Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update .net magazine

Browse Source
This commit is contained in:
Kovid Goyal 2013-05-28 07:28:12 +05:30
parent 542ced3b83
commit ebf397dece
1 changed files with 15 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
recipes/dot_net.recipe
View File

@ -3,7 +3,7 @@ import re
class dotnetMagazine (BasicNewsRecipe):
__author__ = u'Bonni Salles'
__version__ = '1.0'
__version__ = '1.1'
__license__ = 'GPL v3'
__copyright__ = u'2013, Bonni Salles'
title = '.net magazine'
@ -11,6 +11,7 @@ class dotnetMagazine (BasicNewsRecipe):
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
# recursion = 1
language = 'en'
remove_empty_feeds = True
extra_css = ' body{font-family: Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em} '
@ -22,16 +23,25 @@ class dotnetMagazine (BasicNewsRecipe):
remove_tags = [
dict(name='div', attrs={'class': 'item-list'}),
dict(name='h4', attrs={'class': 'std-hdr'}),
dict(name='div', attrs={'class': 'item-list share-links'}), #removes share links
dict(name='div', attrs={'class': 'item-list share-links'}), # removes share links
dict(name=['script', 'noscript']),
dict(name='div', attrs={'id': 'comments-form'}), #comment these out if you want the comments to show
dict(name='div', attrs={'id': 'comments-form'}), # comment these out if you want the comments to show
dict(name='div', attrs={'id': re.compile('advertorial_block_($|| )')}),
dict(name='div', attrs={'id': 'right-col'}),
dict(name='div', attrs={'id': 'comments'}), #comment these out if you want the comments to show
dict(name='div', attrs={'id': 'comments'}), # comment these out if you want the comments to show
dict(name='div', attrs={'class': 'item-list related-content'}),
]
feeds = [
(u'net', u'http://feeds.feedburner.com/net/topstories')
(u'net', u'http://feeds.feedburner.com/net/topstories?format=xml')
]
def skip_ad_pages(self, soup):
text = soup.find(text='click here to continue to article')
if text:
a = text.parent
url = a.get('href')
if url:
return self.index_to_soup(url, raw=True)