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

Update El Correo

Browse Source
This commit is contained in:
Kovid Goyal 2016-07-29 10:55:21 +05:30
parent a585b65f3b
commit 25e60aa62a
1 changed files with 66 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
recipes/el_correo.recipe
View File

@ -3,8 +3,8 @@ __license__ = 'GPL v3'
__copyright__ = '08 Januery 2011, desUBIKado' __copyright__ = '08 Januery 2011, desUBIKado'
__author__ = 'desUBIKado' __author__ = 'desUBIKado'
__description__ = 'Daily newspaper from Biscay' __description__ = 'Daily newspaper from Biscay'
__version__ = 'v0.11' __version__ = 'v0.13'
__date__ = '26, July 2014' __date__ = '28, July 2016'
''' '''
http://www.elcorreo.com/ http://www.elcorreo.com/
''' '''
@ -58,21 +58,25 @@ class elcorreo(BasicNewsRecipe):
] ]
keep_only_tags = [ keep_only_tags = [
dict(name='ul', attrs={'class':['media-list']}) dict(name='article', attrs={'class':['story media-list ']})
] ]
remove_tags = [ remove_tags = [
dict(name='span', attrs={'class':['no-comments']}) dict(name='span', attrs={'class':['no-comments']}),
dict(name='div', attrs={'class':['compApoyosText compNoticiasR']})
] ]
remove_tags_before = dict(name='ul' , attrs={'class':'media-list'}) remove_tags_before = dict(name='article' , attrs={'class':'story media-list '})
remove_tags_after = dict(name='ul' , attrs={'class':'media-list'}) remove_tags_after = dict(name='article' , attrs={'class':'story media-list '})
# Usamos la versión para móviles # Usamos la versión para móviles
def print_version(self, url): def print_version(self, url):
return url.replace('http://www.', 'http://m.') return url.replace('http://www.', 'http://m.')
_processed_links = [] _processed_links = []
def get_article_url(self, article): def get_article_url(self, article):
@ -100,6 +104,7 @@ class elcorreo(BasicNewsRecipe):
if parte[2] == 'alaves.elcorreo.com': if parte[2] == 'alaves.elcorreo.com':
link = 'http://m.elcorreo.com/' + parte[3] + '/' + parte[4] + '/' + parte[5] + '/' + parte[6] + '?external=deportes/alaves' link = 'http://m.elcorreo.com/' + parte[3] + '/' + parte[4] + '/' + parte[5] + '/' + parte[6] + '?external=deportes/alaves'
# A veces el mismo articulo aparece en la versión de Alava y en la de Bizkaia. Por ejemplo: # A veces el mismo articulo aparece en la versión de Alava y en la de Bizkaia. Por ejemplo:
# http://www.elcorreo.com/alava/deportes/motor/formula-1/201407/27/ecclestone-quiere-briatore-ayude-20140727140820-rc.html # http://www.elcorreo.com/alava/deportes/motor/formula-1/201407/27/ecclestone-quiere-briatore-ayude-20140727140820-rc.html
# http://www.elcorreo.com/bizkaia/deportes/motor/formula-1/201407/27/ecclestone-quiere-briatore-ayude-20140727140820-rc.html # http://www.elcorreo.com/bizkaia/deportes/motor/formula-1/201407/27/ecclestone-quiere-briatore-ayude-20140727140820-rc.html
@ -108,6 +113,7 @@ class elcorreo(BasicNewsRecipe):
if ((parte[3] == 'alava') and (parte[4] != 'araba')): if ((parte[3] == 'alava') and (parte[4] != 'araba')):
link = link.replace('elcorreo.com/alava', 'elcorreo.com/bizkaia') link = link.replace('elcorreo.com/alava', 'elcorreo.com/bizkaia')
# Controlamos si el artículo ha sido incluido en otro feed para eliminarlo # Controlamos si el artículo ha sido incluido en otro feed para eliminarlo
if not (link in self._processed_links): if not (link in self._processed_links):
@ -115,6 +121,7 @@ class elcorreo(BasicNewsRecipe):
else: else:
link = None link = None
return link return link
# Recuperamos la portada de papel (la imagen format=1 tiene mayor resolucion) # Recuperamos la portada de papel (la imagen format=1 tiene mayor resolucion)