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

Remove unmaintained recipes. Fixes #1632813 [Remove obsolete recipes](https://bugs.launchpad.net/calibre/+bug/1632813)

Browse Source
This commit is contained in:
Kovid Goyal 2016-10-13 06:47:05 +05:30
parent c06e8d6b20
commit 21763cf0b1
24 changed files with 0 additions and 1011 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
recipes/7dias.recipe
View File

@ -1,68 +0,0 @@
#!/usr/bin/env python2
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
elargentino.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class SieteDias(BasicNewsRecipe):
title = '7 dias'
__author__ = 'Darko Miletic'
description = 'Revista Argentina'
publisher = 'ElArgentino.com'
category = 'news, politics, show, Argentina'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = 'es_AR'
lang = 'es-AR'
direction = 'ltr'
INDEX = 'http://www.elargentino.com/medios/125/7-Dias.html'
extra_css = ' .titulo{font-size: x-large; font-weight: bold} .volantaImp{font-size: small; font-weight: bold} '
keep_only_tags = [dict(name='div', attrs={'class': 'ContainerPop'})]
remove_tags = [dict(name='link')]
feeds = [(u'Articulos', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=125&Content-Type=text/xml&ChannelDesc=7%20D%C3%ADas')]
def print_version(self, url):
main, sep, article_part = url.partition('/nota-')
article_id, rsep, rrest = article_part.partition('-')
return u'http://www.elargentino.com/Impresion.aspx?Id=' + article_id
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
soup.html['lang'] = self.lang
soup.html['dir'] = self.direction
mlang = Tag(soup, 'meta', [
("http-equiv", "Content-Language"), ("content", self.lang)])
mcharset = Tag(soup, 'meta', [
("http-equiv", "Content-Type"), ("content", "text/html; charset=utf-8")])
soup.head.insert(0, mlang)
soup.head.insert(1, mcharset)
return soup
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup(self.INDEX)
cover_item = soup.find('div', attrs={'class': 'colder'})
if cover_item:
clean_url = self.image_url_processor(
None, cover_item.div.img['src'])
cover_url = 'http://www.elargentino.com' + clean_url + '&height=600'
return cover_url
def image_url_processor(self, baseurl, url):
base, sep, rest = url.rpartition('?Id=')
img, sep2, rrest = rest.partition('&')
return base + sep + img

94
recipes/argnoticias.recipe
View File

@ -1,94 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2013, Darko Miletic <darko.miletic at gmail.com>'
'''
www.argnoticias.com
'''
import time
from calibre import strftime
from calibre.web.feeds.recipes import BasicNewsRecipe
class ArgNoticias(BasicNewsRecipe):
title = 'ARG Noticias'
__author__ = 'Darko Miletic'
description = 'Ultimas noticias de Argentina'
publisher = 'ARG Noticias'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
masthead_url = 'http://www.argnoticias.com/images/arg-logo-footer.png'
language = 'es_AR'
publication_type = 'newsportal'
INDEX = 'http://www.argnoticias.com'
extra_css = ''
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
keep_only_tags = [
dict(name='div', attrs={'class': ['itemHeader', 'itemBody', 'itemAuthorBlock']})]
remove_tags = [
dict(name=['object', 'link', 'base', 'iframe']),
dict(name='div', attrs={
'class': ['b2jsocial_parent', 'itemSocialSharing']})
]
feeds = [
(u'Politica', u'http://www.argnoticias.com/index.php/politica'),
(u'Economia', u'http://www.argnoticias.com/index.php/economia'),
(u'Sociedad', u'http://www.argnoticias.com/index.php/sociedad'),
(u'Mundo', u'http://www.argnoticias.com/index.php/mundo'),
(u'Deportes', u'http://www.argnoticias.com/index.php/deportes'),
(u'Espectaculos', u'http://www.argnoticias.com/index.php/espectaculos'),
(u'Tendencias', u'http://www.argnoticias.com/index.php/tendencias')
]
def parse_index(self):
totalfeeds = []
lfeeds = self.get_feeds()
checker = []
for feedobj in lfeeds:
feedtitle, feedurl = feedobj
self.report_progress(0, _('Fetching feed') + ' %s...' %
(feedtitle if feedtitle else feedurl))
articles = []
soup = self.index_to_soup(feedurl)
for item in soup.findAll('div', attrs={'class': 'Nota'}):
atag = item.find('a', attrs={'class': 'moduleItemTitle'})
ptag = item.find('div', attrs={'class': 'moduleItemIntrotext'})
url = self.INDEX + atag['href']
title = self.tag_to_string(atag)
description = self.tag_to_string(ptag)
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': description
})
for item in soup.findAll('li'):
atag = item.find('a', attrs={'class': 'moduleItemTitle'})
if atag:
ptag = item.find(
'div', attrs={'class': 'moduleItemIntrotext'})
url = self.INDEX + atag['href']
title = self.tag_to_string(atag)
description = self.tag_to_string(ptag)
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': description
})
totalfeeds.append((feedtitle, articles))
return totalfeeds

57
recipes/axxon_magazine.recipe
View File

@ -1,57 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
axxon.com.ar
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Axxon_news(BasicNewsRecipe):
title = 'Revista Axxon'
__author__ = 'Darko Miletic'
description = 'Axxon, Ciencia Ficcion en Bits'
publisher = 'Revista Axxon - Ciencia Ficcion'
category = 'SF, Argentina'
oldest_article = 31
delay = 1
max_articles_per_feed = 100
no_stylesheets = False
use_embedded_content = False
language = 'es_AR'
encoding = 'utf-8'
publication_type = 'magazine'
INDEX = 'http://axxon.com.ar/rev/'
extra_css = ' body{font-family: Verdana,Arial,sans-serif} .editorial{font-family: serif} .posttitle{font-family: "Trebuchet MS","Lucida Grande",Verdana,Arial,sans-serif} .cuento{font-family: "Times New Roman", serif} .biografia{color: red; font-weight: bold; font-family: Verdana,Geneva,Arial,Helvetica,sans-serif} ' # noqa
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
keep_only_tags = [dict(name='div', attrs={'class': 'post'})]
remove_tags = [dict(name=['object', 'link', 'iframe', 'embed', 'img'])]
remove_tags_after = [
dict(attrs={'class': ['editorial', 'correo', 'biografia', 'articulo']})]
remove_attributes = ['width', 'height', 'font', 'border', 'align']
def parse_index(self):
articles = []
soup = self.index_to_soup(self.INDEX)
for item in soup.findAll('strong'):
description = ''
title_prefix = ''
feed_link = item.find('a')
if feed_link and feed_link.has_key('href') and feed_link['href'].startswith('?p='): # noqa
url = self.INDEX + feed_link['href']
title = title_prefix + self.tag_to_string(feed_link)
date = strftime(self.timefmt)
articles.append({
'title': title, 'date': date, 'url': url, 'description': description
})
return [(soup.head.title.string, articles)]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return self.adeify_images(soup)

57
recipes/axxon_news.recipe
View File

@ -1,57 +0,0 @@
#!/usr/bin/env python2
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
axxon.com.ar
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class Axxon_news(BasicNewsRecipe):
title = 'Axxon noticias'
__author__ = 'Darko Miletic'
description = 'Axxon, Ciencia Ficcion en Bits'
publisher = 'Axxon'
category = 'news, SF, Argentina, science, movies'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = False
use_embedded_content = False
language = 'es_AR'
lang = 'es-AR'
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': lang, 'pretty_print': True
}
keep_only_tags = [dict(name='div', attrs={'class': 'post'})]
remove_tags = [dict(name=['object', 'link', 'iframe', 'embed'])]
feeds = [(u'Noticias', u'http://axxon.com.ar/noticias/feed/')]
remove_attributes = ['style', 'width', 'height', 'font', 'border', 'align']
def adeify_images2(cls, soup):
for item in soup.findAll('img'):
for attrib in ['height', 'width', 'border', 'align', 'style']:
if item.has_key(attrib): # noqa
del item[attrib]
oldParent = item.parent
if oldParent.name == 'a':
oldParent.name == 'p'
myIndex = oldParent.contents.index(item)
brtag = Tag(soup, 'br')
oldParent.insert(myIndex + 1, brtag)
return soup
def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang
mlang = Tag(soup, 'meta', [
("http-equiv", "Content-Language"), ("content", self.lang)])
soup.html.insert(0, mlang)
return self.adeify_images2(soup)

49
recipes/diagonales.recipe
View File

@ -1,49 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2009-2013, Darko Miletic <darko.miletic at gmail.com>'
'''
diagonales.infonews.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Diagonales(BasicNewsRecipe):
title = 'Diagonales'
__author__ = 'Darko Miletic'
description = 'Para estar bien informado sobre los temas de actualidad. Conoce sobre pais, economia, deportes, mundo, espectaculos, sociedad, entrevistas y tecnologia.' # noqa
publisher = 'INFOFIN S.A.'
category = 'news, politics, Argentina, La Plata'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = 'es_AR'
publication_type = 'newspaper'
delay = 1
remove_empty_feeds = True
extra_css = ' .titulo{font-size: x-large; font-weight: bold} .volantaImp{font-size: small; font-weight: bold} '
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
keep_only_tags = [dict(name='div', attrs={'class': 'ContainerPop'})]
remove_tags = [dict(name='link')]
feeds = [
(u'Pais', u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=112&Content-Type=text/xml&ChannelDesc=Pa%C3%ADs'),
(u'Deportes', u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=106&Content-Type=text/xml&ChannelDesc=Deportes'),
(u'Economia', u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=107&Content-Type=text/xml&ChannelDesc=Econom%C3%ADa'),
(u'Sociedad', u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=109&Content-Type=text/xml&ChannelDesc=Sociedad'),
(u'Mundo', u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=113&Content-Type=text/xml&ChannelDesc=Mundo'),
(u'Espectaculos', u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=114&Content-Type=text/xml&ChannelDesc=Espect%C3%A1culos'),
(u'Entrevistas', u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=115&Content-Type=text/xml&ChannelDesc=Entrevistas'),
(u'Tecnologia', u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=118&Content-Type=text/xml&ChannelDesc=Tecnolog%C3%ADa')
]
def print_version(self, url):
main, sep, article_part = url.partition('/nota-')
article_id, rsep, rrest = article_part.partition('-')
return u'http://diagonales.infonews.com/Impresion.aspx?Id=' + article_id

61
recipes/elargentino.recipe
View File

@ -1,61 +0,0 @@
#!/usr/bin/env python2
__license__ = 'GPL v3'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
elargentino.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ElArgentino(BasicNewsRecipe):
title = 'ElArgentino.com'
__author__ = 'Darko Miletic'
description = 'Informacion Libre las 24 horas'
publisher = 'ElArgentino.com'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 100
remove_javascript = True
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
cover_url = 'http://www.elargentino.com/TemplateWeb/MediosFooter/tapa_elargentino.png'
language = 'es_AR'
html2lrf_options = [
'--comment', description, '--category', category, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + \
'"\ncomments="' + description + '"\ntags="' + category + '"'
remove_tags = [
dict(name='div', attrs={'id': 'noprint'}), dict(name='div', attrs={
'class': 'encabezadoImprimir'}), dict(name='a', attrs={'target': '_blank'})
]
feeds = [
(u'Portada', u'http://www.elargentino.com/Highlights.aspx?Content-Type=text/xml&ChannelDesc=Home'),
(u'Pais', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=112&Content-Type=text/xml&ChannelDesc=Pa%C3%ADs'),
(u'Economia', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=107&Content-Type=text/xml&ChannelDesc=Econom%C3%ADa'),
(u'Mundo', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=113&Content-Type=text/xml&ChannelDesc=Mundo'),
(u'Tecnologia', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=118&Content-Type=text/xml&ChannelDesc=Tecnolog%C3%ADa'),
(u'Espectaculos', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=114&Content-Type=text/xml&ChannelDesc=Espect%C3%A1culos'),
(u'Deportes', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=106&Content-Type=text/xml&ChannelDesc=Deportes'),
(u'Sociedad', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=109&Content-Type=text/xml&ChannelDesc=Sociedad'),
(u'Entrevistas', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=115&Content-Type=text/xml&ChannelDesc=Entrevistas')
]
def print_version(self, url):
main, sep, article_part = url.partition('/nota-')
article_id, rsep, rrest = article_part.partition('-')
return u'http://www.elargentino.com/Impresion.aspx?Id=' + article_id
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8">\n<meta http-equiv="Content-Language" content="es-AR"/>\n'
soup.head.insert(0, mtag)
for item in soup.findAll(style=True):
del item['style']
return soup

128
recipes/eltribuno_jujuy_impreso.recipe
View File

@ -1,128 +0,0 @@
__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))

46
recipes/eltribuno_salta_impreso.recipe
View File

@ -1,46 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2013 - 2016, Darko Miletic <darko.miletic at gmail.com>'
'''
http://www.eltribuno.info/salta/edicion_impresa.aspx
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ElTribunoSaltaImpreso(BasicNewsRecipe):
title = 'El Tribuno Salta'
__author__ = 'Darko Miletic'
description = "Diario principal de Salta"
publisher = 'Horizontes S.A.'
category = 'news, politics, Salta, 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'
remove_javascript = True
auto_cleanup = True
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher': publisher
, 'language' : language
}
extra_css = """
body{font-family: Arial,Helvetica,sans-serif}
img{margin-top: 0.8em; display: block}
"""
feeds = [
(u'Mas leidas', u'http://www.eltribuno.info/rss/salta/masleidas.xml')
,(u'El Tribuno', u'http://www.eltribuno.info/rss/salta/home.xml')
,(u'Salta' , u'http://www.eltribuno.info/rss/salta/salta.xml')
,(u'Deportes' , u'http://www.eltribuno.info/rss/salta/deportes.xml')
]
def get_masthead_title(self):
return 'El Tribuno'

BIN
recipes/icons/argnoticias.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 128 B

BIN
recipes/icons/axxon_news.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 278 B

BIN
recipes/icons/diagonales.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 4.5 KiB

BIN
recipes/icons/elargentino.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 477 B

BIN
recipes/icons/eltribuno_jujuy_impreso.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 573 B

BIN
recipes/icons/eltribuno_salta_impreso.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 573 B

BIN
recipes/icons/losandes.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 187 B

BIN
recipes/icons/miradasalsur.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 661 B

BIN
recipes/icons/perfil.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 329 B

73
recipes/lamujerdemivida.recipe
View File

@ -1,73 +0,0 @@
#!/usr/bin/env python2
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
lamujerdemivida.com.ar
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class LaMujerDeMiVida(BasicNewsRecipe):
title = 'La Mujer de mi Vida'
__author__ = 'Darko Miletic'
description = 'Cultura de otra manera'
oldest_article = 90
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
publisher = 'La Mujer de mi Vida'
category = 'literatura, critica, arte, ensayos'
language = 'es_AR'
INDEX = 'http://www.lamujerdemivida.com.ar/'
html2lrf_options = [
'--comment', description, '--category', category, '--publisher', publisher, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + \
description + '"\ntags="' + category + '"\nlinearize_tables=True'
keep_only_tags = [dict(name='table', attrs={'width': '570'})]
feeds = [(u'Articulos', u'http://www.lamujerdemivida.com.ar/index.php')]
def preprocess_html(self, soup):
soup.html['xml:lang'] = 'es-AR'
soup.html['lang'] = 'es-AR'
mtag = '<meta http-equiv="Content-Language" content="es-AR"/>'
soup.head.insert(0, mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup(self.INDEX)
cover_item = soup.find('img', attrs={'alt': 'Lamujerdemivida.'})
if cover_item:
cover_url = self.INDEX + cover_item['src']
return cover_url
def parse_index(self):
totalfeeds = []
lfeeds = self.get_feeds()
for feedobj in lfeeds:
feedtitle, feedurl = feedobj
self.report_progress(0, _('Fetching feed') + ' %s...' %
(feedtitle if feedtitle else feedurl))
articles = []
soup = self.index_to_soup(feedurl)
for item in soup.findAll('td', attrs={'width': '390'}):
atag = item.find('a', href=True)
if atag:
url = atag['href']
title = self.tag_to_string(atag)
date = strftime(self.timefmt)
articles.append({
'title': title, 'date': date, 'url': url, 'description': ''
})
totalfeeds.append((feedtitle, articles))
return totalfeeds

75
recipes/losandes.recipe
View File

@ -1,75 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
'''
www.losandes.com.ar
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class LosAndes(BasicNewsRecipe):
title = 'Los Andes'
__author__ = 'Darko Miletic'
description = 'Noticias de Mendoza, Argentina y el resto del mundo'
publisher = 'Los Andes'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'cp1252'
use_embedded_content = False
language = 'es_AR'
remove_empty_feeds = True
publication_type = 'newspaper'
masthead_url = 'http://www.losandes.com.ar/graficos/losandes.png'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif }
h1,h2{font-family: "Times New Roman",Times,serif}
.fechaNota{font-weight: bold; color: gray}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
remove_tags = [
dict(name=['meta', 'link']), dict(attrs={'class': ['cabecera', 'url']})
]
remove_tags_before = dict(attrs={'class': 'cabecera'})
remove_tags_after = dict(attrs={'class': 'url'})
feeds = [
(u'Ultimas Noticias', u'http://www.losandes.com.ar/servicios/rss.asp?r=78'),
(u'Politica', u'http://www.losandes.com.ar/servicios/rss.asp?r=68'),
(u'Economia nacional', u'http://www.losandes.com.ar/servicios/rss.asp?r=65'),
(u'Economia internacional', u'http://www.losandes.com.ar/servicios/rss.asp?r=505'),
(u'Internacionales', u'http://www.losandes.com.ar/servicios/rss.asp?r=66'),
(u'Turismo', u'http://www.losandes.com.ar/servicios/rss.asp?r=502'),
(u'Fincas', u'http://www.losandes.com.ar/servicios/rss.asp?r=504'),
(u'Isha nos habla', u'http://www.losandes.com.ar/servicios/rss.asp?r=562'),
(u'Estilo', u'http://www.losandes.com.ar/servicios/rss.asp?r=81'),
(u'Cultura', u'http://www.losandes.com.ar/servicios/rss.asp?r=503'),
(u'Policiales', u'http://www.losandes.com.ar/servicios/rss.asp?r=70'),
(u'Deportes', u'http://www.losandes.com.ar/servicios/rss.asp?r=69'),
(u'Sociedad', u'http://www.losandes.com.ar/servicios/rss.asp?r=67'),
(u'Opinion', u'http://www.losandes.com.ar/servicios/rss.asp?r=80'),
(u'Editorial', u'http://www.losandes.com.ar/servicios/rss.asp?r=76'),
(u'Mirador', u'http://www.losandes.com.ar/servicios/rss.asp?r=79')
]
def print_version(self, url):
artid = url.rpartition('.')[0].rpartition('-')[2]
return "http://www.losandes.com.ar/includes/modulos/imprimir.asp?tipo=noticia&id=" + artid
def get_cover_url(self):
month = strftime("%m").lstrip('0')
day = strftime("%d").lstrip('0')
year = strftime("%Y")
return "http://www.losandes.com.ar/fotografias/fotosnoticias/" + year + "/" + month + "/" + day + "/th_tapa.jpg"
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup

67
recipes/miradasalsur.recipe
View File

@ -1,67 +0,0 @@
__copyright__ = '2009-2013, Darko Miletic <darko.miletic at gmail.com>'
'''
sur.infonews.com
'''
import datetime
from calibre.web.feeds.news import BasicNewsRecipe
class MiradasAlSur(BasicNewsRecipe):
title = 'Miradas al Sur'
__author__ = 'Darko Miletic'
description = 'Semanario Argentino'
publisher = 'ElArgentino.com'
category = 'news, politics, Argentina'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = 'es_AR'
remove_empty_feeds = True
masthead_url = 'http://sur.infonews.com/sites/default/files/www_miradas_al_sur_com_logo.gif'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif}
h1{font-family: Georgia,Times,serif}
.field-field-story-author{color: gray; font-size: small}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'series': title
}
keep_only_tags = [
dict(name='div', attrs={'id': ['content-header', 'content-area']})]
remove_tags = [
dict(name=['link', 'meta', 'iframe', 'embed', 'object']),
dict(name='form', attrs={'class': 'fivestar-widget'}),
dict(attrs={'class': lambda x: x and 'terms-inline' in x.split()})
]
feeds = [
(u'Politica', u'http://sur.infonews.com/taxonomy/term/1/0/feed'),
(u'Internacional', u'http://sur.infonews.com/taxonomy/term/2/0/feed'),
(u'Informe Especial', u'http://sur.infonews.com/taxonomy/term/14/0/feed'),
(u'Delitos y pesquisas', u'http://sur.infonews.com/taxonomy/term/6/0/feed'),
(u'Lesa Humanidad', u'http://sur.infonews.com/taxonomy/term/7/0/feed'),
(u'Cultura', u'http://sur.infonews.com/taxonomy/term/8/0/feed'),
(u'Deportes', u'http://sur.infonews.com/taxonomy/term/9/0/feed'),
(u'Contratapa', u'http://sur.infonews.com/taxonomy/term/10/0/feed'),
]
def get_cover_url(self):
# determine the series number, unfortunately not gonna happen now
# self.conversion_options.update({'series_index':seriesnr})
cover_url = None
cdate = datetime.date.today()
todayweekday = cdate.isoweekday()
if (todayweekday != 7):
cdate -= datetime.timedelta(days=todayweekday)
cover_page_url = cdate.strftime(
'http://sur.infonews.com/ediciones/%Y-%m-%d/tapa')
soup = self.index_to_soup(cover_page_url)
cover_item = soup.find('img', attrs={
'class': lambda x: x and 'imagecache-tapa_edicion_full' in x.split()})
if cover_item:
cover_url = cover_item['src']
return cover_url

76
recipes/newsweek_argentina.recipe
View File

@ -1,76 +0,0 @@
#!/usr/bin/env python2
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
elargentino.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class Newsweek_Argentina(BasicNewsRecipe):
title = 'NewsWeek Argentina'
__author__ = 'Darko Miletic'
description = 'Revista dedicada a politica'
publisher = 'ElArgentino.com'
category = 'news, politics, world, Argentina'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = 'es_AR'
lang = 'es-AR'
direction = 'ltr'
INDEX = 'http://www.elargentino.com/medios/126/Newsweek.html'
extra_css = ' .titulo{font-size: x-large; font-weight: bold} .volantaImp{font-size: small; font-weight: bold} '
html2lrf_options = [
'--comment', description, '--category', category, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + \
category + \
'"\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
keep_only_tags = [dict(name='div', attrs={'class': 'ContainerPop'})]
remove_tags = [dict(name='link')]
feeds = [(u'Articulos', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=126&Content-Type=text/xml&ChannelDesc=Newsweek')]
def print_version(self, url):
main, sep, article_part = url.partition('/nota-')
article_id, rsep, rrest = article_part.partition('-')
return u'http://www.elargentino.com/Impresion.aspx?Id=' + article_id
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
soup.html['lang'] = self.lang
soup.html['dir'] = self.direction
mlang = Tag(soup, 'meta', [
("http-equiv", "Content-Language"), ("content", self.lang)])
mcharset = Tag(soup, 'meta', [
("http-equiv", "Content-Type"), ("content", "text/html; charset=utf-8")])
soup.head.insert(0, mlang)
soup.head.insert(1, mcharset)
return soup
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup(self.INDEX)
cover_item = soup.find('div', attrs={'class': 'colder'})
if cover_item:
clean_url = self.image_url_processor(
None, cover_item.div.img['src'])
cover_url = 'http://www.elargentino.com' + clean_url + '&height=600'
return cover_url
def image_url_processor(self, baseurl, url):
base, sep, rest = url.rpartition('?Id=')
img, sep2, rrest = rest.partition('&')
return base + sep + img

59
recipes/perfil.recipe
View File

@ -1,59 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2010-2015, Darko Miletic <darko.miletic at gmail.com>'
'''
perfil.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Perfil(BasicNewsRecipe):
title = 'Perfil'
__author__ = 'Darko Miletic'
description = 'Noticias de Argentina y el resto del mundo'
publisher = 'perfil.com'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'es_AR'
remove_empty_feeds = True
masthead_url = 'http://www.perfil.com/__export/1330013400000/system/modules/com.tfsla.perfil.diario/resources/v1/images/perfilcom-logo-secciones.png'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif }
.seccion{border-bottom: 1px dotted #666666; text-transform: uppercase; font-size: x-large}
.foto1 h1{font-size: x-small}
h1{font-family: Georgia,"Times New Roman",serif}
img{margin-bottom: 0.4em}
.hora{font-size: x-small; color: red}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
remove_tags = [
dict(name=['iframe', 'embed', 'object', 'base', 'meta', 'link']), dict(attrs={
'id': ['social-articulo', 'relacionadas']}), dict(attrs={'class': 'destacadoNota'})
]
keep_only_tags = [
dict(attrs={'id': 'header-noticia'}), dict(attrs={'class': 'cuerpo'})]
feeds = [
(u'Ultimo momento', u'http://www.perfil.com/rss/ultimomomento.xml'),
(u'Politica', u'http://www.perfil.com/rss/politica.xml'),
(u'Policia', u'http://www.perfil.com/rss/policia.xml'),
(u'Internacionales', u'http://www.perfil.com/rss/internacional.xml'),
(u'Economia', u'http://www.perfil.com/rss/economia.xml'),
(u'Deportes', u'http://www.perfil.com/rss/deportes.xml'),
(u'Opinion', u'http://www.perfil.com/rss/columnistas.xml'),
(u'Sociedad', u'http://www.perfil.com/rss/sociedad.xml'),
(u'Cultura', u'http://www.perfil.com/rss/cultura.xml'),
(u'Espectaculos', u'http://www.perfil.com/rss/espectaculos.xml'),
(u'Ciencia', u'http://www.perfil.com/rss/ciencia.xml'),
(u'Salud', u'http://www.perfil.com/rss/salud.xml'),
(u'Tecnologia', u'http://www.perfil.com/rss/tecnologia.xml')
]

38
recipes/reptantes.recipe
View File

@ -1,38 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.reptantes.com.ar
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Reptantes(BasicNewsRecipe):
title = 'Reptantes'
__author__ = 'Darko Miletic'
description = u"cada vez que te haces acupuntura, tu muñeco vudú sufre en algún lado"
oldest_article = 130
max_articles_per_feed = 100
language = 'es_AR'
encoding = 'utf-8'
no_stylesheets = True
use_embedded_content = False
publication_type = 'blog'
extra_css = ' body{font-family: "Palatino Linotype",serif} h2{text-align: center; color:#BE7F8D} img{margin-bottom: 2em} '
conversion_options = {
'comment': description, 'tags': 'literatura', 'publisher': 'Hernan Racnati', 'language': language
}
feeds = [(u'Posts', u'http://www.reptantes.com.ar/?feed=rss2')]
keep_only_tags = [dict(attrs={'id': 'content'})]
remove_tags = [dict(attrs={'class': 'iLikeThis'})]
remove_tags_before = dict(name='h2')
remove_tags_after = dict(attrs={'class': 'iLikeThis'})
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return self.adeify_images(soup)

63
recipes/rionegro.recipe
View File

@ -1,63 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>'
'''
www.rionegro.com.ar
'''
from calibre.web.feeds.news import BasicNewsRecipe
class RioNegro(BasicNewsRecipe):
title = 'Diario Rio Negro'
__author__ = 'Darko Miletic'
description = 'Noticias desde la Patagonia Argentina y el resto del mundo'
publisher = 'Editorial Rio Negro SA.'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'es_AR'
remove_empty_feeds = True
publication_type = 'newspaper'
masthead_url = 'http://www.rionegro.com.ar/diario/imagenes/logorn.gif'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif }
img{display:block}
h1 {font-size: 0.89em; color: red}
h2 {font-family: Georgia,"Times New Roman",Times,serif; font-size: 1.8em}
h3 {font-family: Georgia,"Times New Roman",Times,serif; border-bottom: 2px solid gray}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
remove_tags = [
dict(name=['meta', 'link', 'iframe', 'object', 'embed']), dict(
name='div', attrs={'class': 'logo'})
]
keep_only_tags = [dict(attrs={'class': 'nota'})]
remove_attributes = ['lang']
feeds = [
(u'Argentina', u'http://www.rionegro.com.ar/diario/funciones/xml/rss.aspx?idcat=9532'),
(u'El Mundo', u'http://www.rionegro.com.ar/diario/funciones/xml/rss.aspx?idcat=9533'),
(u'Carta de lectores', u'http://www.rionegro.com.ar/diario/funciones/xml/rss.aspx?idcat=9538'),
(u'Columnistas', u'http://www.rionegro.com.ar/diario/funciones/xml/rss.aspx?idcat=9539'),
(u'Domingo a Domingo', u'http://www.rionegro.com.ar/diario/funciones/xml/rss.aspx?idcat=9541'),
(u'Editorial', u'http://www.rionegro.com.ar/diario/funciones/xml/rss.aspx?idcat=9542'),
(u'Deportes', u'http://www.rionegro.com.ar/diario/funciones/xml/rss.aspx?idcat=9522'),
(u'Espectaculos', u'http://www.rionegro.com.ar/diario/funciones/xml/rss.aspx?idcat=9523'),
(u'Sociedad', u'http://www.rionegro.com.ar/diario/funciones/xml/rss.aspx?idcat=9574'),
(u'Policiales', u'http://www.rionegro.com.ar/diario/funciones/xml/rss.aspx?idcat=9525'),
(u'Municipales', u'http://www.rionegro.com.ar/diario/funciones/xml/rss.aspx?idcat=9862'),
(u'Region', u'http://www.rionegro.com.ar/diario/funciones/xml/rss.aspx?idcat=9701')
]
def print_version(self, url):
idart_raw = url.rpartition('idart=')[2]
idart = idart_raw.rpartition('&')[0]
return 'http://www.rionegro.com.ar/diario/rn/print.aspx?idArt=' + idart + '&tipo=2'