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

Perform PEP8 compliance checks on the entire codebase

Browse Source 
Some bits of PEP 8 are turned off via setup.cfg
This commit is contained in:
Kovid Goyal 2016-07-29 11:04:04 +05:30
parent 643977ffa6
commit 567040ee1e
1881 changed files with 49336 additions and 46525 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
recipes/10minutos.recipe
View File

@ -1,16 +1,16 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
## ##
## Title: Diario 10minutos.com.uy News and Sports Calibre Recipe # Title: Diario 10minutos.com.uy News and Sports Calibre Recipe
## Contact: Carlos Alves - <carlos@carlosalves.info> # Contact: Carlos Alves - <carlos@carlosalves.info>
## ##
## License: GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html # License: GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html
## Copyright: Carlos Alves - <carlos@carlosalves.info> # Copyright: Carlos Alves - <carlos@carlosalves.info>
## ##
## Written: September 2013 # Written: September 2013
## Last Edited: 2016-01-11 # Last Edited: 2016-01-11
## ##
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = '2016, Carlos Alves <carlos@carlosalves.info>' __author__ = '2016, Carlos Alves <carlos@carlosalves.info>'
''' '''
10minutos.com.uy 10minutos.com.uy
@ -18,29 +18,30 @@ __author__ = '2016, Carlos Alves <carlos@carlosalves.info>'
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class General(BasicNewsRecipe): class General(BasicNewsRecipe):
title = '10minutos' title = '10minutos'
__author__ = 'Carlos Alves' __author__ = 'Carlos Alves'
description = 'Noticias de Salto - Uruguay' description = 'Noticias de Salto - Uruguay'
tags = 'news, sports' tags = 'news, sports'
language = 'es_UY' language = 'es_UY'
timefmt = '[%a, %d %b, %Y]' timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False use_embedded_content = False
recursion = 5 recursion = 5
encoding = 'utf8' encoding = 'utf8'
remove_javascript = True remove_javascript = True
no_stylesheets = True no_stylesheets = True
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
keep_only_tags = [dict(name='div', attrs={'class':'post-content'})] keep_only_tags = [dict(name='div', attrs={'class': 'post-content'})]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class':['hr', 'titlebar', 'navigation']}), dict(name='div', attrs={'class': ['hr', 'titlebar', 'navigation']}),
dict(name='div', attrs={'class':'sharedaddy sd-sharing-enabled'}), dict(name='div', attrs={'class': 'sharedaddy sd-sharing-enabled'}),
dict(name='p', attrs={'class':'post-meta'}), dict(name='p', attrs={'class': 'post-meta'}),
dict(name=['object','link']) dict(name=['object', 'link'])
] ]
extra_css = ''' extra_css = '''
h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;} h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
@ -49,8 +50,8 @@ class General(BasicNewsRecipe):
p {font-family:Arial,Helvetica,sans-serif;} p {font-family:Arial,Helvetica,sans-serif;}
''' '''
feeds = [ feeds = [
(u'Articulos', u'http://10minutos.com.uy/?feed=rss2') (u'Articulos', u'http://10minutos.com.uy/?feed=rss2')
] ]
def get_cover_url(self): def get_cover_url(self):
return 'http://10minutos.com.uy/a/img/logo.png' return 'http://10minutos.com.uy/a/img/logo.png'

45
recipes/180.recipe
View File

@ -1,9 +1,9 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
## ##
## Last Edited: 2016-01-11 Carlos Alves <carlos@carlosalves.info> # Last Edited: 2016-01-11 Carlos Alves <carlos@carlosalves.info>
## ##
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>' __author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
''' '''
180.com.uy 180.com.uy
@ -11,31 +11,32 @@ __author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Noticias(BasicNewsRecipe): class Noticias(BasicNewsRecipe):
title = '180.com.uy' title = '180.com.uy'
__author__ = 'Gustavo Azambuja' __author__ = 'Gustavo Azambuja'
description = 'Noticias de Uruguay' description = 'Noticias de Uruguay'
language = 'es_UY' language = 'es_UY'
timefmt = '[%a, %d %b, %Y]' timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False use_embedded_content = False
recursion = 5 recursion = 5
encoding = 'utf-8' encoding = 'utf-8'
remove_javascript = True remove_javascript = True
no_stylesheets = True no_stylesheets = True
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
remove_tags_after = dict(name='article') remove_tags_after = dict(name='article')
keep_only_tags = [ keep_only_tags = [
dict(name='h3', attrs={'class':'title'}), dict(name='h3', attrs={'class': 'title'}),
dict(name='div', attrs={'class':'copete'}), dict(name='div', attrs={'class': 'copete'}),
dict(name='article', attrs={'class':'texto'}) dict(name='article', attrs={'class': 'texto'})
] ]
remove_tags = [ remove_tags = [
dict(name=['object','link']) dict(name=['object', 'link'])
] ]
remove_attributes = ['width','height', 'style', 'font', 'color'] remove_attributes = ['width', 'height', 'style', 'font', 'color']
extra_css = ''' extra_css = '''
h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;} h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
@ -44,15 +45,13 @@ class Noticias(BasicNewsRecipe):
p {font-family:Arial,Helvetica,sans-serif;} p {font-family:Arial,Helvetica,sans-serif;}
''' '''
feeds = [ feeds = [
(u'Titulares', u'http://www.180.com.uy/feed.php') (u'Titulares', u'http://www.180.com.uy/feed.php')
] ]
def get_cover_url(self): def get_cover_url(self):
pass pass
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
return soup return soup

5
recipes/1843.recipe
View File

@ -22,7 +22,7 @@ class E1843(BasicNewsRecipe):
encoding = 'utf-8' encoding = 'utf-8'
keep_only_tags = [ keep_only_tags = [
dict(name='h1', attrs={'class':'title'}), dict(name='h1', attrs={'class': 'title'}),
classes('field-name-field-rubric-summary article-header__overlay-main-image meta-info__author article__body'), classes('field-name-field-rubric-summary article-header__overlay-main-image meta-info__author article__body'),
] ]
@ -54,7 +54,8 @@ class E1843(BasicNewsRecipe):
r = div.find(**classes('article-rubric')) r = div.find(**classes('article-rubric'))
if r is not None: if r is not None:
desc = self.tag_to_string(r) desc = self.tag_to_string(r)
articles.append({'title':title, 'url':url, 'description':desc}) articles.append(
{'title': title, 'url': url, 'description': desc})
if current_section and articles: if current_section and articles:
ans.append((current_section, articles)) ans.append((current_section, articles))

93
recipes/20_minutos.recipe
View File

@ -1,8 +1,8 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'Luis Hernandez' __author__ = 'Luis Hernandez'
__copyright__ = 'Luis Hernandez<tolyluis@gmail.com>' __copyright__ = 'Luis Hernandez<tolyluis@gmail.com>'
__version__ = 'v0.85' __version__ = 'v0.85'
__date__ = '31 January 2011' __date__ = '31 January 2011'
''' '''
www.20minutos.es www.20minutos.es
@ -10,46 +10,39 @@ www.20minutos.es
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1294946868(BasicNewsRecipe): class AdvancedUserRecipe1294946868(BasicNewsRecipe):
title = u'20 Minutos new' title = u'20 Minutos new'
publisher = u'Grupo 20 Minutos' publisher = u'Grupo 20 Minutos'
__author__ = 'Luis Hernandez' __author__ = 'Luis Hernandez'
description = 'Free spanish newspaper' description = 'Free spanish newspaper'
cover_url = 'http://estaticos.20minutos.es/mmedia/especiales/corporativo/css/img/logotipos_grupo20minutos.gif' cover_url = 'http://estaticos.20minutos.es/mmedia/especiales/corporativo/css/img/logotipos_grupo20minutos.gif'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
remove_javascript = True remove_javascript = True
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
encoding = 'ISO-8859-1' encoding = 'ISO-8859-1'
language = 'es' language = 'es'
timefmt = '[%a, %d %b, %Y]' timefmt = '[%a, %d %b, %Y]'
remove_empty_feeds = True remove_empty_feeds = True
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'id':['content','vinetas',]}) dict(name='div', attrs={'id': ['content', 'vinetas', ]}), dict(name='div', attrs={'class': ['boxed', 'description', 'lead', 'article-content', 'cuerpo estirar']}), dict(name='span', attrs={'class': ['photo-bar']}), dict(name='ul', attrs={'class': ['article-author']}) # noqa
,dict(name='div', attrs={'class':['boxed','description','lead','article-content','cuerpo estirar']}) ]
,dict(name='span', attrs={'class':['photo-bar']})
,dict(name='ul', attrs={'class':['article-author']})
]
remove_tags_before = dict(name='ul' , attrs={'class':['servicios-sub']}) remove_tags_before = dict(name='ul', attrs={'class': ['servicios-sub']})
remove_tags_after = dict(name='div' , attrs={'class':['related-news','col']}) remove_tags_after = dict(
name='div', attrs={'class': ['related-news', 'col']})
remove_tags = [ remove_tags = [
dict(name='ol', attrs={'class':['navigation',]}) dict(name='ol', attrs={'class': ['navigation', ]}), dict(name='span', attrs={'class': ['action']}), dict(name='div', attrs={'class': ['twitter comments-list hidden', 'related-news', 'col', 'photo-gallery', 'photo-gallery side-art-block', 'calendario', 'article-comment', 'postto estirar', 'otras_vinetas estirar', 'kment', 'user-actions']}), dict( name='div', attrs={'id': ['twitter-destacados', 'eco-tabs', 'inner', 'vineta_calendario', 'vinetistas clearfix', 'otras_vinetas estirar', 'MIN1', 'main', 'SUP1', 'INT']}), dict(name='ul', attrs={'class': ['article-user-actions', 'stripped-list']}), dict(name='ul', attrs={'id': ['site-links']}), dict(name='li', attrs={'class': ['puntuacion', 'enviar', 'compartir']}) # noqa
,dict(name='span', attrs={'class':['action']}) ]
,dict(name='div', attrs={'class':['twitter comments-list hidden','related-news','col','photo-gallery','photo-gallery side-art-block','calendario','article-comment','postto estirar','otras_vinetas estirar','kment','user-actions']})
,dict(name='div', attrs={'id':['twitter-destacados','eco-tabs','inner','vineta_calendario','vinetistas clearfix','otras_vinetas estirar','MIN1','main','SUP1','INT']})
,dict(name='ul', attrs={'class':['article-user-actions','stripped-list']})
,dict(name='ul', attrs={'id':['site-links']})
,dict(name='li', attrs={'class':['puntuacion','enviar','compartir']})
]
extra_css = """ extra_css = """
p{text-align: justify; font-size: 100%} p{text-align: justify; font-size: 100%}
@ -57,23 +50,25 @@ class AdvancedUserRecipe1294946868(BasicNewsRecipe):
h3{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; } h3{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; }
""" """
preprocess_regexps = [(re.compile(r'<a href="http://estaticos.*?[0-999]px;" target="_blank">', re.DOTALL), lambda m: '')] preprocess_regexps = [(re.compile(
r'<a href="http://estaticos.*?[0-999]px;" target="_blank">', re.DOTALL), lambda m: '')]
feeds = [ feeds = [
(u'Portada' , u'http://www.20minutos.es/rss/')
,(u'Nacional' , u'http://www.20minutos.es/rss/nacional/') (u'Portada', u'http://www.20minutos.es/rss/'),
,(u'Internacional' , u'http://www.20minutos.es/rss/internacional/') (u'Nacional', u'http://www.20minutos.es/rss/nacional/'),
,(u'Economia' , u'http://www.20minutos.es/rss/economia/') (u'Internacional', u'http://www.20minutos.es/rss/internacional/'),
,(u'Deportes' , u'http://www.20minutos.es/rss/deportes/') (u'Economia', u'http://www.20minutos.es/rss/economia/'),
,(u'Tecnologia' , u'http://www.20minutos.es/rss/tecnologia/') (u'Deportes', u'http://www.20minutos.es/rss/deportes/'),
,(u'Gente - TV' , u'http://www.20minutos.es/rss/gente-television/') (u'Tecnologia', u'http://www.20minutos.es/rss/tecnologia/'),
,(u'Motor' , u'http://www.20minutos.es/rss/motor/') (u'Gente - TV', u'http://www.20minutos.es/rss/gente-television/'),
,(u'Salud' , u'http://www.20minutos.es/rss/belleza-y-salud/') (u'Motor', u'http://www.20minutos.es/rss/motor/'),
,(u'Viajes' , u'http://www.20minutos.es/rss/viajes/') (u'Salud', u'http://www.20minutos.es/rss/belleza-y-salud/'),
,(u'Vivienda' , u'http://www.20minutos.es/rss/vivienda/') (u'Viajes', u'http://www.20minutos.es/rss/viajes/'),
,(u'Empleo' , u'http://www.20minutos.es/rss/empleo/') (u'Vivienda', u'http://www.20minutos.es/rss/vivienda/'),
,(u'Cine' , u'http://www.20minutos.es/rss/cine/') (u'Empleo', u'http://www.20minutos.es/rss/empleo/'),
,(u'Musica' , u'http://www.20minutos.es/rss/musica/') (u'Cine', u'http://www.20minutos.es/rss/cine/'),
,(u'Vinetas' , u'http://www.20minutos.es/rss/vinetas/') (u'Musica', u'http://www.20minutos.es/rss/musica/'),
,(u'Comunidad20' , u'http://www.20minutos.es/rss/zona20/') (u'Vinetas', u'http://www.20minutos.es/rss/vinetas/'),
] (u'Comunidad20', u'http://www.20minutos.es/rss/zona20/')
]

31
recipes/20minutes.recipe
View File

@ -1,33 +1,34 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2011 Aurélien Chabot <contact@aurelienchabot.fr>' __copyright__ = '2011 Aurélien Chabot <contact@aurelienchabot.fr>'
''' '''
20minutes.fr 20minutes.fr
''' '''
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class Minutes(BasicNewsRecipe): class Minutes(BasicNewsRecipe):
title = '20 minutes' title = '20 minutes'
__author__ = u'Aurélien Chabot' __author__ = u'Aurélien Chabot'
description = 'Actualités' description = 'Actualités'
encoding = 'utf-8' encoding = 'utf-8'
publisher = '20minutes.fr' publisher = '20minutes.fr'
category = 'Actualités, France, Monde' category = 'Actualités, France, Monde'
language = 'fr' language = 'fr'
use_embedded_content = False use_embedded_content = False
timefmt = ' [%d %b %Y]' timefmt = ' [%d %b %Y]'
max_articles_per_feed = 15 max_articles_per_feed = 15
no_stylesheets = True no_stylesheets = True
remove_empty_feeds = True remove_empty_feeds = True
keep_only_tags = [ keep_only_tags = [
dict(name='h1'), dict(name='h1'),
dict(attrs={'class':lambda x: x and 'lt-content' in x.split()}), dict(attrs={'class': lambda x: x and 'lt-content' in x.split()}),
] ]
remove_tags = [ remove_tags = [
dict(attrs={'class':lambda x:x and 'content-related' in x.split()}), dict(attrs={'class': lambda x: x and 'content-related' in x.split()}),
] ]
remove_tags_after = dict(id='ob_holder') remove_tags_after = dict(id='ob_holder')

78
recipes/20minutos.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
''' '''
www.20minutos.es www.20minutos.es
@ -6,45 +6,44 @@ www.20minutos.es
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class t20Minutos(BasicNewsRecipe): class t20Minutos(BasicNewsRecipe):
title = '20 Minutos' title = '20 Minutos'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Diario de informacion general y local mas leido de Espania, noticias de ultima hora de Espania, el mundo, local, deportes, noticias curiosas y mas' description = 'Diario de informacion general y local mas leido de Espania, noticias de ultima hora de Espania, el mundo, local, deportes, noticias curiosas y mas' # noqa
publisher = '20 Minutos Online SL' publisher = '20 Minutos Online SL'
category = 'news, politics, Spain' category = 'news, politics, Spain'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 200 max_articles_per_feed = 200
no_stylesheets = True no_stylesheets = True
encoding = 'utf8' encoding = 'utf8'
use_embedded_content = True use_embedded_content = True
language = 'es' language = 'es'
remove_empty_feeds = True remove_empty_feeds = True
publication_type = 'newspaper' publication_type = 'newspaper'
masthead_url = 'http://estaticos.20minutos.es/css4/img/ui/logo-301x54.png' masthead_url = 'http://estaticos.20minutos.es/css4/img/ui/logo-301x54.png'
extra_css = """ extra_css = """
body{font-family: Arial,Helvetica,sans-serif } body{font-family: Arial,Helvetica,sans-serif }
img{margin-bottom: 0.4em; display:block} img{margin-bottom: 0.4em; display:block}
""" """
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
}
remove_tags = [dict(attrs={'class':'mf-viral'})] remove_tags = [dict(attrs={'class': 'mf-viral'})]
remove_attributes=['border'] remove_attributes = ['border']
feeds = [ feeds = [
(u'Principal' , u'http://20minutos.feedsportal.com/c/32489/f/478284/index.rss')
,(u'Cine' , u'http://20minutos.feedsportal.com/c/32489/f/478285/index.rss') (u'Principal', u'http://20minutos.feedsportal.com/c/32489/f/478284/index.rss'),
,(u'Internacional' , u'http://20minutos.feedsportal.com/c/32489/f/492689/index.rss') (u'Cine', u'http://20minutos.feedsportal.com/c/32489/f/478285/index.rss'),
,(u'Deportes' , u'http://20minutos.feedsportal.com/c/32489/f/478286/index.rss') (u'Internacional', u'http://20minutos.feedsportal.com/c/32489/f/492689/index.rss'),
,(u'Nacional' , u'http://20minutos.feedsportal.com/c/32489/f/492688/index.rss') (u'Deportes', u'http://20minutos.feedsportal.com/c/32489/f/478286/index.rss'),
,(u'Economia' , u'http://20minutos.feedsportal.com/c/32489/f/492690/index.rss') (u'Nacional', u'http://20minutos.feedsportal.com/c/32489/f/492688/index.rss'),
,(u'Tecnologia' , u'http://20minutos.feedsportal.com/c/32489/f/478292/index.rss') (u'Economia', u'http://20minutos.feedsportal.com/c/32489/f/492690/index.rss'),
] (u'Tecnologia', u'http://20minutos.feedsportal.com/c/32489/f/478292/index.rss')
]
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
@ -52,17 +51,16 @@ class t20Minutos(BasicNewsRecipe):
for item in soup.findAll('a'): for item in soup.findAll('a'):
limg = item.find('img') limg = item.find('img')
if item.string is not None: if item.string is not None:
str = item.string str = item.string
item.replaceWith(str) item.replaceWith(str)
else: else:
if limg: if limg:
item.name = 'div' item.name = 'div'
item.attrs = [] item.attrs = []
else: else:
str = self.tag_to_string(item) str = self.tag_to_string(item)
item.replaceWith(str) item.replaceWith(str)
for item in soup.findAll('img'): for item in soup.findAll('img'):
if not item.has_key('alt'): if not item.has_key('alt'): # noqa
item['alt'] = 'image' item['alt'] = 'image'
return soup return soup

57
recipes/24sata.recipe
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
''' '''
@ -11,51 +11,50 @@ import re
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag from calibre.ebooks.BeautifulSoup import Tag
class Cro24Sata(BasicNewsRecipe): class Cro24Sata(BasicNewsRecipe):
title = '24 Sata - Hr' title = '24 Sata - Hr'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = "News Portal from Croatia" description = "News Portal from Croatia"
publisher = '24sata.hr' publisher = '24sata.hr'
category = 'news, politics, Croatia' category = 'news, politics, Croatia'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
delay = 4 delay = 4
no_stylesheets = True no_stylesheets = True
encoding = 'utf-8' encoding = 'utf-8'
use_embedded_content = False use_embedded_content = False
language = 'hr' language = 'hr'
lang = 'hr-HR' lang = 'hr-HR'
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: serif1, serif}' extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: serif1, serif}' # noqa
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': lang, 'pretty_print': True
, 'tags' : category }
, 'publisher' : publisher
, 'language' : lang
, 'pretty_print' : True
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
remove_tags = [ remove_tags = [
dict(name=['object','link','embed']) dict(name=['object', 'link', 'embed']), dict(
,dict(name='table', attrs={'class':'enumbox'}) name='table', attrs={'class': 'enumbox'})
] ]
feeds = [(u'Najnovije Vijesti', u'http://www.24sata.hr/index.php?cmd=show_rss&action=novo')] feeds = [(u'Najnovije Vijesti',
u'http://www.24sata.hr/index.php?cmd=show_rss&action=novo')]
def preprocess_html(self, soup): def preprocess_html(self, soup):
soup.html['lang'] = self.lang soup.html['lang'] = self.lang
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)]) mlang = Tag(soup, 'meta', [
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=UTF-8")]) ("http-equiv", "Content-Language"), ("content", self.lang)])
soup.head.insert(0,mlang) mcharset = Tag(soup, 'meta', [
soup.head.insert(1,mcharset) ("http-equiv", "Content-Type"), ("content", "text/html; charset=UTF-8")])
soup.head.insert(0, mlang)
soup.head.insert(1, mcharset)
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
return soup return soup
def print_version(self, url): def print_version(self, url):
return url + '&action=ispis' return url + '&action=ispis'

44
recipes/24sata_rs.recipe
View File

@ -1,6 +1,6 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009-2012, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2009-2012, Darko Miletic <darko.miletic at gmail.com>'
''' '''
@ -10,40 +10,38 @@ __copyright__ = '2009-2012, Darko Miletic <darko.miletic at gmail.com>'
import re import re
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class Ser24Sata(BasicNewsRecipe): class Ser24Sata(BasicNewsRecipe):
title = '24 Sata - Sr' title = '24 Sata - Sr'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = '24 sata portal vesti iz Srbije' description = '24 sata portal vesti iz Srbije'
publisher = 'Ringier d.o.o.' publisher = 'Ringier d.o.o.'
category = 'news, politics, entertainment, Serbia' category = 'news, politics, entertainment, Serbia'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
encoding = 'utf-8' encoding = 'utf-8'
use_embedded_content = False use_embedded_content = False
language = 'sr' language = 'sr'
publication_type = 'newsportal' publication_type = 'newsportal'
extra_css = """ extra_css = """
@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
body{font-family: serif1, serif} body{font-family: serif1, serif}
""" """
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher': publisher
, 'language' : language
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
feeds = [ feeds = [
(u'Vesti' , u'http://www.24sata.rs/rss/vesti.xml' ), (u'Vesti', u'http://www.24sata.rs/rss/vesti.xml'),
(u'Sport' , u'http://www.24sata.rs/rss/sport.xml' ), (u'Sport', u'http://www.24sata.rs/rss/sport.xml'),
(u'Šou' , u'http://www.24sata.rs/rss/sou.xml' ), (u'Šou', u'http://www.24sata.rs/rss/sou.xml'),
(u'Specijal', u'http://www.24sata.rs/rss/specijal.xml'), (u'Specijal', u'http://www.24sata.rs/rss/specijal.xml'),
(u'Novi Sad', u'http://www.24sata.rs/rss/ns.xml' ) (u'Novi Sad', u'http://www.24sata.rs/rss/ns.xml')
] ]
def print_version(self, url): def print_version(self, url):
dpart, spart, apart = url.rpartition('/') dpart, spart, apart = url.rpartition('/')

69
recipes/3dnews.recipe
View File

@ -3,44 +3,63 @@
from __future__ import unicode_literals, division, absolute_import, print_function from __future__ import unicode_literals, division, absolute_import, print_function
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1438446837(BasicNewsRecipe): class AdvancedUserRecipe1438446837(BasicNewsRecipe):
title = '3DNews: Daily Digital Digest' title = '3DNews: Daily Digital Digest'
__author__ = 'bugmen00t' __author__ = 'bugmen00t'
description = 'Независимое российское онлайн-издание, посвященное цифровым технологиям' description = 'Независимое российское онлайн-издание, посвященное цифровым технологиям'
publisher = '3DNews' publisher = '3DNews'
category = 'news' category = 'news'
cover_url = u'http://www.3dnews.ru/assets/images/logo.png' cover_url = u'http://www.3dnews.ru/assets/images/logo.png'
language = 'ru' language = 'ru'
auto_cleanup = True auto_cleanup = True
oldest_article = 15 oldest_article = 15
max_articles_per_feed = 60 max_articles_per_feed = 60
feeds = [ feeds = [
('\u041d\u043e\u0432\u043e\u0441\u0442\u0438 Hardware', 'http://www.3dnews.ru/news/rss/'), ('\u041d\u043e\u0432\u043e\u0441\u0442\u0438 Hardware',
('\u041d\u043e\u0432\u043e\u0441\u0442\u0438 Software', 'http://www.3dnews.ru/software-news/rss/'), 'http://www.3dnews.ru/news/rss/'),
('\u0423\u043c\u043d\u044b\u0435 \u0432\u0435\u0449\u0438', 'http://www.3dnews.ru/smart-things/rss/'), ('\u041d\u043e\u0432\u043e\u0441\u0442\u0438 Software',
('\u0410\u043d\u0430\u043b\u0438\u0442\u0438\u043a\u0430', 'http://www.3dnews.ru/editorial/rss/'), 'http://www.3dnews.ru/software-news/rss/'),
('\u041f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u044b \u0438 \u043f\u0430\u043c\u044f\u0442\u044c', 'http://www.3dnews.ru/cpu/rss/'), ('\u0423\u043c\u043d\u044b\u0435 \u0432\u0435\u0449\u0438',
('\u041c\u0430\u0442\u0435\u0440\u0438\u043d\u0441\u043a\u0438\u0435 \u043f\u043b\u0430\u0442\u044b', 'http://www.3dnews.ru/motherboard/rss/'), 'http://www.3dnews.ru/smart-things/rss/'),
('\u0410\u043d\u0430\u043b\u0438\u0442\u0438\u043a\u0430',
'http://www.3dnews.ru/editorial/rss/'),
('\u041f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u044b \u0438 \u043f\u0430\u043c\u044f\u0442\u044c',
'http://www.3dnews.ru/cpu/rss/'),
('\u041c\u0430\u0442\u0435\u0440\u0438\u043d\u0441\u043a\u0438\u0435 \u043f\u043b\u0430\u0442\u044b',
'http://www.3dnews.ru/motherboard/rss/'),
('\u041a\u043e\u0440\u043f\u0443\u0441\u0430, \u0411\u041f \u0438 \u043e\u0445\u043b\u0430\u0436\u0434\u0435\u043d\u0438\u0435', ('\u041a\u043e\u0440\u043f\u0443\u0441\u0430, \u0411\u041f \u0438 \u043e\u0445\u043b\u0430\u0436\u0434\u0435\u043d\u0438\u0435',
'http://www.3dnews.ru/cooling/rss/'), 'http://www.3dnews.ru/cooling/rss/'),
('\u0412\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b', 'http://www.3dnews.ru/video/rss/'), ('\u0412\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b',
('\u041c\u043e\u043d\u0438\u0442\u043e\u0440\u044b \u0438 \u043f\u0440\u043e\u0435\u043a\u0442\u043e\u0440\u044b', 'http://www.3dnews.ru/display/rss/'), 'http://www.3dnews.ru/video/rss/'),
('\u041d\u0430\u043a\u043e\u043f\u0438\u0442\u0435\u043b\u0438', 'http://www.3dnews.ru/storage/rss/'), ('\u041c\u043e\u043d\u0438\u0442\u043e\u0440\u044b \u0438 \u043f\u0440\u043e\u0435\u043a\u0442\u043e\u0440\u044b',
('\u0426\u0438\u0444\u0440\u043e\u0432\u043e\u0439 \u0430\u0432\u0442\u043e\u043c\u043e\u0431\u0438\u043b\u044c', 'http://www.3dnews.ru/auto/rss/'), 'http://www.3dnews.ru/display/rss/'),
('\u0421\u043e\u0442\u043e\u0432\u0430\u044f \u0441\u0432\u044f\u0437\u044c', 'http://www.3dnews.ru/phone/rss/'), ('\u041d\u0430\u043a\u043e\u043f\u0438\u0442\u0435\u043b\u0438',
('\u041f\u0435\u0440\u0438\u0444\u0435\u0440\u0438\u044f', 'http://www.3dnews.ru/peripheral/rss/'), 'http://www.3dnews.ru/storage/rss/'),
('\u041d\u043e\u0443\u0442\u0431\u0443\u043a\u0438 \u0438 \u041f\u041a', 'http://www.3dnews.ru/mobile/rss/'), ('\u0426\u0438\u0444\u0440\u043e\u0432\u043e\u0439 \u0430\u0432\u0442\u043e\u043c\u043e\u0431\u0438\u043b\u044c',
('\u041f\u043b\u0430\u043d\u0448\u0435\u0442\u044b', 'http://www.3dnews.ru/tablets/rss/'), 'http://www.3dnews.ru/auto/rss/'),
('\u0417\u0432\u0443\u043a \u0438 \u0430\u043a\u0443\u0441\u0442\u0438\u043a\u0430', 'http://www.3dnews.ru/multimedia/rss/'), ('\u0421\u043e\u0442\u043e\u0432\u0430\u044f \u0441\u0432\u044f\u0437\u044c',
'http://www.3dnews.ru/phone/rss/'),
('\u041f\u0435\u0440\u0438\u0444\u0435\u0440\u0438\u044f',
'http://www.3dnews.ru/peripheral/rss/'),
('\u041d\u043e\u0443\u0442\u0431\u0443\u043a\u0438 \u0438 \u041f\u041a',
'http://www.3dnews.ru/mobile/rss/'),
('\u041f\u043b\u0430\u043d\u0448\u0435\u0442\u044b',
'http://www.3dnews.ru/tablets/rss/'),
('\u0417\u0432\u0443\u043a \u0438 \u0430\u043a\u0443\u0441\u0442\u0438\u043a\u0430',
'http://www.3dnews.ru/multimedia/rss/'),
('\u0426\u0438\u0444\u0440\u043e\u0432\u043e\u0435 \u0444\u043e\u0442\u043e \u0438 \u0432\u0438\u0434\u0435\u043e', ('\u0426\u0438\u0444\u0440\u043e\u0432\u043e\u0435 \u0444\u043e\u0442\u043e \u0438 \u0432\u0438\u0434\u0435\u043e',
'http://www.3dnews.ru/digital/rss/'), 'http://www.3dnews.ru/digital/rss/'),
('\u0421\u0435\u0442\u0438 \u0438 \u043a\u043e\u043c\u043c\u0443\u043d\u0438\u043a\u0430\u0446\u0438\u0438', 'http://www.3dnews.ru/communication/rss/'), ('\u0421\u0435\u0442\u0438 \u0438 \u043a\u043e\u043c\u043c\u0443\u043d\u0438\u043a\u0430\u0446\u0438\u0438',
'http://www.3dnews.ru/communication/rss/'),
('\u0418\u0433\u0440\u044b', 'http://www.3dnews.ru/games/rss/'), ('\u0418\u0433\u0440\u044b', 'http://www.3dnews.ru/games/rss/'),
('\u041f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u043d\u043e\u0435 \u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0435\u043d\u0438\u0435', ('\u041f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u043d\u043e\u0435 \u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0435\u043d\u0438\u0435',
'http://www.3dnews.ru/software/rss/'), 'http://www.3dnews.ru/software/rss/'),
('Off-\u0441\u044f\u043d\u043a\u0430', 'http://www.3dnews.ru/offsyanka/rss/'), ('Off-\u0441\u044f\u043d\u043a\u0430',
('\u041c\u0430\u0441\u0442\u0435\u0440\u0441\u043a\u0430\u044f', 'http://www.3dnews.ru/workshop/rss/'), 'http://www.3dnews.ru/offsyanka/rss/'),
('\u041c\u0430\u0441\u0442\u0435\u0440\u0441\u043a\u0430\u044f',
'http://www.3dnews.ru/workshop/rss/'),
('ServerNews', 'http://servernews.ru/rss'), ('ServerNews', 'http://servernews.ru/rss'),
] ]

58
recipes/7dias.recipe
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
''' '''
elargentino.com elargentino.com
@ -9,33 +9,26 @@ elargentino.com
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag from calibre.ebooks.BeautifulSoup import Tag
class SieteDias(BasicNewsRecipe): class SieteDias(BasicNewsRecipe):
title = '7 dias' title = '7 dias'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Revista Argentina' description = 'Revista Argentina'
publisher = 'ElArgentino.com' publisher = 'ElArgentino.com'
category = 'news, politics, show, Argentina' category = 'news, politics, show, Argentina'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
encoding = 'utf-8' encoding = 'utf-8'
language = 'es_AR' language = 'es_AR'
lang = 'es-AR' lang = 'es-AR'
direction = 'ltr' direction = 'ltr'
INDEX = 'http://www.elargentino.com/medios/125/7-Dias.html' 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} ' extra_css = ' .titulo{font-size: x-large; font-weight: bold} .volantaImp{font-size: small; font-weight: bold} '
html2lrf_options = [ keep_only_tags = [dict(name='div', attrs={'class': 'ContainerPop'})]
'--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')] remove_tags = [dict(name='link')]
@ -50,20 +43,23 @@ class SieteDias(BasicNewsRecipe):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
soup.html['lang'] = self.lang soup.html['lang'] = self.lang
soup.html['dir' ] = self.direction soup.html['dir'] = self.direction
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)]) mlang = Tag(soup, 'meta', [
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")]) ("http-equiv", "Content-Language"), ("content", self.lang)])
soup.head.insert(0,mlang) mcharset = Tag(soup, 'meta', [
soup.head.insert(1,mcharset) ("http-equiv", "Content-Type"), ("content", "text/html; charset=utf-8")])
soup.head.insert(0, mlang)
soup.head.insert(1, mcharset)
return soup return soup
def get_cover_url(self): def get_cover_url(self):
cover_url = None cover_url = None
soup = self.index_to_soup(self.INDEX) soup = self.index_to_soup(self.INDEX)
cover_item = soup.find('div',attrs={'class':'colder'}) cover_item = soup.find('div', attrs={'class': 'colder'})
if cover_item: if cover_item:
clean_url = self.image_url_processor(None,cover_item.div.img['src']) clean_url = self.image_url_processor(
cover_url = 'http://www.elargentino.com' + clean_url + '&height=600' None, cover_item.div.img['src'])
cover_url = 'http://www.elargentino.com' + clean_url + '&height=600'
return cover_url return cover_url
def image_url_processor(self, baseurl, url): def image_url_processor(self, baseurl, url):

55
recipes/7seri.recipe
View File

@ -1,7 +1,7 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103' __copyright__ = u'2011, Silviu Cotoar\u0103'
''' '''
sapteseri.ro sapteseri.ro
@ -9,43 +9,40 @@ sapteseri.ro
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class SapteSeri(BasicNewsRecipe): class SapteSeri(BasicNewsRecipe):
title = u'Sapte Seri' title = u'Sapte Seri'
__author__ = u'Silviu Cotoar\u0103' __author__ = u'Silviu Cotoar\u0103'
description = u'Sapte Seri' description = u'Sapte Seri'
publisher = u'Sapte Seri' publisher = u'Sapte Seri'
oldest_article = 5 oldest_article = 5
language = 'ro' language = 'ro'
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
category = 'Ziare,Oras,Distractie,Fun' category = 'Ziare,Oras,Distractie,Fun'
encoding = 'utf-8' encoding = 'utf-8'
remove_empty_feeds = True remove_empty_feeds = True
remove_javascript = True remove_javascript = True
cover_url = 'http://www.sapteseri.ro/Images/logo.jpg' cover_url = 'http://www.sapteseri.ro/Images/logo.jpg'
conversion_options = { conversion_options = {
'comments' : description 'comments': description, 'tags': category, 'language': language, 'publisher': publisher
,'tags' : category }
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [ keep_only_tags = [
dict(name='h1', attrs={'id':'title'}) dict(name='h1', attrs={'id': 'title'}), dict(name='div', attrs={'class': 'mt10 mb10'}), dict(
, dict(name='div', attrs={'class':'mt10 mb10'}) name='div', attrs={'class': 'mb20 mt10'}), dict(name='div', attrs={'class': 'mt5 mb20'})
, dict(name='div', attrs={'class':'mb20 mt10'}) ]
, dict(name='div', attrs={'class':'mt5 mb20'})
]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'id':['entityimgworking']}) dict(name='div', attrs={'id': ['entityimgworking']})
] ]
feeds = [ feeds = [
(u'Ce se intampla azi in Bucuresti', u'http://www.sapteseri.ro/ro/feed/ce-se-intampla-azi/bucuresti/') (u'Ce se intampla azi in Bucuresti',
] u'http://www.sapteseri.ro/ro/feed/ce-se-intampla-azi/bucuresti/')
]
def preprocess_html(self, soup): def preprocess_html(self, soup):
return self.adeify_images(soup) return self.adeify_images(soup)

93
recipes/Ansa.recipe
View File

@ -1,69 +1,70 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'Gabriele Marini, based on Darko Miletic' __author__ = 'Gabriele Marini, based on Darko Miletic'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
description = 'Italian daily newspaper - 01-05-2010' description = 'Italian daily newspaper - 01-05-2010'
''' '''
http://www.ansa.it/ http://www.ansa.it/
''' '''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Ansa(BasicNewsRecipe): class Ansa(BasicNewsRecipe):
__author__ = 'Gabriele Marini' __author__ = 'Gabriele Marini'
description = 'Italian News Agency' description = 'Italian News Agency'
cover_url = 'http://www.ansa.it/web/images/logo_ansa_interna.gif' cover_url = 'http://www.ansa.it/web/images/logo_ansa_interna.gif'
title = u'Ansa' title = u'Ansa'
publisher = 'Ansa' publisher = 'Ansa'
category = 'News, politics, culture, economy, general interest' category = 'News, politics, culture, economy, general interest'
language = 'it' language = 'it'
timefmt = '[%a, %d %b, %Y]' timefmt = '[%a, %d %b, %Y]'
oldest_article = 1 oldest_article = 1
max_articles_per_feed = 10 max_articles_per_feed = 10
use_embedded_content = False use_embedded_content = False
recursion = 10 recursion = 10
remove_javascript = True remove_javascript = True
no_stylesheets = True no_stylesheets = True
conversion_options = {'linearize_tables':True} conversion_options = {'linearize_tables': True}
remove_attributes = ['colspan'] remove_attributes = ['colspan']
keep_only_tags = [dict(name='div', attrs={'class':['path','header-content','corpo']}), keep_only_tags = [dict(name='div', attrs={'class': ['path', 'header-content', 'corpo']}),
]
remove_tags = [
dict(name='div', attrs={'class':'tools-bar'}),
dict(name='div', attrs={'id':['rssdiv','blocco']})
]
feeds = [
(u'HomePage', u'http://www.ansa.it/web/ansait_web_rss_homepage.xml'),
(u'Top New', u'http://www.ansa.it/web/notizie/rubriche/topnews/topnews_rss.xml'),
(u'Cronaca', u'http://www.ansa.it/web/notizie/rubriche/cronaca/cronaca_rss.xml'),
(u'Mondo', u'http://www.ansa.it/web/notizie/rubriche/mondo/mondo_rss.xml'),
(u'Economia', u'http://www.ansa.it/web/notizie/rubriche/economia/economia_rss.xml'),
(u'Politica', u'http://www.ansa.it/web/notizie/rubriche/politica/politica_rss.xml'),
(u'Scienze', u'http://www.ansa.it/web/notizie/rubriche/scienza/scienza_rss.xml'),
(u'Cinema', u'http://www.ansa.it/web/notizie/rubriche/cinema/cinema_rss.xml'),
(u'Tecnologia e Internet', u'http://www.ansa.it/web/notizie/rubriche/tecnologia/tecnologia_rss.xml'),
(u'Spettacolo', u'http://www.ansa.it/web/notizie/rubriche/spettacolo/spettacolo_rss.xml'),
(u'Cultura e Tendenze', u'http://www.ansa.it/web/notizie/rubriche/cultura/cultura_rss.xml'),
(u'Sport', u'http://www.ansa.it/web/notizie/rubriche/altrisport/altrisport_rss.xml'),
(u'Calcio', u'http://www.ansa.it/web/notizie/rubriche/calcio/calcio_rss.xml'),
(u'Lazio', u'http://www.ansa.it/web/notizie/regioni/lazio/lazio_rss.xml'),
(u'Lombardia', u'http://www.ansa.it/web/notizie/regioni/lombardia/lombardia.shtml'),
(u'Veneto', u'http://www.ansa.it/web/notizie/regioni/veneto/veneto.shtml'),
(u'Campanioa', u'http://www.ansa.it/web/notizie/regioni/campania/campania.shtml'),
(u'Sicilia', u'http://www.ansa.it/web/notizie/regioni/sicilia/sicilia.shtml'),
(u'Toscana', u'http://www.ansa.it/web/notizie/regioni/toscana/toscana.shtml'),
(u'Trentino', u'http://www.ansa.it/web/notizie/regioni/trentino/trentino.shtml')
] ]
remove_tags = [
dict(name='div', attrs={'class': 'tools-bar'}),
dict(name='div', attrs={'id': ['rssdiv', 'blocco']})
]
feeds = [
(u'HomePage', u'http://www.ansa.it/web/ansait_web_rss_homepage.xml'),
(u'Top New', u'http://www.ansa.it/web/notizie/rubriche/topnews/topnews_rss.xml'),
(u'Cronaca', u'http://www.ansa.it/web/notizie/rubriche/cronaca/cronaca_rss.xml'),
(u'Mondo', u'http://www.ansa.it/web/notizie/rubriche/mondo/mondo_rss.xml'),
(u'Economia', u'http://www.ansa.it/web/notizie/rubriche/economia/economia_rss.xml'),
(u'Politica', u'http://www.ansa.it/web/notizie/rubriche/politica/politica_rss.xml'),
(u'Scienze', u'http://www.ansa.it/web/notizie/rubriche/scienza/scienza_rss.xml'),
(u'Cinema', u'http://www.ansa.it/web/notizie/rubriche/cinema/cinema_rss.xml'),
(u'Tecnologia e Internet',
u'http://www.ansa.it/web/notizie/rubriche/tecnologia/tecnologia_rss.xml'),
(u'Spettacolo', u'http://www.ansa.it/web/notizie/rubriche/spettacolo/spettacolo_rss.xml'),
(u'Cultura e Tendenze',
u'http://www.ansa.it/web/notizie/rubriche/cultura/cultura_rss.xml'),
(u'Sport', u'http://www.ansa.it/web/notizie/rubriche/altrisport/altrisport_rss.xml'),
(u'Calcio', u'http://www.ansa.it/web/notizie/rubriche/calcio/calcio_rss.xml'),
(u'Lazio', u'http://www.ansa.it/web/notizie/regioni/lazio/lazio_rss.xml'),
(u'Lombardia', u'http://www.ansa.it/web/notizie/regioni/lombardia/lombardia.shtml'),
(u'Veneto', u'http://www.ansa.it/web/notizie/regioni/veneto/veneto.shtml'),
(u'Campanioa', u'http://www.ansa.it/web/notizie/regioni/campania/campania.shtml'),
(u'Sicilia', u'http://www.ansa.it/web/notizie/regioni/sicilia/sicilia.shtml'),
(u'Toscana', u'http://www.ansa.it/web/notizie/regioni/toscana/toscana.shtml'),
(u'Trentino', u'http://www.ansa.it/web/notizie/regioni/trentino/trentino.shtml')
]
extra_css = ''' extra_css = '''
.path{font-style: italic; font-size: small} .path{font-style: italic; font-size: small}
.header-content h1{font-weight: bold; font-size: xx-large} .header-content h1{font-weight: bold; font-size: xx-large}

54
recipes/DrawAndCook.recipe
View File

@ -1,21 +1,22 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
import re import re
class DrawAndCook(BasicNewsRecipe): class DrawAndCook(BasicNewsRecipe):
title = 'DrawAndCook' title = 'DrawAndCook'
__author__ = 'Starson17' __author__ = 'Starson17'
__version__ = 'v1.10' __version__ = 'v1.10'
__date__ = '13 March 2011' __date__ = '13 March 2011'
description = 'Drawings of recipes!' description = 'Drawings of recipes!'
language = 'en' language = 'en'
publisher = 'Starson17' publisher = 'Starson17'
category = 'news, food, recipes' category = 'news, food, recipes'
use_embedded_content= False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
oldest_article = 24 oldest_article = 24
remove_javascript = True remove_javascript = True
remove_empty_feeds = True remove_empty_feeds = True
cover_url = 'http://farm5.static.flickr.com/4043/4471139063_4dafced67f_o.jpg' cover_url = 'http://farm5.static.flickr.com/4043/4471139063_4dafced67f_o.jpg'
INDEX = 'http://www.theydrawandcook.com' INDEX = 'http://www.theydrawandcook.com'
max_articles_per_feed = 30 max_articles_per_feed = 30
@ -24,8 +25,8 @@ class DrawAndCook(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
feeds = [] feeds = []
for title, url in [ for title, url in [
("They Draw and Cook", "http://www.theydrawandcook.com/") ("They Draw and Cook", "http://www.theydrawandcook.com/")
]: ]:
articles = self.make_links(url) articles = self.make_links(url)
if articles: if articles:
feeds.append((title, articles)) feeds.append((title, articles))
@ -38,22 +39,24 @@ class DrawAndCook(BasicNewsRecipe):
date = '' date = ''
current_articles = [] current_articles = []
soup = self.index_to_soup(url) soup = self.index_to_soup(url)
featured_major_slider = soup.find(name='div', attrs={'id':'featured_major_slider'}) featured_major_slider = soup.find(
recipes = featured_major_slider.findAll('li', attrs={'data-id': re.compile(r'artwork_entry_\d+', re.DOTALL)}) name='div', attrs={'id': 'featured_major_slider'})
recipes = featured_major_slider.findAll(
'li', attrs={'data-id': re.compile(r'artwork_entry_\d+', re.DOTALL)})
for recipe in recipes: for recipe in recipes:
page_url = self.INDEX + recipe.a['href'] page_url = self.INDEX + recipe.a['href']
print 'page_url is: ', page_url print 'page_url is: ', page_url
title = recipe.find('strong').string title = recipe.find('strong').string
print 'title is: ', title print 'title is: ', title
current_articles.append({'title': title, 'url': page_url, 'description':'', 'date':date}) current_articles.append(
{'title': title, 'url': page_url, 'description': '', 'date': date})
return current_articles return current_articles
keep_only_tags = [dict(name='h1', attrs={'id':'page_title'}) keep_only_tags = [dict(name='h1', attrs={'id': 'page_title'}), dict(name='section', attrs={'id': 'artwork'})
,dict(name='section', attrs={'id':'artwork'}) ]
]
remove_tags = [dict(name='article', attrs={'id':['recipe_actions', 'metadata']}) remove_tags = [dict(name='article', attrs={'id': ['recipe_actions', 'metadata']})
] ]
extra_css = ''' extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;} h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
@ -61,5 +64,4 @@ class DrawAndCook(BasicNewsRecipe):
img {max-width:100%; min-width:100%;} img {max-width:100%; min-width:100%;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;} p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;} body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
''' '''

18
recipes/ZIVE.sk.recipe
View File

@ -2,9 +2,8 @@ from calibre.web.feeds.news import BasicNewsRecipe
import re import re
class ZiveRecipe(BasicNewsRecipe): class ZiveRecipe(BasicNewsRecipe):
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'Abelturd' __author__ = 'Abelturd'
language = 'sk' language = 'sk'
version = 1 version = 1
@ -25,21 +24,20 @@ class ZiveRecipe(BasicNewsRecipe):
cover_url = 'http://www.zive.sk/Client.Images/Logos/logo-zive-sk.gif' cover_url = 'http://www.zive.sk/Client.Images/Logos/logo-zive-sk.gif'
feeds = [] feeds = []
feeds.append((u'V\u0161etky \u010dl\xe1nky', u'http://www.zive.sk/rss/sc-47/default.aspx')) feeds.append((u'V\u0161etky \u010dl\xe1nky',
u'http://www.zive.sk/rss/sc-47/default.aspx'))
preprocess_regexps = [ preprocess_regexps = [
(re.compile(r'<p><p><strong>Pokra.*ie</strong></p>', re.DOTALL|re.IGNORECASE), (re.compile(r'<p><p><strong>Pokra.*ie</strong></p>', re.DOTALL | re.IGNORECASE),
lambda match: ''), lambda match: ''),
]
]
remove_tags = [] remove_tags = []
keep_only_tags = [dict(name='h1'), dict(name='span', attrs={'class':'arlist-data-info-author'}), dict(name='div', attrs={'class':'bbtext font-resizer-area'}),] keep_only_tags = [dict(name='h1'), dict(name='span', attrs={
'class': 'arlist-data-info-author'}), dict(name='div', attrs={'class': 'bbtext font-resizer-area'}), ]
extra_css = ''' extra_css = '''
h1 {font-size:140%;font-family:georgia,serif; font-weight:bold} h1 {font-size:140%;font-family:georgia,serif; font-weight:bold}
h3 {font-size:115%;font-family:georgia,serif; font-weight:bold} h3 {font-size:115%;font-family:georgia,serif; font-weight:bold}
''' '''

162
recipes/aachener_nachrichten.recipe
View File

@ -1,71 +1,113 @@
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe(BasicNewsRecipe): class AdvancedUserRecipe(BasicNewsRecipe):
title = u'Aachener Nachrichten' title = u'Aachener Nachrichten'
__author__ = 'schuster' #AGE update 2012-11-28 __author__ = 'schuster' # AGE update 2012-11-28
oldest_article = 1 oldest_article = 1
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
remove_empty_feeds = True remove_empty_feeds = True
language = 'de' language = 'de'
# cover_url = 'http://www.aachener-nachrichten.de/img/logos/an_website_retina.png' # cover_url = 'http://www.aachener-nachrichten.de/img/logos/an_website_retina.png'
masthead_url = 'http://www.aachener-nachrichten.de/img/logos/an_website_retina.png' masthead_url = 'http://www.aachener-nachrichten.de/img/logos/an_website_retina.png'
keep_only_tags = [ keep_only_tags = [
dict(name='article', attrs={'class':['single']}) dict(name='article', attrs={'class': ['single']})
] ]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class':["clearfix navi-wrapper"]}), dict(name='div', attrs={'class': ["clearfix navi-wrapper"]}),
dict(name='div', attrs={'id':["article_actions"]}), dict(name='div', attrs={'id': ["article_actions"]}),
dict(name='style', attrs={'type':["text/css"]}), dict(name='style', attrs={'type': ["text/css"]}),
dict(name='aside'), dict(name='aside'),
dict(name='a', attrs={'class':["btn btn-action"]}) dict(name='a', attrs={'class': ["btn btn-action"]})
] ]
feeds = [ feeds = [
(u'Lokales - Euregio', u'http://www.aachener-nachrichten.de/cmlink/euregio-rss-1.357285'), (u'Lokales - Euregio',
(u'Lokales - Aachen', u'http://www.aachener-nachrichten.de/cmlink/aachen-rss-1.357286'), u'http://www.aachener-nachrichten.de/cmlink/euregio-rss-1.357285'),
(u'Lokales - Nordkreis', u'http://www.aachener-nachrichten.de/cmlink/nordkreis-rss-1.358150'), (u'Lokales - Aachen',
(u'Lokales - Düren', u'http://www.aachener-nachrichten.de/cmlink/dueren-rss-1.358626'), u'http://www.aachener-nachrichten.de/cmlink/aachen-rss-1.357286'),
(u'Lokales - Eiffel', u'http://www.aachener-nachrichten.de/cmlink/eifel-rss-1.358978'), (u'Lokales - Nordkreis',
(u'Lokales - Eschweiler', u'http://www.aachener-nachrichten.de/cmlink/eschweiler-rss-1.359332'), u'http://www.aachener-nachrichten.de/cmlink/nordkreis-rss-1.358150'),
(u'Lokales - Geilenkirchen', u'http://www.aachener-nachrichten.de/cmlink/geilenkirchen-rss-1.359643'), (u'Lokales - Düren',
(u'Lokales - Heinsberg', u'http://www.aachener-nachrichten.de/cmlink/heinsberg-rss-1.359724'), u'http://www.aachener-nachrichten.de/cmlink/dueren-rss-1.358626'),
(u'Lokales - Jülich', u'http://www.aachener-nachrichten.de/cmlink/juelich-rss-1.359725'), (u'Lokales - Eiffel',
(u'Lokales - Stolberg', u'http://www.aachener-nachrichten.de/cmlink/stolberg-rss-1.359726'), u'http://www.aachener-nachrichten.de/cmlink/eifel-rss-1.358978'),
(u'News - Politik', u'http://www.aachener-nachrichten.de/cmlink/politik-rss-1.359727'), (u'Lokales - Eschweiler',
(u'News - Aus aller Welt', u'http://www.aachener-nachrichten.de/cmlink/ausallerwelt-rss-1.453282'), u'http://www.aachener-nachrichten.de/cmlink/eschweiler-rss-1.359332'),
(u'News - Wirtschaft', u'http://www.aachener-nachrichten.de/cmlink/wirtschaft-rss-1.359872'), (u'Lokales - Geilenkirchen',
(u'News - Kultur', u'http://www.aachener-nachrichten.de/cmlink/kultur-rss-1.365018'), u'http://www.aachener-nachrichten.de/cmlink/geilenkirchen-rss-1.359643'),
(u'News - Kino', u'http://www.aachener-nachrichten.de/cmlink/kino-rss-1.365019'), (u'Lokales - Heinsberg',
(u'News - Digital', u'http://www.aachener-nachrichten.de/cmlink/digital-rss-1.365020'), u'http://www.aachener-nachrichten.de/cmlink/heinsberg-rss-1.359724'),
(u'News - Wissenschaft', u'http://www.aachener-nachrichten.de/cmlink/wissenschaft-rss-1.365021'), (u'Lokales - Jülich',
(u'News - Hochschule', u'http://www.aachener-nachrichten.de/cmlink/hochschule-rss-1.365022'), u'http://www.aachener-nachrichten.de/cmlink/juelich-rss-1.359725'),
(u'News - Auto', u'http://www.aachener-nachrichten.de/cmlink/auto-rss-1.365023'), (u'Lokales - Stolberg',
(u'News - Kurioses', u'http://www.aachener-nachrichten.de/cmlink/kurioses-rss-1.365067'), u'http://www.aachener-nachrichten.de/cmlink/stolberg-rss-1.359726'),
(u'News - Musik', u'http://www.aachener-nachrichten.de/cmlink/musik-rss-1.365305'), (u'News - Politik',
(u'News - Tagesthema', u'http://www.aachener-nachrichten.de/cmlink/tagesthema-rss-1.365519'), u'http://www.aachener-nachrichten.de/cmlink/politik-rss-1.359727'),
(u'News - Newsticker', u'http://www.aachener-nachrichten.de/cmlink/newsticker-rss-1.451948'), (u'News - Aus aller Welt',
(u'Sport - Aktuell', u'http://www.aachener-nachrichten.de/cmlink/aktuell-rss-1.366716'), u'http://www.aachener-nachrichten.de/cmlink/ausallerwelt-rss-1.453282'),
(u'Sport - Fußball', u'http://www.aachener-nachrichten.de/cmlink/fussball-rss-1.367060'), (u'News - Wirtschaft',
(u'Sport - Bundesliga', u'http://www.aachener-nachrichten.de/cmlink/bundesliga-rss-1.453367'), u'http://www.aachener-nachrichten.de/cmlink/wirtschaft-rss-1.359872'),
(u'Sport - Alemannia Aachen', u'http://www.aachener-nachrichten.de/cmlink/alemanniaaachen-rss-1.366057'), (u'News - Kultur',
(u'Sport - Volleyball', u'http://www.aachener-nachrichten.de/cmlink/volleyball-rss-1.453370'), u'http://www.aachener-nachrichten.de/cmlink/kultur-rss-1.365018'),
(u'Sport - Chio', u'http://www.aachener-nachrichten.de/cmlink/chio-rss-1.453371'), (u'News - Kino', u'http://www.aachener-nachrichten.de/cmlink/kino-rss-1.365019'),
(u'Dossier - Kinderuni', u'http://www.aachener-nachrichten.de/cmlink/kinderuni-rss-1.453375'), (u'News - Digital',
(u'Dossier - Karlspreis', u'http://www.aachener-nachrichten.de/cmlink/karlspreis-rss-1.453376'), u'http://www.aachener-nachrichten.de/cmlink/digital-rss-1.365020'),
(u'Dossier - Ritterorden', u'http://www.aachener-nachrichten.de/cmlink/ritterorden-rss-1.453377'), (u'News - Wissenschaft',
(u'Dossier - ZAB-Aachen', u'http://www.aachener-nachrichten.de/cmlink/zabaachen-rss-1.453380'), u'http://www.aachener-nachrichten.de/cmlink/wissenschaft-rss-1.365021'),
(u'Dossier - Karneval', u'http://www.aachener-nachrichten.de/cmlink/karneval-rss-1.453384'), (u'News - Hochschule',
(u'Ratgeber - Geld', u'http://www.aachener-nachrichten.de/cmlink/geld-rss-1.453385'), u'http://www.aachener-nachrichten.de/cmlink/hochschule-rss-1.365022'),
(u'Ratgeber - Recht', u'http://www.aachener-nachrichten.de/cmlink/recht-rss-1.453386'), (u'News - Auto', u'http://www.aachener-nachrichten.de/cmlink/auto-rss-1.365023'),
(u'Ratgeber - Gesundheit', u'http://www.aachener-nachrichten.de/cmlink/gesundheit-rss-1.453387'), (u'News - Kurioses',
(u'Ratgeber - Familie', u'http://www.aachener-nachrichten.de/cmlink/familie-rss-1.453388'), u'http://www.aachener-nachrichten.de/cmlink/kurioses-rss-1.365067'),
(u'Ratgeber - Livestyle', u'http://www.aachener-nachrichten.de/cmlink/lifestyle-rss-1.453389'), (u'News - Musik',
(u'Ratgeber - Reisen', u'http://www.aachener-nachrichten.de/cmlink/reisen-rss-1.453390'), u'http://www.aachener-nachrichten.de/cmlink/musik-rss-1.365305'),
(u'Ratgeber - Bauen und Wohnen', u'http://www.aachener-nachrichten.de/cmlink/bauen-rss-1.453398'), (u'News - Tagesthema',
(u'Ratgeber - Bildung und Beruf', u'http://www.aachener-nachrichten.de/cmlink/bildung-rss-1.453400'), u'http://www.aachener-nachrichten.de/cmlink/tagesthema-rss-1.365519'),
] (u'News - Newsticker',
u'http://www.aachener-nachrichten.de/cmlink/newsticker-rss-1.451948'),
(u'Sport - Aktuell',
u'http://www.aachener-nachrichten.de/cmlink/aktuell-rss-1.366716'),
(u'Sport - Fußball',
u'http://www.aachener-nachrichten.de/cmlink/fussball-rss-1.367060'),
(u'Sport - Bundesliga',
u'http://www.aachener-nachrichten.de/cmlink/bundesliga-rss-1.453367'),
(u'Sport - Alemannia Aachen',
u'http://www.aachener-nachrichten.de/cmlink/alemanniaaachen-rss-1.366057'),
(u'Sport - Volleyball',
u'http://www.aachener-nachrichten.de/cmlink/volleyball-rss-1.453370'),
(u'Sport - Chio',
u'http://www.aachener-nachrichten.de/cmlink/chio-rss-1.453371'),
(u'Dossier - Kinderuni',
u'http://www.aachener-nachrichten.de/cmlink/kinderuni-rss-1.453375'),
(u'Dossier - Karlspreis',
u'http://www.aachener-nachrichten.de/cmlink/karlspreis-rss-1.453376'),
(u'Dossier - Ritterorden',
u'http://www.aachener-nachrichten.de/cmlink/ritterorden-rss-1.453377'),
(u'Dossier - ZAB-Aachen',
u'http://www.aachener-nachrichten.de/cmlink/zabaachen-rss-1.453380'),
(u'Dossier - Karneval',
u'http://www.aachener-nachrichten.de/cmlink/karneval-rss-1.453384'),
(u'Ratgeber - Geld',
u'http://www.aachener-nachrichten.de/cmlink/geld-rss-1.453385'),
(u'Ratgeber - Recht',
u'http://www.aachener-nachrichten.de/cmlink/recht-rss-1.453386'),
(u'Ratgeber - Gesundheit',
u'http://www.aachener-nachrichten.de/cmlink/gesundheit-rss-1.453387'),
(u'Ratgeber - Familie',
u'http://www.aachener-nachrichten.de/cmlink/familie-rss-1.453388'),
(u'Ratgeber - Livestyle',
u'http://www.aachener-nachrichten.de/cmlink/lifestyle-rss-1.453389'),
(u'Ratgeber - Reisen',
u'http://www.aachener-nachrichten.de/cmlink/reisen-rss-1.453390'),
(u'Ratgeber - Bauen und Wohnen',
u'http://www.aachener-nachrichten.de/cmlink/bauen-rss-1.453398'),
(u'Ratgeber - Bildung und Beruf',
u'http://www.aachener-nachrichten.de/cmlink/bildung-rss-1.453400'),
]

60
recipes/abc.recipe
View File

@ -1,43 +1,45 @@
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class ABCRecipe(BasicNewsRecipe): class ABCRecipe(BasicNewsRecipe):
title = u'ABC Linuxu' title = u'ABC Linuxu'
oldest_article = 5 oldest_article = 5
max_articles_per_feed = 3#5 max_articles_per_feed = 3 # 5
__author__ = 'Funthomas' __author__ = 'Funthomas'
language = 'cs' language = 'cs'
feeds = [ feeds = [
#(u'Blogy', u'http://www.abclinuxu.cz/auto/blogDigest.rss'), # (u'Blogy', u'http://www.abclinuxu.cz/auto/blogDigest.rss'),
(u'Články', u'http://www.abclinuxu.cz/auto/abc.rss'), (u'Články', u'http://www.abclinuxu.cz/auto/abc.rss'),
(u'Zprávičky','http://www.abclinuxu.cz/auto/zpravicky.rss') (u'Zprávičky', 'http://www.abclinuxu.cz/auto/zpravicky.rss')
] ]
remove_javascript = True remove_javascript = True
no_stylesheets = True no_stylesheets = True
remove_attributes = ['width','height'] remove_attributes = ['width', 'height']
remove_tags_before = dict(name='h1') remove_tags_before = dict(name='h1')
remove_tags = [ remove_tags = [
dict(attrs={'class':['meta-vypis','page_tools','cl_perex']}), dict(attrs={'class': ['meta-vypis', 'page_tools', 'cl_perex']}),
dict(attrs={'class':['cl_nadpis-link','komix-nav']}) dict(attrs={'class': ['cl_nadpis-link', 'komix-nav']})
] ]
remove_tags_after = [ remove_tags_after = [
dict(name='div',attrs={'class':['cl_perex','komix-nav']}), dict(name='div', attrs={'class': ['cl_perex', 'komix-nav']}),
dict(attrs={'class':['meta-vypis','page_tools']}), dict(attrs={'class': ['meta-vypis', 'page_tools']}),
dict(name='',attrs={'':''}), dict(name='', attrs={'': ''}),
] ]
preprocess_regexps = [
(re.compile(r'</div>.*<p class="perex">', re.DOTALL),
lambda match: '</div><p class="perex">')
]
preprocess_regexps = [ def print_version(self, url):
(re.compile(r'</div>.*<p class="perex">', re.DOTALL),lambda match: '</div><p class="perex">') return url + '?varianta=print&noDiz'
]
def print_version(self, url):
return url + '?varianta=print&noDiz'
extra_css = ''' extra_css = '''
h1 {font-size:130%; font-weight:bold} h1 {font-size:130%; font-weight:bold}
h3 {font-size:111%; font-weight:bold} h3 {font-size:111%; font-weight:bold}
''' '''

81
recipes/abc_au.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2011, Pat Stapleton <pat.stapleton at gmail.com>' __copyright__ = '2011, Pat Stapleton <pat.stapleton at gmail.com>'
''' '''
abc.net.au/news abc.net.au/news
@ -6,51 +6,50 @@ abc.net.au/news
import re import re
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class ABCNews(BasicNewsRecipe): class ABCNews(BasicNewsRecipe):
title = 'ABC News' title = 'ABC News'
__author__ = 'Pat Stapleton, Dean Cording' __author__ = 'Pat Stapleton, Dean Cording'
description = 'News from Australia' description = 'News from Australia'
masthead_url = 'http://www.abc.net.au/news/assets/v5/images/common/logo-news.png' masthead_url = 'http://www.abc.net.au/news/assets/v5/images/common/logo-news.png'
cover_url = 'http://www.abc.net.au/news/assets/v5/images/common/logo-news.png' cover_url = 'http://www.abc.net.au/news/assets/v5/images/common/logo-news.png'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = False no_stylesheets = False
#delay = 1 use_embedded_content = False
use_embedded_content = False encoding = 'utf8'
encoding = 'utf8' publisher = 'ABC News'
publisher = 'ABC News' category = 'News, Australia, World'
category = 'News, Australia, World' language = 'en_AU'
language = 'en_AU' publication_type = 'newsportal'
publication_type = 'newsportal'
# preprocess_regexps = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')] # preprocess_regexps = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')]
#Remove annoying map links (inline-caption class is also used for some image captions! hence regex to match maps.google) # Remove annoying map links (inline-caption class is also used for some
preprocess_regexps = [(re.compile(r'<a class="inline-caption" href="http://maps\.google\.com.*?/a>', re.DOTALL), lambda m: '')] # image captions! hence regex to match maps.google)
preprocess_regexps = [(re.compile(
r'<a class="inline-caption" href="http://maps\.google\.com.*?/a>', re.DOTALL), lambda m: '')]
conversion_options = { conversion_options = {
'comments' : description 'comments': description, 'tags': category, 'language': language, 'publisher': publisher, 'linearize_tables': False
,'tags' : category }
,'language' : language
,'publisher' : publisher
,'linearize_tables': False
}
keep_only_tags = [dict(attrs={'class':['article section']})] keep_only_tags = [dict(attrs={'class': ['article section']})]
remove_tags = [dict(attrs={'class':['related', 'tags', 'tools', 'attached-content ready', remove_tags = [dict(attrs={'class': ['related', 'tags', 'tools', 'attached-content ready',
'inline-content story left', 'inline-content map left contracted', 'published', 'inline-content story left', 'inline-content map left contracted', 'published',
'story-map', 'statepromo', 'topics', ]})] 'story-map', 'statepromo', 'topics', ]})]
remove_attributes = ['width','height'] remove_attributes = ['width', 'height']
feeds = [ feeds = [
('Top Stories', 'http://www.abc.net.au/news/feed/45910/rss.xml'), ('Top Stories', 'http://www.abc.net.au/news/feed/45910/rss.xml'),
('Canberra', 'http://www.abc.net.au/news/feed/6910/rss.xml'), ('Canberra', 'http://www.abc.net.au/news/feed/6910/rss.xml'),
('Sydney', 'http://www.abc.net.au/news/feed/10232/rss.xml'), ('Sydney', 'http://www.abc.net.au/news/feed/10232/rss.xml'),
('Melbourne', 'http://www.abc.net.au/news/feed/21708/rss.xml'), ('Melbourne', 'http://www.abc.net.au/news/feed/21708/rss.xml'),
('Brisbane', 'http://www.abc.net.au/news/feed/12858/rss.xml'), ('Brisbane', 'http://www.abc.net.au/news/feed/12858/rss.xml'),
('Perth', 'feed://www.abc.net.au/news/feed/24886/rss.xml'), ('Perth', 'feed://www.abc.net.au/news/feed/24886/rss.xml'),
('Australia', 'http://www.abc.net.au/news/feed/46182/rss.xml'), ('Australia', 'http://www.abc.net.au/news/feed/46182/rss.xml'),
('World', 'http://www.abc.net.au/news/feed/52278/rss.xml'), ('World', 'http://www.abc.net.au/news/feed/52278/rss.xml'),
('Business', 'http://www.abc.net.au/news/feed/51892/rss.xml'), ('Business', 'http://www.abc.net.au/news/feed/51892/rss.xml'),
('Science and Technology', 'http://www.abc.net.au/news/feed/2298/rss.xml'), ('Science and Technology',
] 'http://www.abc.net.au/news/feed/2298/rss.xml'),
]

58
recipes/abc_es.recipe
View File

@ -1,8 +1,8 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'Ricardo Jurado' __author__ = 'Ricardo Jurado'
__copyright__ = 'Ricardo Jurado' __copyright__ = 'Ricardo Jurado'
__version__ = 'v0.4' __version__ = 'v0.4'
__date__ = '11 February 2011' __date__ = '11 February 2011'
''' '''
http://www.abc.es/ http://www.abc.es/
@ -10,16 +10,17 @@ http://www.abc.es/
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1296604369(BasicNewsRecipe): class AdvancedUserRecipe1296604369(BasicNewsRecipe):
title = u'ABC.es' title = u'ABC.es'
masthead_url = 'http://www.abc.es/img/logo-abc.gif' masthead_url = 'http://www.abc.es/img/logo-abc.gif'
cover_url = 'http://www.abc.es/img/logo-abc.gif' cover_url = 'http://www.abc.es/img/logo-abc.gif'
publisher = u'Grupo VOCENTO' publisher = u'Grupo VOCENTO'
__author__ = 'Ricardo Jurado' __author__ = 'Ricardo Jurado'
description = 'Noticias de Spain y el mundo' description = 'Noticias de Spain y el mundo'
category = 'News,Spain,National,International,Economy' category = 'News,Spain,National,International,Economy'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 10 max_articles_per_feed = 10
@ -38,20 +39,21 @@ class AdvancedUserRecipe1296604369(BasicNewsRecipe):
h1{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; } h1{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; }
""" """
feeds = [ feeds = [
(u'PORTADA', u'http://www.abc.es/rss/feeds/abcPortada.xml')
,(u'ULTIMAS', u'http://www.abc.es/rss/feeds/abc_ultima.xml') (u'PORTADA', u'http://www.abc.es/rss/feeds/abcPortada.xml'),
,(u'NACIONAL', u'http://www.abc.es/rss/feeds/abc_EspanaEspana.xml') (u'ULTIMAS', u'http://www.abc.es/rss/feeds/abc_ultima.xml'),
,(u'INTERNACIONAL', u'http://www.abc.es/rss/feeds/abc_Internacional.xml') (u'NACIONAL', u'http://www.abc.es/rss/feeds/abc_EspanaEspana.xml'),
,(u'OPINION', u'http://www.abc.es/rss/feeds/abc_opinioncompleto.xml') (u'INTERNACIONAL', u'http://www.abc.es/rss/feeds/abc_Internacional.xml'),
,(u'BLOGS ABC', u'http://www.abc.es/rss/feeds/blogs-abc.xml') (u'OPINION', u'http://www.abc.es/rss/feeds/abc_opinioncompleto.xml'),
,(u'ECONOMIA', u'http://www.abc.es/rss/feeds/abc_Economia.xml') (u'BLOGS ABC', u'http://www.abc.es/rss/feeds/blogs-abc.xml'),
,(u'CIENCIA Y TECNOLOGIA', u'http://www.abc.es/rss/feeds/abc_Ciencia_Tecnologia.xml') (u'ECONOMIA', u'http://www.abc.es/rss/feeds/abc_Economia.xml'),
,(u'CULTURA', u'http://www.abc.es/rss/feeds/abc_Cultura.xml') (u'CIENCIA Y TECNOLOGIA', u'http://www.abc.es/rss/feeds/abc_Ciencia_Tecnologia.xml'),
,(u'LIBROS', u'http://www.abc.es/rss/feeds/abc_Libros.xml') (u'CULTURA', u'http://www.abc.es/rss/feeds/abc_Cultura.xml'),
,(u'MEDIOS Y REDES', u'http://www.abc.es/rss/feeds/ABC_Medios_Redes.xml') (u'LIBROS', u'http://www.abc.es/rss/feeds/abc_Libros.xml'),
,(u'EVASION', u'http://www.abc.es/rss/feeds/abc_evasion.xml') (u'MEDIOS Y REDES', u'http://www.abc.es/rss/feeds/ABC_Medios_Redes.xml'),
,(u'ESPECTACULOS', u'http://www.abc.es/rss/feeds/abc_Espectaculos.xml') (u'EVASION', u'http://www.abc.es/rss/feeds/abc_evasion.xml'),
,(u'GENTE', u'http://www.abc.es/rss/feeds/abc_Gente.xml') (u'ESPECTACULOS', u'http://www.abc.es/rss/feeds/abc_Espectaculos.xml'),
,(u'DEPORTES', u'http://www.abc.es/rss/feeds/abc_Deportes.xml') (u'GENTE', u'http://www.abc.es/rss/feeds/abc_Gente.xml'),
] (u'DEPORTES', u'http://www.abc.es/rss/feeds/abc_Deportes.xml')
]

69
recipes/abc_py.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010-2012, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2010-2012, Darko Miletic <darko.miletic at gmail.com>'
''' '''
abc.com.py abc.com.py
@ -6,46 +6,45 @@ abc.com.py
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class ABC_py(BasicNewsRecipe): class ABC_py(BasicNewsRecipe):
title = 'ABC Color' title = 'ABC Color'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Noticias de Paraguay y el resto del mundo' description = 'Noticias de Paraguay y el resto del mundo'
publisher = 'ABC' publisher = 'ABC'
category = 'news, politics, Paraguay' category = 'news, politics, Paraguay'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 200 max_articles_per_feed = 200
no_stylesheets = True no_stylesheets = True
encoding = 'utf8' encoding = 'utf8'
use_embedded_content = False use_embedded_content = False
language = 'es_PY' language = 'es_PY'
remove_empty_feeds = True remove_empty_feeds = True
masthead_url = 'http://www.abc.com.py/plantillas/img/abc-logo.png' masthead_url = 'http://www.abc.com.py/plantillas/img/abc-logo.png'
publication_type = 'newspaper' publication_type = 'newspaper'
extra_css = """ extra_css = """
body{font-family: UnitSlabProMedium,"Times New Roman",serif } body{font-family: UnitSlabProMedium,"Times New Roman",serif }
img{margin-bottom: 0.4em; display: block;} img{margin-bottom: 0.4em; display: block;}
""" """
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
}
remove_tags = [
dict(name=['form','iframe','embed','object','link','base','table']),
dict(attrs={'class':['es-carousel-wrapper']}),
dict(attrs={'id':['tools','article-banner-1']})
]
keep_only_tags = [dict(attrs={'id':'article'})]
remove_tags = [
dict(name=['form', 'iframe', 'embed',
'object', 'link', 'base', 'table']),
dict(attrs={'class': ['es-carousel-wrapper']}),
dict(attrs={'id': ['tools', 'article-banner-1']})
]
keep_only_tags = [dict(attrs={'id': 'article'})]
feeds = [ feeds = [
(u'Ultimo momento', u'http://www.abc.com.py/rss.xml' )
,(u'Nacionales' , u'http://www.abc.com.py/nacionales/rss.xml' ) (u'Ultimo momento', u'http://www.abc.com.py/rss.xml'),
,(u'Mundo' , u'http://www.abc.com.py/internacionales/rss.xml') (u'Nacionales', u'http://www.abc.com.py/nacionales/rss.xml'),
,(u'Deportes' , u'http://www.abc.com.py/deportes/rss.xml' ) (u'Mundo', u'http://www.abc.com.py/internacionales/rss.xml'),
,(u'Espectaculos' , u'http://www.abc.com.py/espectaculos/rss.xml' ) (u'Deportes', u'http://www.abc.com.py/deportes/rss.xml'),
,(u'TecnoCiencia' , u'http://www.abc.com.py/ciencia/rss.xml' ) (u'Espectaculos', u'http://www.abc.com.py/espectaculos/rss.xml'),
] (u'TecnoCiencia', u'http://www.abc.com.py/ciencia/rss.xml')
]

30
recipes/accountancyage.recipe
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
''' '''
www.accountancyage.com www.accountancyage.com
@ -8,26 +8,28 @@ www.accountancyage.com
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AccountancyAge(BasicNewsRecipe): class AccountancyAge(BasicNewsRecipe):
title = 'Accountancy Age' title = 'Accountancy Age'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'business news' description = 'business news'
publisher = 'accountancyage.com' publisher = 'accountancyage.com'
category = 'news, politics, finances' category = 'news, politics, finances'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
simultaneous_downloads = 1 simultaneous_downloads = 1
encoding = 'utf-8' encoding = 'utf-8'
lang = 'en' lang = 'en'
language = 'en' language = 'en'
feeds = [(u'All News', u'http://feeds.accountancyage.com/rss/latest/accountancyage/all')] feeds = [
(u'All News', u'http://feeds.accountancyage.com/rss/latest/accountancyage/all')]
keep_only_tags = [ keep_only_tags = [
dict(name='h1'), dict(name='h1'),
dict(attrs={'class':'article_content'}), dict(attrs={'class': 'article_content'}),
] ]
def get_article_url(self, article): def get_article_url(self, article):

25
recipes/acim_bilim_dergisi.recipe
View File

@ -2,26 +2,23 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1334868409(BasicNewsRecipe): class AdvancedUserRecipe1334868409(BasicNewsRecipe):
title = u'AÇIK BİLİM DERGİSİ' title = u'AÇIK BİLİM DERGİSİ'
description = ' Aylık çevrimiçi bilim dergisi' description = ' Aylık çevrimiçi bilim dergisi'
__author__ = u'thomass' __author__ = u'thomass'
oldest_article = 30 oldest_article = 30
max_articles_per_feed = 300 max_articles_per_feed = 300
auto_cleanup = True auto_cleanup = True
encoding = 'UTF-8' encoding = 'UTF-8'
publisher = 'açık bilim' publisher = 'açık bilim'
category = 'haber, bilim,TR,dergi' category = 'haber, bilim,TR,dergi'
language = 'tr' language = 'tr'
publication_type = 'magazine ' publication_type = 'magazine '
conversion_options = { conversion_options = {
'tags' : category 'tags': category, 'language': language, 'publisher': publisher, 'linearize_tables': True
,'language' : language }
,'publisher' : publisher
,'linearize_tables': True
}
cover_img_url = 'http://www.acikbilim.com/wp-content/themes/Equilibrium/images/logodene.jpg' cover_img_url = 'http://www.acikbilim.com/wp-content/themes/Equilibrium/images/logodene.jpg'
masthead_url = 'http://www.acikbilim.com/wp-content/themes/Equilibrium/images/logodene.jpg' masthead_url = 'http://www.acikbilim.com/wp-content/themes/Equilibrium/images/logodene.jpg'
feeds = [(u'Tüm Yayınlar', u'http://www.acikbilim.com/feed')]
feeds = [(u'Tüm Yayınlar', u'http://www.acikbilim.com/feed')]

28
recipes/acrimed.recipe
View File

@ -1,7 +1,7 @@
# vim:fileencoding=utf-8 # vim:fileencoding=utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2012' __copyright__ = '2012'
''' '''
acrimed.org acrimed.org
@ -10,19 +10,21 @@ acrimed.org
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Acrimed(BasicNewsRecipe):
title = u'Acrimed'
__author__ = 'Gaëtan Lehmann'
oldest_article = 30
max_articles_per_feed = 100
auto_cleanup = True
auto_cleanup_keep = '//div[@class="crayon article-chapo-4112 chapo"]'
language = 'fr'
masthead_url = 'http://www.acrimed.org/IMG/siteon0.gif'
feeds = [(u'Acrimed', u'http://www.acrimed.org/spip.php?page=backend')]
preprocess_regexps = [ class Acrimed(BasicNewsRecipe):
(re.compile(r'<title>(.*) - Acrimed \| Action Critique M.*dias</title>'), lambda m: '<title>' + m.group(1) + '</title>'), title = u'Acrimed'
__author__ = 'Gaëtan Lehmann'
oldest_article = 30
max_articles_per_feed = 100
auto_cleanup = True
auto_cleanup_keep = '//div[@class="crayon article-chapo-4112 chapo"]'
language = 'fr'
masthead_url = 'http://www.acrimed.org/IMG/siteon0.gif'
feeds = [(u'Acrimed', u'http://www.acrimed.org/spip.php?page=backend')]
preprocess_regexps = [
(re.compile(r'<title>(.*) - Acrimed \| Action Critique M.*dias</title>'),
lambda m: '<title>' + m.group(1) + '</title>'),
(re.compile(r'<h2>(.*) - Acrimed \| Action Critique M.*dias</h2>'), lambda m: '<h2>' + m.group(1) + '</h2>')] (re.compile(r'<h2>(.*) - Acrimed \| Action Critique M.*dias</h2>'), lambda m: '<h2>' + m.group(1) + '</h2>')]
extra_css = """ extra_css = """

51
recipes/ad.recipe
View File

@ -1,8 +1,9 @@
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class ADRecipe(BasicNewsRecipe): class ADRecipe(BasicNewsRecipe):
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'kwetal' __author__ = 'kwetal'
language = 'nl' language = 'nl'
country = 'NL' country = 'NL'
@ -22,41 +23,54 @@ class ADRecipe(BasicNewsRecipe):
remove_javascript = True remove_javascript = True
keep_only_tags = [] keep_only_tags = []
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'art_box2'})) keep_only_tags.append(dict(name='div', attrs={'id': 'art_box2'}))
keep_only_tags.append(dict(name = 'p', attrs = {'class': 'gen_footnote3'})) keep_only_tags.append(dict(name='p', attrs={'class': 'gen_footnote3'}))
remove_tags = [] remove_tags = []
remove_tags.append(dict(name = 'div', attrs = {'class': 'gen_clear'})) remove_tags.append(dict(name='div', attrs={'class': 'gen_clear'}))
remove_tags.append(dict(name = 'div', attrs = {'class': re.compile(r'gen_spacer.*')})) remove_tags.append(
dict(name='div', attrs={'class': re.compile(r'gen_spacer.*')}))
remove_attributes = ['style'] remove_attributes = ['style']
# feeds from http://ad.nl/ad/nl/1401/home/integration/nmc/frameset/ad_footer/rssFeeds.dhtml # feeds from
# http://ad.nl/ad/nl/1401/home/integration/nmc/frameset/ad_footer/rssFeeds.dhtml
feeds = [] feeds = []
feeds.append((u'Binnenland', u'http://www.ad.nl/nieuws/binnenland/rss.xml')) feeds.append(
feeds.append((u'Buitenland', u'http://www.ad.nl/nieuws/buitenland/rss.xml')) (u'Binnenland', u'http://www.ad.nl/nieuws/binnenland/rss.xml'))
feeds.append(
(u'Buitenland', u'http://www.ad.nl/nieuws/buitenland/rss.xml'))
feeds.append((u'Bizar', u'http://www.ad.nl/nieuws/bizar/rss.xml')) feeds.append((u'Bizar', u'http://www.ad.nl/nieuws/bizar/rss.xml'))
feeds.append((u'Gezondheid & Wetenschap', u'http://www.ad.nl/nieuws/gezondheidwetenschap/rss.xml')) feeds.append((u'Gezondheid & Wetenschap',
u'http://www.ad.nl/nieuws/gezondheidwetenschap/rss.xml'))
feeds.append((u'Economie', u'http://www.ad.nl/nieuws/economie/rss.xml')) feeds.append((u'Economie', u'http://www.ad.nl/nieuws/economie/rss.xml'))
feeds.append((u'Nederlands Voetbal', u'http://www.ad.nl/sportwereld/nederlandsvoetbal/rss.xml')) feeds.append((u'Nederlands Voetbal',
feeds.append((u'Buitenlands Voetbal', u'http://www.ad.nl/sportwereld/buitenlandsvoetbal/rss.xml')) u'http://www.ad.nl/sportwereld/nederlandsvoetbal/rss.xml'))
feeds.append((u'Champions League/Europa League', u'http://www.ad.nl/sportwereld/championsleagueeuropaleague/rss.xml')) feeds.append((u'Buitenlands Voetbal',
feeds.append((u'Wielrennen', u'http://www.ad.nl/sportwereld/wielrennen/rss.xml')) u'http://www.ad.nl/sportwereld/buitenlandsvoetbal/rss.xml'))
feeds.append((u'Champions League/Europa League',
u'http://www.ad.nl/sportwereld/championsleagueeuropaleague/rss.xml'))
feeds.append(
(u'Wielrennen', u'http://www.ad.nl/sportwereld/wielrennen/rss.xml'))
feeds.append((u'Tennis', u'http://www.ad.nl/sportwereld/tennis/rss.xml')) feeds.append((u'Tennis', u'http://www.ad.nl/sportwereld/tennis/rss.xml'))
feeds.append((u'Formule 1', u'http://www.ad.nl/sportwereld/formule1/rss.xml')) feeds.append(
feeds.append((u'Meer Sport', u'http://www.ad.nl/sportwereld/meersport/rss.xml')) (u'Formule 1', u'http://www.ad.nl/sportwereld/formule1/rss.xml'))
feeds.append(
(u'Meer Sport', u'http://www.ad.nl/sportwereld/meersport/rss.xml'))
feeds.append((u'Celebs', u'http://www.ad.nl/showbizz/celebs/rss.xml')) feeds.append((u'Celebs', u'http://www.ad.nl/showbizz/celebs/rss.xml'))
feeds.append((u'Film', u'http://www.ad.nl/showbizz/film/rss.xml')) feeds.append((u'Film', u'http://www.ad.nl/showbizz/film/rss.xml'))
feeds.append((u'Muziek', u'http://www.ad.nl/showbizz/muziek/rss.xml')) feeds.append((u'Muziek', u'http://www.ad.nl/showbizz/muziek/rss.xml'))
feeds.append((u'TV', u'http://www.ad.nl/showbizz/tv/rss.xml')) feeds.append((u'TV', u'http://www.ad.nl/showbizz/tv/rss.xml'))
feeds.append((u'Kunst & Literatuur', u'http://www.ad.nl/showbizz/kunstenliteratuur/rss.xml')) feeds.append((u'Kunst & Literatuur',
u'http://www.ad.nl/showbizz/kunstenliteratuur/rss.xml'))
feeds.append((u'Jouw Wereld', u'http://www.ad.nl/you/rss.xml')) feeds.append((u'Jouw Wereld', u'http://www.ad.nl/you/rss.xml'))
feeds.append((u'Consument', u'http://www.ad.nl/consument/rss.xml')) feeds.append((u'Consument', u'http://www.ad.nl/consument/rss.xml'))
feeds.append((u'Autowereld', u'http://www.ad.nl/autowereld/rss.xml')) feeds.append((u'Autowereld', u'http://www.ad.nl/autowereld/rss.xml'))
feeds.append((u'Reiswereld', u'http://www.ad.nl/reiswereld/rss.xml')) feeds.append((u'Reiswereld', u'http://www.ad.nl/reiswereld/rss.xml'))
feeds.append((u'Internet', u'http://www.ad.nl/digitaal/internet/rss.xml')) feeds.append((u'Internet', u'http://www.ad.nl/digitaal/internet/rss.xml'))
feeds.append((u'Games', u'http://www.ad.nl/digitaal/games/rss.xml')) feeds.append((u'Games', u'http://www.ad.nl/digitaal/games/rss.xml'))
feeds.append((u'Multimedia', u'http://www.ad.nl/digitaal/multimedia/rss.xml')) feeds.append(
(u'Multimedia', u'http://www.ad.nl/digitaal/multimedia/rss.xml'))
feeds.append((u'Planet Watch', u'http://www.ad.nl/planetwatch/rss.xml')) feeds.append((u'Planet Watch', u'http://www.ad.nl/planetwatch/rss.xml'))
extra_css = ''' extra_css = '''
@ -71,7 +85,8 @@ class ADRecipe(BasicNewsRecipe):
def print_version(self, url): def print_version(self, url):
parts = url.split('/') parts = url.split('/')
print_url = 'http://' + parts[2] + '/' + parts[3] + '/' + parts[4] + '/' + parts[5] + '/' \ print_url = 'http://' + parts[2] + '/' + parts[3] + '/' + parts[4] + '/' + parts[5] + '/' \
+ parts[10] + '/' + parts[7] + '/print/' + parts[8] + '/' + parts[9] + '/' + parts[13] + parts[10] + '/' + parts[7] + '/print/' + \
parts[8] + '/' + parts[9] + '/' + parts[13]
return print_url return print_url

59
recipes/adevarul.recipe
View File

@ -1,7 +1,7 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103' __copyright__ = u'2011, Silviu Cotoar\u0103'
''' '''
adevarul.ro adevarul.ro
@ -9,51 +9,38 @@ adevarul.ro
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Adevarul(BasicNewsRecipe): class Adevarul(BasicNewsRecipe):
title = u'Adev\u0103rul' title = u'Adev\u0103rul'
language = 'ro' language = 'ro'
__author__ = u'Silviu Cotoar\u0103' __author__ = u'Silviu Cotoar\u0103'
description = u'\u0218tiri din Rom\u00e2nia' description = u'\u0218tiri din Rom\u00e2nia'
publisher = 'Adevarul' publisher = 'Adevarul'
category = 'Ziare,Stiri,Romania' category = 'Ziare,Stiri,Romania'
oldest_article = 5 oldest_article = 5
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
encoding = 'utf-8' encoding = 'utf-8'
remove_javascript = True remove_javascript = True
cover_url = 'http://upload.wikimedia.org/wikipedia/en/d/d6/Logo_noul_adevarul.png' cover_url = 'http://upload.wikimedia.org/wikipedia/en/d/d6/Logo_noul_adevarul.png'
conversion_options = { conversion_options = {
'comments' : description 'comments': description, 'tags': category, 'language': language, 'publisher': publisher
,'tags' : category }
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [ dict(name='div', attrs={'class':'article_header'})
,dict(name='div', attrs={'class':'bb-tu first-t bb-article-body'})
]
keep_only_tags = [dict(name='div', attrs={'class': 'article_header'}), dict(name='div', attrs={'class': 'bb-tu first-t bb-article-body'})
]
remove_tags = [ remove_tags = [
dict(name='li', attrs={'class':'author'}) dict(name='li', attrs={'class': 'author'}), dict(name='li', attrs={'class': 'date'}), dict(name='li', attrs={'class': 'comments'}), dict(name='div', attrs={'class': 'bb-wg-article_related_attachements'}), dict(name='div', attrs={'class': 'bb-md bb-md-article_comments'}), dict(name='form', attrs={'id': 'bb-comment-create-form'}), dict(name='div', attrs={'id': 'mediatag'}), dict(name='div', attrs={'id': 'ft'}), dict(name='div', attrs={'id': 'comment_wrapper'}) # noqa
,dict(name='li', attrs={'class':'date'}) ]
,dict(name='li', attrs={'class':'comments'})
,dict(name='div', attrs={'class':'bb-wg-article_related_attachements'})
,dict(name='div', attrs={'class':'bb-md bb-md-article_comments'})
,dict(name='form', attrs={'id':'bb-comment-create-form'})
,dict(name='div', attrs={'id':'mediatag'})
,dict(name='div', attrs={'id':'ft'})
,dict(name='div', attrs={'id':'comment_wrapper'})
]
remove_tags_after = [ remove_tags_after = [
dict(name='div', attrs={'id':'comment_wrapper'}), dict(name='div', attrs={'id': 'comment_wrapper'}),
] ]
feeds = [ (u'\u0218tiri', u'http://www.adevarul.ro/rss/latest') ] feeds = [(u'\u0218tiri', u'http://www.adevarul.ro/rss/latest')]
def preprocess_html(self, soup): def preprocess_html(self, soup):
return self.adeify_images(soup) return self.adeify_images(soup)

73
recipes/adnkronos.recipe
View File

@ -1,8 +1,8 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'Gabriele Marini, based on Darko Miletic' __author__ = 'Gabriele Marini, based on Darko Miletic'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
description = 'Italian daily newspaper - 02-05-2010' description = 'Italian daily newspaper - 02-05-2010'
''' '''
http://www.adnkronos.com/ http://www.adnkronos.com/
@ -10,50 +10,49 @@ http://www.adnkronos.com/
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Adnkronos(BasicNewsRecipe):
__author__ = 'Gabriele Marini'
description = 'News agency'
cover_url = 'http://www.adnkronos.com/IGN6/img/popup_ign.jpg'
title = u'Adnkronos'
publisher = 'Adnkronos Group - ews agency'
category = 'News, politics, culture, economy, general interest'
language = 'it' class Adnkronos(BasicNewsRecipe):
timefmt = '[%a, %d %b, %Y]' __author__ = 'Gabriele Marini'
description = 'News agency'
cover_url = 'http://www.adnkronos.com/IGN6/img/popup_ign.jpg'
title = u'Adnkronos'
publisher = 'Adnkronos Group - ews agency'
category = 'News, politics, culture, economy, general interest'
language = 'it'
timefmt = '[%a, %d %b, %Y]'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 80 max_articles_per_feed = 80
use_embedded_content = False use_embedded_content = False
recursion = 10 recursion = 10
remove_javascript = True remove_javascript = True
def get_article_url(self, article): def get_article_url(self, article):
link = article.get('id', article.get('guid', None)) link = article.get('id', article.get('guid', None))
return link return link
extra_css = ' .newsAbstract{font-style: italic} ' extra_css = ' .newsAbstract{font-style: italic} '
keep_only_tags = [dict(name='div', attrs={'class':['breadCrumbs','newsTop','newsText']}) keep_only_tags = [dict(name='div', attrs={'class': ['breadCrumbs', 'newsTop', 'newsText']})
]
remove_tags = [
dict(name='div', attrs={'class':['leogoo','leogoo2']})
]
feeds = [
(u'Prima Pagina', u'http://rss.adnkronos.com/RSS_PrimaPagina.xml'),
(u'Ultima Ora', u'http://rss.adnkronos.com/RSS_Ultimora.xml'),
(u'Politica', u'http://rss.adnkronos.com/RSS_Politica.xml'),
(u'Esteri', u'http://rss.adnkronos.com/RSS_Esteri.xml'),
(u'Cronoca', u'http://rss.adnkronos.com/RSS_Cronaca.xml'),
(u'Economia', u'http://rss.adnkronos.com/RSS_Economia.xml'),
(u'Finanza', u'http://rss.adnkronos.com/RSS_Finanza.xml'),
(u'CyberNews', u'http://rss.adnkronos.com/RSS_CyberNews.xml'),
(u'Spettacolo', u'http://rss.adnkronos.com/RSS_Spettacolo.xml'),
(u'Cultura', u'http://rss.adnkronos.com/RSS_Cultura.xml'),
(u'Sport', u'http://rss.adnkronos.com/RSS_Sport.xml'),
(u'Sostenibilita', u'http://rss.adnkronos.com/RSS_Sostenibilita.xml'),
(u'Salute', u'http://rss.adnkronos.com/RSS_Salute.xml')
] ]
remove_tags = [
dict(name='div', attrs={'class': ['leogoo', 'leogoo2']})
]
feeds = [
(u'Prima Pagina', u'http://rss.adnkronos.com/RSS_PrimaPagina.xml'),
(u'Ultima Ora', u'http://rss.adnkronos.com/RSS_Ultimora.xml'),
(u'Politica', u'http://rss.adnkronos.com/RSS_Politica.xml'),
(u'Esteri', u'http://rss.adnkronos.com/RSS_Esteri.xml'),
(u'Cronoca', u'http://rss.adnkronos.com/RSS_Cronaca.xml'),
(u'Economia', u'http://rss.adnkronos.com/RSS_Economia.xml'),
(u'Finanza', u'http://rss.adnkronos.com/RSS_Finanza.xml'),
(u'CyberNews', u'http://rss.adnkronos.com/RSS_CyberNews.xml'),
(u'Spettacolo', u'http://rss.adnkronos.com/RSS_Spettacolo.xml'),
(u'Cultura', u'http://rss.adnkronos.com/RSS_Cultura.xml'),
(u'Sport', u'http://rss.adnkronos.com/RSS_Sport.xml'),
(u'Sostenibilita', u'http://rss.adnkronos.com/RSS_Sostenibilita.xml'),
(u'Salute', u'http://rss.adnkronos.com/RSS_Salute.xml')
]

22
recipes/ads_of_the_world.recipe
View File

@ -1,26 +1,26 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1336986047(BasicNewsRecipe): class AdvancedUserRecipe1336986047(BasicNewsRecipe):
title = u'Ads of the World' title = u'Ads of the World'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
auto_cleanup = False auto_cleanup = False
description = 'The best international advertising campaigns' description = 'The best international advertising campaigns'
language = 'en' language = 'en'
__author__ = 'faber1971' __author__ = 'faber1971'
no_stylesheets = True no_stylesheets = True
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'id':'primary'}) dict(name='div', attrs={'id': 'primary'})
] ]
remove_tags = [ remove_tags = [
dict(name='ul', attrs={'class':'links inline'}) dict(name='ul', attrs={'class': 'links inline'}), dict(name='div', attrs={'class': 'form-item'}), dict(
,dict(name='div', attrs={'class':'form-item'}) name='div', attrs={'id': ['options', 'comments']}), dict(name='ul', attrs={'id': 'nodePager'})
,dict(name='div', attrs={'id':['options', 'comments']}) ]
,dict(name='ul', attrs={'id':'nodePager'})
]
reverse_article_order = True reverse_article_order = True
masthead_url = 'http://bigcatgroup.co.uk/files/2011/01/05-ads-of-the-world.png' masthead_url = 'http://bigcatgroup.co.uk/files/2011/01/05-ads-of-the-world.png'
feeds = [(u'Ads of the world', u'http://feeds.feedburner.com/adsoftheworld-latest')] feeds = [
(u'Ads of the world', u'http://feeds.feedburner.com/adsoftheworld-latest')]

28
recipes/adventure_zone_pl.recipe
View File

@ -1,10 +1,12 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Adventure_zone(BasicNewsRecipe): class Adventure_zone(BasicNewsRecipe):
title = u'Adventure Zone' title = u'Adventure Zone'
__author__ = 'fenuks' __author__ = 'fenuks'
description = u'Czytaj więcej o przygodzie - codzienne nowinki. Szukaj u nas solucji i poradników, czytaj recenzje i zapowiedzi. Także galeria, pliki oraz forum dla wszystkich fanów gier przygodowych.' description = u'Czytaj więcej o przygodzie - codzienne nowinki. Szukaj u nas solucji i poradników, czytaj recenzje i zapowiedzi. Także galeria, pliki oraz forum dla wszystkich fanów gier przygodowych.' # noqa
category = 'games' category = 'games'
language = 'pl' language = 'pl'
BASEURL = 'http://www.adventure-zone.info/fusion/' BASEURL = 'http://www.adventure-zone.info/fusion/'
no_stylesheets = True no_stylesheets = True
extra_css = '.image {float: left; margin-right: 5px;}' extra_css = '.image {float: left; margin-right: 5px;}'
@ -13,20 +15,20 @@ class Adventure_zone(BasicNewsRecipe):
cover_url = 'http://www.adventure-zone.info/inne/logoaz_2012.png' cover_url = 'http://www.adventure-zone.info/inne/logoaz_2012.png'
remove_attributes = ['style'] remove_attributes = ['style']
use_embedded_content = False use_embedded_content = False
keep_only_tags = [dict(attrs={'class':'content'})] keep_only_tags = [dict(attrs={'class': 'content'})]
remove_tags = [dict(attrs={'class':'footer'})] remove_tags = [dict(attrs={'class': 'footer'})]
feeds = [(u'Nowinki', u'http://www.adventure-zone.info/fusion/rss/index.php')] feeds = [(u'Nowinki', u'http://www.adventure-zone.info/fusion/rss/index.php')]
def skip_ad_pages(self, soup): def skip_ad_pages(self, soup):
skip_tag = soup.body.find(attrs={'class':'content'}) skip_tag = soup.body.find(attrs={'class': 'content'})
skip_tag = skip_tag.findAll(name='a') skip_tag = skip_tag.findAll(name='a')
title = soup.title.string.lower() title = soup.title.string.lower()
if (('zapowied' in title) or ('recenzj' in title) or ('solucj' in title) or ('poradnik' in title)): if (('zapowied' in title) or ('recenzj' in title) or ('solucj' in title) or ('poradnik' in title)):
for r in skip_tag: for r in skip_tag:
if r.strong and r.strong.string: if r.strong and r.strong.string:
word=r.strong.string.lower() word = r.strong.string.lower()
if (('zapowied' in word) or ('recenzj' in word) or ('solucj' in word) or ('poradnik' in word)): if (('zapowied' in word) or ('recenzj' in word) or ('solucj' in word) or ('poradnik' in word)):
return self.index_to_soup(self.BASEURL+r['href'], raw=True) return self.index_to_soup(self.BASEURL + r['href'], raw=True)
def preprocess_html(self, soup): def preprocess_html(self, soup):
for link in soup.findAll('a', href=True): for link in soup.findAll('a', href=True):

87
recipes/adventuregamers.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009-2012, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2009-2012, Darko Miletic <darko.miletic at gmail.com>'
''' '''
www.adventuregamers.com www.adventuregamers.com
@ -6,21 +6,21 @@ www.adventuregamers.com
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AdventureGamers(BasicNewsRecipe): class AdventureGamers(BasicNewsRecipe):
title = u'Adventure Gamers' title = u'Adventure Gamers'
language = 'en' language = 'en'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Adventure games portal' description = 'Adventure games portal'
publisher = 'Adventure Gamers' publisher = 'Adventure Gamers'
category = 'news, games, adventure, technology' category = 'news, games, adventure, technology'
oldest_article = 10 oldest_article = 10
#delay = 10
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
encoding = 'utf8' encoding = 'utf8'
remove_javascript = True remove_javascript = True
use_embedded_content = False use_embedded_content = False
INDEX = u'http://www.adventuregamers.com' INDEX = u'http://www.adventuregamers.com'
extra_css = """ extra_css = """
.pageheader_type{font-size: x-large; font-weight: bold; color: #828D74} .pageheader_type{font-size: x-large; font-weight: bold; color: #828D74}
.pageheader_title,.page_title{font-size: xx-large; color: #394128} .pageheader_title,.page_title{font-size: xx-large; color: #394128}
@ -29,59 +29,54 @@ class AdventureGamers(BasicNewsRecipe):
.score_column_1{ padding-left: 10px; font-size: small; width: 50%} .score_column_1{ padding-left: 10px; font-size: small; width: 50%}
.score_column_2{ padding-left: 10px; font-size: small; width: 50%} .score_column_2{ padding-left: 10px; font-size: small; width: 50%}
.score_column_3{ padding-left: 10px; font-size: small; width: 50%} .score_column_3{ padding-left: 10px; font-size: small; width: 50%}
.score_header{font-size: large; color: #50544A} .score_header{font-size: large; color: #50544A}
img{margin-bottom: 1em;} img{margin-bottom: 1em;}
body{font-family: 'Open Sans',Helvetica,Arial,sans-serif} body{font-family: 'Open Sans',Helvetica,Arial,sans-serif}
""" """
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'class':'cleft_inn'})] keep_only_tags = [dict(name='div', attrs={'class': 'cleft_inn'})]
remove_tags = [ remove_tags = [
dict(name=['object','link','embed','form','iframe','meta']) dict(name=['object', 'link', 'embed', 'form', 'iframe', 'meta']), dict(name='a', attrs={
,dict(name='a', attrs={'href':'http://www.adventuregamers.com/about/scoring'}) 'href': 'http://www.adventuregamers.com/about/scoring'}), dict(name='a', attrs={'href': 'http://www.adventuregamers.com/about/policies'})
,dict(name='a', attrs={'href':'http://www.adventuregamers.com/about/policies'}) ]
] remove_tags_after = [dict(name='div', attrs={'class': 'bodytext'})]
remove_tags_after = [dict(name='div', attrs={'class':'bodytext'})] remove_attributes = ['width', 'height']
remove_attributes = ['width','height']
feeds = [(u'Articles', u'http://www.adventuregamers.com/rss/')] feeds = [(u'Articles', u'http://www.adventuregamers.com/rss/')]
def get_article_url(self, article): def get_article_url(self, article):
url = BasicNewsRecipe.get_article_url(self, article) url = BasicNewsRecipe.get_article_url(self, article)
if '/videos/' in url or '/hypeometer/' in url: if '/videos/' in url or '/hypeometer/' in url:
return None return None
return url return url
def append_page(self, soup, appendtag, position): def append_page(self, soup, appendtag, position):
pager = soup.find('div', attrs={'class':'pagination_big'}) pager = soup.find('div', attrs={'class': 'pagination_big'})
if pager: if pager:
nextpage = soup.find('a', attrs={'class':'next-page'}) nextpage = soup.find('a', attrs={'class': 'next-page'})
if nextpage: if nextpage:
nexturl = nextpage['href'] nexturl = nextpage['href']
soup2 = self.index_to_soup(nexturl) soup2 = self.index_to_soup(nexturl)
texttag = soup2.find('div', attrs={'class':'bodytext'}) texttag = soup2.find('div', attrs={'class': 'bodytext'})
for it in texttag.findAll(style=True): for it in texttag.findAll(style=True):
del it['style'] del it['style']
newpos = len(texttag.contents) newpos = len(texttag.contents)
self.append_page(soup2,texttag,newpos) self.append_page(soup2, texttag, newpos)
texttag.extract() texttag.extract()
pager.extract() pager.extract()
appendtag.insert(position,texttag) appendtag.insert(position, texttag)
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
for item in soup.findAll('div', attrs={'class':'floatright'}): for item in soup.findAll('div', attrs={'class': 'floatright'}):
item.extract() item.extract()
self.append_page(soup, soup.body, 3) self.append_page(soup, soup.body, 3)
pager = soup.find('div',attrs={'class':'pagination_big'}) pager = soup.find('div', attrs={'class': 'pagination_big'})
if pager: if pager:
pager.extract() pager.extract()
return self.adeify_images(soup) return self.adeify_images(soup)

30
recipes/aftenposten.recipe
View File

@ -1,20 +1,20 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Aftenposten(BasicNewsRecipe): class Aftenposten(BasicNewsRecipe):
title = u'Aftenposten' title = u'Aftenposten'
__author__ = 'davotibarna' __author__ = 'davotibarna'
description = 'Norske nyheter' description = 'Norske nyheter'
language = 'no' language = 'no'
oldest_article = 5 oldest_article = 5
max_articles_per_feed = 100 max_articles_per_feed = 100
recipe_disabled = ('The recipe to download Aftenposten has been ' recipe_disabled = ('The recipe to download Aftenposten has been '
'temporarily disabled at the publisher\'s request, while ' 'temporarily disabled at the publisher\'s request, while '
'they finalize their digital strategy.') 'they finalize their digital strategy.')
no_stylesheets = True no_stylesheets = True
encoding = 'ISO-8859-1' encoding = 'ISO-8859-1'
feeds = [(u'Aftenposten', u'http://www.aftenposten.no/eksport/rss-1_0/')] feeds = [(u'Aftenposten', u'http://www.aftenposten.no/eksport/rss-1_0/')]
def print_version(self, url):
return url.replace('#xtor=RSS-3', '?service=print')
def print_version(self, url):
return url.replace('#xtor=RSS-3', '?service=print')

32
recipes/agrogerila.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
''' '''
boljevac.blogspot.com boljevac.blogspot.com
@ -8,25 +8,23 @@ boljevac.blogspot.com
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AgroGerila(BasicNewsRecipe): class AgroGerila(BasicNewsRecipe):
title = 'Agro Gerila' title = 'Agro Gerila'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Politicki nekorektan blog.' description = 'Politicki nekorektan blog.'
oldest_article = 45 oldest_article = 45
max_articles_per_feed = 100 max_articles_per_feed = 100
language = 'sr' language = 'sr'
encoding = 'utf-8' encoding = 'utf-8'
no_stylesheets = True no_stylesheets = True
use_embedded_content = True use_embedded_content = True
publication_type = 'blog' publication_type = 'blog'
extra_css = ' @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: "Trebuchet MS",Trebuchet,Verdana,sans1,sans-serif} .article_description{font-family: sans1, sans-serif} img{margin-bottom: 0.8em; border: 1px solid #333333; padding: 4px } ' extra_css = ' @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: "Trebuchet MS",Trebuchet,Verdana,sans1,sans-serif} .article_description{font-family: sans1, sans-serif} img{margin-bottom: 0.8em; border: 1px solid #333333; padding: 4px } ' # noqa
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': 'film, blog, srbija', 'publisher': 'Dry-Na-Nord', 'language': language
, 'tags' : 'film, blog, srbija' }
, 'publisher': 'Dry-Na-Nord'
, 'language' : language
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
@ -36,5 +34,3 @@ class AgroGerila(BasicNewsRecipe):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
return self.adeify_images(soup) return self.adeify_images(soup)

49
recipes/aif_ru.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010 - 2014, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2010 - 2014, Darko Miletic <darko.miletic at gmail.com>'
''' '''
www.aif.ru www.aif.ru
@ -6,35 +6,32 @@ www.aif.ru
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AIF_ru(BasicNewsRecipe): class AIF_ru(BasicNewsRecipe):
title = 'Arguments & Facts - Russian' title = 'Arguments & Facts - Russian'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'News from Russia' description = 'News from Russia'
publisher = 'AIF' publisher = 'AIF'
category = 'news, politics, Russia' category = 'news, politics, Russia'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
encoding = 'utf8' encoding = 'utf8'
language = 'ru' language = 'ru'
publication_type = 'magazine' publication_type = 'magazine'
masthead_url = 'http://static3.aif.ru/glossy/index/i/logo.png' masthead_url = 'http://static3.aif.ru/glossy/index/i/logo.png'
extra_css = """ extra_css = """
body{font-family: Verdana,Arial,Helvetica,sans1,sans-serif} body{font-family: Verdana,Arial,Helvetica,sans1,sans-serif}
img{display: block} img{display: block}
""" """
keep_only_tags = [ keep_only_tags = [
dict(name='h1', attrs={'class':'title'}) dict(name='h1', attrs={'class': 'title'}), dict(name='div', attrs={'class': 'prew_tags'}), dict(
,dict(name='div', attrs={'class':'prew_tags'}) name='article', attrs={'class': lambda x: x and 'articl_body' in x.split()})
,dict(name='article', attrs={'class':lambda x: x and 'articl_body' in x.split()}) ]
] remove_tags = [
remove_tags = [ dict(name=['iframe', 'object', 'link', 'base', 'input', 'meta']), dict(name='div', attrs={'class': 'in-topic'}), dict(name='div', attrs={
dict(name=['iframe','object','link','base','input','meta']) 'class': lambda x: x and 'related_article' in x.split()}), dict(name='div', attrs={'class': lambda x: x and 'articl_tag' in x.split()})
,dict(name='div',attrs={'class':'in-topic'}) ]
,dict(name='div', attrs={'class':lambda x: x and 'related_article' in x.split()})
,dict(name='div', attrs={'class':lambda x: x and 'articl_tag' in x.split()})
]
feeds = [(u'News', u'http://www.aif.ru/rss/all.php')]
feeds = [(u'News', u'http://www.aif.ru/rss/all.php')]

27
recipes/air_force_times.recipe
View File

@ -1,5 +1,6 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AirForceTimes(BasicNewsRecipe): class AirForceTimes(BasicNewsRecipe):
title = 'Air Force Times' title = 'Air Force Times'
__author__ = 'jde' __author__ = 'jde'
@ -12,7 +13,7 @@ class AirForceTimes(BasicNewsRecipe):
tags = 'news, U.S. Air Force' tags = 'news, U.S. Air Force'
cover_url = 'http://www.airforcetimes.com/images/logo_airforcetimes_alert.jpg' cover_url = 'http://www.airforcetimes.com/images/logo_airforcetimes_alert.jpg'
masthead_url = 'http://www.airforcetimes.com/images/logo_airforcetimes_alert.jpg' masthead_url = 'http://www.airforcetimes.com/images/logo_airforcetimes_alert.jpg'
oldest_article = 7 #days oldest_article = 7 # days
max_articles_per_feed = 25 max_articles_per_feed = 25
publication_type = 'newspaper' publication_type = 'newspaper'
no_stylesheets = True no_stylesheets = True
@ -24,20 +25,14 @@ class AirForceTimes(BasicNewsRecipe):
remove_empty_feeds = True remove_empty_feeds = True
auto_cleanup = True auto_cleanup = True
feeds = [ feeds = [
('News', 'http://www.airforcetimes.com/rss_news.php'), ('News', 'http://www.airforcetimes.com/rss_news.php'),
('Benefits', 'http://www.airforcetimes.com/rss_benefits.php'), ('Benefits', 'http://www.airforcetimes.com/rss_benefits.php'),
('Money', 'http://www.airforcetimes.com/rss_money.php'), ('Money', 'http://www.airforcetimes.com/rss_money.php'),
('Careers & Education', 'http://www.airforcetimes.com/rss_careers.php'), ('Careers & Education', 'http://www.airforcetimes.com/rss_careers.php'),
('Community', 'http://www.airforcetimes.com/rss_community.php'), ('Community', 'http://www.airforcetimes.com/rss_community.php'),
('Off Duty', 'http://www.airforcetimes.com/rss_off_duty.php'), ('Off Duty', 'http://www.airforcetimes.com/rss_off_duty.php'),
('Entertainment', 'http://www.airforcetimes.com/rss_entertainment.php'), ('Entertainment', 'http://www.airforcetimes.com/rss_entertainment.php'),
('Guard & Reserve', 'http://www.airforcetimes.com/rss_guard.php'), ('Guard & Reserve', 'http://www.airforcetimes.com/rss_guard.php'),
] ]

80
recipes/ajc.recipe
View File

@ -1,15 +1,17 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'Creative Commons Attribution 4.0 International License' __license__ = 'Creative Commons Attribution 4.0 International License'
__author__ = 'John McDole' __author__ = 'John McDole'
__copyright__ = '' __copyright__ = ''
__version__ = '0.1' __version__ = '0.1'
__date__ = '2015/01/10' __date__ = '2015/01/10'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import datetime, re import datetime
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag from calibre.ebooks.BeautifulSoup import Tag
class AdvancedUserRecipe1282101454(BasicNewsRecipe): class AdvancedUserRecipe1282101454(BasicNewsRecipe):
now = datetime.datetime.now() now = datetime.datetime.now()
title = 'The AJC' title = 'The AJC'
@ -24,72 +26,81 @@ class AdvancedUserRecipe1282101454(BasicNewsRecipe):
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
# The AJC lists identical articles in multiple feeds; this removes them based on their URL # The AJC lists identical articles in multiple feeds; this removes them
# based on their URL
ignore_duplicate_articles = {'title', 'url'} ignore_duplicate_articles = {'title', 'url'}
# And this says "Hey, AJC, different feeds should mean something!" # And this says "Hey, AJC, different feeds should mean something!"
remove_empty_feeds = True remove_empty_feeds = True
# Sets whether a feed has full articles embedded in it. The AJC feeds do not. # Sets whether a feed has full articles embedded in it. The AJC feeds do
# not.
use_embedded_content = False use_embedded_content = False
masthead_url = 'http://gawand.org/wp-content/uploads/2010/06/ajc-logo.gif' masthead_url = 'http://gawand.org/wp-content/uploads/2010/06/ajc-logo.gif'
# Pick your poison. Business seems to be mostly cross-linked articles. Premium and cross-linked # Pick your poison. Business seems to be mostly cross-linked articles. Premium and cross-linked
# articels will be dropped. # articels will be dropped.
feeds = [ feeds = [
('Breaking News', 'http://www.ajc.com/list/rss/online/ajc-auto-list-iphone-topnews/aFKq/'), ('Breaking News', 'http://www.ajc.com/list/rss/online/ajc-auto-list-iphone-topnews/aFKq/'),
('Metro and Georgia', 'http://www.ajc.com/list/rss/news/local/news-georgia-and-region/aCxP/'), ('Metro and Georgia',
('Business', 'http://www.ajc.com/feeds/categories/business/'), 'http://www.ajc.com/list/rss/news/local/news-georgia-and-region/aCxP/'),
('Health', 'http://www.ajc.com/feeds/categories/health/'), ('Business', 'http://www.ajc.com/feeds/categories/business/'),
# ('Braves', 'http://www.ajc.com/list/rss/sports/baseball/atlanta-braves-news/aGpN/'), ('Health', 'http://www.ajc.com/feeds/categories/health/'),
# ('Falcons', 'http://www.ajc.com/list/rss/sports/football/falcons-news/aGK4/'), # ('Braves', 'http://www.ajc.com/list/rss/sports/baseball/atlanta-braves-news/aGpN/'),
# ('Georgia Tech Yellow Jackets', 'http://www.ajc.com/list/rss/sports/college/georgia-tech-headlines/aGK6/'), # ('Falcons', 'http://www.ajc.com/list/rss/sports/football/falcons-news/aGK4/'),
] # ('Georgia Tech Yellow Jackets', 'http://www.ajc.com/list/rss/sports/college/georgia-tech-headlines/aGK6/'),
]
headline_reg_exp = '^.*cm-story-headline.*$' headline_reg_exp = '^.*cm-story-headline.*$'
story_body_reg_exp = '^.*cm-story-body.*$' story_body_reg_exp = '^.*cm-story-body.*$'
author_reg_exp = '^.*cm-story-author.*$' author_reg_exp = '^.*cm-story-author.*$'
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'class':re.compile(headline_reg_exp, re.IGNORECASE)}), dict(name='div', attrs={'class': re.compile(
dict(name='div', attrs={'class':'cm-story-meta'}), headline_reg_exp, re.IGNORECASE)}),
dict(name='div', attrs={'class':re.compile(author_reg_exp, re.IGNORECASE)}), dict(name='div', attrs={'class': 'cm-story-meta'}),
dict(name='meta', attrs={'name':'description'}), dict(name='div', attrs={'class': re.compile(
dict(name='div', attrs={'class':re.compile(story_body_reg_exp, re.IGNORECASE)}), author_reg_exp, re.IGNORECASE)}),
] dict(name='meta', attrs={'name': 'description'}),
dict(name='div', attrs={'class': re.compile(
story_body_reg_exp, re.IGNORECASE)}),
]
premium_reg_exp = '^.*cmPremiumContent.*$' premium_reg_exp = '^.*cmPremiumContent.*$'
footer_reg_exp = '^.*cm-story-footer.*$' footer_reg_exp = '^.*cm-story-footer.*$'
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class':re.compile(footer_reg_exp, re.IGNORECASE)}), dict(name='div', attrs={'class': re.compile(
dict(name='div', attrs={'class':'cm-inline-related-group'}) footer_reg_exp, re.IGNORECASE)}),
] dict(name='div', attrs={'class': 'cm-inline-related-group'})
]
extra_css = 'body { font-family: verdana, helvetica, sans-serif; } \ extra_css = 'body { font-family: verdana, helvetica, sans-serif; } \
.cm-story-headline h1 { text-align: center; font-size: 175%; font-weight: bold; } \ .cm-story-headline h1 { text-align: center; font-size: 175%; font-weight: bold; } \
.cm-story-meta { font-size: 80%; } \ .cm-story-meta { font-size: 80%; } \
.cm-related-caption, .cmPhotoImageAttribution, img { display: block; font-size: 75%; font-style: italic; text-align: center; margin: 5px auto;} \ .cm-related-caption, .cmPhotoImageAttribution, img { display: block; font-size: 75%; font-style: italic; text-align: center; margin: 5px auto;} \
.cm-story-author { display: block; font-size: 80%; font-style: italic; }' .cm-story-author { display: block; font-size: 80%; font-style: italic; }'
# I would love to remove these completely from the finished product, but I can't see how at the momemnt. # I would love to remove these completely from the finished product, but I can't see how at the momemnt.
# Retuning "None" from preprocess_html(soup) as suggested in mobileread forums leads to errors. # Retuning "None" from preprocess_html(soup) as suggested in mobileread
# forums leads to errors.
def preprocess_html(self, soup): def preprocess_html(self, soup):
premium = soup.find('div', attrs={'class':re.compile(self.premium_reg_exp, re.IGNORECASE)}) premium = soup.find('div', attrs={'class': re.compile(
self.premium_reg_exp, re.IGNORECASE)})
if premium: if premium:
return None return None
crosslink = soup.find('a', attrs={'class':'cm-feed-story-more-link'}) crosslink = soup.find('a', attrs={'class': 'cm-feed-story-more-link'})
if crosslink: if crosslink:
return None return None
return soup return soup
def populate_article_metadata(self, article, soup, first): def populate_article_metadata(self, article, soup, first):
for meta in soup.findAll('meta', attrs={'name':'description'}): for meta in soup.findAll('meta', attrs={'name': 'description'}):
article.text_summary = meta['content'] article.text_summary = meta['content']
article.summary = meta['content'] article.summary = meta['content']
lead = soup.find('div', attrs={'class':'cm-story-photo'}) lead = soup.find('div', attrs={'class': 'cm-story-photo'})
if lead: if lead:
lead = lead.find('img') lead = lead.find('img')
else: else:
@ -98,10 +109,10 @@ class AdvancedUserRecipe1282101454(BasicNewsRecipe):
self.add_toc_thumbnail(article, lead['src']) self.add_toc_thumbnail(article, lead['src'])
names = '' names = ''
comma = '' comma = ''
for div in soup.findAll('div', attrs={'class':re.compile(self.author_reg_exp, re.IGNORECASE)}): for div in soup.findAll('div', attrs={'class': re.compile(self.author_reg_exp, re.IGNORECASE)}):
div.extract() div.extract()
for auth in div.findAll('a'): for auth in div.findAll('a'):
if (auth.has_key('class') and auth['class'] == 'cm-source-image'): if (auth.has_key('class') and auth['class'] == 'cm-source-image'): # noqa
continue continue
names = names + comma + auth.contents[0] names = names + comma + auth.contents[0]
comma = ', ' comma = ', '
@ -110,7 +121,6 @@ class AdvancedUserRecipe1282101454(BasicNewsRecipe):
tag = Tag(soup, 'div', [('class', 'cm-story-author')]) tag = Tag(soup, 'div', [('class', 'cm-story-author')])
tag.append("by: ") tag.append("by: ")
tag.append(names) tag.append(names)
meta = soup.find('div', attrs={'class':'cm-story-meta'}) meta = soup.find('div', attrs={'class': 'cm-story-meta'})
meta_idx = meta.parent.contents.index(meta) meta_idx = meta.parent.contents.index(meta)
meta.parent.insert(meta_idx + 1, tag) meta.parent.insert(meta_idx + 1, tag)

21
recipes/ajiajin.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>' __copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
''' '''
ajiajin.com/blog ajiajin.com/blog
@ -6,18 +6,17 @@ ajiajin.com/blog
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AjiajinBlog(BasicNewsRecipe): class AjiajinBlog(BasicNewsRecipe):
title = u'Ajiajin blog' title = u'Ajiajin blog'
__author__ = 'Hiroshi Miura' __author__ = 'Hiroshi Miura'
oldest_article = 5 oldest_article = 5
publication_type = 'blog' publication_type = 'blog'
max_articles_per_feed = 100 max_articles_per_feed = 100
description = 'The next generation internet trends in Japan and Asia' description = 'The next generation internet trends in Japan and Asia'
publisher = '' publisher = ''
category = 'internet, asia, japan' category = 'internet, asia, japan'
language = 'en' language = 'en'
encoding = 'utf-8' encoding = 'utf-8'
feeds = [(u'blog', u'http://feeds.feedburner.com/Asiajin')]
feeds = [(u'blog', u'http://feeds.feedburner.com/Asiajin')]

77
recipes/aksiyon_derigisi.recipe
View File

@ -2,46 +2,51 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Aksiyon (BasicNewsRecipe): class Aksiyon (BasicNewsRecipe):
title = u'Aksiyon Dergisi' title = u'Aksiyon Dergisi'
__author__ = u'thomass' __author__ = u'thomass'
description = 'Haftalık haber dergisi ' description = 'Haftalık haber dergisi '
oldest_article =13 oldest_article = 13
max_articles_per_feed =100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
#delay = 1 encoding = 'utf-8'
#use_embedded_content = False publisher = 'Aksiyon'
encoding = 'utf-8' category = 'news, haberler,TR,gazete'
publisher = 'Aksiyon' language = 'tr'
category = 'news, haberler,TR,gazete'
language = 'tr'
publication_type = 'magazine' publication_type = 'magazine'
auto_cleanup = True auto_cleanup = True
cover_img_url = 'http://www.aksiyon.com.tr/aksiyon/images/aksiyon/top-page/aksiyon_top_r2_c1.jpg' cover_img_url = 'http://www.aksiyon.com.tr/aksiyon/images/aksiyon/top-page/aksiyon_top_r2_c1.jpg'
masthead_url = 'http://aksiyon.com.tr/aksiyon/images/aksiyon/top-page/aksiyon_top_r2_c1.jpg' masthead_url = 'http://aksiyon.com.tr/aksiyon/images/aksiyon/top-page/aksiyon_top_r2_c1.jpg'
ignore_duplicate_articles = { 'title', 'url' } ignore_duplicate_articles = {'title', 'url'}
remove_empty_feeds= True remove_empty_feeds = True
feeds = [ feeds = [
( u'KAPAK', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=26'), (u'KAPAK', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=26'),
( u'ANASAYFA', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=0'), (u'ANASAYFA', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=0'),
( u'EKONOMİ', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=35'), (u'EKONOMİ', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=35'),
( u'EKOANALİZ', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=284'), (u'EKOANALİZ', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=284'),
( u'YAZARLAR', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=17'), (u'YAZARLAR', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=17'),
( u'KİTAPLIK', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=13'), (u'KİTAPLIK', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=13'),
( u'SİNEMA', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=14'), (u'SİNEMA', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=14'),
( u'ARKA PENCERE', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=27'), (u'ARKA PENCERE',
( u'DÜNYA', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=32'), u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=27'),
( u'DOSYALAR', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=34'), (u'DÜNYA', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=32'),
( u'KARAKUTU', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=11'), (u'DOSYALAR', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=34'),
( u'KÜLTÜR & SANAT', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=12'), (u'KARAKUTU', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=11'),
( u'SPOR', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=38'), (u'KÜLTÜR & SANAT',
( u'BİLİŞİM - TEKNOLOJİ', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=39'), u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=12'),
( u'3. BOYUT', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=172'), (u'SPOR', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=38'),
( u'HAYAT BİLGİSİ', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=283'), (u'BİLİŞİM - TEKNOLOJİ',
( u'İŞ DÜNYASI', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=283'), u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=39'),
] (u'3. BOYUT', u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=172'),
(u'HAYAT BİLGİSİ',
#def print_version(self, url): u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=283'),
#return url.replace('http://www.aksiyon.com.tr/aksiyon/newsDetail_getNewsById.action?load=detay&', 'http://www.aksiyon.com.tr/aksiyon/mobile_detailn.action?') (u'İŞ DÜNYASI',
u'http://www.aksiyon.com.tr/aksiyon/rss?sectionId=283'),
]
# def print_version(self, url):
# return
# url.replace('http://www.aksiyon.com.tr/aksiyon/newsDetail_getNewsById.action?load=detay&',
# 'http://www.aksiyon.com.tr/aksiyon/mobile_detailn.action?')

51
recipes/akter.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010-2012, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2010-2012, Darko Miletic <darko.miletic at gmail.com>'
''' '''
akter.co.rs akter.co.rs
@ -7,37 +7,35 @@ akter.co.rs
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Akter(BasicNewsRecipe): class Akter(BasicNewsRecipe):
title = 'AKTER - Nedeljnik' title = 'AKTER - Nedeljnik'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'AKTER - nedeljni politicki magazin savremene Srbije' description = 'AKTER - nedeljni politicki magazin savremene Srbije'
publisher = 'Akter Media Group d.o.o.' publisher = 'Akter Media Group d.o.o.'
category = 'vesti, online vesti, najnovije vesti, politika, sport, ekonomija, biznis, finansije, berza, kultura, zivot, putovanja, auto, automobili, tehnologija, politicki magazin, dogadjaji, desavanja, lifestyle, zdravlje, zdravstvo, vest, novine, nedeljnik, srbija, novi sad, vojvodina, svet, drustvo, zabava, republika srpska, beograd, intervju, komentar, reportaza, arhiva vesti, news, serbia, politics' category = 'vesti, online vesti, najnovije vesti, politika, sport, ekonomija, biznis, finansije, berza, kultura, zivot, putovanja, auto, automobili, tehnologija, politicki magazin, dogadjaji, desavanja, lifestyle, zdravlje, zdravstvo, vest, novine, nedeljnik, srbija, novi sad, vojvodina, svet, drustvo, zabava, republika srpska, beograd, intervju, komentar, reportaza, arhiva vesti, news, serbia, politics' # noqa
oldest_article = 8 oldest_article = 8
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
encoding = 'utf-8' encoding = 'utf-8'
masthead_url = 'http://www.akter.co.rs/gfx/logoneover.png' masthead_url = 'http://www.akter.co.rs/gfx/logoneover.png'
language = 'sr' language = 'sr'
publication_type = 'magazine' publication_type = 'magazine'
remove_empty_feeds = True remove_empty_feeds = True
extra_css = """ extra_css = """
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
body{font-family: Tahoma,Geneva,sans1,sans-serif} body{font-family: Tahoma,Geneva,sans1,sans-serif}
img{margin-bottom: 0.8em; display: block;} img{margin-bottom: 0.8em; display: block;}
""" """
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher': publisher
, 'language' : language
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
keep_only_tags = [dict(name='div', attrs={'id':'section_to_print'})] keep_only_tags = [dict(name='div', attrs={'id': 'section_to_print'})]
feeds = [(u'Nedeljnik', u'http://akter.co.rs/rss/nedeljnik')] feeds = [(u'Nedeljnik', u'http://akter.co.rs/rss/nedeljnik')]
def print_version(self, url): def print_version(self, url):
dpart, spart, apart = url.rpartition('/') dpart, spart, apart = url.rpartition('/')
@ -45,10 +43,9 @@ class Akter(BasicNewsRecipe):
def get_cover_url(self): def get_cover_url(self):
soup = self.index_to_soup('http://www.akter.co.rs/weekly.html') soup = self.index_to_soup('http://www.akter.co.rs/weekly.html')
divt = soup.find('div', attrs={'class':'lastissue'}) divt = soup.find('div', attrs={'class': 'lastissue'})
if divt: if divt:
imgt = divt.find('img') imgt = divt.find('img')
if imgt: if imgt:
return 'http://www.akter.co.rs' + imgt['src'] return 'http://www.akter.co.rs' + imgt['src']
return None return None

41
recipes/akter_dnevnik.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>'
''' '''
akter.co.rs akter.co.rs
@ -7,37 +7,34 @@ akter.co.rs
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Akter(BasicNewsRecipe): class Akter(BasicNewsRecipe):
title = 'AKTER - Dnevnik' title = 'AKTER - Dnevnik'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'AKTER - Najnovije vesti iz Srbije' description = 'AKTER - Najnovije vesti iz Srbije'
publisher = 'Akter Media Group d.o.o.' publisher = 'Akter Media Group d.o.o.'
category = 'vesti, online vesti, najnovije vesti, politika, sport, ekonomija, biznis, finansije, berza, kultura, zivot, putovanja, auto, automobili, tehnologija, politicki magazin, dogadjaji, desavanja, lifestyle, zdravlje, zdravstvo, vest, novine, nedeljnik, srbija, novi sad, vojvodina, svet, drustvo, zabava, republika srpska, beograd, intervju, komentar, reportaza, arhiva vesti, news, serbia, politics' oldest_article = 8
oldest_article = 8
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
encoding = 'utf-8' encoding = 'utf-8'
masthead_url = 'http://www.akter.co.rs/gfx/logodnover.png' masthead_url = 'http://www.akter.co.rs/gfx/logodnover.png'
language = 'sr' language = 'sr'
publication_type = 'magazine' publication_type = 'magazine'
remove_empty_feeds = True remove_empty_feeds = True
extra_css = """ extra_css = """
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
body{font-family: Tahoma,Geneva,sans1,sans-serif} body{font-family: Tahoma,Geneva,sans1,sans-serif}
img{margin-bottom: 0.8em; display: block;} img{margin-bottom: 0.8em; display: block;}
""" """
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher': publisher
, 'language' : language
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
keep_only_tags = [dict(name='div', attrs={'id':'section_to_print'})] keep_only_tags = [dict(name='div', attrs={'id': 'section_to_print'})]
feeds = [(u'Vesti', u'http://akter.co.rs/rss/dnevni')] feeds = [(u'Vesti', u'http://akter.co.rs/rss/dnevni')]
def print_version(self, url): def print_version(self, url):
dpart, spart, apart = url.rpartition('/') dpart, spart, apart = url.rpartition('/')

53
recipes/aktualne.cz.recipe
View File

@ -3,8 +3,9 @@ from __future__ import unicode_literals
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
import re import re
class aktualneRecipe(BasicNewsRecipe): class aktualneRecipe(BasicNewsRecipe):
__author__ = 'bubak' __author__ = 'bubak'
title = u'aktualne.cz' title = u'aktualne.cz'
publisher = u'Centrum holdings' publisher = u'Centrum holdings'
description = 'aktuálně.cz' description = 'aktuálně.cz'
@ -13,13 +14,13 @@ class aktualneRecipe(BasicNewsRecipe):
encoding = 'utf-8' encoding = 'utf-8'
feeds = [ feeds = [
(u'Domácí', u'http://aktualne.centrum.cz/feeds/rss/domaci/?photo=0'), (u'Domácí', u'http://aktualne.centrum.cz/feeds/rss/domaci/?photo=0'),
(u'Zprávy', u'http://aktualne.centrum.cz/feeds/rss/zpravy/?photo=0'), (u'Zprávy', u'http://aktualne.centrum.cz/feeds/rss/zpravy/?photo=0'),
(u'Praha', u'http://aktualne.centrum.cz/feeds/rss/domaci/regiony/praha/?photo=0'), (u'Praha', u'http://aktualne.centrum.cz/feeds/rss/domaci/regiony/praha/?photo=0'),
(u'Ekonomika', u'http://aktualne.centrum.cz/feeds/rss/ekonomika/?photo=0'), (u'Ekonomika', u'http://aktualne.centrum.cz/feeds/rss/ekonomika/?photo=0'),
(u'Finance', u'http://aktualne.centrum.cz/feeds/rss/finance/?photo=0'), (u'Finance', u'http://aktualne.centrum.cz/feeds/rss/finance/?photo=0'),
(u'Blogy a názory', u'http://blog.aktualne.centrum.cz/export-all.php') (u'Blogy a názory', u'http://blog.aktualne.centrum.cz/export-all.php')
] ]
language = 'cs' language = 'cs'
cover_url = 'http://img.aktualne.centrum.cz/design/akt4/o/l/logo-akt-ciste.png' cover_url = 'http://img.aktualne.centrum.cz/design/akt4/o/l/logo-akt-ciste.png'
@ -27,29 +28,31 @@ class aktualneRecipe(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
remove_attributes = [] remove_attributes = []
remove_tags_before = dict(name='h1', attrs={'class':['titulek-clanku']}) remove_tags_before = dict(name='h1', attrs={'class': ['titulek-clanku']})
filter_regexps = [r'img.aktualne.centrum.cz'] filter_regexps = [r'img.aktualne.centrum.cz']
remove_tags = [dict(name='div', attrs={'id':['social-bookmark']}), remove_tags = [dict(name='div', attrs={'id': ['social-bookmark']}),
dict(name='div', attrs={'class':['box1', 'svazane-tagy']}), dict(name='div', attrs={'class': ['box1', 'svazane-tagy']}),
dict(name='div', attrs={'class':'itemcomment id0'}), dict(name='div', attrs={'class': 'itemcomment id0'}),
dict(name='div', attrs={'class':'hlavicka'}), dict(name='div', attrs={'class': 'hlavicka'}),
dict(name='div', attrs={'class':'hlavni-menu'}), dict(name='div', attrs={'class': 'hlavni-menu'}),
dict(name='div', attrs={'class':'top-standard-brand-obal'}), dict(name='div', attrs={
dict(name='div', attrs={'class':'breadcrumb'}), 'class': 'top-standard-brand-obal'}),
dict(name='div', attrs={'id':'start-standard'}), dict(name='div', attrs={'class': 'breadcrumb'}),
dict(name='div', attrs={'id':'forum'}), dict(name='div', attrs={'id': 'start-standard'}),
dict(name='span', attrs={'class':'akce'}), dict(name='div', attrs={'id': 'forum'}),
dict(name='span', attrs={'class':'odrazka vetsi'}), dict(name='span', attrs={'class': 'akce'}),
dict(name='div', attrs={'class':'boxP'}), dict(name='span', attrs={'class': 'odrazka vetsi'}),
dict(name='div', attrs={'class':'box2'})] dict(name='div', attrs={'class': 'boxP'}),
dict(name='div', attrs={'class': 'box2'})]
preprocess_regexps = [ preprocess_regexps = [
(re.compile(r'<div class="(contenttitle"|socialni-site|wiki|facebook-promo|facebook-like-button"|meta-akce).*', (re.compile(r'<div class="(contenttitle"|socialni-site|wiki|facebook-promo|facebook-like-button"|meta-akce).*',
re.DOTALL|re.IGNORECASE), lambda match: '</body>'), re.DOTALL | re.IGNORECASE), lambda match: '</body>'),
(re.compile(r'<div class="[^"]*poutak-clanek-trojka".*', re.DOTALL|re.IGNORECASE), lambda match: '</body>')] (re.compile(r'<div class="[^"]*poutak-clanek-trojka".*', re.DOTALL | re.IGNORECASE), lambda match: '</body>')]
keep_only_tags = [] keep_only_tags = []
visited_urls = {} visited_urls = {}
def get_article_url(self, article): def get_article_url(self, article):
url = BasicNewsRecipe.get_article_url(self, article) url = BasicNewsRecipe.get_article_url(self, article)
if url in self.visited_urls: if url in self.visited_urls:

114
recipes/al_ahram.recipe
View File

@ -1,66 +1,76 @@
# coding=utf-8 # coding=utf-8
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2011-2016, Hassan Williamson <haz at hazrpg.co.uk>' __copyright__ = '2011-2016, Hassan Williamson <haz at hazrpg.co.uk>'
''' '''
ahram.org.eg ahram.org.eg
''' '''
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class AlAhram(BasicNewsRecipe): class AlAhram(BasicNewsRecipe):
title = u'Al-Ahram (الأهرام)' title = u'Al-Ahram (الأهرام)'
__author__ = 'Hassan Williamson' __author__ = 'Hassan Williamson'
description = 'The Arabic version of the Al-Ahram newspaper.' description = 'The Arabic version of the Al-Ahram newspaper.'
language = 'ar' language = 'ar'
encoding = 'utf8' encoding = 'utf8'
cover_url = 'http://www.ahram.org.eg/Media/News/2015/3/14/2015-635619650946000713-600.jpg' cover_url = 'http://www.ahram.org.eg/Media/News/2015/3/14/2015-635619650946000713-600.jpg'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
#delay = 1 use_embedded_content = False
use_embedded_content = False publisher = 'Al-Ahram'
publisher = 'Al-Ahram' category = 'News'
category = 'News' publication_type = 'newsportal'
publication_type = 'newsportal'
extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif; direction: rtl; } .bbtitle{ font-weight: bold; font-size: 2em; } .bbsubtitle{ font-size: 1.3em; } #WriterImage{ height: 10px; } ' extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif; direction: rtl; } .bbtitle{ font-weight: bold; font-size: 2em; } .bbsubtitle{ font-size: 1.3em; } #WriterImage{ height: 10px; } ' # noqa
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'class':['bbcolright']}) dict(name='div', attrs={'class': ['bbcolright']})
] ]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class':['bbnav', 'bbsp']}), dict(name='div', attrs={'class': ['bbnav', 'bbsp']}),
dict(name='div', attrs={'id':['AddThisButton']}), dict(name='div', attrs={'id': ['AddThisButton']}),
dict(name='a', attrs={'class':['twitter-share-button']}), dict(name='a', attrs={'class': ['twitter-share-button']}),
dict(name='div', attrs={'id':['ReaderCount']}), dict(name='div', attrs={'id': ['ReaderCount']}),
] ]
remove_attributes = [ remove_attributes = [
'width','height','style' 'width', 'height', 'style'
] ]
feeds = [ feeds = [
(u'الأولى', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=25'), (u'الأولى', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=25'),
(u'الصفحة الثانية', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=74'), (u'الصفحة الثانية',
(u'مصر', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=27'), 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=74'),
(u'المشهد السياسي', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=60'), (u'مصر', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=27'),
(u'المحافظات', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=29'), (u'المشهد السياسي',
(u'الوطن العربي', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=31'), 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=60'),
(u'العالم', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=26'), (u'المحافظات', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=29'),
(u'تقارير المراسلين', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=2'), (u'الوطن العربي',
(u'تحقيقات', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=3'), 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=31'),
(u'قضايا واراء', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=4'), (u'العالم', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=26'),
(u'اقتصاد', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=5'), (u'تقارير المراسلين',
(u'رياضة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=6'), 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=2'),
(u'حوادث', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=38'), (u'تحقيقات', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=3'),
(u'دنيا الثقافة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=7'), (u'قضايا واراء',
(u'المراة والطفل', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=8'), 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=4'),
(u'يوم جديد', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=9'), (u'اقتصاد', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=5'),
(u'الكتاب', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=10'), (u'رياضة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=6'),
(u'الاعمدة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=11'), (u'حوادث', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=38'),
(u'أراء حرة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=59'), (u'دنيا الثقافة',
(u'ملفات الاهرام', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=12'), 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=7'),
(u'بريد الاهرام', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=15'), (u'المراة والطفل',
(u'برلمان الثورة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=61'), 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=8'),
(u'الاخيرة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=16'), (u'يوم جديد', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=9'),
] (u'الكتاب', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=10'),
(u'الاعمدة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=11'),
(u'أراء حرة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=59'),
(u'ملفات الاهرام',
'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=12'),
(u'بريد الاهرام',
'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=15'),
(u'برلمان الثورة',
'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=61'),
(u'الاخيرة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=16'),
]

53
recipes/al_jazeera.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
''' '''
@ -6,57 +6,62 @@ english.aljazeera.net
''' '''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
def has_cls(x): def has_cls(x):
return dict(attrs={'class':lambda cls: cls and x in cls.split()}) return dict(attrs={'class': lambda cls: cls and x in cls.split()})
class AlJazeera(BasicNewsRecipe): class AlJazeera(BasicNewsRecipe):
title = 'Al Jazeera in English' title = 'Al Jazeera in English'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'News from Middle East' description = 'News from Middle East'
language = 'en' language = 'en'
publisher = 'Al Jazeera' publisher = 'Al Jazeera'
category = 'news, politics, middle east' category = 'news, politics, middle east'
delay = 1 delay = 1
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
extra_css = """ extra_css = """
body{font-family: Arial,sans-serif} body{font-family: Arial,sans-serif}
#ctl00_cphBody_dvSummary{font-weight: bold} #ctl00_cphBody_dvSummary{font-weight: bold}
#dvArticleDate{font-size: small; color: #999999} #dvArticleDate{font-size: small; color: #999999}
""" """
conversion_options = { conversion_options = {
'comment' : description , 'tags' : category , 'comment': description, 'tags': category,
'publisher' : publisher , 'language' : language 'publisher': publisher, 'language': language
} }
keep_only_tags = [ keep_only_tags = [
dict(id='main-story'), dict(id='main-story'),
] ]
remove_tags = [ remove_tags = [
has_cls('MoreOnTheStory'), has_cls('ArticleBottomToolbar'), dict(smtitle="ShowMore"), has_cls('MoreOnTheStory'), has_cls(
dict(name=['object','link','table','meta','base','iframe','embed']), 'ArticleBottomToolbar'), dict(smtitle="ShowMore"),
dict(name=['object', 'link', 'table',
'meta', 'base', 'iframe', 'embed']),
] ]
feeds = [(u'Al Jazeera English', u'http://english.aljazeera.net/Services/Rss/?PostingId=2007731105943979989')] feeds = [(u'Al Jazeera English',
u'http://english.aljazeera.net/Services/Rss/?PostingId=2007731105943979989')]
def get_article_url(self, article): def get_article_url(self, article):
artlurl = article.get('link', None) artlurl = article.get('link', None)
return artlurl.replace('http://english.aljazeera.net//','http://english.aljazeera.net/') return artlurl.replace('http://english.aljazeera.net//', 'http://english.aljazeera.net/')
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
for item in soup.findAll(face=True): for item in soup.findAll(face=True):
del item['face'] del item['face']
td = soup.find('td',attrs={'class':'DetailedSummary'}) td = soup.find('td', attrs={'class': 'DetailedSummary'})
if td: if td:
td.name = 'div' td.name = 'div'
spn = soup.find('span',attrs={'id':'DetailedTitle'}) spn = soup.find('span', attrs={'id': 'DetailedTitle'})
if spn: if spn:
spn.name='h1' spn.name = 'h1'
for itm in soup.findAll('span', attrs={'id':['dvArticleDate','ctl00_cphBody_lblDate']}): for itm in soup.findAll('span', attrs={'id': ['dvArticleDate', 'ctl00_cphBody_lblDate']}):
itm.name = 'div' itm.name = 'div'
for alink in soup.findAll('a'): for alink in soup.findAll('a'):
if alink.string is not None: if alink.string is not None:

136
recipes/al_masry_alyoum_arabic.recipe
View File

@ -1,79 +1,85 @@
# coding=utf-8 # coding=utf-8
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2016, Hassan Williamson <haz at hazrpg.co.uk>' __copyright__ = '2016, Hassan Williamson <haz at hazrpg.co.uk>'
''' '''
almasryalyoum.com almasryalyoum.com
''' '''
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class AlMasryAlyoum(BasicNewsRecipe): class AlMasryAlyoum(BasicNewsRecipe):
title = u'Al-Masry Alyoum (المصري اليوم)' title = u'Al-Masry Alyoum (المصري اليوم)'
__author__ = 'Hassan Williamson' __author__ = 'Hassan Williamson'
description = 'The Arabic version of the Al-Masry Alyoum (Egypt Independent) newspaper.' description = 'The Arabic version of the Al-Masry Alyoum (Egypt Independent) newspaper.'
language = 'ar' language = 'ar'
encoding = 'utf8' encoding = 'utf8'
cover_url = 'http://www.almasryalyoum.com/content/images/header_logo.png' cover_url = 'http://www.almasryalyoum.com/content/images/header_logo.png'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
#delay = 1 use_embedded_content = False
use_embedded_content = False publisher = 'Al-Masry Alyoum'
publisher = 'Al-Masry Alyoum' category = 'News'
category = 'News' publication_type = 'newsportal'
publication_type = 'newsportal'
extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif; direction: rtl; } .tit_2{ font-weight: bold; font-size: 2em; } .pinfo{ font-size: 1.3em; } .articleimg img{ max-width: 100%; } .imgauther{ display: block; font-size: 0.7em; } .caption{ font-size: 0.7em; } ' extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif; direction: rtl; } .tit_2{ font-weight: bold; font-size: 2em; } .pinfo{ font-size: 1.3em; } .articleimg img{ max-width: 100%; } .imgauther{ display: block; font-size: 0.7em; } .caption{ font-size: 0.7em; } ' # noqa
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'class':['article']}) dict(name='div', attrs={'class': ['article']})
] ]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class':['share_buttons_container']}), dict(name='div', attrs={'class': ['share_buttons_container']}),
dict(name='div', attrs={'class':['min_related']}), dict(name='div', attrs={'class': ['min_related']}),
dict(name='div', attrs={'id':['feedback']}), dict(name='div', attrs={'id': ['feedback']}),
dict(name='div', attrs={'class':['news_SMSBox']}), dict(name='div', attrs={'class': ['news_SMSBox']}),
dict(name='div', attrs={'class':['tags']}), dict(name='div', attrs={'class': ['tags']}),
dict(name='div', attrs={'class':['ads', 'y_logo_news']}), dict(name='div', attrs={'class': ['ads', 'y_logo_news']}),
dict(name='div', attrs={'class':['ads']}), dict(name='div', attrs={'class': ['ads']}),
dict(name='div', attrs={'class':['option']}), dict(name='div', attrs={'class': ['option']}),
dict(name='div', attrs={'class':['seealso']}), dict(name='div', attrs={'class': ['seealso']}),
dict(name='div', attrs={'id':['comments']}), dict(name='div', attrs={'id': ['comments']}),
] ]
remove_attributes = [ remove_attributes = [
'width','height','style' 'width', 'height', 'style'
] ]
feeds = [ feeds = [
(u'أخر الأخبار', 'http://www.almasryalyoum.com/rss/RssFeeds'), (u'أخر الأخبار', 'http://www.almasryalyoum.com/rss/RssFeeds'),
(u'الصفحة الرئيسية', 'http://www.almasryalyoum.com/rss/RssFeeds?homePage=true'), (u'الصفحة الرئيسية',
(u'أقلام وآراء', 'http://www.almasryalyoum.com/rss/RssFeeds?typeId=2&homePage=false'), 'http://www.almasryalyoum.com/rss/RssFeeds?homePage=true'),
(u'أخبار مصر', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=3'), (u'أقلام وآراء', 'http://www.almasryalyoum.com/rss/RssFeeds?typeId=2&homePage=false'),
(u'رياضة', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=8'), (u'أخبار مصر', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=3'),
(u'اقتصاد', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=4'), (u'رياضة', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=8'),
(u'حوادث', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=7'), (u'اقتصاد', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=4'),
(u'فنون', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=10'), (u'حوادث', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=7'),
(u'منوعاتنون', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=12'), (u'فنون', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=10'),
(u'ثقافة', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=6'), (u'منوعاتنون', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=12'),
(u'علوم وتكنولوجيا', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=9'), (u'ثقافة', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=6'),
(u'تحقيقات وحوارات', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=5'), (u'علوم وتكنولوجيا',
(u'المرأة', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=69'), 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=9'),
(u'رأي', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=2'), (u'تحقيقات وحوارات',
(u'وسط الناس', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=13'), 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=5'),
(u'مركز المصري للدراسات و المعلومات', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=56'), (u'المرأة', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=69'),
(u'مطبخ', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=81'), (u'رأي', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=2'),
(u'برلمان مصر', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=78'), (u'وسط الناس', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=13'),
(u'تقارير', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=54'), (u'مركز المصري للدراسات و المعلومات',
(u'تحليلات', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=60'), 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=56'),
(u'عروض نقدية', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=61'), (u'مطبخ', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=81'),
(u'دراسات', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=62'), (u'برلمان مصر', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=78'),
(u'كتاب المصري اليوم', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=65'), (u'تقارير', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=54'),
(u'فعاليات', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=66'), (u'تحليلات', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=60'),
(u'إسلامي', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=75'), (u'عروض نقدية', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=61'),
(u'مطبخي', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=76'), (u'دراسات', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=62'),
(u'مسلسلاتيطبخي', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=77'), (u'كتاب المصري اليوم',
(u'رمضان زمان', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=82'), 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=65'),
(u'تقارير', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=85'), (u'فعاليات', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=66'),
(u'سيارات', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=86'), (u'إسلامي', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=75'),
] (u'مطبخي', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=76'),
(u'مسلسلاتيطبخي',
'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=77'),
(u'رمضان زمان', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=82'),
(u'تقارير', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=85'),
(u'سيارات', 'http://www.almasryalyoum.com/rss/RssFeeds?sectionId=86'),
]

78
recipes/al_monitor.recipe
View File

@ -1,14 +1,18 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2014, spswerling' __copyright__ = '2014, spswerling'
''' '''
http://www.al-monitor.com/ http://www.al-monitor.com/
''' '''
import string, inspect, datetime, re import string
import inspect
import datetime
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup from calibre.ebooks.BeautifulSoup import BeautifulSoup
class AlMonitor(BasicNewsRecipe): class AlMonitor(BasicNewsRecipe):
title = u'Al Monitor' title = u'Al Monitor'
__author__ = u'spswerling' __author__ = u'spswerling'
@ -26,39 +30,39 @@ class AlMonitor(BasicNewsRecipe):
recursions = 0 recursions = 0
compress_news_images = True compress_news_images = True
compress_news_images_max_size = 7 compress_news_images_max_size = 7
scale_news_images = (150,200) # (kindle touch: 600x800) scale_news_images = (150, 200) # (kindle touch: 600x800)
useHighResImages = False useHighResImages = False
oldest_article = 1.5 oldest_article = 1.5
max_articles_per_section = 15 max_articles_per_section = 15
sections = [ sections = [
(u'egypt',u'http://www.al-monitor.com/pulse/egypt-pulse'), (u'egypt', u'http://www.al-monitor.com/pulse/egypt-pulse'),
(u'gulf',u'http://www.al-monitor.com/pulse/gulf-pulse'), (u'gulf', u'http://www.al-monitor.com/pulse/gulf-pulse'),
(u'iran',u'http://www.al-monitor.com/pulse/iran-pulse'), (u'iran', u'http://www.al-monitor.com/pulse/iran-pulse'),
(u'iraq',u'http://www.al-monitor.com/pulse/iraq-pulse'), (u'iraq', u'http://www.al-monitor.com/pulse/iraq-pulse'),
(u'israel',u'http://www.al-monitor.com/pulse/israel-pulse'), (u'israel', u'http://www.al-monitor.com/pulse/israel-pulse'),
(u'lebanon',u'http://www.al-monitor.com/pulse/lebanon-pulse'), (u'lebanon', u'http://www.al-monitor.com/pulse/lebanon-pulse'),
(u'palistine',u'http://www.al-monitor.com/pulse/palistine-pulse'), (u'palistine', u'http://www.al-monitor.com/pulse/palistine-pulse'),
(u'syria',u'http://www.al-monitor.com/pulse/syria-pulse'), (u'syria', u'http://www.al-monitor.com/pulse/syria-pulse'),
(u'turkey',u'http://www.al-monitor.com/pulse/turkey-pulse'), (u'turkey', u'http://www.al-monitor.com/pulse/turkey-pulse'),
] ]
# util for creating remove_tags and keep_tags style regex matchers # util for creating remove_tags and keep_tags style regex matchers
def tag_matcher(elt, attr, rgx_str): def tag_matcher(elt, attr, rgx_str):
return dict(name=elt, attrs={attr:re.compile(rgx_str, re.IGNORECASE)}) return dict(name=elt, attrs={attr: re.compile(rgx_str, re.IGNORECASE)})
remove_tags = [ remove_tags = [
dict(attrs={'id':[ dict(attrs={'id': [
'header', 'header',
'pulsebanner', 'pulsebanner',
'relatedarticles', 'relatedarticles',
'sidecolumn', 'sidecolumn',
'disqus', 'disqus',
'footer', 'footer',
'footer2', 'footer2',
'footer3', 'footer3',
'mobile-extras', 'mobile-extras',
]}), ]}),
tag_matcher('hr', 'id', 'spacer'), tag_matcher('hr', 'id', 'spacer'),
tag_matcher('a', 'title', 'print this article'), tag_matcher('a', 'title', 'print this article'),
tag_matcher('div', 'class', 'extras'), tag_matcher('div', 'class', 'extras'),
@ -118,12 +122,12 @@ class AlMonitor(BasicNewsRecipe):
if len(self.articles[section]) >= self.max_articles_per_section: if len(self.articles[section]) >= self.max_articles_per_section:
return return
self.articles[section].append( self.articles[section].append(
dict(title=title, dict(title=title,
url=full_url, url=full_url,
date='', date='',
description='', description='',
author='', author='',
content='')) content=''))
def preprocess_raw_html(self, raw_html, url): def preprocess_raw_html(self, raw_html, url):
reason_to_skip = self.should_skip_article(BeautifulSoup(raw_html)) reason_to_skip = self.should_skip_article(BeautifulSoup(raw_html))
@ -136,7 +140,7 @@ class AlMonitor(BasicNewsRecipe):
return super(self.__class__, self).preprocess_raw_html(raw_html, url) return super(self.__class__, self).preprocess_raw_html(raw_html, url)
def populate_article_metadata(self, article, soup, first): def populate_article_metadata(self, article, soup, first):
summary_node = soup.find('div', {'id':'summary'}) summary_node = soup.find('div', {'id': 'summary'})
if summary_node: if summary_node:
summary = self.text(summary_node) summary = self.text(summary_node)
self._p('Summary: ' + summary) self._p('Summary: ' + summary)
@ -167,7 +171,7 @@ class AlMonitor(BasicNewsRecipe):
def date_from_string(self, datestring): def date_from_string(self, datestring):
try: try:
# eg: Posted September 17, 2014 # eg: Posted September 17, 2014
dt = datetime.datetime.strptime(datestring,"Posted %B %d, %Y") dt = datetime.datetime.strptime(datestring, "Posted %B %d, %Y")
except: except:
dt = None dt = None
@ -192,14 +196,14 @@ class AlMonitor(BasicNewsRecipe):
return abs_url return abs_url
def text(self,n): def text(self, n):
return self.tag_to_string(n).strip() return self.tag_to_string(n).strip()
def _dbg_soup_node(self, node): def _dbg_soup_node(self, node):
s = ' cls: ' + str(node.get('class')).strip() + \ s = ' cls: ' + str(node.get('class')).strip() + \
' id: ' + str(node.get('id')).strip() + \ ' id: ' + str(node.get('id')).strip() + \
' role: ' + str(node.get('role')).strip() + \ ' role: ' + str(node.get('role')).strip() + \
' txt: ' + self.text(node) ' txt: ' + self.text(node)
return s return s
def _p(self, msg): def _p(self, msg):

8
recipes/albert_mohler.recipe
View File

@ -1,10 +1,11 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2012, Peter Grungi <p dot grungi at gmail dot com>' __copyright__ = '2012, Peter Grungi <p dot grungi at gmail dot com>'
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AlbertMohlersBlog(BasicNewsRecipe): class AlbertMohlersBlog(BasicNewsRecipe):
title = u'Albert Mohler\'s Blog' title = u'Albert Mohler\'s Blog'
__author__ = 'Peter Grungi' __author__ = 'Peter Grungi'
language = 'en' language = 'en'
oldest_article = 90 oldest_article = 90
@ -15,4 +16,5 @@ class AlbertMohlersBlog(BasicNewsRecipe):
language = 'en' language = 'en'
author = 'Albert Mohler' author = 'Albert Mohler'
feeds = [(u'Albert Mohler\'s Blog', u'http://feeds.feedburner.com/AlbertMohlersBlog?format=xml')] feeds = [(u'Albert Mohler\'s Blog',
u'http://feeds.feedburner.com/AlbertMohlersBlog?format=xml')]

24
recipes/alejakomiksu_com.recipe
View File

@ -2,16 +2,16 @@ __license__ = 'GPL v3'
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AlejaKomiksu(BasicNewsRecipe): class AlejaKomiksu(BasicNewsRecipe):
title = u'Aleja Komiksu' title = u'Aleja Komiksu'
__author__ = 'fenuks' __author__ = 'fenuks'
description = u'Serwis poświęcony komiksom. Najnowsze wieści, recenzje, artykuły, wywiady, galerie, komiksy online, konkursy, linki, baza komiksów online.' description = u'Serwis poświęcony komiksom. Najnowsze wieści, recenzje, artykuły, wywiady, galerie, komiksy online, konkursy, linki, baza komiksów online.'
category = 'comics' category = 'comics'
#publication_type = '' language = 'pl'
language = 'pl'
#encoding = ''
extra_css = 'ul {list-style-type: none;} .gfx_news {float: right;}' extra_css = 'ul {list-style-type: none;} .gfx_news {float: right;}'
preprocess_regexps = [(re.compile(ur'((<li class="no_img_b">(Do poczytania)|(Nowości):</li>)|(<p class="head2">Komentarze</p>)).*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>')] preprocess_regexps = [(re.compile(ur'((<li class="no_img_b">(Do poczytania)|(Nowości):</li>)|(<p class="head2">Komentarze</p>)).*</body>',
re.DOTALL | re.IGNORECASE), lambda match: '</body>')]
cover_url = 'http://www.alejakomiksu.com/gfx/build/logo.png' cover_url = 'http://www.alejakomiksu.com/gfx/build/logo.png'
masthead_url = 'http://www.alejakomiksu.com/gfx/build/logo.png' masthead_url = 'http://www.alejakomiksu.com/gfx/build/logo.png'
use_embedded_content = False use_embedded_content = False
@ -23,15 +23,13 @@ class AlejaKomiksu(BasicNewsRecipe):
remove_attributes = ['style', 'font'] remove_attributes = ['style', 'font']
ignore_duplicate_articles = {'title', 'url'} ignore_duplicate_articles = {'title', 'url'}
keep_only_tags = [dict(attrs={'class':'cont_tresc'})] keep_only_tags = [dict(attrs={'class': 'cont_tresc'})]
#remove_tags = [dict()]
#remove_tags_before = dict()
feeds = [(u'Wiadomości', 'http://www.alejakomiksu.com/rss.php5')] feeds = [(u'Wiadomości', 'http://www.alejakomiksu.com/rss.php5')]
def skip_ad_pages(self, soup): def skip_ad_pages(self, soup):
tag = soup.find(attrs={'class':'rodzaj'}) tag = soup.find(attrs={'class': 'rodzaj'})
if tag and tag.a.string.lower().strip() == 'recenzje': if tag and tag.a.string.lower().strip() == 'recenzje':
link = soup.find(text=re.compile('recenzuje')) link = soup.find(text=re.compile('recenzuje'))
if link: if link:
return self.index_to_soup(link.parent['href'], raw=True) return self.index_to_soup(link.parent['href'], raw=True)

54
recipes/alo_novine.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
''' '''
@ -8,19 +8,20 @@ www.alo.rs
import re import re
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class Alo_Novine(BasicNewsRecipe): class Alo_Novine(BasicNewsRecipe):
title = 'Alo!' title = 'Alo!'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = "News Portal from Serbia" description = "News Portal from Serbia"
publisher = 'Alo novine d.o.o.' publisher = 'Alo novine d.o.o.'
category = 'news, politics, Serbia' category = 'news, politics, Serbia'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
delay = 4 delay = 4
no_stylesheets = True no_stylesheets = True
encoding = 'utf-8' encoding = 'utf-8'
use_embedded_content = False use_embedded_content = False
language = 'sr' language = 'sr'
extra_css = """ extra_css = """
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
.article_description,body{font-family: Arial,Helvetica,sans1,sans-serif} .article_description,body{font-family: Arial,Helvetica,sans1,sans-serif}
@ -30,25 +31,23 @@ class Alo_Novine(BasicNewsRecipe):
img{margin-bottom: 0.8em} """ img{margin-bottom: 0.8em} """
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher': publisher
, 'language' : language
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
remove_tags = [dict(name=['object','link','embed'])] remove_tags = [dict(name=['object', 'link', 'embed'])]
remove_attributes = ['height','width'] remove_attributes = ['height', 'width']
feeds = [ feeds = [
(u'Najnovije Vijesti', u'http://www.alo.rs/rss/danasnje_vesti')
,(u'Politika' , u'http://www.alo.rs/rss/politika') (u'Najnovije Vijesti', u'http://www.alo.rs/rss/danasnje_vesti'),
,(u'Vesti' , u'http://www.alo.rs/rss/vesti') (u'Politika', u'http://www.alo.rs/rss/politika'),
,(u'Sport' , u'http://www.alo.rs/rss/sport') (u'Vesti', u'http://www.alo.rs/rss/vesti'),
,(u'Ljudi' , u'http://www.alo.rs/rss/ljudi') (u'Sport', u'http://www.alo.rs/rss/sport'),
,(u'Saveti' , u'http://www.alo.rs/rss/saveti') (u'Ljudi', u'http://www.alo.rs/rss/ljudi'),
] (u'Saveti', u'http://www.alo.rs/rss/saveti')
]
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
@ -61,5 +60,4 @@ class Alo_Novine(BasicNewsRecipe):
return 'http://www.alo.rs/resources/templates/tools/print.php?id=' + artid return 'http://www.alo.rs/resources/templates/tools/print.php?id=' + artid
def image_url_processor(self, baseurl, url): def image_url_processor(self, baseurl, url):
return url.replace('alo.rs//','alo.rs/') return url.replace('alo.rs//', 'alo.rs/')

45
recipes/alt_om_herning.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2011, Rasmus Lauritsen <rasmus at lauritsen.info>' __copyright__ = '2011, Rasmus Lauritsen <rasmus at lauritsen.info>'
''' '''
aoh.dk aoh.dk
@ -6,38 +6,35 @@ aoh.dk
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class aoh_dk(BasicNewsRecipe): class aoh_dk(BasicNewsRecipe):
title = 'Alt om Herning' title = 'Alt om Herning'
__author__ = 'Rasmus Lauritsen' __author__ = 'Rasmus Lauritsen'
description = 'Nyheder fra Herning om omegn' description = 'Nyheder fra Herning om omegn'
publisher = 'Mediehuset Herning Folkeblad' publisher = 'Mediehuset Herning Folkeblad'
category = 'news, local, Denmark' category = 'news, local, Denmark'
oldest_article = 14 oldest_article = 14
max_articles_per_feed = 50 max_articles_per_feed = 50
no_stylesheets = True no_stylesheets = True
delay = 1 delay = 1
encoding = 'utf8' encoding = 'utf8'
use_embedded_content = False use_embedded_content = False
language = 'da' language = 'da'
extra_css = """ body{font-family: Verdana,Arial,sans-serif } extra_css = """ body{font-family: Verdana,Arial,sans-serif }
img{margin-bottom: 0.4em} img{margin-bottom: 0.4em}
.txtContent,.stamp{font-size: small} .txtContent,.stamp{font-size: small}
""" """
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
}
feeds = [(u'All news', u'http://aoh.dk/rss.xml')] feeds = [(u'All news', u'http://aoh.dk/rss.xml')]
keep_only_tags = [ keep_only_tags = [
dict(name='h1') dict(name='h1'), dict(name='span', attrs={'class': ['frontpage_body']})
,dict(name='span', attrs={'class':['frontpage_body']}) ]
]
remove_tags = [ remove_tags = [
dict(name=['object','link']) dict(name=['object', 'link'])
] ]

19
recipes/alternet.recipe
View File

@ -1,34 +1,35 @@
from calibre.ptempfile import PersistentTemporaryFile from calibre.ptempfile import PersistentTemporaryFile
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Alternet(BasicNewsRecipe): class Alternet(BasicNewsRecipe):
title = u'Alternet' title = u'Alternet'
__author__= 'rty' __author__ = 'rty'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
publisher = 'alternet.org' publisher = 'alternet.org'
category = 'News, Magazine' category = 'News, Magazine'
description = 'News magazine and online community' description = 'News magazine and online community'
feeds = [ feeds = [
(u'Front Page', u'http://feeds.feedblitz.com/alternet') (u'Front Page', u'http://feeds.feedblitz.com/alternet')
] ]
remove_attributes = ['width', 'align','cellspacing'] remove_attributes = ['width', 'align', 'cellspacing']
remove_javascript = True remove_javascript = True
use_embedded_content = True use_embedded_content = True
no_stylesheets = True no_stylesheets = True
language = 'en' language = 'en'
encoding = 'UTF-8' encoding = 'UTF-8'
temp_files = [] temp_files = []
articles_are_obfuscated = True articles_are_obfuscated = True
def get_article_url(self, article): def get_article_url(self, article):
return article.get('link', None) return article.get('link', None)
def get_obfuscated_article(self, url): def get_obfuscated_article(self, url):
br = self.get_browser() br = self.get_browser()
br.open(url) br.open(url)
response = br.follow_link(url_regex = r'/printversion/[0-9]+', nr = 0) response = br.follow_link(url_regex=r'/printversion/[0-9]+', nr=0)
html = response.read() html = response.read()
self.temp_files.append(PersistentTemporaryFile('_fa.html')) self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(html) self.temp_files[-1].write(html)

103
recipes/am730.recipe
View File

@ -1,6 +1,6 @@
# vim:fileencoding=UTF-8 # vim:fileencoding=UTF-8
from __future__ import unicode_literals from __future__ import unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2013, Eddie Lau' __copyright__ = '2013, Eddie Lau'
__Date__ = '' __Date__ = ''
@ -12,7 +12,9 @@ Change Log:
from calibre import (__appname__, force_unicode, strftime) from calibre import (__appname__, force_unicode, strftime)
from calibre.utils.date import now as nowf from calibre.utils.date import now as nowf
import os, datetime, re import os
import datetime
import re
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
from contextlib import nested from contextlib import nested
from calibre.ebooks.BeautifulSoup import BeautifulSoup from calibre.ebooks.BeautifulSoup import BeautifulSoup
@ -21,10 +23,11 @@ from calibre.ebooks.metadata.toc import TOC
from calibre.ebooks.metadata import MetaInformation from calibre.ebooks.metadata import MetaInformation
from calibre.utils.localization import canonicalize_lang from calibre.utils.localization import canonicalize_lang
class AppleDaily(BasicNewsRecipe): class AppleDaily(BasicNewsRecipe):
title = u'AM730' title = u'AM730'
__author__ = 'Eddie Lau' __author__ = 'Eddie Lau'
publisher = 'AM730' publisher = 'AM730'
oldest_article = 1 oldest_article = 1
max_articles_per_feed = 100 max_articles_per_feed = 100
auto_cleanup = False auto_cleanup = False
@ -35,46 +38,46 @@ class AppleDaily(BasicNewsRecipe):
use_embedded_content = False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
description = 'http://www.am730.com.hk' description = 'http://www.am730.com.hk'
category = 'Chinese, News, Hong Kong' category = 'Chinese, News, Hong Kong'
masthead_url = 'http://www.am730.com.hk/images/logo.jpg' masthead_url = 'http://www.am730.com.hk/images/logo.jpg'
extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 20px; margin-bottom: 20px; max-height:70%;} div[id=articleHeader] {font-size:200%; text-align:left; font-weight:bold;} li {font-size:50%; margin-left:auto; margin-right:auto;}' extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 20px; margin-bottom: 20px; max-height:70%;} div[id=articleHeader] {font-size:200%; text-align:left; font-weight:bold;} li {font-size:50%; margin-left:auto; margin-right:auto;}' # noqa
keep_only_tags = [dict(name='h2', attrs={'class':'printTopic'}), keep_only_tags = [dict(name='h2', attrs={'class': 'printTopic'}),
dict(name='div', attrs={'id':'article_content'}), dict(name='div', attrs={'id': 'article_content'}),
dict(name='div', attrs={'id':'slider'})] dict(name='div', attrs={'id': 'slider'})]
remove_tags = [dict(name='img', attrs={'src':'images/am730_article_logo.jpg'}), remove_tags = [dict(name='img', attrs={'src': 'images/am730_article_logo.jpg'}),
dict(name='img', attrs={'src':'images/am_endmark.gif'})] dict(name='img', attrs={'src': 'images/am_endmark.gif'})]
def get_dtlocal(self): def get_dtlocal(self):
dt_utc = datetime.datetime.utcnow() dt_utc = datetime.datetime.utcnow()
# convert UTC to local hk time - at HKT 6am, all news are available # convert UTC to local hk time - at HKT 6am, all news are available
return dt_utc + datetime.timedelta(8.0/24) - datetime.timedelta(6.0/24) return dt_utc + datetime.timedelta(8.0 / 24) - datetime.timedelta(6.0 / 24)
def get_fetchdate(self): def get_fetchdate(self):
if __Date__ <> '': if __Date__ != '':
return __Date__ return __Date__
else: else:
return self.get_dtlocal().strftime("%Y%m%d") return self.get_dtlocal().strftime("%Y%m%d")
def get_fetchformatteddate(self): def get_fetchformatteddate(self):
if __Date__ <> '': if __Date__ != '':
return __Date__[0:4]+'-'+__Date__[4:6]+'-'+__Date__[6:8] return __Date__[0:4] + '-' + __Date__[4:6] + '-' + __Date__[6:8]
else: else:
return self.get_dtlocal().strftime("%Y-%m-%d") return self.get_dtlocal().strftime("%Y-%m-%d")
def get_fetchyear(self): def get_fetchyear(self):
if __Date__ <> '': if __Date__ != '':
return __Date__[0:4] return __Date__[0:4]
else: else:
return self.get_dtlocal().strftime("%Y") return self.get_dtlocal().strftime("%Y")
def get_fetchmonth(self): def get_fetchmonth(self):
if __Date__ <> '': if __Date__ != '':
return __Date__[4:6] return __Date__[4:6]
else: else:
return self.get_dtlocal().strftime("%m") return self.get_dtlocal().strftime("%m")
def get_fetchday(self): def get_fetchday(self):
if __Date__ <> '': if __Date__ != '':
return __Date__[6:8] return __Date__[6:8]
else: else:
return self.get_dtlocal().strftime("%d") return self.get_dtlocal().strftime("%d")
@ -85,7 +88,9 @@ class AppleDaily(BasicNewsRecipe):
def get_cover_url(self): def get_cover_url(self):
soup = self.index_to_soup('http://www.am730.com.hk') soup = self.index_to_soup('http://www.am730.com.hk')
cover = 'http://www.am730.com.hk/' + soup.find(attrs={'id':'mini_news_img'}).find('img').get('src', False) cover = 'http://www.am730.com.hk/' + \
soup.find(attrs={'id': 'mini_news_img'}).find(
'img').get('src', False)
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
try: try:
br.open(cover) br.open(cover)
@ -97,7 +102,7 @@ class AppleDaily(BasicNewsRecipe):
if first and hasattr(self, 'add_toc_thumbnail'): if first and hasattr(self, 'add_toc_thumbnail'):
picdiv = soup.find('img') picdiv = soup.find('img')
if picdiv is not None: if picdiv is not None:
self.add_toc_thumbnail(article,picdiv['src']) self.add_toc_thumbnail(article, picdiv['src'])
def parse_index(self): def parse_index(self):
feeds = [] feeds = []
@ -123,7 +128,8 @@ class AppleDaily(BasicNewsRecipe):
mi.publisher = __appname__ mi.publisher = __appname__
mi.author_sort = __appname__ mi.author_sort = __appname__
if self.publication_type: if self.publication_type:
mi.publication_type = 'periodical:'+self.publication_type+':'+self.short_title() mi.publication_type = 'periodical:' + \
self.publication_type + ':' + self.short_title()
mi.timestamp = nowf() mi.timestamp = nowf()
article_titles, aseen = [], set() article_titles, aseen = [], set()
for f in feeds: for f in feeds:
@ -136,15 +142,15 @@ class AppleDaily(BasicNewsRecipe):
if not isinstance(mi.comments, unicode): if not isinstance(mi.comments, unicode):
mi.comments = mi.comments.decode('utf-8', 'replace') mi.comments = mi.comments.decode('utf-8', 'replace')
mi.comments += ('\n\n' + _('Articles in this issue: ') + '\n' + mi.comments += ('\n\n' + _('Articles in this issue: ') + '\n' +
'\n\n'.join(article_titles)) '\n\n'.join(article_titles))
language = canonicalize_lang(self.language) language = canonicalize_lang(self.language)
if language is not None: if language is not None:
mi.language = language mi.language = language
# This one affects the pub date shown in kindle title # This one affects the pub date shown in kindle title
#mi.pubdate = nowf()
# now appears to need the time field to be > 12.00noon as well # now appears to need the time field to be > 12.00noon as well
mi.pubdate = datetime.datetime(int(self.get_fetchyear()), int(self.get_fetchmonth()), int(self.get_fetchday()), 12, 30, 0) mi.pubdate = datetime.datetime(int(self.get_fetchyear()), int(
self.get_fetchmonth()), int(self.get_fetchday()), 12, 30, 0)
opf_path = os.path.join(dir, 'index.opf') opf_path = os.path.join(dir, 'index.opf')
ncx_path = os.path.join(dir, 'index.ncx') ncx_path = os.path.join(dir, 'index.ncx')
@ -153,12 +159,14 @@ class AppleDaily(BasicNewsRecipe):
mp = getattr(self, 'masthead_path', None) mp = getattr(self, 'masthead_path', None)
if mp is not None and os.access(mp, os.R_OK): if mp is not None and os.access(mp, os.R_OK):
from calibre.ebooks.metadata.opf2 import Guide from calibre.ebooks.metadata.opf2 import Guide
ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu()) ref = Guide.Reference(os.path.basename(
self.masthead_path), os.getcwdu())
ref.type = 'masthead' ref.type = 'masthead'
ref.title = 'Masthead Image' ref.title = 'Masthead Image'
opf.guide.append(ref) opf.guide.append(ref)
manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))] manifest = [os.path.join(dir, 'feed_%d' % i)
for i in range(len(feeds))]
manifest.append(os.path.join(dir, 'index.html')) manifest.append(os.path.join(dir, 'index.html'))
manifest.append(os.path.join(dir, 'index.ncx')) manifest.append(os.path.join(dir, 'index.ncx'))
@ -167,7 +175,7 @@ class AppleDaily(BasicNewsRecipe):
if cpath is None: if cpath is None:
pf = open(os.path.join(dir, 'cover.jpg'), 'wb') pf = open(os.path.join(dir, 'cover.jpg'), 'wb')
if self.default_cover(pf): if self.default_cover(pf):
cpath = pf.name cpath = pf.name
if cpath is not None and os.access(cpath, os.R_OK): if cpath is not None and os.access(cpath, os.R_OK):
opf.cover = cpath opf.cover = cpath
manifest.append(cpath) manifest.append(cpath)
@ -189,12 +197,11 @@ class AppleDaily(BasicNewsRecipe):
self.play_order_counter = 0 self.play_order_counter = 0
self.play_order_map = {} self.play_order_map = {}
def feed_index(num, parent): def feed_index(num, parent):
f = feeds[num] f = feeds[num]
for j, a in enumerate(f): for j, a in enumerate(f):
if getattr(a, 'downloaded', False): if getattr(a, 'downloaded', False):
adir = 'feed_%d/article_%d/'%(num, j) adir = 'feed_%d/article_%d/' % (num, j)
auth = a.author auth = a.author
if not auth: if not auth:
auth = None auth = None
@ -204,16 +211,18 @@ class AppleDaily(BasicNewsRecipe):
else: else:
desc = self.description_limiter(desc) desc = self.description_limiter(desc)
tt = a.toc_thumbnail if a.toc_thumbnail else None tt = a.toc_thumbnail if a.toc_thumbnail else None
entries.append('%sindex.html'%adir) entries.append('%sindex.html' % adir)
po = self.play_order_map.get(entries[-1], None) po = self.play_order_map.get(entries[-1], None)
if po is None: if po is None:
self.play_order_counter += 1 self.play_order_counter += 1
po = self.play_order_counter po = self.play_order_counter
parent.add_item('%sindex.html'%adir, None, parent.add_item('%sindex.html' % adir, None,
a.title if a.title else _('Untitled Article'), a.title if a.title else _(
play_order=po, author=auth, 'Untitled Article'),
description=desc, toc_thumbnail=tt) play_order=po, author=auth,
last = os.path.join(self.output_dir, ('%sindex.html'%adir).replace('/', os.sep)) description=desc, toc_thumbnail=tt)
last = os.path.join(
self.output_dir, ('%sindex.html' % adir).replace('/', os.sep))
for sp in a.sub_pages: for sp in a.sub_pages:
prefix = os.path.commonprefix([opf_path, sp]) prefix = os.path.commonprefix([opf_path, sp])
relp = sp[len(prefix):] relp = sp[len(prefix):]
@ -226,12 +235,14 @@ class AppleDaily(BasicNewsRecipe):
soup = BeautifulSoup(src) soup = BeautifulSoup(src)
body = soup.find('body') body = soup.find('body')
if body is not None: if body is not None:
prefix = '/'.join('..'for i in range(2*len(re.findall(r'link\d+', last)))) prefix = '/'.join('..'for i in range(2 *
len(re.findall(r'link\d+', last))))
templ = self.navbar.generate(True, num, j, len(f), templ = self.navbar.generate(True, num, j, len(f),
not self.has_single_feed, not self.has_single_feed,
a.orig_url, __appname__, prefix=prefix, a.orig_url, __appname__, prefix=prefix,
center=self.center_navbar) center=self.center_navbar)
elem = BeautifulSoup(templ.render(doctype='xhtml').decode('utf-8')).find('div') elem = BeautifulSoup(templ.render(
doctype='xhtml').decode('utf-8')).find('div')
body.insert(len(body.contents), elem) body.insert(len(body.contents), elem)
with open(last, 'wb') as fi: with open(last, 'wb') as fi:
fi.write(unicode(soup).encode('utf-8')) fi.write(unicode(soup).encode('utf-8'))
@ -240,7 +251,7 @@ class AppleDaily(BasicNewsRecipe):
if len(feeds) > 1: if len(feeds) > 1:
for i, f in enumerate(feeds): for i, f in enumerate(feeds):
entries.append('feed_%d/index.html'%i) entries.append('feed_%d/index.html' % i)
po = self.play_order_map.get(entries[-1], None) po = self.play_order_map.get(entries[-1], None)
if po is None: if po is None:
self.play_order_counter += 1 self.play_order_counter += 1
@ -251,11 +262,11 @@ class AppleDaily(BasicNewsRecipe):
desc = getattr(f, 'description', None) desc = getattr(f, 'description', None)
if not desc: if not desc:
desc = None desc = None
feed_index(i, toc.add_item('feed_%d/index.html'%i, None, feed_index(i, toc.add_item('feed_%d/index.html' % i, None,
f.title, play_order=po, description=desc, author=auth)) f.title, play_order=po, description=desc, author=auth))
else: else:
entries.append('feed_%d/index.html'%0) entries.append('feed_%d/index.html' % 0)
feed_index(0, toc) feed_index(0, toc)
for i, p in enumerate(entries): for i, p in enumerate(entries):
@ -265,5 +276,3 @@ class AppleDaily(BasicNewsRecipe):
with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file): with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file):
opf.render(opf_file, ncx_file) opf.render(opf_file, ncx_file)

66
recipes/ambito.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008-2015, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2015, Darko Miletic <darko.miletic at gmail.com>'
''' '''
ambito.com ambito.com
@ -6,46 +6,46 @@ ambito.com
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Ambito(BasicNewsRecipe): class Ambito(BasicNewsRecipe):
title = 'Ambito.com' title = 'Ambito.com'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Ambito.com con noticias del Diario Ambito Financiero de Buenos Aires' description = 'Ambito.com con noticias del Diario Ambito Financiero de Buenos Aires'
publisher = 'Editorial Nefir S.A.' publisher = 'Editorial Nefir S.A.'
category = 'news, politics, economy, finances, Argentina' category = 'news, politics, economy, finances, Argentina'
oldest_article = 2 oldest_article = 2
no_stylesheets = True no_stylesheets = True
encoding = 'cp1252' encoding = 'cp1252'
masthead_url = 'http://www.ambito.com/img/logo.jpg' masthead_url = 'http://www.ambito.com/img/logo.jpg'
use_embedded_content = False use_embedded_content = False
remove_empty_feeds = True remove_empty_feeds = True
language = 'es_AR' language = 'es_AR'
publication_type = 'newsportal' publication_type = 'newsportal'
extra_css = """ extra_css = """
body{font-family: "Trebuchet MS",Verdana,sans-serif} body{font-family: "Trebuchet MS",Verdana,sans-serif}
.volanta{font-size: small} .volanta{font-size: small}
.t2_portada{font-size: xx-large; font-family: Georgia,serif; color: #026698} .t2_portada{font-size: xx-large; font-family: Georgia,serif; color: #026698}
""" """
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(attrs={'id':['tituloDespliegue','imgDesp','textoDespliegue']})] keep_only_tags = [
remove_tags = [dict(name=['object','link','embed','iframe','meta','link'])] dict(attrs={'id': ['tituloDespliegue', 'imgDesp', 'textoDespliegue']})]
remove_tags = [
dict(name=['object', 'link', 'embed', 'iframe', 'meta', 'link'])]
feeds = [ feeds = [
(u'Principales Noticias', u'http://www.ambito.com/rss/noticiasp.asp' )
,(u'Economia' , u'http://www.ambito.com/rss/noticias.asp?S=Econom%EDa' ) (u'Principales Noticias', u'http://www.ambito.com/rss/noticiasp.asp'),
,(u'Politica' , u'http://www.ambito.com/rss/noticias.asp?S=Pol%EDtica' ) (u'Economia', u'http://www.ambito.com/rss/noticias.asp?S=Econom%EDa'),
,(u'Informacion General' , u'http://www.ambito.com/rss/noticias.asp?S=Informaci%F3n%20General') (u'Politica', u'http://www.ambito.com/rss/noticias.asp?S=Pol%EDtica'),
,(u'Campo' , u'http://www.ambito.com/rss/noticias.asp?S=Agro' ) (u'Informacion General', u'http://www.ambito.com/rss/noticias.asp?S=Informaci%F3n%20General'),
,(u'Internacionales' , u'http://www.ambito.com/rss/noticias.asp?S=Internacionales' ) (u'Campo', u'http://www.ambito.com/rss/noticias.asp?S=Agro'),
,(u'Deportes' , u'http://www.ambito.com/rss/noticias.asp?S=Deportes' ) (u'Internacionales', u'http://www.ambito.com/rss/noticias.asp?S=Internacionales'),
,(u'Espectaculos' , u'http://www.ambito.com/rss/noticias.asp?S=Espect%E1culos' ) (u'Deportes', u'http://www.ambito.com/rss/noticias.asp?S=Deportes'),
,(u'Tecnologia' , u'http://www.ambito.com/rss/noticias.asp?S=Tecnolog%EDa' ) (u'Espectaculos', u'http://www.ambito.com/rss/noticias.asp?S=Espect%E1culos'),
,(u'Ambito Nacional' , u'http://www.ambito.com/rss/noticias.asp?S=Ambito%20Nacional' ) (u'Tecnologia', u'http://www.ambito.com/rss/noticias.asp?S=Tecnolog%EDa'),
] (u'Ambito Nacional', u'http://www.ambito.com/rss/noticias.asp?S=Ambito%20Nacional')
]

68
recipes/ambito_financiero.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
''' '''
ambito.com/diario ambito.com/diario
@ -8,22 +8,23 @@ import time
from calibre import strftime from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
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 = 'cp1252' encoding = 'cp1252'
masthead_url = 'http://www.ambito.com/diario/img/logo_af.gif' masthead_url = 'http://www.ambito.com/diario/img/logo_af.gif'
publication_type = 'newspaper' publication_type = 'newspaper'
needs_subscription = 'optional' needs_subscription = 'optional'
use_embedded_content = False use_embedded_content = False
language = 'es_AR' language = 'es_AR'
PREFIX = 'http://www.ambito.com' PREFIX = 'http://www.ambito.com'
INDEX = PREFIX + '/diario/index.asp' INDEX = PREFIX + '/diario/index.asp'
LOGIN = PREFIX + '/diario/login/entrada.asp' LOGIN = PREFIX + '/diario/login/entrada.asp'
extra_css = """ extra_css = """
body{font-family: "Trebuchet MS",Verdana,sans-serif} body{font-family: "Trebuchet MS",Verdana,sans-serif}
.volanta{font-size: small} .volanta{font-size: small}
@ -31,14 +32,12 @@ class Ambito_Financiero(BasicNewsRecipe):
""" """
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'align':'justify'})] keep_only_tags = [dict(name='div', attrs={'align': 'justify'})]
remove_tags = [dict(name=['object','link','embed','iframe','meta','link','table','img'])] remove_tags = [dict(name=['object', 'link', 'embed',
'iframe', 'meta', 'link', 'table', 'img'])]
remove_attributes = ['align'] remove_attributes = ['align']
def get_browser(self): def get_browser(self):
@ -53,7 +52,7 @@ class Ambito_Financiero(BasicNewsRecipe):
return br return br
def print_version(self, url): def print_version(self, url):
return url.replace('/diario/noticia.asp?','/noticias/imprimir.asp?') return url.replace('/diario/noticia.asp?', '/noticias/imprimir.asp?')
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
@ -61,27 +60,24 @@ class Ambito_Financiero(BasicNewsRecipe):
for item in soup.findAll('a'): for item in soup.findAll('a'):
str = item.string str = item.string
if str is None: if str is None:
str = self.tag_to_string(item) str = self.tag_to_string(item)
item.replaceWith(str) item.replaceWith(str)
return soup return soup
def parse_index(self): def parse_index(self):
soup = self.index_to_soup(self.INDEX) soup = self.index_to_soup(self.INDEX)
cover_item = soup.find('img',attrs={'class':'fotodespliegue'}) cover_item = soup.find('img', attrs={'class': 'fotodespliegue'})
if cover_item: if cover_item:
self.cover_url = self.PREFIX + cover_item['src'] self.cover_url = self.PREFIX + cover_item['src']
articles = [] articles = []
checker = [] checker = []
for feed_link in soup.findAll('a', attrs={'class':['t0_portada','t2_portada','bajada']}): for feed_link in soup.findAll('a', attrs={'class': ['t0_portada', 't2_portada', 'bajada']}):
url = self.PREFIX + feed_link['href'] url = self.PREFIX + feed_link['href']
title = self.tag_to_string(feed_link) title = self.tag_to_string(feed_link)
date = strftime("%a, %d %b %Y %H:%M:%S +0000",time.gmtime()) date = strftime("%a, %d %b %Y %H:%M:%S +0000", time.gmtime())
if url not in checker: if url not in checker:
checker.append(url) checker.append(url)
articles.append({ articles.append({
'title' :title 'title': title, 'date': date, 'url': url, 'description': u''
,'date' :date })
,'url' :url
,'description':u''
})
return [(self.title, articles)] return [(self.title, articles)]

35
recipes/american_thinker.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010, Walt Anthony <workshop.northpole at gmail.com>' __copyright__ = '2010, Walt Anthony <workshop.northpole at gmail.com>'
''' '''
www.americanthinker.com www.americanthinker.com
@ -8,37 +8,34 @@ from calibre.web.feeds.news import BasicNewsRecipe
from calibre.utils.cleantext import clean_xml_chars from calibre.utils.cleantext import clean_xml_chars
from lxml import etree from lxml import etree
class AmericanThinker(BasicNewsRecipe): class AmericanThinker(BasicNewsRecipe):
title = u'American Thinker' title = u'American Thinker'
description = "American Thinker is a daily internet publication devoted to the thoughtful exploration of issues of importance to Americans." description = "American Thinker is a daily internet publication devoted to the thoughtful exploration of issues of importance to Americans."
__author__ = 'Walt Anthony' __author__ = 'Walt Anthony'
publisher = 'Thomas Lifson' publisher = 'Thomas Lifson'
category = 'news, politics, USA' category = 'news, politics, USA'
oldest_article = 7 # days oldest_article = 7 # days
max_articles_per_feed = 50 max_articles_per_feed = 50
summary_length = 150 summary_length = 150
language = 'en' language = 'en'
ignore_duplicate_articles = {'title', 'url'} ignore_duplicate_articles = {'title', 'url'}
remove_javascript = True remove_javascript = True
auto_cleanup = True auto_cleanup = True
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'linearize_tables': True
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
, 'linearize_tables' : True
}
def preprocess_raw_html(self, raw, url): def preprocess_raw_html(self, raw, url):
root = html5lib.parse( root = html5lib.parse(
clean_xml_chars(raw), treebuilder='lxml', clean_xml_chars(raw), treebuilder='lxml',
namespaceHTMLElements=False) namespaceHTMLElements=False)
for x in root.xpath('''descendant-or-self::*[@class and contains(concat(' ', normalize-space(@class), ' '), ' article_body ') and (@class and contains(concat(' ', normalize-space(@class), ' '), ' bottom '))]'''): for x in root.xpath('''descendant-or-self::*[@class and contains(concat(' ', normalize-space(@class), ' '), ' article_body ') and (@class and contains(concat(' ', normalize-space(@class), ' '), ' bottom '))]'''): # noqa
x.getparent().remove(x) x.getparent().remove(x)
return etree.tostring(root, encoding=unicode) return etree.tostring(root, encoding=unicode)
feeds = [(u'http://feeds.feedburner.com/americanthinker'), feeds = [(u'http://feeds.feedburner.com/americanthinker'),
(u'http://feeds.feedburner.com/AmericanThinkerBlog') (u'http://feeds.feedburner.com/AmericanThinkerBlog')
] ]

23
recipes/amspec.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
''' '''
spectator.org spectator.org
@ -7,20 +7,22 @@ spectator.org
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from css_selectors import Select from css_selectors import Select
class TheAmericanSpectator(BasicNewsRecipe): class TheAmericanSpectator(BasicNewsRecipe):
title = 'The American Spectator' title = 'The American Spectator'
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal'
description = 'News from USA' description = 'News from USA'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
language = 'en' language = 'en'
auto_cleanup = True auto_cleanup = True
encoding = 'utf-8' encoding = 'utf-8'
def parse_index(self): def parse_index(self):
root = self.index_to_soup('http://spectator.org/issues/current', as_tree=True) root = self.index_to_soup(
'http://spectator.org/issues/current', as_tree=True)
select = Select(root) select = Select(root)
main = tuple(select('div#block-system-main'))[0] main = tuple(select('div#block-system-main'))[0]
feeds = [] feeds = []
@ -43,7 +45,8 @@ class TheAmericanSpectator(BasicNewsRecipe):
for x in select('div.views-field-field-short-summary', li): for x in select('div.views-field-field-short-summary', li):
desc = self.tag_to_string(x) desc = self.tag_to_string(x)
break break
articles.append({'title':title, 'url':url, 'description':desc}) articles.append(
{'title': title, 'url': url, 'description': desc})
self.log('\t', title, 'at', url) self.log('\t', title, 'at', url)
feeds.append((section_title, articles)) feeds.append((section_title, articles))
return feeds return feeds

7
recipes/an_druma_mor.recipe
View File

@ -1,12 +1,13 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AnDrumaMor(BasicNewsRecipe): class AnDrumaMor(BasicNewsRecipe):
title = u'An Druma M\xf3r' title = u'An Druma M\xf3r'
__author__ = "David O'Callaghan" __author__ = "David O'Callaghan"
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
language = 'ga' language = 'ga'
use_embedded_content = True use_embedded_content = True
feeds = [(u'Nuacht Laeth\xfail', u'http://feeds.feedburner.com/NuachtLneLaethilArAnDrumaMr')] feeds = [(u'Nuacht Laeth\xfail',
u'http://feeds.feedburner.com/NuachtLneLaethilArAnDrumaMr')]

26
recipes/anandtech.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>' __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
''' '''
@ -13,10 +13,10 @@ class anan(BasicNewsRecipe):
title = 'Anandtech' title = 'Anandtech'
description = 'comprehensive Hardware Tests' description = 'comprehensive Hardware Tests'
__author__ = 'Oliver Niesner, Armin Geller' # 2014-02-27 AGE: update __author__ = 'Oliver Niesner, Armin Geller' # 2014-02-27 AGE: update
use_embedded_content = False use_embedded_content = False
language = 'en' language = 'en'
timefmt = ' [%d %b %Y]' timefmt = ' [%d %b %Y]'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 40 max_articles_per_feed = 40
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
@ -26,17 +26,17 @@ class anan(BasicNewsRecipe):
masthead_url = 'http://www.anandtech.com/content/images/globals/printheader.png' masthead_url = 'http://www.anandtech.com/content/images/globals/printheader.png'
keep_only_tags = [ keep_only_tags = [
dict(name='section', attrs={'class':['main_cont']}), dict(name='section', attrs={'class': ['main_cont']}),
] ]
remove_tags=[ remove_tags = [
dict(name='div', attrs={'class':['print', dict(name='div', attrs={'class': ['print',
'breadcrumb_area noprint', 'breadcrumb_area noprint',
'fl-rt noprint', 'fl-rt noprint',
'blog_top_right',]}) 'blog_top_right', ]})
] ]
feeds = [('Anandtech', 'http://www.anandtech.com/rss/')] feeds = [('Anandtech', 'http://www.anandtech.com/rss/')]
def print_version(self,url): def print_version(self, url):
# return url.replace("0Cshow0C", "0Cprint0C") # 2013-09-07 AGE: update # return url.replace("0Cshow0C", "0Cprint0C") # 2013-09-07 AGE: update
return url.replace("/show/", "/print/") # 2014-02-27 AGE: update return url.replace("/show/", "/print/") # 2014-02-27 AGE: update

30
recipes/anchorage_daily.recipe
View File

@ -1,38 +1,28 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1278347258(BasicNewsRecipe): class AdvancedUserRecipe1278347258(BasicNewsRecipe):
title = u'Anchorage Daily News' title = u'Anchorage Daily News'
__author__ = 'rty' __author__ = 'rty'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
auto_cleanup = True auto_cleanup = True
feeds = [(u'Alaska News', u'http://www.adn.com/rss-feeds/feed/all'),
feeds = [(u'Alaska News', u'http://www.adn.com/rss-feeds/feed/all'), (u'Politics', u'http://www.adn.com/rss-feeds/feed/politics'),
(u'Politics', u'http://www.adn.com/rss-feeds/feed/politics'), ]
]
description = ''''Alaska's Newspaper''' description = ''''Alaska's Newspaper'''
publisher = 'http://www.adn.com' publisher = 'http://www.adn.com'
category = 'news, Alaska, Anchorage' category = 'news, Alaska, Anchorage'
language = 'en' language = 'en'
extra_css = ''' extra_css = '''
p{font-weight: normal;text-align: justify} p{font-weight: normal;text-align: justify}
''' '''
remove_javascript = True remove_javascript = True
use_embedded_content = False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
language = 'en' language = 'en'
encoding = 'utf-8' encoding = 'utf-8'
conversion_options = {'linearize_tables':True} conversion_options = {'linearize_tables': True}
masthead_url = 'http://media.adn.com/includes/assets/images/adn_logo.2.gif' masthead_url = 'http://media.adn.com/includes/assets/images/adn_logo.2.gif'
#keep_only_tags = [
#dict(name='div', attrs={'class':'left_col story_mainbar'}),
#]
#remove_tags = [
#dict(name='div', attrs={'class':'story_tools'}),
#dict(name='p', attrs={'class':'ad_label'}),
#]
#remove_tags_after = [
#dict(name='div', attrs={'class':'advertisement'}),
#]

16
recipes/android_com_pl.recipe
View File

@ -1,15 +1,17 @@
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Android_com_pl(BasicNewsRecipe): class Android_com_pl(BasicNewsRecipe):
title = u'Android.com.pl' title = u'Android.com.pl'
__author__ = 'fenuks' __author__ = 'fenuks'
description = u'Android.com.pl - to największe w Polsce centrum Android OS. Znajdziesz tu: nowości, forum, pomoc, recenzje, gry, aplikacje.' description = u'Android.com.pl - to największe w Polsce centrum Android OS. Znajdziesz tu: nowości, forum, pomoc, recenzje, gry, aplikacje.'
category = 'Android, mobile' category = 'Android, mobile'
language = 'pl' language = 'pl'
use_embedded_content = True use_embedded_content = True
cover_url = 'http://android.com.pl/wp-content/themes/android/images/logo.png' cover_url = 'http://android.com.pl/wp-content/themes/android/images/logo.png'
oldest_article = 8 oldest_article = 8
max_articles_per_feed = 100 max_articles_per_feed = 100
preprocess_regexps = [(re.compile(ur'<p>.{,1}</p>', re.DOTALL), lambda match: '')] preprocess_regexps = [
feeds = [(u'Android', u'http://android.com.pl/feed/')] (re.compile(ur'<p>.{,1}</p>', re.DOTALL), lambda match: '')]
feeds = [(u'Android', u'http://android.com.pl/feed/')]

110
recipes/animal_politico.recipe
View File

@ -3,43 +3,43 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1290663986(BasicNewsRecipe): class AdvancedUserRecipe1290663986(BasicNewsRecipe):
title = u'Animal Pol\u00EDtico' title = u'Animal Pol\u00EDtico'
publisher = u'Animal Pol\u00EDtico' publisher = u'Animal Pol\u00EDtico'
category = u'News, Mexico' category = u'News, Mexico'
description = u'Noticias Pol\u00EDticas' description = u'Noticias Pol\u00EDticas'
__author__ = 'leamsi' __author__ = 'leamsi'
masthead_url = 'http://www.animalpolitico.com/wp-content/themes/animal_mu/images/logo.png' masthead_url = 'http://www.animalpolitico.com/wp-content/themes/animal_mu/images/logo.png'
oldest_article = 1 oldest_article = 1
max_articles_per_feed = 100 max_articles_per_feed = 100
language = 'es_MX' language = 'es_MX'
#feeds = [(u'Animal Politico', u'http://www.animalpolitico.com/feed/')]
remove_tags_before = dict(name='div', id='main') remove_tags_before = dict(name='div', id='main')
remove_tags = [dict(name='div', attrs={'class':'fb-like-button'})] remove_tags = [dict(name='div', attrs={'class': 'fb-like-button'})]
keep_only_tags = [dict(name='h1', attrs={'class':'entry-title'}), keep_only_tags = [dict(name='h1', attrs={'class': 'entry-title'}),
dict(name='div', attrs={'class':'entry-content'})] dict(name='div', attrs={'class': 'entry-content'})]
remove_javascript = True remove_javascript = True
INDEX = 'http://www.animalpolitico.com/' INDEX = 'http://www.animalpolitico.com/'
def generic_parse(self, soup): def generic_parse(self, soup):
articles = [] articles = []
for entry in soup.findAll(lambda tag: tag.name == 'li' and tag.has_key('class') and tag['class'].find('hentry') != -1): #soup.findAll('li', 'hentry'): # soup.findAll('li', 'hentry'):
article_url = entry.a['href'] + '?print=yes' for entry in soup.findAll(lambda tag: tag.name == 'li' and tag.has_key('class') and tag['class'].find('hentry') != -1): # noqa
article_title= entry.find('h3', 'entry-title') article_url = entry.a['href'] + '?print=yes'
article_title= self.tag_to_string(article_title) article_title = entry.find('h3', 'entry-title')
article_title = self.tag_to_string(article_title)
article_date = entry.find('span', 'the-time') article_date = entry.find('span', 'the-time')
article_date = self.tag_to_string(article_date) article_date = self.tag_to_string(article_date)
article_desc = self.tag_to_string(entry.find('p')) article_desc = self.tag_to_string(entry.find('p'))
#print 'Article:',article_title, article_date,article_url # print 'Article:',article_title, article_date,article_url
#print entry['class'] # print entry['class']
articles.append({'title' : article_title, articles.append({'title': article_title,
'date' : article_date, 'date': article_date,
'description' : article_desc, 'description': article_desc,
'url' : article_url}) 'url': article_url})
# Avoid including the multimedia stuff. # Avoid including the multimedia stuff.
if entry['class'].find('last') != -1: if entry['class'].find('last') != -1:
break break
@ -48,56 +48,57 @@ class AdvancedUserRecipe1290663986(BasicNewsRecipe):
def plumaje_parse(self, soup): def plumaje_parse(self, soup):
articles = [] articles = []
blogs_soup = soup.find(lambda tag: tag.name == 'ul' and tag.has_key('class') and tag['class'].find('bloglist-fecha') != -1) blogs_soup = soup.find(lambda tag: tag.name == 'ul' and tag.has_key('class') and tag['class'].find('bloglist-fecha') != -1) # noqa
for entry in blogs_soup.findAll('li'): for entry in blogs_soup.findAll('li'):
article_title = entry.p article_title = entry.p
article_url = article_title.a['href'] + '?print=yes' article_url = article_title.a['href'] + '?print=yes'
article_date = article_title.nextSibling article_date = article_title.nextSibling
article_title = self.tag_to_string(article_title) article_title = self.tag_to_string(article_title)
article_date = self.tag_to_string(article_date).replace(u'Last Updated: ', '') article_date = self.tag_to_string(
article_desc = self.tag_to_string(entry.find('h4')) article_date).replace(u'Last Updated: ', '')
article_desc = self.tag_to_string(entry.find('h4'))
#print 'Article:',article_title, article_date,article_url # print 'Article:',article_title, article_date,article_url
articles.append({'title' : article_title, articles.append({'title': article_title,
'date' : article_date, 'date': article_date,
'description' : article_desc, 'description': article_desc,
'url' : article_url}) 'url': article_url})
return articles return articles
def boca_parse(self, soup): def boca_parse(self, soup):
articles = [] articles = []
for entry in soup.findAll(lambda tag: tag.name == 'div' and tag.has_key('class') and tag['class'].find('hentry') != -1): #soup.findAll('li', 'hentry'): # soup.findAll('li', 'hentry'):
article_title= entry.find('h2', 'entry-title') for entry in soup.findAll(lambda tag: tag.name == 'div' and tag.has_key('class') and tag['class'].find('hentry') != -1): # noqa
article_url = article_title.a['href'] + '?print=yes' article_title = entry.find('h2', 'entry-title')
article_title= self.tag_to_string(article_title) article_url = article_title.a['href'] + '?print=yes'
article_title = self.tag_to_string(article_title)
article_date = entry.find('span', 'entry-date') article_date = entry.find('span', 'entry-date')
article_date = self.tag_to_string(article_date) article_date = self.tag_to_string(article_date)
article_desc = self.tag_to_string(entry.find('div', 'entry-content')) article_desc = self.tag_to_string(
entry.find('div', 'entry-content'))
#print 'Article:',article_title, article_date,article_url # print 'Article:',article_title, article_date,article_url
#print entry['class'] # print entry['class']
articles.append({'title' : article_title, articles.append({'title': article_title,
'date' : article_date, 'date': article_date,
'description' : article_desc, 'description': article_desc,
'url' : article_url}) 'url': article_url})
# Avoid including the multimedia stuff. # Avoid including the multimedia stuff.
if entry['class'].find('last') != -1: if entry['class'].find('last') != -1:
break break
return articles return articles
def parse_index(self): def parse_index(self):
gobierno_soup = self.index_to_soup(self.INDEX+'gobierno/') gobierno_soup = self.index_to_soup(self.INDEX + 'gobierno/')
congreso_soup = self.index_to_soup(self.INDEX+'congreso/') congreso_soup = self.index_to_soup(self.INDEX + 'congreso/')
seguridad_soup = self.index_to_soup(self.INDEX+'seguridad/') seguridad_soup = self.index_to_soup(self.INDEX + 'seguridad/')
comunidad_soup = self.index_to_soup(self.INDEX+'comunidad/') comunidad_soup = self.index_to_soup(self.INDEX + 'comunidad/')
plumaje_soup = self.index_to_soup(self.INDEX+'plumaje/') plumaje_soup = self.index_to_soup(self.INDEX + 'plumaje/')
la_boca_del_lobo_soup = self.index_to_soup(self.INDEX+'category/la-boca-del-lobo/') la_boca_del_lobo_soup = self.index_to_soup(
self.INDEX + 'category/la-boca-del-lobo/')
gobierno_articles = self.generic_parse(gobierno_soup) gobierno_articles = self.generic_parse(gobierno_soup)
congreso_articles = self.generic_parse(congreso_soup) congreso_articles = self.generic_parse(congreso_soup)
@ -106,6 +107,5 @@ class AdvancedUserRecipe1290663986(BasicNewsRecipe):
plumaje_articles = self.plumaje_parse(plumaje_soup) plumaje_articles = self.plumaje_parse(plumaje_soup)
la_boca_del_lobo_articles = self.boca_parse(la_boca_del_lobo_soup) la_boca_del_lobo_articles = self.boca_parse(la_boca_del_lobo_soup)
return [(u'Gobierno', gobierno_articles), (u'Congreso', congreso_articles), (u'Seguridad', seguridad_articles),
return [ (u'Gobierno', gobierno_articles), (u'Congreso', congreso_articles), (u'Seguridad', seguridad_articles), (u'Comunidad', comunidad_articles), (u'Plumaje', plumaje_articles), (u'La Boca del Lobo', la_boca_del_lobo_articles), ]
(u'Comunidad', comunidad_articles), (u'Plumaje', plumaje_articles), (u'La Boca del Lobo', la_boca_del_lobo_articles), ]

53
recipes/antyweb.recipe
View File

@ -1,6 +1,7 @@
#-*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AntywebRecipe(BasicNewsRecipe): class AntywebRecipe(BasicNewsRecipe):
encoding = 'utf-8' encoding = 'utf-8'
__license__ = 'GPL v3' __license__ = 'GPL v3'
@ -10,38 +11,40 @@ class AntywebRecipe(BasicNewsRecipe):
title = u'Antyweb' title = u'Antyweb'
category = u'News' category = u'News'
description = u'Blog o internecie i nowych technologiach' description = u'Blog o internecie i nowych technologiach'
cover_url='' cover_url = ''
remove_empty_feeds= True remove_empty_feeds = True
auto_cleanup = False auto_cleanup = False
no_stylesheets=True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
remove_javascript = True remove_javascript = True
simultaneous_downloads = 10 simultaneous_downloads = 10
ignore_duplicate_articles = {'title', 'url'} # zignoruj zduplikowane artykuły o takich samych tytułach LUB adresach # zignoruj zduplikowane artykuły o takich samych tytułach LUB adresach
scale_news_images =True ignore_duplicate_articles = {'title', 'url'}
conversion_options = { 'tags' : u'news, aplikacje mobilne, Android, iOS, Windows Phone ', scale_news_images = True
'smarten_punctuation' : True, conversion_options = {'tags': u'news, aplikacje mobilne, Android, iOS, Windows Phone ',
'publisher' : 'AntyWeb' 'smarten_punctuation': True,
} # opcje konwersji. 'publisher': 'AntyWeb'
} # opcje konwersji.
keep_only_tags=[] keep_only_tags = []
keep_only_tags.append(dict(name = 'h1')) keep_only_tags.append(dict(name='h1'))
keep_only_tags.append(dict(name = 'article', attrs = {'class' : 'article'})) keep_only_tags.append(dict(name='article', attrs={'class': 'article'}))
remove_tags =[] remove_tags = []
remove_tags.append(dict(name = 'div', attrs = {'class' : 'ac-footer group'})) remove_tags.append(dict(name='div', attrs={'class': 'ac-footer group'}))
feeds = [
(u'News', 'http://feeds.feedburner.com/antyweb'),
(u'Felietony', 'http://feeds.feedburner.com/AntywebFelietony'),
(u'Apple', 'http://feeds.feedburner.com/AntywebApple'),
(u'Gry', 'http://feeds.feedburner.com/AntywebGry'),
(u'Mobile', 'http://feeds.feedburner.com/AntywebMobile'),
(u'Startups', 'http://feeds.feedburner.com/AntywebStartups'),
(u'Google', 'http://feeds.feedburner.com/AntywebGoogle'),
(u'Microsoft', 'http://feeds.feedburner.com/AntywebMicrosoft')
]
feeds = [
(u'News', 'http://feeds.feedburner.com/antyweb'),
(u'Felietony', 'http://feeds.feedburner.com/AntywebFelietony'),
(u'Apple', 'http://feeds.feedburner.com/AntywebApple'),
(u'Gry', 'http://feeds.feedburner.com/AntywebGry'),
(u'Mobile', 'http://feeds.feedburner.com/AntywebMobile'),
(u'Startups', 'http://feeds.feedburner.com/AntywebStartups'),
(u'Google', 'http://feeds.feedburner.com/AntywebGoogle'),
(u'Microsoft', 'http://feeds.feedburner.com/AntywebMicrosoft')
]
def preprocess_html(self, soup): def preprocess_html(self, soup):
for alink in soup.findAll('a'): for alink in soup.findAll('a'):
if alink.string is not None: if alink.string is not None:

23
recipes/ap.recipe
View File

@ -6,21 +6,23 @@ class AssociatedPress(BasicNewsRecipe):
title = u'Associated Press' title = u'Associated Press'
description = 'Global news' description = 'Global news'
__author__ = 'Krittika Goyal' __author__ = 'Krittika Goyal'
use_embedded_content = False use_embedded_content = False
language = 'en' language = 'en'
no_stylesheets = True no_stylesheets = True
conversion_options = { conversion_options = {
'linearize_tables' : True 'linearize_tables': True
} }
keep_only_tags = {'name':'table', 'attrs':{'class':lambda x: x and 'ap-story-table' in x.split()}} keep_only_tags = {'name': 'table', 'attrs': {
'class': lambda x: x and 'ap-story-table' in x.split()}}
remove_tags = [ remove_tags = [
{'class':['ap-mediabox-table']}, {'class': ['ap-mediabox-table']},
{'name':'img', 'src':lambda x: x and '//analytics.' in x}, {'name': 'img', 'src': lambda x: x and '//analytics.' in x},
] ]
def parse_index(self): def parse_index(self):
feeds = [] feeds = []
fronts = ('HOME', 'US', 'WORLD', 'BUSINESS', 'TECHNOLOGY', 'SPORTS', 'ENTERTAINMENT', 'HEALTH', 'SCIENCE', 'POLITICS') fronts = ('HOME', 'US', 'WORLD', 'BUSINESS', 'TECHNOLOGY',
'SPORTS', 'ENTERTAINMENT', 'HEALTH', 'SCIENCE', 'POLITICS')
for front in fronts: for front in fronts:
feeds.append([front.capitalize(), self.parse_section(front)]) feeds.append([front.capitalize(), self.parse_section(front)])
feeds[0][0] = 'Top Stories' feeds[0][0] = 'Top Stories'
@ -28,19 +30,20 @@ class AssociatedPress(BasicNewsRecipe):
def parse_section(self, front): def parse_section(self, front):
self.log('Processing section:', front) self.log('Processing section:', front)
soup = self.index_to_soup('http://hosted.ap.org/dynamic/fronts/%s?SITE=AP' % front) soup = self.index_to_soup(
'http://hosted.ap.org/dynamic/fronts/%s?SITE=AP' % front)
articles = [] articles = []
for x in soup.findAll('p', attrs={'class':['ap-newsbriefitem-p', 'ap-topheadlineitem-p']}): for x in soup.findAll('p', attrs={'class': ['ap-newsbriefitem-p', 'ap-topheadlineitem-p']}):
a = x.find('a', href=True) a = x.find('a', href=True)
title = self.tag_to_string(a) title = self.tag_to_string(a)
url = "http://hosted.ap.org" + a['href'] url = "http://hosted.ap.org" + a['href']
p = x.find(attrs={'class':'topheadlinebody'}) p = x.find(attrs={'class': 'topheadlinebody'})
desc = '' desc = ''
if p is not None: if p is not None:
desc = self.tag_to_string(p) desc = self.tag_to_string(p)
self.log('\tFound article:', title, '\n\t\t', desc) self.log('\tFound article:', title, '\n\t\t', desc)
articles.append({'title':title, 'url':url}) articles.append({'title': title, 'url': url})
self.log('\n\n') self.log('\n\n')

55
recipes/apcom.recipe
View File

@ -1,8 +1,8 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'Gabriele Marini, based on Darko Miletic' __author__ = 'Gabriele Marini, based on Darko Miletic'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
description = 'Italian daily newspaper - 14-05-2010' description = 'Italian daily newspaper - 14-05-2010'
''' '''
http://www.apcom.NET/ http://www.apcom.NET/
@ -10,39 +10,38 @@ http://www.apcom.NET/
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Apcom(BasicNewsRecipe): class Apcom(BasicNewsRecipe):
__author__ = 'Marini Gabriele' __author__ = 'Marini Gabriele'
description = 'Italian daily newspaper' description = 'Italian daily newspaper'
cover_url = 'http://www.apcom.net/img/logoAP.gif' cover_url = 'http://www.apcom.net/img/logoAP.gif'
title = u'Apcom' title = u'Apcom'
publisher = 'TM News S.p.A.' publisher = 'TM News S.p.A.'
category = 'News, politics, culture, economy, general interest' category = 'News, politics, culture, economy, general interest'
language = 'it' language = 'it'
timefmt = '[%a, %d %b, %Y]' timefmt = '[%a, %d %b, %Y]'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 50 max_articles_per_feed = 50
use_embedded_content = False use_embedded_content = False
recursion = 100 recursion = 100
no_stylesheets = True no_stylesheets = True
conversion_options = {'linearize_tables':True} conversion_options = {'linearize_tables': True}
remove_javascript = True remove_javascript = True
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'id':'ag_center'}) dict(name='div', attrs={'id': 'ag_center'})
] ]
feeds = [ feeds = [
(u'Globale', u'http://www.apcom.net/rss/globale.xml '), (u'Globale', u'http://www.apcom.net/rss/globale.xml '),
(u'Politica', u'http://www.apcom.net/rss/politica.xml'), (u'Politica', u'http://www.apcom.net/rss/politica.xml'),
(u'Cronaca', u'http://www.apcom.net/rss/cronaca.xml'), (u'Cronaca', u'http://www.apcom.net/rss/cronaca.xml'),
(u'Econimia', u'http://www.apcom.net/rss/economia.xml'), (u'Econimia', u'http://www.apcom.net/rss/economia.xml'),
(u'Esteri', u'http://www.apcom.net/rss/esteri.xml'), (u'Esteri', u'http://www.apcom.net/rss/esteri.xml'),
(u'Cultura', u'http://www.apcom.net/rss/cultura.xml'), (u'Cultura', u'http://www.apcom.net/rss/cultura.xml'),
(u'Sport', u'http://www.apcom.net/rss/sport.xml') (u'Sport', u'http://www.apcom.net/rss/sport.xml')
] ]

21
recipes/apod.recipe
View File

@ -1,28 +1,30 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class APOD(BasicNewsRecipe): class APOD(BasicNewsRecipe):
title = u'Astronomy Picture of the Day' title = u'Astronomy Picture of the Day'
__author__ = 'Starson17' __author__ = 'Starson17'
description = 'Astronomy Pictures' description = 'Astronomy Pictures'
language = 'en' language = 'en'
use_embedded_content = False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
cover_url = 'http://apod.nasa.gov/apod/image/1003/m78_torregrosa.jpg' cover_url = 'http://apod.nasa.gov/apod/image/1003/m78_torregrosa.jpg'
remove_javascript = True remove_javascript = True
recursions = 0 recursions = 0
oldest_article = 14 oldest_article = 14
remove_attributes = ['onmouseover', 'onmouseout'] remove_attributes = ['onmouseover', 'onmouseout']
feeds = [ feeds = [
(u'Astronomy Picture of the Day', u'http://apod.nasa.gov/apod.rss') (u'Astronomy Picture of the Day', u'http://apod.nasa.gov/apod.rss')
] ]
extra_css = ''' extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;} h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;} h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;} p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;} body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
''' '''
def postprocess_html(self, soup, first_fetch): def postprocess_html(self, soup, first_fetch):
center_tags = soup.findAll(['center']) center_tags = soup.findAll(['center'])
p_tags = soup.findAll(['p']) p_tags = soup.findAll(['p'])
@ -35,4 +37,3 @@ class APOD(BasicNewsRecipe):
for tag in last2_p: for tag in last2_p:
tag.extract() tag.extract()
return soup return soup

17
recipes/app_funds.recipe
View File

@ -9,18 +9,19 @@ appfunds.blogspot.com
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class app_funds(BasicNewsRecipe): class app_funds(BasicNewsRecipe):
title = u'APP Funds' title = u'APP Funds'
__author__ = 'teepel <teepel44@gmail.com>' __author__ = 'teepel <teepel44@gmail.com>'
language = 'pl' language = 'pl'
description ='Blog inwestora dla inwestorów i oszczędzających' description = 'Blog inwestora dla inwestorów i oszczędzających'
INDEX='http://appfunds.blogspot.com' INDEX = 'http://appfunds.blogspot.com'
remove_empty_feeds= True remove_empty_feeds = True
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
simultaneous_downloads = 5 simultaneous_downloads = 5
remove_javascript=True remove_javascript = True
no_stylesheets=True no_stylesheets = True
auto_cleanup = True auto_cleanup = True
feeds = [(u'blog', u'http://feeds.feedburner.com/blogspot/etVI')] feeds = [(u'blog', u'http://feeds.feedburner.com/blogspot/etVI')]

107
recipes/apple_daily.recipe
View File

@ -1,12 +1,14 @@
# vim:fileencoding=UTF-8 # vim:fileencoding=UTF-8
from __future__ import unicode_literals from __future__ import unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2013-2015, Eddie Lau' __copyright__ = '2013-2015, Eddie Lau'
__Date__ = '' __Date__ = ''
from calibre import (__appname__, force_unicode, strftime) from calibre import (__appname__, force_unicode, strftime)
from calibre.utils.date import now as nowf from calibre.utils.date import now as nowf
import os, datetime, re import os
import datetime
import re
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
from contextlib import nested from contextlib import nested
from calibre.ebooks.BeautifulSoup import BeautifulSoup from calibre.ebooks.BeautifulSoup import BeautifulSoup
@ -15,10 +17,11 @@ from calibre.ebooks.metadata.toc import TOC
from calibre.ebooks.metadata import MetaInformation from calibre.ebooks.metadata import MetaInformation
from calibre.utils.localization import canonicalize_lang from calibre.utils.localization import canonicalize_lang
class AppleDaily(BasicNewsRecipe): class AppleDaily(BasicNewsRecipe):
title = u'蘋果日報 (香港)' title = u'蘋果日報 (香港)'
__author__ = 'Eddie Lau' __author__ = 'Eddie Lau'
publisher = '蘋果日報' publisher = '蘋果日報'
oldest_article = 1 oldest_article = 1
max_articles_per_feed = 100 max_articles_per_feed = 100
auto_cleanup = False auto_cleanup = False
@ -26,48 +29,48 @@ class AppleDaily(BasicNewsRecipe):
encoding = 'utf-8' encoding = 'utf-8'
auto_cleanup = False auto_cleanup = False
remove_javascript = True remove_javascript = True
use_embedded_content = False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
description = 'http://hkm.appledaily.com/' description = 'http://hkm.appledaily.com/'
category = 'Chinese, News, Hong Kong' category = 'Chinese, News, Hong Kong'
masthead_url = 'http://upload.wikimedia.org/wikipedia/zh/c/cf/AppleDailyLogo1.png' masthead_url = 'http://upload.wikimedia.org/wikipedia/zh/c/cf/AppleDailyLogo1.png'
extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px; max-height:90%;} h1 {font-size:200%; text-align:left; font-weight:bold;} p[class=video-caption] {font-size:50%; margin-left:auto; margin-right:auto;}' extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px; max-height:90%;} h1 {font-size:200%; text-align:left; font-weight:bold;} p[class=video-caption] {font-size:50%; margin-left:auto; margin-right:auto;}' # noqa
keep_only_tags = [dict(name='div', attrs={'id':'content-article'})] keep_only_tags = [dict(name='div', attrs={'id': 'content-article'})]
remove_tags = [dict(name='div', attrs={'class':'prev-next-btn'}), remove_tags = [dict(name='div', attrs={'class': 'prev-next-btn'}),
dict(name='p', attrs={'class':'next'})] dict(name='p', attrs={'class': 'next'})]
def get_dtlocal(self): def get_dtlocal(self):
dt_utc = datetime.datetime.utcnow() dt_utc = datetime.datetime.utcnow()
# convert UTC to local hk time - at HKT 6am, all news are available # convert UTC to local hk time - at HKT 6am, all news are available
return dt_utc + datetime.timedelta(8.0/24) - datetime.timedelta(6.0/24) return dt_utc + datetime.timedelta(8.0 / 24) - datetime.timedelta(6.0 / 24)
def get_fetchdate(self): def get_fetchdate(self):
if __Date__ <> '': if __Date__ != '':
return __Date__ return __Date__
else: else:
return self.get_dtlocal().strftime("%Y%m%d") return self.get_dtlocal().strftime("%Y%m%d")
def get_fetchformatteddate(self): def get_fetchformatteddate(self):
if __Date__ <> '': if __Date__ != '':
return __Date__[0:4]+'-'+__Date__[4:6]+'-'+__Date__[6:8] return __Date__[0:4] + '-' + __Date__[4:6] + '-' + __Date__[6:8]
else: else:
return self.get_dtlocal().strftime("%Y-%m-%d") return self.get_dtlocal().strftime("%Y-%m-%d")
def get_fetchyear(self): def get_fetchyear(self):
if __Date__ <> '': if __Date__ != '':
return __Date__[0:4] return __Date__[0:4]
else: else:
return self.get_dtlocal().strftime("%Y") return self.get_dtlocal().strftime("%Y")
def get_fetchmonth(self): def get_fetchmonth(self):
if __Date__ <> '': if __Date__ != '':
return __Date__[4:6] return __Date__[4:6]
else: else:
return self.get_dtlocal().strftime("%m") return self.get_dtlocal().strftime("%m")
def get_fetchday(self): def get_fetchday(self):
if __Date__ <> '': if __Date__ != '':
return __Date__[6:8] return __Date__[6:8]
else: else:
return self.get_dtlocal().strftime("%d") return self.get_dtlocal().strftime("%d")
@ -78,7 +81,7 @@ class AppleDaily(BasicNewsRecipe):
def get_cover_url(self): def get_cover_url(self):
soup = self.index_to_soup('http://hkm.appledaily.com/') soup = self.index_to_soup('http://hkm.appledaily.com/')
cover = soup.find(attrs={'class':'top-news'}).get('src', False) cover = soup.find(attrs={'class': 'top-news'}).get('src', False)
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
try: try:
br.open(cover) br.open(cover)
@ -90,12 +93,12 @@ class AppleDaily(BasicNewsRecipe):
if first and hasattr(self, 'add_toc_thumbnail'): if first and hasattr(self, 'add_toc_thumbnail'):
picdiv = soup.find('img') picdiv = soup.find('img')
if picdiv is not None: if picdiv is not None:
self.add_toc_thumbnail(article,picdiv['src']) self.add_toc_thumbnail(article, picdiv['src'])
def parse_index(self): def parse_index(self):
feeds = [] feeds = []
soup = self.index_to_soup('http://hkm.appledaily.com/') soup = self.index_to_soup('http://hkm.appledaily.com/')
ul = soup.find(attrs={'class':'menu'}) ul = soup.find(attrs={'class': 'menu'})
sectionList = [] sectionList = []
for li in ul.findAll('li'): for li in ul.findAll('li'):
relativea = li.find('a', href=True).get('href', False) relativea = li.find('a', href=True).get('href', False)
@ -111,13 +114,14 @@ class AppleDaily(BasicNewsRecipe):
def parse_section(self, url): def parse_section(self, url):
soup = self.index_to_soup(url) soup = self.index_to_soup(url)
ul = soup.find(attrs={'class':'list'}) ul = soup.find(attrs={'class': 'list'})
current_articles = [] current_articles = []
for li in ul.findAll('li'): for li in ul.findAll('li'):
a = li.find('a', href=True) a = li.find('a', href=True)
title = li.find('p', text=True).strip() title = li.find('p', text=True).strip()
if a is not None: if a is not None:
current_articles.append({'title': title, 'url':'http://hkm.appledaily.com/' + a.get('href', False)}) current_articles.append(
{'title': title, 'url': 'http://hkm.appledaily.com/' + a.get('href', False)})
pass pass
return current_articles return current_articles
@ -131,7 +135,8 @@ class AppleDaily(BasicNewsRecipe):
mi.publisher = __appname__ mi.publisher = __appname__
mi.author_sort = __appname__ mi.author_sort = __appname__
if self.publication_type: if self.publication_type:
mi.publication_type = 'periodical:'+self.publication_type+':'+self.short_title() mi.publication_type = 'periodical:' + \
self.publication_type + ':' + self.short_title()
mi.timestamp = nowf() mi.timestamp = nowf()
article_titles, aseen = [], set() article_titles, aseen = [], set()
for f in feeds: for f in feeds:
@ -144,15 +149,16 @@ class AppleDaily(BasicNewsRecipe):
if not isinstance(mi.comments, unicode): if not isinstance(mi.comments, unicode):
mi.comments = mi.comments.decode('utf-8', 'replace') mi.comments = mi.comments.decode('utf-8', 'replace')
mi.comments += ('\n\n' + _('Articles in this issue: ') + '\n' + mi.comments += ('\n\n' + _('Articles in this issue: ') + '\n' +
'\n\n'.join(article_titles)) '\n\n'.join(article_titles))
language = canonicalize_lang(self.language) language = canonicalize_lang(self.language)
if language is not None: if language is not None:
mi.language = language mi.language = language
# This one affects the pub date shown in kindle title # This one affects the pub date shown in kindle title
#mi.pubdate = nowf() # mi.pubdate = nowf()
# now appears to need the time field to be > 12.00noon as well # now appears to need the time field to be > 12.00noon as well
mi.pubdate = datetime.datetime(int(self.get_fetchyear()), int(self.get_fetchmonth()), int(self.get_fetchday()), 12, 30, 0) mi.pubdate = datetime.datetime(int(self.get_fetchyear()), int(
self.get_fetchmonth()), int(self.get_fetchday()), 12, 30, 0)
opf_path = os.path.join(dir, 'index.opf') opf_path = os.path.join(dir, 'index.opf')
ncx_path = os.path.join(dir, 'index.ncx') ncx_path = os.path.join(dir, 'index.ncx')
@ -161,12 +167,14 @@ class AppleDaily(BasicNewsRecipe):
mp = getattr(self, 'masthead_path', None) mp = getattr(self, 'masthead_path', None)
if mp is not None and os.access(mp, os.R_OK): if mp is not None and os.access(mp, os.R_OK):
from calibre.ebooks.metadata.opf2 import Guide from calibre.ebooks.metadata.opf2 import Guide
ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu()) ref = Guide.Reference(os.path.basename(
self.masthead_path), os.getcwdu())
ref.type = 'masthead' ref.type = 'masthead'
ref.title = 'Masthead Image' ref.title = 'Masthead Image'
opf.guide.append(ref) opf.guide.append(ref)
manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))] manifest = [os.path.join(dir, 'feed_%d' % i)
for i in range(len(feeds))]
manifest.append(os.path.join(dir, 'index.html')) manifest.append(os.path.join(dir, 'index.html'))
manifest.append(os.path.join(dir, 'index.ncx')) manifest.append(os.path.join(dir, 'index.ncx'))
@ -175,7 +183,7 @@ class AppleDaily(BasicNewsRecipe):
if cpath is None: if cpath is None:
pf = open(os.path.join(dir, 'cover.jpg'), 'wb') pf = open(os.path.join(dir, 'cover.jpg'), 'wb')
if self.default_cover(pf): if self.default_cover(pf):
cpath = pf.name cpath = pf.name
if cpath is not None and os.access(cpath, os.R_OK): if cpath is not None and os.access(cpath, os.R_OK):
opf.cover = cpath opf.cover = cpath
manifest.append(cpath) manifest.append(cpath)
@ -197,12 +205,11 @@ class AppleDaily(BasicNewsRecipe):
self.play_order_counter = 0 self.play_order_counter = 0
self.play_order_map = {} self.play_order_map = {}
def feed_index(num, parent): def feed_index(num, parent):
f = feeds[num] f = feeds[num]
for j, a in enumerate(f): for j, a in enumerate(f):
if getattr(a, 'downloaded', False): if getattr(a, 'downloaded', False):
adir = 'feed_%d/article_%d/'%(num, j) adir = 'feed_%d/article_%d/' % (num, j)
auth = a.author auth = a.author
if not auth: if not auth:
auth = None auth = None
@ -212,16 +219,18 @@ class AppleDaily(BasicNewsRecipe):
else: else:
desc = self.description_limiter(desc) desc = self.description_limiter(desc)
tt = a.toc_thumbnail if a.toc_thumbnail else None tt = a.toc_thumbnail if a.toc_thumbnail else None
entries.append('%sindex.html'%adir) entries.append('%sindex.html' % adir)
po = self.play_order_map.get(entries[-1], None) po = self.play_order_map.get(entries[-1], None)
if po is None: if po is None:
self.play_order_counter += 1 self.play_order_counter += 1
po = self.play_order_counter po = self.play_order_counter
parent.add_item('%sindex.html'%adir, None, parent.add_item('%sindex.html' % adir, None,
a.title if a.title else _('Untitled Article'), a.title if a.title else _(
play_order=po, author=auth, 'Untitled Article'),
description=desc, toc_thumbnail=tt) play_order=po, author=auth,
last = os.path.join(self.output_dir, ('%sindex.html'%adir).replace('/', os.sep)) description=desc, toc_thumbnail=tt)
last = os.path.join(
self.output_dir, ('%sindex.html' % adir).replace('/', os.sep))
for sp in a.sub_pages: for sp in a.sub_pages:
prefix = os.path.commonprefix([opf_path, sp]) prefix = os.path.commonprefix([opf_path, sp])
relp = sp[len(prefix):] relp = sp[len(prefix):]
@ -234,12 +243,14 @@ class AppleDaily(BasicNewsRecipe):
soup = BeautifulSoup(src) soup = BeautifulSoup(src)
body = soup.find('body') body = soup.find('body')
if body is not None: if body is not None:
prefix = '/'.join('..'for i in range(2*len(re.findall(r'link\d+', last)))) prefix = '/'.join('..'for i in range(2 *
len(re.findall(r'link\d+', last))))
templ = self.navbar.generate(True, num, j, len(f), templ = self.navbar.generate(True, num, j, len(f),
not self.has_single_feed, not self.has_single_feed,
a.orig_url, __appname__, prefix=prefix, a.orig_url, __appname__, prefix=prefix,
center=self.center_navbar) center=self.center_navbar)
elem = BeautifulSoup(templ.render(doctype='xhtml').decode('utf-8')).find('div') elem = BeautifulSoup(templ.render(
doctype='xhtml').decode('utf-8')).find('div')
body.insert(len(body.contents), elem) body.insert(len(body.contents), elem)
with open(last, 'wb') as fi: with open(last, 'wb') as fi:
fi.write(unicode(soup).encode('utf-8')) fi.write(unicode(soup).encode('utf-8'))
@ -248,7 +259,7 @@ class AppleDaily(BasicNewsRecipe):
if len(feeds) > 1: if len(feeds) > 1:
for i, f in enumerate(feeds): for i, f in enumerate(feeds):
entries.append('feed_%d/index.html'%i) entries.append('feed_%d/index.html' % i)
po = self.play_order_map.get(entries[-1], None) po = self.play_order_map.get(entries[-1], None)
if po is None: if po is None:
self.play_order_counter += 1 self.play_order_counter += 1
@ -259,11 +270,11 @@ class AppleDaily(BasicNewsRecipe):
desc = getattr(f, 'description', None) desc = getattr(f, 'description', None)
if not desc: if not desc:
desc = None desc = None
feed_index(i, toc.add_item('feed_%d/index.html'%i, None, feed_index(i, toc.add_item('feed_%d/index.html' % i, None,
f.title, play_order=po, description=desc, author=auth)) f.title, play_order=po, description=desc, author=auth))
else: else:
entries.append('feed_%d/index.html'%0) entries.append('feed_%d/index.html' % 0)
feed_index(0, toc) feed_index(0, toc)
for i, p in enumerate(entries): for i, p in enumerate(entries):
@ -273,5 +284,3 @@ class AppleDaily(BasicNewsRecipe):
with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file): with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file):
opf.render(opf_file, ncx_file) opf.render(opf_file, ncx_file)

15
recipes/appledaily_tw.recipe
View File

@ -34,12 +34,12 @@ class AppledailyTW(BasicNewsRecipe):
{'name': 'hr'} {'name': 'hr'}
] ]
conversion_options = { conversion_options = {
'title' : title, 'title': title,
'comments' : description, 'comments': description,
'tags' : category, 'tags': category,
'language' : language, 'language': language,
'publisher' : publisher, 'publisher': publisher,
'authors' : publisher, 'authors': publisher,
'linearize_tables': True 'linearize_tables': True
} }
feeds = [ feeds = [
@ -105,5 +105,6 @@ class AppledailyTW(BasicNewsRecipe):
def preprocess_raw_html(self, raw_html, url): def preprocess_raw_html(self, raw_html, url):
raw_html = re.sub(ur'<a href=".*?<br><br>.*?<\/a>', '', raw_html) raw_html = re.sub(ur'<a href=".*?<br><br>.*?<\/a>', '', raw_html)
raw_html = re.sub(ur'<title>(.*?)[\s]+\|.*<\/title>', '<title>\1<\/title>', raw_html) raw_html = re.sub(
ur'<title>(.*?)[\s]+\|.*<\/title>', '<title>\1<\/title>', raw_html)
return raw_html return raw_html

27
recipes/applefobia.recipe
View File

@ -2,21 +2,22 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class BasicUserRecipe1395137685(BasicNewsRecipe): class BasicUserRecipe1395137685(BasicNewsRecipe):
title = u'Applefobia' title = u'Applefobia'
__author__ = 'koliberek' __author__ = 'koliberek'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
auto_cleanup = True auto_cleanup = True
language = 'pl' language = 'pl'
remove_empty_feeds = True remove_empty_feeds = True
remove_javascript = True remove_javascript = True
conversion_options = { conversion_options = {
'tags' : u'newsy, Apple, humor', 'tags': u'newsy, Apple, humor',
'smarten_punctuation' : True, 'smarten_punctuation': True,
'authors' : 'Ogrodnik January', 'authors': 'Ogrodnik January',
'publisher' : 'Blogspot.pl' 'publisher': 'Blogspot.pl'
} }
reverse_article_order = True reverse_article_order = True
feeds = [(u'Aktualne', u'http://applefobia.blogspot.com/feeds/posts/default')] feeds = [(u'Aktualne', u'http://applefobia.blogspot.com/feeds/posts/default')]

22
recipes/aprospect.recipe
View File

@ -1,22 +1,20 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AmericanProspect(BasicNewsRecipe): class AmericanProspect(BasicNewsRecipe):
title = u'American Prospect' title = u'American Prospect'
__author__ = u'Michael Heinz, a.peter' __author__ = u'Michael Heinz, a.peter'
version = 2 version = 2
oldest_article = 30 oldest_article = 30
language = 'en' language = 'en'
max_articles_per_feed = 100 max_articles_per_feed = 100
recursions = 0 recursions = 0
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
#keep_only_tags = [dict(name='div', attrs={'class':'pad_10L10R'})]
#remove_tags = [dict(name='form'), dict(name='div', attrs={'class':['bkt_caption','sharebox noprint','badgebox']})]
use_embedded_content = False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
auto_cleanup = True auto_cleanup = True
feeds = [(u'Articles', u'feed://www.prospect.org/articles_rss.jsp')] feeds = [(u'Articles', u'feed://www.prospect.org/articles_rss.jsp')]

18
recipes/ara_info.recipe
View File

@ -1,19 +1,25 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = 'Ruben Pollan <meskio@sindominio.net>' __copyright__ = 'Ruben Pollan <meskio@sindominio.net>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1335656316(BasicNewsRecipe): class AdvancedUserRecipe1335656316(BasicNewsRecipe):
title = u'AraInfo.org' title = u'AraInfo.org'
__author__ = 'Ruben Pollan' __author__ = 'Ruben Pollan'
description = 'Regional newspaper from Aragon' description = 'Regional newspaper from Aragon'
language = 'es' language = 'es'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
auto_cleanup = True auto_cleanup = True
cover_url = u'http://arainfo.org/wordpress/wp-content/uploads/2011/10/logo-web_alta.jpg' cover_url = u'http://arainfo.org/wordpress/wp-content/uploads/2011/10/logo-web_alta.jpg'
feeds = [(u'Movimientos', u'http://arainfo.org/category/movimientos/feed/'), (u'Econom\xeda', u'http://arainfo.org/category/economia/feed/'), (u'Ecolog\xeda', u'http://arainfo.org/category/ecologia/feed/'), (u'Culturas', u'http://arainfo.org/category/culturas/feed/'), (u'Altavoz', u'http://arainfo.org/category/altavoz/feed/')] feeds = [
(u'Movimientos', u'http://arainfo.org/category/movimientos/feed/'),
(u'Econom\xeda', u'http://arainfo.org/category/economia/feed/'),
(u'Ecolog\xeda', u'http://arainfo.org/category/ecologia/feed/'),
(u'Culturas', u'http://arainfo.org/category/culturas/feed/'),
(u'Altavoz', u'http://arainfo.org/category/altavoz/feed/')]

107
recipes/arabian_business.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
''' '''
www.arabianbusiness.com www.arabianbusiness.com
@ -6,21 +6,21 @@ www.arabianbusiness.com
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Arabian_Business(BasicNewsRecipe): class Arabian_Business(BasicNewsRecipe):
title = 'Arabian Business' title = 'Arabian Business'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Comprehensive Guide to Middle East Business & Gulf Industry News including,Banking & Finance,Construction,Energy,Media & Marketing,Real Estate,Transportation,Travel,Technology,Politics,Healthcare,Lifestyle,Jobs & UAE guide.Top Gulf & Dubai Business News.' description = 'Comprehensive Guide to Middle East Business & Gulf Industry News including,Banking & Finance,Construction,Energy,Media & Marketing,Real Estate,Transportation,Travel,Technology,Politics,Healthcare,Lifestyle,Jobs & UAE guide.Top Gulf & Dubai Business News.' # noqa
publisher = 'Arabian Business Publishing Ltd.' publisher = 'Arabian Business Publishing Ltd.'
category = 'ArabianBusiness.com,Arab Business News,Middle East Business News,Middle East Business,Arab Media News,Industry Events,Middle East Industry News,Arab Business Industry,Dubai Business News,Financial News,UAE Business News,Middle East Press Releases,Gulf News,Arab News,GCC Business News,Banking Finance,Media Marketing,Construction,Oil Gas,Retail,Transportation,Travel Hospitality,Photos,Videos,Life Style,Fashion,United Arab Emirates,UAE,Dubai,Sharjah,Abu Dhabi,Qatar,KSA,Saudi Arabia,Bahrain,Kuwait,Oman,Europe,South Asia,America,Asia,news' oldest_article = 2
oldest_article = 2
max_articles_per_feed = 200 max_articles_per_feed = 200
no_stylesheets = True no_stylesheets = True
encoding = 'utf8' encoding = 'utf8'
use_embedded_content = False use_embedded_content = False
language = 'en' language = 'en'
remove_empty_feeds = True remove_empty_feeds = True
publication_type = 'newsportal' publication_type = 'newsportal'
masthead_url = 'http://www.arabianbusiness.com/skins/ab.main/gfx/arabianbusiness_logo_sm.gif' masthead_url = 'http://www.arabianbusiness.com/skins/ab.main/gfx/arabianbusiness_logo_sm.gif'
extra_css = """ extra_css = """
body{font-family: Georgia,serif } body{font-family: Georgia,serif }
img{margin-bottom: 0.4em; margin-top: 0.4em; display:block} img{margin-bottom: 0.4em; margin-top: 0.4em; display:block}
@ -29,49 +29,46 @@ class Arabian_Business(BasicNewsRecipe):
""" """
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
}
remove_tags_before=dict(attrs={'id':'article-title'}) remove_tags_before = dict(attrs={'id': 'article-title'})
remove_tags = [ remove_tags = [
dict(name=['meta','link','base','iframe','embed','object']) dict(name=['meta', 'link', 'base', 'iframe', 'embed', 'object']), dict(
,dict(attrs={'class':'printfooter'}) attrs={'class': 'printfooter'})
] ]
remove_attributes=['lang'] remove_attributes = ['lang']
feeds = [ feeds = [
(u'Africa' , u'http://www.arabianbusiness.com/world/Africa/?service=rss' )
,(u'Americas' , u'http://www.arabianbusiness.com/world/americas/?service=rss' ) (u'Africa', u'http://www.arabianbusiness.com/world/Africa/?service=rss'),
,(u'Asia Pacific' , u'http://www.arabianbusiness.com/world/asia-pacific/?service=rss' ) (u'Americas', u'http://www.arabianbusiness.com/world/americas/?service=rss'),
,(u'Europe' , u'http://www.arabianbusiness.com/world/europe/?service=rss' ) (u'Asia Pacific', u'http://www.arabianbusiness.com/world/asia-pacific/?service=rss'),
,(u'Middle East' , u'http://www.arabianbusiness.com/world/middle-east/?service=rss' ) (u'Europe', u'http://www.arabianbusiness.com/world/europe/?service=rss'),
,(u'South Asia' , u'http://www.arabianbusiness.com/world/south-asia/?service=rss' ) (u'Middle East', u'http://www.arabianbusiness.com/world/middle-east/?service=rss'),
,(u'Banking & Finance', u'http://www.arabianbusiness.com/industries/banking-finance/?service=rss' ) (u'South Asia', u'http://www.arabianbusiness.com/world/south-asia/?service=rss'),
,(u'Construction' , u'http://www.arabianbusiness.com/industries/construction/?service=rss' ) (u'Banking & Finance', u'http://www.arabianbusiness.com/industries/banking-finance/?service=rss'),
,(u'Education' , u'http://www.arabianbusiness.com/industries/education/?service=rss' ) (u'Construction', u'http://www.arabianbusiness.com/industries/construction/?service=rss'),
,(u'Energy' , u'http://www.arabianbusiness.com/industries/energy/?service=rss' ) (u'Education', u'http://www.arabianbusiness.com/industries/education/?service=rss'),
,(u'Healthcare' , u'http://www.arabianbusiness.com/industries/healthcare/?service=rss' ) (u'Energy', u'http://www.arabianbusiness.com/industries/energy/?service=rss'),
,(u'Media' , u'http://www.arabianbusiness.com/industries/media/?service=rss' ) (u'Healthcare', u'http://www.arabianbusiness.com/industries/healthcare/?service=rss'),
,(u'Real Estate' , u'http://www.arabianbusiness.com/industries/real-estate/?service=rss' ) (u'Media', u'http://www.arabianbusiness.com/industries/media/?service=rss'),
,(u'Retail' , u'http://www.arabianbusiness.com/industries/retail/?service=rss' ) (u'Real Estate', u'http://www.arabianbusiness.com/industries/real-estate/?service=rss'),
,(u'Technology' , u'http://www.arabianbusiness.com/industries/technology/?service=rss' ) (u'Retail', u'http://www.arabianbusiness.com/industries/retail/?service=rss'),
,(u'Transport' , u'http://www.arabianbusiness.com/industries/transport/?service=rss' ) (u'Technology', u'http://www.arabianbusiness.com/industries/technology/?service=rss'),
,(u'Travel' , u'http://www.arabianbusiness.com/industries/travel-hospitality/?service=rss') (u'Transport', u'http://www.arabianbusiness.com/industries/transport/?service=rss'),
,(u'Equities' , u'http://www.arabianbusiness.com/markets/equities/?service=rss' ) (u'Travel', u'http://www.arabianbusiness.com/industries/travel-hospitality/?service=rss'),
,(u'Commodities' , u'http://www.arabianbusiness.com/markets/commodities/?service=rss' ) (u'Equities', u'http://www.arabianbusiness.com/markets/equities/?service=rss'),
,(u'Currencies' , u'http://www.arabianbusiness.com/markets/currencies/?service=rss' ) (u'Commodities', u'http://www.arabianbusiness.com/markets/commodities/?service=rss'),
,(u'Market Data' , u'http://www.arabianbusiness.com/markets/market-data/?service=rss' ) (u'Currencies', u'http://www.arabianbusiness.com/markets/currencies/?service=rss'),
,(u'Comment' , u'http://www.arabianbusiness.com/opinion/comment/?service=rss' ) (u'Market Data', u'http://www.arabianbusiness.com/markets/market-data/?service=rss'),
,(u'Think Tank' , u'http://www.arabianbusiness.com/opinion/think-tank/?service=rss' ) (u'Comment', u'http://www.arabianbusiness.com/opinion/comment/?service=rss'),
,(u'Arts' , u'http://www.arabianbusiness.com/lifestyle/arts/?service=rss' ) (u'Think Tank', u'http://www.arabianbusiness.com/opinion/think-tank/?service=rss'),
,(u'Cars' , u'http://www.arabianbusiness.com/lifestyle/cars/?service=rss' ) (u'Arts', u'http://www.arabianbusiness.com/lifestyle/arts/?service=rss'),
,(u'Food' , u'http://www.arabianbusiness.com/lifestyle/food/?service=rss' ) (u'Cars', u'http://www.arabianbusiness.com/lifestyle/cars/?service=rss'),
,(u'Sport' , u'http://www.arabianbusiness.com/lifestyle/sport/?service=rss' ) (u'Food', u'http://www.arabianbusiness.com/lifestyle/food/?service=rss'),
] (u'Sport', u'http://www.arabianbusiness.com/lifestyle/sport/?service=rss')
]
def print_version(self, url): def print_version(self, url):
return url + '?service=printer&page=' return url + '?service=printer&page='
@ -81,6 +78,6 @@ class Arabian_Business(BasicNewsRecipe):
del item['style'] del item['style']
for alink in soup.findAll('a'): for alink in soup.findAll('a'):
if alink.string is not None: if alink.string is not None:
tstr = alink.string tstr = alink.string
alink.replaceWith(tstr) alink.replaceWith(tstr)
return soup return soup

48
recipes/arbetaren.recipe
View File

@ -1,34 +1,32 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Arbetaren_SE(BasicNewsRecipe): class Arbetaren_SE(BasicNewsRecipe):
title = u'Arbetaren' title = u'Arbetaren'
__author__ = 'Joakim Lindskog' __author__ = 'Joakim Lindskog'
description = 'Nyheter fr\xc3\xa5n Arbetaren' description = 'Nyheter fr\xc3\xa5n Arbetaren'
publisher = 'Arbetaren' publisher = 'Arbetaren'
category = 'news, politics, socialism, Sweden' category = 'news, politics, socialism, Sweden'
oldest_article = 7 oldest_article = 7
delay = 1 delay = 1
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
encoding = 'utf-8' encoding = 'utf-8'
language = 'sv' language = 'sv'
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'id':'article'})] keep_only_tags = [dict(name='div', attrs={'id': 'article'})]
remove_tags_before = dict(name='div', attrs={'id':'article'}) remove_tags_before = dict(name='div', attrs={'id': 'article'})
remove_tags_after = dict(name='p',attrs={'id':'byline'}) remove_tags_after = dict(name='p', attrs={'id': 'byline'})
remove_tags = [ remove_tags = [
dict(name=['object','link','base']), dict(name=['object', 'link', 'base']),
dict(name='p', attrs={'class':'print'}), dict(name='p', attrs={'class': 'print'}),
dict(name='a', attrs={'class':'addthis_button_compact'}), dict(name='a', attrs={'class': 'addthis_button_compact'}),
dict(name='script') dict(name='script')
] ]
feeds = [(u'Nyheter', u'http://www.arbetaren.se/rss/arbetaren.rss?rev=123')] feeds = [(u'Nyheter', u'http://www.arbetaren.se/rss/arbetaren.rss?rev=123')]

20
recipes/arcadia.recipe
View File

@ -3,16 +3,17 @@
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
import re import re
class Arcadia_BBS(BasicNewsRecipe): class Arcadia_BBS(BasicNewsRecipe):
title = u'Arcadia' title = u'Arcadia'
__author__ = 'Masahiro Hasegawa' __author__ = 'Masahiro Hasegawa'
language = 'ja' language = 'ja'
encoding = 'utf8' encoding = 'utf8'
filter_regexps = [r'ad\.jp\.ap\.valuecommerce.com',] filter_regexps = [r'ad\.jp\.ap\.valuecommerce.com', ]
timefmt = '[%Y/%m/%d]' timefmt = '[%Y/%m/%d]'
remove_tags_before = dict(name='a', attrs={'name':'kiji'}) remove_tags_before = dict(name='a', attrs={'name': 'kiji'})
sid_list = [] #some sotory id sid_list = [] # some sotory id
def parse_index(self): def parse_index(self):
result = [] result = []
@ -21,15 +22,12 @@ class Arcadia_BBS(BasicNewsRecipe):
soup = self.index_to_soup( soup = self.index_to_soup(
'http://www.mai-net.net/bbs/sst/sst.php?act=dump&all=%d' 'http://www.mai-net.net/bbs/sst/sst.php?act=dump&all=%d'
% sid) % sid)
sec = soup.findAll('a', attrs={'href':re.compile(r'.*?kiji')}) sec = soup.findAll('a', attrs={'href': re.compile(r'.*?kiji')})
for s in sec[:-2]: for s in sec[:-2]:
s_result.append(dict(title=s.string, s_result.append(dict(title=s.string,
url="http://www.mai-net.net" + s['href'], url="http://www.mai-net.net" + s['href'],
date=s.parent.parent.parent.findAll('td')[3].string[:-6], date=s.parent.parent.parent.findAll('td')[
description='', content='')) 3].string[:-6],
description='', content=''))
result.append((s_result[0]['title'], s_result)) result.append((s_result[0]['title'], s_result))
return result return result

53
recipes/arcamax.recipe
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = 'Copyright 2010 Starson17' __copyright__ = 'Copyright 2010 Starson17'
''' '''
www.arcamax.com www.arcamax.com
@ -10,30 +10,29 @@ import os
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ptempfile import PersistentTemporaryDirectory from calibre.ptempfile import PersistentTemporaryDirectory
class Arcamax(BasicNewsRecipe): class Arcamax(BasicNewsRecipe):
title = 'Arcamax' title = 'Arcamax'
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal'
description = u'Family Friendly Comics - Customize for more days/comics: Defaults to 7 days, 25 comics - 20 general, 5 editorial.' description = u'Family Friendly Comics - Customize for more days/comics: Defaults to 7 days, 25 comics - 20 general, 5 editorial.'
category = 'news, comics' category = 'news, comics'
language = 'en' language = 'en'
use_embedded_content= False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
cover_url = 'http://www.arcamax.com/images/pub/amuse/leftcol/zits.jpg' cover_url = 'http://www.arcamax.com/images/pub/amuse/leftcol/zits.jpg'
# ###### USER PREFERENCES - SET COMICS AND NUMBER OF COMICS TO RETRIEVE ######## # ###### USER PREFERENCES - SET COMICS AND NUMBER OF COMICS TO RETRIEVE ##
num_comics_to_get = 7 num_comics_to_get = 7
# CHOOSE COMIC STRIPS BELOW - REMOVE COMMENT '# ' FROM IN FRONT OF DESIRED STRIPS # CHOOSE COMIC STRIPS BELOW - REMOVE COMMENT '# ' FROM IN FRONT OF DESIRED
# STRIPS
conversion_options = {'linearize_tables' : True conversion_options = {'linearize_tables': True, 'comment': description, 'tags': category, 'language': language
, 'comment' : description }
, 'tags' : category
, 'language' : language
}
keep_only_tags = [ keep_only_tags = [
dict(name='header', attrs={'class':'fn-content-header bluelabel'}), dict(name='header', attrs={'class': 'fn-content-header bluelabel'}),
dict(name='figure', attrs={'class':['comic']}), dict(name='figure', attrs={'class': ['comic']}),
] ]
def parse_index(self): def parse_index(self):
@ -93,18 +92,22 @@ class Arcamax(BasicNewsRecipe):
num -= 1 num -= 1
raw = self.index_to_soup(url, raw=True) raw = self.index_to_soup(url, raw=True)
self.panel_counter += 1 self.panel_counter += 1
path = os.path.join(self.panel_tdir, '%d.html' % self.panel_counter) path = os.path.join(self.panel_tdir, '%d.html' %
self.panel_counter)
with open(path, 'wb') as f: with open(path, 'wb') as f:
f.write(raw) f.write(raw)
soup = self.index_to_soup(raw) soup = self.index_to_soup(raw)
a = soup.find(name='a', attrs={'class':['prev']}) a = soup.find(name='a', attrs={'class': ['prev']})
prev_page_url = 'http://www.arcamax.com' + a['href'] prev_page_url = 'http://www.arcamax.com' + a['href']
title = self.tag_to_string(soup.find('title')).partition('|')[0].strip() title = self.tag_to_string(
soup.find('title')).partition('|')[0].strip()
if 'for' not in title.split(): if 'for' not in title.split():
title = title + ' for today' title = title + ' for today'
date = self.tag_to_string(soup.find(name='span', attrs={'class':['cur']})) date = self.tag_to_string(
soup.find(name='span', attrs={'class': ['cur']}))
self.log('\tFound:', title, 'at:', url) self.log('\tFound:', title, 'at:', url)
current_articles.append({'title': title, 'url':'file://' + path , 'description':'', 'date': date}) current_articles.append(
{'title': title, 'url': 'file://' + path, 'description': '', 'date': date})
if self.test and len(current_articles) >= self.test[1]: if self.test and len(current_articles) >= self.test[1]:
break break
url = prev_page_url url = prev_page_url

34
recipes/archeowiesci.recipe
View File

@ -1,33 +1,35 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Archeowiesci(BasicNewsRecipe): class Archeowiesci(BasicNewsRecipe):
title = u'Archeowieści' title = u'Archeowieści'
__author__ = 'fenuks' __author__ = 'fenuks'
category = 'archeology' category = 'archeology'
language = 'pl' language = 'pl'
description = u'Z pasją o przeszłości' description = u'Z pasją o przeszłości'
cover_url='http://archeowiesci.pl/wp-content/uploads/2011/05/Archeowiesci2-115x115.jpg' cover_url = 'http://archeowiesci.pl/wp-content/uploads/2011/05/Archeowiesci2-115x115.jpg'
oldest_article = 7 oldest_article = 7
needs_subscription='optional' needs_subscription = 'optional'
max_articles_per_feed = 100 max_articles_per_feed = 100
auto_cleanup = True auto_cleanup = True
remove_tags=[dict(name='span', attrs={'class':['post-ratings', 'post-ratings-loading']})] remove_tags = [
feeds = [(u'Archeowieści', u'http://archeowiesci.pl/feed/')] dict(name='span', attrs={'class': ['post-ratings', 'post-ratings-loading']})]
feeds = [(u'Archeowieści', u'http://archeowiesci.pl/feed/')]
def parse_feeds (self): def parse_feeds(self):
feeds = BasicNewsRecipe.parse_feeds(self) feeds = BasicNewsRecipe.parse_feeds(self)
for feed in feeds: for feed in feeds:
for article in feed.articles[:]: for article in feed.articles[:]:
if self.username is None and 'subskrypcja' in article.title: if self.username is None and 'subskrypcja' in article.title:
feed.articles.remove(article) feed.articles.remove(article)
return feeds return feeds
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None: if self.username is not None and self.password is not None:
br.open('http://archeowiesci.pl/wp-login.php') br.open('http://archeowiesci.pl/wp-login.php')
br.select_form(name='loginform') br.select_form(name='loginform')
br['log'] = self.username br['log'] = self.username
br['pwd'] = self.password br['pwd'] = self.password
br.submit() br.submit()
return br return br

108
recipes/argnoticias.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2013, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2013, Darko Miletic <darko.miletic at gmail.com>'
''' '''
@ -10,87 +10,85 @@ import time
from calibre import strftime from calibre import strftime
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class ArgNoticias(BasicNewsRecipe): class ArgNoticias(BasicNewsRecipe):
title = 'ARG Noticias' title = 'ARG Noticias'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Ultimas noticias de Argentina' description = 'Ultimas noticias de Argentina'
publisher = 'ARG Noticias' publisher = 'ARG Noticias'
category = 'news, politics, Argentina' category = 'news, politics, Argentina'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
encoding = 'utf-8' encoding = 'utf-8'
use_embedded_content = False use_embedded_content = False
masthead_url = 'http://www.argnoticias.com/images/arg-logo-footer.png' masthead_url = 'http://www.argnoticias.com/images/arg-logo-footer.png'
language = 'es_AR' language = 'es_AR'
publication_type = 'newsportal' publication_type = 'newsportal'
INDEX = 'http://www.argnoticias.com' INDEX = 'http://www.argnoticias.com'
extra_css = '' extra_css = ''
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher': publisher
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'class':['itemHeader','itemBody','itemAuthorBlock']})] keep_only_tags = [
dict(name='div', attrs={'class': ['itemHeader', 'itemBody', 'itemAuthorBlock']})]
remove_tags = [ remove_tags = [
dict(name=['object','link','base','iframe']), dict(name=['object', 'link', 'base', 'iframe']),
dict(name='div', attrs={'class':['b2jsocial_parent','itemSocialSharing']}) dict(name='div', attrs={
] 'class': ['b2jsocial_parent', 'itemSocialSharing']})
]
feeds = [ feeds = [
(u'Politica' , u'http://www.argnoticias.com/index.php/politica' )
,(u'Economia' , u'http://www.argnoticias.com/index.php/economia' ) (u'Politica', u'http://www.argnoticias.com/index.php/politica'),
,(u'Sociedad' , u'http://www.argnoticias.com/index.php/sociedad' ) (u'Economia', u'http://www.argnoticias.com/index.php/economia'),
,(u'Mundo' , u'http://www.argnoticias.com/index.php/mundo' ) (u'Sociedad', u'http://www.argnoticias.com/index.php/sociedad'),
,(u'Deportes' , u'http://www.argnoticias.com/index.php/deportes' ) (u'Mundo', u'http://www.argnoticias.com/index.php/mundo'),
,(u'Espectaculos', u'http://www.argnoticias.com/index.php/espectaculos') (u'Deportes', u'http://www.argnoticias.com/index.php/deportes'),
,(u'Tendencias' , u'http://www.argnoticias.com/index.php/tendencias' ) (u'Espectaculos', u'http://www.argnoticias.com/index.php/espectaculos'),
] (u'Tendencias', u'http://www.argnoticias.com/index.php/tendencias')
]
def parse_index(self): def parse_index(self):
totalfeeds = [] totalfeeds = []
lfeeds = self.get_feeds() lfeeds = self.get_feeds()
checker = [] checker = []
for feedobj in lfeeds: for feedobj in lfeeds:
feedtitle, feedurl = feedobj feedtitle, feedurl = feedobj
self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl)) self.report_progress(0, _('Fetching feed') + ' %s...' %
(feedtitle if feedtitle else feedurl))
articles = [] articles = []
soup = self.index_to_soup(feedurl) soup = self.index_to_soup(feedurl)
for item in soup.findAll('div', attrs={'class':'Nota'}): for item in soup.findAll('div', attrs={'class': 'Nota'}):
atag = item.find('a', attrs={'class':'moduleItemTitle'}) atag = item.find('a', attrs={'class': 'moduleItemTitle'})
ptag = item.find('div', attrs={'class':'moduleItemIntrotext'}) ptag = item.find('div', attrs={'class': 'moduleItemIntrotext'})
url = self.INDEX + atag['href'] url = self.INDEX + atag['href']
title = self.tag_to_string(atag) title = self.tag_to_string(atag)
description = self.tag_to_string(ptag) description = self.tag_to_string(ptag)
date = strftime("%a, %d %b %Y %H:%M:%S +0000",time.gmtime()) date = strftime("%a, %d %b %Y %H:%M:%S +0000", time.gmtime())
if url not in checker: if url not in checker:
checker.append(url) checker.append(url)
articles.append({ articles.append({
'title' :title 'title': title, 'date': date, 'url': url, 'description': description
,'date' :date })
,'url' :url
,'description':description
})
for item in soup.findAll('li'): for item in soup.findAll('li'):
atag = item.find('a', attrs={'class':'moduleItemTitle'}) atag = item.find('a', attrs={'class': 'moduleItemTitle'})
if atag: if atag:
ptag = item.find('div', attrs={'class':'moduleItemIntrotext'}) ptag = item.find(
url = self.INDEX + atag['href'] 'div', attrs={'class': 'moduleItemIntrotext'})
title = self.tag_to_string(atag) url = self.INDEX + atag['href']
title = self.tag_to_string(atag)
description = self.tag_to_string(ptag) description = self.tag_to_string(ptag)
date = strftime("%a, %d %b %Y %H:%M:%S +0000",time.gmtime()) date = strftime(
"%a, %d %b %Y %H:%M:%S +0000", time.gmtime())
if url not in checker: if url not in checker:
checker.append(url) checker.append(url)
articles.append({ articles.append({
'title' :title 'title': title, 'date': date, 'url': url, 'description': description
,'date' :date })
,'url' :url
,'description':description
})
totalfeeds.append((feedtitle, articles)) totalfeeds.append((feedtitle, articles))
return totalfeeds return totalfeeds

115
recipes/arizona_republic.recipe
View File

@ -1,68 +1,77 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010, jolo' __copyright__ = '2010, jolo'
''' '''
azrepublic.com azrepublic.com
''' '''
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1307301031(BasicNewsRecipe): class AdvancedUserRecipe1307301031(BasicNewsRecipe):
title = u'AZRepublic' title = u'AZRepublic'
__author__ = 'Jim Olo' __author__ = 'Jim Olo'
language = 'en' language = 'en'
description = "The Arizona Republic is Arizona's leading provider of news and information, and has published a daily newspaper in Phoenix for more than 110 years" description = "The Arizona Republic is Arizona's leading provider of news and information, and has published a daily newspaper in Phoenix for more than 110 years" # noqa
publisher = 'AZRepublic/AZCentral' publisher = 'AZRepublic/AZCentral'
masthead_url = 'http://freedom2t.com/wp-content/uploads/press_az_republic_v2.gif' masthead_url = 'http://freedom2t.com/wp-content/uploads/press_az_republic_v2.gif'
cover_url = 'http://www.valleyleadership.org/Common/Img/2line4c_AZRepublic%20with%20azcentral%20logo.jpg' cover_url = 'http://www.valleyleadership.org/Common/Img/2line4c_AZRepublic%20with%20azcentral%20logo.jpg'
category = 'news, politics, USA, AZ, Arizona' category = 'news, politics, USA, AZ, Arizona'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
remove_empty_feeds = True remove_empty_feeds = True
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
# extra_css = '.headline {font-size: medium;} \n .fact { padding-top: 10pt }' # extra_css = '.headline {font-size: medium;} \n .fact { padding-top: 10pt }'
extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif } .headline {font-size: medium} .introduction{font-weight: bold} .story-feature{display: block; padding: 0; border: 1px solid; width: 40%; font-size: small} .story-feature h2{text-align: center; text-transform: uppercase} ' extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif } .headline {font-size: medium} .introduction{font-weight: bold} .story-feature{display: block; padding: 0; border: 1px solid; width: 40%; font-size: small} .story-feature h2{text-align: center; text-transform: uppercase} ' # noqa
remove_attributes = ['width','height','h2','subHeadline','style'] remove_attributes = ['width', 'height', 'h2', 'subHeadline', 'style']
remove_tags = [ remove_tags = [
dict(name='div', attrs={'id':['slidingBillboard', 'top728x90', 'subindex-header', 'topSearch']}), dict(name='div', attrs={
dict(name='div', attrs={'id':['simplesearch', 'azcLoginBox', 'azcLoginBoxInner', 'topNav']}), 'id': ['slidingBillboard', 'top728x90', 'subindex-header', 'topSearch']}),
dict(name='div', attrs={'id':['carsDrop', 'homesDrop', 'rentalsDrop', 'classifiedDrop']}), dict(name='div', attrs={
dict(name='div', attrs={'id':['nav', 'mp', 'subnav', 'jobsDrop']}), 'id': ['simplesearch', 'azcLoginBox', 'azcLoginBoxInner', 'topNav']}),
dict(name='h6', attrs={'class':['section-header']}), dict(name='div', attrs={
dict(name='a', attrs={'href':['#comments']}), 'id': ['carsDrop', 'homesDrop', 'rentalsDrop', 'classifiedDrop']}),
dict(name='div', attrs={'class':['articletools clearfix', 'floatRight']}), dict(name='div', attrs={'id': ['nav', 'mp', 'subnav', 'jobsDrop']}),
dict(name='div', attrs={'id':['fbFrame', 'ob', 'storyComments', 'storyGoogleAdBox']}), dict(name='h6', attrs={'class': ['section-header']}),
dict(name='div', attrs={'id':['storyTopHomes', 'openRight', 'footerwrap', 'copyright']}), dict(name='a', attrs={'href': ['#comments']}),
dict(name='div', attrs={'id':['blogsHed', 'blog_comments', 'blogByline','blogTopics']}), dict(name='div', attrs={
dict(name='div', attrs={'id':['membersRightMain', 'dealsfooter', 'azrTopHed', 'azrRightCol']}), 'class': ['articletools clearfix', 'floatRight']}),
dict(name='div', attrs={'id':['ttdHeader', 'ttdTimeWeather']}), dict(name='div', attrs={
dict(name='div', attrs={'id':['membersRightMain', 'deals-header-wrap']}), 'id': ['fbFrame', 'ob', 'storyComments', 'storyGoogleAdBox']}),
dict(name='div', attrs={'id':['todoTopSearchBar', 'byline clearfix', 'subdex-topnav']}), dict(name='div', attrs={
dict(name='h1', attrs={'id':['SEOtext']}), 'id': ['storyTopHomes', 'openRight', 'footerwrap', 'copyright']}),
dict(name='table', attrs={'class':['ap-mediabox-table']}), dict(name='div', attrs={
dict(name='p', attrs={'class':['ap_para']}), 'id': ['blogsHed', 'blog_comments', 'blogByline', 'blogTopics']}),
dict(name='span', attrs={'class':['source-org vcard', 'org fn']}), dict(name='div', attrs={
dict(name='a', attrs={'href':['http://hosted2.ap.org/APDEFAULT/privacy']}), 'id': ['membersRightMain', 'dealsfooter', 'azrTopHed', 'azrRightCol']}),
dict(name='a', attrs={'href':['http://hosted2.ap.org/APDEFAULT/terms']}), dict(name='div', attrs={'id': ['ttdHeader', 'ttdTimeWeather']}),
dict(name='div', attrs={'id':['onespot_nextclick']}), dict(name='div', attrs={
] 'id': ['membersRightMain', 'deals-header-wrap']}),
dict(name='div', attrs={
feeds = [ 'id': ['todoTopSearchBar', 'byline clearfix', 'subdex-topnav']}),
(u'FrontPage', u'http://www.azcentral.com/rss/feeds/republicfront.xml'), dict(name='h1', attrs={'id': ['SEOtext']}),
(u'TopUS-News', u'http://hosted.ap.org/lineups/USHEADS.rss?SITE=AZPHG&SECTION=HOME'), dict(name='table', attrs={'class': ['ap-mediabox-table']}),
(u'WorldNews', u'http://hosted.ap.org/lineups/WORLDHEADS.rss?SITE=AZPHG&SECTION=HOME'), dict(name='p', attrs={'class': ['ap_para']}),
(u'TopBusiness', u'http://hosted.ap.org/lineups/BUSINESSHEADS.rss?SITE=AZPHG&SECTION=HOME'), dict(name='span', attrs={'class': ['source-org vcard', 'org fn']}),
(u'Entertainment', u'http://hosted.ap.org/lineups/ENTERTAINMENT.rss?SITE=AZPHG&SECTION=HOME'), dict(name='a', attrs={
(u'ArizonaNews', u'http://www.azcentral.com/rss/feeds/news.xml'), 'href': ['http://hosted2.ap.org/APDEFAULT/privacy']}),
(u'Gilbert', u'http://www.azcentral.com/rss/feeds/gilbert.xml'), dict(name='a', attrs={
(u'Chandler', u'http://www.azcentral.com/rss/feeds/chandler.xml'), 'href': ['http://hosted2.ap.org/APDEFAULT/terms']}),
(u'DiningReviews', u'http://www.azcentral.com/rss/feeds/diningreviews.xml'), dict(name='div', attrs={'id': ['onespot_nextclick']}),
(u'AZBusiness', u'http://www.azcentral.com/rss/feeds/business.xml'), ]
(u'ArizonaDeals', u'http://www.azcentral.com/members/Blog%7E/RealDealsblog'),
(u'GroceryDeals', u'http://www.azcentral.com/members/Blog%7E/RealDealsblog/tag/2646')
]
feeds = [
(u'FrontPage', u'http://www.azcentral.com/rss/feeds/republicfront.xml'),
(u'TopUS-News', u'http://hosted.ap.org/lineups/USHEADS.rss?SITE=AZPHG&SECTION=HOME'),
(u'WorldNews', u'http://hosted.ap.org/lineups/WORLDHEADS.rss?SITE=AZPHG&SECTION=HOME'),
(u'TopBusiness', u'http://hosted.ap.org/lineups/BUSINESSHEADS.rss?SITE=AZPHG&SECTION=HOME'),
(u'Entertainment', u'http://hosted.ap.org/lineups/ENTERTAINMENT.rss?SITE=AZPHG&SECTION=HOME'),
(u'ArizonaNews', u'http://www.azcentral.com/rss/feeds/news.xml'),
(u'Gilbert', u'http://www.azcentral.com/rss/feeds/gilbert.xml'),
(u'Chandler', u'http://www.azcentral.com/rss/feeds/chandler.xml'),
(u'DiningReviews', u'http://www.azcentral.com/rss/feeds/diningreviews.xml'),
(u'AZBusiness', u'http://www.azcentral.com/rss/feeds/business.xml'),
(u'ArizonaDeals', u'http://www.azcentral.com/members/Blog%7E/RealDealsblog'),
(u'GroceryDeals', u'http://www.azcentral.com/members/Blog%7E/RealDealsblog/tag/2646')
]

69
recipes/army_times.recipe
View File

@ -1,42 +1,39 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class ArmyTimes(BasicNewsRecipe): class ArmyTimes(BasicNewsRecipe):
title = 'Army Times' title = 'Army Times'
__author__ = 'jde' __author__ = 'jde'
__date__ = '16 May 2012' __date__ = '16 May 2012'
__version__ = '1.0' __version__ = '1.0'
description = 'News of the U.S. Army' description = 'News of the U.S. Army'
language = 'en' language = 'en'
publisher = 'ArmyTimes.com' publisher = 'ArmyTimes.com'
category = 'news, U.S. Army' category = 'news, U.S. Army'
tags = 'news, U.S. Army' tags = 'news, U.S. Army'
cover_url = 'http://www.armytimes.com/images/logo_armytimes_alert.jpg' cover_url = 'http://www.armytimes.com/images/logo_armytimes_alert.jpg'
masthead_url = 'http://www.armytimes.com/images/logo_armytimes_alert.jpg' masthead_url = 'http://www.armytimes.com/images/logo_armytimes_alert.jpg'
oldest_article = 7 #days oldest_article = 7 # days
max_articles_per_feed = 25 max_articles_per_feed = 25
publication_type = 'newspaper' publication_type = 'newspaper'
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
encoding = None encoding = None
recursions = 0 recursions = 0
needs_subscription = False needs_subscription = False
remove_javascript = True remove_javascript = True
remove_empty_feeds = True remove_empty_feeds = True
auto_cleanup = True auto_cleanup = True
feeds = [
('News', 'http://www.armytimes.com/rss_news.php'),
feeds = [ ('Benefits', 'http://www.armytimes.com/rss_benefits.php'),
('Money', 'http://www.armytimes.com/rss_money.php'),
('News', 'http://www.armytimes.com/rss_news.php'), ('Careers & Education', 'http://www.armytimes.com/rss_careers.php'),
('Benefits', 'http://www.armytimes.com/rss_benefits.php'), ('Community', 'http://www.armytimes.com/rss_community.php'),
('Money', 'http://www.armytimes.com/rss_money.php'), ('Off Duty', 'http://www.armytimes.com/rss_off_duty.php'),
('Careers & Education', 'http://www.armytimes.com/rss_careers.php'), ('Entertainment', 'http://www.armytimes.com/rss_entertainment.php'),
('Community', 'http://www.armytimes.com/rss_community.php'), ('Guard & Reserve', 'http://www.armytimes.com/rss_guard.php'),
('Off Duty', 'http://www.armytimes.com/rss_off_duty.php'),
('Entertainment', 'http://www.armytimes.com/rss_entertainment.php'),
('Guard & Reserve', 'http://www.armytimes.com/rss_guard.php'),
] ]

13
recipes/arret_sur_images.recipe
View File

@ -7,10 +7,11 @@ __description__ = 'Get some fresh news from Arrêt sur images'
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class Asi(BasicNewsRecipe): class Asi(BasicNewsRecipe):
title = 'Arrêt sur images' title = 'Arrêt sur images'
__author__ = 'François D. (aka franek)' __author__ = 'François D. (aka franek)'
description = 'Global news in french from news site "Arrêt sur images"' description = 'Global news in french from news site "Arrêt sur images"'
oldest_article = 7.0 oldest_article = 7.0
@ -26,15 +27,16 @@ class Asi(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
feeds = [ feeds = [
('vite dit et gratuit', 'http://www.arretsurimages.net/vite-dit.rss'), ('vite dit et gratuit', 'http://www.arretsurimages.net/vite-dit.rss'),
('Toutes les chroniques', 'http://www.arretsurimages.net/chroniques.rss'), ('Toutes les chroniques', 'http://www.arretsurimages.net/chroniques.rss'),
('Contenus et dossiers', 'http://www.arretsurimages.net/dossiers.rss'), ('Contenus et dossiers', 'http://www.arretsurimages.net/dossiers.rss'),
] ]
conversion_options = { 'smarten_punctuation' : True } conversion_options = {'smarten_punctuation': True}
remove_tags = [dict(id='vite-titre'), dict(id='header'), dict(id='wrap-connexion'), dict(id='col_right'), dict(name='div', attrs={'class':'bloc-chroniqueur-2'}), dict(id='footercontainer')] remove_tags = [dict(id='vite-titre'), dict(id='header'), dict(id='wrap-connexion'), dict(id='col_right'),
dict(name='div', attrs={'class': 'bloc-chroniqueur-2'}), dict(id='footercontainer')]
def print_version(self, url): def print_version(self, url):
return url.replace('contenu.php', 'contenu-imprimable.php') return url.replace('contenu.php', 'contenu-imprimable.php')
@ -51,4 +53,3 @@ class Asi(BasicNewsRecipe):
br['password'] = self.password br['password'] = self.password
br.submit() br.submit()
return br return br

89
recipes/ars_technica.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008-2012, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2012, Darko Miletic <darko.miletic at gmail.com>'
''' '''
arstechnica.com arstechnica.com
@ -7,20 +7,21 @@ arstechnica.com
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup from calibre.ebooks.BeautifulSoup import BeautifulSoup
class ArsTechnica(BasicNewsRecipe): class ArsTechnica(BasicNewsRecipe):
title = u'Ars Technica' title = u'Ars Technica'
language = 'en' language = 'en'
__author__ = 'Darko Miletic, Sujata Raman, Alexis Rohou, Tom Sparks' __author__ = 'Darko Miletic, Sujata Raman, Alexis Rohou, Tom Sparks'
description = 'Ars Technica: Serving the technologist for 1.2 decades' description = 'Ars Technica: Serving the technologist for 1.2 decades'
publisher = 'Conde Nast Publications' publisher = 'Conde Nast Publications'
category = 'news, IT, technology' category = 'news, IT, technology'
oldest_article = 5 oldest_article = 5
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
encoding = 'utf-8' encoding = 'utf-8'
use_embedded_content = False use_embedded_content = False
remove_empty_feeds = True remove_empty_feeds = True
publication_type = 'newsportal' publication_type = 'newsportal'
extra_css = ''' extra_css = '''
body {font-family: Arial,sans-serif} body {font-family: Arial,sans-serif}
.heading{font-family: "Times New Roman",serif} .heading{font-family: "Times New Roman",serif}
@ -31,56 +32,48 @@ class ArsTechnica(BasicNewsRecipe):
''' '''
conversion_options = { conversion_options = {
'comments' : description 'comments': description, 'tags': category, 'language': language, 'publisher': publisher
,'tags' : category }
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [ keep_only_tags = [
dict(attrs={'class':'standalone'}) dict(attrs={'class': 'standalone'}), dict(attrs={'id': 'article-guts'})
,dict(attrs={'id':'article-guts'}) ]
]
remove_tags = [ remove_tags = [
dict(name=['object','link','embed','iframe','meta']) dict(name=['object', 'link', 'embed', 'iframe', 'meta']), dict(attrs={'class': 'corner-info'}), dict(attrs={
,dict(attrs={'class':'corner-info'}) 'id': 'article-footer-wrap'}), dict(attrs={'class': 'article-expander'}), dict(name='nav', attrs={'class': 'subheading'})
,dict(attrs={'id': 'article-footer-wrap'}) ]
,dict(attrs={'class': 'article-expander'})
,dict(name='nav',attrs={'class': 'subheading'})
]
remove_attributes = ['lang'] remove_attributes = ['lang']
feeds = [ feeds = [
(u'Ars Features (All our long-form feature articles)', u'http://feeds.arstechnica.com/arstechnica/features'),
(u'Ars Features (All our long-form feature articles)' , u'http://feeds.arstechnica.com/arstechnica/features') (u'Technology Lab (Information Technology)', u'http://feeds.arstechnica.com/arstechnica/technology-lab'),
, (u'Technology Lab (Information Technology)' , u'http://feeds.arstechnica.com/arstechnica/technology-lab') (u'Gear & Gadgets', u'http://feeds.arstechnica.com/arstechnica/gadgets'),
,(u'Gear & Gadgets' , u'http://feeds.arstechnica.com/arstechnica/gadgets') (u'Ministry of Innovation (Business of Technology)', u'http://feeds.arstechnica.com/arstechnica/business'),
,(u'Ministry of Innovation (Business of Technology)' , u'http://feeds.arstechnica.com/arstechnica/business') (u'Risk Assessment (Security & Hacktivism)', u'http://feeds.arstechnica.com/arstechnica/security'),
,(u'Risk Assessment (Security & Hacktivism)' , u'http://feeds.arstechnica.com/arstechnica/security') (u'Law & Disorder (Civilizations & Discontents)', u'http://feeds.arstechnica.com/arstechnica/tech-policy'),
,(u'Law & Disorder (Civilizations & Discontents)' , u'http://feeds.arstechnica.com/arstechnica/tech-policy') (u'Infinite Loop (Apple Ecosystem)', u'http://feeds.arstechnica.com/arstechnica/apple'),
,(u'Infinite Loop (Apple Ecosystem)' , u'http://feeds.arstechnica.com/arstechnica/apple') (u'Opposable Thumbs (Gaming & Entertainment)', u'http://feeds.arstechnica.com/arstechnica/gaming'),
,(u'Opposable Thumbs (Gaming & Entertainment)' , u'http://feeds.arstechnica.com/arstechnica/gaming') (u'Scientific Method (Science & Exploration)', u'http://feeds.arstechnica.com/arstechnica/science'),
,(u'Scientific Method (Science & Exploration)' , u'http://feeds.arstechnica.com/arstechnica/science') (u'Multiverse (Exploratoins & Meditations on Sci-Fi)', u'http://feeds.arstechnica.com/arstechnica/multiverse'),
,(u'Multiverse (Exploratoins & Meditations on Sci-Fi)' , u'http://feeds.arstechnica.com/arstechnica/multiverse') (u'Cars Technica (All Things Automotive)', u'http://feeds.arstechnica.com/arstechnica/cars'),
,(u'Cars Technica (All Things Automotive)' , u'http://feeds.arstechnica.com/arstechnica/cars') (u'Staff Blogs (From the Minds of Ars)', u'http://feeds.arstechnica.com/arstechnica/staff-blogs')
,(u'Staff Blogs (From the Minds of Ars)' , u'http://feeds.arstechnica.com/arstechnica/staff-blogs') ]
]
def append_page(self, soup, appendtag, position): def append_page(self, soup, appendtag, position):
pager = soup.find(attrs={'class':'numbers'}) pager = soup.find(attrs={'class': 'numbers'})
if pager: if pager:
nexttag = pager.find(attrs={'class':'next'}) nexttag = pager.find(attrs={'class': 'next'})
if nexttag: if nexttag:
nurl = nexttag.parent['href'] nurl = nexttag.parent['href']
rawc = self.index_to_soup(nurl,True) rawc = self.index_to_soup(nurl, True)
soup2 = BeautifulSoup(rawc, fromEncoding=self.encoding) soup2 = BeautifulSoup(rawc, fromEncoding=self.encoding)
texttag = soup2.find(attrs={'id':'article-guts'}) texttag = soup2.find(attrs={'id': 'article-guts'})
newpos = len(texttag.contents) newpos = len(texttag.contents)
self.append_page(soup2,texttag,newpos) self.append_page(soup2, texttag, newpos)
texttag.extract() texttag.extract()
pager.extract() pager.extract()
appendtag.insert(position,texttag) appendtag.insert(position, texttag)
def preprocess_html(self, soup): def preprocess_html(self, soup):
self.append_page(soup, soup.body, 3) self.append_page(soup, soup.body, 3)
@ -102,4 +95,4 @@ class ArsTechnica(BasicNewsRecipe):
return soup return soup
def preprocess_raw_html(self, raw, url): def preprocess_raw_html(self, raw, url):
return '<html><head>'+raw[raw.find('</head>'):] return '<html><head>' + raw[raw.find('</head>'):]

22
recipes/asco_de_vida.recipe
View File

@ -1,20 +1,18 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class HindustanTimes(BasicNewsRecipe): class HindustanTimes(BasicNewsRecipe):
title = u'Asco de vida' title = u'Asco de vida'
language = 'es' language = 'es'
__author__ = 'Krittika Goyal' __author__ = 'Krittika Goyal'
oldest_article = 1 #days oldest_article = 1 # days
max_articles_per_feed = 25 max_articles_per_feed = 25
#encoding = 'cp1252'
use_embedded_content = False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
keep_only_tags = dict(name='div', attrs={'class':'box story'}) keep_only_tags = dict(name='div', attrs={'class': 'box story'})
feeds = [
('News',
'http://feeds2.feedburner.com/AscoDeVida'),
]
feeds = [
('News',
'http://feeds2.feedburner.com/AscoDeVida'),
]

26
recipes/asia_one.recipe
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Bruce <bruce at dotdoh.com>' __copyright__ = '2009, Bruce <bruce at dotdoh.com>'
''' '''
asiaone.com asiaone.com
@ -8,23 +8,25 @@ asiaone.com
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AsiaOne(BasicNewsRecipe): class AsiaOne(BasicNewsRecipe):
title = u'AsiaOne' title = u'AsiaOne'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
__author__ = 'Bruce' __author__ = 'Bruce'
description = 'News from Singapore Press Holdings Portal' description = 'News from Singapore Press Holdings Portal'
no_stylesheets = False no_stylesheets = False
language = 'en_SG' language = 'en_SG'
remove_javascript = True remove_javascript = True
remove_tags = [dict(name='span', attrs={'class':'footer'})] remove_tags = [dict(name='span', attrs={'class': 'footer'})]
keep_only_tags = [ keep_only_tags = [
dict(name='h1', attrs={'class':'headline'}), dict(name='h1', attrs={'class': 'headline'}),
dict(name='div', attrs={'class':['article-content','person-info row']}) dict(name='div', attrs={
] 'class': ['article-content', 'person-info row']})
]
feeds = [ feeds = [
('Singapore', 'http://asiaone.feedsportal.com/c/34151/f/618415/index.rss'), ('Singapore', 'http://asiaone.feedsportal.com/c/34151/f/618415/index.rss'),
('Asia', 'http://asiaone.feedsportal.com/c/34151/f/618416/index.rss') ('Asia', 'http://asiaone.feedsportal.com/c/34151/f/618416/index.rss')
] ]

42
recipes/asianreviewofbooks.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>'
''' '''
www.asianreviewofbooks.com www.asianreviewofbooks.com
@ -7,20 +7,21 @@ www.asianreviewofbooks.com
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AsianReviewOfBooks(BasicNewsRecipe): class AsianReviewOfBooks(BasicNewsRecipe):
title = 'The Asian Review of Books' title = 'The Asian Review of Books'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'In addition to reviewing books about or of relevance to Asia, the Asian Review of Books also features long-format essays by leading Asian writers and thinkers, to providing an unparalleled forum for discussion of key contemporary issues by Asians for Asia and a vehicle of intellectual depth and breadth where leading thinkers can write on the books, arts and ideas of the day. Widely quoted and referenced, with an archive of more than one thousand book reviews, it is the only web resource dedicated to Asian books. And now, with the addition of the new premium content, the Asian Review of Books, is a must-read publication.' description = 'In addition to reviewing books about or of relevance to Asia, the Asian Review of Books also features long-format essays by leading Asian writers and thinkers, to providing an unparalleled forum for discussion of key contemporary issues by Asians for Asia and a vehicle of intellectual depth and breadth where leading thinkers can write on the books, arts and ideas of the day. Widely quoted and referenced, with an archive of more than one thousand book reviews, it is the only web resource dedicated to Asian books. And now, with the addition of the new premium content, the Asian Review of Books, is a must-read publication.' # noqa
publisher = 'The Asian Review of Books' publisher = 'The Asian Review of Books'
category = 'literature, books, reviews, Asia' category = 'literature, books, reviews, Asia'
oldest_article = 30 oldest_article = 30
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
encoding = 'cp1252' encoding = 'cp1252'
language = 'en_CN' language = 'en_CN'
publication_type = 'magazine' publication_type = 'magazine'
masthead_url = 'http://www.asianreviewofbooks.com/new/images/mob_arb.png' masthead_url = 'http://www.asianreviewofbooks.com/new/images/mob_arb.png'
extra_css = """ extra_css = """
body{font-family: serif} body{font-family: serif}
.big {font-size: xx-large} .big {font-size: xx-large}
@ -31,21 +32,16 @@ class AsianReviewOfBooks(BasicNewsRecipe):
""" """
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
}
remove_tags = [dict(name=['object', 'script', 'iframe', 'embed'])]
remove_tags = [dict(name=['object','script','iframe','embed'])]
remove_attributes = ['style', 'onclick'] remove_attributes = ['style', 'onclick']
feeds = [(u'Articles' , u'http://www.asianreviewofbooks.com/new/rss.php')] feeds = [(u'Articles', u'http://www.asianreviewofbooks.com/new/rss.php')]
def print_version(self, url): def print_version(self, url):
root, sep, artid = url.rpartition('?ID=') root, sep, artid = url.rpartition('?ID=')
return root + 'getarticle.php?articleID=' + artid + '&stats=web' return root + 'getarticle.php?articleID=' + artid + '&stats=web'
def preprocess_raw_html(self, raw, url): def preprocess_raw_html(self, raw, url):
return '<html><head><title>title</title></head><body>' + raw + '</body></html>' return '<html><head><title>title</title></head><body>' + raw + '</body></html>'

21
recipes/astro_news_pl.recipe
View File

@ -1,18 +1,19 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AstroNEWS(BasicNewsRecipe): class AstroNEWS(BasicNewsRecipe):
title = u'AstroNEWS' title = u'AstroNEWS'
__author__ = 'fenuks' __author__ = 'fenuks'
description = u'AstroNEWS regularnie dostarcza wiadomości o wydarzeniach związanych z astronomią i astronautyką. Informujemy o aktualnych odkryciach i wydarzeniach naukowych, zapowiadamy ciekawe zjawiska astronomiczne. Serwis jest częścią portalu astronomicznego AstroNET prowadzonego przez miłośników astronomii i zawodowych astronomów.' description = u'AstroNEWS regularnie dostarcza wiadomości o wydarzeniach związanych z astronomią i astronautyką. Informujemy o aktualnych odkryciach i wydarzeniach naukowych, zapowiadamy ciekawe zjawiska astronomiczne. Serwis jest częścią portalu astronomicznego AstroNET prowadzonego przez miłośników astronomii i zawodowych astronomów.' # noqa
category = 'astronomy, science' category = 'astronomy, science'
language = 'pl' language = 'pl'
oldest_article = 8 oldest_article = 8
max_articles_per_feed = 100 max_articles_per_feed = 100
#extra_css= 'table {text-align: left;}' no_stylesheets = True
no_stylesheets=True cover_url = 'http://news.astronet.pl/img/logo_news.jpg'
cover_url='http://news.astronet.pl/img/logo_news.jpg'
remove_attributes = ['width', 'align'] remove_attributes = ['width', 'align']
remove_tags=[dict(name='hr')] remove_tags = [dict(name='hr')]
feeds = [(u'Wiadomości', u'http://news.astronet.pl/rss.cgi')] feeds = [(u'Wiadomości', u'http://news.astronet.pl/rss.cgi')]
def print_version(self, url): def print_version(self, url):
return url.replace('astronet.pl/', 'astronet.pl/print.cgi?') return url.replace('astronet.pl/', 'astronet.pl/print.cgi?')

10
recipes/astroflesz.recipe
View File

@ -1,11 +1,12 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:fdm=marker:ai # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:fdm=marker:ai
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Astroflesz(BasicNewsRecipe): class Astroflesz(BasicNewsRecipe):
title = u'Astroflesz' title = u'Astroflesz'
oldest_article = 7 oldest_article = 7
__author__ = 'fenuks' __author__ = 'fenuks'
description = u'astroflesz.pl - to portal poświęcony astronomii. Informuje zarówno o aktualnych wydarzeniach i odkryciach naukowych, jak również zapowiada ciekawe zjawiska astronomiczne' description = u'astroflesz.pl - to portal poświęcony astronomii. Informuje zarówno o aktualnych wydarzeniach i odkryciach naukowych, jak również zapowiada ciekawe zjawiska astronomiczne' # noqa
category = 'astronomy' category = 'astronomy'
language = 'pl' language = 'pl'
cover_url = 'http://www.astroflesz.pl/templates/astroflesz/images/logo/logo.png' cover_url = 'http://www.astroflesz.pl/templates/astroflesz/images/logo/logo.png'
@ -16,12 +17,13 @@ class Astroflesz(BasicNewsRecipe):
remove_empty_feeds = True remove_empty_feeds = True
remove_attributes = ['style'] remove_attributes = ['style']
keep_only_tags = [dict(id="k2Container")] keep_only_tags = [dict(id="k2Container")]
remove_tags_after = dict(name='div', attrs={'class':'itemLinks'}) remove_tags_after = dict(name='div', attrs={'class': 'itemLinks'})
remove_tags = [dict(name='div', attrs={'class':['itemLinks', 'itemToolbar', 'itemRatingBlock']})] remove_tags = [dict(name='div', attrs={
'class': ['itemLinks', 'itemToolbar', 'itemRatingBlock']})]
feeds = [(u'Wszystkie', u'http://astroflesz.pl/?format=feed')] feeds = [(u'Wszystkie', u'http://astroflesz.pl/?format=feed')]
def postprocess_html(self, soup, first_fetch): def postprocess_html(self, soup, first_fetch):
t = soup.find(attrs={'class':'itemIntroText'}) t = soup.find(attrs={'class': 'itemIntroText'})
if t: if t:
for i in t.findAll('img'): for i in t.findAll('img'):
i['style'] = 'float: left; margin-right: 5px;' i['style'] = 'float: left; margin-right: 5px;'

77
recipes/athens_news.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
''' '''
www.athensnews.gr www.athensnews.gr
@ -6,21 +6,22 @@ www.athensnews.gr
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AthensNews(BasicNewsRecipe): class AthensNews(BasicNewsRecipe):
title = 'Athens News' title = 'Athens News'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Greece in English since 1952' description = 'Greece in English since 1952'
publisher = 'NEP Publishing Company SA' publisher = 'NEP Publishing Company SA'
category = 'news, politics, Greece, Athens' category = 'news, politics, Greece, Athens'
oldest_article = 1 oldest_article = 1
max_articles_per_feed = 200 max_articles_per_feed = 200
no_stylesheets = True no_stylesheets = True
encoding = 'utf8' encoding = 'utf8'
use_embedded_content = False use_embedded_content = False
language = 'en_GR' language = 'en_GR'
remove_empty_feeds = True remove_empty_feeds = True
publication_type = 'newspaper' publication_type = 'newspaper'
masthead_url = 'http://www.athensnews.gr/sites/athensnews/themes/athensnewsv3/images/logo.jpg' masthead_url = 'http://www.athensnews.gr/sites/athensnews/themes/athensnewsv3/images/logo.jpg'
extra_css = """ extra_css = """
body{font-family: Arial,Helvetica,sans-serif } body{font-family: Arial,Helvetica,sans-serif }
img{margin-bottom: 0.4em; display:block} img{margin-bottom: 0.4em; display:block}
@ -30,36 +31,32 @@ class AthensNews(BasicNewsRecipe):
""" """
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'linearize_tables': True
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
, 'linearize_tables' : True
}
remove_tags = [ remove_tags = [
dict(name=['meta','link']) dict(name=['meta', 'link'])
] ]
keep_only_tags=[ keep_only_tags = [
dict(name='span',attrs={'class':'big'}) dict(name='span', attrs={'class': 'big'}), dict(
,dict(name='td', attrs={'class':['articlepubdate','text']}) name='td', attrs={'class': ['articlepubdate', 'text']})
] ]
remove_attributes=['lang'] remove_attributes = ['lang']
feeds = [ feeds = [
(u'News' , u'http://www.athensnews.gr/category/1/feed' )
,(u'Politics' , u'http://www.athensnews.gr/category/8/feed' ) (u'News', u'http://www.athensnews.gr/category/1/feed'),
,(u'Business' , u'http://www.athensnews.gr/category/2/feed' ) (u'Politics', u'http://www.athensnews.gr/category/8/feed'),
,(u'Economy' , u'http://www.athensnews.gr/category/11/feed') (u'Business', u'http://www.athensnews.gr/category/2/feed'),
,(u'Community' , u'http://www.athensnews.gr/category/5/feed' ) (u'Economy', u'http://www.athensnews.gr/category/11/feed'),
,(u'Arts' , u'http://www.athensnews.gr/category/3/feed' ) (u'Community', u'http://www.athensnews.gr/category/5/feed'),
,(u'Living in Athens', u'http://www.athensnews.gr/category/7/feed' ) (u'Arts', u'http://www.athensnews.gr/category/3/feed'),
,(u'Sports' , u'http://www.athensnews.gr/category/4/feed' ) (u'Living in Athens', u'http://www.athensnews.gr/category/7/feed'),
,(u'Travel' , u'http://www.athensnews.gr/category/6/feed' ) (u'Sports', u'http://www.athensnews.gr/category/4/feed'),
,(u'Letters' , u'http://www.athensnews.gr/category/44/feed') (u'Travel', u'http://www.athensnews.gr/category/6/feed'),
,(u'Media' , u'http://www.athensnews.gr/multimedia/feed' ) (u'Letters', u'http://www.athensnews.gr/category/44/feed'),
] (u'Media', u'http://www.athensnews.gr/multimedia/feed')
]
def print_version(self, url): def print_version(self, url):
return url + '?action=print' return url + '?action=print'

37
recipes/atlantic.recipe
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
from __future__ import unicode_literals from __future__ import unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>' __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
''' '''
theatlantic.com theatlantic.com
@ -9,13 +9,15 @@ import html5lib
from lxml import html from lxml import html
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes): def classes(classes):
q = frozenset(classes.split(' ')) q = frozenset(classes.split(' '))
return dict(attrs={'class':lambda x:x and frozenset(x.split()).intersection(q)}) return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
class TheAtlantic(BasicNewsRecipe): class TheAtlantic(BasicNewsRecipe):
title = 'The Atlantic' title = 'The Atlantic'
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal'
description = 'Current affairs and politics focussed on the US' description = 'Current affairs and politics focussed on the US'
INDEX = 'http://www.theatlantic.com/magazine/' INDEX = 'http://www.theatlantic.com/magazine/'
@ -23,13 +25,14 @@ class TheAtlantic(BasicNewsRecipe):
encoding = 'utf-8' encoding = 'utf-8'
keep_only_tags = [ keep_only_tags = [
classes('article-header article-body article-magazine metadata article-cover-content lead-img'), classes(
'article-header article-body article-magazine metadata article-cover-content lead-img'),
] ]
remove_tags = [ remove_tags = [
{'name': ['meta', 'link', 'noscript']}, {'name': ['meta', 'link', 'noscript']},
{'attrs':{'class':['offset-wrapper', 'ad-boxfeatures-wrapper']}}, {'attrs': {'class': ['offset-wrapper', 'ad-boxfeatures-wrapper']}},
{'attrs':{'class':lambda x: x and 'article-tools' in x}}, {'attrs': {'class': lambda x: x and 'article-tools' in x}},
{'src':lambda x:x and 'spotxchange.com' in x}, {'src': lambda x: x and 'spotxchange.com' in x},
] ]
remove_tags_after = classes('article-body') remove_tags_after = classes('article-body')
@ -48,7 +51,7 @@ class TheAtlantic(BasicNewsRecipe):
return url + '?single_page=true' return url + '?single_page=true'
def preprocess_html(self, soup): def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src':True}): for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src'] img['src'] = img['data-src']
return soup return soup
@ -61,8 +64,8 @@ class TheAtlantic(BasicNewsRecipe):
self.cover_url = img['src'] self.cover_url = img['src']
current_section, current_articles = 'Cover Story', [] current_section, current_articles = 'Cover Story', []
feeds = [] feeds = []
for div in soup.findAll('div', attrs={'class':lambda x: x and set(x.split()).intersection({'top-sections', 'bottom-sections'})}): for div in soup.findAll('div', attrs={'class': lambda x: x and set(x.split()).intersection({'top-sections', 'bottom-sections'})}):
for h2 in div.findAll('h2', attrs={'class':True}): for h2 in div.findAll('h2', attrs={'class': True}):
if 'section-name' in h2['class'].split(): if 'section-name' in h2['class'].split():
if current_articles: if current_articles:
feeds.append((current_section, current_articles)) feeds.append((current_section, current_articles))
@ -75,18 +78,22 @@ class TheAtlantic(BasicNewsRecipe):
url = a['href'] url = a['href']
if url.startswith('/'): if url.startswith('/'):
url = 'http://www.theatlantic.com' + url url = 'http://www.theatlantic.com' + url
li = a.findParent('li', attrs={'class':lambda x: x and 'article' in x.split()}) li = a.findParent(
'li', attrs={'class': lambda x: x and 'article' in x.split()})
desc = '' desc = ''
dek = li.find(attrs={'class':lambda x:x and 'dek' in x.split()}) dek = li.find(
attrs={'class': lambda x: x and 'dek' in x.split()})
if dek is not None: if dek is not None:
desc += self.tag_to_string(dek) desc += self.tag_to_string(dek)
byline = li.find(attrs={'class':lambda x:x and 'byline' in x.split()}) byline = li.find(
attrs={'class': lambda x: x and 'byline' in x.split()})
if byline is not None: if byline is not None:
desc += ' -- ' + self.tag_to_string(byline) desc += ' -- ' + self.tag_to_string(byline)
self.log('\t', title, 'at', url) self.log('\t', title, 'at', url)
if desc: if desc:
self.log('\t\t', desc) self.log('\t\t', desc)
current_articles.append({'title':title, 'url':url, 'description':desc}) current_articles.append(
{'title': title, 'url': url, 'description': desc})
if current_articles: if current_articles:
feeds.append((current_section, current_articles)) feeds.append((current_section, current_articles))
return feeds return feeds

13
recipes/atlantic_com.recipe
View File

@ -3,20 +3,21 @@
from __future__ import unicode_literals, division, absolute_import, print_function from __future__ import unicode_literals, division, absolute_import, print_function
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1421956712(BasicNewsRecipe): class AdvancedUserRecipe1421956712(BasicNewsRecipe):
title = 'TheAtlantic.com' title = 'TheAtlantic.com'
__author__ = 'ebrandon' __author__ = 'ebrandon'
language = 'en' language = 'en'
description = 'News and editorial about politics, culture, entertainment, tech, etc. Contains many articles not seen in The Atlantic magazine' description = 'News and editorial about politics, culture, entertainment, tech, etc. Contains many articles not seen in The Atlantic magazine'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
auto_cleanup = True auto_cleanup = True
ignore_duplicate_articles = {'title', 'url'} ignore_duplicate_articles = {'title', 'url'}
def print_version(self, url): def print_version(self, url):
return url.replace('/archive/', '/print/') return url.replace('/archive/', '/print/')
feeds = [ feeds = [
('Politics', 'http://feeds.feedburner.com/AtlanticPoliticsChannel'), ('Politics', 'http://feeds.feedburner.com/AtlanticPoliticsChannel'),
('International', 'http://feeds.feedburner.com/AtlanticInternational'), ('International', 'http://feeds.feedburner.com/AtlanticInternational'),
('National', 'http://feeds.feedburner.com/AtlanticNational'), ('National', 'http://feeds.feedburner.com/AtlanticNational'),

9
recipes/attac_es.recipe
View File

@ -2,14 +2,15 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AttacEspanaRecipe (BasicNewsRecipe): class AttacEspanaRecipe (BasicNewsRecipe):
__author__ = 'Marc Busqué <marc@lamarciana.com>' __author__ = 'Marc Busqué <marc@lamarciana.com>'
__url__ = 'http://www.lamarciana.com' __url__ = 'http://www.lamarciana.com'
__version__ = '1.0.2' __version__ = '1.0.2'
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2012, Marc Busqué <marc@lamarciana.com>' __copyright__ = '2012, Marc Busqué <marc@lamarciana.com>'
title = u'attac.es' title = u'attac.es'
description = u'La Asociación por la Tasación de las Transacciones Financieras y por la Ayuda a los Ciudadanos (ATTAC) es un movimiento internacional altermundialista que promueve el control democrático de los mercados financieros y las instituciones encargadas de su control mediante la reflexión política y la movilización social.' description = u'La Asociación por la Tasación de las Transacciones Financieras y por la Ayuda a los Ciudadanos (ATTAC) es un movimiento internacional altermundialista que promueve el control democrático de los mercados financieros y las instituciones encargadas de su control mediante la reflexión política y la movilización social.' # noqa
url = 'http://www.attac.es' url = 'http://www.attac.es'
language = 'es' language = 'es'
tags = 'contrainformación, información alternativa' tags = 'contrainformación, información alternativa'
@ -27,5 +28,5 @@ class AttacEspanaRecipe (BasicNewsRecipe):
cover_url = u'http://www.attac.es/wp-content/themes/attacweb/images/attaces.jpg' cover_url = u'http://www.attac.es/wp-content/themes/attacweb/images/attaces.jpg'
feeds = [ feeds = [
(u'Attac', u'http://www.attac.es/feed'), (u'Attac', u'http://www.attac.es/feed'),
] ]

69
recipes/auto.recipe
View File

@ -1,9 +1,9 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'GabrieleMarini, based on Darko Miletic' __author__ = 'GabrieleMarini, based on Darko Miletic'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>, Gabriele Marini' __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>, Gabriele Marini'
__version__ = 'v1.02 Marini Gabriele ' __version__ = 'v1.02 Marini Gabriele '
__date__ = '14062010' __date__ = '14062010'
__description__ = 'Italian daily newspaper' __description__ = 'Italian daily newspaper'
''' '''
@ -11,53 +11,46 @@ http://www.corrieredellosport.it/
''' '''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Auto(BasicNewsRecipe): class Auto(BasicNewsRecipe):
__author__ = 'Gabriele Marini' __author__ = 'Gabriele Marini'
description = 'Auto and Formula 1' description = 'Auto and Formula 1'
cover_url = 'http://www.auto.it/res/imgs/logo_Auto.png' cover_url = 'http://www.auto.it/res/imgs/logo_Auto.png'
title = u'Auto'
publisher = 'CONTE Editore'
category = 'Sport'
title = u'Auto' language = 'it'
publisher = 'CONTE Editore' timefmt = '[%a, %d %b, %Y]'
category = 'Sport'
language = 'it'
timefmt = '[%a, %d %b, %Y]'
oldest_article = 60 oldest_article = 60
max_articles_per_feed = 30 max_articles_per_feed = 30
use_embedded_content = False use_embedded_content = False
recursion = 10 recursion = 10
remove_javascript = True remove_javascript = True
no_stylesheets = True no_stylesheets = True
html2lrf_options = [ html2lrf_options = [
'--comment', description '--comment', description, '--category', category, '--publisher', publisher, '--ignore-tables'
, '--category', category ]
, '--publisher', publisher
, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' html2epub_options = 'publisher="' + publisher + '"\ncomments="' + \
description + '"\ntags="' + category + '"\nlinearize_tables=True'
keep_only_tags = [ keep_only_tags = [
dict(name='h2', attrs={'class':['tit_Article y_Txt']}), dict(name='h2', attrs={'class': ['tit_Article y_Txt']}),
dict(name='h2', attrs={'class':['tit_Article']}), dict(name='h2', attrs={'class': ['tit_Article']}),
dict(name='div', attrs={'class':['box_Img newsdet_new ']}), dict(name='div', attrs={'class': ['box_Img newsdet_new ']}),
dict(name='div', attrs={'class':['box_Img newsdet_as ']}), dict(name='div', attrs={'class': ['box_Img newsdet_as ']}),
dict(name='table', attrs={'class':['table_A']}), dict(name='table', attrs={'class': ['table_A']}),
dict(name='div', attrs={'class':['txt_Article txtBox_cms']}), dict(name='div', attrs={'class': ['txt_Article txtBox_cms']}),
dict(name='testoscheda')] dict(name='testoscheda')]
feeds = [ feeds = [
(u'Tutte le News' , u'http://www.auto.it/rss/articoli.xml' ), (u'Tutte le News', u'http://www.auto.it/rss/articoli.xml'),
(u'Prove su Strada' , u'http://www.auto.it/rss/prove+6.xml'), (u'Prove su Strada', u'http://www.auto.it/rss/prove+6.xml'),
(u'Novit\xe0' , u'http://www.auto.it/rss/novita+3.xml') (u'Novit\xe0', u'http://www.auto.it/rss/novita+3.xml')
] ]

9
recipes/auto_blog.recipe
View File

@ -1,16 +1,15 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AutoBlog(BasicNewsRecipe): class AutoBlog(BasicNewsRecipe):
title = u'Auto Blog' title = u'Auto Blog'
__author__ = 'Welovelucy' __author__ = 'Welovelucy'
language = 'en' language = 'en'
description = 'Auto industry news' description = 'Auto industry news'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
feeds = [(u'AutoBlog', u'http://www.autoblog.com/rss.xml')] feeds = [(u'AutoBlog', u'http://www.autoblog.com/rss.xml')]
def print_version(self, url): def print_version(self, url):
return url + 'print/' return url + 'print/'

84
recipes/auto_prove.recipe
View File

@ -1,9 +1,9 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'GabrieleMarini, based on Darko Miletic' __author__ = 'GabrieleMarini, based on Darko Miletic'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>, Gabriele Marini' __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>, Gabriele Marini'
__version__ = 'v1.02 Marini Gabriele ' __version__ = 'v1.02 Marini Gabriele '
__date__ = '10, January 2010' __date__ = '10, January 2010'
__description__ = 'Italian daily newspaper' __description__ = 'Italian daily newspaper'
''' '''
@ -11,80 +11,80 @@ http://www.corrieredellosport.it/
''' '''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AutoPR(BasicNewsRecipe): class AutoPR(BasicNewsRecipe):
__author__ = 'Gabriele Marini' __author__ = 'Gabriele Marini'
description = 'Auto and Formula 1' description = 'Auto and Formula 1'
cover_url = 'http://www.auto.it/res/imgs/logo_Auto.png' cover_url = 'http://www.auto.it/res/imgs/logo_Auto.png'
title = u'Auto Prove'
publisher = 'CONTE Editore'
category = 'Sport'
title = u'Auto Prove' language = 'it'
publisher = 'CONTE Editore' timefmt = '[%a, %d %b, %Y]'
category = 'Sport'
language = 'it'
timefmt = '[%a, %d %b, %Y]'
oldest_article = 60 oldest_article = 60
max_articles_per_feed = 20 max_articles_per_feed = 20
use_embedded_content = False use_embedded_content = False
recursion = 100 recursion = 100
remove_javascript = True remove_javascript = True
no_stylesheets = True no_stylesheets = True
#html2lrf_options = [ # html2lrf_options = [
# '--comment', description # '--comment', description
# , '--category', category # , '--category', category
# , '--publisher', publisher # , '--publisher', publisher
# , '--ignore-tables' # , '--ignore-tables'
# ] # ]
#html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
keep_only_tags = [ keep_only_tags = [
dict(name='h2', attrs={'class':['tit_Article y_Txt']}), dict(name='h2', attrs={'class': ['tit_Article y_Txt']}),
dict(name='h2', attrs={'class':['tit_Article']}), dict(name='h2', attrs={'class': ['tit_Article']}),
dict(name='div', attrs={'class':['box_Img newsdet_new ']}), dict(name='div', attrs={'class': ['box_Img newsdet_new ']}),
dict(name='div', attrs={'class':['box_Img newsdet_as ']}), dict(name='div', attrs={'class': ['box_Img newsdet_as ']}),
dict(name='table', attrs={'class':['table_A']}), dict(name='table', attrs={'class': ['table_A']}),
dict(name='div', attrs={'class':['txt_Article txtBox_cms']}), dict(name='div', attrs={'class': ['txt_Article txtBox_cms']}),
dict(name='testoscheda')] dict(name='testoscheda')]
def parse_index(self): def parse_index(self):
feeds = [] feeds = []
for title, url in [ for title, url in [
("Prove su Strada" , "http://www.auto.it/rss/prove+6.xml") ("Prove su Strada", "http://www.auto.it/rss/prove+6.xml")
]: ]:
soup = self.index_to_soup(url) soup = self.index_to_soup(url)
soup = soup.find('channel') soup = soup.find('channel')
print soup print soup
for article in soup.findAllNext('item'): for article in soup.findAllNext('item'):
title = self.tag_to_string(article.title) title = self.tag_to_string(article.title)
date = self.tag_to_string(article.pubDate) date = self.tag_to_string(article.pubDate)
description = self.tag_to_string(article.description) description = self.tag_to_string(article.description)
link = self.tag_to_string(article.guid) link = self.tag_to_string(article.guid)
# print article # print article
articles = self.create_links_append(link, date, description) articles = self.create_links_append(link, date, description)
if articles: if articles:
feeds.append((title, articles)) feeds.append((title, articles))
return feeds return feeds
def create_links_append(self, link, date, description): def create_links_append(self, link, date, description):
current_articles = [] current_articles = []
current_articles.append({'title': 'Generale', 'url': link,'description':description, 'date':date}), current_articles.append(
current_articles.append({'title': 'Design', 'url': link.replace('scheda','design'),'description':'scheda', 'date':''}), {'title': 'Generale', 'url': link, 'description': description, 'date': date}),
current_articles.append({'title': 'Interni', 'url': link.replace('scheda','interni'),'description':'Interni', 'date':''}), current_articles.append({'title': 'Design', 'url': link.replace(
current_articles.append({'title': 'Tecnica', 'url': link.replace('scheda','tecnica'),'description':'Tecnica', 'date':''}), 'scheda', 'design'), 'description': 'scheda', 'date': ''}),
current_articles.append({'title': 'Su Strada', 'url': link.replace('scheda','su_strada'),'description':'Su Strada', 'date':''}), current_articles.append({'title': 'Interni', 'url': link.replace(
current_articles.append({'title': 'Pagella', 'url': link.replace('scheda','pagella'),'description':'Pagella', 'date':''}), 'scheda', 'interni'), 'description': 'Interni', 'date': ''}),
current_articles.append({'title': 'Rilevamenti', 'url': link.replace('scheda','telemetria'),'description':'Rilevamenti', 'date':''}) current_articles.append({'title': 'Tecnica', 'url': link.replace(
'scheda', 'tecnica'), 'description': 'Tecnica', 'date': ''}),
current_articles.append({'title': 'Su Strada', 'url': link.replace(
'scheda', 'su_strada'), 'description': 'Su Strada', 'date': ''}),
current_articles.append({'title': 'Pagella', 'url': link.replace(
'scheda', 'pagella'), 'description': 'Pagella', 'date': ''}),
current_articles.append({'title': 'Rilevamenti', 'url': link.replace(
'scheda', 'telemetria'), 'description': 'Rilevamenti', 'date': ''})
return current_articles return current_articles

53
recipes/autobild.recipe
View File

@ -1,7 +1,7 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103' __copyright__ = u'2011, Silviu Cotoar\u0103'
''' '''
auto-bild.ro auto-bild.ro
@ -9,47 +9,42 @@ auto-bild.ro
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AutoBild(BasicNewsRecipe): class AutoBild(BasicNewsRecipe):
title = u'Auto Bild' title = u'Auto Bild'
__author__ = u'Silviu Cotoar\u0103' __author__ = u'Silviu Cotoar\u0103'
description = 'Auto' description = 'Auto'
publisher = 'Auto Bild' publisher = 'Auto Bild'
oldest_article = 50 oldest_article = 50
language = 'ro' language = 'ro'
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
category = 'Ziare,Reviste,Auto' category = 'Ziare,Reviste,Auto'
encoding = 'utf-8' encoding = 'utf-8'
cover_url = 'http://www.auto-bild.ro/images/autobild.gif' cover_url = 'http://www.auto-bild.ro/images/autobild.gif'
conversion_options = { conversion_options = {
'comments' : description 'comments': description, 'tags': category, 'language': language, 'publisher': publisher
,'tags' : category }
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'class':'box_2 articol clearfix'}) dict(name='div', attrs={'class': 'box_2 articol clearfix'})
] ]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class':['detail']}) dict(name='div', attrs={'class': ['detail']}), dict(name='a', attrs={'id': ['zoom_link']}), dict(
, dict(name='a', attrs={'id':['zoom_link']}) name='div', attrs={'class': ['icons clearfix']}), dict(name='div', attrs={'class': ['pub_articol clearfix']})
, dict(name='div', attrs={'class':['icons clearfix']})
, dict(name='div', attrs={'class':['pub_articol clearfix']})
] ]
remove_tags_after = [ remove_tags_after = [
dict(name='div', attrs={'class':['pub_articol clearfix']}) dict(name='div', attrs={'class': ['pub_articol clearfix']})
] ]
feeds = [ feeds = [
(u'Feeds', u'http://www.auto-bild.ro/rss/toate') (u'Feeds', u'http://www.auto-bild.ro/rss/toate')
] ]
def preprocess_html(self, soup): def preprocess_html(self, soup):
return self.adeify_images(soup) return self.adeify_images(soup)

25
recipes/automatiseringgids.recipe
View File

@ -1,27 +1,28 @@
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class autogids(BasicNewsRecipe): class autogids(BasicNewsRecipe):
title = u'Automatiseringgids IT' title = u'Automatiseringgids IT'
oldest_article = 7 oldest_article = 7
__author__ = 'DrMerry' __author__ = 'DrMerry'
description = 'IT-nieuws van Automatiseringgids' description = 'IT-nieuws van Automatiseringgids'
language = 'nl' language = 'nl'
publisher = 'AutomatiseringGids' publisher = 'AutomatiseringGids'
category = 'Nieuws, IT, Nederlandstalig' category = 'Nieuws, IT, Nederlandstalig'
simultaneous_downloads = 5 simultaneous_downloads = 5
timefmt = ' [%a, %d %B, %Y]' timefmt = ' [%a, %d %B, %Y]'
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
remove_empty_feeds = True remove_empty_feeds = True
publication_type = 'newspaper' publication_type = 'newspaper'
encoding = 'utf-8' encoding = 'utf-8'
cover_url = 'http://www.automatiseringgids.nl/binaries/content/gallery/ag/marketing/ag-avatar-100x50.jpg' cover_url = 'http://www.automatiseringgids.nl/binaries/content/gallery/ag/marketing/ag-avatar-100x50.jpg'
keep_only_tags = [dict(name='div', attrs={'class':['content']})] keep_only_tags = [dict(name='div', attrs={'class': ['content']})]
preprocess_regexps = [ preprocess_regexps = [
(re.compile(r'(<h3>Reacties</h3>|<h2>Zie ook:</h2>|<div style=".*</div>|<a[^>]*>|</a>)', re.DOTALL|re.IGNORECASE), (re.compile(r'(<h3>Reacties</h3>|<h2>Zie ook:</h2>|<div style=".*</div>|<a[^>]*>|</a>)', re.DOTALL | re.IGNORECASE),
lambda match: ''), lambda match: ''),
] ]
feeds = [(u'Actueel', u'http://www.automatiseringgids.nl/rss.aspx')] feeds = [(u'Actueel', u'http://www.automatiseringgids.nl/rss.aspx')]

23
recipes/autosport.recipe
View File

@ -9,22 +9,25 @@ www.autosport.com
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class autosport(BasicNewsRecipe): class autosport(BasicNewsRecipe):
title = u'Autosport' title = u'Autosport'
__author__ = 'MrStefan <mrstefaan@gmail.com>' __author__ = 'MrStefan <mrstefaan@gmail.com>'
language = 'en_GB' language = 'en_GB'
description =u'Daily Formula 1 and motorsport news from the leading weekly motor racing magazine. The authority on Formula 1, F1, MotoGP, GP2, Champ Car, Le Mans...' description = u'Daily Formula 1 and motorsport news from the leading weekly motor racing magazine. The authority on Formula 1, F1, MotoGP, GP2, Champ Car, Le Mans...' # noqa
masthead_url='http://cdn.images.autosport.com/asdotcom.gif' masthead_url = 'http://cdn.images.autosport.com/asdotcom.gif'
remove_empty_feeds= True remove_empty_feeds = True
oldest_article = 1 oldest_article = 1
max_articles_per_feed = 100 max_articles_per_feed = 100
remove_javascript=True remove_javascript = True
no_stylesheets=True no_stylesheets = True
keep_only_tags =[] keep_only_tags = []
keep_only_tags.append(dict(name = 'h1', attrs = {'class' : 'news_headline'})) keep_only_tags.append(dict(name='h1', attrs={'class': 'news_headline'}))
keep_only_tags.append(dict(name = 'td', attrs = {'class' : 'news_article_author'})) keep_only_tags.append(
keep_only_tags.append(dict(name = 'td', attrs = {'class' : 'news_article_date'})) dict(name='td', attrs={'class': 'news_article_author'}))
keep_only_tags.append(dict(name = 'p')) keep_only_tags.append(
dict(name='td', attrs={'class': 'news_article_date'}))
keep_only_tags.append(dict(name='p'))
feeds = [(u'ALL NEWS', u'http://www.autosport.com/rss/allnews.xml')] feeds = [(u'ALL NEWS', u'http://www.autosport.com/rss/allnews.xml')]

58
recipes/avantaje.recipe
View File

@ -1,7 +1,7 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103' __copyright__ = u'2011, Silviu Cotoar\u0103'
''' '''
avantaje.ro avantaje.ro
@ -9,49 +9,41 @@ avantaje.ro
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Avantaje(BasicNewsRecipe): class Avantaje(BasicNewsRecipe):
title = u'Avantaje' title = u'Avantaje'
__author__ = u'Silviu Cotoar\u0103' __author__ = u'Silviu Cotoar\u0103'
description = u'' description = u''
publisher = u'Avantaje' publisher = u'Avantaje'
oldest_article = 25 oldest_article = 25
language = 'ro' language = 'ro'
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
category = 'Ziare,Reviste,Stiri' category = 'Ziare,Reviste,Stiri'
encoding = 'utf-8' encoding = 'utf-8'
cover_url = 'http://www.avantaje.ro/images/default/logo.gif' cover_url = 'http://www.avantaje.ro/images/default/logo.gif'
conversion_options = { conversion_options = {
'comments' : description 'comments': description, 'tags': category, 'language': language, 'publisher': publisher
,'tags' : category }
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'id':'articol'}) dict(name='div', attrs={'id': 'articol'}), dict(name='div', attrs={
, dict(name='div', attrs={'class':'gallery clearfix'}) 'class': 'gallery clearfix'}), dict(name='div', attrs={'align': 'justify'})
, dict(name='div', attrs={'align':'justify'}) ]
]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'id':['color_sanatate_box']}) dict(name='div', attrs={'id': ['color_sanatate_box']}), dict(name='div', attrs={'class': ['nav']}), dict(name='div', attrs={'class': ['voteaza_art']}), dict(name='div', attrs={'class': ['bookmark']}), dict(name='div', attrs={'class': ['links clearfix']}), dict(name='div', attrs={'class': ['title']}) # noqa
, dict(name='div', attrs={'class':['nav']}) ]
, dict(name='div', attrs={'class':['voteaza_art']})
, dict(name='div', attrs={'class':['bookmark']})
, dict(name='div', attrs={'class':['links clearfix']})
, dict(name='div', attrs={'class':['title']})
]
remove_tags_after = [ remove_tags_after = [
dict(name='div', attrs={'class':['title']}) dict(name='div', attrs={'class': ['title']})
] ]
feeds = [ feeds = [
(u'Feeds', u'http://feeds.feedburner.com/Avantaje') (u'Feeds', u'http://feeds.feedburner.com/Avantaje')
] ]
def preprocess_html(self, soup): def preprocess_html(self, soup):
return self.adeify_images(soup) return self.adeify_images(soup)

52
recipes/aventurilapescuit.recipe
View File

@ -1,7 +1,7 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103' __copyright__ = u'2011, Silviu Cotoar\u0103'
''' '''
aventurilapescuit.ro aventurilapescuit.ro
@ -9,43 +9,41 @@ aventurilapescuit.ro
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AventuriLaPescuit(BasicNewsRecipe): class AventuriLaPescuit(BasicNewsRecipe):
title = u'Aventuri La Pescuit' title = u'Aventuri La Pescuit'
__author__ = u'Silviu Cotoar\u0103' __author__ = u'Silviu Cotoar\u0103'
description = 'Aventuri La Pescuit' description = 'Aventuri La Pescuit'
publisher = 'Aventuri La Pescuit' publisher = 'Aventuri La Pescuit'
oldest_article = 5 oldest_article = 5
language = 'ro' language = 'ro'
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
category = 'Ziare,Pescuit,Hobby' category = 'Ziare,Pescuit,Hobby'
encoding = 'utf-8' encoding = 'utf-8'
cover_url = 'http://www.aventurilapescuit.ro/images/logo.gif' cover_url = 'http://www.aventurilapescuit.ro/images/logo.gif'
conversion_options = { conversion_options = {
'comments' : description 'comments': description, 'tags': category, 'language': language, 'publisher': publisher
,'tags' : category }
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'id':'Article'}) dict(name='div', attrs={'id': 'Article'})
] ]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class':['right option']}) dict(name='div', attrs={'class': ['right option']}), dict(
, dict(name='iframe', attrs={'scrolling':['no']}) name='iframe', attrs={'scrolling': ['no']})
] ]
remove_tags_after = [ remove_tags_after = [
dict(name='iframe', attrs={'scrolling':['no']}) dict(name='iframe', attrs={'scrolling': ['no']})
] ]
feeds = [ feeds = [
(u'Feeds', u'http://www.aventurilapescuit.ro/sections/rssread/1') (u'Feeds', u'http://www.aventurilapescuit.ro/sections/rssread/1')
] ]
def preprocess_html(self, soup): def preprocess_html(self, soup):
return self.adeify_images(soup) return self.adeify_images(soup)

68
recipes/avto-magazin.recipe
View File

@ -4,44 +4,44 @@ __copyright__ = '2010, BlonG'
avto-magazin.si avto-magazin.si
''' '''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Dnevnik(BasicNewsRecipe): class Dnevnik(BasicNewsRecipe):
title = u'Avto Magazin' title = u'Avto Magazin'
__author__ = u'BlonG' __author__ = u'BlonG'
description = u'Za avtomobilisti\xc4\x8dne frike, poznavalce in nedeljske \xc5\xa1oferje.' description = u'Za avtomobilisti\xc4\x8dne frike, poznavalce in nedeljske \xc5\xa1oferje.'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 20 max_articles_per_feed = 20
labguage = 'sl' labguage = 'sl'
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
language = 'sl' language = 'sl'
conversion_options = {'linearize_tables' : True} conversion_options = {'linearize_tables': True}
cover_url = 'https://sites.google.com/site/javno2010/home/avto_magazin_cover.jpg'
cover_url = 'https://sites.google.com/site/javno2010/home/avto_magazin_cover.jpg' extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
extra_css = ''' keep_only_tags = [
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;} dict(name='div', attrs={'id': '_iprom_inStream'}),
h2{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;} # dict(name='div', attrs={'class':'entry-content'}),
p{font-family:Arial,Helvetica,sans-serif;font-size:small;} ]
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
keep_only_tags = [ remove_tags = [
dict(name='div', attrs={'id':'_iprom_inStream'}), dict(name='div', attrs={'id': 'voteConfirmation'}),
# dict(name='div', attrs={'class':'entry-content'}), dict(name='div', attrs={'id': 'InsideVote'}),
] dict(name='div', attrs={'class': 'Zone234'}),
dict(name='div', attrs={'class': 'Comments'}),
dict(name='div', attrs={'class': 'sorodneNovice'}),
dict(name='div', attrs={'id': 'footer'}),
]
remove_tags = [ feeds = [
dict(name='div', attrs={'id':'voteConfirmation'}), (u'Novice', u'http://www.avto-magazin.si/rss/')
dict(name='div', attrs={'id':'InsideVote'}), ]
dict(name='div', attrs={'class':'Zone234'}),
dict(name='div', attrs={'class':'Comments'}),
dict(name='div', attrs={'class':'sorodneNovice'}),
dict(name='div', attrs={'id':'footer'}),
]
feeds = [
(u'Novice', u'http://www.avto-magazin.si/rss/')
]

63
recipes/axxon_magazine.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
''' '''
axxon.com.ar axxon.com.ar
@ -6,35 +6,33 @@ axxon.com.ar
from calibre import strftime from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Axxon_news(BasicNewsRecipe): class Axxon_news(BasicNewsRecipe):
title = 'Revista Axxon' title = 'Revista Axxon'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Axxon, Ciencia Ficcion en Bits' description = 'Axxon, Ciencia Ficcion en Bits'
publisher = 'Revista Axxon - Ciencia Ficcion' publisher = 'Revista Axxon - Ciencia Ficcion'
category = 'SF, Argentina' category = 'SF, Argentina'
oldest_article = 31 oldest_article = 31
delay = 1 delay = 1
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = False no_stylesheets = False
use_embedded_content = False use_embedded_content = False
language = 'es_AR' language = 'es_AR'
encoding = 'utf-8' encoding = 'utf-8'
publication_type = 'magazine' publication_type = 'magazine'
INDEX = 'http://axxon.com.ar/rev/' 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} ' 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 = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'class': 'post'})]
keep_only_tags = [dict(name='div', attrs={'class':'post'})] remove_tags = [dict(name=['object', 'link', 'iframe', 'embed', 'img'])]
remove_tags = [dict(name=['object','link','iframe','embed','img'])] remove_tags_after = [
remove_tags_after = [dict(attrs={'class':['editorial','correo','biografia','articulo']})] dict(attrs={'class': ['editorial', 'correo', 'biografia', 'articulo']})]
remove_attributes = ['width','height','font','border','align'] remove_attributes = ['width', 'height', 'font', 'border', 'align']
def parse_index(self): def parse_index(self):
articles = [] articles = []
@ -44,21 +42,16 @@ class Axxon_news(BasicNewsRecipe):
description = '' description = ''
title_prefix = '' title_prefix = ''
feed_link = item.find('a') feed_link = item.find('a')
if feed_link and feed_link.has_key('href') and feed_link['href'].startswith('?p='): if feed_link and feed_link.has_key('href') and feed_link['href'].startswith('?p='): # noqa
url = self.INDEX + feed_link['href'] url = self.INDEX + feed_link['href']
title = title_prefix + self.tag_to_string(feed_link) title = title_prefix + self.tag_to_string(feed_link)
date = strftime(self.timefmt) date = strftime(self.timefmt)
articles.append({ articles.append({
'title' :title 'title': title, 'date': date, 'url': url, 'description': description
,'date' :date })
,'url' :url
,'description':description
})
return [(soup.head.title.string, articles)] return [(soup.head.title.string, articles)]
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
return self.adeify_images(soup) return self.adeify_images(soup)

59
recipes/axxon_news.recipe
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
''' '''
axxon.com.ar axxon.com.ar
@ -8,55 +8,50 @@ axxon.com.ar
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag from calibre.ebooks.BeautifulSoup import Tag
class Axxon_news(BasicNewsRecipe): class Axxon_news(BasicNewsRecipe):
title = 'Axxon noticias' title = 'Axxon noticias'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Axxon, Ciencia Ficcion en Bits' description = 'Axxon, Ciencia Ficcion en Bits'
publisher = 'Axxon' publisher = 'Axxon'
category = 'news, SF, Argentina, science, movies' category = 'news, SF, Argentina, science, movies'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = False no_stylesheets = False
use_embedded_content = False use_embedded_content = False
language = 'es_AR' language = 'es_AR'
lang = 'es-AR' lang = 'es-AR'
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': lang, 'pretty_print': True
, 'tags' : category }
, 'publisher' : publisher
, 'language' : lang
, 'pretty_print' : True
}
keep_only_tags = [dict(name='div', attrs={'class': 'post'})]
keep_only_tags = [dict(name='div', attrs={'class':'post'})] remove_tags = [dict(name=['object', 'link', 'iframe', 'embed'])]
remove_tags = [dict(name=['object','link','iframe','embed'])] feeds = [(u'Noticias', u'http://axxon.com.ar/noticias/feed/')]
feeds = [(u'Noticias', u'http://axxon.com.ar/noticias/feed/')]
remove_attributes = ['style','width','height','font','border','align']
remove_attributes = ['style', 'width', 'height', 'font', 'border', 'align']
def adeify_images2(cls, soup): def adeify_images2(cls, soup):
for item in soup.findAll('img'): for item in soup.findAll('img'):
for attrib in ['height','width','border','align','style']: for attrib in ['height', 'width', 'border', 'align', 'style']:
if item.has_key(attrib): if item.has_key(attrib): # noqa
del item[attrib] del item[attrib]
oldParent = item.parent oldParent = item.parent
if oldParent.name == 'a': if oldParent.name == 'a':
oldParent.name == 'p' oldParent.name == 'p'
myIndex = oldParent.contents.index(item) myIndex = oldParent.contents.index(item)
brtag = Tag(soup,'br') brtag = Tag(soup, 'br')
oldParent.insert(myIndex+1,brtag) oldParent.insert(myIndex + 1, brtag)
return soup return soup
def preprocess_html(self, soup): def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang soup.html['lang'] = self.lang
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)]) mlang = Tag(soup, 'meta', [
soup.html.insert(0,mlang) ("http-equiv", "Content-Language"), ("content", self.lang)])
soup.html.insert(0, mlang)
return self.adeify_images2(soup) return self.adeify_images2(soup)

65
recipes/azstarnet.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
''' '''
azstarnet.com azstarnet.com
@ -7,53 +7,47 @@ azstarnet.com
import urllib import urllib
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Azstarnet(BasicNewsRecipe): class Azstarnet(BasicNewsRecipe):
title = 'Arizona Daily Star' title = 'Arizona Daily Star'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'news from Arizona' description = 'news from Arizona'
language = 'en' language = 'en'
publisher = 'azstarnet.com' publisher = 'azstarnet.com'
category = 'news, politics, Arizona, USA' category = 'news, politics, Arizona, USA'
oldest_article = 3 oldest_article = 3
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
encoding = 'utf-8' encoding = 'utf-8'
masthead_url = 'http://azstarnet.com/content/tncms/live/global/resources/images/logo.gif' masthead_url = 'http://azstarnet.com/content/tncms/live/global/resources/images/logo.gif'
needs_subscription = True needs_subscription = True
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
}
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
br.open('http://azstarnet.com/') br.open('http://azstarnet.com/')
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({ 'm':'login' data = urllib.urlencode({'m': 'login', 'u': self.username, 'p': self.password, 'z': 'http://azstarnet.com/'
,'u':self.username })
,'p':self.password br.open('http://azstarnet.com/app/registration/proxy.php', data)
,'z':'http://azstarnet.com/'
})
br.open('http://azstarnet.com/app/registration/proxy.php',data)
return br return br
remove_tags = [dict(name=['object','link','iframe','base','img'])] remove_tags = [dict(name=['object', 'link', 'iframe', 'base', 'img'])]
feeds = [ feeds = [
(u'Local News' , u'http://azstarnet.com/search/?f=rss&t=article&c=news/local&l=25&s=start_time&sd=desc')
,(u'National News' , u'http://azstarnet.com/search/?f=rss&t=article&c=news/national&l=25&s=start_time&sd=desc') (u'Local News', u'http://azstarnet.com/search/?f=rss&t=article&c=news/local&l=25&s=start_time&sd=desc'),
,(u'World News' , u'http://azstarnet.com/search/?f=rss&t=article&c=news/world&l=25&s=start_time&sd=desc') (u'National News', u'http://azstarnet.com/search/?f=rss&t=article&c=news/national&l=25&s=start_time&sd=desc'),
,(u'Sports' , u'http://azstarnet.com/search/?f=rss&t=article&c=sports&l=25&s=start_time&sd=desc') (u'World News', u'http://azstarnet.com/search/?f=rss&t=article&c=news/world&l=25&s=start_time&sd=desc'),
,(u'Opinion' , u'http://azstarnet.com/search/?f=rss&t=article&c=news/opinion&l=25&s=start_time&sd=desc') (u'Sports', u'http://azstarnet.com/search/?f=rss&t=article&c=sports&l=25&s=start_time&sd=desc'),
,(u'Movies' , u'http://azstarnet.com/search/?f=rss&t=article&c=entertainment/movies&l=25&s=start_time&sd=desc') (u'Opinion', u'http://azstarnet.com/search/?f=rss&t=article&c=news/opinion&l=25&s=start_time&sd=desc'),
,(u'Food' , u'http://azstarnet.com/search/?f=rss&t=article&c=lifestyles/food-and-cooking&l=25&s=start_time&sd=desc') (u'Movies', u'http://azstarnet.com/search/?f=rss&t=article&c=entertainment/movies&l=25&s=start_time&sd=desc'),
] (u'Food', u'http://azstarnet.com/search/?f=rss&t=article&c=lifestyles/food-and-cooking&l=25&s=start_time&sd=desc')
]
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
@ -62,4 +56,3 @@ class Azstarnet(BasicNewsRecipe):
def print_version(self, url): def print_version(self, url):
return url + '?print=1' return url + '?print=1'

53
recipes/b365realitatea.recipe
View File

@ -1,6 +1,6 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103' __copyright__ = u'2011, Silviu Cotoar\u0103'
''' '''
b365.realitatea.net b365.realitatea.net
@ -8,45 +8,40 @@ b365.realitatea.net
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class b365Realitatea(BasicNewsRecipe): class b365Realitatea(BasicNewsRecipe):
title = u'b365 Realitatea' title = u'b365 Realitatea'
__author__ = u'Silviu Cotoar\u0103' __author__ = u'Silviu Cotoar\u0103'
publisher = u'b365 Realitatea' publisher = u'b365 Realitatea'
description = u'b365 Realitatea' description = u'b365 Realitatea'
oldest_article = 5 oldest_article = 5
language = 'ro' language = 'ro'
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
category = 'Ziare,Romania,Bucuresti' category = 'Ziare,Romania,Bucuresti'
encoding = 'utf-8' encoding = 'utf-8'
cover_url = 'http://b365.realitatea.net/wp-content/themes/b/images/b365-logo.png' cover_url = 'http://b365.realitatea.net/wp-content/themes/b/images/b365-logo.png'
conversion_options = { conversion_options = {
'comments' : description 'comments': description, 'tags': category, 'language': language, 'publisher': publisher
,'tags' : category }
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'class':'newsArticle'}) dict(name='div', attrs={'class': 'newsArticle'})
] ]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class':'date'}) dict(name='div', attrs={'class': 'date'}), dict(name='dic', attrs={'class': 'addthis_toolbox addthis_default_style'}), dict(
, dict(name='dic', attrs={'class':'addthis_toolbox addthis_default_style'}) name='div', attrs={'class': 'related_posts'}), dict(name='div', attrs={'id': 'RelevantiWidget'})
, dict(name='div', attrs={'class':'related_posts'}) ]
, dict(name='div', attrs={'id':'RelevantiWidget'})
]
remove_tags_after = [ remove_tags_after = [
dict(name='div', attrs={'id':'RelevantiWidget'}) dict(name='div', attrs={'id': 'RelevantiWidget'})
] ]
feeds = [ feeds = [
(u'\u0218tiri', u'http://b365.realitatea.net/rss-full/') (u'\u0218tiri', u'http://b365.realitatea.net/rss-full/')
] ]
def preprocess_html(self, soup): def preprocess_html(self, soup):
return self.adeify_images(soup) return self.adeify_images(soup)

92
recipes/b92.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008-2012, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2012, Darko Miletic <darko.miletic at gmail.com>'
''' '''
b92.net b92.net
@ -7,63 +7,63 @@ b92.net
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class B92(BasicNewsRecipe): class B92(BasicNewsRecipe):
title = 'B92' title = 'B92'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Najnovije vesti iz Srbije, regiona i sveta, aktuelne teme iz sveta politike, ekonomije, drustva, foto galerija, kolumne' description = 'Najnovije vesti iz Srbije, regiona i sveta, aktuelne teme iz sveta politike, ekonomije, drustva, foto galerija, kolumne'
publisher = 'B92' publisher = 'B92'
category = 'news, politics, Serbia' category = 'news, politics, Serbia'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
encoding = 'cp1250' encoding = 'cp1250'
language = 'sr' language = 'sr'
publication_type = 'newsportal' publication_type = 'newsportal'
masthead_url = 'http://b92s.net/v4/img/new-logo.png' masthead_url = 'http://b92s.net/v4/img/new-logo.png'
extra_css = """ extra_css = """
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
body{font-family: Arial,Helvetica,sans1,sans-serif} body{font-family: Arial,Helvetica,sans1,sans-serif}
.article-info2,.article-info1{text-transform: uppercase; font-size: small} .article-info2,.article-info1{text-transform: uppercase; font-size: small}
img{display: block} img{display: block}
.sms{font-weight: bold} .sms{font-weight: bold}
""" """
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher': publisher
, 'language' : language
, 'linearize_tables' : True
}
preprocess_regexps = [
(re.compile(u'\u0110'), lambda match: u'\u00D0'),
(re.compile(r'<html.*?<body>', re.DOTALL|re.IGNORECASE), lambda match: '<html><head><title>something</title></head><body>')
]
keep_only_tags = [dict(attrs={'class':['article-info1','article-text']})]
remove_attributes = ['width','height','align','hspace','vspace','border','lang','xmlns:fb']
remove_tags = [
dict(name=['embed','link','base','meta','iframe'])
,dict(attrs={'id':'social'})
]
feeds = [ conversion_options = {
(u'Vesti' , u'http://www.b92.net/info/rss/vesti.xml' ) 'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'linearize_tables': True
,(u'Biz' , u'http://www.b92.net/info/rss/biz.xml' ) }
,(u'Sport' , u'http://www.b92.net/info/rss/sport.xml' )
,(u'Zivot' , u'http://www.b92.net/info/rss/zivot.xml' ) preprocess_regexps = [
,(u'Kultura' , u'http://www.b92.net/info/rss/kultura.xml' ) (re.compile(u'\u0110'), lambda match: u'\u00D0'),
,(u'Automobili' , u'http://www.b92.net/info/rss/automobili.xml') (re.compile(r'<html.*?<body>', re.DOTALL | re.IGNORECASE),
,(u'Tehnopolis' , u'http://www.b92.net/info/rss/tehnopolis.xml') lambda match: '<html><head><title>something</title></head><body>')
] ]
keep_only_tags = [dict(attrs={'class': ['article-info1', 'article-text']})]
remove_attributes = ['width', 'height', 'align',
'hspace', 'vspace', 'border', 'lang', 'xmlns:fb']
remove_tags = [
dict(name=['embed', 'link', 'base', 'meta', 'iframe']), dict(
attrs={'id': 'social'})
]
feeds = [
(u'Vesti', u'http://www.b92.net/info/rss/vesti.xml'),
(u'Biz', u'http://www.b92.net/info/rss/biz.xml'),
(u'Sport', u'http://www.b92.net/info/rss/sport.xml'),
(u'Zivot', u'http://www.b92.net/info/rss/zivot.xml'),
(u'Kultura', u'http://www.b92.net/info/rss/kultura.xml'),
(u'Automobili', u'http://www.b92.net/info/rss/automobili.xml'),
(u'Tehnopolis', u'http://www.b92.net/info/rss/tehnopolis.xml')
]
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
for alink in soup.findAll('a'): for alink in soup.findAll('a'):
if alink.string is not None: if alink.string is not None:
tstr = alink.string tstr = alink.string
alink.replaceWith(tstr) alink.replaceWith(tstr)
return soup return soup

Some files were not shown because too many files have changed in this diff Show More