# -*- coding: utf-8 -*- from calibre.web.feeds.news import BasicNewsRecipe class Star (BasicNewsRecipe): title = u'Star Gazetesi' __author__ = u'thomass' description = 'yeni Türkiye''nin Gazetesi' oldest_article =2 max_articles_per_feed =100 no_stylesheets = True #delay = 1 #use_embedded_content = False encoding = 'utf-8' publisher = 'thomass' category = 'güncel, haber, türkçe' language = 'tr' publication_type = 'newspaper' conversion_options = { 'tags' : category ,'language' : language ,'publisher' : publisher ,'linearize_tables': True } extra_css = ' .font8{font-weight: bold; font-size:20px}.font11{font-weight: normal; font-size:small}#hdetay{ font-family:sans-serif;font-size: 9px }' #.story-feature{display: block; padding: 0; border: 1px solid; width: 40%; font-size: small} .story-feature h2{text-align: center; text-transform: uppercase} ' #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='div', attrs={'class':['font8']}),dict(name='span', attrs={'class':['font11']}),dict(name='div', attrs={'id':['hdetay']})]#,,dict(name='h6', attrs={'class':['KirmiziText']}) dict(name='div', attrs={'id':['Haber']}),dict(name='div', attrs={'id':['gallery']})] #remove_tags = [dict(name='img', attrs={'src':[ 'http://medya.aksiyon.com.tr/aksiyon/images/logo/logo.bmp','/aksiyon/images/template/green/baslik0.gif','mobile/home.jpg']}) ],dict(name='h1', attrs={'class':['H1-Haber-DetayBasligi']}),dict(name='h4', attrs={'class':['BrownText']}) , cover_img_url = 'http://www.stargazete.com/starnew/img/starlogo.png' masthead_url = 'http://www.stargazete.com/starnew/img/starlogo.png' remove_empty_feeds= True #remove_attributes = ['width','height'] feeds = [ ( u'MANSET', u'http://open.dapper.net/services/starmanset'), ( u'GÜNCEL', u'http://www.stargazete.com/guncel.xml'), ( u'POLİTİKA', u'http://www.stargazete.com/politika.xml'), ( u' EKONOMİ', u'http://www.stargazete.com/ekonomi.xml'), ( u'DÜNYA', u'http://www.stargazete.com/dunya.xml'), ( u'YAZARLAR', u'http://www.stargazete.com/gazeteyazarlar.xml'), ( u'SPOR', u'http://www.stargazete.com/spor.xml'), ( u'SPOR YAZARLARI', u'http://www.stargazete.com/index.php?metot=rss&islem=sporyazarlar'), ( u'SİNEMA', u'http://www.stargazete.com/sinema.xml'), ( u'KADIN&SAĞLIK', u'http://www.stargazete.com/kadinsaglik.xml'), ( u' STARTEK', u'http://www.stargazete.com/startek.xml'), ( u' AÇIK GÖRÜŞ', u'http://www.stargazete.com/acikgorus.xml'), ( u'Star PAZAR', u'http://www.stargazete.com/pazar.xml'), ( u'Star CUMARTESİ', u'http://www.stargazete.com/cumartesi.xml'), ] def preprocess_html(self, soup):#remove links for alink in soup.findAll('a'): if alink.string is not None: tstr = alink.string alink.replaceWith(tstr) return soup #def print_version(self, url): #return url.replace('/', 'http://www.stargazete.com/')