[khromov]

Another update incoming. I noticed that the text-only view on some articles did not have a <h1> tag for me to reflect the title, so I changed the script to use the <title> tag instead, which always reflects the article title.

The code in its entirety can be found below: (Remember to use Dereks post above if you want to add your Archive and other custom folders.)

import urllib
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe

class AdvancedUserRecipe1299694372(BasicNewsRecipe):
    title                             = u'Instapaper'
    __author__                  = 'Darko Miletic'
    publisher                     = 'Instapaper.com'
    category                      = 'info, custom, Instapaper'
    oldest_article               = 365
    max_articles_per_feed = 100
    no_stylesheets        = True
    remove_javascript     = True
    remove_tags              = [
	dict(name='div', attrs={'id':'text_controls_toggle'})
	,dict(name='script')
	,dict(name='div', attrs={'id':'text_controls'})
	,dict(name='div', attrs={'id':'editing_controls'})
	,dict(name='div', attrs={'class':'bar bottom'})
	 ]
    use_embedded_content  = False
    needs_subscription    = True
    INDEX                 = u'http://www.instapaper.com'
    LOGIN                 = INDEX + u'/user/login'


    feeds          = [(u'Instapaper Unread', u'http://www.instapaper.com/u')]

    def get_browser(self):
        br = BasicNewsRecipe.get_browser()
        if self.username is not None:
            br.open(self.LOGIN)
            br.select_form(nr=0)
            br['username'] = self.username
            if self.password is not None:
               br['password'] = self.password
            br.submit()
        return br

    def parse_index(self):
        totalfeeds = []
        lfeeds = self.get_feeds()
        for feedobj in lfeeds:
            feedtitle, feedurl = feedobj
            self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
            articles = []
            soup = self.index_to_soup(feedurl)
            for item in soup.findAll('div', attrs={'class':'cornerControls'}):
                description = self.tag_to_string(item.div)
                atag = item.a
                if atag and atag.has_key('href'):
                    url         = atag['href']
                    articles.append({
                                     'url'        :url
                                    })
            totalfeeds.append((feedtitle, articles))
        return totalfeeds

    def print_version(self, url): 
        return 'http://www.instapaper.com' + url

    def populate_article_metadata(self, article, soup, first):
        article.title  = soup.find('title').contents[0].strip()