mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
2d263573cb
Fix #1784857 [Updated recipe for Ambito.com and Ambito financiero](https://bugs.launchpad.net/calibre/+bug/1784857)
122 lines
4.2 KiB
Python
122 lines
4.2 KiB
Python
#!/usr/bin/env python2
|
|
# -*- mode: python -*-
|
|
# -*- coding: utf-8 -*-
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2011 - 2018, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
ambito.com/diario
|
|
'''
|
|
|
|
import time
|
|
import urllib
|
|
import re
|
|
from calibre import strftime
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
|
|
|
|
|
class Ambito_Financiero(BasicNewsRecipe):
|
|
title = 'Ambito Financiero'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Informacion Libre las 24 horas'
|
|
publisher = 'Editorial Nefir S.A.'
|
|
category = 'news, politics, economy, Argentina'
|
|
no_stylesheets = True
|
|
encoding = 'utf8'
|
|
publication_type = 'newspaper'
|
|
needs_subscription = True
|
|
use_embedded_content = False
|
|
language = 'es_AR'
|
|
delay = 1
|
|
session_id = None
|
|
PREFIX = 'http://www.ambito.com'
|
|
PREFIXDIARIO = PREFIX + '/diario'
|
|
INDEX = PREFIX + '/diario/index.asp'
|
|
LOGIN = PREFIX + '/login/login_cabezal.asp'
|
|
extra_css = """
|
|
body{font-family: Roboto,sans-serif}
|
|
"""
|
|
|
|
conversion_options = {
|
|
'comment': description,
|
|
'tags': category,
|
|
'publisher': publisher,
|
|
'language': language
|
|
}
|
|
|
|
keep_only_tags = [
|
|
dict(name='h6', attrs={'class': lambda x: x and 'bajada' in x.split()}),
|
|
dict(name='span', attrs={'class': lambda x: x and 'dia' in x.split()}),
|
|
dict(attrs={'class': lambda x: x and 'titulo-noticia' in x.split()}),
|
|
dict(attrs={'class': lambda x: x and 'foto-perfil-columnista' in x.split()}),
|
|
dict(attrs={'class': lambda x: x and 'despliegue-noticia' in x.split()})
|
|
]
|
|
remove_tags = [dict(name=['object', 'link', 'embed', 'iframe', 'meta', 'link'])]
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser(self)
|
|
br.open(self.INDEX)
|
|
if self.username is not None and self.password is not None:
|
|
data = urllib.urlencode({
|
|
'txtUser': self.username,
|
|
'txtPassword': self.password
|
|
})
|
|
response = br.open(
|
|
'http://www.ambito.com/diario/no-cache/login/x_login_cabezal.asp',
|
|
data
|
|
)
|
|
sessiondata = response.read()
|
|
prog = re.compile(
|
|
r"^(?P<status>\d+?),(?P<session_id>.+?),(?P<username>.+?),.*?"
|
|
)
|
|
m = prog.match(sessiondata)
|
|
if m:
|
|
self.session_id = m.group('session_id')
|
|
return br
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup(self.INDEX)
|
|
articles = []
|
|
checker = []
|
|
rootitem = soup.find(attrs={'class': 'ei-dropdown'})
|
|
for feed_link in rootitem.findAll('a', href=True):
|
|
url = self.PREFIXDIARIO + feed_link['href']
|
|
title = self.tag_to_string(feed_link)
|
|
date = strftime("%a, %d %b %Y %H:%M:%S +0000", time.gmtime())
|
|
if url not in checker:
|
|
checker.append(url)
|
|
articles.append({
|
|
'title': title,
|
|
'date': date,
|
|
'url': url,
|
|
'description': u''
|
|
})
|
|
return [(self.title, articles)]
|
|
|
|
def preprocess_raw_html(self, raw_html, url):
|
|
if self.session_id:
|
|
l, s, r = url.rpartition('/')
|
|
artid, s1, r1 = r.partition('-')
|
|
data = urllib.urlencode({'id': artid, 'id_session': self.session_id})
|
|
response = self.browser.open(
|
|
'http://data.ambito.com/diario/cuerpo_noticia.asp', data
|
|
)
|
|
soup = BeautifulSoup(raw_html)
|
|
p = soup.find('p', id="cuerpo_noticia")
|
|
if p:
|
|
smallsoup = BeautifulSoup(response.read())
|
|
cfind = smallsoup.find('div', id="contenido_data")
|
|
if cfind:
|
|
p.append(cfind)
|
|
return unicode(soup)
|
|
return raw_html
|
|
|
|
def cleanup(self):
|
|
if self.session_id is not None:
|
|
data = urllib.urlencode({'session_id': self.session_id})
|
|
self.browser.open(
|
|
'http://www.ambito.com/diario/no-cache/login/x_logout.asp', data
|
|
)
|
|
self.session_id = None
|