__license__ = 'GPL v3' __copyright__ = '2010, Darko Miletic ' ''' bhdani.com ''' import re from calibre import strftime from calibre.web.feeds.news import BasicNewsRecipe class BHDani(BasicNewsRecipe): title = 'Dani' __author__ = 'Darko Miletic' description = 'On line izdanje najutjecajnijeg bosanskohercegovackog magazina' publisher = 'd.o.o. CIVITAS' category = 'dani, bh, bhdani, magazin, sarajevo, bosna, novine, mediji, listovi, news, magazines, weekly' no_stylesheets = True oldest_article = 15 encoding = 'cp1250' needs_subscription = True remove_empty_feeds = True PREFIX = 'http://bhdani.com' INDEX = PREFIX + '/' LOGIN = PREFIX + '/users/login.asp' use_embedded_content = False language = 'bs' publication_type = 'magazine' extra_css = ' @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: Arial, sans1, sans-serif} .article_description{font-family: Arial, sans1, sans-serif} .plv18{font-size: xx-large; font-weight: bold; color: #5261A9} .crn10{font-weight: bold} ' conversion_options = { 'comment' : description , 'tags' : category , 'publisher' : publisher , 'language' : language , 'linearize_tables' : True } preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] remove_attributes = ['height','width','align'] def get_browser(self): br = BasicNewsRecipe.get_browser(self) if self.username is not None and self.password is not None: br.open(self.INDEX) br.select_form(name='form') br['username'] = self.username br['password'] = self.password br.submit() return br remove_tags = [dict(name=['link','embed','object','iframe','form'])] remove_tags_before= dict(name='div',attrs={'class':'crn10'}) def get_cover_url(self): cover_url = None soup = self.index_to_soup(self.INDEX) link_item = soup.find('img',attrs={'alt':'Naslovna strana'}) if link_item: cover_url = self.PREFIX + link_item['src'].replace('&slika=slika120&','&slika=slika400&') return cover_url def print_version(self, url): return url.replace('/default.asp?','/print.asp?') def parse_index(self): articles = [] soup = self.index_to_soup(self.PREFIX) nrtit = soup.find('font',attrs={'class':'broj'}) nrtitle = 'Dani' if nrtit: nrtitle += ' ' + self.tag_to_string(nrtit) for item in soup.findAll('a',attrs={'class':['naslov12','menilink2']}): url = self.PREFIX + item['href'] title = self.tag_to_string(item) description = '' date = strftime(self.timefmt) articles.append({ 'title' :title ,'date' :date ,'url' :url ,'description':description }) return [(nrtitle, articles)]