Hi, I'm downloading Financial Times articles and would like to have a "Table of Contents" created for the eBook... using the each feed's title as the separate sections.
Here is the code... can you help guide me on how to add this feature?
Thank you so much!
Davies Town
Code:
Spoiler:
class AdvancedUserRecipe1293009575(BasicNewsRecipe):
title = 'Financial Times'
description = 'Financial Times'
publisher = 'Financial Times'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
needs_subscription = True
simultaneous_downloads= 5
delay = 0
LOGIN = 'https://registration.ft.com/registration/barrier/login'
def get_browser(self):
br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None:
br.open(self.LOGIN)
br.select_form(name='loginForm')
br['username'] = self.username
br['password'] = self.password
br.submit()
return br
keep_only_tags = [ dict(name='div', attrs={'id':'cont'}) ]
remove_tags_after = dict(name='p', attrs={'class':'copyright'})
remove_tags = [ dict(name='div', attrs={'id':'floating-con'}) ]
remove_tags = [ dict(name='p', attrs={'class':'copyright'}) ]
feeds = [(u'World', u'http://www.ft.com/rss/world')
,(u'US', u'http://www.ft.com/rss/world/us')
,(u'Canada', u'http://www.ft.com/rss/world/canada')
,(u'Asia-Pacific', u'http://www.ft.com/rss/world/asiapacific')
,(u'Equities', u'http://www.ft.com/rss/markets/equities')
,(u'Commodities', u'http://www.ft.com/rss/markets/commodities')
]
def preprocess_html(self, soup):
content_type = soup.find('meta', {'http-equiv':'Content-Type'})
if content_type:
content_type['content'] = 'text/html; charset=utf-8'
return soup