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

Fix #7308 (Updated recipe for CubaDebate)

Browse Source
This commit is contained in:
Kovid Goyal 2010-10-26 10:57:14 -06:00
parent 6ba05b0e44
commit ae1e165aa3
1 changed files with 22 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
resources/recipes/cubadebate.recipe
View File

@ -1,9 +1,7 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
newyorker.com
cubadebate.cu
'''
from calibre.web.feeds.news import BasicNewsRecipe
@ -13,32 +11,44 @@ class CubaDebate(BasicNewsRecipe):
__author__ = 'Darko Miletic'
description = 'Contra el Terorismo Mediatico'
oldest_article = 15
language = 'es'
language = 'es'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
publisher = 'Cubadebate'
category = 'news, politics, Cuba'
encoding = 'utf-8'
extra_css = ' #BlogTitle{font-size: x-large; font-weight: bold} '
masthead_url = 'http://www.cubadebate.cu/wp-content/themes/cubadebate/images/logo.gif'
publication_type = 'newsportal'
extra_css = """
#BlogTitle{font-size: xx-large; font-weight: bold}
body{font-family: Verdana, Arial, Tahoma, sans-serif}
"""
conversion_options = {
'comments' : description
,'tags' : category
,'language' : 'es'
,'language' : language
,'publisher' : publisher
,'pretty_print': True
}
keep_only_tags = [dict(name='div', attrs={'id':'Outline'})]
remove_tags_after = dict(name='div',attrs={'id':'BlogContent'})
remove_tags = [dict(name='link')]
remove_tags = [
dict(name=['link','base','embed','object','meta','iframe'])
,dict(attrs={'id':'addthis_container'})
]
feeds = [(u'Articulos', u'http://www.cubadebate.cu/feed/')]
remove_attributes=['width','height','lang']
def print_version(self, url):
return url + 'print/'
def preprocess_html(self, soup):
return self.adeify_images(soup)
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
return soup