-Trim down the unknown language recipe list

This commit is contained in:
Kovid Goyal 2009-07-22 15:45:50 -06:00
parent b589f00b3b
commit 70a254267c
8 changed files with 32 additions and 24 deletions

View File

@ -12,26 +12,27 @@ class AlJazeera(BasicNewsRecipe):
title = 'Al Jazeera in English'
__author__ = 'Darko Miletic'
description = 'News from Middle East'
language = _('English')
publisher = 'Al Jazeera'
category = 'news, politics, middle east'
simultaneous_downloads = 1
delay = 4
delay = 4
oldest_article = 1
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'iso-8859-1'
remove_javascript = True
use_embedded_content = False
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_table=True'
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_table=True'
keep_only_tags = [dict(name='div', attrs={'id':'ctl00_divContent'})]
remove_tags = [

View File

@ -12,9 +12,10 @@ class Azstarnet(BasicNewsRecipe):
title = 'Arizona Daily Star'
__author__ = 'Darko Miletic'
description = 'news from Arizona'
language = _('English')
publisher = 'azstarnet.com'
category = 'news, politics, Arizona, USA'
delay = 1
delay = 1
oldest_article = 1
max_articles_per_feed = 100
no_stylesheets = True
@ -28,8 +29,8 @@ class Azstarnet(BasicNewsRecipe):
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
def get_browser(self):
br = BasicNewsRecipe.get_browser()
@ -40,8 +41,8 @@ class Azstarnet(BasicNewsRecipe):
br['pass' ] = self.password
br.submit()
return br
keep_only_tags = [dict(name='div', attrs={'id':'storycontent'})]
remove_tags = [
@ -49,15 +50,15 @@ class Azstarnet(BasicNewsRecipe):
,dict(name='div',attrs={'class':'bannerinstory'})
]
feeds = [(u'Tucson Region', u'http://rss.azstarnet.com/index.php?site=metro')]
def preprocess_html(self, soup):
soup.html['dir' ] = 'ltr'
soup.html['lang'] = 'en-US'
mtag = '\n<meta http-equiv="Content-Language" content="en-US"/>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8">\n'
soup.head.insert(0,mtag)
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
del item['style']
return soup

View File

@ -14,6 +14,7 @@ class CodingHorror(BasicNewsRecipe):
description = 'programming and human factors - Jeff Atwood'
category = 'blog, programming'
publisher = 'Jeff Atwood'
language = _('English')
author = 'Jeff Atwood'
oldest_article = 30
max_articles_per_feed = 100

View File

@ -16,6 +16,7 @@ class Sueddeutsche(BasicNewsRecipe):
use_embedded_content = False
timefmt = ' [%a %d %b %Y]'
max_articles_per_feed = 50
language = _('English')
no_stylesheets = True
html2epub_options = 'linearize_tables = True\nbase_font_size2=14'
html2lrf_options = ['--ignore-tables']

View File

@ -11,25 +11,26 @@ from calibre.web.feeds.news import BasicNewsRecipe
class MoneyNews(BasicNewsRecipe):
title = 'Moneynews.com'
__author__ = 'Darko Miletic'
description = 'Financial news worldwide'
description = 'Financial news worldwide'
publisher = 'moneynews.com'
category = 'news, finances, USA, business'
language = _('English')
category = 'news, finances, USA, business'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
feeds = [
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
feeds = [
(u'Street Talk' , u'http://moneynews.newsmax.com/xml/streettalk.xml' )
,(u'Finance News' , u'http://moneynews.newsmax.com/xml/FinanceNews.xml' )
,(u'Economy' , u'http://moneynews.newsmax.com/xml/economy.xml' )
@ -38,12 +39,12 @@ class MoneyNews(BasicNewsRecipe):
,(u'Investing & Analysis' , u'http://moneynews.newsmax.com/xml/investing.xml' )
]
keep_only_tags = [dict(name='table', attrs={'class':'copy'})]
remove_tags = [
dict(name='td' , attrs={'id':'article_fontsize'})
,dict(name='table', attrs={'id':'toolbox' })
,dict(name='tr' , attrs={'id':'noprint3' })
]

View File

@ -15,6 +15,7 @@ class ScottHanselman(BasicNewsRecipe):
category = "Scott, Computer, Zen, .NET, C#, Hanselman, Scott, Weblog, Diabetes, Portland, Zimbabwe, ComputerZen.com - Scott Hanselman's Musings"
publisher = 'Scott Hanselman'
author = 'Scott Hanselman'
language = _('English')
oldest_article = 30
max_articles_per_feed = 100
no_stylesheets = True

View File

@ -15,6 +15,7 @@ class Slate(BasicNewsRecipe):
title = 'Slate'
description = 'A daily magazine on the Web, offering analysis and commentary about politics, news and culture.'
__author__ = 'GRiker@hotmail.com'
language = _('English')
max_articles_per_feed = 40
oldest_article = 7.0
recursions = 0

View File

@ -15,6 +15,7 @@ class StackOverflowBlog(BasicNewsRecipe):
category = 'blog, programming'
publisher = 'StackOverflow team'
oldest_article = 30
language = _('English')
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = True