I independently noticed some of these issues and dealt with them just now (getting rid of the lengthy list at the beginning, and also the Evernote etc links at the end). I also added some improvements from this post:
https://www.mobileread.com/forums/sho...7&postcount=69
I've probably wasted enough time on this now, but I hope it's helpful. I haven't noticed the issue with markup in any of my article titles, so I am not going to worry about that for now! The full script is below.
# Calibre recipe for Instapaper.com (Stable version)
#
# Homepage:
http://khromov.wordpress.com/project...alibre-recipe/
# Code Repository:
https://bitbucket.org/khromov/calibre-instapaper
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1299694372(BasicNewsRecipe):
title = u'Instapaper'
__author__ = 'Darko Miletic, Stanislav Khromov, Jim Ramsay'
publisher = 'Instapaper.com'
category = 'info, custom, Instapaper'
oldest_article = 365
max_articles_per_feed = 100
oldest_article = 0
no_stylesheets = False
extra_css = 'q { font-style: italic; } .size3mode { color: black; }'
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='section', attrs={'class':'primary_bar'})
,dict(name='div', attrs={'class':'modal_group'})
,dict(name='div', attrs={'id':'editing_controls'})
,dict(name='div', attrs={'class':'modal_name'})
,dict(name='div', attrs={'class':'highlight_popover'})
,dict(name='div', attrs={'class':'bar bottom'})
,dict(name='div', attrs={'id':'controlbar_container'})
,dict(name='div', attrs={'id':'footer'})
,dict(name='label')
]
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')
]
#Adds the title tag to the body of the recipe. Use this if your articles miss headings.
add_title_tag = False;
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
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':'js_title_row title_row'}):
#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()
def postprocess_html(self, soup, first_fetch):
#adds the title to each story, as it is not always included
if self.add_title_tag:
for link_tag in soup.findAll(attrs={"id" : "story"}):
link_tag.insert(0,'<h1>'+soup.find('title').conten ts[0].strip()+'</h1>')
#print repr(soup)
return soup