from calibre.web.feeds.news import BasicNewsRecipe from datetime import datetime from calibre.ebooks.BeautifulSoup import Tag from calibre.utils.magick import Image, PixelWand class LifeHacker(BasicNewsRecipe): THUMBALIZR_API = '' # ---->Get your at http://www.thumbalizr.com/ and put here LANGUAGE = 'en' LANGHTM = 'en' language = 'en' ENCODING = 'utf' ENCHTM = 'utf-8' requires_version = (0,7,47) news = True title = u'LifeHacker' __author__ = 'Euler Alves' description = u'Tips, tricks, and downloads for getting things done.' publisher = u'lifehacker.com' author = u'Adam Pash & Kevin Purdy & Adam Dachis & Whitson Gordon & Gina Trapani' category = 'news, rss' oldest_article = 4 max_articles_per_feed = 20 summary_length = 1000 remove_javascript = True no_stylesheets = True use_embedded_content = True remove_empty_feeds = True timefmt = ' [%d %b %Y (%a)]' hoje = datetime.now() pubdate = hoje.strftime('%a, %d %b') cover_url = 'http://api.thumbalizr.com/?api_key='+THUMBALIZR_API+'&url=http://lifehacker.com&width=600&quality=90' cover_margins = (0,0,'white') masthead_url = 'http://cache.gawkerassets.com/assets/lifehacker.com/img/logo.png' remove_tags = [ {'class': 'feedflare'}, dict(name='div', attrs={'class':[ 'ad_container' ,'ad_300x250' ,'ad_interstitial' ,'share-wrap' ,'ad_300x600' ,'ad_perma-footer-adsense' ,'ad_perma-panorama' ,'ad panorama' ,'ad_container' ]}) ,dict(name='div', attrs={'id':[ 'agegate_container' ,'agegate_container_rejected' ,'sharemenu-wrap' ]}) ] feeds = [(u'Articles', u'http://feeds.gawker.com/lifehacker/vip?format=xml')] conversion_options = { 'title' : title ,'comments' : description ,'publisher' : publisher ,'tags' : category ,'language' : LANGUAGE ,'linearize_tables': True } def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] if not soup.find(attrs={'http-equiv':'Content-Language'}): meta0 = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.LANGHTM)]) soup.head.insert(0,meta0) if not soup.find(attrs={'http-equiv':'Content-Type'}): meta1 = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset="+self.ENCHTM)]) soup.head.insert(0,meta1) return soup def postprocess_html(self, soup, first): #process all the images. assumes that the new html has the correct path for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')): iurl = tag['src'] img = Image() img.open(iurl) width, height = img.size print 'img is: ', iurl, 'width is: ', width, 'height is: ', height if img < 0: raise RuntimeError('Out of memory') pw = PixelWand() if( width > height and width > 590) : print 'Rotate image' img.rotate(pw, -90) img.save(iurl) return soup