diff --git a/recipes/frontlineonnet.recipe b/recipes/frontlineonnet.recipe deleted file mode 100644 index eeaf437de4..0000000000 --- a/recipes/frontlineonnet.recipe +++ /dev/null @@ -1,74 +0,0 @@ -# -*- mode: python -*- -# -*- coding: utf-8 -*- - -__license__ = 'GPL v3' -__copyright__ = '2011 - 2016, Darko Miletic ' -''' -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&') diff --git a/recipes/hawaii.recipe b/recipes/hawaii.recipe deleted file mode 100644 index 9295ae2c26..0000000000 --- a/recipes/hawaii.recipe +++ /dev/null @@ -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') - ] diff --git a/recipes/heise_online.recipe b/recipes/heise_online.recipe deleted file mode 100644 index 68db42eaf8..0000000000 --- a/recipes/heise_online.recipe +++ /dev/null @@ -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' diff --git a/recipes/heraldo.recipe b/recipes/heraldo.recipe deleted file mode 100644 index 99134ad8ce..0000000000 --- a/recipes/heraldo.recipe +++ /dev/null @@ -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'
', re.DOTALL | re.IGNORECASE), - lambda match: '

' - ), - ( - re.compile(r'