Debian Codegraph @

recipes/el_pais.recipe

raw
1 #!/usr/bin/env python
2 __license__ = 'GPL v3'
3 __author__ = 'Alvaro Beiro, improving Jordi Balcells work based on an earlier version by Lorenzo Vigentini & Kovid Goyal'
4 __copyright__ = '2008, Kovid Goyal [email protected]'
5 description = 'Main daily newspaper from Spain - v1.05 (13, March 2023)'
6 __docformat__ = 'restructuredtext en'
7
8 '''
9 elpais.es
10 '''
11
12 from calibre.web.feeds.news import BasicNewsRecipe
13
14
15 class ElPais(BasicNewsRecipe):
16 __author__ = 'Kovid Goyal & Lorenzo Vigentini & Jordi Balcells & Alvaro Beiro'
17 description = 'Main daily newspaper from Spain'
18
19 title = 'El Pa\xeds'
20 publisher = 'Ediciones El Pa\xeds SL'
21 category = 'News, politics, culture, economy, general interest'
22 publication_type = 'newspaper'
23
24 language = 'es'
25 timefmt = '[%a, %d %b, %Y]'
26
27 oldest_article = 2.1
28 max_articles_per_feed = 25
29
30 recipe_specific_options = {
31 'days': {
32 'short': 'Oldest article to download from this news source. In days ',
33 'long': 'For example, 0.5, gives you articles from the past 12 hours',
34 'default': str(oldest_article),
35 }
36 }
37
38 def __init__(self, *args, **kwargs):
39 BasicNewsRecipe.__init__(self, *args, **kwargs)
40 d = self.recipe_specific_options.get('days')
41 if d and isinstance(d, str):
42 self.oldest_article = float(d)
43
44 use_embedded_content = False
45 recursion = 5
46
47 remove_javascript = True
48 no_stylesheets = True
49
50 extra_css = '''
51 span._db {max-width: 100%; height: auto;}
52 .a_m_p {font-size: .75rem;}
53 .a_m_m {text-transform: uppercase; padding-top: 0.5rem;}
54 div.a_md_a {text-align: center; text-transform: uppercase; font-size: .8rem;}
55 '''
56
57 keep_only_tags = [
58 dict(
59 attrs={
60 'class': [
61 'article_header',
62 'article_body',
63 'a_t',
64 'a_st',
65 'articulo-titulares',
66 'articulo-apertura',
67 'articulo__contenedora_e_m',
68 'a_md_a',
69 ]
70 }
71 ),
72 dict(
73 name='div',
74 attrs={
75 'class': 'a_c',
76 },
77 ),
78 ]
79
80 remove_tags = [
81 dict(
82 attrs={
83 'class': [
84 'sumario__interior',
85 'articulo-trust',
86 'compartir',
87 'articulo-tags',
88 'outbrain',
89 'more_info',
90 'articulo-apoyos',
91 'top10',
92 'a_ei',
93 'w-cta',
94 'ph-v_b',
95 ]
96 },
97 ),
98 dict(id='cta_id'),
99 dict(name='svg'),
100 ]
101
102 remove_attributes = ['width', 'height']
103
104 feeds = [
105 ('Espa\xf1a', 'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/espana/portada'),
106 ('Internacional', 'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/internacional/portada'),
107 ('Economía', 'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/economia/portada'),
108 ('Opinión', 'http://ep00.epimg.net/rss/elpais/opinion.xml'),
109 ('Ciencia', 'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/ciencia/portada'),
110 ('Tecnología', 'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/tecnologia/portada'),
111 ('Cultura', 'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/cultura/portada'),
112 ('Estilo', 'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/estilo/portada'),
113 ('Deportes', 'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/deportes/portada'),
114 ('Televisión', 'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/television/portada'),
115 ('Sociedad', 'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/sociedad/portada'),
116 ('Blogs', 'http://ep01.epimg.net/rss/elpais/blogs.xml'),
117 ]
118
119 def get_cover_url(self):
120 from datetime import date
121
122 cover = (
123 'https://srv00.epimg.net/pdf/elpais/snapshot/'
124 + str(date.today().year)
125 + '/'
126 + date.today().strftime('%m')
127 + '/elpais/'
128 + str(date.today().year)
129 + date.today().strftime('%m')
130 + date.today().strftime('%d')
131 + 'Big.jpg'
132 )
133 br = BasicNewsRecipe.get_browser(self)
134 try:
135 br.open(cover)
136 except Exception:
137 self.log('\nCover unavailable')
138 cover = None
139 return cover
140
141 def image_url_processor(cls, baseurl, url):
142 splitUrl = url.split('cloudfront-')
143 parsedUrl = 'https://cloudfront-' + splitUrl[1]
144 return parsedUrl