Fix Corriere Della Seraa (EN)

This commit is contained in:
Kovid Goyal 2010-03-15 18:16:26 +05:30
parent 7bafe49277
commit 576cf5c269

View File

@ -2,17 +2,21 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'Lorenzo Vigentini, based on Darko Miletic' __author__ = 'Lorenzo Vigentini, based on Darko Miletic'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>, Lorenzo Vigentini <l.vigentini at gmail.com>' __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>, Lorenzo Vigentini <l.vigentini at gmail.com>'
__version__ = 'v1.01' __version__ = 'v1.02'
__date__ = '10, January 2010' __date__ = '14, March 2010'
__description__ = 'Italian daily newspaper (english version)' __description__ = 'Italian daily newspaper (english version)'
# NOTE: the feeds url are broken on the main site as the permalink structure has been changed erroneously ie:
# actual link in feed http://www.corriere.it/english/10_marzo_11/legitimate_impediment_approved_de9ba480-2cfd-11df-a00c-00144f02aabe.shtml
# this needs to be change to
# real feed URL http://www.corriere.it/International/english/articoli/2010/03/11/legitimate_impediment_approved.shtml
''' '''
http://www.corriere.it/ http://www.corriere.it/
''' '''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class ilCorriere(BasicNewsRecipe): class ilCorriereEn(BasicNewsRecipe):
__author__ = 'Lorenzo Vigentini, based on Darko Miletic' author = 'Lorenzo Vigentini, based on Darko Miletic'
description = 'Italian daily newspaper (english version)' description = 'Italian daily newspaper (english version)'
cover_url = 'http://images.corriereobjects.it/images/static/common/logo_home.gif?v=200709121520' cover_url = 'http://images.corriereobjects.it/images/static/common/logo_home.gif?v=200709121520'
@ -23,7 +27,7 @@ class ilCorriere(BasicNewsRecipe):
language = 'en' language = 'en'
timefmt = '[%a, %d %b, %Y]' timefmt = '[%a, %d %b, %Y]'
oldest_article = 1 oldest_article = 5
max_articles_per_feed = 100 max_articles_per_feed = 100
use_embedded_content = False use_embedded_content = False
recursion = 10 recursion = 10
@ -31,14 +35,30 @@ class ilCorriere(BasicNewsRecipe):
remove_javascript = True remove_javascript = True
no_stylesheets = True no_stylesheets = True
html2lrf_options = [ def get_article_url(self, article):
'--comment', description articleUrl= article.get('link')
, '--category', category segments = articleUrl.split('/')
, '--publisher', publisher basename = '/'.join(segments[:3]) + '/' + 'International/english/articoli/'
, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' #the date has to be redone with the url structure
mlist1 = ['gennaio','febbraio','marzo','aprile','maggio','giugno','luglio','agosto','settembre','ottobre','novembre','dicembre']
mlist2 = ['01','02','03','04','05','06','07','08','09','10','11','12']
myDate = segments[4].split('_')
x=0
for x in range(11):
if myDate[1] == mlist1[x]:
noMonth=mlist2[x]
break
newDateUrl= '20'+ myDate[0] + '/' + noMonth + '/' + myDate[2] + '/'
#clean the article title
articleURLseg=segments[5].split('-')
myArticle = (articleURLseg[0])[:-9] + '.shtml'
myURL= basename + newDateUrl + myArticle
#print myURL
return myURL
keep_only_tags = [dict(name='div', attrs={'class':['news-dettaglio article','article']})] keep_only_tags = [dict(name='div', attrs={'class':['news-dettaglio article','article']})]