mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-08-05 08:40:13 -04:00
remove non-working recipes
This commit is contained in:
Kovid Goyal
parent
f8447df256
commit
79eae80788
@ -1,74 +0,0 @@
|
|||||||
# -*- mode: python -*-
|
|
||||||
# -*- coding: utf-8 -*-
|
|
||||||
|
|
||||||
__license__ = 'GPL v3'
|
|
||||||
__copyright__ = '2011 - 2016, Darko Miletic <darko.miletic at gmail.com>'
|
|
||||||
'''
|
|
||||||
www.frontline.in
|
|
||||||
'''
|
|
||||||
|
|
||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
|
||||||
|
|
||||||
|
|
||||||
class Frontlineonnet(BasicNewsRecipe):
|
|
||||||
title = 'Frontline'
|
|
||||||
__author__ = 'Darko Miletic'
|
|
||||||
description = """
|
|
||||||
India's National Magazine
|
|
||||||
Frontline, the fortnightly English magazine from the stable of The Hindu, has been a distinguished presence in the media world for the past 27 years.
|
|
||||||
As per the Indian Readership Survey (IRS) Q4, its average issue readership is 152,000.
|
|
||||||
|
|
||||||
Frontline's journalism is characterised by in-depth, insightful reporting and analysis of issues and events at the regional, national and international levels.
|
|
||||||
It excels in long-form journalism.
|
|
||||||
|
|
||||||
The topics Frontline covers range from politics, economics and social issues to the environment, nature, culture and cinema.
|
|
||||||
Its cover stories are comprehensive.
|
|
||||||
"""
|
|
||||||
publisher = 'Frontline'
|
|
||||||
category = 'news, politics, India'
|
|
||||||
no_stylesheets = True
|
|
||||||
oldest_article = 15
|
|
||||||
INDEX = 'http://www.frontline.in/'
|
|
||||||
use_embedded_content = False
|
|
||||||
encoding = 'utf-8'
|
|
||||||
language = 'en_IN'
|
|
||||||
publication_type = 'magazine'
|
|
||||||
auto_cleanup = True
|
|
||||||
masthead_url = 'http://www.frontline.in/template/1-0-1/gfx/fl_logo.jpg'
|
|
||||||
extra_css = """
|
|
||||||
body{font-family: Georgia,"Times New Roman",serif}
|
|
||||||
img{margin-top:0.5em; margin-bottom: 0.7em; display: block}
|
|
||||||
"""
|
|
||||||
|
|
||||||
conversion_options = {
|
|
||||||
'comment' : description,
|
|
||||||
'tags' : category ,
|
|
||||||
'publisher': publisher ,
|
|
||||||
'language' : language
|
|
||||||
}
|
|
||||||
|
|
||||||
feeds = [
|
|
||||||
(u'Cover story' , u'http://www.frontline.in/cover-story/?service=rss'),
|
|
||||||
(u'The Nation' , u'http://www.frontline.in/the-nation/?service=rss'),
|
|
||||||
(u'Politics' , u'http://www.frontline.in/politics/?service=rss'),
|
|
||||||
(u'Columns' , u'http://www.frontline.in/columns/?service=rss'),
|
|
||||||
(u'Social Issues' , u'http://www.frontline.in/social-issues/?service=rss'),
|
|
||||||
(u'General issues' , u'http://www.frontline.in/social-issues/general-issues/?service=rss'),
|
|
||||||
(u'Social justice' , u'http://www.frontline.in/social-issues/social-justice/?service=rss'),
|
|
||||||
(u'Arts&Culture' , u'http://www.frontline.in/arts-and-culture/?service=rss'),
|
|
||||||
(u'Economy' , u'http://www.frontline.in/economy/?service=rss'),
|
|
||||||
(u'World Affairs' , u'http://www.frontline.in/world-affairs/?service=rss'),
|
|
||||||
(u'Science&Technology', u'http://www.frontline.in/science-and-technology/?service=rss'),
|
|
||||||
(u'Books' , u'http://www.frontline.in/books/?service=rss'),
|
|
||||||
(u'Sport' , u'http://www.frontline.in/other/sport/?service=rss')
|
|
||||||
]
|
|
||||||
|
|
||||||
def get_cover_url(self):
|
|
||||||
soup = self.index_to_soup(self.INDEX)
|
|
||||||
divtag = soup.find('div', 'smallMagCont')
|
|
||||||
if divtag:
|
|
||||||
return divtag.img['src']
|
|
||||||
return None
|
|
||||||
|
|
||||||
def print_version(self, url):
|
|
||||||
return url.replace('?','?css=print&')
|
|
||||||
@ -1,35 +0,0 @@
|
|||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
|
||||||
|
|
||||||
|
|
||||||
class AdvancedUserRecipe1282101454(BasicNewsRecipe):
|
|
||||||
title = 'West Hawaii Today'
|
|
||||||
__author__ = 'Tony Stegall, fixed by HK'
|
|
||||||
language = 'en'
|
|
||||||
description = 'Westhawaiitoday.com'
|
|
||||||
publisher = 'West Hawaii '
|
|
||||||
category = 'news,Hawaii,USA'
|
|
||||||
oldest_article = 7
|
|
||||||
max_articles_per_feed = 100
|
|
||||||
no_stylesheets = True
|
|
||||||
remove_javascript = True
|
|
||||||
use_embedded_content = True
|
|
||||||
|
|
||||||
masthead_url = 'http://images.townnews.com/westhawaiitoday.com/art/whttoplogo.gif'
|
|
||||||
|
|
||||||
feeds = [
|
|
||||||
('http://www.westhawaiitoday.com/taxonomy/term/2/feed'), # Local News
|
|
||||||
# Local Sports
|
|
||||||
('http://www.westhawaiitoday.com/taxonomy/term/15/feed'),
|
|
||||||
# Local Features
|
|
||||||
('http://www.westhawaiitoday.com/taxonomy/term/4/feed'),
|
|
||||||
# Obituaries
|
|
||||||
('http://www.westhawaiitoday.com/taxonomy/term/12/feed'),
|
|
||||||
# Letters
|
|
||||||
('http://www.westhawaiitoday.com/taxonomy/term/18/feed'),
|
|
||||||
# Editorial
|
|
||||||
('http://www.westhawaiitoday.com/taxonomy/term/19/feed'),
|
|
||||||
# columns
|
|
||||||
('http://www.westhawaiitoday.com/taxonomy/term/20/feed'),
|
|
||||||
# Volcano Update (Sundays)
|
|
||||||
('http://www.westhawaiitoday.com/taxonomy/term/13/feed')
|
|
||||||
]
|
|
||||||
@ -1,51 +0,0 @@
|
|||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
|
||||||
|
|
||||||
|
|
||||||
class AdvancedUserRecipe(BasicNewsRecipe):
|
|
||||||
|
|
||||||
title = 'Heise-online'
|
|
||||||
description = 'News vom Heise-Verlag'
|
|
||||||
__author__ = 'schuster'
|
|
||||||
masthead_url = 'http://www.heise.de/icons/ho/heise_online_logo.gif'
|
|
||||||
publisher = 'Heise Zeitschriften Verlag GmbH & Co. KG'
|
|
||||||
use_embedded_content = False
|
|
||||||
language = 'de'
|
|
||||||
oldest_article = 2
|
|
||||||
max_articles_per_feed = 35
|
|
||||||
rescale_images = True
|
|
||||||
remove_empty_feeds = True
|
|
||||||
timeout = 5
|
|
||||||
no_stylesheets = True
|
|
||||||
|
|
||||||
keep_only_tags = [dict(name='div', attrs={'id': 'mitte_news'}),
|
|
||||||
dict(name='h1', attrs={'class': 'clear'}),
|
|
||||||
dict(name='div', attrs={'class': 'meldung_wrapper'})]
|
|
||||||
|
|
||||||
remove_tags = [dict(id='navi_top_container'),
|
|
||||||
dict(name='p', attrs={'class': 'size80'})]
|
|
||||||
|
|
||||||
feeds = [
|
|
||||||
('Newsticker', 'http://www.heise.de/newsticker/heise.rdf'),
|
|
||||||
('Auto', 'http://www.heise.de/autos/rss/news.rdf'),
|
|
||||||
('Foto ', 'http://www.heise.de/foto/rss/news-atom.xml'),
|
|
||||||
('Mac&i', 'http://www.heise.de/mac-and-i/news.rdf'),
|
|
||||||
('Mobile ', 'http://www.heise.de/mobil/newsticker/heise-atom.xml'),
|
|
||||||
('Netz ', 'http://www.heise.de/netze/rss/netze-atom.xml'),
|
|
||||||
('Open ', 'http://www.heise.de/open/news/news-atom.xml'),
|
|
||||||
('Resale ', 'http://www.heise.de/resale/rss/resale.rdf'),
|
|
||||||
('Security ', 'http://www.heise.de/security/news/news-atom.xml'),
|
|
||||||
('C`t', 'http://www.heise.de/ct/rss/artikel-atom.xml'),
|
|
||||||
('iX', 'http://www.heise.de/ix/news/news.rdf'),
|
|
||||||
('Mach-flott', 'http://www.heise.de/mach-flott/rss/mach-flott-atom.xml'),
|
|
||||||
('Blog: Babel-Bulletin',
|
|
||||||
'http://www.heise.de/developer/rss/babel-bulletin/blog.rdf'),
|
|
||||||
('Blog: Der Dotnet-Doktor',
|
|
||||||
'http://www.heise.de/developer/rss/dotnet-doktor/blog.rdf'),
|
|
||||||
('Blog: Bernds Management-Welt',
|
|
||||||
'http://www.heise.de/developer/rss/bernds-management-welt/blog.rdf'),
|
|
||||||
('Blog: IT conversation',
|
|
||||||
'http://www.heise.de/developer/rss/world-of-it/blog.rdf'),
|
|
||||||
('Blog: Kais bewegtes Web', 'http://www.heise.de/developer/rss/kais-bewegtes-web/blog.rdf')]
|
|
||||||
|
|
||||||
def print_version(self, url):
|
|
||||||
return url + '?view=print'
|
|
||||||
@ -1,127 +0,0 @@
|
|||||||
#!/usr/bin/env python2
|
|
||||||
__license__ = 'GPL v3'
|
|
||||||
__copyright__ = '04 December 2010, desUBIKado'
|
|
||||||
__author__ = 'desUBIKado'
|
|
||||||
__description__ = 'Daily newspaper from Aragon'
|
|
||||||
__version__ = 'v0.08'
|
|
||||||
__date__ = '10, September 2017'
|
|
||||||
'''
|
|
||||||
http://www.heraldo.es/
|
|
||||||
'''
|
|
||||||
|
|
||||||
import time
|
|
||||||
import re
|
|
||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
|
||||||
|
|
||||||
|
|
||||||
class heraldo(BasicNewsRecipe):
|
|
||||||
author = 'desUBIKado'
|
|
||||||
description = 'Daily newspaper from Aragon'
|
|
||||||
title = u'Heraldo de Aragon'
|
|
||||||
publisher = 'Grupo Heraldo'
|
|
||||||
category = 'News, politics, culture, economy, general interest'
|
|
||||||
language = 'es'
|
|
||||||
timefmt = '[%a, %d %b, %Y]'
|
|
||||||
oldest_article = 2
|
|
||||||
delay = 1
|
|
||||||
max_articles_per_feed = 100
|
|
||||||
use_embedded_content = False
|
|
||||||
masthead_url = 'http://aureel.com/es/wp-content/uploads/sites/4/2016/07/Heraldo_de_Arago%CC%81n.png'
|
|
||||||
remove_empty_feeds = True
|
|
||||||
remove_javascript = True
|
|
||||||
no_stylesheets = True
|
|
||||||
|
|
||||||
feeds = [(u'Noticias', u'http://www.heraldo.es/index.php/mod.portadas/mem.rss')]
|
|
||||||
|
|
||||||
keep_only_tags = [
|
|
||||||
dict(
|
|
||||||
name='div',
|
|
||||||
attrs={
|
|
||||||
'class':
|
|
||||||
['row-f2 brd-row-f4 bck-row-f1-f1 padd-t padd-btt con n-marg-btt']
|
|
||||||
}
|
|
||||||
),
|
|
||||||
dict(name='div', attrs={'id': ['dts', 'com']}),
|
|
||||||
dict(name='img', attrs={'class': ['lazy']})
|
|
||||||
]
|
|
||||||
|
|
||||||
remove_tags = [
|
|
||||||
dict(
|
|
||||||
name='a', attrs={'class': ['com flo-r', 'enl-if', 'enl-df', 'next_com']}
|
|
||||||
),
|
|
||||||
dict(
|
|
||||||
name='div',
|
|
||||||
attrs={
|
|
||||||
'class': [
|
|
||||||
'brb-b-s con marg-btt', 'cnt-rel con', 'col5-f1',
|
|
||||||
'tit txt-wh f-s con', 'con cont-top ', 'col5-f1 flo-l',
|
|
||||||
'cnt-rel brr', 'caj_part con', 'caj_topic con'
|
|
||||||
]
|
|
||||||
}
|
|
||||||
),
|
|
||||||
dict(
|
|
||||||
name='div',
|
|
||||||
attrs={
|
|
||||||
'id': [
|
|
||||||
'cont-Top-8760', 'caj-pub', '8760-cpt1', 'caj_topic con',
|
|
||||||
'slider-oferplan', 'cont-Top-'
|
|
||||||
]
|
|
||||||
}
|
|
||||||
),
|
|
||||||
dict(name='form', attrs={'class': 'form'}),
|
|
||||||
dict(
|
|
||||||
name='ul',
|
|
||||||
attrs={'class': ['tabs-nav', 'men_nav con hg_2n', 'lst-not-f2 con ']}
|
|
||||||
),
|
|
||||||
dict(name='span', attrs={'class': ['flo-r']}),
|
|
||||||
dict(name='ul', attrs={'id': ['cont-tags', 'pag-1', 'pag-cnt-I-']})
|
|
||||||
]
|
|
||||||
|
|
||||||
remove_tags_before = dict(name='div', attrs={'id': 'dts'})
|
|
||||||
remove_tags_after = dict(name='div', attrs={'id': 'com'})
|
|
||||||
|
|
||||||
def get_cover_url(self):
|
|
||||||
cover = None
|
|
||||||
st = time.localtime()
|
|
||||||
year = str(st.tm_year)
|
|
||||||
month = "%.2d" % st.tm_mon
|
|
||||||
day = "%.2d" % st.tm_mday
|
|
||||||
|
|
||||||
# http://img.kiosko.net/2017/09/10/es/heraldo_aragon.750.jpg
|
|
||||||
cover = 'http://img.kiosko.net/' + year + '/' + month + '/' + day + '/es/heraldo_aragon.750.jpg'
|
|
||||||
|
|
||||||
br = BasicNewsRecipe.get_browser(self)
|
|
||||||
try:
|
|
||||||
br.open(cover)
|
|
||||||
except:
|
|
||||||
self.log("\nPortada no disponible")
|
|
||||||
cover = 'http://aureel.com/es/wp-content/uploads/sites/4/2016/07/Heraldo_de_Arago%CC%81n.png'
|
|
||||||
return cover
|
|
||||||
|
|
||||||
extra_css = '''
|
|
||||||
h1 {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:28px;}
|
|
||||||
h2 {font-family:georgia,serif; font-style:italic; font-weight:normal;font-size:22px;color:#4D4D4D;}
|
|
||||||
.ladillo {font-family:georgia,serif; font-weight:bold;font-size:18px;}
|
|
||||||
.firm, .sp, .fech, ".com flo-r" {font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:12px;}
|
|
||||||
img{margin-bottom: 0.4em}
|
|
||||||
'''
|
|
||||||
|
|
||||||
preprocess_regexps = [
|
|
||||||
|
|
||||||
# Para separar los comentarios con una linea en blanco
|
|
||||||
(
|
|
||||||
re.compile(r'<div class="tit-f2">', re.DOTALL | re.IGNORECASE),
|
|
||||||
lambda match: '<br /><br /><div class="tit-f2">'
|
|
||||||
),
|
|
||||||
(
|
|
||||||
re.compile(r'<div id="com"', re.DOTALL | re.IGNORECASE),
|
|
||||||
lambda match: '<br><div id="com"'
|
|
||||||
),
|
|
||||||
|
|
||||||
# Para ver las imágenes de las noticias
|
|
||||||
(
|
|
||||||
re.compile(
|
|
||||||
r'<img class="lazy" data-original="', re.DOTALL | re.IGNORECASE
|
|
||||||
), lambda match: '<img src="http://www.heraldo.es'
|
|
||||||
)
|
|
||||||
]
|
|
||||||
@ -1,29 +0,0 @@
|
|||||||
#!/usr/bin/env python2
|
|
||||||
# vim:fileencoding=utf-8
|
|
||||||
# https://manual.calibre-ebook.com/news_recipe.html
|
|
||||||
from __future__ import unicode_literals, division, absolute_import, print_function
|
|
||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
|
||||||
'''
|
|
||||||
Hillerød Posten
|
|
||||||
'''
|
|
||||||
|
|
||||||
|
|
||||||
class HilleroedLokalavisen_dk(BasicNewsRecipe):
|
|
||||||
__author__ = 'CoderAllan.github.com'
|
|
||||||
title = 'Hillerød Posten'
|
|
||||||
description = 'Lokale og regionale nyheder, sport og kultur fra Hillerød, Skævinge og Gørløse på hilleroed.lokalavisen.dk'
|
|
||||||
category = 'newspaper, news, localnews, sport, culture, Denmark'
|
|
||||||
oldest_article = 7
|
|
||||||
max_articles_per_feed = 50
|
|
||||||
auto_cleanup = True
|
|
||||||
language = 'da'
|
|
||||||
|
|
||||||
feeds = [
|
|
||||||
('Seneste nyt fra Hillerød Posten', 'http://hilleroed.lokalavisen.dk/section/senestenytrss'),
|
|
||||||
('Seneste lokale nyheder fra Hillerød Posten', 'http://hilleroed.lokalavisen.dk/section/senestelokalenyhederrss'),
|
|
||||||
('Seneste sport fra Hillerød Posten', 'http://hilleroed.lokalavisen.dk/section/senestesportrss'),
|
|
||||||
('Seneste 112 nyheder fra Hillerød Posten', 'http://hilleroed.lokalavisen.dk/section/seneste112rss'),
|
|
||||||
('Seneste kultur nyheder fra Hillerød Posten', 'http://hilleroed.lokalavisen.dk/section/senestekulturrss'),
|
|
||||||
('Seneste læserbreve fra Hillerød Posten', 'http://hilleroed.lokalavisen.dk/section/senestelaeserbreverss'),
|
|
||||||
|
|
||||||
]
|
|
||||||
@ -1,45 +0,0 @@
|
|||||||
# coding=utf-8
|
|
||||||
|
|
||||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
||||||
|
|
||||||
|
|
||||||
class Hira(BasicNewsRecipe):
|
|
||||||
title = 'Hira'
|
|
||||||
__author__ = 'thomass'
|
|
||||||
description = 'مجلة حراء مجلة علمية ثقافية فكرية تصدر كل شهرين، تعنى بالعلوم الطبيعية والإنسانية والاجتماعية وتحاور أسرار النفس البشرية وآفاق الكون الشاسعة بالمنظور القرآني الإيماني في تآلف وتناسب بين العلم والإيمان، والعقل والقلب، والفكر والواقع.' # noqa
|
|
||||||
oldest_article = 63
|
|
||||||
max_articles_per_feed = 50
|
|
||||||
no_stylesheets = True
|
|
||||||
use_embedded_content = False
|
|
||||||
encoding = 'utf-8'
|
|
||||||
publisher = 'thomass'
|
|
||||||
category = 'News'
|
|
||||||
language = 'ar'
|
|
||||||
publication_type = 'magazine'
|
|
||||||
extra_css = ' .title-detail-wrap{ font-weight: bold ;text-align:right;color:#FF0000;font-size:25px}.title-detail{ font-family:sans-serif;text-align:right;} ' # noqa
|
|
||||||
|
|
||||||
conversion_options = {
|
|
||||||
'tags': category, 'language': language, 'publisher': publisher, 'linearize_tables': True, 'base-font-size': '10'
|
|
||||||
}
|
|
||||||
keep_only_tags = [
|
|
||||||
dict(name='div', attrs={'class': ['title-detail']})
|
|
||||||
]
|
|
||||||
|
|
||||||
remove_tags = [
|
|
||||||
dict(name='div', attrs={'class': ['clear', 'bbsp']}),
|
|
||||||
]
|
|
||||||
|
|
||||||
remove_attributes = [
|
|
||||||
'width', 'height'
|
|
||||||
]
|
|
||||||
|
|
||||||
feeds = [
|
|
||||||
(u'حراء', 'http://open.dapper.net/services/hira'),
|
|
||||||
]
|
|
||||||
|
|
||||||
def preprocess_html(self, soup):
|
|
||||||
for alink in soup.findAll('a'):
|
|
||||||
if alink.string is not None:
|
|
||||||
tstr = alink.string
|
|
||||||
alink.replaceWith(tstr)
|
|
||||||
return soup
|
|
||||||
@ -1,30 +0,0 @@
|
|||||||
#!/usr/bin/env python2
|
|
||||||
|
|
||||||
__license__ = 'GPL v3'
|
|
||||||
__copyright__ = '2010, matek09, matek09@gmail.com'
|
|
||||||
|
|
||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
|
||||||
|
|
||||||
|
|
||||||
class Histmag(BasicNewsRecipe):
|
|
||||||
title = u'Histmag'
|
|
||||||
oldest_article = 7
|
|
||||||
max_articles_per_feed = 100
|
|
||||||
cover_url = 'http://histmag.org/grafika/loga/histmag-logo-2-300px.png'
|
|
||||||
__author__ = 'matek09'
|
|
||||||
description = u"Artykuly historyczne i publicystyczne"
|
|
||||||
encoding = 'utf-8'
|
|
||||||
extra_css = '''.center img {display: block;}'''
|
|
||||||
no_stylesheets = True
|
|
||||||
language = 'pl'
|
|
||||||
remove_javascript = True
|
|
||||||
keep_only_tags = [dict(id='article')]
|
|
||||||
remove_tags = [dict(name='p', attrs={
|
|
||||||
'class': 'article-tags'}), dict(attrs={'class': 'twitter-share-button'})]
|
|
||||||
|
|
||||||
feeds = [
|
|
||||||
(u'Wszystkie', u'http://histmag.org/rss/wszystkie.xml'),
|
|
||||||
(u'Wydarzenia', u'http://histmag.org/rss/wydarzenia.xml'),
|
|
||||||
(u'Recenzje', u'http://histmag.org/rss/recenzje.xml'),
|
|
||||||
(u'Artykuły historyczne', u'http://histmag.org/rss/historia.xml'),
|
|
||||||
(u'Publicystyka', u'http://histmag.org/rss/publicystyka.xml')]
|
|
||||||
@ -1,22 +0,0 @@
|
|||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
|
||||||
|
|
||||||
|
|
||||||
class historia_news(BasicNewsRecipe):
|
|
||||||
title = u'historia-news'
|
|
||||||
__author__ = 'fenuks'
|
|
||||||
description = u'Historia-news to portal dla ludzi kochających historię. Najnowsze newsy z historii bliższej i dalszej, archeologii, paleontologii oraz ciekawostki i podcasty z historii kultury, sportu, motoryzacji i inne.' # noqa
|
|
||||||
masthead_url = 'http://historia-news.pl/templates/hajak4/images/header.jpg'
|
|
||||||
cover_url = 'http://www.historia-news.pl/templates/hajak4/images/header.jpg'
|
|
||||||
category = 'history'
|
|
||||||
language = 'pl'
|
|
||||||
oldest_article = 7
|
|
||||||
max_articles_per_feed = 100
|
|
||||||
no_stylesheets = True
|
|
||||||
remove_empty_feeds = True
|
|
||||||
remove_tags = [dict(name='form'), dict(name='img', attrs={'alt': 'Print'}), dict(
|
|
||||||
attrs={'class': ['commbutt', 'cpr']}), dict(id=['plusone', 'facebook'])]
|
|
||||||
feeds = [(u'Wiadomo\u015bci', u'http://historia-news.pl/wiadomoci.feed?type=rss'),
|
|
||||||
(u'Artyku\u0142y', u'http://historia-news.pl/artykuy.feed?type=rss')]
|
|
||||||
|
|
||||||
def print_version(self, url):
|
|
||||||
return url + '?tmpl=component&print=1&layout=default&page='
|
|
||||||
@ -1,46 +0,0 @@
|
|||||||
#!/usr/bin/env python2
|
|
||||||
# -*- coding: utf-8 -*-
|
|
||||||
|
|
||||||
__license__ = 'GPL v3'
|
|
||||||
__copyright__ = u'2011, Silviu Cotoar\u0103'
|
|
||||||
'''
|
|
||||||
historia.ro
|
|
||||||
'''
|
|
||||||
|
|
||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
|
||||||
|
|
||||||
|
|
||||||
class HistoriaRo(BasicNewsRecipe):
|
|
||||||
title = u'Historia'
|
|
||||||
__author__ = u'Silviu Cotoar\u0103'
|
|
||||||
description = ''
|
|
||||||
publisher = 'Historia'
|
|
||||||
oldest_article = 5
|
|
||||||
language = 'ro'
|
|
||||||
max_articles_per_feed = 100
|
|
||||||
no_stylesheets = True
|
|
||||||
use_embedded_content = False
|
|
||||||
category = 'Ziare,Reviste,Istorie'
|
|
||||||
encoding = 'utf-8'
|
|
||||||
cover_url = 'http://www.historia.ro/sites/all/themes/historia/images/historia.png'
|
|
||||||
|
|
||||||
conversion_options = {
|
|
||||||
'comments': description, 'tags': category, 'language': language, 'publisher': publisher
|
|
||||||
}
|
|
||||||
|
|
||||||
keep_only_tags = [
|
|
||||||
dict(name='div', attrs={'class': 'c_antet_title'}), dict(name='a', attrs={
|
|
||||||
'class': 'overlaybox'}), dict(name='div', attrs={'class': 'art_content'})
|
|
||||||
]
|
|
||||||
|
|
||||||
remove_tags = [
|
|
||||||
dict(name='div', attrs={'class': ['fl_left']}), dict(name='div', attrs={
|
|
||||||
'id': ['article_toolbar']}), dict(name='div', attrs={'class': ['zoom_cont']})
|
|
||||||
]
|
|
||||||
|
|
||||||
feeds = [
|
|
||||||
(u'Feeds', u'http://www.historia.ro/rss.xml')
|
|
||||||
]
|
|
||||||
|
|
||||||
def preprocess_html(self, soup):
|
|
||||||
return self.adeify_images(soup)
|
|
||||||
@ -1,41 +0,0 @@
|
|||||||
#!/usr/bin/env python2
|
|
||||||
# -*- coding: utf-8 -*-
|
|
||||||
|
|
||||||
__license__ = 'GPL v3'
|
|
||||||
__copyright__ = u'2011, Silviu Cotoar\u0103'
|
|
||||||
'''
|
|
||||||
hit.ro
|
|
||||||
'''
|
|
||||||
|
|
||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
|
||||||
|
|
||||||
|
|
||||||
class Hit(BasicNewsRecipe):
|
|
||||||
title = u'HIT'
|
|
||||||
__author__ = u'Silviu Cotoar\u0103'
|
|
||||||
description = 'IT'
|
|
||||||
publisher = 'HIT'
|
|
||||||
oldest_article = 5
|
|
||||||
language = 'ro'
|
|
||||||
max_articles_per_feed = 100
|
|
||||||
no_stylesheets = True
|
|
||||||
use_embedded_content = False
|
|
||||||
category = 'Ziare,Reviste,IT'
|
|
||||||
encoding = 'utf-8'
|
|
||||||
cover_url = 'http://www.hit.ro/lib/images/frontend/hit_logo.png'
|
|
||||||
|
|
||||||
conversion_options = {
|
|
||||||
'comments': description, 'tags': category, 'language': language, 'publisher': publisher
|
|
||||||
}
|
|
||||||
|
|
||||||
keep_only_tags = [
|
|
||||||
dict(name='h1', attrs={'class': 'art_titl'}), dict(
|
|
||||||
name='div', attrs={'id': 'continut_articol'})
|
|
||||||
]
|
|
||||||
|
|
||||||
feeds = [
|
|
||||||
(u'Feeds', u'http://www.hit.ro/rss')
|
|
||||||
]
|
|
||||||
|
|
||||||
def preprocess_html(self, soup):
|
|
||||||
return self.adeify_images(soup)
|
|
||||||
@ -1,69 +0,0 @@
|
|||||||
#!/usr/bin/env python2
|
|
||||||
|
|
||||||
__license__ = 'GPL v3'
|
|
||||||
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
||||||
'''
|
|
||||||
www.hln.be
|
|
||||||
'''
|
|
||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
|
||||||
from calibre.ebooks.BeautifulSoup import Tag
|
|
||||||
|
|
||||||
|
|
||||||
def new_tag(soup, name, attrs=()):
|
|
||||||
impl = getattr(soup, 'new_tag', None)
|
|
||||||
if impl is not None:
|
|
||||||
return impl(name, attrs=dict(attrs))
|
|
||||||
return Tag(soup, name, attrs=attrs or None)
|
|
||||||
|
|
||||||
|
|
||||||
class HLN_be(BasicNewsRecipe):
|
|
||||||
title = 'Het Belang Van Limburg'
|
|
||||||
__author__ = 'Darko Miletic and Sujata Raman'
|
|
||||||
description = 'News from Belgium in Dutch'
|
|
||||||
publisher = 'Het Belang Van Limburg'
|
|
||||||
category = 'news, politics, Belgium'
|
|
||||||
oldest_article = 2
|
|
||||||
max_articles_per_feed = 100
|
|
||||||
no_stylesheets = True
|
|
||||||
use_embedded_content = False
|
|
||||||
encoding = 'utf-8'
|
|
||||||
language = 'nl_BE'
|
|
||||||
|
|
||||||
lang = 'nl-BE'
|
|
||||||
direction = 'ltr'
|
|
||||||
|
|
||||||
html2lrf_options = [
|
|
||||||
'--comment', description, '--category', category, '--publisher', publisher
|
|
||||||
]
|
|
||||||
|
|
||||||
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + \
|
|
||||||
category + \
|
|
||||||
'"\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
|
|
||||||
|
|
||||||
extra_css = '''
|
|
||||||
body{font-family:"Verdana",sans-serif; font-size:80%;}
|
|
||||||
.h1{font-family:"Verdana",sans-serif; font-size:large; font-weight:bold;}
|
|
||||||
.captionEmbeddedMasterObject{font-style:italic; font-size:80%;}
|
|
||||||
.gen_footnote3{font-size:80%; color: #666666;}
|
|
||||||
'''
|
|
||||||
|
|
||||||
keep_only_tags = [dict(name='div', attrs={'class': 'art_box2'})]
|
|
||||||
remove_tags = [
|
|
||||||
dict(name=['embed', 'object'])
|
|
||||||
]
|
|
||||||
|
|
||||||
feeds = [(u'Alle nieuws', u'http://www.hln.be/rss.xml')]
|
|
||||||
|
|
||||||
def preprocess_html(self, soup):
|
|
||||||
del soup.body['onload']
|
|
||||||
for item in soup.findAll(style=True):
|
|
||||||
del item['style']
|
|
||||||
soup.html['lang'] = self.lang
|
|
||||||
soup.html['dir'] = self.direction
|
|
||||||
mlang = new_tag(soup, 'meta', [
|
|
||||||
("http-equiv", "Content-Language"), ("content", self.lang)])
|
|
||||||
mcharset = new_tag(soup, 'meta', [
|
|
||||||
("http-equiv", "Content-Type"), ("content", "text/html; charset=utf-8")])
|
|
||||||
soup.head.insert(0, mlang)
|
|
||||||
soup.head.insert(1, mcharset)
|
|
||||||
return soup
|
|
||||||
Binary file not shown.
|
Before Width: | Height: | Size: 527 B |
Binary file not shown.
|
Before Width: | Height: | Size: 420 B |
Binary file not shown.
|
Before Width: | Height: | Size: 383 B |
Binary file not shown.
|
Before Width: | Height: | Size: 676 B |
Binary file not shown.
|
Before Width: | Height: | Size: 329 B |
Binary file not shown.
|
Before Width: | Height: | Size: 605 B |
Binary file not shown.
|
Before Width: | Height: | Size: 462 B |
Binary file not shown.
|
Before Width: | Height: | Size: 503 B |
Binary file not shown.
|
Before Width: | Height: | Size: 125 B |
Loading…
x
Reference in New Issue
Block a user