| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
""" |
| 4 |
http://www.elcorreo.com/ |
| 5 |
""" |
| 6 |
|
| 7 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 8 |
|
| 9 |
|
| 10 |
class elcorreo(BasicNewsRecipe): |
| 11 |
title = 'El Correo' |
| 12 |
__author__ = 'unkn0wn' |
| 13 |
description = 'Daily newspaper in Bilbao and the Basque Country of northern Spain' |
| 14 |
oldest_article = 1 # days |
| 15 |
language = 'es' |
| 16 |
no_stylesheets = True |
| 17 |
remove_attributes = ['height', 'width', 'style'] |
| 18 |
ignore_duplicate_articles = {'url'} |
| 19 |
encoding = 'utf-8' |
| 20 |
masthead_url = 'https://s1.ppllstatics.com/starfish/1.3.76/assets/images/logos/logo-elcorreo.svg' |
| 21 |
remove_empty_feeds = True |
| 22 |
resolve_internal_links = True |
| 23 |
max_articles_per_feed = 25 # articles |
| 24 |
compress_news_images = True |
| 25 |
|
| 26 |
recipe_specific_options = { |
| 27 |
'days': { |
| 28 |
'short': 'Oldest article to download from this news source. In days ', |
| 29 |
'long': 'For example, 0.5, gives you articles from the past 12 hours', |
| 30 |
'default': str(oldest_article), |
| 31 |
} |
| 32 |
} |
| 33 |
|
| 34 |
def __init__(self, *args, **kwargs): |
| 35 |
BasicNewsRecipe.__init__(self, *args, **kwargs) |
| 36 |
d = self.recipe_specific_options.get('days') |
| 37 |
if d and isinstance(d, str): |
| 38 |
self.oldest_article = float(d) |
| 39 |
|
| 40 |
extra_css = ''' |
| 41 |
.v-mdl-ath__inf, .v-mdl-ath__p--2, .v-mdl-ath__p {font-size:small; color:#404040;} |
| 42 |
.v-fc, .v-a-fig { text-align:center; font-size:small; } |
| 43 |
#sub { font-style:italic; color:#202020; } |
| 44 |
blockquote, em { color:#202020; } |
| 45 |
img { display:block; margin:0 auto; } |
| 46 |
''' |
| 47 |
|
| 48 |
def get_cover_url(self): |
| 49 |
from datetime import date |
| 50 |
|
| 51 |
return 'https://portada.iperiodico.es/' + date.today().strftime('%Y/%m/%d') + '_elcorreo.750.jpg' |
| 52 |
|
| 53 |
keep_only_tags = [ |
| 54 |
dict(name='article', attrs={'class': lambda x: x and set(x.split()).intersection({'v-a--d-bs', 'v-a--d-opn', 'v-a--d-rpg'})}), |
| 55 |
classes('v-d--ab-c v-d--rpg'), |
| 56 |
] |
| 57 |
|
| 58 |
remove_tags = [ |
| 59 |
dict(name=['svg', 'section', 'nav']), |
| 60 |
dict(attrs={'data-voc-component': ['dropdown', 'modal', 'slider-grab']}), |
| 61 |
classes( |
| 62 |
'v-mdl-ath__img-c v-adv v-i-b v-mdl-ath__c--2 v-d-cmp-adv v-d-cmp-nws v-pill-m--zoom v-stk-adv slider-grab g-artboard v-d-cmp-rld v-pill-m--glly' |
| 63 |
), |
| 64 |
] |
| 65 |
|
| 66 |
def preprocess_html(self, soup): |
| 67 |
art = soup.find('article') |
| 68 |
h1 = soup.find('h1') |
| 69 |
h2 = soup.find('h2') |
| 70 |
if h1 and art: |
| 71 |
art.insert_before(h1) |
| 72 |
if h2 and h1: |
| 73 |
h1.insert_after(h2) |
| 74 |
h2.name = 'p' |
| 75 |
h2['id'] = 'sub' |
| 76 |
for but in soup.findAll('button'): |
| 77 |
if but.find('img'): |
| 78 |
but.name = 'div' |
| 79 |
else: |
| 80 |
but.extract() |
| 81 |
x = soup.find(**classes('v-mdl-ath__c')) |
| 82 |
if x: |
| 83 |
for p in x.findAll('p'): |
| 84 |
p.name = 'div' |
| 85 |
return soup |
| 86 |
|
| 87 |
def get_browser(self, *args, **kwargs): |
| 88 |
kwargs['user_agent'] = 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)' |
| 89 |
br = BasicNewsRecipe.get_browser(self, *args, **kwargs) |
| 90 |
br.addheaders += [('Referer', 'https://www.google.com/'), ('X-Forwarded-For', '66.249.66.1')] |
| 91 |
return br |
| 92 |
|
| 93 |
# https://www.elcorreo.com/rss/ |
| 94 |
feeds = [ |
| 95 |
('Portada', 'http://www.elcorreo.com/rss/atom/portada'), |
| 96 |
('Mundo', 'http://www.elcorreo.com/rss/atom/?section=internacional'), |
| 97 |
('Bizkaia', 'http://www.elcorreo.com/rss/atom/?section=bizkaia'), |
| 98 |
('Opinión', 'https://www.elcorreo.com/rss/atom/?section=opinion'), |
| 99 |
('Internacional', 'https://www.elcorreo.com/rss/atom/?section=internacional'), |
| 100 |
('Ciencia', 'https://www.elcorreo.com/rss/atom/?section=ciencia'), |
| 101 |
# ('Guipuzkoa', 'http://www.elcorreo.com/rss/atom/?section=gipuzkoa'), |
| 102 |
# ('Araba', 'http://www.elcorreo.com/rss/atom/?section=araba'), |
| 103 |
# ('La Rioja', 'http://www.elcorreo.com/rss/atom/?section=larioja'), |
| 104 |
# ('Miranda', 'http://www.elcorreo.com/rss/atom/?section=miranda'), |
| 105 |
('Economía', 'http://www.elcorreo.com/rss/atom/?section=economia'), |
| 106 |
# ('Culturas', 'http://www.elcorreo.com/rss/atom/?section=culturas'), |
| 107 |
('Politica', 'http://www.elcorreo.com/rss/atom/?section=politica'), |
| 108 |
# ('De tiendas', 'https://www.elcorreo.com/rss/atom/?section=de-tiendas'), |
| 109 |
# ('Elecciones', 'https://www.elcorreo.com/rss/atom/?section=elecciones'), |
| 110 |
# ('Sociedad', 'https://www.elcorreo.com/rss/atom/?section=sociedad'), |
| 111 |
# ('Vivir', 'https://www.elcorreo.com/rss/atom/?section=vivir'), |
| 112 |
('Tecnología', 'http://www.elcorreo.com/rss/atom/?section=tecnologia'), |
| 113 |
# ('Gente - Estilo', 'http://www.elcorreo.com/rss/atom/?section=gente-estilo'), |
| 114 |
# ('Planes', 'http://www.elcorreo.com/rss/atom/?section=planes'), |
| 115 |
# ('Athletic', 'http://www.elcorreo.com/rss/atom/?section=athletic'), |
| 116 |
# ('Alavés', 'http://www.elcorreo.com/rss/atom/?section=alaves'), |
| 117 |
# ('Bilbao Basket', 'http://www.elcorreo.com/rss/atom/?section=bilbaobasket'), |
| 118 |
# ('Baskonia', 'http://www.elcorreo.com/rss/atom/?section=baskonia'), |
| 119 |
('Deportes', 'http://www.elcorreo.com/rss/atom/?section=deportes'), |
| 120 |
# ('Jaiak', 'http://www.elcorreo.com/rss/atom/?section=jaiak'), |
| 121 |
# ('La Blanca', 'http://www.elcorreo.com/rss/atom/?section=la-blanca-vitoria'), |
| 122 |
# ('Aste Nagusia', 'http://www.elcorreo.com/rss/atom/?section=aste-nagusia-bilbao'), |
| 123 |
# ('Semana Santa', 'http://www.elcorreo.com/rss/atom/?section=semana-santa'), |
| 124 |
# ('Festivales', 'http://www.elcorreo.com/rss/atom/?section=festivales') |
| 125 |
] |