Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #6986 (Updated recipe for Telegraph UK)

Browse Source
This commit is contained in:
Kovid Goyal 2010-09-28 09:57:49 -06:00
parent 0319a6c025
commit a0382a8d86
1 changed files with 20 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
resources/recipes/telegraph_uk.recipe
View File

@ -1,6 +1,5 @@
#!/usr/bin/env python
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
''' '''
telegraph.co.uk telegraph.co.uk
''' '''
@ -8,14 +7,16 @@ telegraph.co.uk
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class TelegraphUK(BasicNewsRecipe): class TelegraphUK(BasicNewsRecipe):
title = u'Telegraph.co.uk' title = 'Telegraph.co.uk'
__author__ = 'Darko Miletic and Sujata Raman' __author__ = 'Darko Miletic and Sujata Raman'
description = 'News from United Kingdom' description = 'News from United Kingdom'
oldest_article = 7 oldest_article = 2
category = 'news, politics, UK'
publisher = 'Telegraph Media Group ltd.'
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
language = 'en' language = 'en_GB'
remove_empty_feeds = True
use_embedded_content = False use_embedded_content = False
extra_css = ''' extra_css = '''
@ -27,13 +28,20 @@ class TelegraphUK(BasicNewsRecipe):
.imageExtras{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;} .imageExtras{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
''' '''
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'class':'storyHead'}) dict(name='div', attrs={'class':['storyHead','byline']})
,dict(name='div', attrs={'class':'story' }) ,dict(name='div', attrs={'id':'mainBodyArea' })
#,dict(name='div', attrs={'class':['slideshowHD gutterUnder',"twoThirds gutter","caption" ] })
] ]
remove_tags = [dict(name='div', attrs={'class':['related_links_inline',"imgindex","next","prev","gutterUnder",'ssImgHide','imageExtras','ssImg hide']}) remove_tags = [dict(name='div', attrs={'class':['related_links_inline',"imgindex","next","prev","gutterUnder",'ssImgHide','imageExtras','ssImg hide','related_links_video']})
#,dict(name='div', attrs={'class':['toolshideoneQuarter']}) ,dict(name='ul' , attrs={'class':['shareThis shareBottom']})
,dict(name='span', attrs={'class':['num','placeComment']}) ,dict(name='span', attrs={'class':['num','placeComment']})
] ]
@ -51,24 +59,7 @@ class TelegraphUK(BasicNewsRecipe):
] ]
def get_article_url(self, article): def get_article_url(self, article):
url = article.get('link', None)
url = article.get('guid', None)
if 'picture-galleries' in url or 'pictures' in url or 'picturegalleries' in url : if 'picture-galleries' in url or 'pictures' in url or 'picturegalleries' in url :
url = None url = None
return url return url
def postprocess_html(self,soup,first):
for bylineTag in soup.findAll(name='div', attrs={'class':'byline'}):
for pTag in bylineTag.findAll(name='p'):
if getattr(pTag.contents[0],"Comments",True):
pTag.extract()
return soup