Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

New recipe for stuff.co.nz by Krittika Goyal

Browse Source
This commit is contained in:
Kovid Goyal 2010-01-15 21:34:51 -07:00
parent 3240c330c1
commit 9e30796443
3 changed files with 52 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
resources/recipes/dominion.recipe Normal file
View File

@ -0,0 +1,50 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class stuffconz(BasicNewsRecipe):
title = u'stuff.co.nz'
language = 'en_NZ'
__author__ = 'Krittika Goyal'
oldest_article = 1 #days
max_articles_per_feed = 25
#encoding = 'latin1'
remove_stylesheets = True
#remove_tags_before = dict(name='h1', attrs={'class':'heading'})
remove_tags_after = dict(name='div', attrs={'id':'related_box'})
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':['story_feature_title']}),
dict(name='div', attrs={'id':['toolbox', 'related_box', 'adSTORYBODY']}),
dict(name='span', attrs={'class':['related_link', 'slideshowcontrols']}),
#dict(name='ul', attrs={'class':'articleTools'}),
]
feeds = [
('Dominion Post',
'http://www.stuff.co.nz/rss/dominion-post'),
('National',
'http://www.stuff.co.nz/rss/national'),
('World',
'http://www.stuff.co.nz/rss/world'),
('Business',
'http://www.stuff.co.nz/rss/business'),
('Technology',
'http://www.stuff.co.nz/rss/technology'),
('Sport',
'http://www.stuff.co.nz/rss/sport'),
('Entertainment',
'http://www.stuff.co.nz/rss/entertainment'),
('Life and Style',
'http://www.stuff.co.nz/rss/life-style'),
]
def preprocess_html(self, soup):
story = soup.find(name='div', attrs={'id':'left_col'})
#td = heading.findParent(name='td')
#td.extract()
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
body = soup.find(name='body')
body.insert(0, story)
return soup

2
resources/recipes/nzherald.recipe
View File

@ -6,7 +6,7 @@ class NewZealandHerald(BasicNewsRecipe):
__author__ = 'Krittika Goyal' __author__ = 'Krittika Goyal'
description = 'Daily news' description = 'Daily news'
timefmt = ' [%d %b, %Y]' timefmt = ' [%d %b, %Y]'
language = 'en_AU' language = 'en_NZ'
no_stylesheets = True no_stylesheets = True
remove_tags_before = dict(name='div', attrs={'class':'contentContainer left eight'}) remove_tags_before = dict(name='div', attrs={'class':'contentContainer left eight'})

1
src/calibre/utils/localization.py
View File

@ -97,6 +97,7 @@ _extra_lang_codes = {
'zh_TW' : _('Traditional Chinese'), 'zh_TW' : _('Traditional Chinese'),
'en' : _('English'), 'en' : _('English'),
'en_AU' : _('English (Australia)'), 'en_AU' : _('English (Australia)'),
'en_NZ' : _('English (New Zealand)'),
'en_CA' : _('English (Canada)'), 'en_CA' : _('English (Canada)'),
'en_IN' : _('English (India)'), 'en_IN' : _('English (India)'),
'en_TH' : _('English (Thailand)'), 'en_TH' : _('English (Thailand)'),