Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix Fudzilla

Browse Source
This commit is contained in:
Kovid Goyal 2010-03-05 09:49:04 -07:00
parent bac7e6b78c
commit c7e8c889a4
1 changed files with 21 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
resources/recipes/fudzilla.recipe
View File

@ -1,27 +1,41 @@
#!/usr/bin/env python #!/usr/bin/env python
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2010 Starson17'
''' '''
fudzilla.com fudzilla.com
''' '''
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Fudzilla(BasicNewsRecipe): class Fudzilla(BasicNewsRecipe):
title = u'Fudzilla' title = u'Fudzilla'
__author__ = 'Darko Miletic' __author__ = 'Starson17'
language = 'en' language = 'en'
description = 'Tech news' description = 'Tech news'
oldest_article = 7 oldest_article = 7
remove_javascript = True
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
feeds = [ (u'Posts', u'http://www.fudzilla.com/index.php?option=com_rss&feed=RSS2.0&no_html=1')]
def print_version(self, url): remove_tags_before = dict(name='div', attrs={'class':['padding']})
nurl = url.replace('http://www.fudzilla.com/index.php','http://www.fudzilla.com/index2.php')
nmain, nsep, nrest = nurl.partition('&Itemid=') remove_tags = [dict(name='td', attrs={'class':['left','right']}),
return nmain + '&pop=1&page=0&Itemid=1' dict(name='div', attrs={'id':['toolbar','buttons']}),
dict(name='div', attrs={'class':['artbannersxtd','back_button']}),
dict(name='span', attrs={'class':['pathway']}),
dict(name='th', attrs={'class':['pagenav_next','pagenav_prev']}),
dict(name='table', attrs={'class':['headlines']}),
]
feeds = [
(u'Posts', u'http://www.fudzilla.com/index.php?option=com_rss&feed=RSS2.0&no_html=1')
]
preprocess_regexps = [
(re.compile(r'<p class="MsoNormal"> Welcome.*</p> ', re.DOTALL|re.IGNORECASE), lambda match: '')
]