">\n<meta http-equiv="Content-Language" content="es-AR"/>\n'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

27
src/calibre/web/feeds/recipes/recipe_jb_online.py
View File

@ -6,25 +6,29 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
jbonline.terra.com.br
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class JBOnline(BasicNewsRecipe):
title = 'Jornal Brasileiro Online'
__author__ = 'Darko Miletic'
description = 'News from Brasil'
description = 'News from Brasil'
publisher = 'Jornal Brasileiro'
category = 'news, politics, Brasil'
oldest_article = 2
language = _('Spanish')
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
cover_url = 'http://jbonline.terra.com.br/img/logo_01.gif'
remove_javascript = True
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Brasil'
, '--publisher' , title
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'id':'corpoNoticia'})]
@ -36,7 +40,8 @@ class JBOnline(BasicNewsRecipe):
ifr = soup.find('iframe')
if ifr:
ifr.extract()
item = soup.find('div', attrs={'id':'corpoNoticia'})
if item:
del item['style']
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Portugese')

40
src/calibre/web/feeds/recipes/recipe_jutarnji.py
View File

@ -6,28 +6,35 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
jutarnji.hr
'''
import string, re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Jutarnji(BasicNewsRecipe):
title = 'Jutarnji'
__author__ = 'Darko Miletic'
description = 'Online izdanje Jutarnjeg lista'
title = u'Jutarnji'
__author__ = u'Darko Miletic'
description = u'Hrvatski portal'
publisher = 'Jutarnji.hr'
category = 'news, politics, Croatia'
oldest_article = 2
max_articles_per_feed = 100
simultaneous_downloads = 1
delay = 1
no_stylesheets = True
use_embedded_content = False
remove_javascript = True
encoding = 'cp1250'
cover_url = 'http://www.jutarnji.hr/EPHResources/Images/2008/06/05/jhrlogo.png'
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
html2lrf_options = [
'--comment', description
, '--base-font-size', '10'
, '--category', 'news, Croatia'
, '--publisher', 'Europapress holding d.o.o.'
]
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
remove_tags = [
@ -49,11 +56,16 @@ class Jutarnji(BasicNewsRecipe):
def print_version(self, url):
main, split, rest = url.partition('.jl')
rmain, rsplit, rrest = main.rpartition(',')
return u'http://www.jutarnji.hr/ispis_clanka.jl?artid=' + rrest
return 'http://www.jutarnji.hr/ispis_clanka.jl?artid=' + rrest
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8">'
soup.head.insert(0,mtag)
soup.prettify()
mtag = '<meta http-equiv="Content-Language" content="hr"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(width=True):
del item['width']
return soup

29
src/calibre/web/feeds/recipes/recipe_juventudrebelde.py
View File

@ -7,26 +7,30 @@ juventudrebelde.cu
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class Juventudrebelde(BasicNewsRecipe):
title = 'Juventud Rebelde'
__author__ = 'Darko Miletic'
description = 'Diario de la Juventud Cubana'
description = 'Diario de la Juventud Cubana'
publisher = 'Juventud rebelde'
category = 'news, politics, Cuba'
oldest_article = 2
language = _('Spanish')
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
cover_url = strftime('http://www.juventudrebelde.cu/UserFiles/File/impreso/iportada-%Y-%m-%d.jpg')
remove_javascript = True
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Cuba'
, '--publisher' , title
'--comment', description
, '--category', category
, '--publisher', publisher
, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'id':'noticia'})]
@ -40,4 +44,11 @@ class Juventudrebelde(BasicNewsRecipe):
,(u'Lectura', u'http://www.juventudrebelde.cu/rss/generales.php?seccion=lectura' )
]
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="es-CU"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

28
src/calibre/web/feeds/recipes/recipe_juventudrebelde_english.py
View File

@ -5,30 +5,40 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
juventudrebelde.co.cu
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class Juventudrebelde_english(BasicNewsRecipe):
title = 'Juventud Rebelde in english'
__author__ = 'Darko Miletic'
description = 'The newspaper of Cuban Youth'
language = _('English')
description = 'The newspaper of Cuban Youth'
publisher = 'Juventud Rebelde'
category = 'news, politics, Cuba'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'iso-8859-1'
remove_javascript = True
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Cuba'
, '--publisher' , title
'--comment', description
, '--category', category
, '--publisher', publisher
, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'class':'read'})]
feeds = [(u'All news', u'http://www.juventudrebelde.cip.cu/rss/all/' )]
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="es-CU"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('English')

30
src/calibre/web/feeds/recipes/recipe_la_cuarta.py
View File

@ -6,30 +6,33 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
lacuarta.cl
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class LaCuarta(BasicNewsRecipe):
title = 'La Cuarta'
__author__ = 'Darko Miletic'
description = 'El sitio de noticias online de Chile'
description = 'La Cuarta Cibernetica: El Diario popular'
publisher = 'CODISA, Consorcio Digital S.A.'
category = 'news, politics, entertainment, Chile'
oldest_article = 2
language = _('Spanish')
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
remove_javascript = True
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Chile'
, '--publisher' , title
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'class':'articulo desplegado'}) ]
remove_tags = [
dict(name='script')
,dict(name='ul')
dict(name='ul')
,dict(name='div', attrs={'id':['toolbox','articleImageDisplayer','enviarAmigo']})
,dict(name='div', attrs={'class':['par ad-1','par ad-2']})
,dict(name='input')
@ -37,7 +40,14 @@ class LaCuarta(BasicNewsRecipe):
,dict(name='strong', text='PUBLICIDAD')
]
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="es-CL"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
feeds = [(u'Noticias', u'http://lacuarta.cl/app/rss?sc=TEFDVUFSVEE=')]
language = _('Spanish')

31
src/calibre/web/feeds/recipes/recipe_la_segunda.py
View File

@ -6,26 +6,29 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
lasegunda.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class LaSegunda(BasicNewsRecipe):
title = 'La Segunda'
__author__ = 'Darko Miletic'
description = 'El sitio de noticias online de Chile'
language = _('Spanish')
description = 'El sitio de noticias online de Chile'
publisher = 'La Segunda'
category = 'news, politics, Chile'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
cover_url = 'http://www.lasegunda.com/imagenes/logotipo_lasegunda_Oli.gif'
remove_javascript = True
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Chile'
, '--publisher' , title
, '--ignore-tables'
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='table')]
@ -45,4 +48,14 @@ class LaSegunda(BasicNewsRecipe):
def print_version(self, url):
rest, sep, article_id = url.partition('index.asp?idnoticia=')
return u'http://www.lasegunda.com/edicionOnline/include/secciones/_detalle_impresion.asp?idnoticia=' + article_id
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="es-CL"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(name='table', width=True):
del item['width']
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

31
src/calibre/web/feeds/recipes/recipe_la_tercera.py
View File

@ -6,26 +6,30 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
latercera.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class LaTercera(BasicNewsRecipe):
title = 'La Tercera'
__author__ = 'Darko Miletic'
description = 'El sitio de noticias online de Chile'
description = 'El sitio de noticias online de Chile'
publisher = 'La Tercera'
category = 'news, politics, Chile'
oldest_article = 2
language = _('Spanish')
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
remove_javascript = True
use_embedded_content = False
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Chile'
, '--publisher' , title
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'class':'span-16 articulo border'}) ]
keep_only_tags = [dict(name='div', attrs={'class':['span-16 articulo border','span-16 border','span-16']}) ]
remove_tags = [
dict(name='script')
@ -50,4 +54,11 @@ class LaTercera(BasicNewsRecipe):
,(u'Educacion', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=657')
]
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="es-CL"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

41
src/calibre/web/feeds/recipes/recipe_lanacion.py
View File

@ -1,29 +1,32 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
lanacion.com.ar
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class Lanacion(BasicNewsRecipe):
title = 'La Nacion'
__author__ = 'Darko Miletic'
description = 'Informacion actualizada las 24 horas, con noticias de Argentina y del mundo - Informate ya!'
description = 'Noticias de Argentina y el resto del mundo'
publisher = 'La Nacion'
category = 'news, politics, Argentina'
oldest_article = 2
language = _('Spanish')
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
remove_javascript = True
no_stylesheets = True
html2lrf_options = [
'--comment', description
, '--base-font-size', '10'
, '--category', 'news, Argentina'
, '--publisher', 'La Nacion SA'
]
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'class':'nota floatFix'})]
remove_tags = [
@ -47,11 +50,11 @@ class Lanacion(BasicNewsRecipe):
,(u'Revista' , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=494' )
]
def get_cover_url(self):
index = 'http://www.lanacion.com.ar'
cover_url = None
soup = self.index_to_soup(index)
cover_item = soup.find('img',attrs={'class':'logo'})
if cover_item:
cover_url = index + cover_item['src']
return cover_url
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="es-AR"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

25
src/calibre/web/feeds/recipes/recipe_lanacion_chile.py
View File

@ -7,25 +7,29 @@ lanacion.cl
'''
import urllib
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class LaNacionChile(BasicNewsRecipe):
title = 'La Nacion Chile'
__author__ = 'Darko Miletic'
description = 'El sitio de noticias online de Chile'
description = 'El sitio de noticias online de Chile'
publisher = 'La Nacion'
category = 'news, politics, Chile'
oldest_article = 2
language = _('Spanish')
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
cover_url = 'http://www.lanacion.cl/prontus_noticias_v2/imag/site/logo.gif'
remove_javascript = True
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Chile'
, '--publisher' , title
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'class':'bloque'})]
@ -41,5 +45,10 @@ class LaNacionChile(BasicNewsRecipe):
item = soup.find('a', attrs={'href':'javascript:window.close()'})
if item:
item.extract()
mtag = '<meta http-equiv="Content-Language" content="es-CL"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

27
src/calibre/web/feeds/recipes/recipe_laprensa.py
View File

@ -1,31 +1,35 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
laprensa.com.ar
'''
import urllib
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class LaPrensa(BasicNewsRecipe):
title = 'La Prensa'
__author__ = 'Darko Miletic'
description = 'Informacion Libre las 24 horas'
description = 'Informacion Libre las 24 horas'
publisher = 'La Prensa'
category = 'news, politics, Argentina'
oldest_article = 7
language = _('Spanish')
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
cover_url = 'http://www.laprensa.com.ar/imgs/logo.gif'
remove_javascript = True
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Argentina'
, '--publisher' , title
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
feeds = [
(u'Politica' , u'http://www.laprensa.com.ar/Rss.aspx?Rss=4' )
@ -47,5 +51,10 @@ class LaPrensa(BasicNewsRecipe):
def preprocess_html(self, soup):
del soup.body['onload']
mtag = '<meta http-equiv="Content-Language" content="es-AR"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

28
src/calibre/web/feeds/recipes/recipe_nin.py
View File

@ -7,12 +7,15 @@ nin.co.yu
'''
import re, urllib
from calibre.web.feeds.news import BasicNewsRecipe
class Nin(BasicNewsRecipe):
from calibre.web.feeds.news import BasicNewsRecipe
class Nin(BasicNewsRecipe):
title = 'NIN online'
__author__ = 'Darko Miletic'
description = 'Nedeljne informativne novine'
publisher = 'NIN'
category = 'news, politics, Serbia'
no_stylesheets = True
oldest_article = 15
simultaneous_downloads = 1
@ -22,11 +25,17 @@ class Nin(BasicNewsRecipe):
PREFIX = 'http://www.nin.co.yu'
INDEX = PREFIX + '/?change_lang=ls'
LOGIN = PREFIX + '/?logout=true'
remove_javascript = True
use_embedded_content = False
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
html2lrf_options = [
'--comment' , description
, '--category' , 'news, politics, Serbia'
, '--publisher' , 'NIN'
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
@ -53,3 +62,12 @@ class Nin(BasicNewsRecipe):
if link_item:
cover_url = self.PREFIX + link_item['src']
return cover_url
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="sr-Latn-RS"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Serbian')

46
src/calibre/web/feeds/recipes/recipe_novosti.py
View File

@ -5,31 +5,45 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
novosti.rs
'''
import string,re
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Novosti(BasicNewsRecipe):
title = 'Vecernje Novosti'
__author__ = 'Darko Miletic'
description = 'novosti, vesti, politika, dosije, drustvo, ekonomija, hronika, reportaze, svet, kultura, sport, beograd, regioni, mozaik, feljton, intrvju, pjer, fudbal, kosarka, podvig, arhiva, komentari, kolumne, srbija, republika srpska,Vecernje novosti'
title = u'Vecernje Novosti'
__author__ = u'Darko Miletic'
description = u'Vesti'
publisher = 'Kompanija Novosti'
category = 'news, politics, Serbia'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
remove_javascript = True
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
html2lrf_options = [
'--comment', description
, '--base-font-size', '10'
, '--category', 'news, Serbia'
, '--publisher', 'Novosti AD'
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
keep_only_tags = [ dict(name='div', attrs={'class':'jednaVest'}) ]
remove_tags_after = dict(name='div', attrs={'class':'info_bottom'})
remove_tags = [
dict(name='div', attrs={'class':'info'})
,dict(name='div', attrs={'class':'info_bottom'})
]
keep_only_tags = [dict(name='div', attrs={'class':'jednaVest'})]
remove_tags = [dict(name='div', attrs={'class':['info','info_bottom','clip_div']})]
feeds = [ (u'Vesti', u'http://www.novosti.rs/php/vesti/rss.php')]
feeds = [(u'Vesti', u'http://www.novosti.rs/php/vesti/rss.php')]
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="sr-Latn"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Serbian')

40
src/calibre/web/feeds/recipes/recipe_nspm.py
View File

@ -6,35 +6,55 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
nspm.rs
'''
import string,re
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Nspm(BasicNewsRecipe):
title = u'Nova srpska politicka misao'
__author__ = 'Darko Miletic'
description = 'Casopis za politicku teoriju i drustvena istrazivanja'
publisher = 'NSPM'
category = 'news, politics, Serbia'
oldest_article = 7
language = _('Serbian')
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
INDEX = 'http://www.nspm.rs/?alphabet=l'
cover_url = 'http://nspm.rs/templates/jsn_epic_pro/images/logol.jpg'
encoding = 'utf8'
remove_javascript = True
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
html2lrf_options = [
'--comment', description
, '--base-font-size', '10'
, '--category', 'news, politics, Serbia'
, '--publisher', 'IIC NSPM'
'--comment', description
, '--category', category
, '--publisher', publisher
, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
remove_tags = [dict(name='a')]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
br.open(self.INDEX)
return br
feeds = [ (u'Nova srpska politicka misao', u'http://www.nspm.rs/feed/rss.html')]
feeds = [(u'Nova srpska politicka misao', u'http://www.nspm.rs/feed/rss.html')]
def print_version(self, url):
return url.replace('.html','/stampa.html')
def preprocess_html(self, soup):
soup.html['xml:lang'] = 'sr-Latn-RS'
soup.html['lang'] = 'sr-Latn-RS'
ftag = soup.find('meta',attrs={'http-equiv':'Content-Language'})
if ftag:
ftag['content'] = 'sr-Latn-RS'
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Serbian')

27
src/calibre/web/feeds/recipes/recipe_o_globo.py
View File

@ -6,25 +6,29 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
oglobo.globo.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class OGlobo(BasicNewsRecipe):
title = 'O Globo'
__author__ = 'Darko Miletic'
description = 'News from Brasil'
description = 'News from Brasil'
publisher = 'O Globo'
category = 'news, politics, Brasil'
oldest_article = 2
max_articles_per_feed = 100
language = _('Spanish')
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
cover_url = 'http://oglobo.globo.com/_img/o-globo.png'
remove_javascript = True
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Brasil'
, '--publisher' , title
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'id':'ltintb'})]
@ -56,3 +60,10 @@ class OGlobo(BasicNewsRecipe):
,(u'Economia', u'http://oglobo.globo.com/rss/plantaoeconomia.xml')
,(u'Tecnologia', u'http://oglobo.globo.com/rss/plantaotecnologia.xml')
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Portugese')

30
src/calibre/web/feeds/recipes/recipe_pagina12.py
View File

@ -1,31 +1,36 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
pagina12.com.ar
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class Pagina12(BasicNewsRecipe):
title = u'Pagina/12'
__author__ = 'Darko Miletic'
description = 'Noticias de Argentina y el resto del mundo'
language = _('Spanish')
publisher = 'La Pagina S.A.'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
cover_url = strftime('http://www.pagina12.com.ar/fotos/%Y%m%d/diario/TAPAN.jpg')
remove_javascript = True
use_embedded_content = False
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Argentina'
, '--publisher' , 'La Pagina S.A.'
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
remove_tags = [
@ -38,3 +43,12 @@ class Pagina12(BasicNewsRecipe):
def print_version(self, url):
return url.replace('http://www.pagina12.com.ar/','http://www.pagina12.com.ar/imprimir/')
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="es-AR"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Spanish')

39
src/calibre/web/feeds/recipes/recipe_pescanik.py
View File

@ -6,30 +6,53 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
pescanik.net
'''
import string,re
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Pescanik(BasicNewsRecipe):
title = 'Pescanik'
__author__ = 'Darko Miletic'
description = 'Pescanik'
publisher = 'Pescanik'
category = 'news, politics, Serbia'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
html2lrf_options = ['--base-font-size', '10']
html2epub_options = 'base_font_size = "10pt"'
remove_javascript = True
encoding = 'utf8'
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
cover_url = "http://pescanik.net/templates/ja_teline/images/logo.png"
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
remove_tags_after = dict(name='div', attrs={'class':'article_seperator'})
remove_tags = [dict(name='td' , attrs={'class':'buttonheading'})]
remove_tags = [
dict(name='td' , attrs={'class':'buttonheading'})
,dict(name='span', attrs={'class':'article_seperator'})
,dict(name=['object','link'])
]
feeds = [(u'Pescanik Online', u'http://pescanik.net/index.php?option=com_rd_rss&id=12')]
def print_version(self, url):
nurl = url.replace('http://pescanik.net/index.php','http://pescanik.net/index2.php')
nurl = url.replace('/index.php','/index2.php')
return nurl + '&pop=1&page=0'
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="sr-Latn-RS"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Serbian')

48
src/calibre/web/feeds/recipes/recipe_politika.py
View File

@ -5,37 +5,61 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
politika.rs
'''
import string,re
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Politika(BasicNewsRecipe):
title = 'Politika Online'
title = u'Politika Online'
__author__ = 'Darko Miletic'
description = 'Najstariji dnevni list na Balkanu'
description = 'Najstariji dnevni list na Balkanu'
publisher = 'Politika novine i Magazini d.o.o'
category = 'news, politics, Serbia'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
extra_css = '.content_center_border {text-align: left;}'
use_embedded_content = False
cover_url = 'http://www.politika.rs:8080/images/politika.gif'
remove_javascript = True
encoding = 'utf8'
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
html2lrf_options = [
'--comment', description
, '--base-font-size', '10'
, '--category', 'news, Serbia'
, '--publisher', 'POLITIKA NOVINE I MAGAZINI d.o.o.'
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
keep_only_tags = [ dict(name='div', attrs={'class':'contentcenter'}) ]
remove_tags_after = dict(name='div', attrs={'class':'datum_item_details'})
keep_only_tags = [dict(name='div', attrs={'class':'content_center_border'})]
remove_tags = [
dict(name='div', attrs={'class':['send_print','txt-komentar']})
,dict(name=['object','link','a'])
,dict(name='h1', attrs={'class':'box_header-tags'})
]
feeds = [
(u'Politika' , u'http://www.politika.rs/rubrike/Politika/index.1.lt.xml' )
,(u'Svet' , u'http://www.politika.rs/rubrike/Svet/index.1.lt.xml' )
,(u'Redakcijski komentari', u'http://www.politika.rs/rubrike/redakcijski-komentari/index.1.lt.xml')
,(u'Pogledi' , u'http://www.politika.rs/pogledi/index.lt.xml' )
,(u'Pogledi sa strane' , u'http://www.politika.rs/rubrike/Pogledi-sa-strane/index.1.lt.xml' )
,(u'Tema dana' , u'http://www.politika.rs/rubrike/tema-dana/index.1.lt.xml' )
,(u'Kultura' , u'http://www.politika.rs/rubrike/Kultura/index.1.lt.xml' )
,(u'Zivot i stil' , u'http://www.politika.rs/rubrike/zivot-i-stil/index.1.lt.xml' )
]
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="sr-Latn-RS"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
ftag = soup.find('div',attrs={'class':'content_center_border'})
if ftag:
ftag['align'] = 'left'
return soup

4
src/calibre/web/feeds/recipes/recipe_st_petersburg_times.py
View File

@ -17,7 +17,7 @@ class PetersburgTimes(BasicNewsRecipe):
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = _('Russian')
language = _('English')
INDEX = 'http://www.sptimes.ru'
def parse_index(self):
@ -36,4 +36,4 @@ class PetersburgTimes(BasicNewsRecipe):
'url':url,
'description':description
})
return [(soup.head.title.string, articles)]
return [(soup.head.title.string, articles)]

58
src/calibre/web/feeds/recipes/recipe_starbulletin.py Normal file
View File

@ -0,0 +1,58 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
starbulletin.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Starbulletin(BasicNewsRecipe):
title = 'Honolulu Star-Bulletin'
__author__ = 'Darko Miletic'
description = "Latest national and local Hawaii sports news"
publisher = 'Honolulu Star-Bulletin'
category = 'news, Honolulu, Hawaii'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
remove_javascript = True
cover_url = 'http://media.starbulletin.com/designimages/spacer.gif'
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher' , publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [ dict(name='div', attrs={'id':'storyColoumn'}) ]
remove_tags = [
dict(name=['object','link'])
,dict(name='span', attrs={'id':'printdesc'})
,dict(name='div' , attrs={'class':'lightGreyBox storyTools clearAll'})
,dict(name='div' , attrs={'id':'breadcrumbs'})
]
feeds = [
(u'Headlines', u'http://www.starbulletin.com/starbulletin_headlines.rss' )
,(u'News', u'http://www.starbulletin.com/news/index.rss' )
,(u'Sports', u'http://www.starbulletin.com/sports/index.rss' )
,(u'Features', u'http://www.starbulletin.com/features/index.rss' )
,(u'Editorials', u'http://www.starbulletin.com/editorials/index.rss' )
,(u'Business', u'http://www.starbulletin.com/business/index.rss' )
,(u'Travel', u'http://www.starbulletin.com/travel/index.rss' )
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
mtag = '\n<meta http-equiv="Content-Language" content="en"/>\n'
soup.head.insert(0,mtag)
return soup

46
src/calibre/web/feeds/recipes/recipe_vijesti.py
View File

@ -1,37 +1,49 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
vijesti.cg.yu
'''
import string,re
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Vijesti(BasicNewsRecipe):
title = 'Vijesti'
__author__ = 'Darko Miletic'
description = 'News from Montenegro'
oldest_article = 2
description = 'News from Montenegro'
publisher = 'Daily Press Vijesti'
category = 'news, politics, Montenegro'
oldest_article = 1
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
remove_javascript = True
encoding = 'cp1250'
cover_url = 'http://www.vijesti.cg.yu/img/logo.gif'
remove_javascript = True
use_embedded_content = False
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
html2lrf_options = [
'--comment' , description
, '--category' , 'news, Montenegro'
, '--publisher' , 'Daily Press Vijesti'
]
keep_only_tags = [dict(name='div', attrs={'id':'mainnews'})]
remove_tags = [
dict(name='div', attrs={'align':'right'})
,dict(name=['object','link'])
]
feeds = [(u'Sve vijesti', u'http://www.vijesti.cg.yu/rss.php' )]
def preprocess_html(self, soup):
@ -39,4 +51,10 @@ class Vijesti(BasicNewsRecipe):
soup.html['lang'] = 'sr-Latn-ME'
mtag = '<meta http-equiv="Content-Language" content="sr-Latn-ME"/>'
soup.head.insert(0,mtag)
for item in soup.findAll('img'):
if item.has_key('align'):
del item['align']
item.insert(0,'<br /><br />')
return soup
language = _('Serbian')

53
src/calibre/web/feeds/recipes/recipe_vreme.py
View File

@ -6,26 +6,34 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
vreme.com
'''
import string,re
import re
from calibre import strftime
from calibre.web.feeds.recipes import BasicNewsRecipe
class Vreme(BasicNewsRecipe):
title = 'Vreme'
__author__ = 'Darko Miletic'
description = 'Politicki Nedeljnik Srbije'
from calibre.web.feeds.news import BasicNewsRecipe
class Vreme(BasicNewsRecipe):
title = 'Vreme'
__author__ = 'Darko Miletic'
description = 'Politicki Nedeljnik Srbije'
publisher = 'Vreme d.o.o.'
category = 'news, politics, Serbia'
no_stylesheets = True
remove_javascript = True
needs_subscription = True
INDEX = 'http://www.vreme.com'
LOGIN = 'http://www.vreme.com/account/index.php'
remove_javascript = True
use_embedded_content = False
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "monospace1";src:url(res:///opt/sony/ebook/FONT/tt0419m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: left; font-family: serif1, serif} .article_date{font-family: monospace1, monospace} .article_description{font-family: sans1, sans-serif} .navbar{font-family: monospace1, monospace}'
html2lrf_options = [
'--comment', description
, '--base-font-size', '10'
, '--category', 'news, politics, Serbia'
, '--publisher', 'Vreme d.o.o.'
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
def get_browser(self):
@ -66,10 +74,29 @@ class Vreme(BasicNewsRecipe):
,'description':description
})
return [(soup.head.title.string, articles)]
remove_tags = [
dict(name=['object','link'])
,dict(name='table',attrs={'xclass':'image'})
]
def print_version(self, url):
return url + '&print=yes'
def preprocess_html(self, soup):
del soup.body['text' ]
del soup.body['bgcolor']
del soup.body['onload' ]
mtag = '<meta http-equiv="Content-Language" content="sr-Latn"/>'
soup.head.insert(0,mtag)
tbl = soup.body.table
tbbb = soup.find('td')
if tbbb:
tbbb.extract()
tbl.extract()
soup.body.insert(0,tbbb)
return soup
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup(self.INDEX)
@ -77,3 +104,5 @@ class Vreme(BasicNewsRecipe):
if cover_item:
cover_url = self.INDEX + cover_item['src']
return cover_url
language = _('Serbian')

1
src/calibre/web/fetch/simple.py
View File

@ -410,6 +410,7 @@ class RecursiveFetcher(object, LoggingInterface):
_fname.decode('latin1', 'replace')
_fname = _fname.encode('ascii', 'replace').replace('%', '').replace(os.sep, '')
_fname = sanitize_file_name(_fname)
_fname = os.path.splitext(_fname)[0]+'.xhtml'
res = os.path.join(linkdiskpath, _fname)
self.downloaded_paths.append(res)
self.filemap[nurl] = res

2
upload.py
View File

@ -77,7 +77,7 @@ def run_windows_install_jammer(installer):
def build_windows(shutdown=True):
installer = installer_name('exe')
vm = '/vmware/Windows XP/Windows XP Professional.vmx'
vm = '/mnt/backup/calibre_windows_xp_home/calibre_windows_xp_home.vmx'
start_vm(vm, 'windows', BUILD_SCRIPT%('python setup.py develop', 'python','installer\\\\windows\\\\freeze.py'))
if os.path.exists('build/py2exe'):
shutil.rmtree('build/py2exe')