Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Pagina 12

Browse Source 
Fixes #1796371 [Updated recipe for Pagina 12](https://bugs.launchpad.net/calibre/+bug/1796371)
This commit is contained in:
Kovid Goyal 2018-10-05 23:06:10 +05:30
parent 6a20a354bb
commit b413b8c40b
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 60 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
recipes/pagina12.recipe
View File

@ -2,12 +2,13 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2008-2017, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2018, Darko Miletic <darko.miletic at gmail.com>'
'''
pagina12.com.ar
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ptempfile import PersistentTemporaryFile
class Pagina12(BasicNewsRecipe):
@ -24,12 +25,17 @@ class Pagina12(BasicNewsRecipe):
remove_empty_feeds = True
publication_type = 'newspaper'
auto_cleanup = False
delay = 1
simultaneous_downloads = 1
timeout = 8
ignore_duplicate_articles = {'url'}
PREFIX = 'https://www.pagina12.com.ar'
articles_are_obfuscated = True
temp_files = []
fetch_retries = 10
extra_css = """
body{font-family: Lora,serif}
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; font-family: Oswald,sans-serif}
.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}
@ -44,16 +50,15 @@ class Pagina12(BasicNewsRecipe):
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-date',
'article-main-media-image',
'article-prefix',
'article-title',
'article-summary',
'article-author',
'article-info',
'article-titles',
'article-main-media-header',
'article-main-media',
'article-text'
]})
]
@ -74,7 +79,7 @@ class Pagina12(BasicNewsRecipe):
(u'Dialogos' , u'https://www.pagina12.com.ar/rss/secciones/dialogos/notas'),
(u'Hoy' , u'https://www.pagina12.com.ar/rss/secciones/hoy/notas'),
(u'Plastica' , u'https://www.pagina12.com.ar/rss/secciones/plastica/notas'),
(u'Carta de Lectores', u'https://www.pagina12.com.ar/rss/secciones/cartas-de-lectores/notas'),
(u'Cartas de Lectores', u'https://www.pagina12.com.ar/rss/secciones/cartas-de-lectores/notas'),
(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'),
@ -82,19 +87,12 @@ class Pagina12(BasicNewsRecipe):
(u'Turismo' , u'https://www.pagina12.com.ar/rss/suplementos/turismo/notas'),
(u'Libero' , u'https://www.pagina12.com.ar/rss/suplementos/libero/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'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'Futuro' , u'http://www.pagina12.com.ar/diario/rss/futuro.xml'),
(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')
(u'Rosario 12' , u'https://www.pagina12.com.ar/rss/suplementos/rosario12/notas')
]
def get_article_url(self, article):
url = article.get('guid', None)
if url.startswith('/'):
return self.PREFIX + url
return url
def get_cover_url(self):
lurl = strftime('https://www.pagina12.com.ar/edicion-impresa/%d-%m-%Y')
soup = self.index_to_soup(lurl)
@ -104,3 +102,21 @@ class Pagina12(BasicNewsRecipe):
if image['data-src'].startswith('https://images.pagina12.com.ar/styles/width700/public/'):
return image['data-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:
print "Retrying download..."
count += 1
return result