diff --git a/resources/recipes/la_segunda.recipe b/resources/recipes/la_segunda.recipe index 3076899950..537bff4104 100644 --- a/resources/recipes/la_segunda.recipe +++ b/resources/recipes/la_segunda.recipe @@ -1,7 +1,5 @@ -#!/usr/bin/env python - __license__ = 'GPL v3' -__copyright__ = '2009, Darko Miletic ' +__copyright__ = '2009-2010, Darko Miletic ' ''' lasegunda.com ''' @@ -19,43 +17,38 @@ class LaSegunda(BasicNewsRecipe): no_stylesheets = True use_embedded_content = False encoding = 'cp1252' - cover_url = 'http://www.lasegunda.com/imagenes/logotipo_lasegunda_Oli.gif' - remove_javascript = True - language = 'es' + masthead_url = 'http://www.lasegunda.com/imagenes/logotipo_lasegunda_Oli.gif' + remove_empty_feeds = True + language = 'es' + extra_css = ' .titulonegritastop{font-size: xx-large; font-weight: bold} ' - - html2lrf_options = [ - '--comment', description - , '--category', category - , '--publisher', publisher - , '--ignore-tables' - ] - - html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True\noverride_css=" p {text-indent: 0em; margin-top: 0em; margin-bottom: 0.5em} "' + conversion_options = { + 'comment' : description + , 'tags' : category + , 'publisher' : publisher + , 'language' : language + , 'linearize_tables' : True + } - keep_only_tags = [dict(name='table')] + remove_tags_before = dict(attrs={'class':'titulonegritastop'}) + remove_tags = [dict(name='img')] + remove_attributes = ['width','height'] + feeds = [ (u'Noticias de ultima hora', u'http://www.lasegunda.com/rss20/index.asp?canal=0') - ,(u'Politica', u'http://www.lasegunda.com/rss20/index.asp?canal=21') - ,(u'Cronica', u'http://www.lasegunda.com/rss20/index.asp?canal=20') - ,(u'Internacional', u'http://www.lasegunda.com/rss20/index.asp?canal=23') - ,(u'Deportes', u'http://www.lasegunda.com/rss20/index.asp?canal=24') - ,(u'Epectaculos/Cultura', u'http://www.lasegunda.com/rss20/index.asp?canal=25') - ,(u'Educacion', u'http://www.lasegunda.com/rss20/index.asp?canal=26') - ,(u'Ciencia y Tecnologia', u'http://www.lasegunda.com/rss20/index.asp?canal=27') - ,(u'Solidaridad', u'http://www.lasegunda.com/rss20/index.asp?canal=28') - ,(u'Buena Vida', u'http://www.lasegunda.com/rss20/index.asp?canal=32') + ,(u'Politica' , u'http://www.lasegunda.com/rss20/index.asp?canal=21') + ,(u'Cronica' , u'http://www.lasegunda.com/rss20/index.asp?canal=20') + ,(u'Internacional' , u'http://www.lasegunda.com/rss20/index.asp?canal=23') + ,(u'Deportes' , u'http://www.lasegunda.com/rss20/index.asp?canal=24') + ,(u'Epectaculos/Cultura' , u'http://www.lasegunda.com/rss20/index.asp?canal=25') + ,(u'Educacion' , u'http://www.lasegunda.com/rss20/index.asp?canal=26') + ,(u'Ciencia y Tecnologia' , u'http://www.lasegunda.com/rss20/index.asp?canal=27') + ,(u'Solidaridad' , u'http://www.lasegunda.com/rss20/index.asp?canal=28') + ,(u'Buena Vida' , u'http://www.lasegunda.com/rss20/index.asp?canal=32') ] 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 = '' - soup.head.insert(0,mtag) - for item in soup.findAll(style=True): - del item['style'] - return soup diff --git a/resources/recipes/la_tercera.recipe b/resources/recipes/la_tercera.recipe index 1faf3eec20..4734925d97 100644 --- a/resources/recipes/la_tercera.recipe +++ b/resources/recipes/la_tercera.recipe @@ -1,7 +1,5 @@ -#!/usr/bin/env python - __license__ = 'GPL v3' -__copyright__ = '2009, Darko Miletic ' +__copyright__ = '2009-2010, Darko Miletic ' ''' latercera.com ''' @@ -18,32 +16,32 @@ class LaTercera(BasicNewsRecipe): max_articles_per_feed = 100 no_stylesheets = True encoding = 'cp1252' - remove_javascript = True use_embedded_content = False - - html2lrf_options = [ - '--comment', description - , '--category', category - , '--publisher', publisher - ] - - html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' + remove_empty_feeds = True + language = 'es' + + conversion_options = { + 'comment' : description + , 'tags' : category + , 'publisher' : publisher + , 'language' : language + , 'linearize_tables' : True + } keep_only_tags = [dict(name='div', attrs={'class':['span-16 articulo border','span-16 border','span-16']}) ] remove_tags = [ - dict(name='script') - ,dict(name='ul') + dict(name=['ul','input','base']) ,dict(name='div', attrs={'id':['boxComentarios','shim','enviarAmigo']}) ,dict(name='div', attrs={'class':['ad640','span-10 imgSet A','infoRelCol']}) - ,dict(name='input') ,dict(name='p', attrs={'id':['mensajeError','mensajeEnviandoNoticia','mensajeExito']}) ] feeds = [ (u'Noticias de ultima hora', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&ul=1') - ,(u'Pais', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=654') + ,(u'Nacional', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=680') + ,(u'Politica', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=674') ,(u'Mundo', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=678') ,(u'Deportes', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=656') ,(u'Negocios', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=655') @@ -55,10 +53,6 @@ class LaTercera(BasicNewsRecipe): ] def preprocess_html(self, soup): - mtag = '' - soup.head.insert(0,mtag) for item in soup.findAll(style=True): del item['style'] return soup - - language = 'es' diff --git a/src/calibre/devices/usbms/device.py b/src/calibre/devices/usbms/device.py index 1db85ea18b..9c2c0d95fc 100644 --- a/src/calibre/devices/usbms/device.py +++ b/src/calibre/devices/usbms/device.py @@ -398,16 +398,6 @@ class Device(DeviceConfig, DevicePlugin): if len(matches) > 2: drives['cardb'] = matches[2] - pat = self.OSX_MAIN_MEM_VOL_PAT - if pat is not None and len(drives) > 1 and 'main' in drives: - if pat.search(drives['main']) is None: - main = drives['main'] - for x in ('carda', 'cardb'): - if x in drives and pat.search(drives[x]): - drives['main'] = drives.pop(x) - drives[x] = main - break - return drives def osx_bsd_names(self): @@ -431,6 +421,16 @@ class Device(DeviceConfig, DevicePlugin): if drives['main'] is None: print bsd_drives, mount_map, drives raise DeviceError(_('Unable to detect the %s mount point. Try rebooting.')%self.__class__.__name__) + pat = self.OSX_MAIN_MEM_VOL_PAT + if pat is not None and len(drives) > 1 and 'main' in drives: + if pat.search(drives['main']) is None: + main = drives['main'] + for x in ('carda', 'cardb'): + if x in drives and pat.search(drives[x]): + drives['main'] = drives.pop(x) + drives[x] = main + break + self._main_prefix = drives['main']+os.sep def get_card_prefix(c): ans = drives.get(c, None)