Various Greek news sources by Stelios

This commit is contained in:
Kovid Goyal 2011-11-01 07:41:52 +05:30
parent 9744bd7400
commit 70dafe05cc
4 changed files with 154 additions and 0 deletions

35
recipes/capital_gr.recipe Normal file
View File

@ -0,0 +1,35 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class Capital(BasicNewsRecipe):
title = 'Capital.gr'
__author__ ='Stelios'
description = 'Financial News from Greece'
#max_articles_per_feed = 100
oldest_article = 3
publisher = 'Capital.gr'
category = 'news, GR'
language = 'el'
encoding = 'windows-1253'
cover_url = 'http://files.capital.gr/images/caplogo.gif'
no_stylesheets = True
use_embedded_content = False
remove_empty_feeds = True
keep_only_tags = [
dict(name='h1'),
dict(name='p'),
dict(name='span', attrs={'id' : ["textbody"]})
]
#3 posts seemed to have utf8 encoding
feeds = [
(u'\u039F\u039B\u0395\u03A3 \u039F\u0399 \u0395\u0399\u0394\u0397\u03A3\u0395\u0399\u03A3', 'http://www.capital.gr/news/newsrss.asp?s=-1'),
(u'\u0395\u03A0\u0399\u03A7\u0395\u0399\u03A1\u0397\u03A3\u0395\u0399\u03A3', 'http://www.capital.gr/news/newsrss.asp?s=-2'),
(u'\u0391\u0393\u039F\u03A1\u0395\u03A3', 'http://www.capital.gr/news/newsrss.asp?s=-3'),
(u'\u039F\u0399\u039A\u039F\u039D\u039F\u039C\u0399\u0391', 'http://www.capital.gr/news/newsrss.asp?s=-4'),
(u'\u03A7\u03A1\u0397\u039C. \u0391\u039D\u0391\u039A\u039F\u0399\u039D\u03A9\u03A3\u0395\u0399\u03A3', 'http://www.capital.gr/news/newsrss.asp?s=-6'),
(u'\u039C\u03CC\u03BD\u03B9\u03BC\u03B5\u03C2 \u03C3\u03C4\u03AE\u03BB\u03B5\u03C2: \u039C\u0395 \u0391\u03A0\u039F\u03A8\u0397', 'http://www.capital.gr/articles/articlesrss.asp?catid=4'),
(u'\u039C\u03CC\u03BD\u03B9\u03BC\u03B5\u03C2 \u03C3\u03C4\u03AE\u03BB\u03B5\u03C2: \u03A3\u0399\u03A9\u03A0\u0397\u03A4\u0397\u03A1\u0399\u039F', 'http://www.capital.gr/articles/articlesrss.asp?catid=6'),
(u'\u039C\u03CC\u03BD\u03B9\u03BC\u03B5\u03C2 \u03C3\u03C4\u03AE\u03BB\u03B5\u03C2: \u03A0\u0399\u03A3\u03A9 \u0391\u03A0\u039F \u03A4\u0399\u03A3 \u0393\u03A1\u0391\u039C\u039C\u0395\u03A3', 'http://www.capital.gr/articles/articlesrss.asp?catid=8'),
#(u'\u039C\u03CC\u03BD\u03B9\u03BC\u03B5\u03C2 \u03C3\u03C4\u03AE\u03BB\u03B5\u03C2: \u03A4\u0395\u03A7\u039D\u039F\u039B\u039F\u0393\u0399\u0391', 'http://www.capital.gr/news/newsrss.asp?s=-8') not working for now
]

34
recipes/in_gr.recipe Normal file
View File

@ -0,0 +1,34 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class ingr(BasicNewsRecipe):
title = 'in.gr'
__author__ = 'Stelios'
description = 'News from Greece'
# max_articles_per_feed = 100
oldest_article = 4
publisher = 'in.gr'
category = 'news, GR'
language = 'el'
encoding = 'utf8'
no_stylesheets = True
use_embedded_content = False
remove_empty_feeds = True
encoding = 'utf8'
keep_only_tags = [
dict(name='h1'),
dict(name='div', attrs={'id' : ['in-news-article']})
]
remove_tags = [
dict(name='em', attrs={'class' : ['credits']}),
dict(name='div', attrs={'class' : ['article-tools-hor', 'promo-banners gAds', 'main', 'article-listen-player', 'article-tools-hor-bttm', 'tools-sec', 'article-tools', 'article-listen-player-ver']})
]
feeds = [
(u'\u0395\u03BB\u03BB\u03AC\u03B4\u03B1', 'http://rss.in.gr/feed/news/greece'),
(u'\u0395\u03B9\u03B4\u03AE\u03C3\u03B5\u03B9\u03C2', 'http://rss.in.gr/feed/news'),
(u'\u039A\u03CC\u03C3\u03BC\u03BF\u03C2', 'http://rss.in.gr/feed/news/world'),
(u'\u0395\u03C0\u03B9\u03C3\u03C4\u03AE\u03BC\u03B7', 'http://rss.in.gr/feed/news/science'),
(u'\u03A0\u03BF\u03BB\u03B9\u03C4\u03B9\u03C3\u03BC\u03CC\u03C2', 'http://rss.in.gr/feed/news/culture')
]

48
recipes/newsbeast.recipe Normal file
View File

@ -0,0 +1,48 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class newsbeast(BasicNewsRecipe):
title = 'Newsbeast'
__author__ = 'Stelios'
description = 'News from Greece'
oldest_article = 2
max_articles_per_feed = 100
publisher = 'newsbeast'
category = 'news, GR'
language = 'el'
encoding = 'utf8'
no_stylesheets = True
use_embedded_content = False
remove_empty_feeds = True
encoding = 'utf8'
keep_only_tags = [
dict(name='div', attrs={'class' : ['article-title']}),
# dict(name='img', attrs={'class' : ['article_photo']}),
#If enabled feeds exceede 15MB
dict(name='div', attrs={'class' : ['txt']})
]
remove_tags = [
dict(name='table', attrs={'id':['artFoot']}),
dict(name='img'),
#If removed feeds exceede 15MB
dict(name='p', attrs={'class':['article-details']})
]
feeds = [
(u'\u0395\u03BB\u03BB\u03AC\u03B4\u03B1', 'http://www.newsbeast.gr/feeds/greece'),
(u'\u039A\u03CC\u03C3\u03BC\u03BF\u03C2', 'http://www.newsbeast.gr/feeds/world'),
(u'\u03A0\u03BF\u03BB\u03B9\u03C4\u03B9\u03BA\u03AE', 'http://www.newsbeast.gr/feeds/politiki'),
(u'\u039F\u03B9\u03BA\u03BF\u03BD\u03BF\u03BC\u03AF\u03B1', 'http://www.newsbeast.gr/feeds/financial'),
(u'\u0391\u03B8\u03BB\u03B7\u03C4\u03B9\u03BA\u03AC', 'http://www.newsbeast.gr/feeds/sports'),
(u'\u039A\u03BF\u03B9\u03BD\u03C9\u03BD\u03AF\u03B1', 'http://www.newsbeast.gr/feeds/society'),
(u'\u03A0\u03B5\u03C1\u03B9\u03B2\u03AC\u03BB\u03BB\u03BF\u03BD', 'http://www.newsbeast.gr/feeds/environment'),
(u'Media', 'http://www.newsbeast.gr/feeds/media'),
(u'\u0394\u03B9\u03B1\u03C3\u03BA\u03AD\u03B4\u03B1\u03C3\u03B7', 'http://www.newsbeast.gr/feeds/entertainment'),
(u'Lifestyle', 'http://www.newsbeast.gr/feeds/lifestyle'),
(u'\u03A4\u03B5\u03C7\u03BD\u03BF\u03BB\u03BF\u03B3\u03AF\u03B1', 'http://www.newsbeast.gr/feeds/technology'),
(u'\u0391\u03C5\u03C4\u03BF\u03BA\u03AF\u03BD\u03B7\u03C4\u03BF', 'http://www.newsbeast.gr/feeds/car'),
(u'\u0393\u03C5\u03BD\u03B1\u03AF\u03BA\u03B1', 'http://www.newsbeast.gr/feeds/woman'),
(u'\u03A5\u03B3\u03B5\u03AF\u03B1', 'http://www.newsbeast.gr/feeds/health'),
(u'\u03A0\u03BF\u03BB\u03B9\u03C4\u03B9\u03C3\u03BC\u03CC\u03C2', 'http://www.newsbeast.gr/feeds/culture'),
(u'\u038C,\u03C4\u03B9 \u03BD\u03B1 \u03BD\u03B1\u03B9', 'http://www.newsbeast.gr/feeds/weird')
]

37
recipes/skai.recipe Normal file
View File

@ -0,0 +1,37 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class SKAI(BasicNewsRecipe):
title = 'SKAI'
__author__ = 'Stelios'
description = 'News from Greece'
oldest_article = 2
max_articles_per_feed = 100
publisher = 'skai.gr'
category = 'news, GR'
language = 'el'
encoding = 'utf8'
no_stylesheets = True
use_embedded_content = False
remove_empty_feeds = True
encoding = 'utf8'
keep_only_tags = [
dict(name='h1'),
dict(name='div', attrs={'class' : ['articleText']})
]
feeds = [
(u'\u039A\u03C5\u03C1\u03B9\u03CC\u03C4\u03B5\u03C1\u03B5\u03C2 \u0395\u03B9\u03B4\u03AE\u03C3\u03B5\u03B9\u03C2', 'http://feeds.feedburner.com/skai/Uulu'),
(u'\u0395\u03BB\u03BB\u03AC\u03B4\u03B1', 'http://feeds.feedburner.com/skai/PLwa'),
(u'\u039A\u03CC\u03C3\u03BC\u03BF\u03C2', 'http://feeds.feedburner.com/skai/aqOL'),
(u'\u03A0\u03BF\u03BB\u03B9\u03C4\u03B9\u03BA\u03AE','http://feeds.feedburner.com/skai/yinm'),
(u'\u039F\u03B9\u03BA\u03BF\u03BD\u03BF\u03BC\u03AF\u03B1', 'http://feeds.feedburner.com/skai/oPUt'),
(u'\u03A4\u03B5\u03C7\u03BD\u03BF\u03BB\u03BF\u03B3\u03AF\u03B1', 'http://feeds.feedburner.com/skai/fqsg'),
(u'\u0391\u03B8\u03BB\u03B7\u03C4\u03B9\u03C3\u03BC\u03CC\u03C2', 'http://feeds.feedburner.com/skai/TfmK'),
(u'\u03A5\u03B3\u03B5\u03AF\u03B1', 'http://feeds.feedburner.com/skai/TABn'),
(u'\u03A0\u03BF\u03BB\u03B9\u03C4\u03B9\u03C3\u03BC\u03CC\u03C2', 'http://feeds.feedburner.com/skai/ppGl'),
(u'\u0391\u03C5\u03C4\u03BF\u03BA\u03AF\u03BD\u03B7\u03C3\u03B7', 'http://feeds.feedburner.com/skai/HCCc'),
(u'\u03A0\u03B5\u03C1\u03B9\u03B2\u03AC\u03BB\u03BB\u03BF\u03BD', 'http://feeds.feedburner.com/skai/jVWs'),
(u'\u03A0\u03B1\u03C1\u03AC\u03BE\u03B5\u03BD\u03B1', 'http://feeds.feedburner.com/skai/bpAR')
]