Various Turkish news sources by Osman Kaysan

This commit is contained in:
Kovid Goyal 2011-11-15 09:28:04 +05:30
parent dfc1f39af7
commit 6bed672533
5 changed files with 172 additions and 10 deletions

38
recipes/biamag.recipe Normal file
View File

@ -0,0 +1,38 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
bianet.com.tr
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Radikal_tr(BasicNewsRecipe):
title = 'BiaMag'
__author__ = 'Osman Kaysan'
description = 'Independent News from Turkey'
publisher = 'BiaMag'
category = 'news, politics, Turkey'
oldest_article = 15
max_articles_per_feed = 120
masthead_url = 'http://bianet.org/images/biamag_logo.gif'
language = 'tr'
no_stylesheets = True
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
,'linearize_tables': True
,'remove_paragraph_spacing': True,
}
remove_tags_before = dict(name='div', attrs={'class':'manset'})
remove_tags = [ dict(name='ul', attrs={'class':['altul']}), dict(name='div', attrs={'id':['habermenu']}), dict(name='div', attrs={'class':['mail']}), dict(name='div', attrs={'class':['from']})]
remove_tags_after = dict(name='div', attrs={'id':'habermenu'})
feeds = [(u'BiaMag', u'http://www.bianet.org/biamag.rss')]
def preprocess_html(self, soup):
return self.adeify_images(soup)

38
recipes/biamag_en.recipe Normal file
View File

@ -0,0 +1,38 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
bianet.com.tr
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Radikal_tr(BasicNewsRecipe):
title = 'Bianet-English'
__author__ = 'Osman Kaysan'
description = 'Independent News Network from Turkey(English)'
publisher = 'Bianet'
category = 'news, politics, Turkey'
oldest_article = 7
max_articles_per_feed = 150
masthead_url = 'http://bianet.org/images/english_logo.gif'
language = 'en_TR'
no_stylesheets = True
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
,'linearize_tables': True
,'remove_paragraph_spacing': True,
}
remove_tags_before = dict(name='div', attrs={'class':'manset'})
remove_tags = [ dict(name='ul', attrs={'class':['altul']}), dict(name='div', attrs={'id':['habermenu']}), dict(name='div', attrs={'class':['mail']}), dict(name='div', attrs={'class':['from']})]
remove_tags_after = dict(name='div', attrs={'id':'habermenu'})
feeds = [(u'Bianet-English', u'http://www.bianet.org/english.rss')]
def preprocess_html(self, soup):
return self.adeify_images(soup)

38
recipes/bianet.recipe Normal file
View File

@ -0,0 +1,38 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
bianet.com.tr
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Radikal_tr(BasicNewsRecipe):
title = 'Bianet'
__author__ = 'Osman Kaysan'
description = 'Independent News from Turkey'
publisher = 'Bianet'
category = 'news, politics, Turkey'
oldest_article = 7
max_articles_per_feed = 120
masthead_url = 'http://bianet.org/images/bianet_logo.gif'
language = 'tr'
no_stylesheets = True
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
,'linearize_tables': True
,'remove_paragraph_spacing': True,
}
remove_tags_before = dict(name='div', attrs={'class':'manset'})
remove_tags = [ dict(name='ul', attrs={'class':['altul']}), dict(name='div', attrs={'id':['habermenu']}), dict(name='div', attrs={'class':['mail']}), dict(name='div', attrs={'class':['from']})]
remove_tags_after = dict(name='div', attrs={'id':'habermenu'})
feeds = [(u'Bianet', u'http://bianet.org/bianet.rss')]
def preprocess_html(self, soup):
return self.adeify_images(soup)

View File

@ -0,0 +1,50 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from calibre.web.feeds.news import BasicNewsRecipe
class Birgun (BasicNewsRecipe):
title = u'Birgün Gazetesi'
__author__ = u'Osman Kaysan'
oldest_article = 7
max_articles_per_feed =150
use_embedded_content = False
description = 'Birgun gazatesi haberleri, kose yazarlari'
publisher = 'Birgün'
category = 'news,haberler,turkce,gazete,birgun'
language = 'tr'
no_stylesheets = True
publication_type = 'newspaper'
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
,'linearize_tables': True
,'remove_paragraph_spacing': True,
}
cover_img_url = 'http://www.birgun.net/i/birgun.png'
masthead_url = 'http://www.birgun.net/i/birgun.png'
remove_attributes = ['width','height']
remove_tags_before = dict(name='h2', attrs={'class':'storyHeadline'})
#remove_tags_after = dict(name='div', attrs={'class':'toollinks'})
remove_tags_after = dict(name='tr', attrs={'valign':'top'})
remove_tags = [ dict(name='div', attrs={'id':'byLine'}), dict(name='div', attrs={'class':'toollinks'})
, dict(name='div', attrs={'class':'main-lead'}), dict(name='div', attrs={'class':'addthis_toolbox addthis_default_style'})
, dict(name='a', attrs={'class':'addthis_button'})]
remove_empty_feeds= True
feeds = [
( u'Güncel', u'http://www.birgun.net/actuels.xml')
,( u'Köşe Yazarları', u'http://www.birgun.net/writer.xml')
,( u'Politika', u'http://www.birgun.net/politics.xml')
,( u'Ekonomi', u'http://www.birgun.net/economic.xml')
,( u'Çalışma Yaşamı', u'http://www.birgun.net/workers.xml')
,( u'Dünya', u'http://www.birgun.net/worlds.xml')
,( u'Yaşam', u'http://www.birgun.net/lifes.xml')
]

View File

@ -8,13 +8,13 @@ radikal.com.tr
from calibre.web.feeds.news import BasicNewsRecipe
class Radikal_tr(BasicNewsRecipe):
title = 'Radikal - Turkey'
__author__ = 'Darko Miletic'
description = 'News from Turkey'
title = 'Radikal Ekleri'
__author__ = 'Darko Mileticden uyarlama'
description = 'Politic-Cultural Articles from Turkey'
publisher = 'radikal'
category = 'news, politics, Turkey'
oldest_article = 7
max_articles_per_feed = 150
oldest_article = 14
max_articles_per_feed = 120
no_stylesheets = True
encoding = 'cp1254'
use_embedded_content = False
@ -37,11 +37,9 @@ class Radikal_tr(BasicNewsRecipe):
feeds = [
(u'Yazarlar' , u'http://www.radikal.com.tr/d/rss/RssYazarlar.xml')
,(u'Turkiye' , u'http://www.radikal.com.tr/d/rss/Rss_97.xml' )
,(u'Politika' , u'http://www.radikal.com.tr/d/rss/Rss_98.xml' )
,(u'Dis Haberler', u'http://www.radikal.com.tr/d/rss/Rss_100.xml' )
,(u'Ekonomi' , u'http://www.radikal.com.tr/d/rss/Rss_101.xml' )
(u'Radikal Iki' , u'http://www.radikal.com.tr/d/rss/Rss_42.xml')
,(u'Radikal Hayat' , u'http://www.radikal.com.tr/d/rss/Rss_41.xml' )
,(u'Radikal Kitap' , u'http://www.radikal.com.tr/d/rss/Rss_40.xml' )
]
def print_version(self, url):