Katherimini and Ta Nea by Pan

This commit is contained in:
Kovid Goyal 2010-02-16 17:44:17 -07:00
parent e81b241895
commit 108c53e194
2 changed files with 67 additions and 0 deletions

View File

@ -0,0 +1,37 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class Kathimerini(BasicNewsRecipe):
title = 'Kathimerini'
__author__ = 'Pan'
description = 'News from Greece'
max_articles_per_feed = 100
oldest_article = 100
publisher = 'Kathimerini'
category = 'news, GR'
language = 'el'
no_stylesheets = True
remove_tags_before = dict(name='td',attrs={'class':'news'})
remove_tags_after = dict(name='td',attrs={'class':'news'})
remove_attributes = ['width', 'src','header','footer']
feeds = [(u'\u03a0\u03bf\u03bb\u03b9\u03c4\u03b9\u03ba\u03ae',
'http://wk.kathimerini.gr/xml_files/politics.xml'),
(u'\u0395\u03bb\u03bb\u03ac\u03b4\u03b1',
' http://wk.kathimerini.gr/xml_files/ell.xml'),
(u'\u039a\u03cc\u03c3\u03bc\u03bf\u03c2',
' http://wk.kathimerini.gr/xml_files/world.xml'),
(u'\u039f\u03b9\u03ba\u03bf\u03bd\u03bf\u03bc\u03af\u03b1',
'http://wk.kathimerini.gr/xml_files/economy_1.xml'),
(u'\u0395\u03c0\u03b9\u03c7\u03b5\u03b9\u03c1\u03ae\u03c3\u03b5\u03b9\u03c2',
'http://wk.kathimerini.gr/xml_files/economy_2.xml'),
(u'\u0394\u03b9\u03b5\u03b8\u03bd\u03ae\u03c2 \u039f\u03b9\u03ba\u03bf\u03bd\u03bf\u03bc\u03af\u03b1',
'http://wk.kathimerini.gr/xml_files/economy_3.xml'),
(u'\u03a0\u03bf\u03bb\u03b9\u03c4\u03b9\u03c3\u03bc\u03cc\u03c2',
'http://wk.kathimerini.gr/xml_files/civ.xml'),
(u'\u039c\u03cc\u03bd\u03b9\u03bc\u03b5\u03c2 \u03a3\u03c4\u03ae\u03bb\u03b5\u03c2',
'http://wk.kathimerini.gr/xml_files/st.xml')]
def print_version(self, url):
return url.replace('http://news.kathimerini.gr/4dcgi/', 'http://news.kathimerini.gr/4dcgi/4dcgi/')

30
resources/tanea.recipe Normal file
View File

@ -0,0 +1,30 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class TaNea(BasicNewsRecipe):
title = u'Ta Nea'
__author__ = 'Pan'
oldest_article = 1
max_articles_per_feed = 100
no_stylesheets = True
remove_tags_before = dict(name='div',attrs={'id':'print-body'})
remove_tags_after = dict(name='div',attrs={'id':'text'})
feeds = [
(u'\xce\x95\xce\xbb\xce\xbb\xce\xac\xce\xb4\xce\xb1',
u'http://www.tanea.gr/default.asp?pid=66&la=1'),
(u'\xce\x9a\xcf\x8c\xcf\x83\xce\xbc\xce\xbf\xcf\x82',
u'http://www.tanea.gr/default.asp?pid=67&la=1'),
(u'\xce\x9f\xce\xb9\xce\xba\xce\xbf\xce\xbd\xce\xbf\xce\xbc\xce\xaf\xce\xb1',
u'http://www.tanea.gr/default.asp?pid=68&la=1'),
(u'\xce\xa0\xce\xbf\xce\xbb\xce\xb9\xcf\x84\xce\xb9\xcf\x83\xce\xbc\xcf\x8c\xcf\x82',
u'http://www.tanea.gr/default.asp?pid=69&la=1'),
(u'\xce\x93\xce\xbd\xcf\x8e\xce\xbc\xce\xb5\xcf\x82',
u'http://www.tanea.gr/default.asp?pid=79&la=1'),
(u'\xce\xa1\xce\xb9\xcf\x80\xce\xad\xcf\x82',
u'http://www.tanea.gr/default.asp?pid=80&la=1'),
(u'\xce\x91\xce\xb9\xcf\x87\xce\xbc\xce\xad\xcf\x82',
u'http://www.tanea.gr/default.asp?pid=81&la=1')]
def print_version(self, url):
return url.replace('http://www.tanea.gr/default.asp?pid=2', 'http://www.tanea.gr/default.asp?pid=96')