diff --git a/recipes/cosmopolitan_uk.recipe b/recipes/cosmopolitan_uk.recipe index 078718f6f7..e06cb0964c 100644 --- a/recipes/cosmopolitan_uk.recipe +++ b/recipes/cosmopolitan_uk.recipe @@ -1,58 +1,36 @@ -from calibre.web.feeds.news import BasicNewsRecipe import re -from calibre import browser +from calibre.web.feeds.news import BasicNewsRecipe -class AdvancedUserRecipe1306097511(BasicNewsRecipe): +class AdvancedUserRecipe1390635673(BasicNewsRecipe): title = u'Cosmopolitan UK' - description = 'Author : D.Asbury : Womens Fashion, beauty and Gossip for women from COSMOPOLITAN -UK' + description = 'Womens Fashion, beauty and Gossip for women from COSMOPOLITAN -UK' __author__ = 'Dave Asbury' - #last update 7/7/12 hopefully get current cover from itunes - # greyscale code by Starson - cover_url = 'http://www.cosmopolitan.magazine.co.uk/files/4613/2085/8988/Cosmo_Cover3.jpg' - no_stylesheets = True - oldest_article = 7 - max_articles_per_feed = 20 - remove_empty_feeds = True - remove_javascript = True - ignore_duplicate_articles = {'title'} + # 2/2/14 + oldest_article = 28 + max_articles_per_feed = 10 + compress_news_images = True + compress_news_images_max_size = 20 + auto_cleanup_keep = '//div[@class="articleHeading"]' + auto_cleanup = True + ignore_duplicate_articles = {'title', 'url'} + no_stylesheets = True + masthead_url = 'http://www.cosmopolitan.co.uk//cm/cosmopolitanuk/site_images/site_logo.gif' + cover_url ='http://www.natmagnewsletters.co.uk/CIRCULES/CosmoXXLCover.jpg' + # kovids code + def preprocess_raw_html(self, raw_html, url): + for pat, f in [ + (re.compile(r':: [\w].+', re.DOTALL), lambda m: ''), - preprocess_regexps = [ - (re.compile(r'.*?', re.IGNORECASE | re.DOTALL), lambda match: '')] - language = 'en_GB' - - - masthead_url = 'http://www.cosmopolitan.co.uk/cm/cosmopolitanuk/site_images/header/cosmouk_logo_home.gif' - - - keep_only_tags = [ - dict(attrs={'class' : ['dateAuthor', 'publishDate']}), - dict(name='div',attrs ={'id' : ['main_content']}) - ] - remove_tags = [ - dict(name='div',attrs={'class' : ['blogInfo','viral_toolbar','comment_number','prevEntry nav']}), - dict(name='div',attrs={'class' : 'blog_module_about_the_authors'}), - dict(attrs={'id': ['breadcrumbs','comment','related_links_list','right_rail','content_sec_fb_more','content_sec_mostpopularstories','content-sec_fb_frame_viewfb_bot']}), - dict(attrs={'class' : ['read_liked_that_header','fb_back_next_area']}), - dict(name='li',attrs={'class' : 'thumb'}) - ] + ]: + raw_html = pat.sub(f, raw_html) + return raw_html feeds = [ - (u'Love & Sex', u'http://www.cosmopolitan.co.uk/love-sex/rss/'), (u'Men', u'http://cosmopolitan.co.uk/men/rss/'), (u'Fashion', u'http://cosmopolitan.co.uk/fashion/rss/'), (u'Hair & Beauty', u'http://cosmopolitan.co.uk/beauty-hair/rss/'), (u'LifeStyle', u'http://cosmopolitan.co.uk/lifestyle/rss/'), (u'Cosmo On Campus', u'http://cosmopolitan.co.uk/campus/rss/'), (u'Celebrity Gossip', u'http://cosmopolitan.co.uk/celebrity-gossip/rss/')] - - def get_cover_url(self): - soup = self.index_to_soup('http://itunes.apple.com/gb/app/cosmopolitan-uk/id461363572?mt=8') - # look for the block containing the sun button and url - cov = soup.find(attrs={'alt' : 'iPhone Screenshot 1'}) - cov2 = str(cov['src']) - br = browser() - br.set_handle_redirect(False) - try: - br.open_novisit(cov2) - cover_url = cov2 - except: - cover_url = 'http://www.cosmopolitan.magazine.co.uk/files/4613/2085/8988/Cosmo_Cover3.jpg' - - return cover_url - - + (u'Love & Sex', u'http://www.cosmopolitan.co.uk/love-sex/rss/'), + (u'Men', u'http://cosmopolitan.co.uk/men/rss/'), + (u'Fashion', u'http://cosmopolitan.co.uk/fashion/rss/'), + (u'Hair & Beauty', u'http://cosmopolitan.co.uk/beauty-hair/rss/'), + (u'LifeStyle', u'http://cosmopolitan.co.uk/lifestyle/rss/'), + (u'Cosmo On Campus', u'http://cosmopolitan.co.uk/campus/rss/'), + (u'Celebrity Gossip', u'http://cosmopolitan.co.uk/celebrity-gossip/rss/')]