Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #2084 (Updated New Scientist recipe)

Browse Source
This commit is contained in:
Kovid Goyal 2009-03-15 14:21:36 -07:00
parent 6e5547011a
commit 08b3ee1a79
1 changed files with 69 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

117
src/calibre/web/feeds/recipes/recipe_new_scientist.py
View File

@ -1,48 +1,69 @@
#!/usr/bin/env python #!/usr/bin/env python
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2009, AprilHare, Darko Miletic <darko.miletic at gmail.com>'
''' '''
newscientist.com newscientist.com
''' '''
#!/usr/bin/env python
from calibre.web.feeds.news import BasicNewsRecipe
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>, AprilHare' class NewScientist(BasicNewsRecipe):
''' title = 'New Scientist - Online News'
newscientist.com __author__ = 'Darko Miletic'
''' description = 'Science news and science articles from New Scientist.'
language = _('English')
from calibre.web.feeds.news import BasicNewsRecipe publisher = 'New Scientist'
category = 'science news, science articles, science jobs, drugs, cancer, depression, computer software, sex'
class NewScientist(BasicNewsRecipe): delay = 3
title = u'New Scientist - Online News' oldest_article = 7
__author__ = 'Darko Miletic' max_articles_per_feed = 100
description = 'News from Science' no_stylesheets = True
language = _('English') use_embedded_content = False
oldest_article = 7 remove_javascript = True
max_articles_per_feed = 100 encoding = 'utf-8'
no_stylesheets = True
use_embedded_content = False html2lrf_options = [
'--comment', description
keep_only_tags = [ , '--category', category
dict(name='div' , attrs={'id':'pgtop' }) , '--publisher', publisher
,dict(name='div' , attrs={'id':'maincol' }) ]
]
remove_tags = [ html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
dict(name='div' , attrs={'class':'hldBd' })
,dict(name='div' , attrs={'id':'compnl' }) keep_only_tags = [dict(name='div', attrs={'id':['pgtop','maincol']})]
,dict(name='div' , attrs={'id':'artIssueInfo' })
] remove_tags = [
dict(name='div', attrs={'class':['hldBd','adline','pnl','infotext' ]})
feeds = [ ,dict(name='div', attrs={'id' :['compnl','artIssueInfo','artTools']})
(u'Latest Headlines' , u'http://feeds.newscientist.com/science-news' ) ,dict(name='p' , attrs={'class':['marker','infotext' ]})
,(u'Magazine' , u'http://www.newscientist.com/feed/magazine' ) ]
,(u'Health' , u'http://www.newscientist.com/feed/view?id=2&type=channel' )
,(u'Life' , u'http://www.newscientist.com/feed/view?id=3&type=channel' ) feeds = [
,(u'Space' , u'http://www.newscientist.com/feed/view?id=6&type=channel' ) (u'Latest Headlines' , u'http://feeds.newscientist.com/science-news' )
,(u'Physics and Mathematics' , u'http://www.newscientist.com/feed/view?id=4&type=channel' ) ,(u'Magazine' , u'http://www.newscientist.com/feed/magazine' )
,(u'Environment' , u'http://www.newscientist.com/feed/view?id=1&type=channel' ) ,(u'Health' , u'http://www.newscientist.com/feed/view?id=2&type=channel' )
,(u'Science in Society' , u'http://www.newscientist.com/feed/view?id=5&type=channel' ) ,(u'Life' , u'http://www.newscientist.com/feed/view?id=3&type=channel' )
,(u'Tech' , u'http://www.newscientist.com/feed/view?id=7&type=channel' ) ,(u'Space' , u'http://www.newscientist.com/feed/view?id=6&type=channel' )
] ,(u'Physics and Mathematics' , u'http://www.newscientist.com/feed/view?id=4&type=channel' )
,(u'Environment' , u'http://www.newscientist.com/feed/view?id=1&type=channel' )
,(u'Science in Society' , u'http://www.newscientist.com/feed/view?id=5&type=channel' )
,(u'Tech' , u'http://www.newscientist.com/feed/view?id=7&type=channel' )
]
def get_article_url(self, article):
url = article.get('link', None)
raw = article.get('description', None)
rsoup = self.index_to_soup(raw)
atags = rsoup.findAll('a',href=True)
for atag in atags:
if atag['href'].startswith('http://res.feedsportal.com/viral/sendemail2.html?'):
st, sep, rest = atag['href'].partition('&link=')
real_url, sep2, drest = rest.partition('" target=')
return real_url
return url
def print_version(self, url):
rawurl, sep, params = url.partition('?')
return rawurl + '?full=true&print=true'