Hi guys.
I wrote this simple code for Forbes. It works, could use better cleaning of the text. There is even a low resolution cover page :-) But it doesn't create the menu items for articles: Next, Previous, Main, etc.
If somebody can improve this, please post back.
Thanks, David
PHP Code:
class AdvancedUserRecipe1226018223(BasicNewsRecipe):
title = u'Forbes'
oldest_article = 30
max_articles_per_feed = 100
no_stylesheets = True
html2lrf_options = ['--base-font-size', '10']
remove_tags_before = dict(id='p_RightTop')
remove_tags_after = dict(id='contextualLinks')
remove_tags = [dict(id=['controlsbox', 'sharePanel']),
]
feeds = [(u'Latest', u'http://www.forbes.com/news/index.xml'),
(u'Most Popular', u'http://www.forbes.com/feeds/popstories.xml'),
(u'Most Emailed', u'http://www.forbes.com/feeds/mostemailed.xml'),
(u'Faces', u'http://www.forbes.com/facesscan/index.xml'),
(u'Technology', u'http://www.forbes.com/technology/index.xml'),
(u'Personal Tech', u'http://www.forbes.com/personaltech/index.xml'),
(u'Wireless', u'http://www.forbes.com/wireless/index.xml'),
(u'Business', u'http://www.forbes.com/business/index.xml'),
(u'Sports Money', u'http://www.forbes.com/sportsmoney/index.xml'),
(u'Sports', u'http://www.forbes.com/forbeslife/sports/index.xml'),
(u'Vehicles', u'http://www.forbes.com/forbeslife/vehicles/index.xml'),
(u'Leadership', u'http://www.forbes.com/leadership/index.xml'),
(u'Careers', u'http://www.forbes.com/leadership/careers/index.xml'),
(u'Compensation', u'http://www.forbes.com/leadership/compensation/index.xml'),
(u'Managing', u'http://www.forbes.com/leadership/managing/index.xml')]
def get_cover_url(self):
self.cover_url = u'http://www.forbes.com/media/current_covers/forbes_120_160.gif'
cover = self.cover_url
return cover