| 1 |
#!/usr/bin/env python |
| 2 |
__license__ = 'GPL v3' |
| 3 |
__copyright__ = '4 February 2011, desUBIKado' |
| 4 |
__author__ = 'desUBIKado' |
| 5 |
__version__ = 'v0.12' |
| 6 |
__date__ = '28, Jul 2016' |
| 7 |
''' |
| 8 |
http://www.weblogssl.com/ |
| 9 |
''' |
| 10 |
|
| 11 |
import re |
| 12 |
|
| 13 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 14 |
|
| 15 |
|
| 16 |
class weblogssl(BasicNewsRecipe): |
| 17 |
__author__ = 'desUBIKado' |
| 18 |
description = 'Weblogs colectivos dedicados a seguir la actualidad sobre tecnologia, entretenimiento, estilos de vida, motor, deportes y economia.' |
| 19 |
title = 'Weblogs SL (Xataka, Genbeta, VidaExtra, Blog de Cine y otros)' |
| 20 |
publisher = 'Weblogs SL' |
| 21 |
language = 'es' |
| 22 |
timefmt = '[%a, %d %b, %Y]' |
| 23 |
oldest_article = 1 |
| 24 |
max_articles_per_feed = 100 |
| 25 |
encoding = 'utf-8' |
| 26 |
use_embedded_content = False |
| 27 |
remove_empty_feeds = True |
| 28 |
remove_javascript = True |
| 29 |
no_stylesheets = True |
| 30 |
|
| 31 |
# Si no se quiere recuperar todos los blogs se puede suprimir la descarga del que se desee poniendo |
| 32 |
# un caracter # por delante, es decir, # (u'Applesfera', u'http://feeds.weblogssl.com/applesfera'), |
| 33 |
# haría que no se descargase Applesfera. |
| 34 |
|
| 35 |
feeds = [ |
| 36 |
('Xataka', 'http://feeds.weblogssl.com/xataka2'), |
| 37 |
('Xataka M\xf3vil', 'http://feeds.weblogssl.com/xatakamovil'), |
| 38 |
('Xataka Foto', 'http://feeds.weblogssl.com/xatakafoto'), |
| 39 |
('Xataka Android', 'http://feeds.weblogssl.com/xatakandroid'), |
| 40 |
('Xataka Smart Home', 'http://feeds.weblogssl.com/Xatakahome'), |
| 41 |
('Xataka Windows', 'http://feeds.weblogssl.com/xatakawindows'), |
| 42 |
('Xataka Ciencia', 'http://feeds.weblogssl.com/xatakaciencia'), |
| 43 |
('Applesfera', 'http://feeds.weblogssl.com/applesfera'), |
| 44 |
('Vida Extra', 'http://feeds.weblogssl.com/vidaextra'), |
| 45 |
('Genbeta', 'http://feeds.weblogssl.com/genbeta'), |
| 46 |
('Genbeta Dev', 'http://feeds.weblogssl.com/genbetadev'), |
| 47 |
('Magnet', 'http://feeds.weblogssl.com/xatakamagnet2'), |
| 48 |
('Tendencias', 'http://feeds.weblogssl.com/trendencias'), |
| 49 |
('Tendencias Belleza', 'http://feeds.weblogssl.com/trendenciasbelleza'), |
| 50 |
('Tendencias Hombre', 'http://feeds.weblogssl.com/trendenciashombre'), |
| 51 |
('Tendencias Lifestyle', 'http://feeds.weblogssl.com/trendenciaslifestyle'), |
| 52 |
('Directo al paladar', 'http://feeds.weblogssl.com/directoalpaladar'), |
| 53 |
('Beb\xe9s y m\xe1s', 'http://feeds.weblogssl.com/bebesymas'), |
| 54 |
('Vit\xf3nica', 'http://feeds.weblogssl.com/vitonica'), |
| 55 |
('Decoesfera', 'http://feeds.weblogssl.com/decoesfera'), |
| 56 |
('Embelezzia', 'http://feeds.weblogssl.com/embelezzia'), |
| 57 |
('Pop rosa', 'http://feeds.weblogssl.com/poprosa'), |
| 58 |
('Motorpasi\xf3n', 'http://feeds.weblogssl.com/motorpasion'), |
| 59 |
('Motorpasi\xf3n Moto', 'http://feeds.weblogssl.com/motorpasionmoto'), |
| 60 |
('Motorpasi\xf3n Futuro', 'http://feeds.weblogssl.com/motorpasionfuturo'), |
| 61 |
('Blog de Cine', 'http://feeds.weblogssl.com/blogdecine'), |
| 62 |
('Vaya tele', 'http://feeds.weblogssl.com/vayatele2'), |
| 63 |
('Diario del viajero', 'http://feeds.weblogssl.com/diariodelviajero'), |
| 64 |
('Papel en blanco', 'http://feeds.weblogssl.com/papelenblanco'), |
| 65 |
('El blog salm\xf3n', 'http://feeds.weblogssl.com/elblogsalmon2'), |
| 66 |
('Pymes y aut\xf3nomos', 'http://feeds.weblogssl.com/pymesyautonomos'), |
| 67 |
('Ahorro diario', 'http://feeds.weblogssl.com/ahorrodiario'), |
| 68 |
('Xataka México', 'http://feeds.weblogssl.com/xatakamx'), |
| 69 |
('Xataka Android México', 'http://feeds.weblogssl.com/xatakandroidmx'), |
| 70 |
('Vida Extra México', 'http://feeds.weblogssl.com/vidaextramx'), |
| 71 |
('Xataka Colombia', 'http://feeds.weblogssl.com/xatakaco'), |
| 72 |
('Directo al paladar México', 'http://feeds.weblogssl.com/directoalpaladarmx'), |
| 73 |
('Vit\xf3nica México', 'http://feeds.weblogssl.com/vitonicamx'), |
| 74 |
('Tendencias Hombre México', 'http://feeds.weblogssl.com/trendenciashombremx'), |
| 75 |
('Motorpasi\xf3n México', 'http://feeds.weblogssl.com/motorpasionmx'), |
| 76 |
] |
| 77 |
|
| 78 |
keep_only_tags = [dict(name='div', attrs={'class': 'content-container'})] |
| 79 |
|
| 80 |
remove_tags = [ |
| 81 |
dict(name='div', attrs={'class': 'article-social-share m-v1 js-article-share js-article-social-share'}), |
| 82 |
dict(name='div', attrs={'class': 'article-social-share m-v1 js-article-social-share'}), |
| 83 |
dict(name='div', attrs={'class': 'social-widgets'}), |
| 84 |
dict(name='div', attrs={'class': 'article-social-share m-in-normal'}), |
| 85 |
dict(name='div', attrs={'class': 'article-comments'}), |
| 86 |
dict(name='div', attrs={'class': 'article-links'}), |
| 87 |
dict(name='div', attrs={'class': 'article-topics-list'}), |
| 88 |
dict(name='div', attrs={'class': 'ad-box'}), |
| 89 |
dict(name='blockquote', attrs={'class': 'instagram-media'}), |
| 90 |
dict(name='img', attrs={'alt': 'Código QR'}), |
| 91 |
dict(name='div', attrs={'id': 'comments'}), |
| 92 |
] |
| 93 |
|
| 94 |
remove_tags_after = dict(name='div', attrs={'id': 'comments'}) |
| 95 |
|
| 96 |
def print_version(self, url): |
| 97 |
if url.startswith('http://www'): |
| 98 |
return url.replace('http://www.', 'http://m.') |
| 99 |
else: |
| 100 |
return url.replace('http://', 'http://m.') |
| 101 |
|
| 102 |
preprocess_regexps = [ |
| 103 |
# Para poner una linea en blanco entre un comentario y el siguiente |
| 104 |
(re.compile(r'<li id="c', re.DOTALL | re.IGNORECASE), lambda match: '<br><br><li id="c'), |
| 105 |
# Para ver las imágenes en las noticias de m.xataka.com |
| 106 |
(re.compile(r'<noscript>', re.DOTALL | re.IGNORECASE), lambda m: ''), |
| 107 |
(re.compile(r'</noscript>', re.DOTALL | re.IGNORECASE), lambda m: ''), |
| 108 |
# Para cambiar de sitio el more |
| 109 |
(re.compile(r'<div class="article-content">', re.DOTALL | re.IGNORECASE), lambda m: '<div class="article-content"><!--more-->'), |
| 110 |
(re.compile(r'<div class="\/n<!--more-->">', re.DOTALL | re.IGNORECASE), lambda m: ''), |
| 111 |
# Para presentar la primera imagen del artículo |
| 112 |
(re.compile(r' srcset="http://i.blogs.es/', re.DOTALL | re.IGNORECASE), lambda match: ' src="http://i.blogs.es/'), |
| 113 |
(re.compile(r' 450w, http://i.blogs.es', re.DOTALL | re.IGNORECASE), lambda match: '"><!--'), |
| 114 |
(re.compile(r'1366w"><span></span>', re.DOTALL | re.IGNORECASE), lambda match: '-->'), |
| 115 |
(re.compile(r'1366w" sf-src="http://i.blogs.es', re.DOTALL | re.IGNORECASE), lambda match: '--> sf-src="http://i.blogs.es'), |
| 116 |
] |
| 117 |
|
| 118 |
# Para sustituir el video incrustado de YouTube por una imagen |
| 119 |
|
| 120 |
def preprocess_html(self, soup): |
| 121 |
for video_yt in soup.findAll('iframe', {'title': 'YouTube video player'}): |
| 122 |
if video_yt: |
| 123 |
video_yt.name = 'img' |
| 124 |
fuente = video_yt['src'] |
| 125 |
fuente2pre = fuente.replace('http://www.youtube.com/embed/', 'http://img.youtube.com/vi/') |
| 126 |
fuente2 = fuente2pre.replace('https://www.youtube.com/embed/', 'https://img.youtube.com/vi/') |
| 127 |
fuente3 = fuente2.replace('?rel=0', '') |
| 128 |
video_yt['src'] = fuente3 + '/0.jpg' |
| 129 |
|
| 130 |
for video_yt2 in soup.findAll('iframe', {'allowfullscreen'}): |
| 131 |
if video_yt2: |
| 132 |
esyt = video_yt2.find('youtube') |
| 133 |
if esyt: |
| 134 |
video_yt2.name = 'img' |
| 135 |
fuente = video_yt2['src'] |
| 136 |
fuente2pre = fuente.replace('http://www.youtube.com/embed/', 'http://img.youtube.com/vi/') |
| 137 |
fuente2 = fuente2pre.replace('https://www.youtube.com/embed/', 'https://img.youtube.com/vi/') |
| 138 |
video_yt2['src'] = fuente2 + '/0.jpg' |
| 139 |
|
| 140 |
return soup |
| 141 |
|
| 142 |
def get_article_url(self, article): |
| 143 |
return article.get('guid', None) |