Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Linux Magazine

Browse Source 
Fixes #1453406 [Updated recipe for Linux Magazine](https://bugs.launchpad.net/calibre/+bug/1453406)
This commit is contained in:
Kovid Goyal 2015-05-10 06:47:26 +05:30
parent e62986fa41
commit 383643a9d1
1 changed files with 23 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
recipes/linux_magazine.recipe
View File

@ -1,38 +1,42 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2015 , Darko Miletic <darko.miletic at gmail.com>'
''' '''
linux-magazine.com linux-magazine.com
''' '''
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class LinuxMagazine(BasicNewsRecipe): class LinuxMagazine(BasicNewsRecipe):
title = u'Linux Magazine' title = 'Linux Magazine'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Linux news' description = 'Linux news'
language = 'en' publisher = 'Linux Magazine'
category = 'news, linux, open source, software'
oldest_article = 7 language = 'en'
encoding = 'utf-8'
oldest_article = 35
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
remove_tags_after = dict(name='div', attrs={'class':'end_intro'}) conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags=dict(name='div', attrs={'class':lambda x:'full' in (x or '').split()})
remove_tags_after = dict(name='div', attrs={'id':'disqus_thread'})
remove_tags = [ remove_tags = [
dict(name='div' , attrs={'class':'end_intro' }) dict(name='div' , attrs={'class':['attribute-relatedcontent',
,dict(name='table' , attrs={'width':'100%'}) 'social_bookmarks',
'paginate'] })
,dict(name='div' , attrs={'id':'articlebox'})
] ]
feeds = [(u'Linux Magazine Full Feed', u'http://www.linux-magazine.com/rss/feed/lmi_full')] feeds = [(u'Linux Magazine Full Feed', u'http://www.linux-magazine.com/rss/feed/lmi_full')]
def print_version(self, url):
raw = self.browser.open(url).read()
soup = BeautifulSoup(raw.decode('utf8', 'replace'))
print_link = soup.find('a', {'title':'Print this page'})
if print_link is None:
return url
return 'http://www.linux-magazine.com'+print_link['href']