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

remove dead recipes

Browse Source 
These recipes are based on RSS feeds that no longer work.
This commit is contained in:
unkn0w7n 2024-09-22 12:06:31 +05:30 committed by Kovid Goyal
parent ab383122cd
commit 764948ab37
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
139 changed files with 0 additions and 3681 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
recipes/balkanist.recipe
View File

@ -1,50 +0,0 @@
# -*- mode: python -*-
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2017, Darko Miletic <darko.miletic at gmail.com>'
'''
http://balkanist.net/magazine
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Pagina12(BasicNewsRecipe):
title = 'Balkanist'
__author__ = 'Darko Miletic'
description = 'Balkanist is an experimental, bilingual platform featuring politics, analysis, culture, and criticism for a smart international audience underwhelmed by what is currently on offer. Our aim is to provide bold, uncompromising coverage of the Balkan region and everything to its East. We are currently entirely independent, self- and reader-funded, and are not affiliated with any organization, company, or government institution.' # noqa
publisher = 'Balkanist'
category = 'news, politics, Balkans'
oldest_article = 30
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'en'
remove_empty_feeds = True
publication_type = 'magazine'
auto_cleanup = True
masthead_url = 'http://media.balkanist.net/2013/07/Balkanist-Magazine-cover.png'
ignore_duplicate_articles = {'url'}
extra_css = """
body{font-family: Lora,serif}
img{margin-top:1em; margin-bottom: 1em; display:block}
"""
conversion_options = {
'comment': description,
'tags': category,
'publisher': publisher,
'language': language
}
remove_tags = [
dict(name=['meta', 'link']),
]
feeds = [
(u'Magazine', u'http://balkanist.net/magazine/feed/'),
(u'News', u'http://balkanist.net/news/feed/'),
(u'Commentary', u'http://balkanist.net/commentary/feed/'),
(u'Arts and Culture', u'http://balkanist.net/arts-and-culture/feed/'),
(u'Politics', u'http://balkanist.net/politics/feed/'),
]

25
recipes/bangkok_biz.recipe
View File

@ -1,25 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1290689337(BasicNewsRecipe):
__author__ = 'Anat R.'
language = 'th'
title = u'Bangkok Biz News'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
feeds = [(u'Headlines',
u'http://www.bangkokbiznews.com/home/services/rss/home.xml'),
(u'Politics', u'http://www.bangkokbiznews.com/home/services/rss/politics.xml'),
(u'Business', u'http://www.bangkokbiznews.com/home/services/rss/business.xml'),
(u'Finance', u' http://www.bangkokbiznews.com/home/services/rss/finance.xml'),
(u'Technology', u' http://www.bangkokbiznews.com/home/services/rss/it.xml')]
remove_tags_before = dict(name='div', attrs={'class': 'box-Detailcontent'})
remove_tags_after = dict(name='p', attrs={'class': 'allTags'})
remove_tags = []
remove_tags.append(dict(name='div', attrs={'id': 'content-tools'}))
remove_tags.append(dict(name='p', attrs={'class': 'allTags'}))
remove_tags.append(dict(name='div', attrs={'id': 'morePic'}))
remove_tags.append(dict(name='ul', attrs={'class': 'tabs-nav'}))

49
recipes/bankier_pl.recipe
View File

@ -1,49 +0,0 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = 'teepel <teepel44@gmail.com>'
'''
bankier.pl
'''
from calibre.web.feeds.news import BasicNewsRecipe
class bankier(BasicNewsRecipe):
title = u'Bankier.pl'
__author__ = 'teepel <teepel44@gmail.com>'
language = 'pl'
description = 'Polski portal finansowy. Informacje o: gospodarka, inwestowanie, finanse osobiste, prowadzenie firmy, kursy walut, notowania akcji, fundusze.' # noqa
masthead_url = 'http://www.bankier.pl/gfx/hd-mid-02.gif'
INDEX = 'http://bankier.pl/'
remove_empty_feeds = True
oldest_article = 1
max_articles_per_feed = 100
remove_javascript = True
no_stylesheets = True
simultaneous_downloads = 5
keep_only_tags = []
keep_only_tags.append(dict(name='div', attrs={'align': 'left'}))
remove_tags = []
remove_tags.append(dict(name='table', attrs={'cellspacing': '2'}))
remove_tags.append(dict(name='div', attrs={'align': 'center'}))
remove_tags.append(dict(name='img', attrs={'src': '/gfx/hd-mid-02.gif'}))
feeds = [
(u'Wiadomości dnia', u'http://feeds.feedburner.com/bankier-wiadomosci-dnia'),
(u'Finanse osobiste', u'http://feeds.feedburner.com/bankier-finanse-osobiste'),
(u'Firma', u'http://feeds.feedburner.com/bankier-firma'),
(u'Giełda', u'http://feeds.feedburner.com/bankier-gielda'),
(u'Rynek walutowy', u'http://feeds.feedburner.com/bankier-rynek-walutowy'),
(u'Komunikaty ze spółek', u'http://feeds.feedburner.com/bankier-espi'),
]
def print_version(self, url):
segment = url.split('.')
urlPart = segment[2]
segments = urlPart.split('-')
urlPart2 = segments[-1]
return 'http://www.bankier.pl/wiadomosci/print.html?article_id=' + urlPart2

46
recipes/bay_citizen.recipe
View File

@ -1,46 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class TheBayCitizen(BasicNewsRecipe):
title = 'The Bay Citizen'
language = 'en'
__author__ = 'noah'
description = 'The Bay Citizen'
publisher = 'The Bay Citizen'
INDEX = u'http://www.baycitizen.org'
category = 'news'
oldest_article = 2
max_articles_per_feed = 20
no_stylesheets = True
masthead_url = 'http://media.baycitizen.org/images/layout/logo1.png'
feeds = [('Main Feed', 'http://www.baycitizen.org/feeds/stories/')]
keep_only_tags = [dict(name='div', attrs={'class': 'story'})]
remove_tags = [
dict(name='div', attrs={'class': 'socialBar'}),
dict(name='div', attrs={'id': 'text-resize'}),
dict(name='div', attrs={'class': 'story relatedContent'}),
dict(name='div', attrs={'id': 'comment_status_loading'}),
]
def append_page(self, soup, appendtag, position):
pager = soup.find('a', attrs={'class': 'stry-next'})
if pager:
nexturl = self.INDEX + pager['href']
soup2 = self.index_to_soup(nexturl)
texttag = soup2.find('div', attrs={'class': 'body'})
for it in texttag.findAll(style=True):
del it['style']
newpos = len(texttag.contents)
self.append_page(soup2, texttag, newpos)
texttag.extract()
appendtag.insert(position, texttag)
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
self.append_page(soup, soup.body, 3)
garbage = soup.findAll(id='story-pagination')
[trash.extract() for trash in garbage]
garbage = soup.findAll('em', 'cont-from-prev')
[trash.extract() for trash in garbage]
return soup

16
recipes/beppe_grillo.recipe
View File

@ -1,16 +0,0 @@
__license__ = 'GPL v3'
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1327747616(BasicNewsRecipe):
title = u'Beppe Grillo'
oldest_article = 7
max_articles_per_feed = 100
auto_cleanup = True
feeds = [(u'Beppe Grillo', u'http://feeds.feedburner.com/beppegrillo/atom')]
description = 'Blog of the famous comedian and politician Beppe Grillo - v1.00 (28, January 2012)'
__author__ = 'faber1971'
language = 'it'

48
recipes/berliner_zeitung.recipe
View File

@ -1,48 +0,0 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2016, Kovid Goyal <kovid at kovidgoyal.net>
from __future__ import absolute_import, division, print_function, unicode_literals
from calibre.web.feeds.recipes import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
class BerlinerZeitung(BasicNewsRecipe):
title = 'Berliner Zeitung'
__author__ = 'Kovid Goyal'
language = 'de'
description = 'Berliner Zeitung RSS'
timefmt = ' [%d.%m.%Y]'
ignore_duplicate_articles = {'title', 'url'}
remove_empty_feeds = True
# oldest_article = 7.0
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
publication_type = 'newspaper'
keep_only_tags = [
classes('dm_article_body dm_article_header'),
]
remove_tags = [
classes('dm_article_share'),
]
feeds = [x.split() for x in [
'Berlin http://www.berliner-zeitung.de/blueprint/servlet/xml/berliner-zeitung/23699382-asYahooFeed.xml',
'Brandenburg http://www.berliner-zeitung.de/blueprint/servlet/xml/berliner-zeitung/23699570-asYahooFeed.xml',
'Politik http://www.berliner-zeitung.de/blueprint/servlet/xml/berliner-zeitung/23699614-asYahooFeed.xml',
'Wirtschaft http://www.berliner-zeitung.de/blueprint/servlet/xml/berliner-zeitung/23699644-asYahooFeed.xml',
'Sport http://www.berliner-zeitung.de/blueprint/servlet/xml/berliner-zeitung/23699874-asYahooFeed.xml',
'Kultur http://www.berliner-zeitung.de/blueprint/servlet/xml/berliner-zeitung/23700020-asYahooFeed.xml',
'Panorama http://www.berliner-zeitung.de/blueprint/servlet/xml/berliner-zeitung/23700178-asYahooFeed.xml',
'Wissen http://www.berliner-zeitung.de/blueprint/servlet/xml/berliner-zeitung/23700222-asYahooFeed.xml',
'Digital http://www.berliner-zeitung.de/blueprint/servlet/xml/berliner-zeitung/23700594-asYahooFeed.xml',
'Ratgeber http://www.berliner-zeitung.de/blueprint/servlet/xml/berliner-zeitung/23700190-asYahooFeed.xml',
]]

49
recipes/berlingske_dk.recipe
View File

@ -1,49 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
berlingske.dk
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Berlingske_dk(BasicNewsRecipe):
title = 'Berlingske Tidende'
__author__ = 'Darko Miletic'
description = 'News from Denmark'
publisher = 'berlingske.dk'
category = 'news, politics, Denmark'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
remove_empty_feeds = True
use_embedded_content = False
remove_javascript = True
publication_type = 'newspaper'
encoding = 'utf8'
language = 'da'
auto_cleanup = True
extra_css = '''
.manchet {color:#888888;}
.dateline {font-size: x-small; color:#444444;}
.manchet,.dateline { font-family: Cambria,Georgia,Times,"Times New Roman",serif }
.body {font-family: Arial,Helvetica,sans-serif }
'''
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
feeds = [
(u'Breaking news', u'http://www.b.dk/breaking/rss'),
(u'Seneste nyt', u'http://www.b.dk/seneste/rss'),
(u'Topnyheder', u'http://www.b.dk/top/rss'),
(u'Danmark', u'http://www.b.dk/danmark/seneste/rss'),
(u'Verden', u'http://www.b.dk/verden/seneste/rss'),
(u'Klima', u'http://www.b.dk/klima/seneste/rss'),
(u'Debat', u'http://www.b.dk/debat/seneste/rss'),
(u'Koebenhavn', u'http://www.b.dk/koebenhavn/seneste/rss'),
(u'Politik', u'http://www.b.dk/politik/seneste/rss'),
(u'Kultur', u'http://www.b.dk/kultur/seneste/rss')
]

60
recipes/bighollywood.recipe
View File

@ -1,60 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
'''
bighollywood.breitbart.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class BigHollywood(BasicNewsRecipe):
title = 'Big Hollywood'
__author__ = 'Darko Miletic'
description = 'News and articles from the media world'
publisher = 'Big Hollywood'
category = 'news, media, art, literature, movies, politics, USA, Hollywood'
oldest_article = 7
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'en'
remove_empty_feeds = True
publication_type = 'blog'
extra_css = """
body{font-family: Arial,sans-serif }
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
keep_only_tags = [dict(attrs={'class': 'postcontent'})]
remove_tags = [
dict(name=['meta', 'link', 'link', 'iframe', 'embed', 'object']), dict(
name='p', attrs={'class': ['post_meta_links', 'postfooter']})
]
remove_attributes = ['original', 'onclick']
feeds = [(u'Articles', u'http://bighollywood.breitbart.com/feed/')]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('a'):
limg = item.find('img')
if item.string is not None:
str = item.string
item.replaceWith(str)
else:
if limg:
if limg['src'].endswith('BlogPrintButton.png'):
limg.extract()
item.name = 'div'
item.attrs = []
else:
str = self.tag_to_string(item)
item.replaceWith(str)
for item in soup.findAll('img', alt=False):
item['alt'] = 'image'
return soup

45
recipes/birgun_gazetesi.recipe
View File

@ -1,45 +0,0 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from calibre.web.feeds.news import BasicNewsRecipe
class Birgun (BasicNewsRecipe):
title = u'Birgün Gazetesi'
__author__ = u'Osman Kaysan'
oldest_article = 7
max_articles_per_feed = 150
use_embedded_content = False
description = 'Birgun gazatesi haberleri, kose yazarlari'
publisher = 'Birgün'
category = 'news,haberler,turkce,gazete,birgun'
language = 'tr'
no_stylesheets = True
publication_type = 'newspaper'
conversion_options = {
'comments': description, 'tags': category, 'language': language, 'publisher': publisher, 'linearize_tables': True, 'remove_paragraph_spacing': True,
}
cover_img_url = 'http://www.birgun.net/i/birgun.png'
masthead_url = 'http://www.birgun.net/i/birgun.png'
remove_attributes = ['width', 'height']
remove_tags_before = dict(name='h2', attrs={'class': 'storyHeadline'})
remove_tags_after = dict(name='tr', attrs={'valign': 'top'})
remove_tags = [dict(name='div', attrs={'id': 'byLine'}), dict(name='div', attrs={'class': 'toollinks'}), dict(name='div', attrs={
'class': 'main-lead'}), dict(name='div', attrs={'class': 'addthis_toolbox addthis_default_style'}), dict(name='a', attrs={'class': 'addthis_button'})]
remove_empty_feeds = True
feeds = [
(u'Güncel', u'http://www.birgun.net/actuels.xml'),
(u'Köşe Yazarları', u'http://www.birgun.net/writer.xml'),
(u'Politika', u'http://www.birgun.net/politics.xml'),
(u'Ekonomi', u'http://www.birgun.net/economic.xml'),
(u'Çalışma Yaşamı', u'http://www.birgun.net/workers.xml'),
(u'Dünya', u'http://www.birgun.net/worlds.xml'),
(u'Yaşam', u'http://www.birgun.net/lifes.xml')
]

56
recipes/birmingham_post.recipe
View File

@ -1,56 +0,0 @@
from __future__ import print_function
import re
import mechanize
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1306097511(BasicNewsRecipe):
title = u'Birmingham post'
description = 'Author D.Asbury. News for Birmingham UK'
__author__ = 'Dave Asbury'
cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/161987_9010212100_2035706408_n.jpg'
oldest_article = 2
max_articles_per_feed = 20
linearize_tables = True
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
auto_cleanup = True
language = 'en_GB'
compress_news_images = True
cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/161987_9010212100_2035706408_n.jpg'
masthead_url = 'http://www.trinitymirror.com/images/birminghampost-logo.gif'
def get_cover_url(self):
soup = self.index_to_soup('http://www.birminghampost.net')
# look for the block containing the sun button and url
cov = soup.find(attrs={'height': re.compile(
'3'), 'alt': re.compile('Post')})
print()
print('%%%%%%%%%%%%%%%', cov)
print()
cov2 = str(cov['src'])
print('88888888 ', cov2, ' 888888888888')
# cover_url=cov2
# return cover_url
br = mechanize.Browser()
br.set_handle_redirect(False)
try:
br.open_novisit(cov2)
cover_url = cov2
except:
cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/161987_9010212100_2035706408_n.jpg'
return cover_url
feeds = [
(u'West Mids. News',
u'http://www.birminghampost.net/news/west-midlands-news/rss.xml'),
(u'UK News', u'http://www.birminghampost.net/news/uk-news/rss.xml'),
(u'Sports', u'http://www.birminghampost.net/midlands-birmingham-sport/rss.xml'),
(u'Bloggs & Comments', u'http://www.birminghampost.net/comment/rss.xml')
]

57
recipes/bitacora.recipe
View File

@ -1,57 +0,0 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
'''
bitacora.com.uy
'''
from calibre.web.feeds.news import BasicNewsRecipe
class General(BasicNewsRecipe):
title = 'bitacora.com.uy'
__author__ = 'Gustavo Azambuja'
description = 'Noticias de Uruguay'
language = 'es_UY'
timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False
recursion = 5
encoding = 'iso-8859-1'
remove_javascript = True
no_stylesheets = True
oldest_article = 2
max_articles_per_feed = 100
keep_only_tags = [dict(id=['txt'])]
remove_tags = [
dict(name='div', attrs={'class': 'tablafoot'}),
dict(name=['object', 'h4']),
dict(name=['object', 'link'])
]
remove_attributes = ['width', 'height', 'style', 'font', 'color']
extra_css = '''
h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
p {font-family:Arial,Helvetica,sans-serif;}
'''
feeds = [
(u'Titulares', u'http://www.bitacora.com.uy/anxml.cgi?15')
]
def get_cover_url(self):
cover_url = None
index = 'http://www.bitacora.com.uy'
soup = self.index_to_soup(index)
link_item = soup.find('img', attrs={'class': 'imgtapa'})
if link_item:
cover_url = "http://www.bitacora.com.uy/" + link_item['src']
return cover_url
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup

38
recipes/biz_portal.recipe
View File

@ -1,38 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1283848012(BasicNewsRecipe):
description = 'This is a recipe of BizPortal.co.il.'
cover_url = 'http://www.bizportal.co.il/shukhahon/images/bizportal.jpg'
title = u'BizPortal'
language = 'he'
__author__ = 'marbs'
extra_css = 'img {max-width:100%;} body{direction: rtl;},title{direction: rtl; } ,article_description{direction: rtl; }, a.article{direction: rtl; } ,calibre_feed_description{direction: rtl; }' # noqa
simultaneous_downloads = 5
remove_javascript = True
timefmt = '[%a, %d %b, %Y]'
remove_empty_feeds = True
oldest_article = 1
max_articles_per_feed = 100
remove_attributes = ['width']
simultaneous_downloads = 5
remove_tags = [dict(name='img', attrs={'scr': ['images/bizlogo_nl.gif']})]
max_articles_per_feed = 100
feeds = [(u'חדשות שוק ההון', u'http://www.bizportal.co.il/shukhahon/messRssUTF2.xml'),
(u'חדשות וול סטריט בעברית',
u'http://www.bizportal.co.il/shukhahon/images/bizportal.jpg'),
(u'שיווק ופרסום', u'http://www.bizportal.co.il/shukhahon/messRssUTF145.xml'),
(u'משפט', u'http://www.bizportal.co.il/shukhahon/messRssUTF3.xml'),
(u'ניתוח טכני', u'http://www.bizportal.co.il/shukhahon/messRssUTF5.xml'),
(u'דיני עבודה ושכר', u'http://www.bizportal.co.il/shukhahon/messRssUTF6.xml'),
(u'מיסוי', u'http://www.bizportal.co.il/shukhahon/messRssUTF7.xml'),
(u'טאבו', u'http://www.bizportal.co.il/shukhahon/messRssUTF8.xml'),
(u'נדל"ן', u'http://www.bizportal.co.il/shukhahon/messRssUTF160.xml'),
]
def print_version(self, url):
split1 = url.split("=")
print_url = 'http://www.bizportal.co.il/web/webnew/shukhahon/biznews02print.shtml?mid=' + \
split1[1]
return print_url

31
recipes/boortz.recipe
View File

@ -1,31 +0,0 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = 'Tony Stegall'
__copyright__ = '2010, Tony Stegall or Tonythebookworm on mobiread.com'
__version__ = '1.04'
__date__ = '27, September 2010'
__docformat__ = 'restructuredtext en'
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1282101454(BasicNewsRecipe):
title = 'Nealz Nuze'
language = 'en'
__author__ = 'TonytheBookworm'
description = 'Neal Boortz Show Radio Notes'
publisher = 'Neal Boortz'
category = 'news, politics, USA, talkshow'
oldest_article = 1
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
use_embedded_content = True
masthead_url = 'http://boortz.com/images/nuze_logo.gif'
conversion_options = {'linearize_tables': True}
feeds = [
('NUZE', 'http://boortz.com/nealz_nuze_rss/rss.xml')
]

34
recipes/borse_online.recipe
View File

@ -1,34 +0,0 @@
# vim:fileencoding=utf-8
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = u'Börse-online'
__author__ = 'schuster, Armin Geller' # AGE upd 2013-11-29
oldest_article = 1
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = 'de'
remove_javascript = True
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
encoding = 'utf-8'
timefmt = ' [%a, %d %b %Y]'
cover_url = 'http://www.wirtschaftsmedien-shop.de/s/media/coverimages/7576_2013107.jpg'
masthead_url = 'http://upload.wikimedia.org/wikipedia/de/5/56/B%C3%B6rse_Online_Logo.svg'
feeds = [(u'Börsennachrichten', u'http://www.boerse-online.de/rss'),
(u'Märkte', u'http://www.boerse-online.de/rss/maerkte'),
(u'Chartanalyse', u'http://www.boerse-online.de/rss/maerkte/chartanalyse'),
(u'Aktien', u'http://www.boerse-online.de/rss/aktie'),
(u'Aktien-Chartanalyse',
u'http://www.boerse-online.de/rss/aktie/chartanalyse'),
(u'zertifikate', u'http://www.boerse-online.de/rss/zertifikat')
]
def print_version(self, url):
s1, s2 = url.rsplit('/', 1)
return 'http://www.boerse-online.de/nachrichten/drucken/' + s2

18
recipes/boxis.recipe
View File

@ -1,18 +0,0 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import absolute_import, division, print_function, unicode_literals
from calibre.web.feeds.news import AutomaticNewsRecipe
class BasicUserRecipe1501590114(AutomaticNewsRecipe):
title = 'Boxis'
oldest_article = 240
max_articles_per_feed = 100
auto_cleanup = True
language = 'sc'
__author__ = 'tzium'
feeds = [
('Boxis', 'http://www.boxis.it/sc/feed/'),
]

130
recipes/brand_eins.recipe
View File

@ -1,130 +0,0 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import unicode_literals
__license__ = 'GPL v3'
__version__ = '0.2'
'''
brand eins.de
'''
from collections import OrderedDict
from calibre.web.feeds.news import BasicNewsRecipe
class BrandEins(BasicNewsRecipe):
title = u'brand eins'
__author__ = 'Nikolas Mangold-Takao, Thomas Schlenkhoff'
language = 'de'
description = u'brand eins beschreibt den momentanen Wandel in Wirtschaft und Gesellschaft.'
publisher = u'brand eins Verlag GmbH & Co. oHG'
category = 'politics, business, wirtschaft, Germany'
PREFIX = 'http://www.brandeins.de/'
INDEX = PREFIX + 'archiv/listeansicht.html'
use_embedded_content = False
resolve_internal_links = True
no_stylesheets = True
needs_subscription = False
delay = 1
summary_length = 200
simultaneous_downloads = 5
remove_javascript = True
keep_only_tags = dict(name='div', attrs={'id': 'content'})
# remove share image from articles
remove_tags = [dict(name='div', attrs={'id': 'oms_gpt_billboard'}),
dict(name='div', attrs={'id': 'oms_gpt_rectangle'}),
dict(name='h3', attrs={'class': 'sharing-headline'}),
dict(name='div', attrs={'class': 'sharing-links'}),
dict(name='aside', attrs={'class': 'articleAside'})]
remove_tags_before = dict(
name='div', attrs={'class': 'innerContent typeArticle'})
remove_tags_after = dict(name='div', attrs={'id': 'socialshareprivacy'})
extra_css = '''
body, p {text-align: left;}
.headline {font-size: x-large;}
h2 {font-size: medium;}
h1 {font-size: large;}
em.Bold {font-weight:bold;font-style:normal;}
em.Italic {font-style:italic;}
'''
def parse_index(self):
issue = ""
soup = self.index_to_soup(self.INDEX)
issue_list = soup.findAll('div', attrs={'class': 'details'})
issue_map = {}
i = 0
for entry in issue_list:
title = self.tag_to_string(entry.find(
'h3', attrs={'class': 'like-h1'}))
issue_string = self.tag_to_string(
entry.find('span', attrs={'class': 'meta'}))
year = issue_string[8:]
month = issue_string[5:-5]
yyyymm = "{}{}".format(year, month)
link = entry.findAll('a')[0]
issue_map[yyyymm] = link.get('href')
self.log('- ', year, month, title, link.get('href'))
# Issue 1 (most recent) has only few articles online,
# Issue 2 and 3 (2nd and 3rd recent) is not completely online.
# Issue 4 (4th recent) is completely online, hence i == 3
if issue == "" and i == 3:
issue = yyyymm
i += 1
url = 'http://brandeins.de/' + issue_map[issue]
self.log('Issue to get: ', issue, title, url)
self.issue_url = url # save to extract cover
return self.parse_issue(url)
def parse_issue(self, url):
soup = self.index_to_soup(url)
feeds = OrderedDict()
for item in soup.findAll(attrs={'class': lambda x: 'ihv_item' in (x or '').split()}):
a = item.findParent('a', href=True)
if a is None:
continue
url = self.PREFIX + a['href']
title = self.tag_to_string(item.find(attrs={'class': 'ihv_title'}))
sec = self.tag_to_string(
item.find(attrs={'class': 'ihv_page_category'}).findAll('span')[-1])
if sec not in feeds:
feeds[sec] = []
desc = ''
for p in item.findAll('p'):
desc += self.tag_to_string(p)
feeds[sec].append(
{'title': title, 'url': url, 'description': desc})
self.log('Found article:', title, 'at', url)
return [(st, articles) for st, articles in feeds.items() if articles]
def get_cover_url(self):
# the index does not contain a usable cover, but the 'Welt in
# Zahlen'-article contains it
cover_article = "{}{}".format(
self.issue_url, 'die-welt-in-zahlen.html')
self.log('Cover article URL: %s' % cover_article)
soup = self.index_to_soup(cover_article)
img = soup.find('section', 'asideSection no-content').find('img')
self.log('Found cover image url: %s' % img['src'])
return (self.PREFIX + img['src'])
def preprocess_raw_html(self, raw_html, url):
return raw_html.replace('<p>• ', '<p>')

33
recipes/brasil_de_fato.recipe
View File

@ -1,33 +0,0 @@
# -*- coding: utf-8 -*-
from calibre.web.feeds.news import BasicNewsRecipe
class BrasilDeFato(BasicNewsRecipe):
news = True
title = u'Brasil de Fato'
__author__ = 'Alex Mitrani'
description = u'Uma visão popular do Brasil e do mundo.'
publisher = u'SOCIEDADE EDITORIAL BRASIL DE FATO'
category = 'news, politics, Brazil, rss, Portuguese'
oldest_article = 10
max_articles_per_feed = 100
summary_length = 1000
language = 'pt_BR'
remove_javascript = True
no_stylesheets = True
use_embedded_content = False
remove_empty_feeds = True
masthead_url = 'http://www.brasildefato.com.br/sites/default/files/zeropoint_logo.jpg'
keep_only_tags = [dict(name='div', attrs={'id': 'main'})]
remove_tags = [dict(name='div', attrs={'class': 'links'})]
remove_tags_after = [dict(name='div', attrs={'class': 'links'})]
feeds = [
(u'Nacional', u'http://www.brasildefato.com.br/rss_nacional'),
(u'Internacional', u'http://www.brasildefato.com.br/rss_internacional'),
(u'Entrevista', u'http://www.brasildefato.com.br/rss_entrevista'),
(u'Cultura', u'http://www.brasildefato.com.br/rss_cultura'),
(u'Análise', u'http://www.brasildefato.com.br/rss_analise')
]

81
recipes/brecha.recipe
View File

@ -1,81 +0,0 @@
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>'
'''
www.brecha.com.uy
'''
try:
from urllib.parse import quote, urlencode
except ImportError:
from urllib import quote, urlencode
from calibre.web.feeds.news import BasicNewsRecipe
class Brecha(BasicNewsRecipe):
title = 'Brecha Digital'
__author__ = 'Darko Miletic'
description = 'Brecha , Cultura ,Sociales , Separatas, Lupas, Vueltas de Montevideo y toda la infomacion que caracteriza a este semanario'
publisher = 'Brecha'
category = 'brecha, digital, prensa, uruguay, semanario, sociedad, politica, cultura'
oldest_article = 7
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'es_UY'
remove_empty_feeds = True
publication_type = 'magazine'
auto_cleanup = True
needs_subscription = 'optional'
masthead_url = 'http://www.brecha.com.uy/templates/ja_nex/themes/orange/images/logo.png'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif }
img{margin-bottom: 0.4em; display:block}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open('http://www.brecha.com.uy/index.php/acceder-miembros')
if self.username is not None and self.password is not None:
data = urlencode({'task': 'login', 'view': 'register', 'username': self.username, 'password': self.password
})
br.open(
'http://www.brecha.com.uy/index.php/index.php?option=com_osemsc&controller=register', data)
return br
remove_tags = [
dict(name=['meta', 'link']),
dict(name='div', attrs={'id': 'js_ja'}),
dict(name='ul', attrs={'class': 'actions'})
]
remove_attributes = ['lang', 'border']
feeds = [
(u'Politica', u'http://www.brecha.com.uy/index.php/politica-uruguaya?format=feed&type=rss'),
(u'Mundo', u'http://www.brecha.com.uy/index.php/mundo?format=feed&type=rss'),
(u'Mapamundi', u'http://www.brecha.com.uy/index.php/mundo/mapamundi?format=feed&type=rss'),
(u'Cultura', u'http://www.brecha.com.uy/index.php/cultura?format=feed&type=rss'),
(u'Vueltas de Montevideo',
u'http://www.brecha.com.uy/index.php/cultura/vueltas-de-montevideo?format=feed&type=rss'),
(u'Secos y Mojados', u'http://www.brecha.com.uy/index.php/cultura/secos-y-mojados?format=feed&type=rss'),
(u'Literarias', u'http://www.brecha.com.uy/index.php/cultura/literarias?format=feed&type=rss'),
(u'Sociedad', u'http://www.brecha.com.uy/index.php/sociedad?format=feed&type=rss'),
(u'Especiales', u'http://www.brecha.com.uy/index.php/especiales?format=feed&type=rss'),
(u'Contratapa', u'http://www.brecha.com.uy/index.php/contratapa?format=feed&type=rss')
]
def print_version(self, url):
return url + '?tmpl=component&print=1&layout=default&page='
def get_cover_url(self):
soup = self.index_to_soup('http://www.brecha.com.uy/index.php')
for image in soup.findAll('img', alt=True):
if image['alt'].startswith('Tapa '):
return 'http://www.brecha.com.uy' + quote(image['src'])
return None

16
recipes/brhat.recipe
View File

@ -1,16 +0,0 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe
class Brhat(BasicNewsRecipe):
title = 'Brhat'
__author__ = 'Vishvas Vasuki'
language = 'en_IN'
oldest_article = 365
max_articles_per_feed = 100
auto_cleanup = True
feeds = [
('Main', 'https://brhat.in/feed/'),
]

63
recipes/bsi_news.recipe
View File

@ -1,63 +0,0 @@
#!/usr/bin/env python
from __future__ import absolute_import, division, print_function, unicode_literals
from calibre.web.feeds.news import BasicNewsRecipe
class germanyBSI(BasicNewsRecipe):
# Title of the Recipe
# title = 'News des Bundesamt für Sicherheit in der Informationstechnik'
title = 'BSI News - DE'
cover_url = 'https://www.bsi.bund.de/SiteGlobals/Frontend/Images/BSI/logo.png'
# Author
__author__ = 'Volker Heggemann, VoHe'
# oldest article to download (in days) ---- can be edit by user
oldest_article = 7
# describes itself, ---- can be edit by user
max_articles_per_feed = 100
# speed up the download on fast computers be careful (I test max.20)
# ---- can be edit by user
simultaneous_downloads = 10
# description, some Reader show this in titlepage
description = u'News from BSI'
# Who published the content?
publisher = u'Newsfeeds des BSI'
# What is the content of?
category = u'Sie erfahren, wenn neue Nachrichten auf der Internetseite des BSI veröffentlicht werden'
# describes itself, ---- can be edit by user
use_embedded_content = False
# describes itself, ---- can be edit by user
language = 'de'
# encoding of content. e.g. utf-8, None, ...
# ---- can be edit by user
encoding = None # 'utf-8' doesn't work here
# Removes javascript- why keep this, we only want static content
remove_javascript = True
# Removes empty feeds - why keep them!?
remove_empty_feeds = True
# remove the rubbish (in ebook)
auto_cleanup = True
# now the content description and URL follows
# feel free to add, wipe out what you need ---- can be edit by user
#
# some of this are double
#
#
# Make some tests, may you first comment all of them out, and step by step you add what you'll need?
#
feeds = [
('BSI - Germany - Sicherheitshinweise des Buerger-CERT',
'https://www.bsi-fuer-buerger.de/SiteGlobals/Functions/RSSFeed/RSSNewsfessBSIFB/RSSNewsfeed_BuergerCERT.xml'
),
('BSI - Germany - Aktuelle Informationen BSI f\xfcr B\xfcrger',
'https://www.bsi-fuer-buerger.de/SiteGlobals/Functions/RSSFeed/RSSNewsfessBSIFB/RSSNewsfeed_Buerger_aktuelle_Informationen.xml'
),
('Kurzinformationen des CERT-Bund zu Sicherheitsl\xfccken und Schwachstellen in IT-Systemen',
'https://www.bsi.bund.de/SiteGlobals/Functions/RSSFeed/RSSNewsfeed/RSSNewsfeed_WID.xml'
),
('BSI - Germany - RSS-Newsfeed (Presse-, Kurzmitteilungen und Veranstaltungshinweise)',
'https://www.bsi.bund.de/SiteGlobals/Functions/RSSFeed/RSSNewsfeed/RSSNewsfeed.xml'
),
]

45
recipes/buchreport.recipe
View File

@ -1,45 +0,0 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
'''Calibre recipe to convert the RSS feeds of the Buchreport to an ebook.'''
class Buchreport(BasicNewsRecipe):
__author__ = 'a.peter'
__copyright__ = 'a.peter'
__license__ = 'GPL v3'
description = 'Buchreport'
version = 4
title = u'Buchreport'
timefmt = ' [%d.%m.%Y]'
encoding = 'cp1252'
language = 'de'
extra_css = 'body { margin-left: 0.00em; margin-right: 0.00em; } \
article, articledate, articledescription { text-align: left; } \
h1 { text-align: left; font-size: 140%; font-weight: bold; } \
h2 { text-align: left; font-size: 100%; font-weight: bold; font-style: italic; } \
h3 { text-align: left; font-size: 100%; font-weight: regular; font-style: italic; } \
h4, h5, h6 { text-align: left; font-size: 100%; font-weight: bold; }'
oldest_article = 7.0
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
publication_type = 'newspaper'
remove_tags_before = dict(name='h2')
remove_tags_after = [
dict(name='div', attrs={'style': ["padding-top:10px;clear:both"]})
]
remove_tags = [
dict(name='div', attrs={'style': ["padding-top:10px;clear:both"]}),
dict(name='iframe'),
dict(name='img')
]
feeds = [
(u'Buchreport', u'http://www.buchreport.de/index.php?id=5&type=100')
]
def get_masthead_url(self):
return 'http://www.buchreport.de/fileadmin/template/img/buchreport_logo.jpg'

49
recipes/buckmasters.recipe
View File

@ -1,49 +0,0 @@
from calibre.ebooks.BeautifulSoup import Tag
from calibre.web.feeds.news import BasicNewsRecipe
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 AdvancedUserRecipe1282101454(BasicNewsRecipe):
title = 'BuckMasters In The Kitchen'
language = 'en'
__author__ = 'TonytheBookworm & Starson17'
description = 'Learn how to cook all those outdoor varments'
publisher = 'BuckMasters.com'
category = 'food,cooking,recipes'
oldest_article = 365
max_articles_per_feed = 100
conversion_options = {'linearize_tables': True}
masthead_url = 'http://www.buckmasters.com/Portals/_default/Skins/BM_10/images/header_bg.jpg'
keep_only_tags = [
dict(name='table', attrs={'class': ['containermaster_black']})
]
remove_tags_after = [dict(name='div', attrs={'align': ['left']})]
feeds = [
('Recipes', 'http://www.buckmasters.com/DesktopModules/DnnForge%20-%20NewsArticles/RSS.aspx?TabID=292&ModuleID=658&MaxCount=25'),
]
def preprocess_html(self, soup):
item = soup.find('a', attrs={'class': ['MenuTopSelected']})
if item:
item.parent.extract()
for img_tag in soup.findAll('img'):
parent_tag = img_tag.parent
if parent_tag.name == 'a':
ntag = new_tag(soup, 'p')
ntag.insert(0, img_tag)
parent_tag.replaceWith(ntag)
elif parent_tag.name == 'p':
if not self.tag_to_string(parent_tag) == '':
new_div = new_tag(soup, 'div')
ntag = new_tag(soup, 'p')
ntag.insert(0, img_tag)
parent_tag.replaceWith(new_div)
new_div.insert(0, ntag)
new_div.insert(1, parent_tag)
return soup

53
recipes/buenosaireseconomico.recipe
View File

@ -1,53 +0,0 @@
#!/usr/bin/env python
# -*- mode: python -*-
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2009-2016, Darko Miletic <darko.miletic at gmail.com>'
'''
www.diariobae.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class BsAsEconomico(BasicNewsRecipe):
title = 'Buenos Aires Economico'
__author__ = 'Darko Miletic'
description = 'Diario BAE es el diario economico-politico con mas influencia en la Argentina. Fuente de empresarios y politicos del pais y el exterior. El pozo estaria aportando en periodos breves un volumen equivalente a 800m3 diarios. Pero todavia deben efectuarse otras perforaciones adicionales.' # noqa
publisher = 'Diario BAE'
category = 'news, politics, economy, Argentina'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = 'es_AR'
masthead_url = 'http://static.cronica.com.ar/FileAccessHandler.ashx?code=635959869637084622'
remove_empty_feeds = True
publication_type = 'newspaper'
extra_css = """
body{font-family: Georgia,"Times New Roman",Times,serif}
img{display: block; margin-top: 1em}
"""
conversion_options = {
'comment' : description,
'tags' : category,
'publisher': publisher,
'language' : language
}
keep_only_tags = [dict(name='div', attrs={'class':'post'})]
remove_tags = [
dict(name=['meta', 'base', 'iframe', 'link', 'lang'])
,dict(attrs={'class':'pdfprnt-bottom-right'})
]
feeds = [(u'Articles', u'http://www.diariobae.com/feed/getfeed')]
def get_cover_url(self):
cover = None
soup = self.index_to_soup('http://www.diariobae.com/')
tag = soup.find('a', rel='lightbox[tapa]', href=True)
if tag:
cover = tag['href']
return cover

49
recipes/buffalo_news.recipe
View File

@ -1,49 +0,0 @@
__license__ = 'GPL v3'
__author__ = 'Todd Chapman'
__copyright__ = 'Todd Chapman'
__version__ = 'v0.2'
__date__ = '2 March 2011'
'''
http://www.buffalonews.com/RSS/
'''
from calibre.web.feeds.news import BasicNewsRecipe
class BuffaloNews(BasicNewsRecipe):
title = u'Buffalo News'
oldest_article = 2
language = 'en'
__author__ = 'ChappyOnIce, Krittika Goyal'
max_articles_per_feed = 20
encoding = 'utf-8'
masthead_url = 'http://www.buffalonews.com/buffalonews/skins/buffalonews/images/masthead/the_buffalo_news_logo.png'
auto_cleanup = True
remove_empty_feeds = True
feeds = [
(u'City of Buffalo', u'http://www.buffalonews.com/city/communities/buffalo/?widget=rssfeed&view=feed&contentId=77944'),
(u'Southern Erie County',
u'http://www.buffalonews.com/city/communities/southern-erie/?widget=rssfeed&view=feed&contentId=77944'),
(u'Eastern Erie County', u'http://www.buffalonews.com/city/communities/eastern-erie/?widget=rssfeed&view=feed&contentId=77944'),
(u'Southern Tier', u'http://www.buffalonews.com/city/communities/southern-tier/?widget=rssfeed&view=feed&contentId=77944'),
(u'Niagara County', u'http://www.buffalonews.com/city/communities/niagara-county/?widget=rssfeed&view=feed&contentId=77944'),
(u'Business', u'http://www.buffalonews.com/business/?widget=rssfeed&view=feed&contentId=77944'),
(u'MoneySmart', u'http://www.buffalonews.com/business/moneysmart/?widget=rssfeed&view=feed&contentId=77944'),
(u'Bills & NFL', u'http://www.buffalonews.com/sports/bills-nfl/?widget=rssfeed&view=feed&contentId=77944'),
(u'Sabres & NHL', u'http://www.buffalonews.com/sports/sabres-nhl/?widget=rssfeed&view=feed&contentId=77944'),
(u'Bob DiCesare', u'http://www.buffalonews.com/sports/columns/bob-dicesare/?widget=rssfeed&view=feed&contentId=77944'),
(u'Bucky Gleason', u'http://www.buffalonews.com/sports/columns/bucky-gleason/?widget=rssfeed&view=feed&contentId=77944'),
(u'Mark Gaughan', u'http://www.buffalonews.com/sports/bills-nfl/inside-the-nfl/?widget=rssfeed&view=feed&contentId=77944'),
(u'Mike Harrington', u'http://www.buffalonews.com/sports/columns/mike-harrington/?widget=rssfeed&view=feed&contentId=77944'),
(u'Jerry Sullivan', u'http://www.buffalonews.com/sports/columns/jerry-sullivan/?widget=rssfeed&view=feed&contentId=77944'),
(u'Other Sports Columns', u'http://www.buffalonews.com/sports/columns/other-sports-columns/?widget=rssfeed&view=feed&contentId=77944'),
(u'Life', u'http://www.buffalonews.com/life/?widget=rssfeed&view=feed&contentId=77944'),
(u'Bruce Andriatch', u'http://www.buffalonews.com/city/columns/bruce-andriatch/?widget=rssfeed&view=feed&contentId=77944'),
(u'Donn Esmonde', u'http://www.buffalonews.com/city/columns/donn-esmonde/?widget=rssfeed&view=feed&contentId=77944'),
(u'Rod Watson', u'http://www.buffalonews.com/city/columns/rod-watson/?widget=rssfeed&view=feed&contentId=77944'),
(u'Entertainment', u'http://www.buffalonews.com/entertainment/?widget=rssfeed&view=feed&contentId=77944'),
(u'Off Main Street', u'http://www.buffalonews.com/city/columns/off-main-street/?widget=rssfeed&view=feed&contentId=77944'),
(u'Editorials', u'http://www.buffalonews.com/editorial-page/buffalo-news-editorials/?widget=rssfeed&view=feed&contentId=77944')
]

36
recipes/businessworldin.recipe
View File

@ -1,36 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.businessworld.in
'''
from calibre.web.feeds.news import BasicNewsRecipe
class BusinessWorldMagazine(BasicNewsRecipe):
title = 'Business World Magazine'
__author__ = 'Kovid Goyal'
description = 'News from India'
category = 'news, politics, finances, India, Asia'
no_stylesheets = True
encoding = 'utf-8'
language = 'en_IN'
oldest_article = 2
keep_only_tags = [
dict(attrs={'class': ['main-article']}),
]
remove_tags = [
dict(id='video_n_ad_div'),
dict(attrs={'class': ['meta-tools', 'social-article']}),
]
remove_tags_after = dict(attrs={'class': 'social-article'})
feeds = ['http://www.businessworld.in/rss/all-article.xml']
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-original': True}):
img['src'] = img['data-original']
for ins in soup.findAll(attrs={'class': 'adsbygoogle'}):
ins.parent.extract()
return soup

14
recipes/cafcaf_dergisi.recipe
View File

@ -1,14 +0,0 @@
# -*- coding: utf-8 -*-
from calibre.web.feeds.news import BasicNewsRecipe
class BasicUserRecipe1325259641(BasicNewsRecipe):
language = 'tr'
__author__ = 'asalet_r'
title = u'CafCaf Dergisi'
oldest_article = 7
max_articles_per_feed = 20
auto_cleanup = True
feeds = [(u'CafCaf', u'http://www.cafcafdergisi.net/feed/rss/')]

20
recipes/camera_di_commercio_di_bari.recipe
View File

@ -1,20 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1331729727(BasicNewsRecipe):
title = u'Camera di Commercio di Bari'
oldest_article = 7
__author__ = 'faber1971'
description = 'News from the Chamber of Commerce of Bari'
language = 'it'
max_articles_per_feed = 100
auto_cleanup = True
masthead_url = 'http://www.ba.camcom.it/grafica/layout-bordo/logo_camcom_bari.png'
feeds = [(u'Camera di Commercio di Bari',
u'http://feed43.com/4715147488845101.xml')]
__license__ = 'GPL v3'
__copyright__ = '2012, faber1971'
__version__ = 'v1.00'
__date__ = '17, April 2012'

12
recipes/capes_n_babes.recipe
View File

@ -1,12 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class CapesnBabesRecipe(BasicNewsRecipe):
title = u'Capes n Babes'
language = 'en'
description = 'The Capes n Babes comic Blog'
__author__ = 'skyhawker'
oldest_article = 31
max_articles_per_feed = 100
use_embedded_content = True
feeds = [(u'Capes & Babes', u'feed://www.capesnbabes.com/feed/')]

41
recipes/capital.recipe
View File

@ -1,41 +0,0 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103'
'''
capital.ro
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Capital(BasicNewsRecipe):
title = 'Capital'
__author__ = u'Silviu Cotoar\u0103'
description = u'\u0218tiri din Rom\u00e2nia'
oldest_article = 5
language = 'ro'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
category = 'Ziare,Stiri,Romania'
encoding = 'utf-8'
remove_javascript = True
publisher = 'Capital'
cover_url = 'http://www.mediapress.ro/imagini/sigla-capital-s16.gif'
conversion_options = {
'comments': description, 'tags': category, 'language': language, 'publisher': publisher
}
keep_only_tags = [dict(name='div', attrs={'class': 'single one_article'})
]
remove_tags = [dict(name='div', attrs={'class': 'single_details'}), dict(name='div', attrs={'class': 'tx-addoceansbanners-pi1'})
]
feeds = [(u'\u0218tiri', u'http://www.capital.ro/rss.html')]
def preprocess_html(self, soup):
return self.adeify_images(soup)

84
recipes/capital_de.recipe
View File

@ -1,84 +0,0 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import absolute_import, division, print_function, unicode_literals
'''
capital.de
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1305470859(BasicNewsRecipe):
title = 'Capital.de'
__author__ = 'schuster'
description = 'RSS-Feed von Capital.de'
publisher = 'Gruner+Jahr GmbH & Co KG'
language = 'de'
oldest_article = 14
max_articles_per_feed = 35
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
conversion_options = {'smarten_punctuation': True,
'publisher': publisher}
cover_source = 'http://shop.capital.de/abos/capital/'
masthead_url = 'http://www.capital.de/files/capital/layout/logo.png'
feeds = [
('Capital.de', 'http://www.capital.de/partner-feeds/rss.xml')
]
keep_only_tags = [
dict(name='div', attrs={
'class': 'grid_8 alpha omega layout_full block'})
]
remove_tags = [
dict(name='div', attrs={'class': 'article_header'}),
dict(name='br', attrs={'class': 'clear'})
]
remove_attributes = ['height', 'width']
extra_css = 'h1 {font-size: 1.6em; text-align: left} \
h2 {font-size: 1em; text-align: left} \
.copyright {font-size: 0.6em} \
.caption {font-size: 0.6em}'
def get_cover_url(self):
soup = self.index_to_soup(self.cover_source)
img_span = soup.find('span', {'class': re.compile('coverimage')})
self.cover_url = img_span.find('img', src=True)['src']
return self.cover_url
def preprocess_html(self, soup):
# remove all articles without relevant content
tags = soup.findAll('li', {'class': 'tag-chain-item'})
for li in tags:
if 'BILDERSTRECKE' in self.tag_to_string(li).upper():
self.abort_article()
# remove list of tags
tags = soup.find('ul', {'class': 'tag-chain'})
if tags:
tags.extract()
# remove all style attributes
for item in soup.findAll(style=True):
del item['style']
# remove all local hyperlinks
for a in soup.findAll('a', {'href': True}):
if a['href'] and 'http' not in a['href']:
del a['href']
# remove picture(s) of author(s)
for div in soup.findAll('div', {'class': 'ce_text block'}):
if div.find('hr'):
for hr in div.findAll('hr'):
hr.extract()
for img in div.findAll('img'):
img.extract()
return soup

116
recipes/caravan_magazine_hindi.recipe
View File

@ -1,116 +0,0 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2015, Kovid Goyal <kovid at kovidgoyal.net>
import json
from calibre.web.feeds.recipes import BasicNewsRecipe
from mechanize import Request
def classes(classes):
q = frozenset(classes.split(' '))
return dict(
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
)
class CaravanMagazineHindi(BasicNewsRecipe):
title = 'Caravan Magazine in Hindi'
__author__ = 'Kovid Goyal, Gobelinus, Aareet Mahadevan'
description = 'An Indian Journal of politics and culture'
language = 'hi'
timefmt = ' [%b, %Y]'
encoding = 'utf-8'
needs_subscription = 'optional'
no_stylesheets = True
keep_only_tags = [
classes('post-title short-desc author-details cover'),
dict(itemprop='articleBody'),
]
remove_tags = [
dict(name='meta'),
dict(attrs={'class': ['share-with', 'img-wrap abs']}),
]
remove_attributes = ['style']
def get_browser(self, *args, **kw):
br = BasicNewsRecipe.get_browser(self, *args, **kw)
if not self.username or not self.password:
return br
data = json.dumps({
'email': self.username,
'name': '',
'password': self.password
})
if not isinstance(data, bytes):
data = data.encode('utf-8')
rq = Request(
url='https://caravanmagazine.in/api/users/login',
data=data,
headers={
'Accept': 'application/json, text/plain, */*',
'Origin': 'https://caravanmagazine.in',
'Referer': 'https://caravanmagazine.in/',
'Content-type': 'application/json;charset=UTF-8',
},
method='POST'
)
res = br.open(rq).read()
res = res.decode('utf-8')
self.log('Login request response: {}'.format(res))
res = json.loads(res)
if res['code'] != 200 or res['message'] != "Login success":
raise ValueError('Login failed, check your username and password')
return br
# To parse article toc
def parse_index(self):
base_url = 'https://www.caravanmagazine.in/'
soup = self.index_to_soup('{0}magazine'.format(base_url))
# find current issue cover
feeds = []
sections = soup.find(
attrs={
'class': lambda x: x and 'current-magazine-issue' in x.split()
}
).find(attrs={'class': lambda x: x and 'sections' in x.split()})
for section in sections.findAll(
attrs={'class': lambda x: x and 'section' in x.split()}
):
a = section.find('a')
section_title = self.tag_to_string(a)
self.log('\nSection:', section_title)
articles = []
for article in section.findAll('article'):
details = article.find(
attrs={'class': lambda x: x and 'details' in x.split()}
)
pre = details.find(
attrs={'class': lambda x: x and 'pre-heading' in x.split()}
)
if pre is not None:
pre.extract()
a = details.find('a')
url = base_url + a['href'].lstrip('/') + '-hindi'
title = self.tag_to_string(a)
desc = self.tag_to_string(details.find('div'))
self.log('\t', title, url)
articles.append({'title': title, 'description': desc, 'url': url})
if articles:
feeds.append((section_title, articles))
return feeds
def preprocess_html(self, soup):
for div in soup.findAll(itemprop='image'):
for img in div.findAll('img'):
img['src'] = div['content']
for img in soup.findAll(attrs={'data-src': True}):
img['src'] = img['data-src']
return soup

51
recipes/carta.recipe
View File

@ -1,51 +0,0 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import absolute_import, division, print_function, unicode_literals
from calibre.web.feeds.news import BasicNewsRecipe
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net, Armin Geller>'
class Carta(BasicNewsRecipe):
# Update 2017-09-01
# Armin Geller
title = u'Carta'
description = 'Authors blog for politics, economics and digital community'
__author__ = 'Armin Geller' # AGe Update 2017-09-01
timefmt = ' [%a %d %b %Y]'
oldest_article = 14
max_articles_per_feed = 50
no_stylesheets = True
remove_javascript = True
remove_empty_feeds = True
encoding = 'utf-8'
language = 'de'
cover_url = 'http://www.carta.info/wp-content/themes/carta2014/img/carta-logo.svg' # AGe Update 2014-10-05 new cover
masthead_url = 'http://upload.wikimedia.org/wikipedia/de/b/ba/Carta_logo.png'
# masthead_url ='http://www.carta.info/wp-content/themes/carta2014/img/carta-logo.svg'
extra_css = '''
h2 {font-size: 1.3em; font-style: italic}
.excerpt {font-size: 1.2em; font-style: italic}
'''
keep_only_tags = [
dict(name='div', attrs={'class': ['article-text', 'author']}),
dict(name='p', attrs={'class': 'tags'}),
]
remove_tags = [
dict(name='ul', attrs={'class': 'meta'}),
]
feeds = [
(u'CARTA - Standard', u'http://feeds2.feedburner.com/carta-standard-rss'),
(u'CARTA - Homepage', u'http://feeds2.feedburner.com/carta-homepage-rss'),
(u'CARTA - Agenda', u'http://feeds2.feedburner.com/carta-agenda-rss'),
(u'CARTA - Ökonomie', u'http://feeds2.feedburner.com/carta-oekonomie-rss'),
(u'CARTA - Medien', u'http://feeds2.feedburner.com/carta-medien-rss'),
]

17
recipes/catholic_daily_readings.recipe
View File

@ -1,17 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class BasicUserRecipe1328971305(BasicNewsRecipe):
title = u'Catholic Daily Readings'
language = 'en'
__author__ = 'adoucette'
oldest_article = 7
max_articles_per_feed = 100
auto_cleanup = True
feeds = [
(u'Daily Readings - USCCB', u'http://www.usccb.org/bible/readings/rss/'),
(u'Daily Reflection - One Bread One Body', u'http://www.presentationministries.com/general/rss.asp'),
(u'Mass Readings - Universalis', u'http://www.universalis.com/atommass3.xml'),
(u'Saint Of The Day - CNA', u'http://feeds.feedburner.com/catholicnewsagency/saintoftheday')]

28
recipes/cd_action.recipe
View File

@ -1,28 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class CD_Action(BasicNewsRecipe):
title = u'CD-Action'
__author__ = 'fenuks'
description = 'Strona CD-Action (CDA), największego w Polsce pisma dla graczy.Pełne wersje gier, newsy, recenzje, zapowiedzi, konkursy, forum, opinie, galerie screenów,trailery, filmiki, patche, teksty. Gry komputerowe (PC) oraz na konsole (PS3, XBOX 360).' # noqa
category = 'games'
language = 'pl'
index = 'http://www.cdaction.pl'
oldest_article = 8
max_articles_per_feed = 100
no_stylesheets = True
keep_only_tags = dict(id='news_content')
remove_tags_after = dict(name='div', attrs={'class': 'tresc'})
feeds = [(u'Newsy', u'http://www.cdaction.pl/rss_newsy.xml')]
def get_cover_url(self):
soup = self.index_to_soup('http://www.cdaction.pl/magazyn/')
self.cover_url = 'http://www.cdaction.pl' + \
soup.find(id='wspolnik').div.a['href']
return getattr(self, 'cover_url', self.cover_url)
def preprocess_html(self, soup):
for a in soup.findAll('a', href=True):
if 'http://' not in a['href'] and 'https://' not in a['href']:
a['href'] = self.index + a['href']
return soup

74
recipes/cdrinfo_pl.recipe
View File

@ -1,74 +0,0 @@
__license__ = 'GPL v3'
import re
from calibre.ebooks.BeautifulSoup import Comment
from calibre.web.feeds.news import BasicNewsRecipe
class cdrinfo(BasicNewsRecipe):
title = u'CDRinfo.pl'
__author__ = 'fenuks'
description = u'Serwis poświęcony archiwizacji danych. Testy i recenzje nagrywarek. Programy do nagrywania płyt. Dyski twarde, dyski SSD i serwery sieciowe NAS. Rankingi dyskow twardych, najszybsze dyski twarde, newsy, artykuły, testy, recenzje, porady, oprogramowanie. Zestawienie nagrywarek, najnowsze biosy do nagrywarek, programy dla dysków twardych.' # noqa
category = 'it, hardware'
# publication_type = ''
language = 'pl'
# encoding = ''
# extra_css = ''
cover_url = 'http://www.cdrinfo.pl/gfx/graph3/top.jpg'
# masthead_url = ''
use_embedded_content = False
oldest_article = 777
max_articles_per_feed = 100
no_stylesheets = True
remove_empty_feeds = True
remove_javascript = True
remove_attributes = ['style', 'onmouseover']
preprocess_regexps = [(re.compile(u'<p[^>]*?>Uprzejmie prosimy o przestrzeganie netykiety.+?www\\.gravatar\\.com</a>\\.</p>', re.DOTALL), lambda match: ''),
(re.compile(u'<p[^>]*?>.{,2}</p>', re.DOTALL), lambda match: '')]
ignore_duplicate_articles = {'title', 'url'}
keep_only_tags = [
dict(name='input', attrs={'name': 'ref'}), dict(id=['text', 'text2'])]
remove_tags = [dict(attrs={'class': ['navigation', 'sociable', 'last6news']}), dict(
name=['hr', 'br']), dict(id='respond')]
remove_tags_after = dict(id='artnawigacja')
feeds = [(u'Wiadomości', 'http://feeds.feedburner.com/cdrinfo'),
(u'Recenzje', 'http://www.cdrinfo.pl/rss/rss_recenzje.php'),
(u'Konsole', 'http://konsole.cdrinfo.pl/rss/rss_konsole_news.xml'),
(u'Pliki', 'http://www.cdrinfo.pl/rss/rss_pliki.xml')
]
def preprocess_html(self, soup):
if soup.find(id='artnawigacja'):
self.append_page(soup, soup.body)
return soup
def append_page(self, soup, appendtag):
baseurl = 'http://cdrinfo.pl' + \
soup.find(name='input', attrs={'name': 'ref'})['value'] + '/'
if baseurl[-2] == '/':
baseurl = baseurl[:-1]
tag = soup.find(id='artnawigacja')
div = tag.find('div', attrs={'align': 'right'})
while div:
counter = 0
while counter < 5:
try:
soup2 = self.index_to_soup(baseurl + div.a['href'])
break
except:
counter += 1
tag2 = soup2.find(id='artnawigacja')
div = tag2.find('div', attrs={'align': 'right'})
pagetext = soup2.find(attrs={'class': 'art'})
comments = pagetext.findAll(
text=lambda text: isinstance(text, Comment))
for comment in comments:
comment.extract()
for r in soup2.findAll(attrs={'class': 'star-rating'}):
r.extract()
for r in soup2.findAll(attrs={'class': 'star-rating2'}):
r.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
tag.extract()

70
recipes/ceska_pozice.recipe
View File

@ -1,70 +0,0 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import unicode_literals
from calibre.web.feeds.recipes import BasicNewsRecipe
class ceskaPoziceRecipe(BasicNewsRecipe):
__author__ = 'bubak'
title = u'Česká pozice'
description = 'Česká pozice'
oldest_article = 2
max_articles_per_feed = 20
feeds = [
(u'Všechny články', u'http://www.ceskapozice.cz/rss.xml'),
(u'Domov', u'http://www.ceskapozice.cz/taxonomy/term/16/feed'),
(u'Chrono', u'http://www.ceskapozice.cz/chrono/feed'),
(u'Evropa', u'http://www.ceskapozice.cz/taxonomy/term/17/feed')
]
language = 'cs'
cover_url = 'http://www.ceskapozice.cz/sites/default/files/cpozice_logo.png'
remove_javascript = True
no_stylesheets = True
domain = u'http://www.ceskapozice.cz'
use_embedded_content = False
remove_tags = [dict(name='div', attrs={'class': ['block-ad', 'region region-content-ad']}),
dict(name='ul', attrs={'class': 'links'}),
dict(name='div', attrs={
'id': ['comments', 'back-to-top']}),
dict(name='div', attrs={
'class': ['next-page', 'region region-content-ad']}),
dict(name='cite')]
keep_only_tags = [dict(name='div', attrs={'id': 'content'})]
visited_urls = {}
def get_article_url(self, article):
url = BasicNewsRecipe.get_article_url(self, article)
if url in self.visited_urls:
self.log.debug('Ignoring duplicate: ' + url)
return None
else:
self.visited_urls[url] = True
self.log.debug('Accepting: ' + url)
return url
def preprocess_html(self, soup):
self.append_page(soup, soup.body, 3)
return soup
def append_page(self, soup, appendtag, position):
pager = soup.find('div', attrs={'class': 'paging-bottom'})
if pager:
nextbutton = pager.find('li', attrs={'class': 'pager-next'})
if nextbutton:
nexturl = self.domain + nextbutton.a['href']
soup2 = self.index_to_soup(nexturl)
texttag = soup2.find('div', attrs={'class': 'main-body'})
for it in texttag.findAll('div', attrs={'class': 'region region-content-ad'}):
it.extract()
for it in texttag.findAll('cite'):
it.extract()
newpos = len(texttag.contents)
self.append_page(soup2, texttag, newpos)
texttag.extract()
appendtag.insert(position, texttag)
pager.extract()

27
recipes/cesky_rozhlas_6.recipe
View File

@ -1,27 +0,0 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import unicode_literals
from calibre.web.feeds.recipes import BasicNewsRecipe
class cro6Recipe(BasicNewsRecipe):
__author__ = 'bubak'
title = u'Český rozhlas 6'
description = 'Český rozhlas 6'
oldest_article = 1
max_articles_per_feed = 20
feeds = [
(u'Český rozhlas 6', u'http://www.rozhlas.cz/export/cro6/')
]
language = 'cs'
cover_url = 'http://www.rozhlas.cz/img/e5/logo/cro6.png'
remove_javascript = True
no_stylesheets = True
remove_attributes = []
remove_tags = [dict(name='div', attrs={'class': ['audio-play-all', 'poradHeaders', 'actions']}),
dict(name='p', attrs={'class': ['para-last']})]
keep_only_tags = [dict(name='div', attrs={'id': 'article'})]

34
recipes/cetnixploitation.recipe
View File

@ -1,34 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
chetnixploitation.blogspot.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Chetnixploitation(BasicNewsRecipe):
title = 'Chetnixploitation'
__author__ = 'Darko Miletic'
description = 'Filmski blog'
oldest_article = 7
max_articles_per_feed = 100
language = 'sr'
publication_type = 'blog'
encoding = 'utf-8'
no_stylesheets = True
use_embedded_content = True
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 = {
'comment': description, 'tags': 'film, blog, cetnici, srbija, ex-yu', 'publisher': 'Son of Man', 'language': language
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
feeds = [(u'Posts', u'http://chetnixploitation.blogspot.com/feeds/posts/default')]
def preprocess_html(self, soup):
return self.adeify_images(soup)

48
recipes/cgm_pl.recipe
View File

@ -1,48 +0,0 @@
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.web.feeds.news import BasicNewsRecipe
class CGM(BasicNewsRecipe):
title = u'CGM'
oldest_article = 7
__author__ = 'fenuks'
description = u'Codzienna Gazeta Muzyczna'
masthead_url = 'http://www.cgm.pl/img/header/logo.gif'
cover_url = 'http://www.krafcy.com/foto/tinymce/Image/cgm%281%29.jpg'
category = 'music'
language = 'pl'
use_embedded_content = False
remove_empty_feeds = True
max_articles_per_feed = 100
no_stylesheets = True
extra_css = 'div {color:black;} strong {color:black;} span {color:black;} p {color:black;} h2 {color:black;} img {display: block;} ul.galleryImagesList {list-style: none;} li.item {float: left;} .calibrenavbar {clear: both;}' # noqa
remove_tags_before = dict(id='mainContent')
remove_tags_after = dict(name='div', attrs={'class': 'fbContainer'})
remove_tags = [dict(name='div', attrs={'class': ['fbContainer', 'socials']}),
dict(name='p', attrs={
'class': ['tagCloud', 'galleryAuthor']}),
dict(id=['movieShare', 'container']), dict(name='br')]
feeds = [(u'Informacje', u'http://www.cgm.pl/rss.xml'), (u'Polecamy', u'http://www.cgm.pl/rss,4,news.xml'),
(u'Recenzje', u'http://www.cgm.pl/rss,1,news.xml')]
def preprocess_html(self, soup):
gallery = soup.find('div', attrs={'class': 'galleryFlash'})
if gallery and gallery.div:
img = gallery.div
gallery.img.extract()
if img:
img = img['style']
img = 'http://www.cgm.pl' + \
img[img.find('url(') + 4:img.find(')')]
gallery.contents[1].name = 'img'
gallery.contents[1]['src'] = img
pos = len(gallery.contents)
gallery.insert(pos, BeautifulSoup('<br />'))
for item in soup.findAll(style=True):
del item['style']
ad = soup.findAll('a')
for r in ad:
if 'www.hustla.pl' in r['href'] or 'www.ebilet.pl' in r['href']:
r.extract()
return soup

44
recipes/chicago_breaking_news.recipe
View File

@ -1,44 +0,0 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
chicagobreakingnews.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ChicagoBreakingNews(BasicNewsRecipe):
title = 'Chicago Breaking News'
__author__ = 'Darko Miletic'
description = 'Breaking News from Chicago'
oldest_article = 1
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = True
publisher = 'Chicago Breaking News'
category = 'news, politics, USA, Chicago'
encoding = 'utf8'
language = 'en'
html2lrf_options = [
'--comment', description, '--category', category, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + \
'"\ncomments="' + description + '"\ntags="' + category + '"'
feeds = [(u'Breaking news', u'http://feeds2.feedburner.com/ChicagoBreakingNews/')]
def preprocess_html(self, soup):
for item in soup.findAll('a'):
if item['href'].find('http://feedads.googleadservices.com') > -1:
item.extract()
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(color=True):
del item['color']
for item in soup.findAll(size=True):
del item['size']
return soup

56
recipes/china_economic_net.recipe
View File

@ -1,56 +0,0 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1278162597(BasicNewsRecipe):
__author__ = 'rty'
title = u'China Economic Net'
oldest_article = 7
max_articles_per_feed = 100
publisher = 'www.ce.cn - China Economic net - Beijing'
description = 'China Economic Net Magazine'
category = 'Economic News Magazine, Chinese, China'
recipe_specific_options = {
'days': {
'short': 'Oldest article to download from this news source. In days ',
'long': 'For example, 0.5, gives you articles from the past 12 hours',
'default': str(oldest_article)
}
}
def __init__(self, *args, **kwargs):
BasicNewsRecipe.__init__(self, *args, **kwargs)
d = self.recipe_specific_options.get('days')
if d and isinstance(d, str):
self.oldest_article = float(d)
feeds = [
(u'Stock Market 股市', u'http://finance.ce.cn/stock/index_6304.xml'),
(u'Money 理财', u'http://finance.ce.cn/money/index_6301.xml'),
(u'Health 健康', u'http://www.ce.cn/health/index_6294.xml'),
(u'Technology 科技', u'http://sci.ce.cn/mainpage/index_6307.xml'),
(u'Domestic Politics 国内时政', u'http://www.ce.cn/xwzx/gnsz/index_6273.xml')
]
masthead_url = 'http://finance.ce.cn/images/08mdy_logo.gif'
extra_css = '''
@font-face {font-family: "DroidFont", serif, sans-serif; src: url(res:///system/fonts/DroidSansFallback.ttf); }\n
body {margin-right: 8pt; font-family: 'DroidFont', serif;}\n
h1 {font-family: 'DroidFont', serif;}\n
.articledescription {font-family: 'DroidFont', serif;}
'''
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
language = 'zh_CN'
encoding = 'gb2312'
conversion_options = {'linearize_tables': True}
keep_only_tags = [
dict(name='h1', attrs={'id': 'articleTitle'}),
dict(name='div', attrs={'class': 'laiyuan'}),
dict(name='div', attrs={'id': 'articleText'}),
]

41
recipes/china_times.recipe
View File

@ -1,41 +0,0 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
# dug from http://www.mobileread.com/forums/showthread.php?p=1012294
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1277443634(BasicNewsRecipe):
title = u'中時電子報'
oldest_article = 1
max_articles_per_feed = 100
feeds = [(u'焦點要聞', u'http://feeds.feedburner.com/chinatimes/chinatimes-focus'),
(u'生活新聞', u'http://feeds.feedburner.com/chinatimes/chinatimes-life'),
(u'社會新聞', u'http://feeds.feedburner.com/chinatimes/chinatimes-society'),
(u'兩岸國際', u'http://feeds.feedburner.com/chinatimes/chinatimes-international'),
(u'時論廣場', u'http://feeds.feedburner.com/chinatimes/chinatimes-comment'),
(u'藝文副刊', u'http://feeds.feedburner.com/chinatimes/chinatimes-philology'),
(u'地方新聞', u'http://feeds.feedburner.com/chinatimes/chinatimes-local'),
(u'財經焦點', u'http://feeds.feedburner.com/chinatimes/chinatimes-finance'),
(u'運動天地', u'http://feeds.feedburner.com/chinatimes/chinatimes-sport'),
(u'娛樂新聞', u'http://feeds.feedburner.com/chinatimes/chinatimes-showbiz'),
(u'時尚消費', u'http://feeds.feedburner.com/chinatimes/chinatimes-fashion'),
# (u'財經', u'http://rss.chinatimes.com/rss/finance-u.rss'), # broken links
# (u'股市', u'http://rss.chinatimes.com/rss/stock-u.rss') # broken links
]
__author__ = 'einstuerzende, updated by Eddie Lau'
__version__ = '1.1'
language = 'zh'
publisher = 'China Times Group'
description = 'China Times (Taiwan)'
category = 'News, Chinese, Taiwan'
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
auto_cleanup = True
encoding = 'utf-8'
conversion_options = {'linearize_tables': True}
masthead_url = 'http://www.fcuaa.org/gif/chinatimeslogo.gif'
cover_url = 'http://www.fcuaa.org/gif/chinatimeslogo.gif'

46
recipes/chipro.recipe
View File

@ -1,46 +0,0 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103'
'''
chip.ro
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ChipRo(BasicNewsRecipe):
title = u'Chip Online'
__author__ = u'Silviu Cotoar\u0103'
description = 'Chip Online'
publisher = 'Chip Online'
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.chip.ro/images/logo.png'
conversion_options = {
'comments': description, 'tags': category, 'language': language, 'publisher': publisher
}
keep_only_tags = [
dict(name='h2', attrs={'class': 'contentheading clearfix'}), dict(name='span', attrs={
'class': 'createby'}), dict(name='div', attrs={'class': 'article-content'})
]
remove_tags = [
dict(name='div', attrs={'class': ['sharemecompactbutton']}), dict(name='div', attrs={'align': ['left']}), dict(name='div', attrs={
'align': ['center']}), dict(name='th', attrs={'class': ['pagenav_prev']}), dict(name='table', attrs={'class': ['pagenav']})
]
feeds = [
(u'Feeds', u'http://www.chip.ro/index.php?option=com_ninjarsssyndicator&feed_id=9&format=raw')
]
def preprocess_html(self, soup):
return self.adeify_images(soup)

29
recipes/chosun.recipe
View File

@ -1,29 +0,0 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2015, Hoje Lee <hojelei at gmail.com>'
'''
Profile to download Chosun.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ChosunDotcom(BasicNewsRecipe):
language = 'ko'
title = u'조선일보'
description = u'조선닷컴 기사'
__author__ = 'Hoje Lee'
oldest_article = 7
max_articles_per_feed = 10
auto_cleanup = True
feeds = [
(u'정치', 'http://www.chosun.com/site/data/rss/politics.xml'),
(u'조선비즈', 'http://biz.chosun.com/site/data/rss/rss.xml'),
(u'사회', 'http://www.chosun.com/site/data/rss/national.xml'),
(u'문화', 'http://www.chosun.com/site/data/rss/culture.xml'),
(u'국제', 'http://www.chosun.com/site/data/rss/international.xml'),
(u'오피니언', 'http://www.chosun.com/site/data/rss/editorials.xml'),
(u'스포츠', 'http://www.chosun.com/site/data/rss/sports.xml'),
(u'연예', 'http://www.chosun.com/site/data/rss/ent.xml'),
]

71
recipes/cinco_dias.recipe
View File

@ -1,71 +0,0 @@
__license__ = 'GPL v3'
__author__ = 'Luis Hernandez'
__copyright__ = 'Luis Hernandez<tolyluis@gmail.com>'
__version__ = 'v1.2'
__date__ = '31 January 2011'
'''
http://www.cincodias.com/
'''
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1294946868(BasicNewsRecipe):
title = u'Cinco Dias'
publisher = u'Grupo Prisa'
__author__ = 'Luis Hernandez'
description = 'spanish web about money and business, free edition'
cover_url = 'http://www.prisa.com/images/logos/logo_cinco_dias.gif'
oldest_article = 2
max_articles_per_feed = 100
remove_javascript = True
no_stylesheets = True
use_embedded_content = False
language = 'es'
remove_empty_feeds = True
encoding = 'ISO-8859-1'
timefmt = '[%a, %d %b, %Y]'
keep_only_tags = [
dict(name='div', attrs={'class': ['cab_articulo cab_noticia', 'pos_3', 'txt_noticia', 'mod_despiece']}), dict(
name='p', attrs={'class': ['cintillo']})
]
remove_tags_before = dict(name='div', attrs={'class': ['publi_h']})
remove_tags_after = dict(
name='div', attrs={'class': ['tab_util util_estadisticas']})
remove_tags = [
dict(name='div', attrs={'class': ['util-1', 'util-2', 'util-3', 'inner estirar', 'inner1', 'inner2', 'inner3', 'cont', 'tab_util util_estadisticas', 'tab_util util_enviar', 'mod_list_inf', 'mod_similares', 'mod_divisas', 'mod_sectores', 'mod_termometro', 'mod post', 'mod_img', 'mod_txt', 'nivel estirar', 'barra estirar', 'info_brujula btnBrujula', 'utilidad_brujula estirar']}), dict(name='li', attrs={'class': ['lnk-fcbook', 'lnk-retweet', 'lnk-meneame', 'desplegable', 'comentarios', 'list-options', 'estirar']}), dict(name='ul', attrs={'class': ['lista-izquierda', 'list-options', 'estirar']}), dict(name='p', attrs={'class': ['autor']}) # noqa
]
extra_css = """
p{text-align: justify; font-size: 100%}
body{ text-align: left; font-size:100% }
h1{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; }
h3{font-family: sans-serif; font-size:100%; font-style: italic; text-align: justify; }
"""
feeds = [
(u'Ultima Hora', u'http://www.cincodias.com/rss/feed.html?feedId=17029'),
(u'Empresas', u'http://www.cincodias.com/rss/feed.html?feedId=19'),
(u'Mercados', u'http://www.cincodias.com/rss/feed.html?feedId=20'),
(u'Economia', u'http://www.cincodias.com/rss/feed.html?feedId=21'),
(u'Tecnorama', u'http://www.cincodias.com/rss/feed.html?feedId=17230'),
(u'Tecnologia', u'http://www.cincodias.com/rss/feed.html?feedId=17106'),
(u'Finanzas Personales', u'http://www.cincodias.com/rss/feed.html?feedId=22'),
(u'Fiscalidad', u'http://www.cincodias.com/rss/feed.html?feedId=17107'),
(u'Vivienda', u'http://www.cincodias.com/rss/feed.html?feedId=17108'),
(u'Tendencias', u'http://www.cincodias.com/rss/feed.html?feedId=17109'),
(u'Empleo', u'http://www.cincodias.com/rss/feed.html?feedId=17110'),
(u'IBEX 35', u'http://www.cincodias.com/rss/feed.html?feedId=17125'),
(u'Sectores', u'http://www.cincodias.com/rss/feed.html?feedId=17126'),
(u'Opinion', u'http://www.cincodias.com/rss/feed.html?feedId=17105')
]

46
recipes/cinebel_be.recipe
View File

@ -1,46 +0,0 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008-2011, Lionel Bergeret <lbergeret at gmail.com>'
'''
cinebel.be
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Cinebel(BasicNewsRecipe):
title = u'Cinebel'
__author__ = u'Lionel Bergeret'
description = u'Cinema news from Belgium in French'
publisher = u'cinebel.be'
category = 'news, cinema, movie, Belgium'
oldest_article = 15
language = 'fr'
max_articles_per_feed = 20
no_stylesheets = True
use_embedded_content = False
timefmt = ' [%d %b %Y]'
filterDuplicates = True
keep_only_tags = [
dict(name='span', attrs={'class': 'movieMainTitle'}), dict(name='div', attrs={'id': 'filmPoster'}), dict(
name='div', attrs={'id': 'filmDefinition'}), dict(name='div', attrs={'id': 'synopsis'})
]
feeds = [
(u'Les sorties de la semaine', u'http://www.cinebel.be/Servlets/RssServlet?languageCode=fr&rssType=0'),
(u'Top 10', u'http://www.cinebel.be/Servlets/RssServlet?languageCode=fr&rssType=2')
]
def preprocess_html(self, soup):
for alink in soup.findAll('a', href=True):
tstr = "Site officiel: " + alink['href']
alink.replaceWith(tstr)
return soup
def get_cover_url(self):
cover_url = 'http://www.cinebel.be/portal/resources/common/logo_index.gif'
return cover_url

131
recipes/cio.recipe
View File

@ -1,131 +0,0 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = 'Lorenzo Vigentini'
__copyright__ = '2009, Lorenzo Vigentini <l.vigentini at gmail.com>'
__version__ = 'v1.01'
__date__ = '14, January 2010'
__description__ = 'CIO is the leading information brand for today s busy chief information officer. '
'''
http://www.cio.co.uk/
'''
from calibre.ptempfile import PersistentTemporaryFile
from calibre.web.feeds.news import BasicNewsRecipe
class cio(BasicNewsRecipe):
__author__ = 'Lorenzo Vigentini'
description = 'CIO is the leading information brand for today\'s busy chief information officer.'
cover_url = 'http://media.cio.co.uk/graphics/shared/cio-logo.gif'
title = 'CIO '
publisher = 'IDG Communication'
category = 'IT, technology, business, industry'
language = 'en'
timefmt = '[%a, %d %b, %Y]'
oldest_article = 7
max_articles_per_feed = 10
use_embedded_content = False
recursion = 10
remove_javascript = True
no_stylesheets = True
temp_files = []
articles_are_obfuscated = True
def get_obfuscated_article(self, url):
br = self.get_browser()
br.open(url)
response = br.follow_link(url_regex='&print&intcmp=ROSATT2$', nr=0)
html = response.read()
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(html)
self.temp_files[-1].close()
return self.temp_files[-1].name
keep_only_tags = [
dict(name='div', attrs={'id': 'mainContent'})
]
feeds = [
(u'News', u'http://www.cio.co.uk/rss/feeds/cio-news.xml'),
(u'Debate', u'http://www.cio.co.uk/rss/feeds/cio-debate.xml'),
(u'Analysis', u'http://www.cio.co.uk/rss/feeds/cio-analysis.xml'),
(u'Opinion', u'http://www.cio.co.uk/rss/feeds/cio-opinion.xml'),
(u'In-Depth', u'http://www.cio.co.uk/rss/feeds/cio-in-depth.xml'),
(u'Change management',
u'http://www.cio.co.uk/rss/feeds/cio-change-management-management.xml'),
(u'Regulatory compliance',
u'http://www.cio.co.uk/rss/feeds/cio-regulatory-compliance-management.xml'),
(u'Business strategy',
u'http://www.cio.co.uk/rss/feeds/cio-business-strategy-management.xml'),
(u'Technology', u'http://www.cio.co.uk/rss/feeds/cio-technology-management.xml'),
(u'Security', u'http://www.cio.co.uk/rss/feeds/cio-security-management.xml'),
(u'Soft skills', u'http://www.cio.co.uk/rss/feeds/cio-soft-skills-management.xml'),
(u'The CIO career',
u'http://www.cio.co.uk/rss/feeds/cio-cio-career-management.xml'),
(u'Budgets', u'http://www.cio.co.uk/rss/feeds/cio-budgets-management.xml'),
(u'Supplier management',
u'http://www.cio.co.uk/rss/feeds/cio-supplier-management-management.xml'),
(u'Board politics',
u'http://www.cio.co.uk/rss/feeds/cio-board-politics-management.xml'),
(u'Enterprise software',
u'http://www.cio.co.uk/rss/feeds/cio-enterprise-software-technology.xml'),
(u'Mobile and wireless',
u'http://www.cio.co.uk/rss/feeds/cio-mobile-wireless-technology.xml'),
(u'Security', u'http://www.cio.co.uk/rss/feeds/cio-security-technology.xml'),
(u'Storage', u'http://www.cio.co.uk/rss/feeds/cio-storage-technology.xml'),
(u'Desktop and client',
u'http://www.cio.co.uk/rss/feeds/cio-desktop-client-technology.xml'),
(u'Outsourcing', u'http://www.cio.co.uk/rss/feeds/cio-outsourcing-technology.xml'),
(u'Internet and e-commerce',
u'http://www.cio.co.uk/rss/feeds/cio-internet-technology.xml'),
(u'Database management',
u'http://www.cio.co.uk/rss/feeds/cio-database-management-technology.xml'),
(u'Communications and networking ',
u'http://www.cio.co.uk/rss/feeds/cio-communication-networking-technology.xml'),
(u'Grid computing',
u'http://www.cio.co.uk/rss/feeds/cio-grid-computing-cloud-technology.xml'),
(u'Enterprise search',
u'http://www.cio.co.uk/rss/feeds/cio-enterprise-search-technology.xml'),
(u'CRM ', u'http://www.cio.co.uk/rss/feeds/cio-crm-technology.xml'),
(u'Ade McCormack ',
u'http://www.cio.co.uk/rss/feeds/cio-opinion-ade-mccormack.xml'),
(u'Andy Hayler ',
u'http://www.cio.co.uk/rss/feeds/cio-opinion-andy-hayler.xml'),
(u'CEB ', u'http://www.cio.co.uk/rss/feeds/cio-opinion-ceb.xml'),
(u'CIO Staff ', u'http://www.cio.co.uk/rss/feeds/cio-opinion-cio-staff.xml'),
(u'Dave Pepperell ',
u'http://www.cio.co.uk/rss/feeds/cio-opinion-dave-pepperell.xml'),
(u'Elliot Limb ',
u'http://www.cio.co.uk/rss/feeds/cio-opinion-elliot-limb.xml'),
(u'Freeform Dynamics ',
u'http://www.cio.co.uk/rss/feeds/cio-opinion-freeform-dynamics.xml'),
(u'Giles Nelson ',
u'http://www.cio.co.uk/rss/feeds/cio-opinion-giles-nelson.xml'),
(u'Mark Chillingworth ',
u'http://www.cio.co.uk/rss/feeds/cio-opinion-mark-chillingworth.xml'),
(u'Martin Veitch ',
u'http://www.cio.co.uk/rss/feeds/cio-opinion-martin-veitch.xml'),
(u'Mike Altendorf ',
u'http://www.cio.co.uk/rss/feeds/cio-opinion-mike-altendorf.xml'),
(u'Richard Steel ',
u'http://www.cio.co.uk/rss/feeds/cio-opinion-richard-steel.xml'),
(u'Richard Sykes ',
u'http://www.cio.co.uk/rss/feeds/cio-opinion-richard-sykes.xml'),
(u'Rob Llewellyn ',
u'http://www.cio.co.uk/rss/feeds/cio-opinion-rob-llewellyn.xml'),
(u'Free thinking ',
u'http://www.cio.co.uk/rss/feeds/cio-blog-free-thinking.xml'),
(u'Leading CIOs ',
u'http://www.cio.co.uk/rss/feeds/cio-blog-leading-cios.xml'),
(u'CIO News View ',
u'http://www.cio.co.uk/rss/feeds/cio-blog-cio-news-view.xml'),
(u'CIO Blog ', u'http://www.cio.co.uk/rss/feeds/cio-blog-cio-blog.xml'),
(u'Transformation CIO ',
u'http://www.cio.co.uk/rss/feeds/cio-blog-transformation-cio.xml')
]

147
recipes/cio_magazine.recipe
View File

@ -1,147 +0,0 @@
from __future__ import print_function
import re
# Para convertir el tiempo del articulo
import string
# sys no hace falta... lo intente usar para escribir en stderr
from calibre import strftime
# Los primeros comentarios son las dificultades que he tenido con el Piton
# Cuando da error UTF8 revisa los comentarios (acentos). En notepad++ Search, Goto, posicion y lo ves.
# Editar con Notepad++ Si pone - donde no debe es que ha indentado mal... Edit - Blank operations - tab to space
# He entendido lo que significa el from... son paths dentro de pylib.zip...
# Con from importa solo un simbolo...con import,la libreria completa
from calibre.web.feeds.news import BasicNewsRecipe
# Para usar expresiones regulares
# Visto en pylib.zip... la primera letra es mayuscula
# Estas dos ultimas han sido un vago intento de establecer una cookie (no
# usado)
class CIO_Magazine(BasicNewsRecipe):
title = 'CIO Magazine'
oldest_article = 14
max_articles_per_feed = 100
auto_cleanup = True
__author__ = 'Julio Map'
description = 'CIO is the leading information brand for today-s busy Chief information Officer - CIO Magazine bi-monthly '
language = 'en'
encoding = 'utf8'
cover_url = 'http://www.cio.com/homepage/images/hp-cio-logo-linkedin.png'
remove_tags_before = dict(name='div', attrs={'id': 'container'})
# Absolutamente innecesario... al final he visto un print_version (ver mas
# adelante)
# Dentro de una revista dada...
# issue_details contiene el titulo y las secciones de este ejemplar
# DetailModule esta dentro de issue_details contiene las urls y resumenes
# Dentro de un articulo dado...
# Article-default-body contiene el texto. Pero como digo, he encontrado
# una print_version
no_stylesheets = True
remove_javascript = True
def print_version(self, url):
# A esta funcion le llama el sistema... no hay que llamarla uno mismo (porque seria llamada dos veces)
# Existe una version imprimible de los articulos cambiando
# http://www.cio.com/article/<num>/<titulo> por
# http://www.cio.com/article/print/<num> que contiene todas las paginas
# dentro del div id=container
if url.startswith('/'):
url = 'http://www.cio.com' + url
segments = url.split('/')
printURL = '/'.join(segments[0:4]) + '/print/' + segments[4] + '#'
return printURL
def parse_index(self):
#######################################################################
# This method should be implemented in recipes that parse a website
# instead of feeds to generate a list of articles. Typical uses are for
# news sources that have a Print Edition webpage that lists all the
# articles in the current print edition. If this function is implemented,
# it will be used in preference to BasicNewsRecipe.parse_feeds().
#
# It must return a list. Each element of the list must be a 2-element
# tuple of the form ('feed title', list of articles).
#
# Each list of articles must contain dictionaries of the form:
#
# {
# 'title' : article title,
# 'url' : URL of print version,
# 'date' : The publication date of the article as a string,
# 'description' : A summary of the article
# 'content' : The full article (can be an empty string). This is used by FullContentProfile
# }
#
# For an example, see the recipe for downloading The Atlantic.
# In addition, you can add 'author' for the author of the article.
#######################################################################
# Primero buscamos cual es la ultima revista que se ha creado
soupinicial = self.index_to_soup('http://www.cio.com/magazine')
# Es el primer enlace que hay en el DIV con class content_body
a = soupinicial.find(
True, attrs={'class': 'content_body'}).find('a', href=True)
INDEX = re.sub(r'\?.*', '', a['href'])
# Como cio.com usa enlaces relativos, le anteponemos el domain name.
if INDEX.startswith('/'): # protegiendonos de que dejen de usarlos
INDEX = 'http://www.cio.com' + INDEX
# Y nos aseguramos en los logs que lo estamos haciendo bien
print("INDEX en parse_index: ", INDEX)
# Ya sabemos cual es la revista... procesemosla.
soup = self.index_to_soup(INDEX)
articles = {}
key = None
feeds = []
# Para empezar nos quedamos solo con dos DIV, 'heading' y ' issue_item'
# Del primero sacamos las categorias (key) y del segundo las urls y
# resumenes
for div in soup.findAll(True,
attrs={'class': ['heading', 'issue_item']}):
if ''.join(div['class']) == 'heading':
key = string.capwords(self.tag_to_string(div.span))
print("Key: ", key) # Esto es para depurar
articles[key] = []
feeds.append(key)
elif ''.join(div['class']) == 'issue_item':
a = div.find('a', href=True)
if not a:
continue
url = re.sub(r'\?.*', '', a['href'])
print("url: ", url) # Esto es para depurar
# Ya para nota, quitar al final las dos ultimas palabras
title = self.tag_to_string(a, use_alt=True).strip()
# No es la fecha de publicacion sino la de colecta
pubdate = strftime('%a, %d %b')
# Dentro de la div 'issue_item' el unico parrafo que hay es el
# resumen
summary = div.find('p')
# Si hay summary la description sera el summary... si no, la
# dejamos en blanco
description = ''
if summary:
description = self.tag_to_string(summary, use_alt=False)
print("Description = ", description)
# Esto esta copiado del NY times
feed = key if key is not None else 'Uncategorized'
if feed not in articles:
articles[feed] = []
if 'podcasts' not in url:
articles[feed].append(
dict(title=title, url=url, date=pubdate,
description=description,
content=''))
feeds = [(k, articles[k]) for k in feeds if k in articles]
return feeds

28
recipes/cityavisen_dk.recipe
View File

@ -1,28 +0,0 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
# https://manual.calibre-ebook.com/news_recipe.html
from __future__ import absolute_import, division, print_function, unicode_literals
from calibre.web.feeds.news import BasicNewsRecipe
'''
City Avisen
'''
class CityAvisen_dk(BasicNewsRecipe):
__author__ = 'CoderAllan.github.com'
title = 'City Avisen'
category = 'newspaper, news, localnews, sport, culture, Denmark'
oldest_article = 7
max_articles_per_feed = 50
auto_cleanup = True
language = 'da'
feeds = [
('City Avisen', 'http://minby.dk/city-avisen/feed/'),
('Kommentarer til City Avisen', 'http://minby.dk/city-avisen/comments/feed/'),
]

16
recipes/cjr.recipe
View File

@ -1,16 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class CJR(BasicNewsRecipe):
title = u'Columbia Journalism Review'
__author__ = u'Xanthan Gum'
description = 'News about journalism.'
language = 'en'
oldest_article = 7
max_articles_per_feed = 100
feeds = [(u'News Stories', u'http://www.cjr.org/index.xml')]
def print_version(self, url):
return url + '?page=all&print=true'

28
recipes/clarion_ledger.recipe
View File

@ -1,28 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class ClarionLedger(BasicNewsRecipe):
title = u'Clarion Ledger'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
language = 'en'
__author__ = 'cr4zyd'
feeds = [
(u'Local News', u'http://www.clarionledger.com/apps/pbcs.dll/oversikt?Category=RSS01'),
(u'Breaking News', u'http://www.clarionledger.com/apps/pbcs.dll/section?Category=RSS'),
(u'Sports', u'http://www.clarionledger.com/apps/pbcs.dll/oversikt?Category=RSS02'),
(u'Business', u'http://www.clarionledger.com/apps/pbcs.dll/oversikt?Category=RSS03')]
keep_only_tags = [dict(name='div', attrs={'class': 'article-headline'}),
dict(name='div', attrs={'class': 'article-bodytext'})]
remove_tags = [dict(name=['img', 'script', 'li']),
dict(name='p', attrs={'class': 'ratingbyline'}),
dict(name='div', attrs={'class': 'article-tools'}),
dict(name='div', attrs={
'class': 'article-pagination article-pagination-top'}),
dict(name='div', attrs={
'class': 'article-pagination article-pagination-bottom'}),
dict(name='div', attrs={'class': 'articleflex-container'})]

53
recipes/clic_rbs.recipe
View File

@ -1,53 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class ClicRBS(BasicNewsRecipe):
title = u'ClicRBS'
language = 'pt'
__author__ = 'arvoredo'
oldest_article = 3
max_articles_per_feed = 9
cover_url = 'http://www.publicidade.clicrbs.com.br/clicrbs/imgs/logo_clic.gif'
remove_tags = [
dict(name='div', attrs={
'class': ['clic-barra-inner', 'botao-versao-mobile ']})
]
remove_tags_before = dict(name='div ', attrs={'class': 'descricao'})
remove_tags_before = dict(name='div', attrs={'id': 'glb-corpo'})
remove_tags_before = dict(name='div', attrs={'class': 'descricao'})
remove_tags_before = dict(name='div', attrs={'class': 'coluna'})
remove_tags_after = dict(name='div', attrs={'class': 'extra'})
remove_tags_after = dict(name='div', attrs={'id': 'links-patrocinados'})
remove_tags_after = dict(name='h4', attrs={'class': 'tipo-c comente'})
remove_tags_after = dict(name='ul', attrs={'class': 'lista'})
feeds = [
(u'zerohora.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?uf=1&local=1&channel=13'),
(u'diariocatarinense.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?uf=2&local=18&channel=67'),
(u'Concursos e Emprego', u'http://g1.globo.com/Rss2/0,,AS0-9654,00.xml'),
(u'Pioneiro.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?channel=87&uf=1&local=1'),
(u'Economia, zerohora.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=801&uf=1&local=1&channel=13'),
(u'Esportes, zerohora.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=802&uf=1&local=1&channel=13'),
(u'Economia, Pioneiro.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=1180&channel=87&uf=1&local=1'),
(u'Política, Pioneiro.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=1185&channel=87&uf=1&local=1'),
(u'Mundo, Pioneiro.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=1184&channel=87&uf=1&local=1'),
(u'Catarinense, Esportes, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=&theme=371&uf=2&channel=2'),
(u'Geral, Pioneiro.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=1183&channel=87&uf=1&local=1'),
(u'Estilo de Vida, zerohora.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=805&uf=1&local=1&channel=13'),
(u'Corrida, Corrida, Esportes, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=1313&theme=15704&uf=1&channel=2'),
(u'Jornal de Santa Catarina, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?espid=159&uf=2&local=18'),
(u'Grêmio, Futebol, Esportes, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=11&theme=65&uf=1&channel=2'),
(u'Velocidade, Esportes, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=1314&theme=2655&uf=1&channel=2')
]
extra_css = '''
cite{color:#007BB5; font-size:xx-small; font-style:italic;}
body{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
h3{font-size:large; color:#082963; font-weight:bold;}
#ident{color:#0179B4; font-size:xx-small;}
p{color:#000000;font-weight:normal;}
.commentario p{color:#007BB5; font-style:italic;}
'''

63
recipes/climate_progress.recipe
View File

@ -1,63 +0,0 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
climateprogress.org
'''
from calibre.ebooks.BeautifulSoup import Tag
from calibre.web.feeds.news import BasicNewsRecipe
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 ClimateProgress(BasicNewsRecipe):
title = 'Climate Progress'
__author__ = 'Darko Miletic'
description = "An insider's view of climate science, politics and solutions"
publisher = 'Climate Progress'
category = 'news, ecology, climate, blog'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = True
encoding = 'utf-8'
language = 'en'
lang = 'en'
direction = 'ltr'
html2lrf_options = [
'--comment', description, '--category', category, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + \
'"\ncomments="' + description + '"\ntags="' + category + '"'
extra_css = '''
h2{color:#003366;font-size: large ;font-family:Arial,Helvetica,sans-serif; font-weight:bold;}
h3{color:#003366;font-size: small ;font-family:Arial,Helvetica,sans-serif; font-weight:bold;}
h4{color:#003366;font-size: x-small ;font-family:Arial,Helvetica,sans-serif; font-weight:bold;}
.date{color:#333333; font-size:xx-small; font-family:Arial,Helvetica,sans-serif; font-style:italic}
a{color:#339966;}
body{font-family:Georgia,Times New Roman,Times,serif; font-size:x-small;color:#333333;}
'''
feeds = [(u'Posts', u'http://feeds.feedburner.com/climateprogress/lCrX')]
def preprocess_html(self, soup):
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 self.adeify_images(soup)

33
recipes/coding_horror.recipe
View File

@ -1,33 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2009-2012, Darko Miletic <darko.miletic at gmail.com>'
'''
www.codinghorror.com/blog/
'''
from calibre.web.feeds.news import BasicNewsRecipe
class CodingHorror(BasicNewsRecipe):
title = 'Coding Horror'
__author__ = 'Darko Miletic'
description = 'programming and human factors - Jeff Atwood'
category = 'blog, programming'
publisher = 'Jeff Atwood'
language = 'en'
oldest_article = 30
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = True
encoding = 'utf8'
auto_cleanup = True
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'authors': publisher
}
remove_tags = [
dict(name=['object', 'link']), dict(
name='div', attrs={'class': 'feedflare'})
]
feeds = [(u'Articles', u'http://feeds2.feedburner.com/codinghorror')]

54
recipes/columbusdispatch.recipe
View File

@ -1,54 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class ColumbusDispatchRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'kwetal'
language = 'en'
version = 1
title = u'The Columbus Dispatch'
publisher = u'The Columbus Dispatch'
category = u'News, Newspaper'
description = u'Daily newspaper from central Ohio'
use_embedded_content = False
remove_empty_feeds = True
oldest_article = 1.2
use_embedded_content = False
no_stylesheets = True
auto_cleanup = True
# Feeds from http://www.dispatch.com/live/content/rss/index.html
feeds = [
('Local',
'http://www.dispatch.com/content/syndication/news_local-state.xml'),
('National',
'http://www.dispatch.com/content/syndication/news_national.xml'),
('Business',
'http://www.dispatch.com/content/syndication/news_business.xml'),
('Editorials',
'http://www.dispatch.com/content/syndication/opinion_editorials.xml'),
('Columnists',
'http://www.dispatch.com/content/syndication/opinion_columns.xml'),
('Life and Arts',
'http://www.dispatch.com/content/syndication/lae_life-and-arts.xml'),
('OSU Sports',
'http://www.dispatch.com/content/syndication/sports_osu.xml'),
('Auto Racing',
'http://www.dispatch.com/content/syndication/sports_auto-racing.xml'),
('Outdoors',
'http://www.dispatch.com/content/syndication/sports_outdoors.xml'),
('Bengals',
'http://www.dispatch.com/content/syndication/sports_bengals.xml'),
('Indians',
'http://www.dispatch.com/content/syndication/sports_indians.xml'),
('Clippers',
'http://www.dispatch.com/content/syndication/sports_clippers.xml'),
('Crew',
'http://www.dispatch.com/content/syndication/sports_crew.xml'),
('Reds',
'http://www.dispatch.com/content/syndication/sports_reds.xml'),
('Blue Jackets',
'http://www.dispatch.com/content/syndication/sports_bluejackets.xml'),
]

27
recipes/computerworld_pl.recipe
View File

@ -1,27 +0,0 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Computerworld_pl(BasicNewsRecipe):
title = u'Computerworld.pl'
__author__ = 'fenuks'
description = u'Serwis o IT w przemyśle, finansach, handlu, administracji oraz rynku IT i telekomunikacyjnym - wiadomości, opinie, analizy, porady prawne'
category = 'IT'
language = 'pl'
masthead_url = 'http://g1.computerworld.pl/cw/beta_gfx/cw2.gif'
cover_url = 'http://g1.computerworld.pl/cw/beta_gfx/cw2.gif'
no_stylesheets = True
oldest_article = 7
max_articles_per_feed = 100
use_embedded_content = False
preprocess_regexps = [(re.compile(u'Zobacz również:', re.IGNORECASE), lambda m: ''),
(re.compile(u'[*]+reklama[*]+', re.IGNORECASE), lambda m: ''), ]
keep_only_tags = [dict(name='article')]
remove_tags = [dict(attrs={'class': ['share_tools nocontent', 'rec']}),
dict(name='ul',attrs={'class':'tags'}),
dict(name='ol'),
dict(id=['topComment', 'bottom_tools'])]
feeds = [(u'Wiadomo\u015bci', u'https://www.computerworld.pl/news?rss')]

78
recipes/consortium_news.recipe
View File

@ -1,78 +0,0 @@
#!/usr/bin/env python
##
# Title: Consortium News
##
# License: GNU General Public License v3 -
# http://www.gnu.org/copyleft/gpl.html
# Feb 2012: Initial release
__license__ = 'GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html'
'''
consortiumnews.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class ConsortiumNews(BasicNewsRecipe):
title = u'Consortium News'
publisher = 'Copyright © 2012 Consortiumnews. All Rights Reserved.'
language = 'en'
__author__ = 'kiavash'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
# Flattens all the tables to make it compatible with Nook
conversion_options = {'linearize_tables': True}
remove_attributes = ['border', 'cellspacing', 'align', 'cellpadding', 'colspan',
'valign', 'vspace', 'hspace', 'alt', 'width', 'height']
# Specify extra CSS - overrides ALL other CSS (IE. Added last).
extra_css = 'body { font-family: verdana, helvetica, sans-serif; } \
.introduction, .first { font-weight: bold; } \
.cross-head { font-weight: bold; font-size: 125%; } \
.cap, .caption { display: block; font-size: 80%; font-style: italic; } \
.cap, .caption, .caption img, .caption span { display: block; margin: 5px auto; } \
.byl, .byd, .byline img, .byline-name, .byline-title, .author-name, .author-position, \
.correspondent-portrait img, .byline-lead-in, .name, .bbc-role { display: block; \
font-size: 80%; font-style: italic; margin: 1px auto; } \
.story-date, .published { font-size: 80%; } \
table { width: 100%; } \
td img { display: block; margin: 5px auto; } \
ul { padding-top: 10px; } \
ol { padding-top: 10px; } \
li { padding-top: 5px; padding-bottom: 5px; } \
h1 { font-size: 175%; font-weight: bold; } \
h2 { font-size: 150%; font-weight: bold; } \
h3 { font-size: 125%; font-weight: bold; } \
h4, h5, h6 { font-size: 100%; font-weight: bold; }'
# Remove the line breaks and float left/right and picture width/height.
preprocess_regexps = [(re.compile(r'<br[ ]*/>', re.IGNORECASE), lambda m: ''),
(re.compile(r'<br[ ]*clear.*/>',
re.IGNORECASE), lambda m: ''),
(re.compile(r'float:.*?'), lambda m: ''),
(re.compile(r'width:.*?px'), lambda m: ''),
(re.compile(r'height:.*?px'), lambda m: ''),
(re.compile(r'<a.*?>'), lambda h1: ''),
(re.compile(r'</a>'), lambda h2: ''),
]
# Main article is inside this tag
keep_only_tags = [
dict(name='div', attrs={'id': lambda x: x and 'post-' in x})]
remove_tags = [
# remove 'Share this Article'
dict(name='div', attrs={'class': 'sociable'}),
dict(name='p', attrs={'class': 'tags'}), # remove 'Tags: ... '
]
feeds = [(u'Consortium News', u'http://feeds.feedburner.com/Consortiumnewscom')]

33
recipes/contemporary_argentine_writers.recipe
View File

@ -1,33 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2013, Darko Miletic <darko.miletic at gmail.com>'
'''
contemporaryargentinewriters.wordpress.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class contemporaryargentinewriters(BasicNewsRecipe):
title = 'Contemporary Argentine Writers'
__author__ = 'Darko Miletic'
description = 'Short stories by Argentine writers (and others) translated into English'
publisher = 'Dario Bard'
category = 'fiction, literature, Argentina, english'
oldest_article = 25
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = True
language = 'en_AR'
remove_empty_feeds = True
publication_type = 'blog'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif }
img{margin-bottom: 0.4em; display:block}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
feeds = [(u'Posts', u'http://contemporaryargentinewriters.wordpress.com/feed/')]

95
recipes/corriere_della_sera_en.recipe
View File

@ -1,95 +0,0 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = 'Lorenzo Vigentini, based on Darko Miletic'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>, Lorenzo Vigentini <l.vigentini at gmail.com>'
__version__ = 'v1.02'
__date__ = '14, March 2010'
__description__ = 'Italian daily newspaper (english version)'
# NOTE: the feeds url are broken on the main site as the permalink structure has been changed erroneously ie:
# actual link in feed http://www.corriere.it/english/10_marzo_11/legitimate_impediment_approved_de9ba480-2cfd-11df-a00c-00144f02aabe.shtml
# this needs to be change to
# real feed URL
# http://www.corriere.it/International/english/articoli/2010/03/11/legitimate_impediment_approved.shtml
'''
http://www.corriere.it/
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ilCorriereEn(BasicNewsRecipe):
author = 'Lorenzo Vigentini, based on Darko Miletic'
description = 'Italian daily newspaper (english version)'
cover_url = 'http://images.corriereobjects.it/images/static/common/logo_home.gif?v=200709121520'
title = u'Il Corriere della sera (english) '
publisher = 'RCS Digital'
category = 'News, politics, culture, economy, general interest'
language = 'en'
timefmt = '[%a, %d %b, %Y]'
oldest_article = 5
max_articles_per_feed = 100
use_embedded_content = False
recursion = 10
remove_javascript = True
no_stylesheets = True
recipe_specific_options = {
'days': {
'short': 'Oldest article to download from this news source. In days ',
'long': 'For example, 0.5, gives you articles from the past 12 hours',
'default': str(oldest_article)
}
}
def __init__(self, *args, **kwargs):
BasicNewsRecipe.__init__(self, *args, **kwargs)
d = self.recipe_specific_options.get('days')
if d and isinstance(d, str):
self.oldest_article = float(d)
def get_article_url(self, article):
articleUrl = article.get('link')
segments = articleUrl.split('/')
basename = '/'.join(segments[:3]) + '/' + \
'International/english/articoli/'
# the date has to be redone with the url structure
mlist1 = ['gennaio', 'febbraio', 'marzo', 'aprile', 'maggio', 'giugno',
'luglio', 'agosto', 'settembre', 'ottobre', 'novembre', 'dicembre']
mlist2 = ['01', '02', '03', '04', '05',
'06', '07', '08', '09', '10', '11', '12']
myDate = segments[4].split('_')
x = 0
for x in range(11):
if myDate[1] == mlist1[x]:
noMonth = mlist2[x]
break
newDateUrl = '20' + myDate[0] + '/' + noMonth + '/' + myDate[2] + '/'
# clean the article title
articleURLseg = segments[5].split('-')
myArticle = (articleURLseg[0])[:-9] + '.shtml'
myURL = basename + newDateUrl + myArticle
# print myURL
return myURL
keep_only_tags = [
dict(name='div', attrs={'class': ['news-dettaglio article', 'article']})]
remove_tags = [
dict(name=['base', 'object', 'link', 'embed']),
dict(name='div', attrs={'class': 'news-goback'}),
dict(name='ul', attrs={'class': 'toolbar'})
]
remove_tags_after = dict(name='p', attrs={'class': 'footnotes'})
feeds = [
(u'News', u'http://www.corriere.it/rss/english.xml')
]

55
recipes/corriere_dello_sport.recipe
View File

@ -1,55 +0,0 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = 'GabrieleMarini, based on Darko Miletic'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>, Gabriele Marini'
__version__ = ' '
__date__ = '14-06-2010'
__description__ = 'Italian daily newspaper'
'''
http://www.corrieredellosport.it/
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ilCorrieredelloSport(BasicNewsRecipe):
__author__ = 'Gabriele Marini'
description = 'Italian daily newspaper'
cover_url = 'http://edicola.corrieredellosport.it/newsmem/corsport/prima/nazionale_prima.jpg'
title = u'Il Corriere dello Sport'
publisher = 'CORRIERE DELLO SPORT s.r.l. '
category = 'Sport'
language = 'it'
timefmt = '[%a, %d %b, %Y]'
oldest_article = 10
max_articles_per_feed = 100
use_embedded_content = False
recursion = 10
remove_javascript = True
no_stylesheets = True
html2lrf_options = [
'--comment', description, '--category', category, '--publisher', publisher, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + \
description + '"\ntags="' + category + '"\nlinearize_tables=True'
keep_only_tags = [
dict(name='h1', attrs={'class': ['tit_Article']}),
dict(name='h1', attrs={'class': ['tit_Article_mondiali']}),
dict(name='div', attrs={'class': ['box_Img']}),
dict(name='p', attrs={'class': ['summary', 'text']})]
feeds = [
(u'Primo Piano', u'http://www.corrieredellosport.it/rss/primo_piano.xml'),
(u'Calcio', u'http://www.corrieredellosport.it/rss/Calcio-3.xml'),
(u'Formula 1', u'http://www.corrieredellosport.it/rss/Formula-1-7.xml'),
(u'Moto', u'http://www.corrieredellosport.it/rss/Moto-8.xml'),
(u'Piu visti', u'http://www.corrieredellosport.it/rss/piu_visti.xml')
]

66
recipes/cosmopolitan.recipe
View File

@ -1,66 +0,0 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
'''
Muy Interesante
'''
from calibre.web.feeds.news import BasicNewsRecipe
class General(BasicNewsRecipe):
title = 'Cosmopolitan'
__author__ = 'Gustavo Azambuja'
description = 'Revista Cosmopolitan, Edicion Espanola'
language = 'es'
timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False
recursion = 1
encoding = 'utf8'
remove_javascript = True
no_stylesheets = True
conversion_options = {'linearize_tables': True}
oldest_article = 180
max_articles_per_feed = 100
keep_only_tags = [
dict(id=['contenido']),
dict(name='td', attrs={'class': ['contentheading', 'txt_articulo']})
]
remove_tags = [
dict(name='div', attrs={'class': ['breadcrumb', 'bloque1', 'article', 'bajo_title',
'tags_articles', 'otrosenlaces_title', 'otrosenlaces_parent', 'compartir']}),
dict(name='div', attrs={'id': 'comment'}),
dict(name='table', attrs={'class': 'pagenav'}),
dict(name=['object', 'link'])
]
remove_attributes = ['width', 'height', 'style', 'font', 'color']
extra_css = '''
h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
img {float:left; clear:both; margin:10px}
p {font-family:Arial,Helvetica,sans-serif;}
'''
feeds = [
(u'Articulos', u'http://feeds.feedburner.com/cosmohispano/FSSt')
]
def preprocess_html(self, soup):
attribs = ['style', 'font', 'valign', 'colspan', 'width', 'height', 'rowspan', 'summary', 'align', 'cellspacing', 'cellpadding', 'frames', 'rules', 'border' ] # noqa
for item in soup.body.findAll(name=['table', 'td', 'tr', 'th', 'caption', 'thead', 'tfoot', 'tbody', 'colgroup', 'col']):
item.name = 'div'
for attrib in attribs:
item[attrib] = ''
del item[attrib]
return soup
def get_cover_url(self):
index = 'http://www.cosmohispano.com/revista'
soup = self.index_to_soup(index)
link_item = soup.find('img', attrs={'class': 'img_portada'})
if link_item:
cover_url = "http://www.cosmohispano.com" + link_item['src']
return cover_url

36
recipes/cosmopolitan_de.recipe
View File

@ -1,36 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1305567197(BasicNewsRecipe):
title = u'Cosmopolitan.de'
__author__ = 'schuster'
oldest_article = 7
language = 'de'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
remove_javascript = True
cover_url = 'http://www.cosmopolitan.com/cm/shared/site_images/print_this/cosmopolitan_logo.gif'
remove_tags_before = dict(name='h1', attrs={'class': 'artikel'})
remove_tags_after = dict(name='div', attrs={'class': 'morePages'})
extra_css = '''
h2{font-family:Arial,Helvetica,sans-serif; font-size: x-small;}
h1{ font-family:Arial,Helvetica,sans-serif; font-size:x-large; font-weight:bold;}
'''
remove_tags = [dict(id='strong'),
dict(title='strong'),
dict(name='span'),
dict(name='li', attrs={'class': 'large'}),
dict(name='ul', attrs={
'class': 'articleImagesPortrait clearfix'}),
dict(name='p', attrs={'class': 'external'}),
dict(name='a', attrs={'target': '_blank'}), ]
feeds = [(u'Komplett', u'http://www.cosmopolitan.de/rss/allgemein.xml'),
(u'Mode', u'http://www.cosmopolitan.de/rss/mode.xml'),
(u'Beauty', u'http://www.cosmopolitan.de/rss/beauty.xml'),
(u'Liebe&Sex', u'http://www.cosmopolitan.de/rss/liebe.xml'),
(u'Psychologie', u'http://www.cosmopolitan.de/rss/psychologie.xml'),
(u'Job&Karriere', u'http://www.cosmopolitan.de/rss/job.xml'),
(u'Lifestyle', u'http://www.cosmopolitan.de/rss/lifestyle.xml'),
(u'Shopping', u'http://www.cosmopolitan.de/rss/shopping.xml'),
(u'Bildergalerien', u'http://www.cosmopolitan.de/rss/bildgalerien.xml')]

41
recipes/cosmopolitan_uk.recipe
View File

@ -1,41 +0,0 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1390635673(BasicNewsRecipe):
title = u'Cosmopolitan UK'
description = 'Womens Fashion, beauty and Gossip for women from COSMOPOLITAN -UK'
language = 'en_GB'
__author__ = 'Dave Asbury'
# 2/2/14
oldest_article = 28
max_articles_per_feed = 10
compress_news_images = True
compress_news_images_max_size = 20
auto_cleanup_keep = '//div[@class="articleHeading"]'
auto_cleanup = True
ignore_duplicate_articles = {'title', 'url'}
no_stylesheets = True
masthead_url = 'http://www.cosmopolitan.co.uk//cm/cosmopolitanuk/site_images/site_logo.gif'
cover_url = 'http://www.natmagnewsletters.co.uk/CIRCULES/CosmoXXLCover.jpg'
# kovids code
def preprocess_raw_html(self, raw_html, url):
for pat, f in [
(re.compile(r':: [\w].+</title>',
re.DOTALL), lambda m: '</title>'),
]:
raw_html = pat.sub(f, raw_html)
return raw_html
feeds = [
(u'Love & Sex', u'http://www.cosmopolitan.co.uk/love-sex/rss/'),
(u'Men', u'http://cosmopolitan.co.uk/men/rss/'),
(u'Fashion', u'http://cosmopolitan.co.uk/fashion/rss/'),
(u'Hair & Beauty', u'http://cosmopolitan.co.uk/beauty-hair/rss/'),
(u'LifeStyle', u'http://cosmopolitan.co.uk/lifestyle/rss/'),
(u'Cosmo On Campus', u'http://cosmopolitan.co.uk/campus/rss/'),
(u'Celebrity Gossip', u'http://cosmopolitan.co.uk/celebrity-gossip/rss/')]

66
recipes/cotidianul.recipe
View File

@ -1,66 +0,0 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103'
'''
cotidianul.ro
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Cotidianul(BasicNewsRecipe):
title = u'Cotidianul'
__author__ = u'Silviu Cotoar\u0103'
description = u''
publisher = u'Cotidianul'
oldest_article = 25
language = 'ro'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
category = 'Ziare,Stiri'
encoding = 'utf-8'
cover_url = 'http://www.cotidianul.ro/images/cotidianul.png'
conversion_options = {
'comments': description, 'tags': category, 'language': language, 'publisher': publisher
}
extra_css = '''
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;}
.byline {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
.date {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
.copyright {font-family:Arial,Helvetica,sans-serif;font-size:xx-small;text-align:center}
.story{font-family:Arial,Helvetica,sans-serif;font-size:small;}
.entry-asset asset hentry{font-family:Arial,Helvetica,sans-serif;font-size:small;}
.pagebody{font-family:Arial,Helvetica,sans-serif;font-size:small;}
.maincontentcontainer{font-family:Arial,Helvetica,sans-serif;font-size:small;}
.story-body{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
keep_only_tags = [
dict(name='div', attrs={'class': 'titlu'}), dict(name='div', attrs={
'class': 'gallery clearfix'}), dict(name='div', attrs={'align': 'justify'})
]
remove_tags = [
dict(name='div', attrs={'class': ['space']}), dict(
name='div', attrs={'id': ['title_desc']})
]
remove_tags_after = [
dict(name='div', attrs={'class': ['space']}), dict(
name='span', attrs={'class': ['date']})
]
feeds = [
(u'Feeds', u'http://www.cotidianul.ro/rssfeed/ToateStirile.xml')
]
def preprocess_html(self, soup):
return self.adeify_images(soup)

11
recipes/counterpunch.recipe
View File

@ -1,11 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class Counterpunch(BasicNewsRecipe):
title = u'Counterpunch'
oldest_article = 7
max_articles_per_feed = 100
auto_cleanup = True
language = 'en'
feeds = [(u'Counterpunch', u'http://www.counterpunch.org/category/article/feed/')]

44
recipes/countryfile.recipe
View File

@ -1,44 +0,0 @@
import re
from calibre import browser
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1325006965(BasicNewsRecipe):
title = u'Countryfile.com'
__author__ = 'Dave Asbury'
description = 'The official website of Countryfile Magazine'
# last updated 24.10.14
language = 'en_GB'
oldest_article = 30
max_articles_per_feed = 25
remove_empty_feeds = True
no_stylesheets = True
auto_cleanup = True
compress_news_images = True
ignore_duplicate_articles = {'title', 'url'}
def get_cover_url(self):
soup = self.index_to_soup('http://www.countryfile.com/magazine')
cov = soup.find(attrs={'class': re.compile(
'imagecache imagecache-250px')}) # 'width' : '160',
cov = str(cov)
cov = cov[10:]
cov = cov[:-135]
# print '++++ ',cov,' ++++'
br = browser()
br.set_handle_redirect(False)
try:
br.open_novisit(cov)
cover_url = cov
except:
cover_url = 'http://www.countryfile.com/sites/default/files/imagecache/160px_wide/cover/2_1.jpg'
return cover_url
preprocess_regexps = [
(re.compile(r' \| Countryfile.com', re.IGNORECASE | re.DOTALL), lambda match: '')]
feeds = [
(u'Country News', u'http://www.feed43.com/7204505705648666.xml'),
(u'Articles', u'http://www.feed43.com/8542080013204443.xml'),
]

33
recipes/courier_mail.recipe
View File

@ -1,33 +0,0 @@
import datetime
from calibre.web.feeds.news import BasicNewsRecipe
class Politics(BasicNewsRecipe):
title = u'The Courier-Mail'
description = 'Breaking news headlines for Brisbane and Queensland, Australia. The Courier-Mail is owned by News Corp Australia.'
language = 'en_AU'
__author__ = 'Krittika Goyal, James Cridland'
oldest_article = 3 # days
max_articles_per_feed = 20
use_embedded_content = False
d = datetime.datetime.today()
cover_url='http://mfeeds.news.com.au/smedia/NCCOURIER/NCCM_1_' + d.strftime('%Y_%m_%d') + '_thumb_big.jpg'
masthead_url='https://couriermail.digitaleditions.com.au/images/couriermail-logo.jpg'
no_stylesheets = True
auto_cleanup = True
handle_gzip = True
feeds = [
('Top Stories', 'http://www.couriermail.com.au/rss'),
('Breaking', 'https://www.couriermail.com.au/news/breaking-news/rss'),
('Queensland', 'https://www.couriermail.com.au/news/queensland/rss'),
('Technology', 'https://www.couriermail.com.au/technology/rss'),
('Entertainment', 'https://www.couriermail.com.au/entertainment/rss'),
('Finance','https://www.couriermail.com.au/business/rss'),
('Sport', 'https://www.couriermail.com.au/sport/rss'),
]
# This isn't perfect, but works rather better than it once did. To do - remove links to subscription content.

28
recipes/courrier.recipe
View File

@ -1,28 +0,0 @@
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.web.feeds.news import BasicNewsRecipe
class CourierPress(BasicNewsRecipe):
title = u'Courier Press'
language = 'en'
__author__ = 'Krittika Goyal'
oldest_article = 1 # days
max_articles_per_feed = 25
remove_stylesheets = True
remove_tags = [
dict(name='iframe'),
]
feeds = [
('Courier Press',
'http://www.courierpress.com/rss/headlines/news/'),
]
def preprocess_html(self, soup):
story = soup.find(name='div', attrs={'id': 'article_body'})
soup = BeautifulSoup(
'<html><head><title>t</title></head><body></body></html>')
body = soup.find(name='body')
body.insert(0, story)
return soup

21
recipes/craigslist.recipe
View File

@ -1,21 +0,0 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import with_statement
__license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
from calibre.web.feeds.news import BasicNewsRecipe
class CraigsList(BasicNewsRecipe):
title = u'craigslist - Best Of'
oldest_article = 365
max_articles_per_feed = 100
language = 'en'
__author__ = 'kiodane'
feeds = [(u'Best of craigslist',
u'http://www.craigslist.org/about/best/all/index.rss'), ]

45
recipes/credit_slips.recipe
View File

@ -1,45 +0,0 @@
#!/usr/bin/env python
__license__ = 'GPL 3'
__copyright__ = 'zotzo'
__docformat__ = 'restructuredtext en'
from calibre.web.feeds.news import BasicNewsRecipe
class CreditSlips(BasicNewsRecipe):
language = 'en'
__author__ = 'zotzot'
version = 2
title = u'Credit Slips.org'
publisher = u'Bankr-L'
category = u'Economic blog'
description = u'A discussion on credit and bankruptcy'
cover_url = 'http://bit.ly/eAKNCB'
oldest_article = 15
max_articles_per_feed = 100
use_embedded_content = True
no_stylesheets = True
remove_javascript = True
conversion_options = {
'comments': description,
'tags': category,
'language': 'en',
'publisher': publisher,
}
feeds = [
(u'Credit Slips', u'http://www.creditslips.org/creditslips/atom.xml')
]
extra_css = '''
.author {font-family:Helvetica,sans-serif; font-weight:normal;font-size:small;}
h1 {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
p {font-family:Helvetica,Arial,sans-serif;font-size:small;}
body {font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
def populate_article_metadata(self, article, soup, first):
h2 = soup.find('h2')
h2.replaceWith(h2.prettify() + '<p><em>Posted by ' +
article.author + '</em></p>')

79
recipes/cronica.recipe
View File

@ -1,79 +0,0 @@
# -*- mode: python -*-
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2018, Darko Miletic <darko.miletic at gmail.com>'
'''
www.cronica.com.ar
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Veintitres(BasicNewsRecipe):
title = 'Cronica'
__author__ = 'Darko Miletic'
description = 'Últimas noticias'
publisher = 'Grupo Crónica'
category = 'politica, noticias generales, Argentina'
oldest_article = 15
max_articles_per_feed = 100
no_stylesheets = False
use_embedded_content = False
encoding = 'utf-8'
masthead_url = 'https://www.cronica.com.ar/export/sites/cronica/arte/logos/logoCronica.svg_799932565.svg'
language = 'es_AR'
remove_javascript = True
publication_type = 'magazine'
remove_empty_feeds = True
auto_cleanup = True
auto_cleanup_keep = '//h1'
resolve_internal_links = True
INDEX = "https://www.cronica.com.ar"
extra_css = """
img{margin-bottom: 0.8em}
"""
conversion_options = {
'comment': description,
'tags': category,
'publisher': publisher,
'language': language
}
feeds = [
(u'Policiales', u'https://www.cronica.com.ar/seccion/policiales/'),
(u'Politica', u'https://www.cronica.com.ar/seccion/politica/'),
(u'General', u'https://www.cronica.com.ar/seccion/info-general/'),
(u'Mundo', u'https://www.cronica.com.ar/seccion/mundo/'),
(u'Opinion', u'https://www.cronica.com.ar/seccion/opinion/'),
(u'Deportes', u'https://www.cronica.com.ar/seccion/deportes/'),
(u'Cosa de locos', u'https://www.cronica.com.ar/seccion/cosa-de-locos/'),
(u'Espectaculos', u'https://www.diarioshow.com/seccion/espectaculos/'),
]
def parse_index(self):
totalfeeds = []
lfeeds = self.get_feeds()
for feedobj in lfeeds:
feedtitle, feedurl = feedobj
self.report_progress(
0,
_('Fetching feed') + ' %s...' %
(feedtitle if feedtitle else feedurl)
)
articles = []
soup = self.index_to_soup(feedurl)
for item in soup.findAll('a', attrs={'class': 'cover-link'}):
url = self.INDEX + item['href']
if feedtitle == 'Espectaculos':
url = 'https://www.diarioshow.com' + item['href']
title = item['title']
articles.append({
'title': title,
'date': '',
'url': url,
'description': ''
})
totalfeeds.append((feedtitle, articles))
return totalfeeds

50
recipes/curierulnational.recipe
View File

@ -1,50 +0,0 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103'
'''
curierulnational.ro
'''
from calibre.web.feeds.news import BasicNewsRecipe
class CurierulNal(BasicNewsRecipe):
title = u'Curierul Na\u0163ional'
__author__ = u'Silviu Cotoar\u0103'
description = ''
publisher = 'Curierul Na\u0163ional'
oldest_article = 5
language = 'ro'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
category = 'Ziare,Stiri'
encoding = 'utf-8'
cover_url = 'http://www.curierulnational.ro/logo.gif'
conversion_options = {
'comments': description, 'tags': category, 'language': language, 'publisher': publisher
}
keep_only_tags = [
dict(name='div', attrs={'id': 'col1'}), dict(
name='img', attrs={'id': 'placeholder'})
]
remove_tags = [
dict(name='p', attrs={'id': ['alteArticole']}), dict(name='div', attrs={'id': ['textSize']}), dict(
name='ul', attrs={'class': ['unit-rating']}), dict(name='div', attrs={'id': ['comments']})
]
remove_tags_after = [
dict(name='ul', attrs={'class': 'unit-rating'})
]
feeds = [
(u'Feeds', u'http://www.curierulnational.ro/feed.xml')
]
def preprocess_html(self, soup):
return self.adeify_images(soup)

56
recipes/cyberpresse.recipe
View File

@ -1,56 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
class Cyberpresse(BasicNewsRecipe):
title = u'Cyberpresse'
__author__ = 'balok and Sujata Raman'
description = 'Canadian news in French'
language = 'fr'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
html2lrf_options = ['--left-margin=0', '--right-margin=0',
'--top-margin=0', '--bottom-margin=0']
encoding = 'utf-8'
keep_only_tags = [dict(name='div', attrs={'class': 'article-page'}),
dict(name='div', attrs={'id': 'articlePage'}),
]
extra_css = '''
.photodata{font-family:Arial,Helvetica,Verdana,sans-serif;color: #999999; font-size: 90%; }
h1{font-family:Georgia,Times,serif ; font-size: large; }
.amorce{font-family:Arial,Helvetica,Verdana,sans-serif; font-weight:bold;}
.article-page{font-family:Arial,Helvetica,Verdana,sans-serif; font-size: x-small;}
#articlePage{font-family:Arial,Helvetica,Verdana,sans-serif; font-size: x-small;}
.auteur{font-family:Georgia,Times,sans-serif; font-size: 90%; color:#006699 ;}
.bodyText{font-family:Arial,Helvetica,Verdana,sans-serif; font-size: x-small;}
.byLine{font-family:Arial,Helvetica,Verdana,sans-serif; font-size: 90%;}
.entry{font-family:Arial,Helvetica,Verdana,sans-serif; font-size: x-small;}
.minithumb-auteurs{font-family:Arial,Helvetica,Verdana,sans-serif; font-size: 90%; }
a{color:#003399; font-weight:bold; }
'''
remove_tags = [
dict(name='div', attrs={
'class': ['centerbar', 'colspan', 'share-module']}),
dict(name='p', attrs={'class': ['zoom']}),
dict(name='ul', attrs={'class': ['stories']}),
dict(name='h4', attrs={'class': ['general-cat']}),
]
feeds = [(u'Manchettes', u'http://www.cyberpresse.ca/rss/225.xml'),
(u'Capitale nationale', u'http://www.cyberpresse.ca/rss/501.xml'),
(u'Opinions', u'http://www.cyberpresse.ca/rss/977.xml'),
(u'Insolite', u'http://www.cyberpresse.ca/rss/279.xml')
]
def postprocess_html(self, soup, first):
for tag in soup.findAll(name=['i', 'strong']):
tag.name = 'div'
return soup

118
recipes/cynewslive.recipe
View File

@ -1,118 +0,0 @@
from datetime import datetime, timedelta
from calibre.web.feeds.news import BasicNewsRecipe
class CyNewsLiveRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'kwetal'
language = 'en_CY'
version = 1
title = u'Cyprus News Live'
publisher = u'The Cyprus Weekly'
category = u'News, Newspaper'
description = u'News from Cyprus'
use_embedded_content = False
remove_empty_feeds = True
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
pubTime = None
minTime = None
articleCount = 0
INDEX = 'http://www.cynewslive.com'
feeds = []
feeds.append(
('News: Cyprus', 'http://www.cynewslive.com/main/92,0,0,0-CYPRUS.aspx'))
feeds.append(
('News: World', 'http://www.cynewslive.com/main/78,0,0,0-UKWORLD.aspx'))
feeds.append(
('Sport: Football', 'http://www.cynewslive.com/main/82,0,0,0-FOOTBALL.aspx'))
feeds.append(
('Sport: Rugby', 'http://www.cynewslive.com/main/83,0,0,0-RUGBY.aspx'))
feeds.append(
('Sport: Cricket', 'http://www.cynewslive.com/main/85,0,0,0-CRICKET.aspx'))
feeds.append(
('Sport: Tennis', 'http://www.cynewslive.com/main/84,0,0,0-TENNIS.aspx'))
feeds.append(
('Sport: Other', 'http://www.cynewslive.com/main/86,0,0,0-OTHER.aspx'))
feeds.append(
('Business: Local', 'http://www.cynewslive.com/main/100,0,0,0-LOCAL.aspx'))
feeds.append(
('Business: Foreign', 'http://www.cynewslive.com/main/101,0,0,0-FOREIGN.aspx'))
feeds.append(
('Environment', 'http://www.cynewslive.com/main/93,0,0,0-ENVIRONMENT.aspx'))
feeds.append(
('Culture', 'http://www.cynewslive.com/main/208,0,0,0-CULTURE.aspx'))
keep_only_tags = []
keep_only_tags.append(
dict(name='div', attrs={'class': 'ArticleCategories'}))
extra_css = '''
body{font-family:verdana,arial,helvetica,geneva,sans-serif ;}
'''
def parse_index(self):
answer = []
for feed in self.feeds:
self.articleCount = 0
articles = []
soup = self.index_to_soup(feed[1])
table = soup.find('table', attrs={'id': 'ctl00_cp_ctl01_listp'})
if table:
self.pubTime = datetime.now()
self.minTime = self.pubTime - \
timedelta(days=self.oldest_article)
self.find_articles(table, articles)
answer.append((feed[0], articles))
return answer
def postprocess_html(self, soup, first):
for el in soup.findAll(attrs={'style': True}):
del el['style']
for el in soup.findAll('font'):
el.name = 'div'
for attr, value in el:
del el[attr]
return soup
def find_articles(self, table, articles):
for div in table.findAll('div', attrs={'class': 'ListArticle'}):
el = div.find('div', attrs={'class': 'ListArticle_T'})
title = self.tag_to_string(el.a)
url = self.INDEX + el.a['href']
description = self.tag_to_string(
div.find('div', attrs={'class': 'ListArticle_BODY300'}))
el = div.find('div', attrs={'class': 'ListArticle_D'})
if el:
dateParts = self.tag_to_string(el).split(' ')
monthNames = {'January': 1, 'February': 2, 'March': 3, 'April': 4, 'May': 5, 'June': 6,
'July': 7, 'August': 8, 'September': 9, 'October': 10, 'November': 11,
'December': 12}
timeParts = dateParts[3].split(':')
self.pubTime = datetime(year=int(dateParts[2]), month=int(monthNames[dateParts[1]]),
day=int(dateParts[0]), hour=int(timeParts[0]),
minute=int(timeParts[1]))
if self.pubTime >= self.minTime and self.articleCount <= self.max_articles_per_feed:
articles.append(
{'title': title, 'date': self.pubTime, 'url': url, 'description': description})
self.articleCount += 1
else:
return

BIN
recipes/icons/balkanist.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 557 B

BIN
recipes/icons/bangkok_biz.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 297 B

BIN
recipes/icons/bay_citizen.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 1.0 KiB

BIN
recipes/icons/beppe_grillo.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 2.7 KiB

BIN
recipes/icons/berliner_zeitung.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 638 B

BIN
recipes/icons/berlingske_dk.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 445 B

BIN
recipes/icons/bighollywood.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 1.1 KiB

BIN
recipes/icons/birmingham_post.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 550 B

BIN
recipes/icons/biz_portal.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 1.0 KiB

BIN
recipes/icons/boortz.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 198 B

BIN
recipes/icons/borse_online.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 206 B

BIN
recipes/icons/brand_eins.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 470 B

BIN
recipes/icons/brasil_de_fato.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 979 B

BIN
recipes/icons/brecha.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 644 B

BIN
recipes/icons/bsi_news.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 1.2 KiB

BIN
recipes/icons/buchreport.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 974 B

BIN
recipes/icons/buckmasters.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 603 B

BIN
recipes/icons/buenosaireseconomico.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 389 B

BIN
recipes/icons/buffalonews.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 394 B

BIN
recipes/icons/businessworldin.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 237 B

BIN
recipes/icons/cafcaf_dergisi.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 2.0 KiB

BIN
recipes/icons/camera_di_commercio_di_bari.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 2.1 KiB

BIN
recipes/icons/capital.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 494 B

BIN
recipes/icons/capital_de.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 1.1 KiB

BIN
recipes/icons/caravan_magazine_hindi.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 1.2 KiB

BIN
recipes/icons/carta.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 195 B

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