calibre/recipes/instapaper.recipe
Kovid Goyal e545b5eb36 ...
2012-06-03 09:46:09 +05:30

83 lines
3.2 KiB
Plaintext

# Calibre recipe for Instapaper.com (Stable version)
#
# Homepage: http://khromov.wordpress.com/projects/instapaper-calibre-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
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'})
,dict(name='div', attrs={'id':'controlbar_container'})
,dict(name='div', attrs={'id':'footer'})
]
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'),
(u'Instapaper Starred', u'http://www.instapaper.com/starred')
]
#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()
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()
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').contents[0].strip()+'</h1>')
#print repr(soup)
return soup