From 2c652bdee745c36b504c761587b977b2d723624f Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Tue, 14 Dec 2010 09:00:45 -0700 Subject: [PATCH] Science based medicine by BuzzKill --- .../recipes/science_based_medicine.recipe | 42 +++++++++++++++++++ 1 file changed, 42 insertions(+) create mode 100644 resources/recipes/science_based_medicine.recipe diff --git a/resources/recipes/science_based_medicine.recipe b/resources/recipes/science_based_medicine.recipe new file mode 100644 index 0000000000..7aa28cb170 --- /dev/null +++ b/resources/recipes/science_based_medicine.recipe @@ -0,0 +1,42 @@ +#!/usr/bin/env python + +import re +from calibre.web.feeds.news import BasicNewsRecipe +from calibre.ebooks.BeautifulSoup import Tag + +class SBM(BasicNewsRecipe): + title = 'Science Based Medicine' + __author__ = 'BuzzKill' + description = 'Exploring issues and controversies in the relationship between science and medicine' + oldest_article = 5 + max_articles_per_feed = 15 + no_stylesheets = True + use_embedded_content = False + encoding = 'utf-8' + publisher = 'SBM' + category = 'science, sbm, ebm, blog, pseudoscience' + language = 'en' + + lang = 'en-US' + + conversion_options = { + 'comment' : description + , 'tags' : category + , 'publisher' : publisher + , 'language' : lang + , 'pretty_print' : True + } + + keep_only_tags = [ + dict(name='a', attrs={'title':re.compile(r'Posts by.*', re.DOTALL|re.IGNORECASE)}), + dict(name='div', attrs={'class':'entry'}) + ] + + feeds = [(u'Science Based Medicine', u'http://www.sciencebasedmedicine.org/?feed=rss2')] + + def preprocess_html(self, soup): + mtag = Tag(soup,'meta',[('http-equiv','Content-Type'),('context','text/html; charset=utf-8')]) + soup.head.insert(0,mtag) + soup.html['lang'] = self.lang + return self.adeify_images(soup) +