Updated Sydney Morning Herald

This commit is contained in:
Kovid Goyal 2010-04-04 22:03:27 +05:30
parent 0953c48b08
commit bd1ee60717
2 changed files with 56 additions and 81 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 348 B

View File

@ -1,91 +1,66 @@
#!/usr/bin/env python
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net' __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
__docformat__ = 'restructuredtext en'
''' '''
smh.com.au smh.com.au
''' '''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Smh_au(BasicNewsRecipe):
title = 'The Sydney Morning Herald - Printed edition'
__author__ = 'Darko Miletic'
description = 'Breaking news from Sydney, Australia and the world. Features the latest business, sport, entertainment, travel, lifestyle, and technology news.'
publisher = 'Fairfax Digital'
category = 'news, politics, Australia, Sydney'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
language = 'en_AU'
remove_empty_feeds = True
masthead_url = 'http://images.smh.com.au/2010/02/02/1087188/smh-620.jpg'
publication_type = 'newspaper'
extra_css = ' h1{font-family: Georgia,"Times New Roman",Times,serif } body{font-family: Arial,Helvetica,sans-serif} .cT-imageLandscape{font-size: x-small} '
class SMH(BasicNewsRecipe): conversion_options = {
'comment' : description
title = 'Sydney Morning Herald' , 'tags' : category
description = 'Business News, World News and Breaking News in Australia' , 'publisher' : publisher
__author__ = 'Kovid Goyal and Sujata Raman' , 'language' : language
language = 'en_AU' }
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
no_javascript = True
timefmt = ' [%A, %d %B, %Y]'
encoding = 'utf-8'
keep_only_tags = [dict(name='div', attrs ={'id':'content'})]
remove_tags = [
dict(name='div', attrs={'align' :'right'}),
dict(name='p', attrs={'class' :'comments'}),
dict(name='a', attrs={'class' :['more-photos','performerpromo']}),
dict(name='img', attrs={'alt' :'aap'}),
dict(name='div', attrs ={'id':['googleAds','moreGoogleAds','comments','footer','sidebar','austereopuff','adSpotIsland']}),
dict(name='div', attrs ={'class':['article-links','wof','articleTools top','cN-multimediaGroup cfix','articleTools bottom']}),
dict(name='div', attrs ={'class':['clear','adSpot-textboxgr1','adSpot-textBox','articleTools-c3 cfix','articleExtras-bottom','span-16 last']}),
dict(name='div', attrs ={'class':[ 'sidebar span-5','cT-socialCommenting','cN-linkList','cN-topicSelector','cT-storyTools cfix','cT-imageMultimedia']}) ,
dict(name='iframe'),
]
extra_css = '''
h1{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:large;}
.cT-storyDetails{font-family:Arial,Helvetica,sans-serif; color:#666666;font-size:x-small;}
.articleBody{font-family:Arial,Helvetica,sans-serif; color:black;font-size:small;}
.cT-imageLandscape{font-family:Arial,Helvetica,sans-serif; color:#333333 ;font-size:x-small;}
.source{font-family:Arial,Helvetica,sans-serif; color:#333333 ;font-size:xx-small;}
#content{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
.pageprint{font-family:Arial,Helvetica,sans-serif;font-size:small;}
#bylineDetails{font-family:Arial,Helvetica,sans-serif; color:#666666;font-size:x-small;}
.featurePic-wide{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
#idfeaturepic{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
h3{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
h2{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
h4{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
h5{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
body{font-family:Arial,Helvetica,sans-serif; font-size:x-small;}
'''
feeds = [
('Top Stories', 'http://feeds.smh.com.au/rssheadlines/top.xml'),
('National', 'http://feeds.smh.com.au/rssheadlines/national.xml'),
('World', 'http://feeds.smh.com.au/rssheadlines/world.xml'),
('Business', 'http://www.smh.com.au/rssheadlines/business.xml'),
('National Times', 'http://www.smh.com.au/rssheadlines/opinion/article/rss.xml'),
('Entertainment', 'http://feeds.smh.com.au/rssheadlines/entertainment.xml'),
('Technology', 'http://feeds.smh.com.au/rssheadlines/technology.xml'),
('Sport', 'http://feeds.smh.com.au/rssheadlines/sport.xml'),
]
def preprocess_html(self, soup):
bod = soup.find('bod')
if bod is not None:
bod.tag = 'div'
p = soup.find(id='content')
bod.extract()
p.insert(len(p), bod)
return soup
def get_browser(self):
br = BasicNewsRecipe.get_browser()
br.set_handle_refresh(False)
return br
def get_article_url(self, article):
url = article.link
if 'media' in url:
url = ''
return url
remove_tags = [
dict(name='div', attrs={'id':['googleAds','moreGoogleAds','comments']})
,dict(name='div', attrs={'class':'cT-imageMultimedia'})
,dict(name=['object','embed','iframe'])
]
remove_tags_after = [dict(name='div',attrs={'class':'articleBody'})]
keep_only_tags = [dict(name='div',attrs={'id':'content'})]
remove_attributes = ['width','height']
def parse_index(self):
articles = []
soup = self.index_to_soup('http://www.smh.com.au/todays-paper')
for itimg in soup.findAll('img',src=True):
if itimg['src'].endswith('frontpage.jpg'):
self.cover_url = itimg['src']
for item in soup.findAll(attrs={'class':'cN-storyHeadlineLead cfix'}):
description = ''
title_prefix = ''
feed_link = item.find('a',href=True)
descript = item.find('p')
if descript:
description = self.tag_to_string(descript)
if feed_link:
url = feed_link['href']
title = title_prefix + self.tag_to_string(feed_link)
date = strftime(self.timefmt)
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description':description
})
return [(soup.head.title.string, articles)]