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 La Jornada

Browse Source 
Merge branch 'master' of https://github.com/rogeliodh/calibre
This commit is contained in:
Kovid Goyal 2015-07-17 20:14:46 +05:30
commit 65f0da0d49
1 changed files with 27 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
recipes/la_jornada.recipe
View File

@ -5,6 +5,8 @@ www.jornada.unam.mx
''' '''
import re import re
from urllib import urlencode
from urlparse import urlparse, urlunparse, parse_qs
from calibre import strftime from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
@ -52,7 +54,7 @@ class LaJornada_mx(BasicNewsRecipe):
} }
preprocess_regexps = [ preprocess_regexps = [
(re.compile( r'<div class="inicial">(.*)</div><p class="s-s">' (re.compile(r'<div class="inicial">(.*)</div><p class="s-s">'
,re.DOTALL|re.IGNORECASE) ,re.DOTALL|re.IGNORECASE)
,lambda match: '<p class="inicial">' + match.group(1) + '</p><p class="s-s">') ,lambda match: '<p class="inicial">' + match.group(1) + '</p><p class="s-s">')
] ]
@ -64,20 +66,20 @@ class LaJornada_mx(BasicNewsRecipe):
remove_tags = [dict(name='div', attrs={'class':['buttonbar','comment-cont']})] remove_tags = [dict(name='div', attrs={'class':['buttonbar','comment-cont']})]
feeds = [ feeds = [
(u'Opinion' , u'http://www.jornada.unam.mx/rss/opinion.xml' ) (u'Opinion' , u'http://www.jornada.unam.mx/rss/opinion.xml')
,(u'Cartones' , u'http://www.jornada.unam.mx/rss/cartones.xml' ) ,(u'Cartones' , u'http://www.jornada.unam.mx/rss/cartones.xml')
,(u'Politica' , u'http://www.jornada.unam.mx/rss/politica.xml' ) ,(u'Politica' , u'http://www.jornada.unam.mx/rss/politica.xml')
,(u'Economia' , u'http://www.jornada.unam.mx/rss/economia.xml' ) ,(u'Economia' , u'http://www.jornada.unam.mx/rss/economia.xml')
,(u'Mundo' , u'http://www.jornada.unam.mx/rss/mundo.xml' ) ,(u'Mundo' , u'http://www.jornada.unam.mx/rss/mundo.xml')
,(u'Estados' , u'http://www.jornada.unam.mx/rss/estados.xml' ) ,(u'Estados' , u'http://www.jornada.unam.mx/rss/estados.xml')
,(u'Capital' , u'http://www.jornada.unam.mx/rss/capital.xml' ) ,(u'Capital' , u'http://www.jornada.unam.mx/rss/capital.xml')
,(u'Sociedad y justicia' , u'http://www.jornada.unam.mx/rss/sociedad.xml' ) ,(u'Sociedad y justicia' , u'http://www.jornada.unam.mx/rss/sociedad.xml')
,(u'Ciencias' , u'http://www.jornada.unam.mx/rss/ciencias.xml' ) ,(u'Ciencias' , u'http://www.jornada.unam.mx/rss/ciencias.xml')
,(u'Cultura' , u'http://www.jornada.unam.mx/rss/cultura.xml' ) ,(u'Cultura' , u'http://www.jornada.unam.mx/rss/cultura.xml')
,(u'Gastronomia' , u'http://www.jornada.unam.mx/rss/gastronomia.xml' ) ,(u'Gastronomia' , u'http://www.jornada.unam.mx/rss/gastronomia.xml')
,(u'Espectaculos' , u'http://www.jornada.unam.mx/rss/espectaculos.xml' ) ,(u'Espectaculos' , u'http://www.jornada.unam.mx/rss/espectaculos.xml')
,(u'Deportes' , u'http://www.jornada.unam.mx/rss/deportes.xml' ) ,(u'Deportes' , u'http://www.jornada.unam.mx/rss/deportes.xml')
,(u'Ultimas noticias' , u'http://www.jornada.unam.mx/ultimas/news/RSS' ) ,(u'Ultimas noticias' , u'http://www.jornada.unam.mx/ultimas/news/RSS')
] ]
def preprocess_html(self, soup): def preprocess_html(self, soup):
@ -86,6 +88,14 @@ class LaJornada_mx(BasicNewsRecipe):
return soup return soup
def get_article_url(self, article): def get_article_url(self, article):
# Get link to original article URL
rurl = article.get('guid', None) rurl = article.get('guid', None)
return rurl.rpartition('&partner=')[0] if not rurl:
# Use the "link" attribute as failover
return article.get('link', None)
# Remove "partner" query param
u = urlparse(rurl)
query = parse_qs(u.query)
query.pop('partner', None)
u = u._replace(query=urlencode(query, True))
return urlunparse(u)