mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
3690241ab1
Fixes #1213759 [Updated recipes for El Tribuno de Salta and Jujuy](https://bugs.launchpad.net/calibre/+bug/1213759)
127 lines
4.6 KiB
Plaintext
127 lines
4.6 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2013, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
http://www.eltribuno.info/jujuy/edicion_impresa.aspx
|
|
'''
|
|
|
|
import urllib
|
|
from calibre.ptempfile import PersistentTemporaryFile
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from collections import OrderedDict
|
|
|
|
class ElTribunoJujuyImpreso(BasicNewsRecipe):
|
|
title = 'El Tribuno Jujuy (Edición Impresa)'
|
|
__author__ = 'Darko Miletic'
|
|
description = "Diario principal de Jujuy"
|
|
publisher = 'Horizontes S.A.'
|
|
category = 'news, politics, Jujuy, Argentina, World'
|
|
oldest_article = 2
|
|
language = 'es_AR'
|
|
max_articles_per_feed = 250
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
encoding = 'utf8'
|
|
publication_type = 'newspaper'
|
|
delay = 1
|
|
articles_are_obfuscated = True
|
|
temp_files = []
|
|
PREFIX = 'http://www.eltribuno.info/jujuy/'
|
|
INDEX = PREFIX + 'edicion_impresa.aspx'
|
|
PRINTURL = PREFIX + 'nota_print.aspx?%s'
|
|
|
|
conversion_options = {
|
|
'comment' : description
|
|
, 'tags' : category
|
|
, 'publisher' : publisher
|
|
, 'language' : language
|
|
, 'linearize_tables' : True
|
|
}
|
|
|
|
keep_only_tags = [dict(name='div' , attrs={'class':['notaHead', 'notaContent']})]
|
|
remove_tags = [
|
|
dict(name=['meta','iframe','base','object','embed','link','img']),
|
|
dict(name='ul', attrs={'class':'Tabs'})
|
|
]
|
|
|
|
extra_css = """
|
|
body{font-family: Arial,Helvetica,sans-serif}
|
|
.notaHead h4{text-transform: uppercase; color: gray}
|
|
img{margin-top: 0.8em; display: block}
|
|
"""
|
|
|
|
def parse_index(self):
|
|
feeds = OrderedDict()
|
|
soup = None
|
|
count = 0
|
|
while (count < 5):
|
|
try:
|
|
soup = self.index_to_soup(self.INDEX)
|
|
count = 5
|
|
except:
|
|
print "Retrying download..."
|
|
count += 1
|
|
if not soup:
|
|
return []
|
|
alink = soup.find('a', href=True, attrs={'class':'ZoomTapa'})
|
|
if alink and 'href' in alink:
|
|
self.cover_url = alink['href']
|
|
sections = soup.findAll('div', attrs={'id':lambda x: x and x.startswith('Ediciones')})
|
|
for section in sections:
|
|
section_title = 'Sin titulo'
|
|
sectiont=section.find('h3', attrs={'class':'NombreSeccion'})
|
|
if sectiont:
|
|
section_title = self.tag_to_string(sectiont.span)
|
|
|
|
arts = section.findAll('div', attrs={'class':'Noticia NoticiaAB1'})
|
|
for article in arts:
|
|
articles = []
|
|
title=self.tag_to_string(article.div.h3.a)
|
|
url=article.div.h3.a['href']
|
|
description=self.tag_to_string(article.p)
|
|
articles.append({'title':title, 'url':url, 'description':description, 'date':''})
|
|
|
|
if articles:
|
|
if section_title not in feeds:
|
|
feeds[section_title] = []
|
|
feeds[section_title] += articles
|
|
|
|
ans = [(key, val) for key, val in feeds.iteritems()]
|
|
return ans
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
for item in soup.findAll('a'):
|
|
if item.string is not None:
|
|
str = item.string
|
|
item.replaceWith(str)
|
|
else:
|
|
str = self.tag_to_string(item)
|
|
item.replaceWith(str)
|
|
return soup
|
|
|
|
def get_masthead_title(self):
|
|
return 'El Tribuno'
|
|
|
|
def get_obfuscated_article(self, url):
|
|
count = 0
|
|
while (count < 10):
|
|
try:
|
|
response = self.browser.open(url)
|
|
html = response.read()
|
|
count = 10
|
|
except:
|
|
print "Retrying download..."
|
|
count += 1
|
|
tfile = PersistentTemporaryFile('_fa.html')
|
|
tfile.write(html)
|
|
tfile.close()
|
|
self.temp_files.append(tfile)
|
|
return tfile.name
|
|
|
|
def print_version(self, url):
|
|
right = url.rpartition('/')[2]
|
|
artid = right.partition('-')[0]
|
|
params = {'Note':artid}
|
|
return (self.PRINTURL % urllib.urlencode(params))
|