Science Advances Recipe

[lui1]

Here is a recipe to for the `Science Advances' magazine published by AAAS.

Science Advances Recipe:

#!/usr/bin/env python2
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
from calibre.web.feeds.news import BasicNewsRecipe

def check_words(words):
    return lambda x: x and frozenset(words.split()).intersection(x.split())


class ScienceAdvances(BasicNewsRecipe):
    title          = 'Science Advances'
    __author__     = 'Jose Ortiz'
    description    = ( 'Science Advances is a peer-reviewed multidisciplinary open-access'
                       ' scientific journal established in early 2015.  The journal\'s scope'
                       ' includes all areas of science, including the life sciences, physical'
                       ' sciences, social sciences, computer sciences, and environmental'
                       ' sciences.' )
    language       = 'en'
    encoding       = 'UTF-8'
    max_articles_per_feed = 100
    publication_type = 'magazine'
    keep_only_tags   = [
        dict(name='article', attrs={'class': check_words('primary')})
    ]
    feeds          = [
        ('Science Advances: Current Issue', 'http://advances.sciencemag.org/rss/current.xml'),
    ]

    def get_cover_url(self):
        soup = self.index_to_soup('http://advances.sciencemag.org/')
        img = soup.find(id='content-block').find('img', attrs={'class': check_words('cover-img')})
        return img['src']

    def preprocess_html(self, soup):
        for img in soup.findAll('img', attrs={'data-src': True}):
            if img['data-src'].endswith('medium.gif'):
                img['src'] = img['data-src'][:-10] + 'large.jpg'
                a=img.findParent(attrs={'href': True})
                if a is not None and a['href'].startswith(img['src']):
                    del a['href']
            else:
                img['src'] = img['data-src']
        return soup

[kovidgoyal]

https://github.com/kovidgoyal/calibr...433b04404b586c