__license__ = 'GPL v3' __copyright__ = '2009-2012, Darko Miletic ' ''' www.adventuregamers.com ''' from calibre.web.feeds.news import BasicNewsRecipe class AdventureGamers(BasicNewsRecipe): title = u'Adventure Gamers' language = 'en' __author__ = 'Darko Miletic' description = 'Adventure games portal' publisher = 'Adventure Gamers' category = 'news, games, adventure, technology' oldest_article = 10 #delay = 10 max_articles_per_feed = 100 no_stylesheets = True encoding = 'utf8' remove_javascript = True use_embedded_content = False INDEX = u'http://www.adventuregamers.com' extra_css = """ .pageheader_type{font-size: x-large; font-weight: bold; color: #828D74} .pageheader_title,.page_title{font-size: xx-large; color: #394128} .pageheader_byline{font-size: small; font-weight: bold; color: #394128} .score_bg {display: inline; width: 100%; margin-bottom: 2em} .score_column_1{ padding-left: 10px; font-size: small; width: 50%} .score_column_2{ padding-left: 10px; font-size: small; width: 50%} .score_column_3{ padding-left: 10px; font-size: small; width: 50%} .score_header{font-size: large; color: #50544A} img{margin-bottom: 1em;} body{font-family: 'Open Sans',Helvetica,Arial,sans-serif} """ conversion_options = { 'comment' : description , 'tags' : category , 'publisher' : publisher , 'language' : language } keep_only_tags = [dict(name='div', attrs={'class':'cleft_inn'})] remove_tags = [ dict(name=['object','link','embed','form','iframe','meta']) ,dict(name='a', attrs={'href':'http://www.adventuregamers.com/about/scoring'}) ,dict(name='a', attrs={'href':'http://www.adventuregamers.com/about/policies'}) ] remove_tags_after = [dict(name='div', attrs={'class':'bodytext'})] remove_attributes = ['width','height'] feeds = [(u'Articles', u'http://www.adventuregamers.com/rss/')] def get_article_url(self, article): url = BasicNewsRecipe.get_article_url(self, article) if '/videos/' in url or '/hypeometer/' in url: return None return url def append_page(self, soup, appendtag, position): pager = soup.find('div', attrs={'class':'pagination_big'}) if pager: nextpage = soup.find('a', attrs={'class':'next-page'}) if nextpage: nexturl = nextpage['href'] soup2 = self.index_to_soup(nexturl) texttag = soup2.find('div', attrs={'class':'bodytext'}) for it in texttag.findAll(style=True): del it['style'] newpos = len(texttag.contents) self.append_page(soup2,texttag,newpos) texttag.extract() pager.extract() appendtag.insert(position,texttag) def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] for item in soup.findAll('div', attrs={'class':'floatright'}): item.extract() self.append_page(soup, soup.body, 3) pager = soup.find('div',attrs={'class':'pagination_big'}) if pager: pager.extract() return self.adeify_images(soup)