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

Fix #7150 (Updated recipe for chilean news portal El Mercurio)

Browse Source
This commit is contained in:
Kovid Goyal 2010-10-12 09:07:18 -06:00
parent 6e2987ad49
commit 63dabd9789
1 changed files with 20 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
resources/recipes/el_mercurio_chile.recipe
View File

@ -1,7 +1,5 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
emol.com
'''
@ -19,43 +17,34 @@ class ElMercurio(BasicNewsRecipe):
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
cover_url = 'http://www.emol.com/especiales/logo_emol/logo_emol.gif'
masthead_url = 'http://www.emol.com/especiales/logo_emol/logo_emol.gif'
remove_javascript = True
use_embedded_content = False
language = 'es'
html2lrf_options = [
'--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'})
,dict(name='div', attrs={'id':['div_centro_dn_opc','div_cabezera','div_secciones','div_contenidos','div_pie','nav']})
]
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'id':['cont_iz_titulobajada','cont_iz_creditos_1_a','cont_iz_cuerpo']})]
remove_tags = [dict(name='div', attrs={'id':'cont_iz_cuerpo_relacionados'})]
remove_attributes = ['height','width']
feeds = [
(u'Noticias de ultima hora', u'http://www.emol.com/rss20/rss.asp?canal=0')
,(u'Nacional', u'http://www.emol.com/rss20/rss.asp?canal=1')
,(u'Mundo', u'http://www.emol.com/rss20/rss.asp?canal=2')
,(u'Deportes', u'http://www.emol.com/rss20/rss.asp?canal=4')
,(u'Magazine', u'http://www.emol.com/rss20/rss.asp?canal=6')
,(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')
(u'Noticias de ultima hora', u'http://rss.emol.com/rss.asp?canal=0')
,(u'Nacional', u'http://rss.emol.com/rss.asp?canal=1')
,(u'Mundo', u'http://rss.emol.com/rss.asp?canal=2')
,(u'Deportes', u'http://rss.emol.com/rss.asp?canal=4')
,(u'Magazine', u'http://rss.emol.com/rss.asp?canal=6')
,(u'Tecnologia', u'http://rss.emol.com/rss.asp?canal=5')
]
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 = 'es'