Debian Codegraph @

recipes/queleer.recipe

raw
1 __license__ = 'GPL v3'
2 __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
3 '''
4 www.que-leer.com
5 '''
6
7 import re
8
9 from calibre.web.feeds.news import BasicNewsRecipe
10
11
12 class QueLeer(BasicNewsRecipe):
13 title = 'Que Leer'
14 __author__ = 'Darko Miletic'
15 description = 'Libros, Novedades en libros, Criticas, Noticias libro'
16 publisher = 'MC Ediciones, S.A.'
17 category = 'news, books, criticas, libros'
18 oldest_article = 7
19 max_articles_per_feed = 200
20 no_stylesheets = True
21 encoding = 'utf-8'
22 use_embedded_content = False
23 language = 'es'
24 remove_empty_feeds = True
25 masthead_url = 'http://www.que-leer.com/wp-content/themes/queleer/images/backgrounds/que-leer.jpg'
26 extra_css = ' body{font-family: Arial,sans-serif } img{margin-bottom: 0.4em} '
27
28 conversion_options = {'comment': description, 'tags': category, 'publisher': publisher, 'language': language}
29
30 preprocess_regexps = [(re.compile(r'<h2 class="izq">.*?</body>', re.DOTALL | re.IGNORECASE), lambda match: '')]
31
32 remove_tags = [
33 dict(attrs={'class': ['post-ratings', 'post-ratings-loading', 'sociable', 'toc-anchor']}),
34 dict(name=['object', 'embed', 'iframe', 'link']),
35 dict(attrs={'id': 'left'}),
36 ]
37
38 remove_tags_after = dict(attrs={'class': 'sociable'})
39 remove_attributes = ['width', 'height']
40 keep_only_tags = [dict(attrs={'class': 'post'})]
41
42 feeds = [('Articulos', 'http://www.que-leer.com/feed')]
43
44 def preprocess_html(self, soup):
45 for item in soup.findAll(style=True):
46 del item['style']
47 url = 'http://www.que-leer.com/comprar-libros-tienda-que-leer/libros-recomendados'
48 fitem = soup.find('a', href=url)
49 if fitem:
50 par = fitem.parent
51 par.extract()
52 return self.adeify_images(soup)