Improved Instapaper recipe

This commit is contained in:
Kovid Goyal 2011-07-18 16:46:31 -06:00
parent dbefbfbd86
commit 2b45d99b02

View File

@ -1,4 +1,3 @@
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1299694372(BasicNewsRecipe):
@ -9,14 +8,24 @@ class AdvancedUserRecipe1299694372(BasicNewsRecipe):
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'), (u'Instapaper Starred', u'http://www.instapaper.com/starred')]
feeds = [
(u'Instapaper Unread', u'http://www.instapaper.com/u'),
(u'Instapaper Starred', u'http://www.instapaper.com/starred')
]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
@ -37,18 +46,20 @@ class AdvancedUserRecipe1299694372(BasicNewsRecipe):
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':'titleRow'}):
description = self.tag_to_string(item.div)
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']
title = self.tag_to_string(atag)
date = strftime(self.timefmt)
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description':description
'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()