From 8e7a83fc9088f90bd6b4e5ccff66de4a9f6a6e9d Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 27 Nov 2011 07:47:27 +0530 Subject: [PATCH] Cosmopolitan UK by Dave Asbury --- recipes/cosmopolitan_uk.recipe | 51 ++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 recipes/cosmopolitan_uk.recipe diff --git a/recipes/cosmopolitan_uk.recipe b/recipes/cosmopolitan_uk.recipe new file mode 100644 index 0000000000..21317063ab --- /dev/null +++ b/recipes/cosmopolitan_uk.recipe @@ -0,0 +1,51 @@ +import re +from calibre.web.feeds.news import BasicNewsRecipe +#from calibre import __appname__ +from calibre.utils.magick import Image +class AdvancedUserRecipe1306097511(BasicNewsRecipe): + title = u'Cosmopolitan UK' + description = 'Fashion, beauty and Gossip for women from COSMOPOLITAN -UK' + + __author__ = 'Dave Asbury' + # 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 + + 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']}) + ] + + 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 postprocess_html(self, soup, first): + #process all the images + for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')): + iurl = tag['src'] + img = Image() + img.open(iurl) + if img < 0: + raise RuntimeError('Out of memory') + img.type = "GrayscaleType" + img.save(iurl) + return soup +