mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
3bcf2c0d1b
Fixes #2073611 [Updated recipe for Pagina 12](https://bugs.launchpad.net/calibre/+bug/2073611)
118 lines
5.0 KiB
Python
118 lines
5.0 KiB
Python
# -*- mode: python -*-
|
|
# -*- coding: utf-8 -*-
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008-2024, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
pagina12.com.ar
|
|
'''
|
|
from calibre import strftime
|
|
from calibre.ptempfile import PersistentTemporaryFile
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class Pagina12(BasicNewsRecipe):
|
|
title = 'Pagina - 12'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Noticias de Argentina y el resto del mundo'
|
|
publisher = 'La Pagina S.A.'
|
|
category = 'news, politics, Argentina'
|
|
oldest_article = 2
|
|
no_stylesheets = True
|
|
encoding = 'utf8'
|
|
use_embedded_content = False
|
|
language = 'es_AR'
|
|
remove_empty_feeds = True
|
|
publication_type = 'newspaper'
|
|
auto_cleanup = False
|
|
delay = 1
|
|
simultaneous_downloads = 1
|
|
timeout = 8
|
|
needs_subscription = 'optional'
|
|
ignore_duplicate_articles = {'url'}
|
|
articles_are_obfuscated = True
|
|
temp_files = []
|
|
fetch_retries = 10
|
|
extra_css = """
|
|
body{font-family: "Open Sans", sans-serif}
|
|
.article-date{font-size: small; margin-bottom: 1em;}
|
|
.article-title{font-size: x-large; font-weight: bold; display: block; margin-bottom: 1em; margin-top: 1em;}
|
|
.article-main-media{display: block; margin-bottom: 1em;}
|
|
.article-summary{margin-top:1em; margin-bottom: 1em; display:block}
|
|
.article-author{font-family: "Archivo Narrow",Helvetica,sans-serif; color: gray; font-size: small; margin-top:1em; margin-bottom: 1em}
|
|
img{margin-top:1em; margin-bottom: 1em; display:block}
|
|
.article-text p:first-letter{display: inline; font-size: xx-large; font-weight: bold}
|
|
.article-prefix{font-family: "Archivo Narrow",Helvetica,sans-serif; font-size: small; text-transform: uppercase;}
|
|
"""
|
|
|
|
conversion_options = {
|
|
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
|
|
}
|
|
|
|
remove_tags = [
|
|
dict(name=['meta', 'link']),
|
|
dict(attrs={'class':'article-main-media-social show-for-medium'})
|
|
]
|
|
|
|
keep_only_tags=[
|
|
dict(name='div', attrs={'class':[
|
|
'article-header',
|
|
'article-titles',
|
|
'article-main-media-header',
|
|
'article-main-media',
|
|
'article-text'
|
|
]})
|
|
]
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser(self)
|
|
br.open('https://www.pagina12.com.ar/')
|
|
if self.username is not None and self.password is not None:
|
|
br.open('https://auth.pagina12.com.ar/ingresar?redirect=https://www.pagina12.com.ar')
|
|
br.select_form(id='login')
|
|
br['email'] = self.username
|
|
br['password'] = self.password
|
|
br.submit()
|
|
return br
|
|
|
|
feeds = [
|
|
(u'Diario de hoy' , u'https://www.pagina12.com.ar/rss/edicion-impresa'),
|
|
(u'Espectaculos' , u'https://www.pagina12.com.ar/rss/suplementos/cultura-y-espectaculos/notas'),
|
|
(u'Radar' , u'https://www.pagina12.com.ar/rss/suplementos/radar/notas'),
|
|
(u'Radar libros' , u'https://www.pagina12.com.ar/rss/suplementos/radar-libros/notas'),
|
|
(u'Cash' , u'https://www.pagina12.com.ar/rss/suplementos/cash/notas'),
|
|
(u'NO' , u'https://www.pagina12.com.ar/rss/suplementos/no/notas'),
|
|
(u'Las 12' , u'https://www.pagina12.com.ar/rss/suplementos/las12/notas'),
|
|
(u'Soy' , u'https://www.pagina12.com.ar/rss/suplementos/soy/notas'),
|
|
(u'M2' , u'https://www.pagina12.com.ar/rss/suplementos/m2/notas'),
|
|
(u'Rosario 12' , u'https://www.pagina12.com.ar/rss/suplementos/rosario12/notas')
|
|
]
|
|
|
|
def get_cover_url(self):
|
|
lurl = strftime('https://www.pagina12.com.ar/edicion-impresa/%d-%m-%Y')
|
|
soup = self.index_to_soup(lurl)
|
|
mydiv = soup.find('div', {'class' : lambda x: x and 'printed-edition-cover' in x.split()})
|
|
if mydiv:
|
|
for image in mydiv.findAll('img'):
|
|
if image['src'].startswith('https://images.pagina12.com.ar/styles/width700/public/'):
|
|
return image['src']
|
|
return None
|
|
|
|
def get_obfuscated_article(self, url):
|
|
result = None
|
|
count = 0
|
|
while (count < self.fetch_retries):
|
|
try:
|
|
response = self.browser.open(url, timeout=self.timeout)
|
|
html = response.read()
|
|
count = self.fetch_retries
|
|
tfile = PersistentTemporaryFile('_fa.html')
|
|
tfile.write(html)
|
|
tfile.close()
|
|
self.temp_files.append(tfile)
|
|
result = tfile.name
|
|
except:
|
|
self.info("Retrying download...")
|
|
count += 1
|
|
return result
|