Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #2972 (Problem with Accented characters in recipe_publico.py)

Browse Source
This commit is contained in:
Kovid Goyal 2009-07-28 10:31:10 -06:00
parent 4def7e4f9b
commit c129efbb00
6 changed files with 181 additions and 175 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/calibre/gui2/main.py
View File

@ -418,8 +418,10 @@ class Main(MainWindow, Ui_MainWindow, DeviceGUI):
try:
db = LibraryDatabase2(self.library_path)
except Exception, err:
import traceback
error_dialog(self, _('Bad database location'),
unicode(err)).exec_()
_('Bad database location')+':'+self.library_path,
det_msg=traceback.format_exc()).exec_()
dir = unicode(QFileDialog.getExistingDirectory(self,
_('Choose a location for your ebook library.'),
os.path.expanduser('~')))

4
src/calibre/trac/plugins/templates/linux.html
View File

@ -91,6 +91,10 @@ sudo python -c "import urllib2; exec urllib2.urlopen('http://calibre.kovidgoyal.
You must have xdg-utils installed
on your system before running the installer.
</li>
<li>
For device automounting to work, you must have the pmount
package installed on your system.
</li>
<li>
On a 64bit machine, you must have 32-bit versions
of common libraries like X11, freetype, fontconfig,

118
src/calibre/web/feeds/recipes/recipe_estadao.py
View File

@ -1,62 +1,62 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
estadao.com.br
'''
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
estadao.com.br
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Estadao(BasicNewsRecipe):
title = 'O Estado de S. Paulo'
__author__ = 'Darko Miletic'
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 = [
class Estadao(BasicNewsRecipe):
title = 'O Estado de S. Paulo'
__author__ = 'Darko Miletic'
description = 'News from Brasil in Portuguese'
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', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'id':'c1'})]
remove_tags = [
dict(name=['script','object','form','ul'])
,dict(name='div', attrs={'id':['votacao','estadaohoje']})
,dict(name='p', attrs={'id':'ctrl_texto'})
,dict(name='p', attrs={'class':'texto'})
]
feeds = [
(u'Manchetes Estadao', u'http://www.estadao.com.br/rss/manchetes.xml')
,(u'Ultimas noticias', u'http://www.estadao.com.br/rss/ultimas.xml')
,(u'Nacional', u'http://www.estadao.com.br/rss/nacional.xml')
,(u'Internacional', u'http://www.estadao.com.br/rss/internacional.xml')
,(u'Cidades', u'http://www.estadao.com.br/rss/cidades.xml')
,(u'Esportes', u'http://www.estadao.com.br/rss/esportes.xml')
,(u'Arte & Lazer', u'http://www.estadao.com.br/rss/arteelazer.xml')
,(u'Economia', u'http://www.estadao.com.br/rss/economia.xml')
,(u'Vida &', u'http://www.estadao.com.br/rss/vidae.xml')
]
def preprocess_html(self, soup):
ifr = soup.find('iframe')
if ifr:
ifr.extract()
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Portugese')
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'id':'c1'})]
remove_tags = [
dict(name=['script','object','form','ul'])
,dict(name='div', attrs={'id':['votacao','estadaohoje']})
,dict(name='p', attrs={'id':'ctrl_texto'})
,dict(name='p', attrs={'class':'texto'})
]
feeds = [
(u'Manchetes Estadao', u'http://www.estadao.com.br/rss/manchetes.xml')
,(u'Ultimas noticias', u'http://www.estadao.com.br/rss/ultimas.xml')
,(u'Nacional', u'http://www.estadao.com.br/rss/nacional.xml')
,(u'Internacional', u'http://www.estadao.com.br/rss/internacional.xml')
,(u'Cidades', u'http://www.estadao.com.br/rss/cidades.xml')
,(u'Esportes', u'http://www.estadao.com.br/rss/esportes.xml')
,(u'Arte & Lazer', u'http://www.estadao.com.br/rss/arteelazer.xml')
,(u'Economia', u'http://www.estadao.com.br/rss/economia.xml')
,(u'Vida &', u'http://www.estadao.com.br/rss/vidae.xml')
]
def preprocess_html(self, soup):
ifr = soup.find('iframe')
if ifr:
ifr.extract()
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Portuguese')

88
src/calibre/web/feeds/recipes/recipe_jb_online.py
View File

@ -1,47 +1,47 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
jbonline.terra.com.br
'''
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
jbonline.terra.com.br
'''
from calibre.web.feeds.news import BasicNewsRecipe
class JBOnline(BasicNewsRecipe):
title = 'Jornal Brasileiro Online'
__author__ = 'Darko Miletic'
description = 'News from Brasil'
publisher = 'Jornal Brasileiro'
category = 'news, politics, Brasil'
oldest_article = 2
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 = [
class JBOnline(BasicNewsRecipe):
title = 'Jornal Brasileiro Online'
__author__ = 'Darko Miletic'
description = 'News from Brasil'
publisher = 'Jornal Brasileiro'
category = 'news, politics, Brasil'
oldest_article = 2
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', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'id':'corpoNoticia'})]
remove_tags = [dict(name=['script','object','form'])]
feeds = [(u'Todos as editorias', u'http://jbonline.terra.com.br/extra/rsstrjb.xml')]
def preprocess_html(self, soup):
ifr = soup.find('iframe')
if ifr:
ifr.extract()
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Portugese')
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'id':'corpoNoticia'})]
remove_tags = [dict(name=['script','object','form'])]
feeds = [(u'Todos as editorias', u'http://jbonline.terra.com.br/extra/rsstrjb.xml')]
def preprocess_html(self, soup):
ifr = soup.find('iframe')
if ifr:
ifr.extract()
for item in soup.findAll(style=True):
del item['style']
return soup
language = _('Portuguese')

132
src/calibre/web/feeds/recipes/recipe_o_globo.py
View File

@ -1,69 +1,69 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
oglobo.globo.com
'''
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
oglobo.globo.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class OGlobo(BasicNewsRecipe):
title = 'O Globo'
__author__ = 'Darko Miletic'
description = 'News from Brasil'
publisher = 'O Globo'
category = 'news, politics, Brasil'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
cover_url = 'http://oglobo.globo.com/_img/o-globo.png'
remove_javascript = True
html2lrf_options = [
class OGlobo(BasicNewsRecipe):
title = 'O Globo'
__author__ = 'Darko Miletic'
description = 'News from Brasil'
publisher = 'O Globo'
category = 'news, politics, Brasil'
oldest_article = 2
max_articles_per_feed = 100
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', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'id':'ltintb'})]
remove_tags = [
dict(name='script')
,dict(name='object')
,dict(name='form')
,dict(name='div', attrs={'id':['linksPatGoogle','rdpm','cor','com','env','rcm_st']})
,dict(name='div', attrs={'class':'box-zap-anu2'})
,dict(name='a')
,dict(name='link')
]
feeds = [
(u'Todos os canais', u'http://oglobo.globo.com/rss/plantao.xml')
,(u'Ciencia', u'http://oglobo.globo.com/rss/plantaociencia.xml')
,(u'Educacao', u'http://oglobo.globo.com/rss/plantaoeducacao.xml')
,(u'Opiniao', u'http://oglobo.globo.com/rss/plantaoopiniao.xml')
,(u'Sao Paulo', u'http://oglobo.globo.com/rss/plantaosaopaulo.xml')
,(u'Viagem', u'http://oglobo.globo.com/rss/plantaoviagem.xml')
,(u'Cultura', u'http://oglobo.globo.com/rss/plantaocultura.xml')
,(u'Esportes', u'http://oglobo.globo.com/rss/plantaoesportes.xml')
,(u'Mundo', u'http://oglobo.globo.com/rss/plantaomundo.xml')
,(u'Pais', u'http://oglobo.globo.com/rss/plantaopais.xml')
,(u'Rio', u'http://oglobo.globo.com/rss/plantaorio.xml')
,(u'Saude', u'http://oglobo.globo.com/rss/plantaosaude.xml')
,(u'Viver Melhor', u'http://oglobo.globo.com/rss/plantaovivermelhor.xml')
,(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')
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'id':'ltintb'})]
remove_tags = [
dict(name='script')
,dict(name='object')
,dict(name='form')
,dict(name='div', attrs={'id':['linksPatGoogle','rdpm','cor','com','env','rcm_st']})
,dict(name='div', attrs={'class':'box-zap-anu2'})
,dict(name='a')
,dict(name='link')
]
feeds = [
(u'Todos os canais', u'http://oglobo.globo.com/rss/plantao.xml')
,(u'Ciencia', u'http://oglobo.globo.com/rss/plantaociencia.xml')
,(u'Educacao', u'http://oglobo.globo.com/rss/plantaoeducacao.xml')
,(u'Opiniao', u'http://oglobo.globo.com/rss/plantaoopiniao.xml')
,(u'Sao Paulo', u'http://oglobo.globo.com/rss/plantaosaopaulo.xml')
,(u'Viagem', u'http://oglobo.globo.com/rss/plantaoviagem.xml')
,(u'Cultura', u'http://oglobo.globo.com/rss/plantaocultura.xml')
,(u'Esportes', u'http://oglobo.globo.com/rss/plantaoesportes.xml')
,(u'Mundo', u'http://oglobo.globo.com/rss/plantaomundo.xml')
,(u'Pais', u'http://oglobo.globo.com/rss/plantaopais.xml')
,(u'Rio', u'http://oglobo.globo.com/rss/plantaorio.xml')
,(u'Saude', u'http://oglobo.globo.com/rss/plantaosaude.xml')
,(u'Viver Melhor', u'http://oglobo.globo.com/rss/plantaovivermelhor.xml')
,(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 = _('Portuguese')

10
src/calibre/web/feeds/recipes/recipe_publico.py
View File

@ -11,23 +11,23 @@ from calibre.web.feeds.news import BasicNewsRecipe
import re
class Publico(BasicNewsRecipe):
title = u'P\xc3\xbablico'
title = u'P\xfablico'
__author__ = 'David Rodrigues'
oldest_article = 1
max_articles_per_feed = 30
encoding='utf-8'
no_stylesheets = True
language = _('Portugese')
language = _('Portuguese')
preprocess_regexps = [(re.compile(u"\uFFFD", re.DOTALL|re.IGNORECASE), lambda match: ''),]
feeds = [
(u'Geral', u'http://feeds.feedburner.com/PublicoUltimaHora'),
(u'Internacional', u'http://www.publico.clix.pt/rss.ashx?idCanal=11'),
(u'Pol\xc3\xadtica', u'http://www.publico.clix.pt/rss.ashx?idCanal=12'),
(u'Ci\xc3\xaancias', u'http://www.publico.clix.pt/rss.ashx?idCanal=13'),
(u'Pol\xedtica', u'http://www.publico.clix.pt/rss.ashx?idCanal=12'),
(u'Ci\xcencias', u'http://www.publico.clix.pt/rss.ashx?idCanal=13'),
(u'Desporto', u'http://desporto.publico.pt/rss.ashx'),
(u'Economia', u'http://www.publico.clix.pt/rss.ashx?idCanal=57'),
(u'Educa\xc3\xa7\xc3\xa3o', u'http://www.publico.clix.pt/rss.ashx?idCanal=58'),
(u'Educa\xe7\xe3o', u'http://www.publico.clix.pt/rss.ashx?idCanal=58'),
(u'Local', u'http://www.publico.clix.pt/rss.ashx?idCanal=59'),
(u'Media e Tecnologia', u'http://www.publico.clix.pt/rss.ashx?idCanal=61'),
(u'Sociedade', u'http://www.publico.clix.pt/rss.ashx?idCanal=62')