Update Defense News

This commit is contained in:
Kovid Goyal 2014-11-27 13:06:17 +05:30
parent 712f94049a
commit b524709809

View File

@ -11,52 +11,38 @@ class DefenseNews(BasicNewsRecipe):
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Find late-breaking defense news from the leading defense news weekly' description = 'Find late-breaking defense news from the leading defense news weekly'
publisher = 'Gannett Government Media Corporation' publisher = 'Gannett Government Media Corporation'
category = 'defense news, defence news, defense, defence, defence budget, defence policy'
oldest_article = 31 oldest_article = 31
max_articles_per_feed = 200 max_articles_per_feed = 200
no_stylesheets = True no_stylesheets = True
encoding = 'utf8' encoding = 'cp1252'
use_embedded_content = False use_embedded_content = False
language = 'en' language = 'en'
remove_empty_feeds = True remove_empty_feeds = True
publication_type = 'newspaper' publication_type = 'newspaper'
ignore_duplicate_articles = {'url'}
masthead_url = 'http://www.defensenews.com/images/logo_defensenews2.jpg' masthead_url = 'http://www.defensenews.com/images/logo_defensenews2.jpg'
extra_css = """ extra_css = """
body{font-family: Arial,Helvetica,sans-serif } body{font-family: Arial,Helvetica,sans-serif }
img{margin-bottom: 0.4em; display:block} img{margin-bottom: 0.4em; display:block}
.info{font-size: small; color: gray} .info{font-size: small; color: gray}
""" """
remove_attributes = ['style', 'lang']
conversion_options = { keep_only_tags = [
'comment' : description dict(attrs={'class':['ody-hgroup', 'ody-article']}),
, 'tags' : category ]
, 'publisher' : publisher remove_tags = [
, 'language' : language dict(name=['meta','link']),
} dict(attrs={'class':['toolbar', 'toolsShareWrap', 'ody-bo-sm ', 'ody-comments', 'ody-related-links','left','right']}),
dict(id=['factsMore', 'ody-nextstoryslider']),
remove_tags = [
dict(name=['meta','link'])
,dict(attrs={'class':['toolbar','related','left','right']})
] ]
remove_tags_before = attrs={'class':'storyWrp'}
remove_tags_after = attrs={'class':'middle'}
remove_attributes=['lang']
feeds = [ feeds = [
(u'Europe' , u'http://www.defensenews.com/rss/eur/' ) (u'Europe' , u'http://www.defensenews.com/rss/europe')
,(u'Americas', u'http://www.defensenews.com/rss/ame/' ) ,(u'Americas', u'http://www.defensenews.com/rss/americas')
,(u'Asia & Pacific rim', u'http://www.defensenews.com/rss/asi/' ) ,(u'Asia & Pacific rim', u'http://www.defensenews.com/rss/asia-pacific-rim')
,(u'Middle east & Africa', u'http://www.defensenews.com/rss/mid/') ,(u'Middle east & Africa', u'http://www.defensenews.com/rss/middle-east-africa')
,(u'Air', u'http://www.defensenews.com/rss/air/' ) ,(u'Air', u'http://www.defensenews.com/rss/air-warfare')
,(u'Land', u'http://www.defensenews.com/rss/lan/' ) ,(u'Land', u'http://www.defensenews.com/rss/land-warfare')
,(u'Naval', u'http://www.defensenews.com/rss/sea/' ) ,(u'Naval', u'http://www.defensenews.com/rss/naval-warfare')
] ]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
return soup