Today's Zaman by thomass

This commit is contained in:
Kovid Goyal 2011-07-01 07:57:59 -06:00
parent 98cdcd854e
commit eab34aa0a5
2 changed files with 54 additions and 0 deletions

View File

@ -0,0 +1,53 @@
from calibre.web.feeds.news import BasicNewsRecipe
class TodaysZaman_en(BasicNewsRecipe):
title = u'Todays Zaman'
__author__ = u'thomass'
description = 'a Turkey based daily for national and international news in the fields of business, diplomacy, politics, culture, arts, sports and economics, in addition to commentaries, specials and features'
oldest_article = 2
max_articles_per_feed =100
no_stylesheets = True
#delay = 1
#use_embedded_content = False
encoding = 'utf-8'
#publisher = ' '
category = 'news, haberler,TR,gazete'
language = 'en_TR'
publication_type = 'newspaper'
#extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif } .introduction{font-weight: bold} .story-feature{display: block; padding: 0; border: 1px solid; width: 40%; font-size: small} .story-feature h2{text-align: center; text-transform: uppercase} '
#keep_only_tags = [dict(name='font', attrs={'class':['newsDetail','agenda2NewsSpot']}),dict(name='span', attrs={'class':['agenda2Title']}),dict(name='div', attrs={'id':['gallery']})]
keep_only_tags = [dict(name='h1', attrs={'class':['georgia_30']}),dict(name='span', attrs={'class':['left-date','detailDate','detailCName']}),dict(name='td', attrs={'id':['newsSpot','newsText']})] #resim ekleme: ,dict(name='div', attrs={'id':['gallery','detailDate',]})
remove_attributes = ['aria-describedby']
remove_tags = [dict(name='img', attrs={'src':['/images/icon_print.gif','http://gmodules.com/ig/images/plus_google.gif','/images/template/jazz/agenda/i1.jpg', 'http://medya.todayszaman.com/todayszaman/images/logo/logo.bmp']}),dict(name='hr', attrs={'class':[ 'interactive-hr']}),dict(name='div', attrs={'class':[ 'empty_height_18','empty_height_9']}) ,dict(name='td', attrs={'id':[ 'superTitle']}),dict(name='span', attrs={'class':[ 't-count enabled t-count-focus']}),dict(name='a', attrs={'id':[ 'count']}),dict(name='td', attrs={'class':[ 'left-date']}) ]
cover_img_url = 'http://medya.todayszaman.com/todayszaman/images/logo/logo.bmp'
masthead_url = 'http://medya.todayszaman.com/todayszaman/images/logo/logo.bmp'
remove_empty_feeds= True
# remove_attributes = ['width','height']
feeds = [
( u'Home', u'http://www.todayszaman.com/rss?sectionId=0'),
( u'News', u'http://www.todayszaman.com/rss?sectionId=100'),
( u'Business', u'http://www.todayszaman.com/rss?sectionId=105'),
( u'Interviews', u'http://www.todayszaman.com/rss?sectionId=8'),
( u'Columnists', u'http://www.todayszaman.com/rss?sectionId=6'),
( u'Op-Ed', u'http://www.todayszaman.com/rss?sectionId=109'),
( u'Arts & Culture', u'http://www.todayszaman.com/rss?sectionId=110'),
( u'Expat Zone', u'http://www.todayszaman.com/rss?sectionId=132'),
( u'Sports', u'http://www.todayszaman.com/rss?sectionId=5'),
( u'Features', u'http://www.todayszaman.com/rss?sectionId=116'),
( u'Travel', u'http://www.todayszaman.com/rss?sectionId=117'),
( u'Leisure', u'http://www.todayszaman.com/rss?sectionId=118'),
( u'Weird But True', u'http://www.todayszaman.com/rss?sectionId=134'),
( u'Life', u'http://www.todayszaman.com/rss?sectionId=133'),
( u'Health', u'http://www.todayszaman.com/rss?sectionId=126'),
( u'Press Review', u'http://www.todayszaman.com/rss?sectionId=130'),
( u'Todays think tanks', u'http://www.todayszaman.com/rss?sectionId=159'),
]
#def preprocess_html(self, soup):
# return self.adeify_images(soup)
#def print_version(self, url): #there is a probem caused by table format
#return url.replace('http://www.todayszaman.com/newsDetail_getNewsById.action?load=detay&', 'http://www.todayszaman.com/newsDetail_openPrintPage.action?')

View File

@ -112,6 +112,7 @@ _extra_lang_codes = {
'en_GR' : _('English (Greece)'),
'en_IN' : _('English (India)'),
'en_TH' : _('English (Thailand)'),
'en_TR' : _('English (Turkey)'),
'en_CY' : _('English (Cyprus)'),
'en_CZ' : _('English (Czechoslovakia)'),
'en_PK' : _('English (Pakistan)'),