Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Ambito and Ambito Financiero

Browse Source 
Fix #1784857 [Updated recipe for Ambito.com and Ambito financiero](https://bugs.launchpad.net/calibre/+bug/1784857)
This commit is contained in:
Kovid Goyal 2018-08-01 20:00:41 +05:30
parent bab192fa6c
commit 2d263573cb
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 59 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
recipes/ambito.recipe
View File

@ -2,7 +2,7 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008-2016, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2018, Darko Miletic <darko.miletic at gmail.com>'
''' '''
ambito.com ambito.com
''' '''
@ -39,6 +39,7 @@ class Ambito(BasicNewsRecipe):
dict(name='h6', attrs={'class': lambda x: x and 'bajada' in x.split()}) 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(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 '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()}) ,dict(attrs={'class': lambda x: x and 'despliegue-noticia' in x.split()})
] ]
remove_tags = [dict(name=['object','link','embed','iframe','meta','link'])] remove_tags = [dict(name=['object','link','embed','iframe','meta','link'])]

95
recipes/ambito_financiero.recipe
View File

@ -3,7 +3,7 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2011 - 2016, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2011 - 2018, Darko Miletic <darko.miletic at gmail.com>'
''' '''
ambito.com/diario ambito.com/diario
''' '''
@ -17,50 +17,59 @@ from calibre.ebooks.BeautifulSoup import BeautifulSoup
class Ambito_Financiero(BasicNewsRecipe): class Ambito_Financiero(BasicNewsRecipe):
title = 'Ambito Financiero' title = 'Ambito Financiero'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Informacion Libre las 24 horas' description = 'Informacion Libre las 24 horas'
publisher = 'Editorial Nefir S.A.' publisher = 'Editorial Nefir S.A.'
category = 'news, politics, economy, Argentina' category = 'news, politics, economy, Argentina'
no_stylesheets = True no_stylesheets = True
encoding = 'utf8' encoding = 'utf8'
publication_type = 'newspaper' publication_type = 'newspaper'
needs_subscription = True needs_subscription = True
use_embedded_content = False use_embedded_content = False
language = 'es_AR' language = 'es_AR'
delay = 1 delay = 1
session_id = None session_id = None
PREFIX = 'http://www.ambito.com' PREFIX = 'http://www.ambito.com'
PREFIXDIARIO = PREFIX + '/diario' PREFIXDIARIO = PREFIX + '/diario'
INDEX = PREFIX + '/diario/index.asp' INDEX = PREFIX + '/diario/index.asp'
LOGIN = PREFIX + '/login/login_cabezal.asp' LOGIN = PREFIX + '/login/login_cabezal.asp'
extra_css = """ extra_css = """
body{font-family: Roboto,sans-serif} body{font-family: Roboto,sans-serif}
""" """
conversion_options = { conversion_options = {
'comment' : description, 'comment': description,
'tags' : category, 'tags': category,
'publisher': publisher, 'publisher': publisher,
'language' : language 'language': language
} }
keep_only_tags = [ keep_only_tags = [
dict(name='h6', attrs={'class': lambda x: x and 'bajada' in x.split()}) 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(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 'titulo-noticia' in x.split()}),
,dict(attrs={'class': lambda x: x and 'despliegue-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'])] ]
remove_tags = [dict(name=['object', 'link', 'embed', 'iframe', 'meta', 'link'])]
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
br.open(self.INDEX) br.open(self.INDEX)
if self.username is not None and self.password is not None: if self.username is not None and self.password is not None:
data = urllib.urlencode({'txtUser':self.username, 'txtPassword':self.password}) data = urllib.urlencode({
response = br.open('http://www.ambito.com/diario/no-cache/login/x_login_cabezal.asp', data) '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() sessiondata = response.read()
prog = re.compile(r"^(?P<status>\d+?),(?P<session_id>.+?),(?P<username>.+?),.*?") prog = re.compile(
r"^(?P<status>\d+?),(?P<session_id>.+?),(?P<username>.+?),.*?"
)
m = prog.match(sessiondata) m = prog.match(sessiondata)
if m: if m:
self.session_id = m.group('session_id') self.session_id = m.group('session_id')
@ -70,7 +79,7 @@ class Ambito_Financiero(BasicNewsRecipe):
soup = self.index_to_soup(self.INDEX) soup = self.index_to_soup(self.INDEX)
articles = [] articles = []
checker = [] checker = []
rootitem = soup.find(attrs={'class':'ei-dropdown'}) rootitem = soup.find(attrs={'class': 'ei-dropdown'})
for feed_link in rootitem.findAll('a', href=True): for feed_link in rootitem.findAll('a', href=True):
url = self.PREFIXDIARIO + feed_link['href'] url = self.PREFIXDIARIO + feed_link['href']
title = self.tag_to_string(feed_link) title = self.tag_to_string(feed_link)
@ -78,7 +87,10 @@ class Ambito_Financiero(BasicNewsRecipe):
if url not in checker: if url not in checker:
checker.append(url) checker.append(url)
articles.append({ articles.append({
'title': title, 'date': date, 'url': url, 'description': u'' 'title': title,
'date': date,
'url': url,
'description': u''
}) })
return [(self.title, articles)] return [(self.title, articles)]
@ -86,17 +98,24 @@ class Ambito_Financiero(BasicNewsRecipe):
if self.session_id: if self.session_id:
l, s, r = url.rpartition('/') l, s, r = url.rpartition('/')
artid, s1, r1 = r.partition('-') artid, s1, r1 = r.partition('-')
data = urllib.urlencode({'id':artid, 'id_session':self.session_id}) data = urllib.urlencode({'id': artid, 'id_session': self.session_id})
response = self.browser.open('http://data.ambito.com/diario/cuerpo_noticia.asp', data) response = self.browser.open(
'http://data.ambito.com/diario/cuerpo_noticia.asp', data
)
soup = BeautifulSoup(raw_html) soup = BeautifulSoup(raw_html)
p = soup.find('p', id="cuerpo_noticia") p = soup.find('p', id="cuerpo_noticia")
if p: if p:
p.append(response.read()) smallsoup = BeautifulSoup(response.read())
cfind = smallsoup.find('div', id="contenido_data")
if cfind:
p.append(cfind)
return unicode(soup) return unicode(soup)
return raw_html return raw_html
def cleanup(self): def cleanup(self):
if self.session_id is not None: if self.session_id is not None:
data = urllib.urlencode({'session_id':self.session_id}) data = urllib.urlencode({'session_id': self.session_id})
self.browser.open('http://www.ambito.com/diario/no-cache/login/x_logout.asp', data) self.browser.open(
'http://www.ambito.com/diario/no-cache/login/x_logout.asp', data
)
self.session_id = None self.session_id = None