Updated recipes for Toronto Sun and Telegraph UK

This commit is contained in:
Kovid Goyal 2010-02-11 11:25:39 -07:00
parent 51cfbe852b
commit 2604c986e6
2 changed files with 96 additions and 40 deletions

View File

@ -9,8 +9,8 @@ from calibre.web.feeds.news import BasicNewsRecipe
class TelegraphUK(BasicNewsRecipe):
title = u'Telegraph.co.uk'
__author__ = 'Darko Miletic'
description = 'News from United Kingdom'
__author__ = 'Darko Miletic and Sujata Raman'
description = 'News from United Kingdom'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
@ -18,23 +18,26 @@ class TelegraphUK(BasicNewsRecipe):
use_embedded_content = False
extra_css = '''
h1{font-family :Arial,Helvetica,sans-serif; font-size:large; }
h2{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#444444}
.story{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
.byline{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
a{color:#234B7B; }
.imageExtras{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
'''
keep_only_tags = [
extra_css = '''
h1{font-family :Arial,Helvetica,sans-serif; font-size:large; }
h2{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#444444;}
.story{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
.byline{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
a{color:#234B7B; }
.imageExtras{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
'''
keep_only_tags = [
dict(name='div', attrs={'class':'storyHead'})
,dict(name='div', attrs={'class':'story' })
#,dict(name='div', attrs={'class':['slideshowHD gutterUnder',"twoThirds gutter","caption" ] })
]
remove_tags = [dict(name='div', attrs={'class':['related_links_inline',"imgindex","next","prev","gutterUnder"]})]
feeds = [
#,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']})
#,dict(name='div', attrs={'class':['toolshideoneQuarter']})
,dict(name='span', attrs={'class':['num','placeComment']})
]
feeds = [
(u'UK News' , u'http://www.telegraph.co.uk/news/uknews/rss' )
,(u'World News' , u'http://www.telegraph.co.uk/news/worldnews/rss' )
,(u'Politics' , u'http://www.telegraph.co.uk/news/newstopics/politics/rss' )
@ -45,15 +48,27 @@ class TelegraphUK(BasicNewsRecipe):
,(u'Earth News' , u'http://www.telegraph.co.uk/earth/earthnews/rss' )
,(u'Comment' , u'http://www.telegraph.co.uk/comment/rss' )
,(u'How about that?', u'http://www.telegraph.co.uk/news/newstopics/howaboutthat/rss' )
]
]
def get_article_url(self, article):
url = article.get('guid', None)
if 'picture-galleries' in url or 'pictures' in url or 'picturegalleries' in url :
url = None
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

View File

@ -10,7 +10,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class TorontoSun(BasicNewsRecipe):
title = 'Toronto SUN'
__author__ = 'Darko Miletic'
__author__ = 'Darko Miletic and Sujata Raman'
description = 'News from Canada'
publisher = 'Toronto Sun'
category = 'news, politics, Canada'
@ -21,25 +21,50 @@ class TorontoSun(BasicNewsRecipe):
encoding = 'cp1252'
language = 'en_CA'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags =[
dict(name='div', attrs={'class':'articleHead'})
,dict(name='div', attrs={'id':'channelContent'})
]
remove_tags = [
dict(name='div',attrs={'class':['leftBox','bottomBox clear','bottomBox','breadCrumb']})
,dict(name=['link','iframe','object'])
,dict(name='a',attrs={'rel':'swap'})
,dict(name='ul',attrs={'class':'tabs dl contentSwap'})
]
keep_only_tags = [
dict(name='div', attrs={'class':['articleHead','leftBox']})
,dict(name='div', attrs={'id':'channelContent'})
,dict(name='div', attrs={'id':'rotateBox'})
,dict(name='img')
]
remove_tags = [
dict(name='div',attrs={'class':['bottomBox clear','bottomBox','breadCrumb','articleControls thin','articleControls thin short','extraVideoList']})
,dict(name='h2',attrs={'class':'microhead'})
,dict(name='div',attrs={'id':'commentsBottom'})
,dict(name=['link','iframe','object'])
,dict(name='a',attrs={'rel':'swap'})
,dict(name='a',attrs={'href':'/news/haiti/'})
,dict(name='ul',attrs={'class':['tabs dl contentSwap','micrositeNav clearIt hList','galleryNav rotateNav']})
]
remove_tags_after = [
dict(name='div',attrs={'class':'bottomBox clear'})
,dict(name='div',attrs={'class':'rotateBox'})
,dict(name='div',attrs={'id':'contentSwap'})
]
extra_css = '''
h1{font-family :Arial,Helvetica,sans-serif; font-size:large;}
h2{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#666666;}
h3{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#000000;}
p{font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
.bold{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;color:#444444;margin-left: 0px;}
.subheading{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#000000; font-weight: bold;}
.byline{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
.byline span{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small; text-transform: uppercase;}
.updated{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
.galleryCaption{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
.galleryUpdated{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
'''
remove_tags_after = dict(name='div',attrs={'class':'bottomBox clear'})
feeds = [
(u'News' , u'http://www.torontosun.com/news/rss.xml' )
@ -48,3 +73,19 @@ class TorontoSun(BasicNewsRecipe):
,(u'World' , u'http://www.torontosun.com/news/world/rss.xml' )
,(u'Money' , u'http://www.torontosun.com/money/rss.xml' )
]
def preprocess_html(self, soup):
##To fetch images from the specified source
for img in soup.findAll('img', src=True):
url= img.get('src').split('?')[-1].partition('=')[-1]
if url:
img['src'] = url.split('&')[0].partition('=')[0]
img['width'] = url.split('&')[-1].partition('=')[-1].split('x')[0]
img['height'] =url.split('&')[-1].partition('=')[-1].split('x')[1]
return soup